Upload continuous evaluation checkpoints, batch 42
Browse files- continuous/smollm2/siglip2_b16_512/pretrain/mm_projector.bin +3 -0
- continuous/smollm2/siglip2_b16_512/pretrain/trainer_state.json +421 -0
- continuous/smollm2/siglip2_b32_256/finetune/chat_template.jinja +6 -0
- continuous/smollm2/siglip2_b32_256/finetune/config.json +70 -0
- continuous/smollm2/siglip2_b32_256/finetune/generation_config.json +9 -0
- continuous/smollm2/siglip2_b32_256/finetune/merges.txt +0 -0
- continuous/smollm2/siglip2_b32_256/finetune/model.safetensors +3 -0
- continuous/smollm2/siglip2_b32_256/finetune/special_tokens_map.json +28 -0
- continuous/smollm2/siglip2_b32_256/finetune/tokenizer.json +0 -0
- continuous/smollm2/siglip2_b32_256/finetune/tokenizer_config.json +155 -0
- continuous/smollm2/siglip2_b32_256/finetune/trainer_state.json +1856 -0
- continuous/smollm2/siglip2_b32_256/finetune/training_args.bin +3 -0
- continuous/smollm2/siglip2_b32_256/finetune/vocab.json +0 -0
- continuous/smollm2/siglip2_b32_256/pretrain/config.json +70 -0
- continuous/smollm2/siglip2_b32_256/pretrain/mm_projector.bin +3 -0
- continuous/smollm2/siglip2_b32_256/pretrain/trainer_state.json +421 -0
- continuous/smollm2/siglip2_g16_256/finetune/chat_template.jinja +6 -0
- continuous/smollm2/siglip2_g16_256/finetune/config.json +70 -0
- continuous/smollm2/siglip2_g16_256/finetune/generation_config.json +9 -0
- continuous/smollm2/siglip2_g16_256/finetune/merges.txt +0 -0
- continuous/smollm2/siglip2_g16_256/finetune/model-00001-of-00002.safetensors +3 -0
- continuous/smollm2/siglip2_g16_256/finetune/model-00002-of-00002.safetensors +3 -0
- continuous/smollm2/siglip2_g16_256/finetune/model.safetensors.index.json +729 -0
- continuous/smollm2/siglip2_g16_256/finetune/special_tokens_map.json +28 -0
- continuous/smollm2/siglip2_g16_256/finetune/tokenizer.json +0 -0
- continuous/smollm2/siglip2_g16_256/finetune/tokenizer_config.json +155 -0
- continuous/smollm2/siglip2_g16_256/finetune/trainer_state.json +1856 -0
- continuous/smollm2/siglip2_g16_256/finetune/training_args.bin +3 -0
- continuous/smollm2/siglip2_g16_256/finetune/vocab.json +0 -0
- continuous/smollm2/siglip2_g16_256/pretrain/config.json +70 -0
- continuous/smollm2/siglip2_g16_256/pretrain/mm_projector.bin +3 -0
- continuous/smollm2/siglip2_g16_256/pretrain/trainer_state.json +421 -0
- continuous/smollm2/siglip2_g16_384/finetune/chat_template.jinja +6 -0
- continuous/smollm2/siglip2_g16_384/finetune/config.json +70 -0
- continuous/smollm2/siglip2_g16_384/finetune/generation_config.json +9 -0
- continuous/smollm2/siglip2_g16_384/finetune/merges.txt +0 -0
- continuous/smollm2/siglip2_g16_384/finetune/model-00001-of-00002.safetensors +3 -0
- continuous/smollm2/siglip2_g16_384/finetune/model-00002-of-00002.safetensors +3 -0
- continuous/smollm2/siglip2_g16_384/finetune/model.safetensors.index.json +729 -0
- continuous/smollm2/siglip2_g16_384/finetune/special_tokens_map.json +28 -0
- continuous/smollm2/siglip2_g16_384/finetune/tokenizer.json +0 -0
- continuous/smollm2/siglip2_g16_384/finetune/tokenizer_config.json +155 -0
- continuous/smollm2/siglip2_g16_384/finetune/trainer_state.json +1856 -0
- continuous/smollm2/siglip2_g16_384/finetune/training_args.bin +3 -0
- continuous/smollm2/siglip2_g16_384/finetune/vocab.json +0 -0
- continuous/smollm2/siglip2_g16_384/pretrain/config.json +70 -0
- continuous/smollm2/siglip2_g16_384/pretrain/mm_projector.bin +3 -0
- continuous/smollm2/siglip2_g16_384/pretrain/trainer_state.json +421 -0
- continuous/smollm2/siglip2_l16_256/finetune/chat_template.jinja +6 -0
- continuous/smollm2/siglip2_l16_256/finetune/config.json +70 -0
continuous/smollm2/siglip2_b16_512/pretrain/mm_projector.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:95e2374a0b4348da5646418079bd90df24cd71e30b7060e8ae54df6fbbd11d8d
|
| 3 |
+
size 23087160
|
continuous/smollm2/siglip2_b16_512/pretrain/trainer_state.json
ADDED
|
@@ -0,0 +1,421 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 1.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 545,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.01834862385321101,
|
| 14 |
+
"grad_norm": 0.2603439688682556,
|
| 15 |
+
"learning_rate": 0.00032142857142857147,
|
| 16 |
+
"loss": 3.8477,
|
| 17 |
+
"step": 10
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.03669724770642202,
|
| 21 |
+
"grad_norm": 0.03992080315947533,
|
| 22 |
+
"learning_rate": 0.0006785714285714287,
|
| 23 |
+
"loss": 2.9173,
|
| 24 |
+
"step": 20
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.05504587155963303,
|
| 28 |
+
"grad_norm": 0.039909057319164276,
|
| 29 |
+
"learning_rate": 0.0009999907688176173,
|
| 30 |
+
"loss": 2.8172,
|
| 31 |
+
"step": 30
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.07339449541284404,
|
| 35 |
+
"grad_norm": 0.031246507540345192,
|
| 36 |
+
"learning_rate": 0.0009988834393115766,
|
| 37 |
+
"loss": 2.7564,
|
| 38 |
+
"step": 40
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.09174311926605505,
|
| 42 |
+
"grad_norm": 0.02760007604956627,
|
| 43 |
+
"learning_rate": 0.0009959345572940772,
|
| 44 |
+
"loss": 2.716,
|
| 45 |
+
"step": 50
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.11009174311926606,
|
| 49 |
+
"grad_norm": 0.04057060554623604,
|
| 50 |
+
"learning_rate": 0.0009911550081155983,
|
| 51 |
+
"loss": 2.6494,
|
| 52 |
+
"step": 60
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.12844036697247707,
|
| 56 |
+
"grad_norm": 0.04317605495452881,
|
| 57 |
+
"learning_rate": 0.0009845624347566433,
|
| 58 |
+
"loss": 2.5852,
|
| 59 |
+
"step": 70
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.14678899082568808,
|
| 63 |
+
"grad_norm": 0.0394936203956604,
|
| 64 |
+
"learning_rate": 0.0009761811727013547,
|
| 65 |
+
"loss": 2.5268,
|
| 66 |
+
"step": 80
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.1651376146788991,
|
| 70 |
+
"grad_norm": 0.034126296639442444,
|
| 71 |
+
"learning_rate": 0.0009660421601067666,
|
| 72 |
+
"loss": 2.4769,
|
| 73 |
+
"step": 90
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.1834862385321101,
|
| 77 |
+
"grad_norm": 0.04773363471031189,
|
| 78 |
+
"learning_rate": 0.0009541828235992926,
|
| 79 |
+
"loss": 2.4464,
|
| 80 |
+
"step": 100
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.2018348623853211,
|
| 84 |
+
"grad_norm": 0.04789917916059494,
|
| 85 |
+
"learning_rate": 0.0009406469401200151,
|
| 86 |
+
"loss": 2.4103,
|
| 87 |
+
"step": 110
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.22018348623853212,
|
| 91 |
+
"grad_norm": 0.051995474845170975,
|
| 92 |
+
"learning_rate": 0.0009254844753287492,
|
| 93 |
+
"loss": 2.3862,
|
| 94 |
+
"step": 120
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.23853211009174313,
|
| 98 |
+
"grad_norm": 0.04140513390302658,
|
| 99 |
+
"learning_rate": 0.0009087513991633924,
|
| 100 |
+
"loss": 2.3567,
|
| 101 |
+
"step": 130
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.25688073394495414,
|
| 105 |
+
"grad_norm": 0.03668754920363426,
|
| 106 |
+
"learning_rate": 0.0008905094792353917,
|
| 107 |
+
"loss": 2.3331,
|
| 108 |
+
"step": 140
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.27522935779816515,
|
| 112 |
+
"grad_norm": 0.04853452369570732,
|
| 113 |
+
"learning_rate": 0.0008708260528239789,
|
| 114 |
+
"loss": 2.3293,
|
| 115 |
+
"step": 150
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.29357798165137616,
|
| 119 |
+
"grad_norm": 0.04048741236329079,
|
| 120 |
+
"learning_rate": 0.0008497737783108237,
|
| 121 |
+
"loss": 2.3091,
|
| 122 |
+
"step": 160
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.3119266055045872,
|
| 126 |
+
"grad_norm": 0.03516250476241112,
|
| 127 |
+
"learning_rate": 0.0008274303669726426,
|
| 128 |
+
"loss": 2.3011,
|
| 129 |
+
"step": 170
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.3302752293577982,
|
| 133 |
+
"grad_norm": 0.03516066074371338,
|
| 134 |
+
"learning_rate": 0.0008038782961218137,
|
| 135 |
+
"loss": 2.2809,
|
| 136 |
+
"step": 180
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.3486238532110092,
|
| 140 |
+
"grad_norm": 0.04245098680257797,
|
| 141 |
+
"learning_rate": 0.000779204504653894,
|
| 142 |
+
"loss": 2.2652,
|
| 143 |
+
"step": 190
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.3669724770642202,
|
| 147 |
+
"grad_norm": 0.03913785517215729,
|
| 148 |
+
"learning_rate": 0.0007535000721258791,
|
| 149 |
+
"loss": 2.2253,
|
| 150 |
+
"step": 200
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.3853211009174312,
|
| 154 |
+
"grad_norm": 0.04292743653059006,
|
| 155 |
+
"learning_rate": 0.00072685988254984,
|
| 156 |
+
"loss": 2.2035,
|
| 157 |
+
"step": 210
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.4036697247706422,
|
| 161 |
+
"grad_norm": 0.044347234070301056,
|
| 162 |
+
"learning_rate": 0.0006993822741429906,
|
| 163 |
+
"loss": 2.192,
|
| 164 |
+
"step": 220
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.42201834862385323,
|
| 168 |
+
"grad_norm": 0.04231741279363632,
|
| 169 |
+
"learning_rate": 0.0006711686763270818,
|
| 170 |
+
"loss": 2.1678,
|
| 171 |
+
"step": 230
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.44036697247706424,
|
| 175 |
+
"grad_norm": 0.03522505611181259,
|
| 176 |
+
"learning_rate": 0.0006423232353170831,
|
| 177 |
+
"loss": 2.1504,
|
| 178 |
+
"step": 240
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.45871559633027525,
|
| 182 |
+
"grad_norm": 0.03506094962358475,
|
| 183 |
+
"learning_rate": 0.0006129524296812335,
|
| 184 |
+
"loss": 2.1459,
|
| 185 |
+
"step": 250
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.47706422018348627,
|
| 189 |
+
"grad_norm": 0.03453440219163895,
|
| 190 |
+
"learning_rate": 0.0005831646772915651,
|
| 191 |
+
"loss": 2.1439,
|
| 192 |
+
"step": 260
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.4954128440366973,
|
| 196 |
+
"grad_norm": 0.03520439937710762,
|
| 197 |
+
"learning_rate": 0.0005530699351157809,
|
| 198 |
+
"loss": 2.1199,
|
| 199 |
+
"step": 270
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.5137614678899083,
|
| 203 |
+
"grad_norm": 0.03834917023777962,
|
| 204 |
+
"learning_rate": 0.0005227792933277943,
|
| 205 |
+
"loss": 2.122,
|
| 206 |
+
"step": 280
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.5321100917431193,
|
| 210 |
+
"grad_norm": 0.03571285307407379,
|
| 211 |
+
"learning_rate": 0.0004924045652352092,
|
| 212 |
+
"loss": 2.1071,
|
| 213 |
+
"step": 290
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.5504587155963303,
|
| 217 |
+
"grad_norm": 0.03182421624660492,
|
| 218 |
+
"learning_rate": 0.0004620578745374633,
|
| 219 |
+
"loss": 2.108,
|
| 220 |
+
"step": 300
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.5688073394495413,
|
| 224 |
+
"grad_norm": 0.04003202170133591,
|
| 225 |
+
"learning_rate": 0.0004318512414382059,
|
| 226 |
+
"loss": 2.1114,
|
| 227 |
+
"step": 310
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.5871559633027523,
|
| 231 |
+
"grad_norm": 0.03572125360369682,
|
| 232 |
+
"learning_rate": 0.0004018961691397148,
|
| 233 |
+
"loss": 2.1075,
|
| 234 |
+
"step": 320
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.6055045871559633,
|
| 238 |
+
"grad_norm": 0.03578024357557297,
|
| 239 |
+
"learning_rate": 0.0003723032322457458,
|
| 240 |
+
"loss": 2.0935,
|
| 241 |
+
"step": 330
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.6238532110091743,
|
| 245 |
+
"grad_norm": 0.04012811928987503,
|
| 246 |
+
"learning_rate": 0.0003431816685921625,
|
| 247 |
+
"loss": 2.0965,
|
| 248 |
+
"step": 340
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.6422018348623854,
|
| 252 |
+
"grad_norm": 0.03453461080789566,
|
| 253 |
+
"learning_rate": 0.0003146389760120416,
|
| 254 |
+
"loss": 2.0923,
|
| 255 |
+
"step": 350
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.6605504587155964,
|
| 259 |
+
"grad_norm": 0.03649497404694557,
|
| 260 |
+
"learning_rate": 0.00028678051552373485,
|
| 261 |
+
"loss": 2.0957,
|
| 262 |
+
"step": 360
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.6788990825688074,
|
| 266 |
+
"grad_norm": 0.03195047751069069,
|
| 267 |
+
"learning_rate": 0.0002597091224066581,
|
| 268 |
+
"loss": 2.0876,
|
| 269 |
+
"step": 370
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.6972477064220184,
|
| 273 |
+
"grad_norm": 0.03130752965807915,
|
| 274 |
+
"learning_rate": 0.0002335247266004629,
|
| 275 |
+
"loss": 2.0927,
|
| 276 |
+
"step": 380
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.7155963302752294,
|
| 280 |
+
"grad_norm": 0.03575468063354492,
|
| 281 |
+
"learning_rate": 0.000208323983828828,
|
| 282 |
+
"loss": 2.0828,
|
| 283 |
+
"step": 390
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.7339449541284404,
|
| 287 |
+
"grad_norm": 0.03438407555222511,
|
| 288 |
+
"learning_rate": 0.0001841999188095224,
|
| 289 |
+
"loss": 2.0754,
|
| 290 |
+
"step": 400
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.7522935779816514,
|
| 294 |
+
"grad_norm": 0.03544420003890991,
|
| 295 |
+
"learning_rate": 0.00016124158186777676,
|
| 296 |
+
"loss": 2.0824,
|
| 297 |
+
"step": 410
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.7706422018348624,
|
| 301 |
+
"grad_norm": 0.03054310940206051,
|
| 302 |
+
"learning_rate": 0.0001395337202205211,
|
| 303 |
+
"loss": 2.0749,
|
| 304 |
+
"step": 420
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.7889908256880734,
|
| 308 |
+
"grad_norm": 0.029506154358386993,
|
| 309 |
+
"learning_rate": 0.00011915646514489292,
|
| 310 |
+
"loss": 2.0727,
|
| 311 |
+
"step": 430
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.8073394495412844,
|
| 315 |
+
"grad_norm": 0.03341967612504959,
|
| 316 |
+
"learning_rate": 0.00010018503618578818,
|
| 317 |
+
"loss": 2.0779,
|
| 318 |
+
"step": 440
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.8256880733944955,
|
| 322 |
+
"grad_norm": 0.029777145013213158,
|
| 323 |
+
"learning_rate": 8.268946349432583e-05,
|
| 324 |
+
"loss": 2.0732,
|
| 325 |
+
"step": 450
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.8440366972477065,
|
| 329 |
+
"grad_norm": 0.029243210330605507,
|
| 330 |
+
"learning_rate": 6.673432932217117e-05,
|
| 331 |
+
"loss": 2.0659,
|
| 332 |
+
"step": 460
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.8623853211009175,
|
| 336 |
+
"grad_norm": 0.030101388692855835,
|
| 337 |
+
"learning_rate": 5.2378529625954684e-05,
|
| 338 |
+
"loss": 2.062,
|
| 339 |
+
"step": 470
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.8807339449541285,
|
| 343 |
+
"grad_norm": 0.028815794736146927,
|
| 344 |
+
"learning_rate": 3.9675056661785556e-05,
|
| 345 |
+
"loss": 2.064,
|
| 346 |
+
"step": 480
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.8990825688073395,
|
| 350 |
+
"grad_norm": 0.027936700731515884,
|
| 351 |
+
"learning_rate": 2.8670803372379538e-05,
|
| 352 |
+
"loss": 2.0717,
|
| 353 |
+
"step": 490
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.9174311926605505,
|
| 357 |
+
"grad_norm": 0.028905397281050682,
|
| 358 |
+
"learning_rate": 1.9406390288876586e-05,
|
| 359 |
+
"loss": 2.0743,
|
| 360 |
+
"step": 500
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.9357798165137615,
|
| 364 |
+
"grad_norm": 0.028823575004935265,
|
| 365 |
+
"learning_rate": 1.191601558631461e-05,
|
| 366 |
+
"loss": 2.0655,
|
| 367 |
+
"step": 510
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.9541284403669725,
|
| 371 |
+
"grad_norm": 0.028106914833188057,
|
| 372 |
+
"learning_rate": 6.2273288462559305e-06,
|
| 373 |
+
"loss": 2.0624,
|
| 374 |
+
"step": 520
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.9724770642201835,
|
| 378 |
+
"grad_norm": 0.02887576073408127,
|
| 379 |
+
"learning_rate": 2.361328992552314e-06,
|
| 380 |
+
"loss": 2.0641,
|
| 381 |
+
"step": 530
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.9908256880733946,
|
| 385 |
+
"grad_norm": 0.029404323548078537,
|
| 386 |
+
"learning_rate": 3.322867770044202e-07,
|
| 387 |
+
"loss": 2.0598,
|
| 388 |
+
"step": 540
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 1.0,
|
| 392 |
+
"step": 545,
|
| 393 |
+
"total_flos": 3.2657517845046886e+17,
|
| 394 |
+
"train_loss": 2.2634779413905712,
|
| 395 |
+
"train_runtime": 5523.881,
|
| 396 |
+
"train_samples_per_second": 101.039,
|
| 397 |
+
"train_steps_per_second": 0.099
|
| 398 |
+
}
|
| 399 |
+
],
|
| 400 |
+
"logging_steps": 10,
|
| 401 |
+
"max_steps": 545,
|
| 402 |
+
"num_input_tokens_seen": 31829856,
|
| 403 |
+
"num_train_epochs": 1,
|
| 404 |
+
"save_steps": 500,
|
| 405 |
+
"stateful_callbacks": {
|
| 406 |
+
"TrainerControl": {
|
| 407 |
+
"args": {
|
| 408 |
+
"should_epoch_stop": false,
|
| 409 |
+
"should_evaluate": false,
|
| 410 |
+
"should_log": false,
|
| 411 |
+
"should_save": false,
|
| 412 |
+
"should_training_stop": false
|
| 413 |
+
},
|
| 414 |
+
"attributes": {}
|
| 415 |
+
}
|
| 416 |
+
},
|
| 417 |
+
"total_flos": 3.2657517845046886e+17,
|
| 418 |
+
"train_batch_size": 16,
|
| 419 |
+
"trial_name": null,
|
| 420 |
+
"trial_params": null
|
| 421 |
+
}
|
continuous/smollm2/siglip2_b32_256/finetune/chat_template.jinja
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system
|
| 2 |
+
You are a helpful AI assistant named SmolLM, trained by Hugging Face<|im_end|>
|
| 3 |
+
' }}{% endif %}{{'<|im_start|>' + message['role'] + '
|
| 4 |
+
' + message['content'] + '<|im_end|>' + '
|
| 5 |
+
'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
|
| 6 |
+
' }}{% endif %}
|
continuous/smollm2/siglip2_b32_256/finetune/config.json
ADDED
|
@@ -0,0 +1,70 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_faster_video": false,
|
| 3 |
+
"add_time_instruction": false,
|
| 4 |
+
"architectures": [
|
| 5 |
+
"LlavaLlamaForCausalLM"
|
| 6 |
+
],
|
| 7 |
+
"attention_bias": false,
|
| 8 |
+
"attention_dropout": 0.0,
|
| 9 |
+
"bos_token_id": 1,
|
| 10 |
+
"dtype": "bfloat16",
|
| 11 |
+
"eos_token_id": 2,
|
| 12 |
+
"faster_token_stride": 10,
|
| 13 |
+
"force_sample": false,
|
| 14 |
+
"head_dim": 64,
|
| 15 |
+
"hidden_act": "silu",
|
| 16 |
+
"hidden_size": 2048,
|
| 17 |
+
"image_aspect_ratio": "square",
|
| 18 |
+
"image_crop_resolution": null,
|
| 19 |
+
"image_grid_pinpoints": null,
|
| 20 |
+
"image_split_resolution": null,
|
| 21 |
+
"initializer_range": 0.02,
|
| 22 |
+
"intermediate_size": 8192,
|
| 23 |
+
"max_position_embeddings": 8192,
|
| 24 |
+
"mlp_bias": false,
|
| 25 |
+
"mm_hidden_size": 768,
|
| 26 |
+
"mm_newline_position": "grid",
|
| 27 |
+
"mm_patch_merge_type": "flat",
|
| 28 |
+
"mm_projector_lr": 0.0001,
|
| 29 |
+
"mm_projector_type": "mlp2x_gelu",
|
| 30 |
+
"mm_resampler_type": null,
|
| 31 |
+
"mm_spatial_pool_mode": "bilinear",
|
| 32 |
+
"mm_spatial_pool_stride": null,
|
| 33 |
+
"mm_tunable_parts": "mm_mlp_adapter,mm_language_model",
|
| 34 |
+
"mm_use_im_patch_token": false,
|
| 35 |
+
"mm_use_im_start_end": false,
|
| 36 |
+
"mm_vision_select_feature": "patch",
|
| 37 |
+
"mm_vision_select_layer": -2,
|
| 38 |
+
"mm_vision_tower": "open_clip_hub:ViT-B-32-SigLIP2-256",
|
| 39 |
+
"mm_vision_tower_lr": null,
|
| 40 |
+
"model_type": "llama",
|
| 41 |
+
"num_attention_heads": 32,
|
| 42 |
+
"num_hidden_layers": 24,
|
| 43 |
+
"num_key_value_heads": 32,
|
| 44 |
+
"pad_token_id": 0,
|
| 45 |
+
"pos_skipping_range": 4096,
|
| 46 |
+
"pretraining_tp": 1,
|
| 47 |
+
"rms_norm_eps": 1e-05,
|
| 48 |
+
"rope_scaling": null,
|
| 49 |
+
"rope_theta": 130000,
|
| 50 |
+
"tie_word_embeddings": true,
|
| 51 |
+
"tokenizer_model_max_length": 8192,
|
| 52 |
+
"tokenizer_padding_side": "right",
|
| 53 |
+
"transformers.js_config": {
|
| 54 |
+
"dtype": "q4",
|
| 55 |
+
"kv_cache_dtype": {
|
| 56 |
+
"fp16": "float16",
|
| 57 |
+
"q4f16": "float16"
|
| 58 |
+
},
|
| 59 |
+
"use_external_data_format": {
|
| 60 |
+
"model.onnx": true,
|
| 61 |
+
"model_fp16.onnx": true
|
| 62 |
+
}
|
| 63 |
+
},
|
| 64 |
+
"transformers_version": "4.57.6",
|
| 65 |
+
"use_cache": true,
|
| 66 |
+
"use_mm_proj": true,
|
| 67 |
+
"use_pos_skipping": false,
|
| 68 |
+
"vision_tower_pretrained": "/cache/ckpt/download/tokenizer/continuous/siglip2/siglip2_b32_256.npz",
|
| 69 |
+
"vocab_size": 49152
|
| 70 |
+
}
|
continuous/smollm2/siglip2_b32_256/finetune/generation_config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 1,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
2
|
| 6 |
+
],
|
| 7 |
+
"pad_token_id": 0,
|
| 8 |
+
"transformers_version": "4.57.6"
|
| 9 |
+
}
|
continuous/smollm2/siglip2_b32_256/finetune/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
continuous/smollm2/siglip2_b32_256/finetune/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ebe6d095d7f4e65297ff1500fc8618715f9fd2a870d9e5c92298466ba4a8561e
|
| 3 |
+
size 3836316512
|
continuous/smollm2/siglip2_b32_256/finetune/special_tokens_map.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|im_start|>",
|
| 4 |
+
"<|im_end|>"
|
| 5 |
+
],
|
| 6 |
+
"bos_token": {
|
| 7 |
+
"content": "<|im_start|>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": false,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false
|
| 12 |
+
},
|
| 13 |
+
"eos_token": {
|
| 14 |
+
"content": "<|im_end|>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false
|
| 19 |
+
},
|
| 20 |
+
"pad_token": "<|endoftext|>",
|
| 21 |
+
"unk_token": {
|
| 22 |
+
"content": "<|endoftext|>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false
|
| 27 |
+
}
|
| 28 |
+
}
|
continuous/smollm2/siglip2_b32_256/finetune/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
continuous/smollm2/siglip2_b32_256/finetune/tokenizer_config.json
ADDED
|
@@ -0,0 +1,155 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"0": {
|
| 5 |
+
"content": "<|endoftext|>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": false,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"1": {
|
| 13 |
+
"content": "<|im_start|>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": false,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"2": {
|
| 21 |
+
"content": "<|im_end|>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": false,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
},
|
| 28 |
+
"3": {
|
| 29 |
+
"content": "<repo_name>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": false,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": true
|
| 35 |
+
},
|
| 36 |
+
"4": {
|
| 37 |
+
"content": "<reponame>",
|
| 38 |
+
"lstrip": false,
|
| 39 |
+
"normalized": false,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": true
|
| 43 |
+
},
|
| 44 |
+
"5": {
|
| 45 |
+
"content": "<file_sep>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": false,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false,
|
| 50 |
+
"special": true
|
| 51 |
+
},
|
| 52 |
+
"6": {
|
| 53 |
+
"content": "<filename>",
|
| 54 |
+
"lstrip": false,
|
| 55 |
+
"normalized": false,
|
| 56 |
+
"rstrip": false,
|
| 57 |
+
"single_word": false,
|
| 58 |
+
"special": true
|
| 59 |
+
},
|
| 60 |
+
"7": {
|
| 61 |
+
"content": "<gh_stars>",
|
| 62 |
+
"lstrip": false,
|
| 63 |
+
"normalized": false,
|
| 64 |
+
"rstrip": false,
|
| 65 |
+
"single_word": false,
|
| 66 |
+
"special": true
|
| 67 |
+
},
|
| 68 |
+
"8": {
|
| 69 |
+
"content": "<issue_start>",
|
| 70 |
+
"lstrip": false,
|
| 71 |
+
"normalized": false,
|
| 72 |
+
"rstrip": false,
|
| 73 |
+
"single_word": false,
|
| 74 |
+
"special": true
|
| 75 |
+
},
|
| 76 |
+
"9": {
|
| 77 |
+
"content": "<issue_comment>",
|
| 78 |
+
"lstrip": false,
|
| 79 |
+
"normalized": false,
|
| 80 |
+
"rstrip": false,
|
| 81 |
+
"single_word": false,
|
| 82 |
+
"special": true
|
| 83 |
+
},
|
| 84 |
+
"10": {
|
| 85 |
+
"content": "<issue_closed>",
|
| 86 |
+
"lstrip": false,
|
| 87 |
+
"normalized": false,
|
| 88 |
+
"rstrip": false,
|
| 89 |
+
"single_word": false,
|
| 90 |
+
"special": true
|
| 91 |
+
},
|
| 92 |
+
"11": {
|
| 93 |
+
"content": "<jupyter_start>",
|
| 94 |
+
"lstrip": false,
|
| 95 |
+
"normalized": false,
|
| 96 |
+
"rstrip": false,
|
| 97 |
+
"single_word": false,
|
| 98 |
+
"special": true
|
| 99 |
+
},
|
| 100 |
+
"12": {
|
| 101 |
+
"content": "<jupyter_text>",
|
| 102 |
+
"lstrip": false,
|
| 103 |
+
"normalized": false,
|
| 104 |
+
"rstrip": false,
|
| 105 |
+
"single_word": false,
|
| 106 |
+
"special": true
|
| 107 |
+
},
|
| 108 |
+
"13": {
|
| 109 |
+
"content": "<jupyter_code>",
|
| 110 |
+
"lstrip": false,
|
| 111 |
+
"normalized": false,
|
| 112 |
+
"rstrip": false,
|
| 113 |
+
"single_word": false,
|
| 114 |
+
"special": true
|
| 115 |
+
},
|
| 116 |
+
"14": {
|
| 117 |
+
"content": "<jupyter_output>",
|
| 118 |
+
"lstrip": false,
|
| 119 |
+
"normalized": false,
|
| 120 |
+
"rstrip": false,
|
| 121 |
+
"single_word": false,
|
| 122 |
+
"special": true
|
| 123 |
+
},
|
| 124 |
+
"15": {
|
| 125 |
+
"content": "<jupyter_script>",
|
| 126 |
+
"lstrip": false,
|
| 127 |
+
"normalized": false,
|
| 128 |
+
"rstrip": false,
|
| 129 |
+
"single_word": false,
|
| 130 |
+
"special": true
|
| 131 |
+
},
|
| 132 |
+
"16": {
|
| 133 |
+
"content": "<empty_output>",
|
| 134 |
+
"lstrip": false,
|
| 135 |
+
"normalized": false,
|
| 136 |
+
"rstrip": false,
|
| 137 |
+
"single_word": false,
|
| 138 |
+
"special": true
|
| 139 |
+
}
|
| 140 |
+
},
|
| 141 |
+
"additional_special_tokens": [
|
| 142 |
+
"<|im_start|>",
|
| 143 |
+
"<|im_end|>"
|
| 144 |
+
],
|
| 145 |
+
"bos_token": "<|im_start|>",
|
| 146 |
+
"clean_up_tokenization_spaces": false,
|
| 147 |
+
"eos_token": "<|im_end|>",
|
| 148 |
+
"extra_special_tokens": {},
|
| 149 |
+
"model_max_length": 8192,
|
| 150 |
+
"pad_token": "<|endoftext|>",
|
| 151 |
+
"padding_side": "right",
|
| 152 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 153 |
+
"unk_token": "<|endoftext|>",
|
| 154 |
+
"vocab_size": 49152
|
| 155 |
+
}
|
continuous/smollm2/siglip2_b32_256/finetune/trainer_state.json
ADDED
|
@@ -0,0 +1,1856 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 1.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 2597,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.003850596842510589,
|
| 14 |
+
"grad_norm": 2.9385108947753906,
|
| 15 |
+
"learning_rate": 1.153846153846154e-06,
|
| 16 |
+
"loss": 1.288,
|
| 17 |
+
"step": 10
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.007701193685021178,
|
| 21 |
+
"grad_norm": 2.0354623794555664,
|
| 22 |
+
"learning_rate": 2.435897435897436e-06,
|
| 23 |
+
"loss": 1.1404,
|
| 24 |
+
"step": 20
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.011551790527531768,
|
| 28 |
+
"grad_norm": 2.048875570297241,
|
| 29 |
+
"learning_rate": 3.7179487179487184e-06,
|
| 30 |
+
"loss": 1.0007,
|
| 31 |
+
"step": 30
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.015402387370042356,
|
| 35 |
+
"grad_norm": 1.353585124015808,
|
| 36 |
+
"learning_rate": 5e-06,
|
| 37 |
+
"loss": 0.9549,
|
| 38 |
+
"step": 40
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.019252984212552945,
|
| 42 |
+
"grad_norm": 1.3123875856399536,
|
| 43 |
+
"learning_rate": 6.282051282051282e-06,
|
| 44 |
+
"loss": 0.9435,
|
| 45 |
+
"step": 50
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.023103581055063535,
|
| 49 |
+
"grad_norm": 0.26555335521698,
|
| 50 |
+
"learning_rate": 7.564102564102564e-06,
|
| 51 |
+
"loss": 0.8715,
|
| 52 |
+
"step": 60
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.026954177897574125,
|
| 56 |
+
"grad_norm": 0.2205473631620407,
|
| 57 |
+
"learning_rate": 8.846153846153847e-06,
|
| 58 |
+
"loss": 0.8252,
|
| 59 |
+
"step": 70
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.030804774740084712,
|
| 63 |
+
"grad_norm": 0.22408510744571686,
|
| 64 |
+
"learning_rate": 9.999996111488723e-06,
|
| 65 |
+
"loss": 0.8361,
|
| 66 |
+
"step": 80
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.0346553715825953,
|
| 70 |
+
"grad_norm": 0.21462370455265045,
|
| 71 |
+
"learning_rate": 9.999529497453782e-06,
|
| 72 |
+
"loss": 0.8208,
|
| 73 |
+
"step": 90
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.03850596842510589,
|
| 77 |
+
"grad_norm": 0.18711484968662262,
|
| 78 |
+
"learning_rate": 9.998285264324193e-06,
|
| 79 |
+
"loss": 0.7881,
|
| 80 |
+
"step": 100
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.04235656526761648,
|
| 84 |
+
"grad_norm": 0.19671157002449036,
|
| 85 |
+
"learning_rate": 9.996263605626052e-06,
|
| 86 |
+
"loss": 0.78,
|
| 87 |
+
"step": 110
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.04620716211012707,
|
| 91 |
+
"grad_norm": 0.20407529175281525,
|
| 92 |
+
"learning_rate": 9.99346483580503e-06,
|
| 93 |
+
"loss": 0.7988,
|
| 94 |
+
"step": 120
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.05005775895263766,
|
| 98 |
+
"grad_norm": 0.21296069025993347,
|
| 99 |
+
"learning_rate": 9.989889390177467e-06,
|
| 100 |
+
"loss": 0.7754,
|
| 101 |
+
"step": 130
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.05390835579514825,
|
| 105 |
+
"grad_norm": 0.21108189225196838,
|
| 106 |
+
"learning_rate": 9.985537824862647e-06,
|
| 107 |
+
"loss": 0.7895,
|
| 108 |
+
"step": 140
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.05775895263765884,
|
| 112 |
+
"grad_norm": 0.20821085572242737,
|
| 113 |
+
"learning_rate": 9.980410816696317e-06,
|
| 114 |
+
"loss": 0.7674,
|
| 115 |
+
"step": 150
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.061609549480169425,
|
| 119 |
+
"grad_norm": 0.19848640263080597,
|
| 120 |
+
"learning_rate": 9.97450916312541e-06,
|
| 121 |
+
"loss": 0.7738,
|
| 122 |
+
"step": 160
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.06546014632268002,
|
| 126 |
+
"grad_norm": 0.17649592459201813,
|
| 127 |
+
"learning_rate": 9.967833782084004e-06,
|
| 128 |
+
"loss": 0.7748,
|
| 129 |
+
"step": 170
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.0693107431651906,
|
| 133 |
+
"grad_norm": 0.19415025413036346,
|
| 134 |
+
"learning_rate": 9.960385711850554e-06,
|
| 135 |
+
"loss": 0.8064,
|
| 136 |
+
"step": 180
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.07316134000770119,
|
| 140 |
+
"grad_norm": 0.21349921822547913,
|
| 141 |
+
"learning_rate": 9.952166110886394e-06,
|
| 142 |
+
"loss": 0.793,
|
| 143 |
+
"step": 190
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.07701193685021178,
|
| 147 |
+
"grad_norm": 0.18853576481342316,
|
| 148 |
+
"learning_rate": 9.943176257655567e-06,
|
| 149 |
+
"loss": 0.7917,
|
| 150 |
+
"step": 200
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.08086253369272237,
|
| 154 |
+
"grad_norm": 0.20286451280117035,
|
| 155 |
+
"learning_rate": 9.933417550425952e-06,
|
| 156 |
+
"loss": 0.7792,
|
| 157 |
+
"step": 210
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.08471313053523297,
|
| 161 |
+
"grad_norm": 0.18428759276866913,
|
| 162 |
+
"learning_rate": 9.9228915070518e-06,
|
| 163 |
+
"loss": 0.769,
|
| 164 |
+
"step": 220
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.08856372737774355,
|
| 168 |
+
"grad_norm": 0.18871688842773438,
|
| 169 |
+
"learning_rate": 9.911599764737632e-06,
|
| 170 |
+
"loss": 0.7649,
|
| 171 |
+
"step": 230
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.09241432422025414,
|
| 175 |
+
"grad_norm": 0.19219599664211273,
|
| 176 |
+
"learning_rate": 9.899544079783606e-06,
|
| 177 |
+
"loss": 0.76,
|
| 178 |
+
"step": 240
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.09626492106276473,
|
| 182 |
+
"grad_norm": 0.18898926675319672,
|
| 183 |
+
"learning_rate": 9.886726327312338e-06,
|
| 184 |
+
"loss": 0.7769,
|
| 185 |
+
"step": 250
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.10011551790527531,
|
| 189 |
+
"grad_norm": 0.17017176747322083,
|
| 190 |
+
"learning_rate": 9.87314850097724e-06,
|
| 191 |
+
"loss": 0.7755,
|
| 192 |
+
"step": 260
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.1039661147477859,
|
| 196 |
+
"grad_norm": 0.19011017680168152,
|
| 197 |
+
"learning_rate": 9.858812712652452e-06,
|
| 198 |
+
"loss": 0.7578,
|
| 199 |
+
"step": 270
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.1078167115902965,
|
| 203 |
+
"grad_norm": 0.17899219691753387,
|
| 204 |
+
"learning_rate": 9.843721192104341e-06,
|
| 205 |
+
"loss": 0.7556,
|
| 206 |
+
"step": 280
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.11166730843280709,
|
| 210 |
+
"grad_norm": 0.18876732885837555,
|
| 211 |
+
"learning_rate": 9.827876286644698e-06,
|
| 212 |
+
"loss": 0.7862,
|
| 213 |
+
"step": 290
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.11551790527531768,
|
| 217 |
+
"grad_norm": 0.1634492725133896,
|
| 218 |
+
"learning_rate": 9.811280460765643e-06,
|
| 219 |
+
"loss": 0.7458,
|
| 220 |
+
"step": 300
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.11936850211782826,
|
| 224 |
+
"grad_norm": 0.19525648653507233,
|
| 225 |
+
"learning_rate": 9.793936295756292e-06,
|
| 226 |
+
"loss": 0.7502,
|
| 227 |
+
"step": 310
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.12321909896033885,
|
| 231 |
+
"grad_norm": 0.18404583632946014,
|
| 232 |
+
"learning_rate": 9.775846489301279e-06,
|
| 233 |
+
"loss": 0.7617,
|
| 234 |
+
"step": 320
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.12706969580284944,
|
| 238 |
+
"grad_norm": 0.17926687002182007,
|
| 239 |
+
"learning_rate": 9.757013855061157e-06,
|
| 240 |
+
"loss": 0.7621,
|
| 241 |
+
"step": 330
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.13092029264536004,
|
| 245 |
+
"grad_norm": 0.17416547238826752,
|
| 246 |
+
"learning_rate": 9.737441322234758e-06,
|
| 247 |
+
"loss": 0.7646,
|
| 248 |
+
"step": 340
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.1347708894878706,
|
| 252 |
+
"grad_norm": 0.18931490182876587,
|
| 253 |
+
"learning_rate": 9.717131935103605e-06,
|
| 254 |
+
"loss": 0.7718,
|
| 255 |
+
"step": 350
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.1386214863303812,
|
| 259 |
+
"grad_norm": 0.1822836697101593,
|
| 260 |
+
"learning_rate": 9.696088852558398e-06,
|
| 261 |
+
"loss": 0.7528,
|
| 262 |
+
"step": 360
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.1424720831728918,
|
| 266 |
+
"grad_norm": 0.211773082613945,
|
| 267 |
+
"learning_rate": 9.674315347607686e-06,
|
| 268 |
+
"loss": 0.7805,
|
| 269 |
+
"step": 370
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.14632268001540238,
|
| 273 |
+
"grad_norm": 0.17962698638439178,
|
| 274 |
+
"learning_rate": 9.651814806868796e-06,
|
| 275 |
+
"loss": 0.7449,
|
| 276 |
+
"step": 380
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.15017327685791299,
|
| 280 |
+
"grad_norm": 0.19939550757408142,
|
| 281 |
+
"learning_rate": 9.62859073004107e-06,
|
| 282 |
+
"loss": 0.7476,
|
| 283 |
+
"step": 390
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.15402387370042356,
|
| 287 |
+
"grad_norm": 0.1690509170293808,
|
| 288 |
+
"learning_rate": 9.604646729361547e-06,
|
| 289 |
+
"loss": 0.7546,
|
| 290 |
+
"step": 400
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.15787447054293416,
|
| 294 |
+
"grad_norm": 0.19656462967395782,
|
| 295 |
+
"learning_rate": 9.579986529043099e-06,
|
| 296 |
+
"loss": 0.7521,
|
| 297 |
+
"step": 410
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.16172506738544473,
|
| 301 |
+
"grad_norm": 0.18960249423980713,
|
| 302 |
+
"learning_rate": 9.554613964695189e-06,
|
| 303 |
+
"loss": 0.7667,
|
| 304 |
+
"step": 420
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.16557566422795533,
|
| 308 |
+
"grad_norm": 0.1814795434474945,
|
| 309 |
+
"learning_rate": 9.528532982727281e-06,
|
| 310 |
+
"loss": 0.7494,
|
| 311 |
+
"step": 430
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.16942626107046593,
|
| 315 |
+
"grad_norm": 0.17259085178375244,
|
| 316 |
+
"learning_rate": 9.501747639735018e-06,
|
| 317 |
+
"loss": 0.7554,
|
| 318 |
+
"step": 440
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.1732768579129765,
|
| 322 |
+
"grad_norm": 0.17607246339321136,
|
| 323 |
+
"learning_rate": 9.474262101869272e-06,
|
| 324 |
+
"loss": 0.7413,
|
| 325 |
+
"step": 450
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.1771274547554871,
|
| 329 |
+
"grad_norm": 0.19273661077022552,
|
| 330 |
+
"learning_rate": 9.446080644188141e-06,
|
| 331 |
+
"loss": 0.7506,
|
| 332 |
+
"step": 460
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.18097805159799768,
|
| 336 |
+
"grad_norm": 0.1741396188735962,
|
| 337 |
+
"learning_rate": 9.417207649992017e-06,
|
| 338 |
+
"loss": 0.752,
|
| 339 |
+
"step": 470
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.18482864844050828,
|
| 343 |
+
"grad_norm": 0.18550333380699158,
|
| 344 |
+
"learning_rate": 9.387647610141816e-06,
|
| 345 |
+
"loss": 0.7513,
|
| 346 |
+
"step": 480
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.18867924528301888,
|
| 350 |
+
"grad_norm": 0.17292006313800812,
|
| 351 |
+
"learning_rate": 9.35740512236047e-06,
|
| 352 |
+
"loss": 0.7453,
|
| 353 |
+
"step": 490
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.19252984212552945,
|
| 357 |
+
"grad_norm": 0.16727009415626526,
|
| 358 |
+
"learning_rate": 9.326484890517809e-06,
|
| 359 |
+
"loss": 0.749,
|
| 360 |
+
"step": 500
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.19638043896804006,
|
| 364 |
+
"grad_norm": 0.17827144265174866,
|
| 365 |
+
"learning_rate": 9.294891723898926e-06,
|
| 366 |
+
"loss": 0.7388,
|
| 367 |
+
"step": 510
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.20023103581055063,
|
| 371 |
+
"grad_norm": 0.18273098766803741,
|
| 372 |
+
"learning_rate": 9.262630536456153e-06,
|
| 373 |
+
"loss": 0.7621,
|
| 374 |
+
"step": 520
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.20408163265306123,
|
| 378 |
+
"grad_norm": 0.18189355731010437,
|
| 379 |
+
"learning_rate": 9.229706346044749e-06,
|
| 380 |
+
"loss": 0.7462,
|
| 381 |
+
"step": 530
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.2079322294955718,
|
| 385 |
+
"grad_norm": 0.19236987829208374,
|
| 386 |
+
"learning_rate": 9.196124273642422e-06,
|
| 387 |
+
"loss": 0.7558,
|
| 388 |
+
"step": 540
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.2117828263380824,
|
| 392 |
+
"grad_norm": 0.17076964676380157,
|
| 393 |
+
"learning_rate": 9.161889542552842e-06,
|
| 394 |
+
"loss": 0.7612,
|
| 395 |
+
"step": 550
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.215633423180593,
|
| 399 |
+
"grad_norm": 0.1760680079460144,
|
| 400 |
+
"learning_rate": 9.127007477593193e-06,
|
| 401 |
+
"loss": 0.7626,
|
| 402 |
+
"step": 560
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.21948402002310358,
|
| 406 |
+
"grad_norm": 0.19193334877490997,
|
| 407 |
+
"learning_rate": 9.091483504265974e-06,
|
| 408 |
+
"loss": 0.7771,
|
| 409 |
+
"step": 570
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.22333461686561418,
|
| 413 |
+
"grad_norm": 0.18861053884029388,
|
| 414 |
+
"learning_rate": 9.055323147915116e-06,
|
| 415 |
+
"loss": 0.7455,
|
| 416 |
+
"step": 580
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.22718521370812475,
|
| 420 |
+
"grad_norm": 0.18224377930164337,
|
| 421 |
+
"learning_rate": 9.018532032866585e-06,
|
| 422 |
+
"loss": 0.7608,
|
| 423 |
+
"step": 590
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.23103581055063535,
|
| 427 |
+
"grad_norm": 0.16275642812252045,
|
| 428 |
+
"learning_rate": 8.981115881553579e-06,
|
| 429 |
+
"loss": 0.7577,
|
| 430 |
+
"step": 600
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.23488640739314592,
|
| 434 |
+
"grad_norm": 0.19239147007465363,
|
| 435 |
+
"learning_rate": 8.943080513626476e-06,
|
| 436 |
+
"loss": 0.7774,
|
| 437 |
+
"step": 610
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.23873700423565652,
|
| 441 |
+
"grad_norm": 0.16993758082389832,
|
| 442 |
+
"learning_rate": 8.904431845047641e-06,
|
| 443 |
+
"loss": 0.756,
|
| 444 |
+
"step": 620
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.24258760107816713,
|
| 448 |
+
"grad_norm": 0.17130494117736816,
|
| 449 |
+
"learning_rate": 8.86517588717128e-06,
|
| 450 |
+
"loss": 0.7666,
|
| 451 |
+
"step": 630
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.2464381979206777,
|
| 455 |
+
"grad_norm": 0.1803787499666214,
|
| 456 |
+
"learning_rate": 8.82531874580844e-06,
|
| 457 |
+
"loss": 0.7654,
|
| 458 |
+
"step": 640
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.25028879476318827,
|
| 462 |
+
"grad_norm": 0.16590934991836548,
|
| 463 |
+
"learning_rate": 8.784866620277314e-06,
|
| 464 |
+
"loss": 0.7265,
|
| 465 |
+
"step": 650
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.25413939160569887,
|
| 469 |
+
"grad_norm": 0.17768357694149017,
|
| 470 |
+
"learning_rate": 8.743825802439018e-06,
|
| 471 |
+
"loss": 0.7517,
|
| 472 |
+
"step": 660
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 0.2579899884482095,
|
| 476 |
+
"grad_norm": 0.17851752042770386,
|
| 477 |
+
"learning_rate": 8.702202675718956e-06,
|
| 478 |
+
"loss": 0.7607,
|
| 479 |
+
"step": 670
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 0.2618405852907201,
|
| 483 |
+
"grad_norm": 0.1645706295967102,
|
| 484 |
+
"learning_rate": 8.660003714113959e-06,
|
| 485 |
+
"loss": 0.7421,
|
| 486 |
+
"step": 680
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 0.2656911821332307,
|
| 490 |
+
"grad_norm": 0.17407865822315216,
|
| 491 |
+
"learning_rate": 8.617235481185323e-06,
|
| 492 |
+
"loss": 0.7521,
|
| 493 |
+
"step": 690
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 0.2695417789757412,
|
| 497 |
+
"grad_norm": 0.1837378889322281,
|
| 498 |
+
"learning_rate": 8.573904629037931e-06,
|
| 499 |
+
"loss": 0.7648,
|
| 500 |
+
"step": 700
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.2733923758182518,
|
| 504 |
+
"grad_norm": 0.16211499273777008,
|
| 505 |
+
"learning_rate": 8.530017897285585e-06,
|
| 506 |
+
"loss": 0.7463,
|
| 507 |
+
"step": 710
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.2772429726607624,
|
| 511 |
+
"grad_norm": 0.16822549700737,
|
| 512 |
+
"learning_rate": 8.485582112002746e-06,
|
| 513 |
+
"loss": 0.7472,
|
| 514 |
+
"step": 720
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.281093569503273,
|
| 518 |
+
"grad_norm": 0.17382241785526276,
|
| 519 |
+
"learning_rate": 8.440604184662811e-06,
|
| 520 |
+
"loss": 0.7564,
|
| 521 |
+
"step": 730
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.2849441663457836,
|
| 525 |
+
"grad_norm": 0.18401770293712616,
|
| 526 |
+
"learning_rate": 8.395091111063118e-06,
|
| 527 |
+
"loss": 0.7422,
|
| 528 |
+
"step": 740
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 0.28879476318829417,
|
| 532 |
+
"grad_norm": 0.1604488492012024,
|
| 533 |
+
"learning_rate": 8.349049970236822e-06,
|
| 534 |
+
"loss": 0.7389,
|
| 535 |
+
"step": 750
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 0.29264536003080477,
|
| 539 |
+
"grad_norm": 0.16979795694351196,
|
| 540 |
+
"learning_rate": 8.302487923351842e-06,
|
| 541 |
+
"loss": 0.7361,
|
| 542 |
+
"step": 760
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.29649595687331537,
|
| 546 |
+
"grad_norm": 0.16885393857955933,
|
| 547 |
+
"learning_rate": 8.255412212597021e-06,
|
| 548 |
+
"loss": 0.7558,
|
| 549 |
+
"step": 770
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.30034655371582597,
|
| 553 |
+
"grad_norm": 0.1797810047864914,
|
| 554 |
+
"learning_rate": 8.207830160055688e-06,
|
| 555 |
+
"loss": 0.7504,
|
| 556 |
+
"step": 780
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.3041971505583365,
|
| 560 |
+
"grad_norm": 0.17053641378879547,
|
| 561 |
+
"learning_rate": 8.159749166566786e-06,
|
| 562 |
+
"loss": 0.7335,
|
| 563 |
+
"step": 790
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 0.3080477474008471,
|
| 567 |
+
"grad_norm": 0.1725112348794937,
|
| 568 |
+
"learning_rate": 8.11117671057377e-06,
|
| 569 |
+
"loss": 0.7547,
|
| 570 |
+
"step": 800
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.3118983442433577,
|
| 574 |
+
"grad_norm": 0.16741028428077698,
|
| 575 |
+
"learning_rate": 8.062120346961404e-06,
|
| 576 |
+
"loss": 0.7525,
|
| 577 |
+
"step": 810
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 0.3157489410858683,
|
| 581 |
+
"grad_norm": 0.1686672866344452,
|
| 582 |
+
"learning_rate": 8.012587705880705e-06,
|
| 583 |
+
"loss": 0.7498,
|
| 584 |
+
"step": 820
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 0.3195995379283789,
|
| 588 |
+
"grad_norm": 0.17327840626239777,
|
| 589 |
+
"learning_rate": 7.962586491562146e-06,
|
| 590 |
+
"loss": 0.7372,
|
| 591 |
+
"step": 830
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.32345013477088946,
|
| 595 |
+
"grad_norm": 0.1804196834564209,
|
| 596 |
+
"learning_rate": 7.912124481117357e-06,
|
| 597 |
+
"loss": 0.7384,
|
| 598 |
+
"step": 840
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 0.32730073161340006,
|
| 602 |
+
"grad_norm": 0.1636105626821518,
|
| 603 |
+
"learning_rate": 7.861209523329494e-06,
|
| 604 |
+
"loss": 0.7476,
|
| 605 |
+
"step": 850
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 0.33115132845591067,
|
| 609 |
+
"grad_norm": 0.17785774171352386,
|
| 610 |
+
"learning_rate": 7.809849537432432e-06,
|
| 611 |
+
"loss": 0.7386,
|
| 612 |
+
"step": 860
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 0.33500192529842127,
|
| 616 |
+
"grad_norm": 0.17451360821723938,
|
| 617 |
+
"learning_rate": 7.758052511879035e-06,
|
| 618 |
+
"loss": 0.7413,
|
| 619 |
+
"step": 870
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 0.33885252214093187,
|
| 623 |
+
"grad_norm": 0.16971951723098755,
|
| 624 |
+
"learning_rate": 7.705826503098642e-06,
|
| 625 |
+
"loss": 0.7455,
|
| 626 |
+
"step": 880
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 0.3427031189834424,
|
| 630 |
+
"grad_norm": 0.18642298877239227,
|
| 631 |
+
"learning_rate": 7.653179634243979e-06,
|
| 632 |
+
"loss": 0.7391,
|
| 633 |
+
"step": 890
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 0.346553715825953,
|
| 637 |
+
"grad_norm": 0.16460728645324707,
|
| 638 |
+
"learning_rate": 7.600120093927696e-06,
|
| 639 |
+
"loss": 0.7408,
|
| 640 |
+
"step": 900
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 0.3504043126684636,
|
| 644 |
+
"grad_norm": 0.19431404769420624,
|
| 645 |
+
"learning_rate": 7.546656134948729e-06,
|
| 646 |
+
"loss": 0.7309,
|
| 647 |
+
"step": 910
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 0.3542549095109742,
|
| 651 |
+
"grad_norm": 0.1663501262664795,
|
| 652 |
+
"learning_rate": 7.492796073008661e-06,
|
| 653 |
+
"loss": 0.7394,
|
| 654 |
+
"step": 920
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 0.3581055063534848,
|
| 658 |
+
"grad_norm": 0.19809529185295105,
|
| 659 |
+
"learning_rate": 7.438548285418326e-06,
|
| 660 |
+
"loss": 0.7205,
|
| 661 |
+
"step": 930
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 0.36195610319599536,
|
| 665 |
+
"grad_norm": 0.17655842006206512,
|
| 666 |
+
"learning_rate": 7.3839212097948e-06,
|
| 667 |
+
"loss": 0.7511,
|
| 668 |
+
"step": 940
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 0.36580670003850596,
|
| 672 |
+
"grad_norm": 0.18160831928253174,
|
| 673 |
+
"learning_rate": 7.328923342749039e-06,
|
| 674 |
+
"loss": 0.7681,
|
| 675 |
+
"step": 950
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 0.36965729688101656,
|
| 679 |
+
"grad_norm": 0.1761743426322937,
|
| 680 |
+
"learning_rate": 7.273563238564319e-06,
|
| 681 |
+
"loss": 0.7631,
|
| 682 |
+
"step": 960
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 0.37350789372352716,
|
| 686 |
+
"grad_norm": 0.1623799353837967,
|
| 687 |
+
"learning_rate": 7.217849507865724e-06,
|
| 688 |
+
"loss": 0.7326,
|
| 689 |
+
"step": 970
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 0.37735849056603776,
|
| 693 |
+
"grad_norm": 0.16932454705238342,
|
| 694 |
+
"learning_rate": 7.161790816280858e-06,
|
| 695 |
+
"loss": 0.7407,
|
| 696 |
+
"step": 980
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 0.3812090874085483,
|
| 700 |
+
"grad_norm": 0.17495502531528473,
|
| 701 |
+
"learning_rate": 7.1053958830920125e-06,
|
| 702 |
+
"loss": 0.7283,
|
| 703 |
+
"step": 990
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 0.3850596842510589,
|
| 707 |
+
"grad_norm": 0.17233437299728394,
|
| 708 |
+
"learning_rate": 7.0486734798799715e-06,
|
| 709 |
+
"loss": 0.7406,
|
| 710 |
+
"step": 1000
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 0.3889102810935695,
|
| 714 |
+
"grad_norm": 0.1675395965576172,
|
| 715 |
+
"learning_rate": 6.991632429159708e-06,
|
| 716 |
+
"loss": 0.7604,
|
| 717 |
+
"step": 1010
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 0.3927608779360801,
|
| 721 |
+
"grad_norm": 0.18730506300926208,
|
| 722 |
+
"learning_rate": 6.934281603008132e-06,
|
| 723 |
+
"loss": 0.7572,
|
| 724 |
+
"step": 1020
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 0.39661147477859066,
|
| 728 |
+
"grad_norm": 0.1561717689037323,
|
| 729 |
+
"learning_rate": 6.876629921684143e-06,
|
| 730 |
+
"loss": 0.7543,
|
| 731 |
+
"step": 1030
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 0.40046207162110126,
|
| 735 |
+
"grad_norm": 0.1799876093864441,
|
| 736 |
+
"learning_rate": 6.818686352241199e-06,
|
| 737 |
+
"loss": 0.7416,
|
| 738 |
+
"step": 1040
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 0.40431266846361186,
|
| 742 |
+
"grad_norm": 0.1594628393650055,
|
| 743 |
+
"learning_rate": 6.760459907132573e-06,
|
| 744 |
+
"loss": 0.7366,
|
| 745 |
+
"step": 1050
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 0.40816326530612246,
|
| 749 |
+
"grad_norm": 0.16627565026283264,
|
| 750 |
+
"learning_rate": 6.701959642809589e-06,
|
| 751 |
+
"loss": 0.7424,
|
| 752 |
+
"step": 1060
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 0.41201386214863306,
|
| 756 |
+
"grad_norm": 0.16967129707336426,
|
| 757 |
+
"learning_rate": 6.643194658312987e-06,
|
| 758 |
+
"loss": 0.7344,
|
| 759 |
+
"step": 1070
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 0.4158644589911436,
|
| 763 |
+
"grad_norm": 0.161793053150177,
|
| 764 |
+
"learning_rate": 6.584174093857676e-06,
|
| 765 |
+
"loss": 0.7611,
|
| 766 |
+
"step": 1080
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 0.4197150558336542,
|
| 770 |
+
"grad_norm": 0.177351176738739,
|
| 771 |
+
"learning_rate": 6.5249071294110735e-06,
|
| 772 |
+
"loss": 0.7433,
|
| 773 |
+
"step": 1090
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 0.4235656526761648,
|
| 777 |
+
"grad_norm": 0.18744368851184845,
|
| 778 |
+
"learning_rate": 6.465402983265274e-06,
|
| 779 |
+
"loss": 0.7554,
|
| 780 |
+
"step": 1100
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 0.4274162495186754,
|
| 784 |
+
"grad_norm": 0.17615751922130585,
|
| 785 |
+
"learning_rate": 6.405670910603243e-06,
|
| 786 |
+
"loss": 0.7475,
|
| 787 |
+
"step": 1110
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 0.431266846361186,
|
| 791 |
+
"grad_norm": 0.17402222752571106,
|
| 792 |
+
"learning_rate": 6.345720202059291e-06,
|
| 793 |
+
"loss": 0.7452,
|
| 794 |
+
"step": 1120
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 0.43511744320369655,
|
| 798 |
+
"grad_norm": 0.18303658068180084,
|
| 799 |
+
"learning_rate": 6.285560182274008e-06,
|
| 800 |
+
"loss": 0.7254,
|
| 801 |
+
"step": 1130
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 0.43896804004620715,
|
| 805 |
+
"grad_norm": 0.18317805230617523,
|
| 806 |
+
"learning_rate": 6.225200208443936e-06,
|
| 807 |
+
"loss": 0.7499,
|
| 808 |
+
"step": 1140
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 0.44281863688871775,
|
| 812 |
+
"grad_norm": 0.17036540806293488,
|
| 813 |
+
"learning_rate": 6.16464966886616e-06,
|
| 814 |
+
"loss": 0.7353,
|
| 815 |
+
"step": 1150
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 0.44666923373122835,
|
| 819 |
+
"grad_norm": 0.20545729994773865,
|
| 820 |
+
"learning_rate": 6.103917981478065e-06,
|
| 821 |
+
"loss": 0.7637,
|
| 822 |
+
"step": 1160
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 0.45051983057373896,
|
| 826 |
+
"grad_norm": 0.16565558314323425,
|
| 827 |
+
"learning_rate": 6.043014592392489e-06,
|
| 828 |
+
"loss": 0.7696,
|
| 829 |
+
"step": 1170
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 0.4543704274162495,
|
| 833 |
+
"grad_norm": 0.16897450387477875,
|
| 834 |
+
"learning_rate": 5.981948974428485e-06,
|
| 835 |
+
"loss": 0.7507,
|
| 836 |
+
"step": 1180
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 0.4582210242587601,
|
| 840 |
+
"grad_norm": 0.15597569942474365,
|
| 841 |
+
"learning_rate": 5.920730625637934e-06,
|
| 842 |
+
"loss": 0.7267,
|
| 843 |
+
"step": 1190
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 0.4620716211012707,
|
| 847 |
+
"grad_norm": 0.1758136749267578,
|
| 848 |
+
"learning_rate": 5.8593690678282355e-06,
|
| 849 |
+
"loss": 0.7363,
|
| 850 |
+
"step": 1200
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 0.4659222179437813,
|
| 854 |
+
"grad_norm": 0.1710347980260849,
|
| 855 |
+
"learning_rate": 5.797873845081301e-06,
|
| 856 |
+
"loss": 0.7345,
|
| 857 |
+
"step": 1210
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 0.46977281478629185,
|
| 861 |
+
"grad_norm": 0.17849136888980865,
|
| 862 |
+
"learning_rate": 5.736254522269075e-06,
|
| 863 |
+
"loss": 0.7602,
|
| 864 |
+
"step": 1220
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 0.47362341162880245,
|
| 868 |
+
"grad_norm": 0.168111190199852,
|
| 869 |
+
"learning_rate": 5.6745206835658386e-06,
|
| 870 |
+
"loss": 0.756,
|
| 871 |
+
"step": 1230
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 0.47747400847131305,
|
| 875 |
+
"grad_norm": 0.16375769674777985,
|
| 876 |
+
"learning_rate": 5.612681930957495e-06,
|
| 877 |
+
"loss": 0.7341,
|
| 878 |
+
"step": 1240
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 0.48132460531382365,
|
| 882 |
+
"grad_norm": 0.17046721279621124,
|
| 883 |
+
"learning_rate": 5.550747882748095e-06,
|
| 884 |
+
"loss": 0.7268,
|
| 885 |
+
"step": 1250
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 0.48517520215633425,
|
| 889 |
+
"grad_norm": 0.1810009777545929,
|
| 890 |
+
"learning_rate": 5.4887281720638195e-06,
|
| 891 |
+
"loss": 0.7402,
|
| 892 |
+
"step": 1260
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 0.4890257989988448,
|
| 896 |
+
"grad_norm": 0.1894935816526413,
|
| 897 |
+
"learning_rate": 5.42663244535466e-06,
|
| 898 |
+
"loss": 0.7181,
|
| 899 |
+
"step": 1270
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 0.4928763958413554,
|
| 903 |
+
"grad_norm": 0.17803804576396942,
|
| 904 |
+
"learning_rate": 5.3644703608940205e-06,
|
| 905 |
+
"loss": 0.7344,
|
| 906 |
+
"step": 1280
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 0.496726992683866,
|
| 910 |
+
"grad_norm": 0.16240835189819336,
|
| 911 |
+
"learning_rate": 5.302251587276491e-06,
|
| 912 |
+
"loss": 0.7466,
|
| 913 |
+
"step": 1290
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 0.5005775895263765,
|
| 917 |
+
"grad_norm": 0.1702074259519577,
|
| 918 |
+
"learning_rate": 5.2399858019140005e-06,
|
| 919 |
+
"loss": 0.7374,
|
| 920 |
+
"step": 1300
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 0.5044281863688872,
|
| 924 |
+
"grad_norm": 0.17669494450092316,
|
| 925 |
+
"learning_rate": 5.177682689530615e-06,
|
| 926 |
+
"loss": 0.7558,
|
| 927 |
+
"step": 1310
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 0.5082787832113977,
|
| 931 |
+
"grad_norm": 0.1721785068511963,
|
| 932 |
+
"learning_rate": 5.11535194065619e-06,
|
| 933 |
+
"loss": 0.7268,
|
| 934 |
+
"step": 1320
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 0.5121293800539084,
|
| 938 |
+
"grad_norm": 0.1828662008047104,
|
| 939 |
+
"learning_rate": 5.053003250119113e-06,
|
| 940 |
+
"loss": 0.7343,
|
| 941 |
+
"step": 1330
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 0.515979976896419,
|
| 945 |
+
"grad_norm": 0.16886408627033234,
|
| 946 |
+
"learning_rate": 4.9906463155383925e-06,
|
| 947 |
+
"loss": 0.74,
|
| 948 |
+
"step": 1340
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 0.5198305737389295,
|
| 952 |
+
"grad_norm": 0.16434353590011597,
|
| 953 |
+
"learning_rate": 4.9282908358153046e-06,
|
| 954 |
+
"loss": 0.738,
|
| 955 |
+
"step": 1350
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 0.5236811705814401,
|
| 959 |
+
"grad_norm": 0.18632015585899353,
|
| 960 |
+
"learning_rate": 4.8659465096248345e-06,
|
| 961 |
+
"loss": 0.7537,
|
| 962 |
+
"step": 1360
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 0.5275317674239507,
|
| 966 |
+
"grad_norm": 0.1742846518754959,
|
| 967 |
+
"learning_rate": 4.803623033907169e-06,
|
| 968 |
+
"loss": 0.7462,
|
| 969 |
+
"step": 1370
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 0.5313823642664613,
|
| 973 |
+
"grad_norm": 0.16367043554782867,
|
| 974 |
+
"learning_rate": 4.741330102359441e-06,
|
| 975 |
+
"loss": 0.7601,
|
| 976 |
+
"step": 1380
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 0.5352329611089719,
|
| 980 |
+
"grad_norm": 0.1712270975112915,
|
| 981 |
+
"learning_rate": 4.679077403927996e-06,
|
| 982 |
+
"loss": 0.7349,
|
| 983 |
+
"step": 1390
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 0.5390835579514824,
|
| 987 |
+
"grad_norm": 0.16569560766220093,
|
| 988 |
+
"learning_rate": 4.616874621301373e-06,
|
| 989 |
+
"loss": 0.7362,
|
| 990 |
+
"step": 1400
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 0.5429341547939931,
|
| 994 |
+
"grad_norm": 0.17990632355213165,
|
| 995 |
+
"learning_rate": 4.554731429404293e-06,
|
| 996 |
+
"loss": 0.7535,
|
| 997 |
+
"step": 1410
|
| 998 |
+
},
|
| 999 |
+
{
|
| 1000 |
+
"epoch": 0.5467847516365036,
|
| 1001 |
+
"grad_norm": 0.1815870702266693,
|
| 1002 |
+
"learning_rate": 4.492657493892822e-06,
|
| 1003 |
+
"loss": 0.7369,
|
| 1004 |
+
"step": 1420
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 0.5506353484790143,
|
| 1008 |
+
"grad_norm": 0.17704136669635773,
|
| 1009 |
+
"learning_rate": 4.430662469650999e-06,
|
| 1010 |
+
"loss": 0.7501,
|
| 1011 |
+
"step": 1430
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 0.5544859453215248,
|
| 1015 |
+
"grad_norm": 0.18098022043704987,
|
| 1016 |
+
"learning_rate": 4.368755999289118e-06,
|
| 1017 |
+
"loss": 0.7519,
|
| 1018 |
+
"step": 1440
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 0.5583365421640354,
|
| 1022 |
+
"grad_norm": 0.1753878891468048,
|
| 1023 |
+
"learning_rate": 4.306947711643949e-06,
|
| 1024 |
+
"loss": 0.736,
|
| 1025 |
+
"step": 1450
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 0.562187139006546,
|
| 1029 |
+
"grad_norm": 0.17044010758399963,
|
| 1030 |
+
"learning_rate": 4.245247220281068e-06,
|
| 1031 |
+
"loss": 0.7406,
|
| 1032 |
+
"step": 1460
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 0.5660377358490566,
|
| 1036 |
+
"grad_norm": 0.17354965209960938,
|
| 1037 |
+
"learning_rate": 4.183664121999587e-06,
|
| 1038 |
+
"loss": 0.7358,
|
| 1039 |
+
"step": 1470
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"epoch": 0.5698883326915672,
|
| 1043 |
+
"grad_norm": 0.17415377497673035,
|
| 1044 |
+
"learning_rate": 4.122207995339474e-06,
|
| 1045 |
+
"loss": 0.7286,
|
| 1046 |
+
"step": 1480
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 0.5737389295340778,
|
| 1050 |
+
"grad_norm": 0.1664925068616867,
|
| 1051 |
+
"learning_rate": 4.060888399091734e-06,
|
| 1052 |
+
"loss": 0.7385,
|
| 1053 |
+
"step": 1490
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 0.5775895263765883,
|
| 1057 |
+
"grad_norm": 0.17672127485275269,
|
| 1058 |
+
"learning_rate": 3.999714870811639e-06,
|
| 1059 |
+
"loss": 0.7497,
|
| 1060 |
+
"step": 1500
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 0.581440123219099,
|
| 1064 |
+
"grad_norm": 0.17209744453430176,
|
| 1065 |
+
"learning_rate": 3.938696925335275e-06,
|
| 1066 |
+
"loss": 0.7432,
|
| 1067 |
+
"step": 1510
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 0.5852907200616095,
|
| 1071 |
+
"grad_norm": 0.17436937987804413,
|
| 1072 |
+
"learning_rate": 3.87784405329962e-06,
|
| 1073 |
+
"loss": 0.7511,
|
| 1074 |
+
"step": 1520
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 0.5891413169041202,
|
| 1078 |
+
"grad_norm": 0.16574200987815857,
|
| 1079 |
+
"learning_rate": 3.817165719666382e-06,
|
| 1080 |
+
"loss": 0.751,
|
| 1081 |
+
"step": 1530
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 0.5929919137466307,
|
| 1085 |
+
"grad_norm": 0.1728523075580597,
|
| 1086 |
+
"learning_rate": 3.756671362249841e-06,
|
| 1087 |
+
"loss": 0.7523,
|
| 1088 |
+
"step": 1540
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 0.5968425105891413,
|
| 1092 |
+
"grad_norm": 0.16495642066001892,
|
| 1093 |
+
"learning_rate": 3.6963703902488907e-06,
|
| 1094 |
+
"loss": 0.7415,
|
| 1095 |
+
"step": 1550
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 0.6006931074316519,
|
| 1099 |
+
"grad_norm": 0.16304153203964233,
|
| 1100 |
+
"learning_rate": 3.6362721827835655e-06,
|
| 1101 |
+
"loss": 0.7533,
|
| 1102 |
+
"step": 1560
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 0.6045437042741625,
|
| 1106 |
+
"grad_norm": 0.18440686166286469,
|
| 1107 |
+
"learning_rate": 3.576386087436212e-06,
|
| 1108 |
+
"loss": 0.7567,
|
| 1109 |
+
"step": 1570
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 0.608394301116673,
|
| 1113 |
+
"grad_norm": 0.1850438117980957,
|
| 1114 |
+
"learning_rate": 3.5167214187975913e-06,
|
| 1115 |
+
"loss": 0.7502,
|
| 1116 |
+
"step": 1580
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 0.6122448979591837,
|
| 1120 |
+
"grad_norm": 0.15978150069713593,
|
| 1121 |
+
"learning_rate": 3.457287457018086e-06,
|
| 1122 |
+
"loss": 0.7448,
|
| 1123 |
+
"step": 1590
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 0.6160954948016942,
|
| 1127 |
+
"grad_norm": 0.16930797696113586,
|
| 1128 |
+
"learning_rate": 3.3980934463643003e-06,
|
| 1129 |
+
"loss": 0.7409,
|
| 1130 |
+
"step": 1600
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 0.6199460916442049,
|
| 1134 |
+
"grad_norm": 0.1630074381828308,
|
| 1135 |
+
"learning_rate": 3.3391485937812053e-06,
|
| 1136 |
+
"loss": 0.7182,
|
| 1137 |
+
"step": 1610
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 0.6237966884867154,
|
| 1141 |
+
"grad_norm": 0.16745050251483917,
|
| 1142 |
+
"learning_rate": 3.280462067460115e-06,
|
| 1143 |
+
"loss": 0.7206,
|
| 1144 |
+
"step": 1620
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 0.627647285329226,
|
| 1148 |
+
"grad_norm": 0.17415039241313934,
|
| 1149 |
+
"learning_rate": 3.222042995412669e-06,
|
| 1150 |
+
"loss": 0.7457,
|
| 1151 |
+
"step": 1630
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 0.6314978821717366,
|
| 1155 |
+
"grad_norm": 0.16102497279644012,
|
| 1156 |
+
"learning_rate": 3.163900464051089e-06,
|
| 1157 |
+
"loss": 0.7362,
|
| 1158 |
+
"step": 1640
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 0.6353484790142472,
|
| 1162 |
+
"grad_norm": 0.17055608332157135,
|
| 1163 |
+
"learning_rate": 3.1060435167748826e-06,
|
| 1164 |
+
"loss": 0.7512,
|
| 1165 |
+
"step": 1650
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 0.6391990758567578,
|
| 1169 |
+
"grad_norm": 0.16595607995986938,
|
| 1170 |
+
"learning_rate": 3.048481152564253e-06,
|
| 1171 |
+
"loss": 0.7277,
|
| 1172 |
+
"step": 1660
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 0.6430496726992684,
|
| 1176 |
+
"grad_norm": 0.18641719222068787,
|
| 1177 |
+
"learning_rate": 2.9912223245804017e-06,
|
| 1178 |
+
"loss": 0.7461,
|
| 1179 |
+
"step": 1670
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 0.6469002695417789,
|
| 1183 |
+
"grad_norm": 0.17495304346084595,
|
| 1184 |
+
"learning_rate": 2.934275938772981e-06,
|
| 1185 |
+
"loss": 0.7391,
|
| 1186 |
+
"step": 1680
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 0.6507508663842896,
|
| 1190 |
+
"grad_norm": 0.17646266520023346,
|
| 1191 |
+
"learning_rate": 2.8776508524948676e-06,
|
| 1192 |
+
"loss": 0.7329,
|
| 1193 |
+
"step": 1690
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 0.6546014632268001,
|
| 1197 |
+
"grad_norm": 0.1674959361553192,
|
| 1198 |
+
"learning_rate": 2.821355873124503e-06,
|
| 1199 |
+
"loss": 0.7364,
|
| 1200 |
+
"step": 1700
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 0.6584520600693108,
|
| 1204 |
+
"grad_norm": 0.178955540060997,
|
| 1205 |
+
"learning_rate": 2.7653997566960144e-06,
|
| 1206 |
+
"loss": 0.7417,
|
| 1207 |
+
"step": 1710
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"epoch": 0.6623026569118213,
|
| 1211 |
+
"grad_norm": 0.18975934386253357,
|
| 1212 |
+
"learning_rate": 2.709791206537309e-06,
|
| 1213 |
+
"loss": 0.734,
|
| 1214 |
+
"step": 1720
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 0.6661532537543319,
|
| 1218 |
+
"grad_norm": 0.1821136325597763,
|
| 1219 |
+
"learning_rate": 2.6545388719163747e-06,
|
| 1220 |
+
"loss": 0.7408,
|
| 1221 |
+
"step": 1730
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 0.6700038505968425,
|
| 1225 |
+
"grad_norm": 0.17308925092220306,
|
| 1226 |
+
"learning_rate": 2.599651346695979e-06,
|
| 1227 |
+
"loss": 0.7484,
|
| 1228 |
+
"step": 1740
|
| 1229 |
+
},
|
| 1230 |
+
{
|
| 1231 |
+
"epoch": 0.6738544474393531,
|
| 1232 |
+
"grad_norm": 0.16214801371097565,
|
| 1233 |
+
"learning_rate": 2.545137167997007e-06,
|
| 1234 |
+
"loss": 0.7423,
|
| 1235 |
+
"step": 1750
|
| 1236 |
+
},
|
| 1237 |
+
{
|
| 1238 |
+
"epoch": 0.6777050442818637,
|
| 1239 |
+
"grad_norm": 0.16401617228984833,
|
| 1240 |
+
"learning_rate": 2.4910048148705972e-06,
|
| 1241 |
+
"loss": 0.7348,
|
| 1242 |
+
"step": 1760
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 0.6815556411243743,
|
| 1246 |
+
"grad_norm": 0.18224084377288818,
|
| 1247 |
+
"learning_rate": 2.4372627069793327e-06,
|
| 1248 |
+
"loss": 0.7696,
|
| 1249 |
+
"step": 1770
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 0.6854062379668848,
|
| 1253 |
+
"grad_norm": 0.16809052228927612,
|
| 1254 |
+
"learning_rate": 2.3839192032876486e-06,
|
| 1255 |
+
"loss": 0.7471,
|
| 1256 |
+
"step": 1780
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 0.6892568348093955,
|
| 1260 |
+
"grad_norm": 0.18022237718105316,
|
| 1261 |
+
"learning_rate": 2.3309826007617047e-06,
|
| 1262 |
+
"loss": 0.7623,
|
| 1263 |
+
"step": 1790
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 0.693107431651906,
|
| 1267 |
+
"grad_norm": 0.16593290865421295,
|
| 1268 |
+
"learning_rate": 2.278461133078881e-06,
|
| 1269 |
+
"loss": 0.7301,
|
| 1270 |
+
"step": 1800
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 0.6969580284944167,
|
| 1274 |
+
"grad_norm": 0.17805682122707367,
|
| 1275 |
+
"learning_rate": 2.2263629693471258e-06,
|
| 1276 |
+
"loss": 0.7242,
|
| 1277 |
+
"step": 1810
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 0.7008086253369272,
|
| 1281 |
+
"grad_norm": 0.16343870759010315,
|
| 1282 |
+
"learning_rate": 2.1746962128343414e-06,
|
| 1283 |
+
"loss": 0.7477,
|
| 1284 |
+
"step": 1820
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 0.7046592221794378,
|
| 1288 |
+
"grad_norm": 0.1724991798400879,
|
| 1289 |
+
"learning_rate": 2.1234688997080183e-06,
|
| 1290 |
+
"loss": 0.7312,
|
| 1291 |
+
"step": 1830
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 0.7085098190219484,
|
| 1295 |
+
"grad_norm": 0.16777299344539642,
|
| 1296 |
+
"learning_rate": 2.0726889977853053e-06,
|
| 1297 |
+
"loss": 0.7367,
|
| 1298 |
+
"step": 1840
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 0.712360415864459,
|
| 1302 |
+
"grad_norm": 0.17452380061149597,
|
| 1303 |
+
"learning_rate": 2.022364405293703e-06,
|
| 1304 |
+
"loss": 0.7509,
|
| 1305 |
+
"step": 1850
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 0.7162110127069696,
|
| 1309 |
+
"grad_norm": 0.1674477756023407,
|
| 1310 |
+
"learning_rate": 1.9725029496425814e-06,
|
| 1311 |
+
"loss": 0.7486,
|
| 1312 |
+
"step": 1860
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 0.7200616095494802,
|
| 1316 |
+
"grad_norm": 0.1684352457523346,
|
| 1317 |
+
"learning_rate": 1.923112386205727e-06,
|
| 1318 |
+
"loss": 0.7389,
|
| 1319 |
+
"step": 1870
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 0.7239122063919907,
|
| 1323 |
+
"grad_norm": 0.16971811652183533,
|
| 1324 |
+
"learning_rate": 1.874200397115079e-06,
|
| 1325 |
+
"loss": 0.7505,
|
| 1326 |
+
"step": 1880
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 0.7277628032345014,
|
| 1330 |
+
"grad_norm": 0.17872755229473114,
|
| 1331 |
+
"learning_rate": 1.825774590065857e-06,
|
| 1332 |
+
"loss": 0.7359,
|
| 1333 |
+
"step": 1890
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 0.7316134000770119,
|
| 1337 |
+
"grad_norm": 0.18334773182868958,
|
| 1338 |
+
"learning_rate": 1.7778424971332813e-06,
|
| 1339 |
+
"loss": 0.7455,
|
| 1340 |
+
"step": 1900
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 0.7354639969195226,
|
| 1344 |
+
"grad_norm": 0.16548891365528107,
|
| 1345 |
+
"learning_rate": 1.7304115736010407e-06,
|
| 1346 |
+
"loss": 0.7437,
|
| 1347 |
+
"step": 1910
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 0.7393145937620331,
|
| 1351 |
+
"grad_norm": 0.16715720295906067,
|
| 1352 |
+
"learning_rate": 1.6834891968017108e-06,
|
| 1353 |
+
"loss": 0.7341,
|
| 1354 |
+
"step": 1920
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 0.7431651906045437,
|
| 1358 |
+
"grad_norm": 0.1768849939107895,
|
| 1359 |
+
"learning_rate": 1.6370826649692884e-06,
|
| 1360 |
+
"loss": 0.7504,
|
| 1361 |
+
"step": 1930
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 0.7470157874470543,
|
| 1365 |
+
"grad_norm": 0.1664706915616989,
|
| 1366 |
+
"learning_rate": 1.5911991961040463e-06,
|
| 1367 |
+
"loss": 0.751,
|
| 1368 |
+
"step": 1940
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 0.7508663842895649,
|
| 1372 |
+
"grad_norm": 0.1800420880317688,
|
| 1373 |
+
"learning_rate": 1.545845926849851e-06,
|
| 1374 |
+
"loss": 0.734,
|
| 1375 |
+
"step": 1950
|
| 1376 |
+
},
|
| 1377 |
+
{
|
| 1378 |
+
"epoch": 0.7547169811320755,
|
| 1379 |
+
"grad_norm": 0.180837944149971,
|
| 1380 |
+
"learning_rate": 1.5010299113841397e-06,
|
| 1381 |
+
"loss": 0.7586,
|
| 1382 |
+
"step": 1960
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 0.7585675779745861,
|
| 1386 |
+
"grad_norm": 0.17310890555381775,
|
| 1387 |
+
"learning_rate": 1.4567581203207238e-06,
|
| 1388 |
+
"loss": 0.7487,
|
| 1389 |
+
"step": 1970
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 0.7624181748170966,
|
| 1393 |
+
"grad_norm": 0.18614496290683746,
|
| 1394 |
+
"learning_rate": 1.413037439625593e-06,
|
| 1395 |
+
"loss": 0.7482,
|
| 1396 |
+
"step": 1980
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 0.7662687716596073,
|
| 1400 |
+
"grad_norm": 0.19662554562091827,
|
| 1401 |
+
"learning_rate": 1.3698746695458847e-06,
|
| 1402 |
+
"loss": 0.7372,
|
| 1403 |
+
"step": 1990
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 0.7701193685021178,
|
| 1407 |
+
"grad_norm": 0.16707219183444977,
|
| 1408 |
+
"learning_rate": 1.3272765235521745e-06,
|
| 1409 |
+
"loss": 0.7377,
|
| 1410 |
+
"step": 2000
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"epoch": 0.7739699653446284,
|
| 1414 |
+
"grad_norm": 0.16426987946033478,
|
| 1415 |
+
"learning_rate": 1.2852496272942877e-06,
|
| 1416 |
+
"loss": 0.7436,
|
| 1417 |
+
"step": 2010
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 0.777820562187139,
|
| 1421 |
+
"grad_norm": 0.1641557812690735,
|
| 1422 |
+
"learning_rate": 1.2438005175707396e-06,
|
| 1423 |
+
"loss": 0.7245,
|
| 1424 |
+
"step": 2020
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 0.7816711590296496,
|
| 1428 |
+
"grad_norm": 0.17003794014453888,
|
| 1429 |
+
"learning_rate": 1.2029356413120297e-06,
|
| 1430 |
+
"loss": 0.7216,
|
| 1431 |
+
"step": 2030
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 0.7855217558721602,
|
| 1435 |
+
"grad_norm": 0.16942887008190155,
|
| 1436 |
+
"learning_rate": 1.1626613545778786e-06,
|
| 1437 |
+
"loss": 0.7355,
|
| 1438 |
+
"step": 2040
|
| 1439 |
+
},
|
| 1440 |
+
{
|
| 1441 |
+
"epoch": 0.7893723527146708,
|
| 1442 |
+
"grad_norm": 0.1637715846300125,
|
| 1443 |
+
"learning_rate": 1.1229839215686294e-06,
|
| 1444 |
+
"loss": 0.7379,
|
| 1445 |
+
"step": 2050
|
| 1446 |
+
},
|
| 1447 |
+
{
|
| 1448 |
+
"epoch": 0.7932229495571813,
|
| 1449 |
+
"grad_norm": 0.15483395755290985,
|
| 1450 |
+
"learning_rate": 1.0839095136509188e-06,
|
| 1451 |
+
"loss": 0.7237,
|
| 1452 |
+
"step": 2060
|
| 1453 |
+
},
|
| 1454 |
+
{
|
| 1455 |
+
"epoch": 0.797073546399692,
|
| 1456 |
+
"grad_norm": 0.17606335878372192,
|
| 1457 |
+
"learning_rate": 1.045444208397791e-06,
|
| 1458 |
+
"loss": 0.7406,
|
| 1459 |
+
"step": 2070
|
| 1460 |
+
},
|
| 1461 |
+
{
|
| 1462 |
+
"epoch": 0.8009241432422025,
|
| 1463 |
+
"grad_norm": 0.1571958214044571,
|
| 1464 |
+
"learning_rate": 1.007593988643402e-06,
|
| 1465 |
+
"loss": 0.7161,
|
| 1466 |
+
"step": 2080
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 0.8047747400847132,
|
| 1470 |
+
"grad_norm": 0.16461437940597534,
|
| 1471 |
+
"learning_rate": 9.703647415524613e-07,
|
| 1472 |
+
"loss": 0.745,
|
| 1473 |
+
"step": 2090
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 0.8086253369272237,
|
| 1477 |
+
"grad_norm": 0.16677583754062653,
|
| 1478 |
+
"learning_rate": 9.337622577045485e-07,
|
| 1479 |
+
"loss": 0.7349,
|
| 1480 |
+
"step": 2100
|
| 1481 |
+
},
|
| 1482 |
+
{
|
| 1483 |
+
"epoch": 0.8124759337697343,
|
| 1484 |
+
"grad_norm": 0.17120693624019623,
|
| 1485 |
+
"learning_rate": 8.977922301934588e-07,
|
| 1486 |
+
"loss": 0.7397,
|
| 1487 |
+
"step": 2110
|
| 1488 |
+
},
|
| 1489 |
+
{
|
| 1490 |
+
"epoch": 0.8163265306122449,
|
| 1491 |
+
"grad_norm": 0.17874756455421448,
|
| 1492 |
+
"learning_rate": 8.624602537417009e-07,
|
| 1493 |
+
"loss": 0.754,
|
| 1494 |
+
"step": 2120
|
| 1495 |
+
},
|
| 1496 |
+
{
|
| 1497 |
+
"epoch": 0.8201771274547555,
|
| 1498 |
+
"grad_norm": 0.1770012527704239,
|
| 1499 |
+
"learning_rate": 8.277718238303123e-07,
|
| 1500 |
+
"loss": 0.7354,
|
| 1501 |
+
"step": 2130
|
| 1502 |
+
},
|
| 1503 |
+
{
|
| 1504 |
+
"epoch": 0.8240277242972661,
|
| 1505 |
+
"grad_norm": 0.1783716231584549,
|
| 1506 |
+
"learning_rate": 7.937323358440935e-07,
|
| 1507 |
+
"loss": 0.7372,
|
| 1508 |
+
"step": 2140
|
| 1509 |
+
},
|
| 1510 |
+
{
|
| 1511 |
+
"epoch": 0.8278783211397767,
|
| 1512 |
+
"grad_norm": 0.16886359453201294,
|
| 1513 |
+
"learning_rate": 7.603470842324223e-07,
|
| 1514 |
+
"loss": 0.7264,
|
| 1515 |
+
"step": 2150
|
| 1516 |
+
},
|
| 1517 |
+
{
|
| 1518 |
+
"epoch": 0.8317289179822872,
|
| 1519 |
+
"grad_norm": 0.16562330722808838,
|
| 1520 |
+
"learning_rate": 7.276212616857575e-07,
|
| 1521 |
+
"loss": 0.7487,
|
| 1522 |
+
"step": 2160
|
| 1523 |
+
},
|
| 1524 |
+
{
|
| 1525 |
+
"epoch": 0.8355795148247979,
|
| 1526 |
+
"grad_norm": 0.17247430980205536,
|
| 1527 |
+
"learning_rate": 6.955599583279837e-07,
|
| 1528 |
+
"loss": 0.7415,
|
| 1529 |
+
"step": 2170
|
| 1530 |
+
},
|
| 1531 |
+
{
|
| 1532 |
+
"epoch": 0.8394301116673084,
|
| 1533 |
+
"grad_norm": 0.16585010290145874,
|
| 1534 |
+
"learning_rate": 6.641681609246981e-07,
|
| 1535 |
+
"loss": 0.7367,
|
| 1536 |
+
"step": 2180
|
| 1537 |
+
},
|
| 1538 |
+
{
|
| 1539 |
+
"epoch": 0.8432807085098191,
|
| 1540 |
+
"grad_norm": 0.17537270486354828,
|
| 1541 |
+
"learning_rate": 6.334507521075711e-07,
|
| 1542 |
+
"loss": 0.7366,
|
| 1543 |
+
"step": 2190
|
| 1544 |
+
},
|
| 1545 |
+
{
|
| 1546 |
+
"epoch": 0.8471313053523296,
|
| 1547 |
+
"grad_norm": 0.17970895767211914,
|
| 1548 |
+
"learning_rate": 6.034125096149179e-07,
|
| 1549 |
+
"loss": 0.7396,
|
| 1550 |
+
"step": 2200
|
| 1551 |
+
},
|
| 1552 |
+
{
|
| 1553 |
+
"epoch": 0.8509819021948402,
|
| 1554 |
+
"grad_norm": 0.16297978162765503,
|
| 1555 |
+
"learning_rate": 5.740581055485722e-07,
|
| 1556 |
+
"loss": 0.7111,
|
| 1557 |
+
"step": 2210
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"epoch": 0.8548324990373508,
|
| 1561 |
+
"grad_norm": 0.1664322167634964,
|
| 1562 |
+
"learning_rate": 5.453921056471961e-07,
|
| 1563 |
+
"loss": 0.7434,
|
| 1564 |
+
"step": 2220
|
| 1565 |
+
},
|
| 1566 |
+
{
|
| 1567 |
+
"epoch": 0.8586830958798614,
|
| 1568 |
+
"grad_norm": 0.1833273321390152,
|
| 1569 |
+
"learning_rate": 5.174189685761288e-07,
|
| 1570 |
+
"loss": 0.7375,
|
| 1571 |
+
"step": 2230
|
| 1572 |
+
},
|
| 1573 |
+
{
|
| 1574 |
+
"epoch": 0.862533692722372,
|
| 1575 |
+
"grad_norm": 0.16449737548828125,
|
| 1576 |
+
"learning_rate": 4.901430452338979e-07,
|
| 1577 |
+
"loss": 0.7485,
|
| 1578 |
+
"step": 2240
|
| 1579 |
+
},
|
| 1580 |
+
{
|
| 1581 |
+
"epoch": 0.8663842895648826,
|
| 1582 |
+
"grad_norm": 0.17290154099464417,
|
| 1583 |
+
"learning_rate": 4.6356857807548286e-07,
|
| 1584 |
+
"loss": 0.737,
|
| 1585 |
+
"step": 2250
|
| 1586 |
+
},
|
| 1587 |
+
{
|
| 1588 |
+
"epoch": 0.8702348864073931,
|
| 1589 |
+
"grad_norm": 0.19579645991325378,
|
| 1590 |
+
"learning_rate": 4.376997004524541e-07,
|
| 1591 |
+
"loss": 0.7187,
|
| 1592 |
+
"step": 2260
|
| 1593 |
+
},
|
| 1594 |
+
{
|
| 1595 |
+
"epoch": 0.8740854832499038,
|
| 1596 |
+
"grad_norm": 0.16899782419204712,
|
| 1597 |
+
"learning_rate": 4.12540435970073e-07,
|
| 1598 |
+
"loss": 0.7375,
|
| 1599 |
+
"step": 2270
|
| 1600 |
+
},
|
| 1601 |
+
{
|
| 1602 |
+
"epoch": 0.8779360800924143,
|
| 1603 |
+
"grad_norm": 0.15988123416900635,
|
| 1604 |
+
"learning_rate": 3.880946978614703e-07,
|
| 1605 |
+
"loss": 0.7427,
|
| 1606 |
+
"step": 2280
|
| 1607 |
+
},
|
| 1608 |
+
{
|
| 1609 |
+
"epoch": 0.881786676934925,
|
| 1610 |
+
"grad_norm": 0.1659078299999237,
|
| 1611 |
+
"learning_rate": 3.643662883789878e-07,
|
| 1612 |
+
"loss": 0.745,
|
| 1613 |
+
"step": 2290
|
| 1614 |
+
},
|
| 1615 |
+
{
|
| 1616 |
+
"epoch": 0.8856372737774355,
|
| 1617 |
+
"grad_norm": 0.16312600672245026,
|
| 1618 |
+
"learning_rate": 3.41358898202781e-07,
|
| 1619 |
+
"loss": 0.7266,
|
| 1620 |
+
"step": 2300
|
| 1621 |
+
},
|
| 1622 |
+
{
|
| 1623 |
+
"epoch": 0.889487870619946,
|
| 1624 |
+
"grad_norm": 0.16241589188575745,
|
| 1625 |
+
"learning_rate": 3.190761058667741e-07,
|
| 1626 |
+
"loss": 0.7391,
|
| 1627 |
+
"step": 2310
|
| 1628 |
+
},
|
| 1629 |
+
{
|
| 1630 |
+
"epoch": 0.8933384674624567,
|
| 1631 |
+
"grad_norm": 0.16132062673568726,
|
| 1632 |
+
"learning_rate": 2.9752137720206463e-07,
|
| 1633 |
+
"loss": 0.741,
|
| 1634 |
+
"step": 2320
|
| 1635 |
+
},
|
| 1636 |
+
{
|
| 1637 |
+
"epoch": 0.8971890643049673,
|
| 1638 |
+
"grad_norm": 0.17593403160572052,
|
| 1639 |
+
"learning_rate": 2.7669806479785067e-07,
|
| 1640 |
+
"loss": 0.7511,
|
| 1641 |
+
"step": 2330
|
| 1642 |
+
},
|
| 1643 |
+
{
|
| 1644 |
+
"epoch": 0.9010396611474779,
|
| 1645 |
+
"grad_norm": 0.16278637945652008,
|
| 1646 |
+
"learning_rate": 2.566094074799763e-07,
|
| 1647 |
+
"loss": 0.743,
|
| 1648 |
+
"step": 2340
|
| 1649 |
+
},
|
| 1650 |
+
{
|
| 1651 |
+
"epoch": 0.9048902579899885,
|
| 1652 |
+
"grad_norm": 0.17385677993297577,
|
| 1653 |
+
"learning_rate": 2.3725852980716557e-07,
|
| 1654 |
+
"loss": 0.7232,
|
| 1655 |
+
"step": 2350
|
| 1656 |
+
},
|
| 1657 |
+
{
|
| 1658 |
+
"epoch": 0.908740854832499,
|
| 1659 |
+
"grad_norm": 0.16808927059173584,
|
| 1660 |
+
"learning_rate": 2.1864844158503983e-07,
|
| 1661 |
+
"loss": 0.7382,
|
| 1662 |
+
"step": 2360
|
| 1663 |
+
},
|
| 1664 |
+
{
|
| 1665 |
+
"epoch": 0.9125914516750097,
|
| 1666 |
+
"grad_norm": 0.1804141253232956,
|
| 1667 |
+
"learning_rate": 2.007820373979702e-07,
|
| 1668 |
+
"loss": 0.7304,
|
| 1669 |
+
"step": 2370
|
| 1670 |
+
},
|
| 1671 |
+
{
|
| 1672 |
+
"epoch": 0.9164420485175202,
|
| 1673 |
+
"grad_norm": 0.16312135756015778,
|
| 1674 |
+
"learning_rate": 1.8366209615886532e-07,
|
| 1675 |
+
"loss": 0.7417,
|
| 1676 |
+
"step": 2380
|
| 1677 |
+
},
|
| 1678 |
+
{
|
| 1679 |
+
"epoch": 0.9202926453600309,
|
| 1680 |
+
"grad_norm": 0.16737760603427887,
|
| 1681 |
+
"learning_rate": 1.6729128067693613e-07,
|
| 1682 |
+
"loss": 0.7538,
|
| 1683 |
+
"step": 2390
|
| 1684 |
+
},
|
| 1685 |
+
{
|
| 1686 |
+
"epoch": 0.9241432422025414,
|
| 1687 |
+
"grad_norm": 0.18798159062862396,
|
| 1688 |
+
"learning_rate": 1.5167213724353426e-07,
|
| 1689 |
+
"loss": 0.7475,
|
| 1690 |
+
"step": 2400
|
| 1691 |
+
},
|
| 1692 |
+
{
|
| 1693 |
+
"epoch": 0.927993839045052,
|
| 1694 |
+
"grad_norm": 0.16493511199951172,
|
| 1695 |
+
"learning_rate": 1.3680709523610058e-07,
|
| 1696 |
+
"loss": 0.7252,
|
| 1697 |
+
"step": 2410
|
| 1698 |
+
},
|
| 1699 |
+
{
|
| 1700 |
+
"epoch": 0.9318444358875626,
|
| 1701 |
+
"grad_norm": 0.16221527755260468,
|
| 1702 |
+
"learning_rate": 1.2269846674030418e-07,
|
| 1703 |
+
"loss": 0.7565,
|
| 1704 |
+
"step": 2420
|
| 1705 |
+
},
|
| 1706 |
+
{
|
| 1707 |
+
"epoch": 0.9356950327300732,
|
| 1708 |
+
"grad_norm": 0.16680166125297546,
|
| 1709 |
+
"learning_rate": 1.0934844619042595e-07,
|
| 1710 |
+
"loss": 0.7483,
|
| 1711 |
+
"step": 2430
|
| 1712 |
+
},
|
| 1713 |
+
{
|
| 1714 |
+
"epoch": 0.9395456295725837,
|
| 1715 |
+
"grad_norm": 0.1644672155380249,
|
| 1716 |
+
"learning_rate": 9.675911002803961e-08,
|
| 1717 |
+
"loss": 0.7371,
|
| 1718 |
+
"step": 2440
|
| 1719 |
+
},
|
| 1720 |
+
{
|
| 1721 |
+
"epoch": 0.9433962264150944,
|
| 1722 |
+
"grad_norm": 0.17425920069217682,
|
| 1723 |
+
"learning_rate": 8.493241637904381e-08,
|
| 1724 |
+
"loss": 0.7257,
|
| 1725 |
+
"step": 2450
|
| 1726 |
+
},
|
| 1727 |
+
{
|
| 1728 |
+
"epoch": 0.9472468232576049,
|
| 1729 |
+
"grad_norm": 0.18836142122745514,
|
| 1730 |
+
"learning_rate": 7.387020474909689e-08,
|
| 1731 |
+
"loss": 0.7541,
|
| 1732 |
+
"step": 2460
|
| 1733 |
+
},
|
| 1734 |
+
{
|
| 1735 |
+
"epoch": 0.9510974201001156,
|
| 1736 |
+
"grad_norm": 0.20107921957969666,
|
| 1737 |
+
"learning_rate": 6.357419573750856e-08,
|
| 1738 |
+
"loss": 0.7492,
|
| 1739 |
+
"step": 2470
|
| 1740 |
+
},
|
| 1741 |
+
{
|
| 1742 |
+
"epoch": 0.9549480169426261,
|
| 1743 |
+
"grad_norm": 0.16980546712875366,
|
| 1744 |
+
"learning_rate": 5.4045990769613365e-08,
|
| 1745 |
+
"loss": 0.7347,
|
| 1746 |
+
"step": 2480
|
| 1747 |
+
},
|
| 1748 |
+
{
|
| 1749 |
+
"epoch": 0.9587986137851366,
|
| 1750 |
+
"grad_norm": 0.16393102705478668,
|
| 1751 |
+
"learning_rate": 4.5287071847694434e-08,
|
| 1752 |
+
"loss": 0.7354,
|
| 1753 |
+
"step": 2490
|
| 1754 |
+
},
|
| 1755 |
+
{
|
| 1756 |
+
"epoch": 0.9626492106276473,
|
| 1757 |
+
"grad_norm": 0.1635114997625351,
|
| 1758 |
+
"learning_rate": 3.7298801320467817e-08,
|
| 1759 |
+
"loss": 0.7376,
|
| 1760 |
+
"step": 2500
|
| 1761 |
+
},
|
| 1762 |
+
{
|
| 1763 |
+
"epoch": 0.9664998074701578,
|
| 1764 |
+
"grad_norm": 0.16610437631607056,
|
| 1765 |
+
"learning_rate": 3.0082421671192576e-08,
|
| 1766 |
+
"loss": 0.7362,
|
| 1767 |
+
"step": 2510
|
| 1768 |
+
},
|
| 1769 |
+
{
|
| 1770 |
+
"epoch": 0.9703504043126685,
|
| 1771 |
+
"grad_norm": 0.16644082963466644,
|
| 1772 |
+
"learning_rate": 2.3639055324410355e-08,
|
| 1773 |
+
"loss": 0.7515,
|
| 1774 |
+
"step": 2520
|
| 1775 |
+
},
|
| 1776 |
+
{
|
| 1777 |
+
"epoch": 0.974201001155179,
|
| 1778 |
+
"grad_norm": 0.1704651415348053,
|
| 1779 |
+
"learning_rate": 1.7969704471369477e-08,
|
| 1780 |
+
"loss": 0.733,
|
| 1781 |
+
"step": 2530
|
| 1782 |
+
},
|
| 1783 |
+
{
|
| 1784 |
+
"epoch": 0.9780515979976896,
|
| 1785 |
+
"grad_norm": 0.15912753343582153,
|
| 1786 |
+
"learning_rate": 1.3075250914142413e-08,
|
| 1787 |
+
"loss": 0.7339,
|
| 1788 |
+
"step": 2540
|
| 1789 |
+
},
|
| 1790 |
+
{
|
| 1791 |
+
"epoch": 0.9819021948402002,
|
| 1792 |
+
"grad_norm": 0.15641309320926666,
|
| 1793 |
+
"learning_rate": 8.956455928476049e-09,
|
| 1794 |
+
"loss": 0.7482,
|
| 1795 |
+
"step": 2550
|
| 1796 |
+
},
|
| 1797 |
+
{
|
| 1798 |
+
"epoch": 0.9857527916827108,
|
| 1799 |
+
"grad_norm": 0.16168610751628876,
|
| 1800 |
+
"learning_rate": 5.6139601453786275e-09,
|
| 1801 |
+
"loss": 0.7329,
|
| 1802 |
+
"step": 2560
|
| 1803 |
+
},
|
| 1804 |
+
{
|
| 1805 |
+
"epoch": 0.9896033885252215,
|
| 1806 |
+
"grad_norm": 0.16978590190410614,
|
| 1807 |
+
"learning_rate": 3.0482834514805602e-09,
|
| 1808 |
+
"loss": 0.7295,
|
| 1809 |
+
"step": 2570
|
| 1810 |
+
},
|
| 1811 |
+
{
|
| 1812 |
+
"epoch": 0.993453985367732,
|
| 1813 |
+
"grad_norm": 0.16116097569465637,
|
| 1814 |
+
"learning_rate": 1.2598249081713366e-09,
|
| 1815 |
+
"loss": 0.7197,
|
| 1816 |
+
"step": 2580
|
| 1817 |
+
},
|
| 1818 |
+
{
|
| 1819 |
+
"epoch": 0.9973045822102425,
|
| 1820 |
+
"grad_norm": 0.173573836684227,
|
| 1821 |
+
"learning_rate": 2.488626895302826e-10,
|
| 1822 |
+
"loss": 0.7522,
|
| 1823 |
+
"step": 2590
|
| 1824 |
+
},
|
| 1825 |
+
{
|
| 1826 |
+
"epoch": 1.0,
|
| 1827 |
+
"step": 2597,
|
| 1828 |
+
"total_flos": 5.998728299168137e+18,
|
| 1829 |
+
"train_loss": 0.7540981421619367,
|
| 1830 |
+
"train_runtime": 14485.8985,
|
| 1831 |
+
"train_samples_per_second": 45.9,
|
| 1832 |
+
"train_steps_per_second": 0.179
|
| 1833 |
+
}
|
| 1834 |
+
],
|
| 1835 |
+
"logging_steps": 10,
|
| 1836 |
+
"max_steps": 2597,
|
| 1837 |
+
"num_input_tokens_seen": 584317136,
|
| 1838 |
+
"num_train_epochs": 1,
|
| 1839 |
+
"save_steps": 500,
|
| 1840 |
+
"stateful_callbacks": {
|
| 1841 |
+
"TrainerControl": {
|
| 1842 |
+
"args": {
|
| 1843 |
+
"should_epoch_stop": false,
|
| 1844 |
+
"should_evaluate": false,
|
| 1845 |
+
"should_log": false,
|
| 1846 |
+
"should_save": true,
|
| 1847 |
+
"should_training_stop": true
|
| 1848 |
+
},
|
| 1849 |
+
"attributes": {}
|
| 1850 |
+
}
|
| 1851 |
+
},
|
| 1852 |
+
"total_flos": 5.998728299168137e+18,
|
| 1853 |
+
"train_batch_size": 16,
|
| 1854 |
+
"trial_name": null,
|
| 1855 |
+
"trial_params": null
|
| 1856 |
+
}
|
continuous/smollm2/siglip2_b32_256/finetune/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1583da7875bc2fd4ef2dadab0cf5f8cb4ad584e6a6d639a95ab34eeafec956c0
|
| 3 |
+
size 6264
|
continuous/smollm2/siglip2_b32_256/finetune/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
continuous/smollm2/siglip2_b32_256/pretrain/config.json
ADDED
|
@@ -0,0 +1,70 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_faster_video": false,
|
| 3 |
+
"add_time_instruction": false,
|
| 4 |
+
"architectures": [
|
| 5 |
+
"LlamaForCausalLM"
|
| 6 |
+
],
|
| 7 |
+
"attention_bias": false,
|
| 8 |
+
"attention_dropout": 0.0,
|
| 9 |
+
"bos_token_id": 1,
|
| 10 |
+
"dtype": "bfloat16",
|
| 11 |
+
"eos_token_id": 2,
|
| 12 |
+
"faster_token_stride": 10,
|
| 13 |
+
"force_sample": false,
|
| 14 |
+
"head_dim": 64,
|
| 15 |
+
"hidden_act": "silu",
|
| 16 |
+
"hidden_size": 2048,
|
| 17 |
+
"image_aspect_ratio": "square",
|
| 18 |
+
"image_crop_resolution": null,
|
| 19 |
+
"image_grid_pinpoints": null,
|
| 20 |
+
"image_split_resolution": null,
|
| 21 |
+
"initializer_range": 0.02,
|
| 22 |
+
"intermediate_size": 8192,
|
| 23 |
+
"max_position_embeddings": 8192,
|
| 24 |
+
"mlp_bias": false,
|
| 25 |
+
"mm_hidden_size": 768,
|
| 26 |
+
"mm_newline_position": "grid",
|
| 27 |
+
"mm_patch_merge_type": "flat",
|
| 28 |
+
"mm_projector_lr": null,
|
| 29 |
+
"mm_projector_type": "mlp2x_gelu",
|
| 30 |
+
"mm_resampler_type": null,
|
| 31 |
+
"mm_spatial_pool_mode": "bilinear",
|
| 32 |
+
"mm_spatial_pool_stride": null,
|
| 33 |
+
"mm_tunable_parts": "mm_mlp_adapter",
|
| 34 |
+
"mm_use_im_patch_token": false,
|
| 35 |
+
"mm_use_im_start_end": false,
|
| 36 |
+
"mm_vision_select_feature": "patch",
|
| 37 |
+
"mm_vision_select_layer": -2,
|
| 38 |
+
"mm_vision_tower": "open_clip_hub:ViT-B-32-SigLIP2-256",
|
| 39 |
+
"mm_vision_tower_lr": null,
|
| 40 |
+
"model_type": "llama",
|
| 41 |
+
"num_attention_heads": 32,
|
| 42 |
+
"num_hidden_layers": 24,
|
| 43 |
+
"num_key_value_heads": 32,
|
| 44 |
+
"pad_token_id": 0,
|
| 45 |
+
"pos_skipping_range": 4096,
|
| 46 |
+
"pretraining_tp": 1,
|
| 47 |
+
"rms_norm_eps": 1e-05,
|
| 48 |
+
"rope_scaling": null,
|
| 49 |
+
"rope_theta": 130000,
|
| 50 |
+
"tie_word_embeddings": true,
|
| 51 |
+
"tokenizer_model_max_length": 8192,
|
| 52 |
+
"tokenizer_padding_side": "right",
|
| 53 |
+
"transformers.js_config": {
|
| 54 |
+
"dtype": "q4",
|
| 55 |
+
"kv_cache_dtype": {
|
| 56 |
+
"fp16": "float16",
|
| 57 |
+
"q4f16": "float16"
|
| 58 |
+
},
|
| 59 |
+
"use_external_data_format": {
|
| 60 |
+
"model.onnx": true,
|
| 61 |
+
"model_fp16.onnx": true
|
| 62 |
+
}
|
| 63 |
+
},
|
| 64 |
+
"transformers_version": "4.57.6",
|
| 65 |
+
"use_cache": true,
|
| 66 |
+
"use_mm_proj": true,
|
| 67 |
+
"use_pos_skipping": false,
|
| 68 |
+
"vision_tower_pretrained": "/cache/ckpt/download/tokenizer/continuous/siglip2/siglip2_b32_256.npz",
|
| 69 |
+
"vocab_size": 49152
|
| 70 |
+
}
|
continuous/smollm2/siglip2_b32_256/pretrain/mm_projector.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1ebc7fd973f21fbdcaddfdf9db69cd1d643c1a7008a2c780610e4347a6434fff
|
| 3 |
+
size 23087160
|
continuous/smollm2/siglip2_b32_256/pretrain/trainer_state.json
ADDED
|
@@ -0,0 +1,421 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 1.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 545,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.01834862385321101,
|
| 14 |
+
"grad_norm": 1.5247384309768677,
|
| 15 |
+
"learning_rate": 0.00032142857142857147,
|
| 16 |
+
"loss": 3.4821,
|
| 17 |
+
"step": 10
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.03669724770642202,
|
| 21 |
+
"grad_norm": 0.39422428607940674,
|
| 22 |
+
"learning_rate": 0.0006785714285714287,
|
| 23 |
+
"loss": 2.8436,
|
| 24 |
+
"step": 20
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.05504587155963303,
|
| 28 |
+
"grad_norm": 0.32334190607070923,
|
| 29 |
+
"learning_rate": 0.0009999907688176173,
|
| 30 |
+
"loss": 2.7311,
|
| 31 |
+
"step": 30
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.07339449541284404,
|
| 35 |
+
"grad_norm": 0.1858212947845459,
|
| 36 |
+
"learning_rate": 0.0009988834393115766,
|
| 37 |
+
"loss": 2.6172,
|
| 38 |
+
"step": 40
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.09174311926605505,
|
| 42 |
+
"grad_norm": 0.3032836318016052,
|
| 43 |
+
"learning_rate": 0.0009959345572940772,
|
| 44 |
+
"loss": 2.5438,
|
| 45 |
+
"step": 50
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.11009174311926606,
|
| 49 |
+
"grad_norm": 0.22911584377288818,
|
| 50 |
+
"learning_rate": 0.0009911550081155983,
|
| 51 |
+
"loss": 2.4801,
|
| 52 |
+
"step": 60
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.12844036697247707,
|
| 56 |
+
"grad_norm": 0.293910413980484,
|
| 57 |
+
"learning_rate": 0.0009845624347566433,
|
| 58 |
+
"loss": 2.438,
|
| 59 |
+
"step": 70
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.14678899082568808,
|
| 63 |
+
"grad_norm": 0.2521331310272217,
|
| 64 |
+
"learning_rate": 0.0009761811727013547,
|
| 65 |
+
"loss": 2.4035,
|
| 66 |
+
"step": 80
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.1651376146788991,
|
| 70 |
+
"grad_norm": 0.1716698408126831,
|
| 71 |
+
"learning_rate": 0.0009660421601067666,
|
| 72 |
+
"loss": 2.3758,
|
| 73 |
+
"step": 90
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.1834862385321101,
|
| 77 |
+
"grad_norm": 0.37161785364151,
|
| 78 |
+
"learning_rate": 0.0009541828235992926,
|
| 79 |
+
"loss": 2.3576,
|
| 80 |
+
"step": 100
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.2018348623853211,
|
| 84 |
+
"grad_norm": 0.22280354797840118,
|
| 85 |
+
"learning_rate": 0.0009406469401200151,
|
| 86 |
+
"loss": 2.3318,
|
| 87 |
+
"step": 110
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.22018348623853212,
|
| 91 |
+
"grad_norm": 0.21396410465240479,
|
| 92 |
+
"learning_rate": 0.0009254844753287492,
|
| 93 |
+
"loss": 2.3161,
|
| 94 |
+
"step": 120
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.23853211009174313,
|
| 98 |
+
"grad_norm": 0.1999460905790329,
|
| 99 |
+
"learning_rate": 0.0009087513991633924,
|
| 100 |
+
"loss": 2.2821,
|
| 101 |
+
"step": 130
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.25688073394495414,
|
| 105 |
+
"grad_norm": 0.22965525090694427,
|
| 106 |
+
"learning_rate": 0.0008905094792353917,
|
| 107 |
+
"loss": 2.2581,
|
| 108 |
+
"step": 140
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.27522935779816515,
|
| 112 |
+
"grad_norm": 0.22538428008556366,
|
| 113 |
+
"learning_rate": 0.0008708260528239789,
|
| 114 |
+
"loss": 2.2539,
|
| 115 |
+
"step": 150
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.29357798165137616,
|
| 119 |
+
"grad_norm": 0.21738778054714203,
|
| 120 |
+
"learning_rate": 0.0008497737783108237,
|
| 121 |
+
"loss": 2.2359,
|
| 122 |
+
"step": 160
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.3119266055045872,
|
| 126 |
+
"grad_norm": 0.18391013145446777,
|
| 127 |
+
"learning_rate": 0.0008274303669726426,
|
| 128 |
+
"loss": 2.2279,
|
| 129 |
+
"step": 170
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.3302752293577982,
|
| 133 |
+
"grad_norm": 0.19344037771224976,
|
| 134 |
+
"learning_rate": 0.0008038782961218137,
|
| 135 |
+
"loss": 2.22,
|
| 136 |
+
"step": 180
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.3486238532110092,
|
| 140 |
+
"grad_norm": 0.22577537596225739,
|
| 141 |
+
"learning_rate": 0.000779204504653894,
|
| 142 |
+
"loss": 2.2103,
|
| 143 |
+
"step": 190
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.3669724770642202,
|
| 147 |
+
"grad_norm": 0.18456725776195526,
|
| 148 |
+
"learning_rate": 0.0007535000721258791,
|
| 149 |
+
"loss": 2.1912,
|
| 150 |
+
"step": 200
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.3853211009174312,
|
| 154 |
+
"grad_norm": 0.1932714283466339,
|
| 155 |
+
"learning_rate": 0.00072685988254984,
|
| 156 |
+
"loss": 2.1867,
|
| 157 |
+
"step": 210
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.4036697247706422,
|
| 161 |
+
"grad_norm": 0.17227360606193542,
|
| 162 |
+
"learning_rate": 0.0006993822741429906,
|
| 163 |
+
"loss": 2.1934,
|
| 164 |
+
"step": 220
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.42201834862385323,
|
| 168 |
+
"grad_norm": 0.18149027228355408,
|
| 169 |
+
"learning_rate": 0.0006711686763270818,
|
| 170 |
+
"loss": 2.1854,
|
| 171 |
+
"step": 230
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.44036697247706424,
|
| 175 |
+
"grad_norm": 0.2078525274991989,
|
| 176 |
+
"learning_rate": 0.0006423232353170831,
|
| 177 |
+
"loss": 2.1797,
|
| 178 |
+
"step": 240
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.45871559633027525,
|
| 182 |
+
"grad_norm": 0.18958960473537445,
|
| 183 |
+
"learning_rate": 0.0006129524296812335,
|
| 184 |
+
"loss": 2.1772,
|
| 185 |
+
"step": 250
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.47706422018348627,
|
| 189 |
+
"grad_norm": 0.19692903757095337,
|
| 190 |
+
"learning_rate": 0.0005831646772915651,
|
| 191 |
+
"loss": 2.1818,
|
| 192 |
+
"step": 260
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.4954128440366973,
|
| 196 |
+
"grad_norm": 0.1741868555545807,
|
| 197 |
+
"learning_rate": 0.0005530699351157809,
|
| 198 |
+
"loss": 2.1646,
|
| 199 |
+
"step": 270
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.5137614678899083,
|
| 203 |
+
"grad_norm": 0.18339940905570984,
|
| 204 |
+
"learning_rate": 0.0005227792933277943,
|
| 205 |
+
"loss": 2.1693,
|
| 206 |
+
"step": 280
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.5321100917431193,
|
| 210 |
+
"grad_norm": 0.16860347986221313,
|
| 211 |
+
"learning_rate": 0.0004924045652352092,
|
| 212 |
+
"loss": 2.1564,
|
| 213 |
+
"step": 290
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.5504587155963303,
|
| 217 |
+
"grad_norm": 0.1536913514137268,
|
| 218 |
+
"learning_rate": 0.0004620578745374633,
|
| 219 |
+
"loss": 2.156,
|
| 220 |
+
"step": 300
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.5688073394495413,
|
| 224 |
+
"grad_norm": 0.20742546021938324,
|
| 225 |
+
"learning_rate": 0.0004318512414382059,
|
| 226 |
+
"loss": 2.1629,
|
| 227 |
+
"step": 310
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.5871559633027523,
|
| 231 |
+
"grad_norm": 0.17380154132843018,
|
| 232 |
+
"learning_rate": 0.0004018961691397148,
|
| 233 |
+
"loss": 2.1595,
|
| 234 |
+
"step": 320
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.6055045871559633,
|
| 238 |
+
"grad_norm": 0.1888326108455658,
|
| 239 |
+
"learning_rate": 0.0003723032322457458,
|
| 240 |
+
"loss": 2.1465,
|
| 241 |
+
"step": 330
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.6238532110091743,
|
| 245 |
+
"grad_norm": 0.21494585275650024,
|
| 246 |
+
"learning_rate": 0.0003431816685921625,
|
| 247 |
+
"loss": 2.1498,
|
| 248 |
+
"step": 340
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.6422018348623854,
|
| 252 |
+
"grad_norm": 0.20209936797618866,
|
| 253 |
+
"learning_rate": 0.0003146389760120416,
|
| 254 |
+
"loss": 2.1506,
|
| 255 |
+
"step": 350
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.6605504587155964,
|
| 259 |
+
"grad_norm": 0.18656006455421448,
|
| 260 |
+
"learning_rate": 0.00028678051552373485,
|
| 261 |
+
"loss": 2.1498,
|
| 262 |
+
"step": 360
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.6788990825688074,
|
| 266 |
+
"grad_norm": 0.16458649933338165,
|
| 267 |
+
"learning_rate": 0.0002597091224066581,
|
| 268 |
+
"loss": 2.1452,
|
| 269 |
+
"step": 370
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.6972477064220184,
|
| 273 |
+
"grad_norm": 0.18654096126556396,
|
| 274 |
+
"learning_rate": 0.0002335247266004629,
|
| 275 |
+
"loss": 2.1491,
|
| 276 |
+
"step": 380
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.7155963302752294,
|
| 280 |
+
"grad_norm": 0.1675863116979599,
|
| 281 |
+
"learning_rate": 0.000208323983828828,
|
| 282 |
+
"loss": 2.1397,
|
| 283 |
+
"step": 390
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.7339449541284404,
|
| 287 |
+
"grad_norm": 0.15999102592468262,
|
| 288 |
+
"learning_rate": 0.0001841999188095224,
|
| 289 |
+
"loss": 2.1355,
|
| 290 |
+
"step": 400
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.7522935779816514,
|
| 294 |
+
"grad_norm": 0.17091910541057587,
|
| 295 |
+
"learning_rate": 0.00016124158186777676,
|
| 296 |
+
"loss": 2.1409,
|
| 297 |
+
"step": 410
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.7706422018348624,
|
| 301 |
+
"grad_norm": 0.17112447321414948,
|
| 302 |
+
"learning_rate": 0.0001395337202205211,
|
| 303 |
+
"loss": 2.1373,
|
| 304 |
+
"step": 420
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.7889908256880734,
|
| 308 |
+
"grad_norm": 0.1577204465866089,
|
| 309 |
+
"learning_rate": 0.00011915646514489292,
|
| 310 |
+
"loss": 2.1358,
|
| 311 |
+
"step": 430
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.8073394495412844,
|
| 315 |
+
"grad_norm": 0.18160150945186615,
|
| 316 |
+
"learning_rate": 0.00010018503618578818,
|
| 317 |
+
"loss": 2.1382,
|
| 318 |
+
"step": 440
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.8256880733944955,
|
| 322 |
+
"grad_norm": 0.16557665169239044,
|
| 323 |
+
"learning_rate": 8.268946349432583e-05,
|
| 324 |
+
"loss": 2.1373,
|
| 325 |
+
"step": 450
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.8440366972477065,
|
| 329 |
+
"grad_norm": 0.15993128716945648,
|
| 330 |
+
"learning_rate": 6.673432932217117e-05,
|
| 331 |
+
"loss": 2.1261,
|
| 332 |
+
"step": 460
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.8623853211009175,
|
| 336 |
+
"grad_norm": 0.16715052723884583,
|
| 337 |
+
"learning_rate": 5.2378529625954684e-05,
|
| 338 |
+
"loss": 2.1231,
|
| 339 |
+
"step": 470
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.8807339449541285,
|
| 343 |
+
"grad_norm": 0.15836168825626373,
|
| 344 |
+
"learning_rate": 3.9675056661785556e-05,
|
| 345 |
+
"loss": 2.1255,
|
| 346 |
+
"step": 480
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.8990825688073395,
|
| 350 |
+
"grad_norm": 0.155441015958786,
|
| 351 |
+
"learning_rate": 2.8670803372379538e-05,
|
| 352 |
+
"loss": 2.1347,
|
| 353 |
+
"step": 490
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.9174311926605505,
|
| 357 |
+
"grad_norm": 0.1650736927986145,
|
| 358 |
+
"learning_rate": 1.9406390288876586e-05,
|
| 359 |
+
"loss": 2.1358,
|
| 360 |
+
"step": 500
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.9357798165137615,
|
| 364 |
+
"grad_norm": 0.16247880458831787,
|
| 365 |
+
"learning_rate": 1.191601558631461e-05,
|
| 366 |
+
"loss": 2.1262,
|
| 367 |
+
"step": 510
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.9541284403669725,
|
| 371 |
+
"grad_norm": 0.15282952785491943,
|
| 372 |
+
"learning_rate": 6.2273288462559305e-06,
|
| 373 |
+
"loss": 2.1215,
|
| 374 |
+
"step": 520
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.9724770642201835,
|
| 378 |
+
"grad_norm": 0.15444834530353546,
|
| 379 |
+
"learning_rate": 2.361328992552314e-06,
|
| 380 |
+
"loss": 2.1238,
|
| 381 |
+
"step": 530
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.9908256880733946,
|
| 385 |
+
"grad_norm": 0.16046886146068573,
|
| 386 |
+
"learning_rate": 3.322867770044202e-07,
|
| 387 |
+
"loss": 2.1244,
|
| 388 |
+
"step": 540
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 1.0,
|
| 392 |
+
"step": 545,
|
| 393 |
+
"total_flos": 3.7018051494386074e+17,
|
| 394 |
+
"train_loss": 2.255735644069287,
|
| 395 |
+
"train_runtime": 1361.7669,
|
| 396 |
+
"train_samples_per_second": 409.856,
|
| 397 |
+
"train_steps_per_second": 0.4
|
| 398 |
+
}
|
| 399 |
+
],
|
| 400 |
+
"logging_steps": 10,
|
| 401 |
+
"max_steps": 545,
|
| 402 |
+
"num_input_tokens_seen": 36058112,
|
| 403 |
+
"num_train_epochs": 1,
|
| 404 |
+
"save_steps": 500,
|
| 405 |
+
"stateful_callbacks": {
|
| 406 |
+
"TrainerControl": {
|
| 407 |
+
"args": {
|
| 408 |
+
"should_epoch_stop": false,
|
| 409 |
+
"should_evaluate": false,
|
| 410 |
+
"should_log": false,
|
| 411 |
+
"should_save": false,
|
| 412 |
+
"should_training_stop": false
|
| 413 |
+
},
|
| 414 |
+
"attributes": {}
|
| 415 |
+
}
|
| 416 |
+
},
|
| 417 |
+
"total_flos": 3.7018051494386074e+17,
|
| 418 |
+
"train_batch_size": 128,
|
| 419 |
+
"trial_name": null,
|
| 420 |
+
"trial_params": null
|
| 421 |
+
}
|
continuous/smollm2/siglip2_g16_256/finetune/chat_template.jinja
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system
|
| 2 |
+
You are a helpful AI assistant named SmolLM, trained by Hugging Face<|im_end|>
|
| 3 |
+
' }}{% endif %}{{'<|im_start|>' + message['role'] + '
|
| 4 |
+
' + message['content'] + '<|im_end|>' + '
|
| 5 |
+
'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
|
| 6 |
+
' }}{% endif %}
|
continuous/smollm2/siglip2_g16_256/finetune/config.json
ADDED
|
@@ -0,0 +1,70 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_faster_video": false,
|
| 3 |
+
"add_time_instruction": false,
|
| 4 |
+
"architectures": [
|
| 5 |
+
"LlavaLlamaForCausalLM"
|
| 6 |
+
],
|
| 7 |
+
"attention_bias": false,
|
| 8 |
+
"attention_dropout": 0.0,
|
| 9 |
+
"bos_token_id": 1,
|
| 10 |
+
"dtype": "bfloat16",
|
| 11 |
+
"eos_token_id": 2,
|
| 12 |
+
"faster_token_stride": 10,
|
| 13 |
+
"force_sample": false,
|
| 14 |
+
"head_dim": 64,
|
| 15 |
+
"hidden_act": "silu",
|
| 16 |
+
"hidden_size": 2048,
|
| 17 |
+
"image_aspect_ratio": "square",
|
| 18 |
+
"image_crop_resolution": null,
|
| 19 |
+
"image_grid_pinpoints": null,
|
| 20 |
+
"image_split_resolution": null,
|
| 21 |
+
"initializer_range": 0.02,
|
| 22 |
+
"intermediate_size": 8192,
|
| 23 |
+
"max_position_embeddings": 8192,
|
| 24 |
+
"mlp_bias": false,
|
| 25 |
+
"mm_hidden_size": 1536,
|
| 26 |
+
"mm_newline_position": "grid",
|
| 27 |
+
"mm_patch_merge_type": "flat",
|
| 28 |
+
"mm_projector_lr": 0.0001,
|
| 29 |
+
"mm_projector_type": "mlp2x_gelu",
|
| 30 |
+
"mm_resampler_type": null,
|
| 31 |
+
"mm_spatial_pool_mode": "bilinear",
|
| 32 |
+
"mm_spatial_pool_stride": null,
|
| 33 |
+
"mm_tunable_parts": "mm_mlp_adapter,mm_language_model",
|
| 34 |
+
"mm_use_im_patch_token": false,
|
| 35 |
+
"mm_use_im_start_end": false,
|
| 36 |
+
"mm_vision_select_feature": "patch",
|
| 37 |
+
"mm_vision_select_layer": -2,
|
| 38 |
+
"mm_vision_tower": "open_clip_hub:ViT-gopt-16-SigLIP2-256",
|
| 39 |
+
"mm_vision_tower_lr": null,
|
| 40 |
+
"model_type": "llama",
|
| 41 |
+
"num_attention_heads": 32,
|
| 42 |
+
"num_hidden_layers": 24,
|
| 43 |
+
"num_key_value_heads": 32,
|
| 44 |
+
"pad_token_id": 0,
|
| 45 |
+
"pos_skipping_range": 4096,
|
| 46 |
+
"pretraining_tp": 1,
|
| 47 |
+
"rms_norm_eps": 1e-05,
|
| 48 |
+
"rope_scaling": null,
|
| 49 |
+
"rope_theta": 130000,
|
| 50 |
+
"tie_word_embeddings": true,
|
| 51 |
+
"tokenizer_model_max_length": 8192,
|
| 52 |
+
"tokenizer_padding_side": "right",
|
| 53 |
+
"transformers.js_config": {
|
| 54 |
+
"dtype": "q4",
|
| 55 |
+
"kv_cache_dtype": {
|
| 56 |
+
"fp16": "float16",
|
| 57 |
+
"q4f16": "float16"
|
| 58 |
+
},
|
| 59 |
+
"use_external_data_format": {
|
| 60 |
+
"model.onnx": true,
|
| 61 |
+
"model_fp16.onnx": true
|
| 62 |
+
}
|
| 63 |
+
},
|
| 64 |
+
"transformers_version": "4.57.6",
|
| 65 |
+
"use_cache": true,
|
| 66 |
+
"use_mm_proj": true,
|
| 67 |
+
"use_pos_skipping": false,
|
| 68 |
+
"vision_tower_pretrained": "/cache/ckpt/download/tokenizer/continuous/siglip2/siglip2_g16_256.npz",
|
| 69 |
+
"vocab_size": 49152
|
| 70 |
+
}
|
continuous/smollm2/siglip2_g16_256/finetune/generation_config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 1,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
2
|
| 6 |
+
],
|
| 7 |
+
"pad_token_id": 0,
|
| 8 |
+
"transformers_version": "4.57.6"
|
| 9 |
+
}
|
continuous/smollm2/siglip2_g16_256/finetune/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
continuous/smollm2/siglip2_g16_256/finetune/model-00001-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:868f6c3e894fee2ee2546069f573eafd9649d5b82c4939809ecd176ca35f9f62
|
| 3 |
+
size 4993660304
|
continuous/smollm2/siglip2_g16_256/finetune/model-00002-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:91bf14714131201a0be1fb055bd036aa807952c4cb44e9f5082a8758c27deafd
|
| 3 |
+
size 986225240
|
continuous/smollm2/siglip2_g16_256/finetune/model.safetensors.index.json
ADDED
|
@@ -0,0 +1,729 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_parameters": 2881888768,
|
| 4 |
+
"total_size": 5979792384
|
| 5 |
+
},
|
| 6 |
+
"weight_map": {
|
| 7 |
+
"lm_head.weight": "model-00002-of-00002.safetensors",
|
| 8 |
+
"model.embed_tokens.weight": "model-00001-of-00002.safetensors",
|
| 9 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 10 |
+
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 11 |
+
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 12 |
+
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 13 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 14 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 15 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 16 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 17 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 18 |
+
"model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 19 |
+
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 20 |
+
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 21 |
+
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 22 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 23 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 24 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 25 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 26 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 27 |
+
"model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 28 |
+
"model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 29 |
+
"model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 30 |
+
"model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 31 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 32 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 33 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 34 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 35 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 36 |
+
"model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 37 |
+
"model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 38 |
+
"model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 39 |
+
"model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 40 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 41 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 42 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 43 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 44 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 45 |
+
"model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 46 |
+
"model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 47 |
+
"model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 48 |
+
"model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 49 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 50 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 51 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 52 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 53 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 54 |
+
"model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 55 |
+
"model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 56 |
+
"model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 57 |
+
"model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 58 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 59 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 60 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 61 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 62 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 63 |
+
"model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 64 |
+
"model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 65 |
+
"model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 66 |
+
"model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 67 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 68 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 69 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 70 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 71 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 72 |
+
"model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 73 |
+
"model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 74 |
+
"model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 75 |
+
"model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 76 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 77 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 78 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 79 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 80 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 81 |
+
"model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 82 |
+
"model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 83 |
+
"model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 84 |
+
"model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 85 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 86 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 87 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 88 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 89 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 90 |
+
"model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 91 |
+
"model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 92 |
+
"model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 93 |
+
"model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 94 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 95 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 96 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 97 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 98 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 99 |
+
"model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 100 |
+
"model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 101 |
+
"model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 102 |
+
"model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 103 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 104 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 105 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 106 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 107 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 108 |
+
"model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 109 |
+
"model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 110 |
+
"model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 111 |
+
"model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 112 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 113 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 114 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 115 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 116 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 117 |
+
"model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 118 |
+
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 119 |
+
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 120 |
+
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 121 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 122 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 123 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 124 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 125 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 126 |
+
"model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 127 |
+
"model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 128 |
+
"model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 129 |
+
"model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 130 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 131 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 132 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 133 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 134 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 135 |
+
"model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 136 |
+
"model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 137 |
+
"model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 138 |
+
"model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 139 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 140 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 141 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 142 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 143 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 144 |
+
"model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 145 |
+
"model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 146 |
+
"model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 147 |
+
"model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 148 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 149 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 150 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 151 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 152 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 153 |
+
"model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 154 |
+
"model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 155 |
+
"model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 156 |
+
"model.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 157 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 158 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 159 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 160 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 161 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 162 |
+
"model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 163 |
+
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 164 |
+
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 165 |
+
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 166 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 167 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 168 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 169 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 170 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 171 |
+
"model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 172 |
+
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 173 |
+
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 174 |
+
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 175 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 176 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 177 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 178 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 179 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 180 |
+
"model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 181 |
+
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 182 |
+
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 183 |
+
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 184 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 185 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 186 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 187 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 188 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 189 |
+
"model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 190 |
+
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 191 |
+
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 192 |
+
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 193 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 194 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 195 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 196 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 197 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 198 |
+
"model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 199 |
+
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 200 |
+
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 201 |
+
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 202 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 203 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 204 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 205 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 206 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 207 |
+
"model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 208 |
+
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 209 |
+
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 210 |
+
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 211 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 212 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 213 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 214 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 215 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 216 |
+
"model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 217 |
+
"model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 218 |
+
"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 219 |
+
"model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 220 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 221 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 222 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 223 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 224 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 225 |
+
"model.mm_projector.0.bias": "model-00002-of-00002.safetensors",
|
| 226 |
+
"model.mm_projector.0.weight": "model-00002-of-00002.safetensors",
|
| 227 |
+
"model.mm_projector.2.bias": "model-00002-of-00002.safetensors",
|
| 228 |
+
"model.mm_projector.2.weight": "model-00002-of-00002.safetensors",
|
| 229 |
+
"model.norm.weight": "model-00001-of-00002.safetensors",
|
| 230 |
+
"model.vision_tower.vision_tower.trunk.attn_pool.kv.bias": "model-00002-of-00002.safetensors",
|
| 231 |
+
"model.vision_tower.vision_tower.trunk.attn_pool.kv.weight": "model-00002-of-00002.safetensors",
|
| 232 |
+
"model.vision_tower.vision_tower.trunk.attn_pool.latent": "model-00002-of-00002.safetensors",
|
| 233 |
+
"model.vision_tower.vision_tower.trunk.attn_pool.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
| 234 |
+
"model.vision_tower.vision_tower.trunk.attn_pool.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
| 235 |
+
"model.vision_tower.vision_tower.trunk.attn_pool.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
| 236 |
+
"model.vision_tower.vision_tower.trunk.attn_pool.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
| 237 |
+
"model.vision_tower.vision_tower.trunk.attn_pool.norm.bias": "model-00002-of-00002.safetensors",
|
| 238 |
+
"model.vision_tower.vision_tower.trunk.attn_pool.norm.weight": "model-00002-of-00002.safetensors",
|
| 239 |
+
"model.vision_tower.vision_tower.trunk.attn_pool.proj.bias": "model-00002-of-00002.safetensors",
|
| 240 |
+
"model.vision_tower.vision_tower.trunk.attn_pool.proj.weight": "model-00002-of-00002.safetensors",
|
| 241 |
+
"model.vision_tower.vision_tower.trunk.attn_pool.q.bias": "model-00002-of-00002.safetensors",
|
| 242 |
+
"model.vision_tower.vision_tower.trunk.attn_pool.q.weight": "model-00002-of-00002.safetensors",
|
| 243 |
+
"model.vision_tower.vision_tower.trunk.blocks.0.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 244 |
+
"model.vision_tower.vision_tower.trunk.blocks.0.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 245 |
+
"model.vision_tower.vision_tower.trunk.blocks.0.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 246 |
+
"model.vision_tower.vision_tower.trunk.blocks.0.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 247 |
+
"model.vision_tower.vision_tower.trunk.blocks.0.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 248 |
+
"model.vision_tower.vision_tower.trunk.blocks.0.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 249 |
+
"model.vision_tower.vision_tower.trunk.blocks.0.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 250 |
+
"model.vision_tower.vision_tower.trunk.blocks.0.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 251 |
+
"model.vision_tower.vision_tower.trunk.blocks.0.norm1.bias": "model-00001-of-00002.safetensors",
|
| 252 |
+
"model.vision_tower.vision_tower.trunk.blocks.0.norm1.weight": "model-00001-of-00002.safetensors",
|
| 253 |
+
"model.vision_tower.vision_tower.trunk.blocks.0.norm2.bias": "model-00001-of-00002.safetensors",
|
| 254 |
+
"model.vision_tower.vision_tower.trunk.blocks.0.norm2.weight": "model-00001-of-00002.safetensors",
|
| 255 |
+
"model.vision_tower.vision_tower.trunk.blocks.1.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 256 |
+
"model.vision_tower.vision_tower.trunk.blocks.1.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 257 |
+
"model.vision_tower.vision_tower.trunk.blocks.1.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 258 |
+
"model.vision_tower.vision_tower.trunk.blocks.1.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 259 |
+
"model.vision_tower.vision_tower.trunk.blocks.1.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 260 |
+
"model.vision_tower.vision_tower.trunk.blocks.1.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 261 |
+
"model.vision_tower.vision_tower.trunk.blocks.1.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 262 |
+
"model.vision_tower.vision_tower.trunk.blocks.1.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 263 |
+
"model.vision_tower.vision_tower.trunk.blocks.1.norm1.bias": "model-00001-of-00002.safetensors",
|
| 264 |
+
"model.vision_tower.vision_tower.trunk.blocks.1.norm1.weight": "model-00001-of-00002.safetensors",
|
| 265 |
+
"model.vision_tower.vision_tower.trunk.blocks.1.norm2.bias": "model-00001-of-00002.safetensors",
|
| 266 |
+
"model.vision_tower.vision_tower.trunk.blocks.1.norm2.weight": "model-00001-of-00002.safetensors",
|
| 267 |
+
"model.vision_tower.vision_tower.trunk.blocks.10.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 268 |
+
"model.vision_tower.vision_tower.trunk.blocks.10.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 269 |
+
"model.vision_tower.vision_tower.trunk.blocks.10.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 270 |
+
"model.vision_tower.vision_tower.trunk.blocks.10.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 271 |
+
"model.vision_tower.vision_tower.trunk.blocks.10.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 272 |
+
"model.vision_tower.vision_tower.trunk.blocks.10.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 273 |
+
"model.vision_tower.vision_tower.trunk.blocks.10.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 274 |
+
"model.vision_tower.vision_tower.trunk.blocks.10.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 275 |
+
"model.vision_tower.vision_tower.trunk.blocks.10.norm1.bias": "model-00001-of-00002.safetensors",
|
| 276 |
+
"model.vision_tower.vision_tower.trunk.blocks.10.norm1.weight": "model-00001-of-00002.safetensors",
|
| 277 |
+
"model.vision_tower.vision_tower.trunk.blocks.10.norm2.bias": "model-00001-of-00002.safetensors",
|
| 278 |
+
"model.vision_tower.vision_tower.trunk.blocks.10.norm2.weight": "model-00001-of-00002.safetensors",
|
| 279 |
+
"model.vision_tower.vision_tower.trunk.blocks.11.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 280 |
+
"model.vision_tower.vision_tower.trunk.blocks.11.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 281 |
+
"model.vision_tower.vision_tower.trunk.blocks.11.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 282 |
+
"model.vision_tower.vision_tower.trunk.blocks.11.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 283 |
+
"model.vision_tower.vision_tower.trunk.blocks.11.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 284 |
+
"model.vision_tower.vision_tower.trunk.blocks.11.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 285 |
+
"model.vision_tower.vision_tower.trunk.blocks.11.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 286 |
+
"model.vision_tower.vision_tower.trunk.blocks.11.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 287 |
+
"model.vision_tower.vision_tower.trunk.blocks.11.norm1.bias": "model-00001-of-00002.safetensors",
|
| 288 |
+
"model.vision_tower.vision_tower.trunk.blocks.11.norm1.weight": "model-00001-of-00002.safetensors",
|
| 289 |
+
"model.vision_tower.vision_tower.trunk.blocks.11.norm2.bias": "model-00001-of-00002.safetensors",
|
| 290 |
+
"model.vision_tower.vision_tower.trunk.blocks.11.norm2.weight": "model-00001-of-00002.safetensors",
|
| 291 |
+
"model.vision_tower.vision_tower.trunk.blocks.12.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 292 |
+
"model.vision_tower.vision_tower.trunk.blocks.12.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 293 |
+
"model.vision_tower.vision_tower.trunk.blocks.12.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 294 |
+
"model.vision_tower.vision_tower.trunk.blocks.12.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 295 |
+
"model.vision_tower.vision_tower.trunk.blocks.12.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 296 |
+
"model.vision_tower.vision_tower.trunk.blocks.12.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 297 |
+
"model.vision_tower.vision_tower.trunk.blocks.12.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 298 |
+
"model.vision_tower.vision_tower.trunk.blocks.12.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 299 |
+
"model.vision_tower.vision_tower.trunk.blocks.12.norm1.bias": "model-00001-of-00002.safetensors",
|
| 300 |
+
"model.vision_tower.vision_tower.trunk.blocks.12.norm1.weight": "model-00001-of-00002.safetensors",
|
| 301 |
+
"model.vision_tower.vision_tower.trunk.blocks.12.norm2.bias": "model-00001-of-00002.safetensors",
|
| 302 |
+
"model.vision_tower.vision_tower.trunk.blocks.12.norm2.weight": "model-00001-of-00002.safetensors",
|
| 303 |
+
"model.vision_tower.vision_tower.trunk.blocks.13.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 304 |
+
"model.vision_tower.vision_tower.trunk.blocks.13.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 305 |
+
"model.vision_tower.vision_tower.trunk.blocks.13.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 306 |
+
"model.vision_tower.vision_tower.trunk.blocks.13.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 307 |
+
"model.vision_tower.vision_tower.trunk.blocks.13.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 308 |
+
"model.vision_tower.vision_tower.trunk.blocks.13.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 309 |
+
"model.vision_tower.vision_tower.trunk.blocks.13.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 310 |
+
"model.vision_tower.vision_tower.trunk.blocks.13.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 311 |
+
"model.vision_tower.vision_tower.trunk.blocks.13.norm1.bias": "model-00001-of-00002.safetensors",
|
| 312 |
+
"model.vision_tower.vision_tower.trunk.blocks.13.norm1.weight": "model-00001-of-00002.safetensors",
|
| 313 |
+
"model.vision_tower.vision_tower.trunk.blocks.13.norm2.bias": "model-00001-of-00002.safetensors",
|
| 314 |
+
"model.vision_tower.vision_tower.trunk.blocks.13.norm2.weight": "model-00001-of-00002.safetensors",
|
| 315 |
+
"model.vision_tower.vision_tower.trunk.blocks.14.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 316 |
+
"model.vision_tower.vision_tower.trunk.blocks.14.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 317 |
+
"model.vision_tower.vision_tower.trunk.blocks.14.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 318 |
+
"model.vision_tower.vision_tower.trunk.blocks.14.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 319 |
+
"model.vision_tower.vision_tower.trunk.blocks.14.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 320 |
+
"model.vision_tower.vision_tower.trunk.blocks.14.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 321 |
+
"model.vision_tower.vision_tower.trunk.blocks.14.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 322 |
+
"model.vision_tower.vision_tower.trunk.blocks.14.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 323 |
+
"model.vision_tower.vision_tower.trunk.blocks.14.norm1.bias": "model-00001-of-00002.safetensors",
|
| 324 |
+
"model.vision_tower.vision_tower.trunk.blocks.14.norm1.weight": "model-00001-of-00002.safetensors",
|
| 325 |
+
"model.vision_tower.vision_tower.trunk.blocks.14.norm2.bias": "model-00001-of-00002.safetensors",
|
| 326 |
+
"model.vision_tower.vision_tower.trunk.blocks.14.norm2.weight": "model-00001-of-00002.safetensors",
|
| 327 |
+
"model.vision_tower.vision_tower.trunk.blocks.15.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 328 |
+
"model.vision_tower.vision_tower.trunk.blocks.15.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 329 |
+
"model.vision_tower.vision_tower.trunk.blocks.15.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 330 |
+
"model.vision_tower.vision_tower.trunk.blocks.15.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 331 |
+
"model.vision_tower.vision_tower.trunk.blocks.15.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 332 |
+
"model.vision_tower.vision_tower.trunk.blocks.15.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 333 |
+
"model.vision_tower.vision_tower.trunk.blocks.15.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 334 |
+
"model.vision_tower.vision_tower.trunk.blocks.15.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 335 |
+
"model.vision_tower.vision_tower.trunk.blocks.15.norm1.bias": "model-00001-of-00002.safetensors",
|
| 336 |
+
"model.vision_tower.vision_tower.trunk.blocks.15.norm1.weight": "model-00001-of-00002.safetensors",
|
| 337 |
+
"model.vision_tower.vision_tower.trunk.blocks.15.norm2.bias": "model-00001-of-00002.safetensors",
|
| 338 |
+
"model.vision_tower.vision_tower.trunk.blocks.15.norm2.weight": "model-00001-of-00002.safetensors",
|
| 339 |
+
"model.vision_tower.vision_tower.trunk.blocks.16.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 340 |
+
"model.vision_tower.vision_tower.trunk.blocks.16.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 341 |
+
"model.vision_tower.vision_tower.trunk.blocks.16.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 342 |
+
"model.vision_tower.vision_tower.trunk.blocks.16.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 343 |
+
"model.vision_tower.vision_tower.trunk.blocks.16.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 344 |
+
"model.vision_tower.vision_tower.trunk.blocks.16.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 345 |
+
"model.vision_tower.vision_tower.trunk.blocks.16.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 346 |
+
"model.vision_tower.vision_tower.trunk.blocks.16.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 347 |
+
"model.vision_tower.vision_tower.trunk.blocks.16.norm1.bias": "model-00001-of-00002.safetensors",
|
| 348 |
+
"model.vision_tower.vision_tower.trunk.blocks.16.norm1.weight": "model-00001-of-00002.safetensors",
|
| 349 |
+
"model.vision_tower.vision_tower.trunk.blocks.16.norm2.bias": "model-00001-of-00002.safetensors",
|
| 350 |
+
"model.vision_tower.vision_tower.trunk.blocks.16.norm2.weight": "model-00001-of-00002.safetensors",
|
| 351 |
+
"model.vision_tower.vision_tower.trunk.blocks.17.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 352 |
+
"model.vision_tower.vision_tower.trunk.blocks.17.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 353 |
+
"model.vision_tower.vision_tower.trunk.blocks.17.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 354 |
+
"model.vision_tower.vision_tower.trunk.blocks.17.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 355 |
+
"model.vision_tower.vision_tower.trunk.blocks.17.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 356 |
+
"model.vision_tower.vision_tower.trunk.blocks.17.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 357 |
+
"model.vision_tower.vision_tower.trunk.blocks.17.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 358 |
+
"model.vision_tower.vision_tower.trunk.blocks.17.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 359 |
+
"model.vision_tower.vision_tower.trunk.blocks.17.norm1.bias": "model-00001-of-00002.safetensors",
|
| 360 |
+
"model.vision_tower.vision_tower.trunk.blocks.17.norm1.weight": "model-00001-of-00002.safetensors",
|
| 361 |
+
"model.vision_tower.vision_tower.trunk.blocks.17.norm2.bias": "model-00001-of-00002.safetensors",
|
| 362 |
+
"model.vision_tower.vision_tower.trunk.blocks.17.norm2.weight": "model-00001-of-00002.safetensors",
|
| 363 |
+
"model.vision_tower.vision_tower.trunk.blocks.18.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 364 |
+
"model.vision_tower.vision_tower.trunk.blocks.18.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 365 |
+
"model.vision_tower.vision_tower.trunk.blocks.18.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 366 |
+
"model.vision_tower.vision_tower.trunk.blocks.18.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 367 |
+
"model.vision_tower.vision_tower.trunk.blocks.18.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 368 |
+
"model.vision_tower.vision_tower.trunk.blocks.18.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 369 |
+
"model.vision_tower.vision_tower.trunk.blocks.18.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 370 |
+
"model.vision_tower.vision_tower.trunk.blocks.18.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 371 |
+
"model.vision_tower.vision_tower.trunk.blocks.18.norm1.bias": "model-00001-of-00002.safetensors",
|
| 372 |
+
"model.vision_tower.vision_tower.trunk.blocks.18.norm1.weight": "model-00001-of-00002.safetensors",
|
| 373 |
+
"model.vision_tower.vision_tower.trunk.blocks.18.norm2.bias": "model-00001-of-00002.safetensors",
|
| 374 |
+
"model.vision_tower.vision_tower.trunk.blocks.18.norm2.weight": "model-00001-of-00002.safetensors",
|
| 375 |
+
"model.vision_tower.vision_tower.trunk.blocks.19.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 376 |
+
"model.vision_tower.vision_tower.trunk.blocks.19.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 377 |
+
"model.vision_tower.vision_tower.trunk.blocks.19.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 378 |
+
"model.vision_tower.vision_tower.trunk.blocks.19.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 379 |
+
"model.vision_tower.vision_tower.trunk.blocks.19.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 380 |
+
"model.vision_tower.vision_tower.trunk.blocks.19.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 381 |
+
"model.vision_tower.vision_tower.trunk.blocks.19.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 382 |
+
"model.vision_tower.vision_tower.trunk.blocks.19.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 383 |
+
"model.vision_tower.vision_tower.trunk.blocks.19.norm1.bias": "model-00001-of-00002.safetensors",
|
| 384 |
+
"model.vision_tower.vision_tower.trunk.blocks.19.norm1.weight": "model-00001-of-00002.safetensors",
|
| 385 |
+
"model.vision_tower.vision_tower.trunk.blocks.19.norm2.bias": "model-00001-of-00002.safetensors",
|
| 386 |
+
"model.vision_tower.vision_tower.trunk.blocks.19.norm2.weight": "model-00001-of-00002.safetensors",
|
| 387 |
+
"model.vision_tower.vision_tower.trunk.blocks.2.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 388 |
+
"model.vision_tower.vision_tower.trunk.blocks.2.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 389 |
+
"model.vision_tower.vision_tower.trunk.blocks.2.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 390 |
+
"model.vision_tower.vision_tower.trunk.blocks.2.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 391 |
+
"model.vision_tower.vision_tower.trunk.blocks.2.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 392 |
+
"model.vision_tower.vision_tower.trunk.blocks.2.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 393 |
+
"model.vision_tower.vision_tower.trunk.blocks.2.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 394 |
+
"model.vision_tower.vision_tower.trunk.blocks.2.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 395 |
+
"model.vision_tower.vision_tower.trunk.blocks.2.norm1.bias": "model-00001-of-00002.safetensors",
|
| 396 |
+
"model.vision_tower.vision_tower.trunk.blocks.2.norm1.weight": "model-00001-of-00002.safetensors",
|
| 397 |
+
"model.vision_tower.vision_tower.trunk.blocks.2.norm2.bias": "model-00001-of-00002.safetensors",
|
| 398 |
+
"model.vision_tower.vision_tower.trunk.blocks.2.norm2.weight": "model-00001-of-00002.safetensors",
|
| 399 |
+
"model.vision_tower.vision_tower.trunk.blocks.20.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 400 |
+
"model.vision_tower.vision_tower.trunk.blocks.20.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 401 |
+
"model.vision_tower.vision_tower.trunk.blocks.20.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 402 |
+
"model.vision_tower.vision_tower.trunk.blocks.20.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 403 |
+
"model.vision_tower.vision_tower.trunk.blocks.20.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 404 |
+
"model.vision_tower.vision_tower.trunk.blocks.20.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 405 |
+
"model.vision_tower.vision_tower.trunk.blocks.20.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 406 |
+
"model.vision_tower.vision_tower.trunk.blocks.20.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 407 |
+
"model.vision_tower.vision_tower.trunk.blocks.20.norm1.bias": "model-00001-of-00002.safetensors",
|
| 408 |
+
"model.vision_tower.vision_tower.trunk.blocks.20.norm1.weight": "model-00001-of-00002.safetensors",
|
| 409 |
+
"model.vision_tower.vision_tower.trunk.blocks.20.norm2.bias": "model-00001-of-00002.safetensors",
|
| 410 |
+
"model.vision_tower.vision_tower.trunk.blocks.20.norm2.weight": "model-00001-of-00002.safetensors",
|
| 411 |
+
"model.vision_tower.vision_tower.trunk.blocks.21.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 412 |
+
"model.vision_tower.vision_tower.trunk.blocks.21.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 413 |
+
"model.vision_tower.vision_tower.trunk.blocks.21.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 414 |
+
"model.vision_tower.vision_tower.trunk.blocks.21.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 415 |
+
"model.vision_tower.vision_tower.trunk.blocks.21.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 416 |
+
"model.vision_tower.vision_tower.trunk.blocks.21.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 417 |
+
"model.vision_tower.vision_tower.trunk.blocks.21.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 418 |
+
"model.vision_tower.vision_tower.trunk.blocks.21.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 419 |
+
"model.vision_tower.vision_tower.trunk.blocks.21.norm1.bias": "model-00001-of-00002.safetensors",
|
| 420 |
+
"model.vision_tower.vision_tower.trunk.blocks.21.norm1.weight": "model-00001-of-00002.safetensors",
|
| 421 |
+
"model.vision_tower.vision_tower.trunk.blocks.21.norm2.bias": "model-00001-of-00002.safetensors",
|
| 422 |
+
"model.vision_tower.vision_tower.trunk.blocks.21.norm2.weight": "model-00001-of-00002.safetensors",
|
| 423 |
+
"model.vision_tower.vision_tower.trunk.blocks.22.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 424 |
+
"model.vision_tower.vision_tower.trunk.blocks.22.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 425 |
+
"model.vision_tower.vision_tower.trunk.blocks.22.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 426 |
+
"model.vision_tower.vision_tower.trunk.blocks.22.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 427 |
+
"model.vision_tower.vision_tower.trunk.blocks.22.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 428 |
+
"model.vision_tower.vision_tower.trunk.blocks.22.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 429 |
+
"model.vision_tower.vision_tower.trunk.blocks.22.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 430 |
+
"model.vision_tower.vision_tower.trunk.blocks.22.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 431 |
+
"model.vision_tower.vision_tower.trunk.blocks.22.norm1.bias": "model-00001-of-00002.safetensors",
|
| 432 |
+
"model.vision_tower.vision_tower.trunk.blocks.22.norm1.weight": "model-00001-of-00002.safetensors",
|
| 433 |
+
"model.vision_tower.vision_tower.trunk.blocks.22.norm2.bias": "model-00001-of-00002.safetensors",
|
| 434 |
+
"model.vision_tower.vision_tower.trunk.blocks.22.norm2.weight": "model-00001-of-00002.safetensors",
|
| 435 |
+
"model.vision_tower.vision_tower.trunk.blocks.23.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 436 |
+
"model.vision_tower.vision_tower.trunk.blocks.23.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 437 |
+
"model.vision_tower.vision_tower.trunk.blocks.23.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 438 |
+
"model.vision_tower.vision_tower.trunk.blocks.23.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 439 |
+
"model.vision_tower.vision_tower.trunk.blocks.23.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 440 |
+
"model.vision_tower.vision_tower.trunk.blocks.23.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 441 |
+
"model.vision_tower.vision_tower.trunk.blocks.23.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 442 |
+
"model.vision_tower.vision_tower.trunk.blocks.23.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 443 |
+
"model.vision_tower.vision_tower.trunk.blocks.23.norm1.bias": "model-00001-of-00002.safetensors",
|
| 444 |
+
"model.vision_tower.vision_tower.trunk.blocks.23.norm1.weight": "model-00001-of-00002.safetensors",
|
| 445 |
+
"model.vision_tower.vision_tower.trunk.blocks.23.norm2.bias": "model-00001-of-00002.safetensors",
|
| 446 |
+
"model.vision_tower.vision_tower.trunk.blocks.23.norm2.weight": "model-00001-of-00002.safetensors",
|
| 447 |
+
"model.vision_tower.vision_tower.trunk.blocks.24.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 448 |
+
"model.vision_tower.vision_tower.trunk.blocks.24.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 449 |
+
"model.vision_tower.vision_tower.trunk.blocks.24.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 450 |
+
"model.vision_tower.vision_tower.trunk.blocks.24.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 451 |
+
"model.vision_tower.vision_tower.trunk.blocks.24.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 452 |
+
"model.vision_tower.vision_tower.trunk.blocks.24.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 453 |
+
"model.vision_tower.vision_tower.trunk.blocks.24.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 454 |
+
"model.vision_tower.vision_tower.trunk.blocks.24.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 455 |
+
"model.vision_tower.vision_tower.trunk.blocks.24.norm1.bias": "model-00001-of-00002.safetensors",
|
| 456 |
+
"model.vision_tower.vision_tower.trunk.blocks.24.norm1.weight": "model-00001-of-00002.safetensors",
|
| 457 |
+
"model.vision_tower.vision_tower.trunk.blocks.24.norm2.bias": "model-00001-of-00002.safetensors",
|
| 458 |
+
"model.vision_tower.vision_tower.trunk.blocks.24.norm2.weight": "model-00001-of-00002.safetensors",
|
| 459 |
+
"model.vision_tower.vision_tower.trunk.blocks.25.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 460 |
+
"model.vision_tower.vision_tower.trunk.blocks.25.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 461 |
+
"model.vision_tower.vision_tower.trunk.blocks.25.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 462 |
+
"model.vision_tower.vision_tower.trunk.blocks.25.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 463 |
+
"model.vision_tower.vision_tower.trunk.blocks.25.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 464 |
+
"model.vision_tower.vision_tower.trunk.blocks.25.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 465 |
+
"model.vision_tower.vision_tower.trunk.blocks.25.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 466 |
+
"model.vision_tower.vision_tower.trunk.blocks.25.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 467 |
+
"model.vision_tower.vision_tower.trunk.blocks.25.norm1.bias": "model-00001-of-00002.safetensors",
|
| 468 |
+
"model.vision_tower.vision_tower.trunk.blocks.25.norm1.weight": "model-00001-of-00002.safetensors",
|
| 469 |
+
"model.vision_tower.vision_tower.trunk.blocks.25.norm2.bias": "model-00001-of-00002.safetensors",
|
| 470 |
+
"model.vision_tower.vision_tower.trunk.blocks.25.norm2.weight": "model-00001-of-00002.safetensors",
|
| 471 |
+
"model.vision_tower.vision_tower.trunk.blocks.26.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 472 |
+
"model.vision_tower.vision_tower.trunk.blocks.26.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 473 |
+
"model.vision_tower.vision_tower.trunk.blocks.26.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 474 |
+
"model.vision_tower.vision_tower.trunk.blocks.26.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 475 |
+
"model.vision_tower.vision_tower.trunk.blocks.26.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 476 |
+
"model.vision_tower.vision_tower.trunk.blocks.26.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 477 |
+
"model.vision_tower.vision_tower.trunk.blocks.26.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 478 |
+
"model.vision_tower.vision_tower.trunk.blocks.26.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 479 |
+
"model.vision_tower.vision_tower.trunk.blocks.26.norm1.bias": "model-00001-of-00002.safetensors",
|
| 480 |
+
"model.vision_tower.vision_tower.trunk.blocks.26.norm1.weight": "model-00001-of-00002.safetensors",
|
| 481 |
+
"model.vision_tower.vision_tower.trunk.blocks.26.norm2.bias": "model-00001-of-00002.safetensors",
|
| 482 |
+
"model.vision_tower.vision_tower.trunk.blocks.26.norm2.weight": "model-00001-of-00002.safetensors",
|
| 483 |
+
"model.vision_tower.vision_tower.trunk.blocks.27.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 484 |
+
"model.vision_tower.vision_tower.trunk.blocks.27.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 485 |
+
"model.vision_tower.vision_tower.trunk.blocks.27.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 486 |
+
"model.vision_tower.vision_tower.trunk.blocks.27.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 487 |
+
"model.vision_tower.vision_tower.trunk.blocks.27.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 488 |
+
"model.vision_tower.vision_tower.trunk.blocks.27.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 489 |
+
"model.vision_tower.vision_tower.trunk.blocks.27.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
| 490 |
+
"model.vision_tower.vision_tower.trunk.blocks.27.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
| 491 |
+
"model.vision_tower.vision_tower.trunk.blocks.27.norm1.bias": "model-00001-of-00002.safetensors",
|
| 492 |
+
"model.vision_tower.vision_tower.trunk.blocks.27.norm1.weight": "model-00001-of-00002.safetensors",
|
| 493 |
+
"model.vision_tower.vision_tower.trunk.blocks.27.norm2.bias": "model-00001-of-00002.safetensors",
|
| 494 |
+
"model.vision_tower.vision_tower.trunk.blocks.27.norm2.weight": "model-00001-of-00002.safetensors",
|
| 495 |
+
"model.vision_tower.vision_tower.trunk.blocks.28.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 496 |
+
"model.vision_tower.vision_tower.trunk.blocks.28.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 497 |
+
"model.vision_tower.vision_tower.trunk.blocks.28.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 498 |
+
"model.vision_tower.vision_tower.trunk.blocks.28.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 499 |
+
"model.vision_tower.vision_tower.trunk.blocks.28.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
| 500 |
+
"model.vision_tower.vision_tower.trunk.blocks.28.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
| 501 |
+
"model.vision_tower.vision_tower.trunk.blocks.28.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
| 502 |
+
"model.vision_tower.vision_tower.trunk.blocks.28.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
| 503 |
+
"model.vision_tower.vision_tower.trunk.blocks.28.norm1.bias": "model-00002-of-00002.safetensors",
|
| 504 |
+
"model.vision_tower.vision_tower.trunk.blocks.28.norm1.weight": "model-00002-of-00002.safetensors",
|
| 505 |
+
"model.vision_tower.vision_tower.trunk.blocks.28.norm2.bias": "model-00002-of-00002.safetensors",
|
| 506 |
+
"model.vision_tower.vision_tower.trunk.blocks.28.norm2.weight": "model-00002-of-00002.safetensors",
|
| 507 |
+
"model.vision_tower.vision_tower.trunk.blocks.29.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 508 |
+
"model.vision_tower.vision_tower.trunk.blocks.29.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 509 |
+
"model.vision_tower.vision_tower.trunk.blocks.29.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 510 |
+
"model.vision_tower.vision_tower.trunk.blocks.29.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 511 |
+
"model.vision_tower.vision_tower.trunk.blocks.29.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
| 512 |
+
"model.vision_tower.vision_tower.trunk.blocks.29.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
| 513 |
+
"model.vision_tower.vision_tower.trunk.blocks.29.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
| 514 |
+
"model.vision_tower.vision_tower.trunk.blocks.29.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
| 515 |
+
"model.vision_tower.vision_tower.trunk.blocks.29.norm1.bias": "model-00002-of-00002.safetensors",
|
| 516 |
+
"model.vision_tower.vision_tower.trunk.blocks.29.norm1.weight": "model-00002-of-00002.safetensors",
|
| 517 |
+
"model.vision_tower.vision_tower.trunk.blocks.29.norm2.bias": "model-00002-of-00002.safetensors",
|
| 518 |
+
"model.vision_tower.vision_tower.trunk.blocks.29.norm2.weight": "model-00002-of-00002.safetensors",
|
| 519 |
+
"model.vision_tower.vision_tower.trunk.blocks.3.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 520 |
+
"model.vision_tower.vision_tower.trunk.blocks.3.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 521 |
+
"model.vision_tower.vision_tower.trunk.blocks.3.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 522 |
+
"model.vision_tower.vision_tower.trunk.blocks.3.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 523 |
+
"model.vision_tower.vision_tower.trunk.blocks.3.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 524 |
+
"model.vision_tower.vision_tower.trunk.blocks.3.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 525 |
+
"model.vision_tower.vision_tower.trunk.blocks.3.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 526 |
+
"model.vision_tower.vision_tower.trunk.blocks.3.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 527 |
+
"model.vision_tower.vision_tower.trunk.blocks.3.norm1.bias": "model-00001-of-00002.safetensors",
|
| 528 |
+
"model.vision_tower.vision_tower.trunk.blocks.3.norm1.weight": "model-00001-of-00002.safetensors",
|
| 529 |
+
"model.vision_tower.vision_tower.trunk.blocks.3.norm2.bias": "model-00001-of-00002.safetensors",
|
| 530 |
+
"model.vision_tower.vision_tower.trunk.blocks.3.norm2.weight": "model-00001-of-00002.safetensors",
|
| 531 |
+
"model.vision_tower.vision_tower.trunk.blocks.30.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 532 |
+
"model.vision_tower.vision_tower.trunk.blocks.30.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 533 |
+
"model.vision_tower.vision_tower.trunk.blocks.30.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 534 |
+
"model.vision_tower.vision_tower.trunk.blocks.30.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 535 |
+
"model.vision_tower.vision_tower.trunk.blocks.30.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
| 536 |
+
"model.vision_tower.vision_tower.trunk.blocks.30.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
| 537 |
+
"model.vision_tower.vision_tower.trunk.blocks.30.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
| 538 |
+
"model.vision_tower.vision_tower.trunk.blocks.30.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
| 539 |
+
"model.vision_tower.vision_tower.trunk.blocks.30.norm1.bias": "model-00002-of-00002.safetensors",
|
| 540 |
+
"model.vision_tower.vision_tower.trunk.blocks.30.norm1.weight": "model-00002-of-00002.safetensors",
|
| 541 |
+
"model.vision_tower.vision_tower.trunk.blocks.30.norm2.bias": "model-00002-of-00002.safetensors",
|
| 542 |
+
"model.vision_tower.vision_tower.trunk.blocks.30.norm2.weight": "model-00002-of-00002.safetensors",
|
| 543 |
+
"model.vision_tower.vision_tower.trunk.blocks.31.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 544 |
+
"model.vision_tower.vision_tower.trunk.blocks.31.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 545 |
+
"model.vision_tower.vision_tower.trunk.blocks.31.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 546 |
+
"model.vision_tower.vision_tower.trunk.blocks.31.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 547 |
+
"model.vision_tower.vision_tower.trunk.blocks.31.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
| 548 |
+
"model.vision_tower.vision_tower.trunk.blocks.31.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
| 549 |
+
"model.vision_tower.vision_tower.trunk.blocks.31.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
| 550 |
+
"model.vision_tower.vision_tower.trunk.blocks.31.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
| 551 |
+
"model.vision_tower.vision_tower.trunk.blocks.31.norm1.bias": "model-00002-of-00002.safetensors",
|
| 552 |
+
"model.vision_tower.vision_tower.trunk.blocks.31.norm1.weight": "model-00002-of-00002.safetensors",
|
| 553 |
+
"model.vision_tower.vision_tower.trunk.blocks.31.norm2.bias": "model-00002-of-00002.safetensors",
|
| 554 |
+
"model.vision_tower.vision_tower.trunk.blocks.31.norm2.weight": "model-00002-of-00002.safetensors",
|
| 555 |
+
"model.vision_tower.vision_tower.trunk.blocks.32.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 556 |
+
"model.vision_tower.vision_tower.trunk.blocks.32.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 557 |
+
"model.vision_tower.vision_tower.trunk.blocks.32.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 558 |
+
"model.vision_tower.vision_tower.trunk.blocks.32.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 559 |
+
"model.vision_tower.vision_tower.trunk.blocks.32.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
| 560 |
+
"model.vision_tower.vision_tower.trunk.blocks.32.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
| 561 |
+
"model.vision_tower.vision_tower.trunk.blocks.32.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
| 562 |
+
"model.vision_tower.vision_tower.trunk.blocks.32.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
| 563 |
+
"model.vision_tower.vision_tower.trunk.blocks.32.norm1.bias": "model-00002-of-00002.safetensors",
|
| 564 |
+
"model.vision_tower.vision_tower.trunk.blocks.32.norm1.weight": "model-00002-of-00002.safetensors",
|
| 565 |
+
"model.vision_tower.vision_tower.trunk.blocks.32.norm2.bias": "model-00002-of-00002.safetensors",
|
| 566 |
+
"model.vision_tower.vision_tower.trunk.blocks.32.norm2.weight": "model-00002-of-00002.safetensors",
|
| 567 |
+
"model.vision_tower.vision_tower.trunk.blocks.33.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 568 |
+
"model.vision_tower.vision_tower.trunk.blocks.33.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 569 |
+
"model.vision_tower.vision_tower.trunk.blocks.33.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 570 |
+
"model.vision_tower.vision_tower.trunk.blocks.33.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 571 |
+
"model.vision_tower.vision_tower.trunk.blocks.33.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
| 572 |
+
"model.vision_tower.vision_tower.trunk.blocks.33.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
| 573 |
+
"model.vision_tower.vision_tower.trunk.blocks.33.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
| 574 |
+
"model.vision_tower.vision_tower.trunk.blocks.33.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
| 575 |
+
"model.vision_tower.vision_tower.trunk.blocks.33.norm1.bias": "model-00002-of-00002.safetensors",
|
| 576 |
+
"model.vision_tower.vision_tower.trunk.blocks.33.norm1.weight": "model-00002-of-00002.safetensors",
|
| 577 |
+
"model.vision_tower.vision_tower.trunk.blocks.33.norm2.bias": "model-00002-of-00002.safetensors",
|
| 578 |
+
"model.vision_tower.vision_tower.trunk.blocks.33.norm2.weight": "model-00002-of-00002.safetensors",
|
| 579 |
+
"model.vision_tower.vision_tower.trunk.blocks.34.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 580 |
+
"model.vision_tower.vision_tower.trunk.blocks.34.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 581 |
+
"model.vision_tower.vision_tower.trunk.blocks.34.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 582 |
+
"model.vision_tower.vision_tower.trunk.blocks.34.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 583 |
+
"model.vision_tower.vision_tower.trunk.blocks.34.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
| 584 |
+
"model.vision_tower.vision_tower.trunk.blocks.34.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
| 585 |
+
"model.vision_tower.vision_tower.trunk.blocks.34.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
| 586 |
+
"model.vision_tower.vision_tower.trunk.blocks.34.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
| 587 |
+
"model.vision_tower.vision_tower.trunk.blocks.34.norm1.bias": "model-00002-of-00002.safetensors",
|
| 588 |
+
"model.vision_tower.vision_tower.trunk.blocks.34.norm1.weight": "model-00002-of-00002.safetensors",
|
| 589 |
+
"model.vision_tower.vision_tower.trunk.blocks.34.norm2.bias": "model-00002-of-00002.safetensors",
|
| 590 |
+
"model.vision_tower.vision_tower.trunk.blocks.34.norm2.weight": "model-00002-of-00002.safetensors",
|
| 591 |
+
"model.vision_tower.vision_tower.trunk.blocks.35.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 592 |
+
"model.vision_tower.vision_tower.trunk.blocks.35.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 593 |
+
"model.vision_tower.vision_tower.trunk.blocks.35.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 594 |
+
"model.vision_tower.vision_tower.trunk.blocks.35.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 595 |
+
"model.vision_tower.vision_tower.trunk.blocks.35.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
| 596 |
+
"model.vision_tower.vision_tower.trunk.blocks.35.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
| 597 |
+
"model.vision_tower.vision_tower.trunk.blocks.35.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
| 598 |
+
"model.vision_tower.vision_tower.trunk.blocks.35.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
| 599 |
+
"model.vision_tower.vision_tower.trunk.blocks.35.norm1.bias": "model-00002-of-00002.safetensors",
|
| 600 |
+
"model.vision_tower.vision_tower.trunk.blocks.35.norm1.weight": "model-00002-of-00002.safetensors",
|
| 601 |
+
"model.vision_tower.vision_tower.trunk.blocks.35.norm2.bias": "model-00002-of-00002.safetensors",
|
| 602 |
+
"model.vision_tower.vision_tower.trunk.blocks.35.norm2.weight": "model-00002-of-00002.safetensors",
|
| 603 |
+
"model.vision_tower.vision_tower.trunk.blocks.36.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 604 |
+
"model.vision_tower.vision_tower.trunk.blocks.36.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 605 |
+
"model.vision_tower.vision_tower.trunk.blocks.36.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 606 |
+
"model.vision_tower.vision_tower.trunk.blocks.36.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 607 |
+
"model.vision_tower.vision_tower.trunk.blocks.36.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
| 608 |
+
"model.vision_tower.vision_tower.trunk.blocks.36.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
| 609 |
+
"model.vision_tower.vision_tower.trunk.blocks.36.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
| 610 |
+
"model.vision_tower.vision_tower.trunk.blocks.36.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
| 611 |
+
"model.vision_tower.vision_tower.trunk.blocks.36.norm1.bias": "model-00002-of-00002.safetensors",
|
| 612 |
+
"model.vision_tower.vision_tower.trunk.blocks.36.norm1.weight": "model-00002-of-00002.safetensors",
|
| 613 |
+
"model.vision_tower.vision_tower.trunk.blocks.36.norm2.bias": "model-00002-of-00002.safetensors",
|
| 614 |
+
"model.vision_tower.vision_tower.trunk.blocks.36.norm2.weight": "model-00002-of-00002.safetensors",
|
| 615 |
+
"model.vision_tower.vision_tower.trunk.blocks.37.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 616 |
+
"model.vision_tower.vision_tower.trunk.blocks.37.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 617 |
+
"model.vision_tower.vision_tower.trunk.blocks.37.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 618 |
+
"model.vision_tower.vision_tower.trunk.blocks.37.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 619 |
+
"model.vision_tower.vision_tower.trunk.blocks.37.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
| 620 |
+
"model.vision_tower.vision_tower.trunk.blocks.37.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
| 621 |
+
"model.vision_tower.vision_tower.trunk.blocks.37.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
| 622 |
+
"model.vision_tower.vision_tower.trunk.blocks.37.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
| 623 |
+
"model.vision_tower.vision_tower.trunk.blocks.37.norm1.bias": "model-00002-of-00002.safetensors",
|
| 624 |
+
"model.vision_tower.vision_tower.trunk.blocks.37.norm1.weight": "model-00002-of-00002.safetensors",
|
| 625 |
+
"model.vision_tower.vision_tower.trunk.blocks.37.norm2.bias": "model-00002-of-00002.safetensors",
|
| 626 |
+
"model.vision_tower.vision_tower.trunk.blocks.37.norm2.weight": "model-00002-of-00002.safetensors",
|
| 627 |
+
"model.vision_tower.vision_tower.trunk.blocks.38.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 628 |
+
"model.vision_tower.vision_tower.trunk.blocks.38.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 629 |
+
"model.vision_tower.vision_tower.trunk.blocks.38.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 630 |
+
"model.vision_tower.vision_tower.trunk.blocks.38.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 631 |
+
"model.vision_tower.vision_tower.trunk.blocks.38.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
| 632 |
+
"model.vision_tower.vision_tower.trunk.blocks.38.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
| 633 |
+
"model.vision_tower.vision_tower.trunk.blocks.38.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
| 634 |
+
"model.vision_tower.vision_tower.trunk.blocks.38.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
| 635 |
+
"model.vision_tower.vision_tower.trunk.blocks.38.norm1.bias": "model-00002-of-00002.safetensors",
|
| 636 |
+
"model.vision_tower.vision_tower.trunk.blocks.38.norm1.weight": "model-00002-of-00002.safetensors",
|
| 637 |
+
"model.vision_tower.vision_tower.trunk.blocks.38.norm2.bias": "model-00002-of-00002.safetensors",
|
| 638 |
+
"model.vision_tower.vision_tower.trunk.blocks.38.norm2.weight": "model-00002-of-00002.safetensors",
|
| 639 |
+
"model.vision_tower.vision_tower.trunk.blocks.39.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 640 |
+
"model.vision_tower.vision_tower.trunk.blocks.39.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 641 |
+
"model.vision_tower.vision_tower.trunk.blocks.39.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 642 |
+
"model.vision_tower.vision_tower.trunk.blocks.39.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 643 |
+
"model.vision_tower.vision_tower.trunk.blocks.39.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
| 644 |
+
"model.vision_tower.vision_tower.trunk.blocks.39.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
| 645 |
+
"model.vision_tower.vision_tower.trunk.blocks.39.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
| 646 |
+
"model.vision_tower.vision_tower.trunk.blocks.39.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
| 647 |
+
"model.vision_tower.vision_tower.trunk.blocks.39.norm1.bias": "model-00002-of-00002.safetensors",
|
| 648 |
+
"model.vision_tower.vision_tower.trunk.blocks.39.norm1.weight": "model-00002-of-00002.safetensors",
|
| 649 |
+
"model.vision_tower.vision_tower.trunk.blocks.39.norm2.bias": "model-00002-of-00002.safetensors",
|
| 650 |
+
"model.vision_tower.vision_tower.trunk.blocks.39.norm2.weight": "model-00002-of-00002.safetensors",
|
| 651 |
+
"model.vision_tower.vision_tower.trunk.blocks.4.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 652 |
+
"model.vision_tower.vision_tower.trunk.blocks.4.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 653 |
+
"model.vision_tower.vision_tower.trunk.blocks.4.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 654 |
+
"model.vision_tower.vision_tower.trunk.blocks.4.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 655 |
+
"model.vision_tower.vision_tower.trunk.blocks.4.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 656 |
+
"model.vision_tower.vision_tower.trunk.blocks.4.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 657 |
+
"model.vision_tower.vision_tower.trunk.blocks.4.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 658 |
+
"model.vision_tower.vision_tower.trunk.blocks.4.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 659 |
+
"model.vision_tower.vision_tower.trunk.blocks.4.norm1.bias": "model-00001-of-00002.safetensors",
|
| 660 |
+
"model.vision_tower.vision_tower.trunk.blocks.4.norm1.weight": "model-00001-of-00002.safetensors",
|
| 661 |
+
"model.vision_tower.vision_tower.trunk.blocks.4.norm2.bias": "model-00001-of-00002.safetensors",
|
| 662 |
+
"model.vision_tower.vision_tower.trunk.blocks.4.norm2.weight": "model-00001-of-00002.safetensors",
|
| 663 |
+
"model.vision_tower.vision_tower.trunk.blocks.5.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 664 |
+
"model.vision_tower.vision_tower.trunk.blocks.5.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 665 |
+
"model.vision_tower.vision_tower.trunk.blocks.5.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 666 |
+
"model.vision_tower.vision_tower.trunk.blocks.5.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 667 |
+
"model.vision_tower.vision_tower.trunk.blocks.5.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 668 |
+
"model.vision_tower.vision_tower.trunk.blocks.5.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 669 |
+
"model.vision_tower.vision_tower.trunk.blocks.5.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 670 |
+
"model.vision_tower.vision_tower.trunk.blocks.5.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 671 |
+
"model.vision_tower.vision_tower.trunk.blocks.5.norm1.bias": "model-00001-of-00002.safetensors",
|
| 672 |
+
"model.vision_tower.vision_tower.trunk.blocks.5.norm1.weight": "model-00001-of-00002.safetensors",
|
| 673 |
+
"model.vision_tower.vision_tower.trunk.blocks.5.norm2.bias": "model-00001-of-00002.safetensors",
|
| 674 |
+
"model.vision_tower.vision_tower.trunk.blocks.5.norm2.weight": "model-00001-of-00002.safetensors",
|
| 675 |
+
"model.vision_tower.vision_tower.trunk.blocks.6.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 676 |
+
"model.vision_tower.vision_tower.trunk.blocks.6.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 677 |
+
"model.vision_tower.vision_tower.trunk.blocks.6.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 678 |
+
"model.vision_tower.vision_tower.trunk.blocks.6.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 679 |
+
"model.vision_tower.vision_tower.trunk.blocks.6.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 680 |
+
"model.vision_tower.vision_tower.trunk.blocks.6.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 681 |
+
"model.vision_tower.vision_tower.trunk.blocks.6.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 682 |
+
"model.vision_tower.vision_tower.trunk.blocks.6.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 683 |
+
"model.vision_tower.vision_tower.trunk.blocks.6.norm1.bias": "model-00001-of-00002.safetensors",
|
| 684 |
+
"model.vision_tower.vision_tower.trunk.blocks.6.norm1.weight": "model-00001-of-00002.safetensors",
|
| 685 |
+
"model.vision_tower.vision_tower.trunk.blocks.6.norm2.bias": "model-00001-of-00002.safetensors",
|
| 686 |
+
"model.vision_tower.vision_tower.trunk.blocks.6.norm2.weight": "model-00001-of-00002.safetensors",
|
| 687 |
+
"model.vision_tower.vision_tower.trunk.blocks.7.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 688 |
+
"model.vision_tower.vision_tower.trunk.blocks.7.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 689 |
+
"model.vision_tower.vision_tower.trunk.blocks.7.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 690 |
+
"model.vision_tower.vision_tower.trunk.blocks.7.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 691 |
+
"model.vision_tower.vision_tower.trunk.blocks.7.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 692 |
+
"model.vision_tower.vision_tower.trunk.blocks.7.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 693 |
+
"model.vision_tower.vision_tower.trunk.blocks.7.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 694 |
+
"model.vision_tower.vision_tower.trunk.blocks.7.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 695 |
+
"model.vision_tower.vision_tower.trunk.blocks.7.norm1.bias": "model-00001-of-00002.safetensors",
|
| 696 |
+
"model.vision_tower.vision_tower.trunk.blocks.7.norm1.weight": "model-00001-of-00002.safetensors",
|
| 697 |
+
"model.vision_tower.vision_tower.trunk.blocks.7.norm2.bias": "model-00001-of-00002.safetensors",
|
| 698 |
+
"model.vision_tower.vision_tower.trunk.blocks.7.norm2.weight": "model-00001-of-00002.safetensors",
|
| 699 |
+
"model.vision_tower.vision_tower.trunk.blocks.8.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 700 |
+
"model.vision_tower.vision_tower.trunk.blocks.8.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 701 |
+
"model.vision_tower.vision_tower.trunk.blocks.8.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 702 |
+
"model.vision_tower.vision_tower.trunk.blocks.8.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 703 |
+
"model.vision_tower.vision_tower.trunk.blocks.8.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 704 |
+
"model.vision_tower.vision_tower.trunk.blocks.8.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 705 |
+
"model.vision_tower.vision_tower.trunk.blocks.8.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 706 |
+
"model.vision_tower.vision_tower.trunk.blocks.8.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 707 |
+
"model.vision_tower.vision_tower.trunk.blocks.8.norm1.bias": "model-00001-of-00002.safetensors",
|
| 708 |
+
"model.vision_tower.vision_tower.trunk.blocks.8.norm1.weight": "model-00001-of-00002.safetensors",
|
| 709 |
+
"model.vision_tower.vision_tower.trunk.blocks.8.norm2.bias": "model-00001-of-00002.safetensors",
|
| 710 |
+
"model.vision_tower.vision_tower.trunk.blocks.8.norm2.weight": "model-00001-of-00002.safetensors",
|
| 711 |
+
"model.vision_tower.vision_tower.trunk.blocks.9.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 712 |
+
"model.vision_tower.vision_tower.trunk.blocks.9.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 713 |
+
"model.vision_tower.vision_tower.trunk.blocks.9.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 714 |
+
"model.vision_tower.vision_tower.trunk.blocks.9.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 715 |
+
"model.vision_tower.vision_tower.trunk.blocks.9.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 716 |
+
"model.vision_tower.vision_tower.trunk.blocks.9.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 717 |
+
"model.vision_tower.vision_tower.trunk.blocks.9.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 718 |
+
"model.vision_tower.vision_tower.trunk.blocks.9.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 719 |
+
"model.vision_tower.vision_tower.trunk.blocks.9.norm1.bias": "model-00001-of-00002.safetensors",
|
| 720 |
+
"model.vision_tower.vision_tower.trunk.blocks.9.norm1.weight": "model-00001-of-00002.safetensors",
|
| 721 |
+
"model.vision_tower.vision_tower.trunk.blocks.9.norm2.bias": "model-00001-of-00002.safetensors",
|
| 722 |
+
"model.vision_tower.vision_tower.trunk.blocks.9.norm2.weight": "model-00001-of-00002.safetensors",
|
| 723 |
+
"model.vision_tower.vision_tower.trunk.norm.bias": "model-00002-of-00002.safetensors",
|
| 724 |
+
"model.vision_tower.vision_tower.trunk.norm.weight": "model-00002-of-00002.safetensors",
|
| 725 |
+
"model.vision_tower.vision_tower.trunk.patch_embed.proj.bias": "model-00001-of-00002.safetensors",
|
| 726 |
+
"model.vision_tower.vision_tower.trunk.patch_embed.proj.weight": "model-00001-of-00002.safetensors",
|
| 727 |
+
"model.vision_tower.vision_tower.trunk.pos_embed": "model-00001-of-00002.safetensors"
|
| 728 |
+
}
|
| 729 |
+
}
|
continuous/smollm2/siglip2_g16_256/finetune/special_tokens_map.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|im_start|>",
|
| 4 |
+
"<|im_end|>"
|
| 5 |
+
],
|
| 6 |
+
"bos_token": {
|
| 7 |
+
"content": "<|im_start|>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": false,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false
|
| 12 |
+
},
|
| 13 |
+
"eos_token": {
|
| 14 |
+
"content": "<|im_end|>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false
|
| 19 |
+
},
|
| 20 |
+
"pad_token": "<|endoftext|>",
|
| 21 |
+
"unk_token": {
|
| 22 |
+
"content": "<|endoftext|>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false
|
| 27 |
+
}
|
| 28 |
+
}
|
continuous/smollm2/siglip2_g16_256/finetune/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
continuous/smollm2/siglip2_g16_256/finetune/tokenizer_config.json
ADDED
|
@@ -0,0 +1,155 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"0": {
|
| 5 |
+
"content": "<|endoftext|>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": false,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"1": {
|
| 13 |
+
"content": "<|im_start|>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": false,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"2": {
|
| 21 |
+
"content": "<|im_end|>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": false,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
},
|
| 28 |
+
"3": {
|
| 29 |
+
"content": "<repo_name>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": false,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": true
|
| 35 |
+
},
|
| 36 |
+
"4": {
|
| 37 |
+
"content": "<reponame>",
|
| 38 |
+
"lstrip": false,
|
| 39 |
+
"normalized": false,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": true
|
| 43 |
+
},
|
| 44 |
+
"5": {
|
| 45 |
+
"content": "<file_sep>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": false,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false,
|
| 50 |
+
"special": true
|
| 51 |
+
},
|
| 52 |
+
"6": {
|
| 53 |
+
"content": "<filename>",
|
| 54 |
+
"lstrip": false,
|
| 55 |
+
"normalized": false,
|
| 56 |
+
"rstrip": false,
|
| 57 |
+
"single_word": false,
|
| 58 |
+
"special": true
|
| 59 |
+
},
|
| 60 |
+
"7": {
|
| 61 |
+
"content": "<gh_stars>",
|
| 62 |
+
"lstrip": false,
|
| 63 |
+
"normalized": false,
|
| 64 |
+
"rstrip": false,
|
| 65 |
+
"single_word": false,
|
| 66 |
+
"special": true
|
| 67 |
+
},
|
| 68 |
+
"8": {
|
| 69 |
+
"content": "<issue_start>",
|
| 70 |
+
"lstrip": false,
|
| 71 |
+
"normalized": false,
|
| 72 |
+
"rstrip": false,
|
| 73 |
+
"single_word": false,
|
| 74 |
+
"special": true
|
| 75 |
+
},
|
| 76 |
+
"9": {
|
| 77 |
+
"content": "<issue_comment>",
|
| 78 |
+
"lstrip": false,
|
| 79 |
+
"normalized": false,
|
| 80 |
+
"rstrip": false,
|
| 81 |
+
"single_word": false,
|
| 82 |
+
"special": true
|
| 83 |
+
},
|
| 84 |
+
"10": {
|
| 85 |
+
"content": "<issue_closed>",
|
| 86 |
+
"lstrip": false,
|
| 87 |
+
"normalized": false,
|
| 88 |
+
"rstrip": false,
|
| 89 |
+
"single_word": false,
|
| 90 |
+
"special": true
|
| 91 |
+
},
|
| 92 |
+
"11": {
|
| 93 |
+
"content": "<jupyter_start>",
|
| 94 |
+
"lstrip": false,
|
| 95 |
+
"normalized": false,
|
| 96 |
+
"rstrip": false,
|
| 97 |
+
"single_word": false,
|
| 98 |
+
"special": true
|
| 99 |
+
},
|
| 100 |
+
"12": {
|
| 101 |
+
"content": "<jupyter_text>",
|
| 102 |
+
"lstrip": false,
|
| 103 |
+
"normalized": false,
|
| 104 |
+
"rstrip": false,
|
| 105 |
+
"single_word": false,
|
| 106 |
+
"special": true
|
| 107 |
+
},
|
| 108 |
+
"13": {
|
| 109 |
+
"content": "<jupyter_code>",
|
| 110 |
+
"lstrip": false,
|
| 111 |
+
"normalized": false,
|
| 112 |
+
"rstrip": false,
|
| 113 |
+
"single_word": false,
|
| 114 |
+
"special": true
|
| 115 |
+
},
|
| 116 |
+
"14": {
|
| 117 |
+
"content": "<jupyter_output>",
|
| 118 |
+
"lstrip": false,
|
| 119 |
+
"normalized": false,
|
| 120 |
+
"rstrip": false,
|
| 121 |
+
"single_word": false,
|
| 122 |
+
"special": true
|
| 123 |
+
},
|
| 124 |
+
"15": {
|
| 125 |
+
"content": "<jupyter_script>",
|
| 126 |
+
"lstrip": false,
|
| 127 |
+
"normalized": false,
|
| 128 |
+
"rstrip": false,
|
| 129 |
+
"single_word": false,
|
| 130 |
+
"special": true
|
| 131 |
+
},
|
| 132 |
+
"16": {
|
| 133 |
+
"content": "<empty_output>",
|
| 134 |
+
"lstrip": false,
|
| 135 |
+
"normalized": false,
|
| 136 |
+
"rstrip": false,
|
| 137 |
+
"single_word": false,
|
| 138 |
+
"special": true
|
| 139 |
+
}
|
| 140 |
+
},
|
| 141 |
+
"additional_special_tokens": [
|
| 142 |
+
"<|im_start|>",
|
| 143 |
+
"<|im_end|>"
|
| 144 |
+
],
|
| 145 |
+
"bos_token": "<|im_start|>",
|
| 146 |
+
"clean_up_tokenization_spaces": false,
|
| 147 |
+
"eos_token": "<|im_end|>",
|
| 148 |
+
"extra_special_tokens": {},
|
| 149 |
+
"model_max_length": 8192,
|
| 150 |
+
"pad_token": "<|endoftext|>",
|
| 151 |
+
"padding_side": "right",
|
| 152 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 153 |
+
"unk_token": "<|endoftext|>",
|
| 154 |
+
"vocab_size": 49152
|
| 155 |
+
}
|
continuous/smollm2/siglip2_g16_256/finetune/trainer_state.json
ADDED
|
@@ -0,0 +1,1856 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 1.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 2597,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.003850596842510589,
|
| 14 |
+
"grad_norm": 3.1434969902038574,
|
| 15 |
+
"learning_rate": 1.153846153846154e-06,
|
| 16 |
+
"loss": 1.2645,
|
| 17 |
+
"step": 10
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.007701193685021178,
|
| 21 |
+
"grad_norm": 2.0038814544677734,
|
| 22 |
+
"learning_rate": 2.435897435897436e-06,
|
| 23 |
+
"loss": 1.0993,
|
| 24 |
+
"step": 20
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.011551790527531768,
|
| 28 |
+
"grad_norm": 1.7747228145599365,
|
| 29 |
+
"learning_rate": 3.7179487179487184e-06,
|
| 30 |
+
"loss": 0.9675,
|
| 31 |
+
"step": 30
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.015402387370042356,
|
| 35 |
+
"grad_norm": 1.3159399032592773,
|
| 36 |
+
"learning_rate": 5e-06,
|
| 37 |
+
"loss": 0.9174,
|
| 38 |
+
"step": 40
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.019252984212552945,
|
| 42 |
+
"grad_norm": 1.2928848266601562,
|
| 43 |
+
"learning_rate": 6.282051282051282e-06,
|
| 44 |
+
"loss": 0.9087,
|
| 45 |
+
"step": 50
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.023103581055063535,
|
| 49 |
+
"grad_norm": 0.2649580240249634,
|
| 50 |
+
"learning_rate": 7.564102564102564e-06,
|
| 51 |
+
"loss": 0.8391,
|
| 52 |
+
"step": 60
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.026954177897574125,
|
| 56 |
+
"grad_norm": 0.2197767049074173,
|
| 57 |
+
"learning_rate": 8.846153846153847e-06,
|
| 58 |
+
"loss": 0.7952,
|
| 59 |
+
"step": 70
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.030804774740084712,
|
| 63 |
+
"grad_norm": 0.23076170682907104,
|
| 64 |
+
"learning_rate": 9.999996111488723e-06,
|
| 65 |
+
"loss": 0.8086,
|
| 66 |
+
"step": 80
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.0346553715825953,
|
| 70 |
+
"grad_norm": 0.21788281202316284,
|
| 71 |
+
"learning_rate": 9.999529497453782e-06,
|
| 72 |
+
"loss": 0.7933,
|
| 73 |
+
"step": 90
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.03850596842510589,
|
| 77 |
+
"grad_norm": 0.20987766981124878,
|
| 78 |
+
"learning_rate": 9.998285264324193e-06,
|
| 79 |
+
"loss": 0.7577,
|
| 80 |
+
"step": 100
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.04235656526761648,
|
| 84 |
+
"grad_norm": 0.23202015459537506,
|
| 85 |
+
"learning_rate": 9.996263605626052e-06,
|
| 86 |
+
"loss": 0.7536,
|
| 87 |
+
"step": 110
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.04620716211012707,
|
| 91 |
+
"grad_norm": 0.2243269681930542,
|
| 92 |
+
"learning_rate": 9.99346483580503e-06,
|
| 93 |
+
"loss": 0.7724,
|
| 94 |
+
"step": 120
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.05005775895263766,
|
| 98 |
+
"grad_norm": 0.20443911850452423,
|
| 99 |
+
"learning_rate": 9.989889390177467e-06,
|
| 100 |
+
"loss": 0.7455,
|
| 101 |
+
"step": 130
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.05390835579514825,
|
| 105 |
+
"grad_norm": 0.2214169204235077,
|
| 106 |
+
"learning_rate": 9.985537824862647e-06,
|
| 107 |
+
"loss": 0.7623,
|
| 108 |
+
"step": 140
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.05775895263765884,
|
| 112 |
+
"grad_norm": 0.21322189271450043,
|
| 113 |
+
"learning_rate": 9.980410816696317e-06,
|
| 114 |
+
"loss": 0.7378,
|
| 115 |
+
"step": 150
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.061609549480169425,
|
| 119 |
+
"grad_norm": 0.19492888450622559,
|
| 120 |
+
"learning_rate": 9.97450916312541e-06,
|
| 121 |
+
"loss": 0.7456,
|
| 122 |
+
"step": 160
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.06546014632268002,
|
| 126 |
+
"grad_norm": 0.16997510194778442,
|
| 127 |
+
"learning_rate": 9.967833782084004e-06,
|
| 128 |
+
"loss": 0.7473,
|
| 129 |
+
"step": 170
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.0693107431651906,
|
| 133 |
+
"grad_norm": 0.20555813610553741,
|
| 134 |
+
"learning_rate": 9.960385711850554e-06,
|
| 135 |
+
"loss": 0.7762,
|
| 136 |
+
"step": 180
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.07316134000770119,
|
| 140 |
+
"grad_norm": 0.2049771547317505,
|
| 141 |
+
"learning_rate": 9.952166110886394e-06,
|
| 142 |
+
"loss": 0.7632,
|
| 143 |
+
"step": 190
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.07701193685021178,
|
| 147 |
+
"grad_norm": 0.21551881730556488,
|
| 148 |
+
"learning_rate": 9.943176257655567e-06,
|
| 149 |
+
"loss": 0.7613,
|
| 150 |
+
"step": 200
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.08086253369272237,
|
| 154 |
+
"grad_norm": 0.20298533141613007,
|
| 155 |
+
"learning_rate": 9.933417550425952e-06,
|
| 156 |
+
"loss": 0.7525,
|
| 157 |
+
"step": 210
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.08471313053523297,
|
| 161 |
+
"grad_norm": 0.19362588226795197,
|
| 162 |
+
"learning_rate": 9.9228915070518e-06,
|
| 163 |
+
"loss": 0.7375,
|
| 164 |
+
"step": 220
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.08856372737774355,
|
| 168 |
+
"grad_norm": 0.1884419173002243,
|
| 169 |
+
"learning_rate": 9.911599764737632e-06,
|
| 170 |
+
"loss": 0.7342,
|
| 171 |
+
"step": 230
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.09241432422025414,
|
| 175 |
+
"grad_norm": 0.20223303139209747,
|
| 176 |
+
"learning_rate": 9.899544079783606e-06,
|
| 177 |
+
"loss": 0.7311,
|
| 178 |
+
"step": 240
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.09626492106276473,
|
| 182 |
+
"grad_norm": 0.19399555027484894,
|
| 183 |
+
"learning_rate": 9.886726327312338e-06,
|
| 184 |
+
"loss": 0.7478,
|
| 185 |
+
"step": 250
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.10011551790527531,
|
| 189 |
+
"grad_norm": 0.17266201972961426,
|
| 190 |
+
"learning_rate": 9.87314850097724e-06,
|
| 191 |
+
"loss": 0.7448,
|
| 192 |
+
"step": 260
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.1039661147477859,
|
| 196 |
+
"grad_norm": 0.17775073647499084,
|
| 197 |
+
"learning_rate": 9.858812712652452e-06,
|
| 198 |
+
"loss": 0.7284,
|
| 199 |
+
"step": 270
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.1078167115902965,
|
| 203 |
+
"grad_norm": 0.17229612171649933,
|
| 204 |
+
"learning_rate": 9.843721192104341e-06,
|
| 205 |
+
"loss": 0.7254,
|
| 206 |
+
"step": 280
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.11166730843280709,
|
| 210 |
+
"grad_norm": 0.18820028007030487,
|
| 211 |
+
"learning_rate": 9.827876286644698e-06,
|
| 212 |
+
"loss": 0.7556,
|
| 213 |
+
"step": 290
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.11551790527531768,
|
| 217 |
+
"grad_norm": 0.16895480453968048,
|
| 218 |
+
"learning_rate": 9.811280460765643e-06,
|
| 219 |
+
"loss": 0.7158,
|
| 220 |
+
"step": 300
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.11936850211782826,
|
| 224 |
+
"grad_norm": 0.18340347707271576,
|
| 225 |
+
"learning_rate": 9.793936295756292e-06,
|
| 226 |
+
"loss": 0.7204,
|
| 227 |
+
"step": 310
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.12321909896033885,
|
| 231 |
+
"grad_norm": 0.17628082633018494,
|
| 232 |
+
"learning_rate": 9.775846489301279e-06,
|
| 233 |
+
"loss": 0.7326,
|
| 234 |
+
"step": 320
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.12706969580284944,
|
| 238 |
+
"grad_norm": 0.17060311138629913,
|
| 239 |
+
"learning_rate": 9.757013855061157e-06,
|
| 240 |
+
"loss": 0.7315,
|
| 241 |
+
"step": 330
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.13092029264536004,
|
| 245 |
+
"grad_norm": 0.17486093938350677,
|
| 246 |
+
"learning_rate": 9.737441322234758e-06,
|
| 247 |
+
"loss": 0.7344,
|
| 248 |
+
"step": 340
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.1347708894878706,
|
| 252 |
+
"grad_norm": 0.1962638646364212,
|
| 253 |
+
"learning_rate": 9.717131935103605e-06,
|
| 254 |
+
"loss": 0.7409,
|
| 255 |
+
"step": 350
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.1386214863303812,
|
| 259 |
+
"grad_norm": 0.18348932266235352,
|
| 260 |
+
"learning_rate": 9.696088852558398e-06,
|
| 261 |
+
"loss": 0.7234,
|
| 262 |
+
"step": 360
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.1424720831728918,
|
| 266 |
+
"grad_norm": 0.1896730661392212,
|
| 267 |
+
"learning_rate": 9.674315347607686e-06,
|
| 268 |
+
"loss": 0.7522,
|
| 269 |
+
"step": 370
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.14632268001540238,
|
| 273 |
+
"grad_norm": 0.17307879030704498,
|
| 274 |
+
"learning_rate": 9.651814806868796e-06,
|
| 275 |
+
"loss": 0.7166,
|
| 276 |
+
"step": 380
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.15017327685791299,
|
| 280 |
+
"grad_norm": 0.17759330570697784,
|
| 281 |
+
"learning_rate": 9.62859073004107e-06,
|
| 282 |
+
"loss": 0.7169,
|
| 283 |
+
"step": 390
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.15402387370042356,
|
| 287 |
+
"grad_norm": 0.16116492450237274,
|
| 288 |
+
"learning_rate": 9.604646729361547e-06,
|
| 289 |
+
"loss": 0.7239,
|
| 290 |
+
"step": 400
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.15787447054293416,
|
| 294 |
+
"grad_norm": 0.18952511250972748,
|
| 295 |
+
"learning_rate": 9.579986529043099e-06,
|
| 296 |
+
"loss": 0.7199,
|
| 297 |
+
"step": 410
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.16172506738544473,
|
| 301 |
+
"grad_norm": 0.19572624564170837,
|
| 302 |
+
"learning_rate": 9.554613964695189e-06,
|
| 303 |
+
"loss": 0.7369,
|
| 304 |
+
"step": 420
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.16557566422795533,
|
| 308 |
+
"grad_norm": 0.18704703450202942,
|
| 309 |
+
"learning_rate": 9.528532982727281e-06,
|
| 310 |
+
"loss": 0.7208,
|
| 311 |
+
"step": 430
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.16942626107046593,
|
| 315 |
+
"grad_norm": 0.1784757375717163,
|
| 316 |
+
"learning_rate": 9.501747639735018e-06,
|
| 317 |
+
"loss": 0.7237,
|
| 318 |
+
"step": 440
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.1732768579129765,
|
| 322 |
+
"grad_norm": 0.17592282593250275,
|
| 323 |
+
"learning_rate": 9.474262101869272e-06,
|
| 324 |
+
"loss": 0.7116,
|
| 325 |
+
"step": 450
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.1771274547554871,
|
| 329 |
+
"grad_norm": 0.1851617693901062,
|
| 330 |
+
"learning_rate": 9.446080644188141e-06,
|
| 331 |
+
"loss": 0.7206,
|
| 332 |
+
"step": 460
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.18097805159799768,
|
| 336 |
+
"grad_norm": 0.17649078369140625,
|
| 337 |
+
"learning_rate": 9.417207649992017e-06,
|
| 338 |
+
"loss": 0.7219,
|
| 339 |
+
"step": 470
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.18482864844050828,
|
| 343 |
+
"grad_norm": 0.1863931268453598,
|
| 344 |
+
"learning_rate": 9.387647610141816e-06,
|
| 345 |
+
"loss": 0.7183,
|
| 346 |
+
"step": 480
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.18867924528301888,
|
| 350 |
+
"grad_norm": 0.16716530919075012,
|
| 351 |
+
"learning_rate": 9.35740512236047e-06,
|
| 352 |
+
"loss": 0.7155,
|
| 353 |
+
"step": 490
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.19252984212552945,
|
| 357 |
+
"grad_norm": 0.16632875800132751,
|
| 358 |
+
"learning_rate": 9.326484890517809e-06,
|
| 359 |
+
"loss": 0.7209,
|
| 360 |
+
"step": 500
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.19638043896804006,
|
| 364 |
+
"grad_norm": 0.18506059050559998,
|
| 365 |
+
"learning_rate": 9.294891723898926e-06,
|
| 366 |
+
"loss": 0.7088,
|
| 367 |
+
"step": 510
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.20023103581055063,
|
| 371 |
+
"grad_norm": 0.17775067687034607,
|
| 372 |
+
"learning_rate": 9.262630536456153e-06,
|
| 373 |
+
"loss": 0.7315,
|
| 374 |
+
"step": 520
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.20408163265306123,
|
| 378 |
+
"grad_norm": 0.18340200185775757,
|
| 379 |
+
"learning_rate": 9.229706346044749e-06,
|
| 380 |
+
"loss": 0.7167,
|
| 381 |
+
"step": 530
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.2079322294955718,
|
| 385 |
+
"grad_norm": 0.181379497051239,
|
| 386 |
+
"learning_rate": 9.196124273642422e-06,
|
| 387 |
+
"loss": 0.7246,
|
| 388 |
+
"step": 540
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.2117828263380824,
|
| 392 |
+
"grad_norm": 0.18275395035743713,
|
| 393 |
+
"learning_rate": 9.161889542552842e-06,
|
| 394 |
+
"loss": 0.7337,
|
| 395 |
+
"step": 550
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.215633423180593,
|
| 399 |
+
"grad_norm": 0.1751304268836975,
|
| 400 |
+
"learning_rate": 9.127007477593193e-06,
|
| 401 |
+
"loss": 0.7338,
|
| 402 |
+
"step": 560
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.21948402002310358,
|
| 406 |
+
"grad_norm": 0.18911324441432953,
|
| 407 |
+
"learning_rate": 9.091483504265974e-06,
|
| 408 |
+
"loss": 0.7425,
|
| 409 |
+
"step": 570
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.22333461686561418,
|
| 413 |
+
"grad_norm": 0.18601533770561218,
|
| 414 |
+
"learning_rate": 9.055323147915116e-06,
|
| 415 |
+
"loss": 0.7145,
|
| 416 |
+
"step": 580
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.22718521370812475,
|
| 420 |
+
"grad_norm": 0.17389866709709167,
|
| 421 |
+
"learning_rate": 9.018532032866585e-06,
|
| 422 |
+
"loss": 0.7277,
|
| 423 |
+
"step": 590
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.23103581055063535,
|
| 427 |
+
"grad_norm": 0.1623317450284958,
|
| 428 |
+
"learning_rate": 8.981115881553579e-06,
|
| 429 |
+
"loss": 0.725,
|
| 430 |
+
"step": 600
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.23488640739314592,
|
| 434 |
+
"grad_norm": 0.18609894812107086,
|
| 435 |
+
"learning_rate": 8.943080513626476e-06,
|
| 436 |
+
"loss": 0.7446,
|
| 437 |
+
"step": 610
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.23873700423565652,
|
| 441 |
+
"grad_norm": 0.16859549283981323,
|
| 442 |
+
"learning_rate": 8.904431845047641e-06,
|
| 443 |
+
"loss": 0.7235,
|
| 444 |
+
"step": 620
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.24258760107816713,
|
| 448 |
+
"grad_norm": 0.16717267036437988,
|
| 449 |
+
"learning_rate": 8.86517588717128e-06,
|
| 450 |
+
"loss": 0.7357,
|
| 451 |
+
"step": 630
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.2464381979206777,
|
| 455 |
+
"grad_norm": 0.18238113820552826,
|
| 456 |
+
"learning_rate": 8.82531874580844e-06,
|
| 457 |
+
"loss": 0.7371,
|
| 458 |
+
"step": 640
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.25028879476318827,
|
| 462 |
+
"grad_norm": 0.16501742601394653,
|
| 463 |
+
"learning_rate": 8.784866620277314e-06,
|
| 464 |
+
"loss": 0.6961,
|
| 465 |
+
"step": 650
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.25413939160569887,
|
| 469 |
+
"grad_norm": 0.17482736706733704,
|
| 470 |
+
"learning_rate": 8.743825802439018e-06,
|
| 471 |
+
"loss": 0.7187,
|
| 472 |
+
"step": 660
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 0.2579899884482095,
|
| 476 |
+
"grad_norm": 0.16980578005313873,
|
| 477 |
+
"learning_rate": 8.702202675718956e-06,
|
| 478 |
+
"loss": 0.732,
|
| 479 |
+
"step": 670
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 0.2618405852907201,
|
| 483 |
+
"grad_norm": 0.1632380187511444,
|
| 484 |
+
"learning_rate": 8.660003714113959e-06,
|
| 485 |
+
"loss": 0.7101,
|
| 486 |
+
"step": 680
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 0.2656911821332307,
|
| 490 |
+
"grad_norm": 0.17331236600875854,
|
| 491 |
+
"learning_rate": 8.617235481185323e-06,
|
| 492 |
+
"loss": 0.7199,
|
| 493 |
+
"step": 690
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 0.2695417789757412,
|
| 497 |
+
"grad_norm": 0.18049882352352142,
|
| 498 |
+
"learning_rate": 8.573904629037931e-06,
|
| 499 |
+
"loss": 0.7334,
|
| 500 |
+
"step": 700
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.2733923758182518,
|
| 504 |
+
"grad_norm": 0.16457851231098175,
|
| 505 |
+
"learning_rate": 8.530017897285585e-06,
|
| 506 |
+
"loss": 0.7164,
|
| 507 |
+
"step": 710
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.2772429726607624,
|
| 511 |
+
"grad_norm": 0.17063477635383606,
|
| 512 |
+
"learning_rate": 8.485582112002746e-06,
|
| 513 |
+
"loss": 0.7178,
|
| 514 |
+
"step": 720
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.281093569503273,
|
| 518 |
+
"grad_norm": 0.1636001169681549,
|
| 519 |
+
"learning_rate": 8.440604184662811e-06,
|
| 520 |
+
"loss": 0.7246,
|
| 521 |
+
"step": 730
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.2849441663457836,
|
| 525 |
+
"grad_norm": 0.18470224738121033,
|
| 526 |
+
"learning_rate": 8.395091111063118e-06,
|
| 527 |
+
"loss": 0.7111,
|
| 528 |
+
"step": 740
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 0.28879476318829417,
|
| 532 |
+
"grad_norm": 0.16221095621585846,
|
| 533 |
+
"learning_rate": 8.349049970236822e-06,
|
| 534 |
+
"loss": 0.7093,
|
| 535 |
+
"step": 750
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 0.29264536003080477,
|
| 539 |
+
"grad_norm": 0.1659521907567978,
|
| 540 |
+
"learning_rate": 8.302487923351842e-06,
|
| 541 |
+
"loss": 0.704,
|
| 542 |
+
"step": 760
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.29649595687331537,
|
| 546 |
+
"grad_norm": 0.16713745892047882,
|
| 547 |
+
"learning_rate": 8.255412212597021e-06,
|
| 548 |
+
"loss": 0.7243,
|
| 549 |
+
"step": 770
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.30034655371582597,
|
| 553 |
+
"grad_norm": 0.17290401458740234,
|
| 554 |
+
"learning_rate": 8.207830160055688e-06,
|
| 555 |
+
"loss": 0.7202,
|
| 556 |
+
"step": 780
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.3041971505583365,
|
| 560 |
+
"grad_norm": 0.16897566616535187,
|
| 561 |
+
"learning_rate": 8.159749166566786e-06,
|
| 562 |
+
"loss": 0.7015,
|
| 563 |
+
"step": 790
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 0.3080477474008471,
|
| 567 |
+
"grad_norm": 0.16825851798057556,
|
| 568 |
+
"learning_rate": 8.11117671057377e-06,
|
| 569 |
+
"loss": 0.7225,
|
| 570 |
+
"step": 800
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.3118983442433577,
|
| 574 |
+
"grad_norm": 0.1678372174501419,
|
| 575 |
+
"learning_rate": 8.062120346961404e-06,
|
| 576 |
+
"loss": 0.7209,
|
| 577 |
+
"step": 810
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 0.3157489410858683,
|
| 581 |
+
"grad_norm": 0.17002572119235992,
|
| 582 |
+
"learning_rate": 8.012587705880705e-06,
|
| 583 |
+
"loss": 0.7169,
|
| 584 |
+
"step": 820
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 0.3195995379283789,
|
| 588 |
+
"grad_norm": 0.17832957208156586,
|
| 589 |
+
"learning_rate": 7.962586491562146e-06,
|
| 590 |
+
"loss": 0.7046,
|
| 591 |
+
"step": 830
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.32345013477088946,
|
| 595 |
+
"grad_norm": 0.16853067278862,
|
| 596 |
+
"learning_rate": 7.912124481117357e-06,
|
| 597 |
+
"loss": 0.705,
|
| 598 |
+
"step": 840
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 0.32730073161340006,
|
| 602 |
+
"grad_norm": 0.16091367602348328,
|
| 603 |
+
"learning_rate": 7.861209523329494e-06,
|
| 604 |
+
"loss": 0.7175,
|
| 605 |
+
"step": 850
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 0.33115132845591067,
|
| 609 |
+
"grad_norm": 0.1779157668352127,
|
| 610 |
+
"learning_rate": 7.809849537432432e-06,
|
| 611 |
+
"loss": 0.7069,
|
| 612 |
+
"step": 860
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 0.33500192529842127,
|
| 616 |
+
"grad_norm": 0.16518354415893555,
|
| 617 |
+
"learning_rate": 7.758052511879035e-06,
|
| 618 |
+
"loss": 0.7092,
|
| 619 |
+
"step": 870
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 0.33885252214093187,
|
| 623 |
+
"grad_norm": 0.17269019782543182,
|
| 624 |
+
"learning_rate": 7.705826503098642e-06,
|
| 625 |
+
"loss": 0.7129,
|
| 626 |
+
"step": 880
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 0.3427031189834424,
|
| 630 |
+
"grad_norm": 0.17529204487800598,
|
| 631 |
+
"learning_rate": 7.653179634243979e-06,
|
| 632 |
+
"loss": 0.7078,
|
| 633 |
+
"step": 890
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 0.346553715825953,
|
| 637 |
+
"grad_norm": 0.16014313697814941,
|
| 638 |
+
"learning_rate": 7.600120093927696e-06,
|
| 639 |
+
"loss": 0.7056,
|
| 640 |
+
"step": 900
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 0.3504043126684636,
|
| 644 |
+
"grad_norm": 0.18973998725414276,
|
| 645 |
+
"learning_rate": 7.546656134948729e-06,
|
| 646 |
+
"loss": 0.6981,
|
| 647 |
+
"step": 910
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 0.3542549095109742,
|
| 651 |
+
"grad_norm": 0.16458527743816376,
|
| 652 |
+
"learning_rate": 7.492796073008661e-06,
|
| 653 |
+
"loss": 0.7091,
|
| 654 |
+
"step": 920
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 0.3581055063534848,
|
| 658 |
+
"grad_norm": 0.1940525770187378,
|
| 659 |
+
"learning_rate": 7.438548285418326e-06,
|
| 660 |
+
"loss": 0.6887,
|
| 661 |
+
"step": 930
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 0.36195610319599536,
|
| 665 |
+
"grad_norm": 0.17292875051498413,
|
| 666 |
+
"learning_rate": 7.3839212097948e-06,
|
| 667 |
+
"loss": 0.7195,
|
| 668 |
+
"step": 940
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 0.36580670003850596,
|
| 672 |
+
"grad_norm": 0.17954304814338684,
|
| 673 |
+
"learning_rate": 7.328923342749039e-06,
|
| 674 |
+
"loss": 0.7381,
|
| 675 |
+
"step": 950
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 0.36965729688101656,
|
| 679 |
+
"grad_norm": 0.17223946750164032,
|
| 680 |
+
"learning_rate": 7.273563238564319e-06,
|
| 681 |
+
"loss": 0.7316,
|
| 682 |
+
"step": 960
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 0.37350789372352716,
|
| 686 |
+
"grad_norm": 0.1657610833644867,
|
| 687 |
+
"learning_rate": 7.217849507865724e-06,
|
| 688 |
+
"loss": 0.6981,
|
| 689 |
+
"step": 970
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 0.37735849056603776,
|
| 693 |
+
"grad_norm": 0.16754165291786194,
|
| 694 |
+
"learning_rate": 7.161790816280858e-06,
|
| 695 |
+
"loss": 0.7109,
|
| 696 |
+
"step": 980
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 0.3812090874085483,
|
| 700 |
+
"grad_norm": 0.18175841867923737,
|
| 701 |
+
"learning_rate": 7.1053958830920125e-06,
|
| 702 |
+
"loss": 0.6939,
|
| 703 |
+
"step": 990
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 0.3850596842510589,
|
| 707 |
+
"grad_norm": 0.17627358436584473,
|
| 708 |
+
"learning_rate": 7.0486734798799715e-06,
|
| 709 |
+
"loss": 0.7096,
|
| 710 |
+
"step": 1000
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 0.3889102810935695,
|
| 714 |
+
"grad_norm": 0.16443012654781342,
|
| 715 |
+
"learning_rate": 6.991632429159708e-06,
|
| 716 |
+
"loss": 0.7291,
|
| 717 |
+
"step": 1010
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 0.3927608779360801,
|
| 721 |
+
"grad_norm": 0.18049505352973938,
|
| 722 |
+
"learning_rate": 6.934281603008132e-06,
|
| 723 |
+
"loss": 0.7244,
|
| 724 |
+
"step": 1020
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 0.39661147477859066,
|
| 728 |
+
"grad_norm": 0.1557004451751709,
|
| 729 |
+
"learning_rate": 6.876629921684143e-06,
|
| 730 |
+
"loss": 0.7214,
|
| 731 |
+
"step": 1030
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 0.40046207162110126,
|
| 735 |
+
"grad_norm": 0.1763542741537094,
|
| 736 |
+
"learning_rate": 6.818686352241199e-06,
|
| 737 |
+
"loss": 0.7082,
|
| 738 |
+
"step": 1040
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 0.40431266846361186,
|
| 742 |
+
"grad_norm": 0.16158071160316467,
|
| 743 |
+
"learning_rate": 6.760459907132573e-06,
|
| 744 |
+
"loss": 0.7028,
|
| 745 |
+
"step": 1050
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 0.40816326530612246,
|
| 749 |
+
"grad_norm": 0.15530501306056976,
|
| 750 |
+
"learning_rate": 6.701959642809589e-06,
|
| 751 |
+
"loss": 0.7086,
|
| 752 |
+
"step": 1060
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 0.41201386214863306,
|
| 756 |
+
"grad_norm": 0.17466600239276886,
|
| 757 |
+
"learning_rate": 6.643194658312987e-06,
|
| 758 |
+
"loss": 0.6992,
|
| 759 |
+
"step": 1070
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 0.4158644589911436,
|
| 763 |
+
"grad_norm": 0.15797750651836395,
|
| 764 |
+
"learning_rate": 6.584174093857676e-06,
|
| 765 |
+
"loss": 0.7275,
|
| 766 |
+
"step": 1080
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 0.4197150558336542,
|
| 770 |
+
"grad_norm": 0.1969560831785202,
|
| 771 |
+
"learning_rate": 6.5249071294110735e-06,
|
| 772 |
+
"loss": 0.7103,
|
| 773 |
+
"step": 1090
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 0.4235656526761648,
|
| 777 |
+
"grad_norm": 0.16957779228687286,
|
| 778 |
+
"learning_rate": 6.465402983265274e-06,
|
| 779 |
+
"loss": 0.7222,
|
| 780 |
+
"step": 1100
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 0.4274162495186754,
|
| 784 |
+
"grad_norm": 0.17658253014087677,
|
| 785 |
+
"learning_rate": 6.405670910603243e-06,
|
| 786 |
+
"loss": 0.7127,
|
| 787 |
+
"step": 1110
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 0.431266846361186,
|
| 791 |
+
"grad_norm": 0.17758788168430328,
|
| 792 |
+
"learning_rate": 6.345720202059291e-06,
|
| 793 |
+
"loss": 0.7105,
|
| 794 |
+
"step": 1120
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 0.43511744320369655,
|
| 798 |
+
"grad_norm": 0.17417693138122559,
|
| 799 |
+
"learning_rate": 6.285560182274008e-06,
|
| 800 |
+
"loss": 0.6916,
|
| 801 |
+
"step": 1130
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 0.43896804004620715,
|
| 805 |
+
"grad_norm": 0.18283776938915253,
|
| 806 |
+
"learning_rate": 6.225200208443936e-06,
|
| 807 |
+
"loss": 0.7173,
|
| 808 |
+
"step": 1140
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 0.44281863688871775,
|
| 812 |
+
"grad_norm": 0.17217908799648285,
|
| 813 |
+
"learning_rate": 6.16464966886616e-06,
|
| 814 |
+
"loss": 0.7002,
|
| 815 |
+
"step": 1150
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 0.44666923373122835,
|
| 819 |
+
"grad_norm": 0.2012103646993637,
|
| 820 |
+
"learning_rate": 6.103917981478065e-06,
|
| 821 |
+
"loss": 0.7313,
|
| 822 |
+
"step": 1160
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 0.45051983057373896,
|
| 826 |
+
"grad_norm": 0.16379034519195557,
|
| 827 |
+
"learning_rate": 6.043014592392489e-06,
|
| 828 |
+
"loss": 0.7366,
|
| 829 |
+
"step": 1170
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 0.4543704274162495,
|
| 833 |
+
"grad_norm": 0.17135773599147797,
|
| 834 |
+
"learning_rate": 5.981948974428485e-06,
|
| 835 |
+
"loss": 0.7186,
|
| 836 |
+
"step": 1180
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 0.4582210242587601,
|
| 840 |
+
"grad_norm": 0.1596372127532959,
|
| 841 |
+
"learning_rate": 5.920730625637934e-06,
|
| 842 |
+
"loss": 0.6924,
|
| 843 |
+
"step": 1190
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 0.4620716211012707,
|
| 847 |
+
"grad_norm": 0.17531718313694,
|
| 848 |
+
"learning_rate": 5.8593690678282355e-06,
|
| 849 |
+
"loss": 0.7038,
|
| 850 |
+
"step": 1200
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 0.4659222179437813,
|
| 854 |
+
"grad_norm": 0.1645875722169876,
|
| 855 |
+
"learning_rate": 5.797873845081301e-06,
|
| 856 |
+
"loss": 0.7015,
|
| 857 |
+
"step": 1210
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 0.46977281478629185,
|
| 861 |
+
"grad_norm": 0.16941127181053162,
|
| 862 |
+
"learning_rate": 5.736254522269075e-06,
|
| 863 |
+
"loss": 0.725,
|
| 864 |
+
"step": 1220
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 0.47362341162880245,
|
| 868 |
+
"grad_norm": 0.16853636503219604,
|
| 869 |
+
"learning_rate": 5.6745206835658386e-06,
|
| 870 |
+
"loss": 0.7237,
|
| 871 |
+
"step": 1230
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 0.47747400847131305,
|
| 875 |
+
"grad_norm": 0.1633571982383728,
|
| 876 |
+
"learning_rate": 5.612681930957495e-06,
|
| 877 |
+
"loss": 0.7023,
|
| 878 |
+
"step": 1240
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 0.48132460531382365,
|
| 882 |
+
"grad_norm": 0.16318564116954803,
|
| 883 |
+
"learning_rate": 5.550747882748095e-06,
|
| 884 |
+
"loss": 0.6919,
|
| 885 |
+
"step": 1250
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 0.48517520215633425,
|
| 889 |
+
"grad_norm": 0.18672853708267212,
|
| 890 |
+
"learning_rate": 5.4887281720638195e-06,
|
| 891 |
+
"loss": 0.7086,
|
| 892 |
+
"step": 1260
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 0.4890257989988448,
|
| 896 |
+
"grad_norm": 0.18094518780708313,
|
| 897 |
+
"learning_rate": 5.42663244535466e-06,
|
| 898 |
+
"loss": 0.6834,
|
| 899 |
+
"step": 1270
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 0.4928763958413554,
|
| 903 |
+
"grad_norm": 0.17848673462867737,
|
| 904 |
+
"learning_rate": 5.3644703608940205e-06,
|
| 905 |
+
"loss": 0.7018,
|
| 906 |
+
"step": 1280
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 0.496726992683866,
|
| 910 |
+
"grad_norm": 0.16180351376533508,
|
| 911 |
+
"learning_rate": 5.302251587276491e-06,
|
| 912 |
+
"loss": 0.7123,
|
| 913 |
+
"step": 1290
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 0.5005775895263765,
|
| 917 |
+
"grad_norm": 0.16244953870773315,
|
| 918 |
+
"learning_rate": 5.2399858019140005e-06,
|
| 919 |
+
"loss": 0.7035,
|
| 920 |
+
"step": 1300
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 0.5044281863688872,
|
| 924 |
+
"grad_norm": 0.16772694885730743,
|
| 925 |
+
"learning_rate": 5.177682689530615e-06,
|
| 926 |
+
"loss": 0.7265,
|
| 927 |
+
"step": 1310
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 0.5082787832113977,
|
| 931 |
+
"grad_norm": 0.177913099527359,
|
| 932 |
+
"learning_rate": 5.11535194065619e-06,
|
| 933 |
+
"loss": 0.6925,
|
| 934 |
+
"step": 1320
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 0.5121293800539084,
|
| 938 |
+
"grad_norm": 0.18158507347106934,
|
| 939 |
+
"learning_rate": 5.053003250119113e-06,
|
| 940 |
+
"loss": 0.6991,
|
| 941 |
+
"step": 1330
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 0.515979976896419,
|
| 945 |
+
"grad_norm": 0.16283613443374634,
|
| 946 |
+
"learning_rate": 4.9906463155383925e-06,
|
| 947 |
+
"loss": 0.7065,
|
| 948 |
+
"step": 1340
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 0.5198305737389295,
|
| 952 |
+
"grad_norm": 0.1634514480829239,
|
| 953 |
+
"learning_rate": 4.9282908358153046e-06,
|
| 954 |
+
"loss": 0.7071,
|
| 955 |
+
"step": 1350
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 0.5236811705814401,
|
| 959 |
+
"grad_norm": 0.18576520681381226,
|
| 960 |
+
"learning_rate": 4.8659465096248345e-06,
|
| 961 |
+
"loss": 0.7194,
|
| 962 |
+
"step": 1360
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 0.5275317674239507,
|
| 966 |
+
"grad_norm": 0.16786882281303406,
|
| 967 |
+
"learning_rate": 4.803623033907169e-06,
|
| 968 |
+
"loss": 0.7093,
|
| 969 |
+
"step": 1370
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 0.5313823642664613,
|
| 973 |
+
"grad_norm": 0.16128478944301605,
|
| 974 |
+
"learning_rate": 4.741330102359441e-06,
|
| 975 |
+
"loss": 0.7252,
|
| 976 |
+
"step": 1380
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 0.5352329611089719,
|
| 980 |
+
"grad_norm": 0.17292962968349457,
|
| 981 |
+
"learning_rate": 4.679077403927996e-06,
|
| 982 |
+
"loss": 0.7001,
|
| 983 |
+
"step": 1390
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 0.5390835579514824,
|
| 987 |
+
"grad_norm": 0.16733163595199585,
|
| 988 |
+
"learning_rate": 4.616874621301373e-06,
|
| 989 |
+
"loss": 0.7023,
|
| 990 |
+
"step": 1400
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 0.5429341547939931,
|
| 994 |
+
"grad_norm": 0.18232408165931702,
|
| 995 |
+
"learning_rate": 4.554731429404293e-06,
|
| 996 |
+
"loss": 0.7227,
|
| 997 |
+
"step": 1410
|
| 998 |
+
},
|
| 999 |
+
{
|
| 1000 |
+
"epoch": 0.5467847516365036,
|
| 1001 |
+
"grad_norm": 0.18253807723522186,
|
| 1002 |
+
"learning_rate": 4.492657493892822e-06,
|
| 1003 |
+
"loss": 0.7016,
|
| 1004 |
+
"step": 1420
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 0.5506353484790143,
|
| 1008 |
+
"grad_norm": 0.1733454465866089,
|
| 1009 |
+
"learning_rate": 4.430662469650999e-06,
|
| 1010 |
+
"loss": 0.7156,
|
| 1011 |
+
"step": 1430
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 0.5544859453215248,
|
| 1015 |
+
"grad_norm": 0.18087869882583618,
|
| 1016 |
+
"learning_rate": 4.368755999289118e-06,
|
| 1017 |
+
"loss": 0.7189,
|
| 1018 |
+
"step": 1440
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 0.5583365421640354,
|
| 1022 |
+
"grad_norm": 0.1771393120288849,
|
| 1023 |
+
"learning_rate": 4.306947711643949e-06,
|
| 1024 |
+
"loss": 0.7016,
|
| 1025 |
+
"step": 1450
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 0.562187139006546,
|
| 1029 |
+
"grad_norm": 0.168299600481987,
|
| 1030 |
+
"learning_rate": 4.245247220281068e-06,
|
| 1031 |
+
"loss": 0.7067,
|
| 1032 |
+
"step": 1460
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 0.5660377358490566,
|
| 1036 |
+
"grad_norm": 0.16749408841133118,
|
| 1037 |
+
"learning_rate": 4.183664121999587e-06,
|
| 1038 |
+
"loss": 0.6999,
|
| 1039 |
+
"step": 1470
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"epoch": 0.5698883326915672,
|
| 1043 |
+
"grad_norm": 0.17245137691497803,
|
| 1044 |
+
"learning_rate": 4.122207995339474e-06,
|
| 1045 |
+
"loss": 0.6957,
|
| 1046 |
+
"step": 1480
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 0.5737389295340778,
|
| 1050 |
+
"grad_norm": 0.16602978110313416,
|
| 1051 |
+
"learning_rate": 4.060888399091734e-06,
|
| 1052 |
+
"loss": 0.7033,
|
| 1053 |
+
"step": 1490
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 0.5775895263765883,
|
| 1057 |
+
"grad_norm": 0.17123106122016907,
|
| 1058 |
+
"learning_rate": 3.999714870811639e-06,
|
| 1059 |
+
"loss": 0.7177,
|
| 1060 |
+
"step": 1500
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 0.581440123219099,
|
| 1064 |
+
"grad_norm": 0.16720421612262726,
|
| 1065 |
+
"learning_rate": 3.938696925335275e-06,
|
| 1066 |
+
"loss": 0.7103,
|
| 1067 |
+
"step": 1510
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 0.5852907200616095,
|
| 1071 |
+
"grad_norm": 0.16851963102817535,
|
| 1072 |
+
"learning_rate": 3.87784405329962e-06,
|
| 1073 |
+
"loss": 0.7174,
|
| 1074 |
+
"step": 1520
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 0.5891413169041202,
|
| 1078 |
+
"grad_norm": 0.15905463695526123,
|
| 1079 |
+
"learning_rate": 3.817165719666382e-06,
|
| 1080 |
+
"loss": 0.7158,
|
| 1081 |
+
"step": 1530
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 0.5929919137466307,
|
| 1085 |
+
"grad_norm": 0.17209063470363617,
|
| 1086 |
+
"learning_rate": 3.756671362249841e-06,
|
| 1087 |
+
"loss": 0.7211,
|
| 1088 |
+
"step": 1540
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 0.5968425105891413,
|
| 1092 |
+
"grad_norm": 0.16259653866291046,
|
| 1093 |
+
"learning_rate": 3.6963703902488907e-06,
|
| 1094 |
+
"loss": 0.7074,
|
| 1095 |
+
"step": 1550
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 0.6006931074316519,
|
| 1099 |
+
"grad_norm": 0.16429907083511353,
|
| 1100 |
+
"learning_rate": 3.6362721827835655e-06,
|
| 1101 |
+
"loss": 0.715,
|
| 1102 |
+
"step": 1560
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 0.6045437042741625,
|
| 1106 |
+
"grad_norm": 0.17745929956436157,
|
| 1107 |
+
"learning_rate": 3.576386087436212e-06,
|
| 1108 |
+
"loss": 0.7237,
|
| 1109 |
+
"step": 1570
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 0.608394301116673,
|
| 1113 |
+
"grad_norm": 0.18503187596797943,
|
| 1114 |
+
"learning_rate": 3.5167214187975913e-06,
|
| 1115 |
+
"loss": 0.715,
|
| 1116 |
+
"step": 1580
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 0.6122448979591837,
|
| 1120 |
+
"grad_norm": 0.15307912230491638,
|
| 1121 |
+
"learning_rate": 3.457287457018086e-06,
|
| 1122 |
+
"loss": 0.7112,
|
| 1123 |
+
"step": 1590
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 0.6160954948016942,
|
| 1127 |
+
"grad_norm": 0.17225167155265808,
|
| 1128 |
+
"learning_rate": 3.3980934463643003e-06,
|
| 1129 |
+
"loss": 0.7083,
|
| 1130 |
+
"step": 1600
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 0.6199460916442049,
|
| 1134 |
+
"grad_norm": 0.15949197113513947,
|
| 1135 |
+
"learning_rate": 3.3391485937812053e-06,
|
| 1136 |
+
"loss": 0.6849,
|
| 1137 |
+
"step": 1610
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 0.6237966884867154,
|
| 1141 |
+
"grad_norm": 0.17291763424873352,
|
| 1142 |
+
"learning_rate": 3.280462067460115e-06,
|
| 1143 |
+
"loss": 0.6859,
|
| 1144 |
+
"step": 1620
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 0.627647285329226,
|
| 1148 |
+
"grad_norm": 0.1684974879026413,
|
| 1149 |
+
"learning_rate": 3.222042995412669e-06,
|
| 1150 |
+
"loss": 0.7111,
|
| 1151 |
+
"step": 1630
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 0.6314978821717366,
|
| 1155 |
+
"grad_norm": 0.16074296832084656,
|
| 1156 |
+
"learning_rate": 3.163900464051089e-06,
|
| 1157 |
+
"loss": 0.702,
|
| 1158 |
+
"step": 1640
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 0.6353484790142472,
|
| 1162 |
+
"grad_norm": 0.17313618957996368,
|
| 1163 |
+
"learning_rate": 3.1060435167748826e-06,
|
| 1164 |
+
"loss": 0.7176,
|
| 1165 |
+
"step": 1650
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 0.6391990758567578,
|
| 1169 |
+
"grad_norm": 0.1624966859817505,
|
| 1170 |
+
"learning_rate": 3.048481152564253e-06,
|
| 1171 |
+
"loss": 0.6956,
|
| 1172 |
+
"step": 1660
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 0.6430496726992684,
|
| 1176 |
+
"grad_norm": 0.18665523827075958,
|
| 1177 |
+
"learning_rate": 2.9912223245804017e-06,
|
| 1178 |
+
"loss": 0.7128,
|
| 1179 |
+
"step": 1670
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 0.6469002695417789,
|
| 1183 |
+
"grad_norm": 0.16812998056411743,
|
| 1184 |
+
"learning_rate": 2.934275938772981e-06,
|
| 1185 |
+
"loss": 0.7028,
|
| 1186 |
+
"step": 1680
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 0.6507508663842896,
|
| 1190 |
+
"grad_norm": 0.17579087615013123,
|
| 1191 |
+
"learning_rate": 2.8776508524948676e-06,
|
| 1192 |
+
"loss": 0.6979,
|
| 1193 |
+
"step": 1690
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 0.6546014632268001,
|
| 1197 |
+
"grad_norm": 0.16375090181827545,
|
| 1198 |
+
"learning_rate": 2.821355873124503e-06,
|
| 1199 |
+
"loss": 0.6994,
|
| 1200 |
+
"step": 1700
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 0.6584520600693108,
|
| 1204 |
+
"grad_norm": 0.17252638936042786,
|
| 1205 |
+
"learning_rate": 2.7653997566960144e-06,
|
| 1206 |
+
"loss": 0.7087,
|
| 1207 |
+
"step": 1710
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"epoch": 0.6623026569118213,
|
| 1211 |
+
"grad_norm": 0.18277934193611145,
|
| 1212 |
+
"learning_rate": 2.709791206537309e-06,
|
| 1213 |
+
"loss": 0.7018,
|
| 1214 |
+
"step": 1720
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 0.6661532537543319,
|
| 1218 |
+
"grad_norm": 0.18738071620464325,
|
| 1219 |
+
"learning_rate": 2.6545388719163747e-06,
|
| 1220 |
+
"loss": 0.7032,
|
| 1221 |
+
"step": 1730
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 0.6700038505968425,
|
| 1225 |
+
"grad_norm": 0.1719694584608078,
|
| 1226 |
+
"learning_rate": 2.599651346695979e-06,
|
| 1227 |
+
"loss": 0.7124,
|
| 1228 |
+
"step": 1740
|
| 1229 |
+
},
|
| 1230 |
+
{
|
| 1231 |
+
"epoch": 0.6738544474393531,
|
| 1232 |
+
"grad_norm": 0.1652594357728958,
|
| 1233 |
+
"learning_rate": 2.545137167997007e-06,
|
| 1234 |
+
"loss": 0.7102,
|
| 1235 |
+
"step": 1750
|
| 1236 |
+
},
|
| 1237 |
+
{
|
| 1238 |
+
"epoch": 0.6777050442818637,
|
| 1239 |
+
"grad_norm": 0.1653377115726471,
|
| 1240 |
+
"learning_rate": 2.4910048148705972e-06,
|
| 1241 |
+
"loss": 0.6984,
|
| 1242 |
+
"step": 1760
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 0.6815556411243743,
|
| 1246 |
+
"grad_norm": 0.17673297226428986,
|
| 1247 |
+
"learning_rate": 2.4372627069793327e-06,
|
| 1248 |
+
"loss": 0.7364,
|
| 1249 |
+
"step": 1770
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 0.6854062379668848,
|
| 1253 |
+
"grad_norm": 0.16644734144210815,
|
| 1254 |
+
"learning_rate": 2.3839192032876486e-06,
|
| 1255 |
+
"loss": 0.7127,
|
| 1256 |
+
"step": 1780
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 0.6892568348093955,
|
| 1260 |
+
"grad_norm": 0.17400361597537994,
|
| 1261 |
+
"learning_rate": 2.3309826007617047e-06,
|
| 1262 |
+
"loss": 0.7279,
|
| 1263 |
+
"step": 1790
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 0.693107431651906,
|
| 1267 |
+
"grad_norm": 0.1651696115732193,
|
| 1268 |
+
"learning_rate": 2.278461133078881e-06,
|
| 1269 |
+
"loss": 0.6967,
|
| 1270 |
+
"step": 1800
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 0.6969580284944167,
|
| 1274 |
+
"grad_norm": 0.16867342591285706,
|
| 1275 |
+
"learning_rate": 2.2263629693471258e-06,
|
| 1276 |
+
"loss": 0.6898,
|
| 1277 |
+
"step": 1810
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 0.7008086253369272,
|
| 1281 |
+
"grad_norm": 0.16884014010429382,
|
| 1282 |
+
"learning_rate": 2.1746962128343414e-06,
|
| 1283 |
+
"loss": 0.7115,
|
| 1284 |
+
"step": 1820
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 0.7046592221794378,
|
| 1288 |
+
"grad_norm": 0.171330064535141,
|
| 1289 |
+
"learning_rate": 2.1234688997080183e-06,
|
| 1290 |
+
"loss": 0.6958,
|
| 1291 |
+
"step": 1830
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 0.7085098190219484,
|
| 1295 |
+
"grad_norm": 0.17093545198440552,
|
| 1296 |
+
"learning_rate": 2.0726889977853053e-06,
|
| 1297 |
+
"loss": 0.7022,
|
| 1298 |
+
"step": 1840
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 0.712360415864459,
|
| 1302 |
+
"grad_norm": 0.17732442915439606,
|
| 1303 |
+
"learning_rate": 2.022364405293703e-06,
|
| 1304 |
+
"loss": 0.7175,
|
| 1305 |
+
"step": 1850
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 0.7162110127069696,
|
| 1309 |
+
"grad_norm": 0.16551750898361206,
|
| 1310 |
+
"learning_rate": 1.9725029496425814e-06,
|
| 1311 |
+
"loss": 0.7144,
|
| 1312 |
+
"step": 1860
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 0.7200616095494802,
|
| 1316 |
+
"grad_norm": 0.169295996427536,
|
| 1317 |
+
"learning_rate": 1.923112386205727e-06,
|
| 1318 |
+
"loss": 0.7054,
|
| 1319 |
+
"step": 1870
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 0.7239122063919907,
|
| 1323 |
+
"grad_norm": 0.16840367019176483,
|
| 1324 |
+
"learning_rate": 1.874200397115079e-06,
|
| 1325 |
+
"loss": 0.7156,
|
| 1326 |
+
"step": 1880
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 0.7277628032345014,
|
| 1330 |
+
"grad_norm": 0.17118768393993378,
|
| 1331 |
+
"learning_rate": 1.825774590065857e-06,
|
| 1332 |
+
"loss": 0.7008,
|
| 1333 |
+
"step": 1890
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 0.7316134000770119,
|
| 1337 |
+
"grad_norm": 0.17620398104190826,
|
| 1338 |
+
"learning_rate": 1.7778424971332813e-06,
|
| 1339 |
+
"loss": 0.712,
|
| 1340 |
+
"step": 1900
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 0.7354639969195226,
|
| 1344 |
+
"grad_norm": 0.16244417428970337,
|
| 1345 |
+
"learning_rate": 1.7304115736010407e-06,
|
| 1346 |
+
"loss": 0.707,
|
| 1347 |
+
"step": 1910
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 0.7393145937620331,
|
| 1351 |
+
"grad_norm": 0.16467249393463135,
|
| 1352 |
+
"learning_rate": 1.6834891968017108e-06,
|
| 1353 |
+
"loss": 0.6995,
|
| 1354 |
+
"step": 1920
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 0.7431651906045437,
|
| 1358 |
+
"grad_norm": 0.1791650801897049,
|
| 1359 |
+
"learning_rate": 1.6370826649692884e-06,
|
| 1360 |
+
"loss": 0.7137,
|
| 1361 |
+
"step": 1930
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 0.7470157874470543,
|
| 1365 |
+
"grad_norm": 0.16582731902599335,
|
| 1366 |
+
"learning_rate": 1.5911991961040463e-06,
|
| 1367 |
+
"loss": 0.7173,
|
| 1368 |
+
"step": 1940
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 0.7508663842895649,
|
| 1372 |
+
"grad_norm": 0.17086677253246307,
|
| 1373 |
+
"learning_rate": 1.545845926849851e-06,
|
| 1374 |
+
"loss": 0.7015,
|
| 1375 |
+
"step": 1950
|
| 1376 |
+
},
|
| 1377 |
+
{
|
| 1378 |
+
"epoch": 0.7547169811320755,
|
| 1379 |
+
"grad_norm": 0.17953622341156006,
|
| 1380 |
+
"learning_rate": 1.5010299113841397e-06,
|
| 1381 |
+
"loss": 0.7247,
|
| 1382 |
+
"step": 1960
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 0.7585675779745861,
|
| 1386 |
+
"grad_norm": 0.17344188690185547,
|
| 1387 |
+
"learning_rate": 1.4567581203207238e-06,
|
| 1388 |
+
"loss": 0.7141,
|
| 1389 |
+
"step": 1970
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 0.7624181748170966,
|
| 1393 |
+
"grad_norm": 0.18286748230457306,
|
| 1394 |
+
"learning_rate": 1.413037439625593e-06,
|
| 1395 |
+
"loss": 0.715,
|
| 1396 |
+
"step": 1980
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 0.7662687716596073,
|
| 1400 |
+
"grad_norm": 0.18091848492622375,
|
| 1401 |
+
"learning_rate": 1.3698746695458847e-06,
|
| 1402 |
+
"loss": 0.704,
|
| 1403 |
+
"step": 1990
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 0.7701193685021178,
|
| 1407 |
+
"grad_norm": 0.1724209487438202,
|
| 1408 |
+
"learning_rate": 1.3272765235521745e-06,
|
| 1409 |
+
"loss": 0.7041,
|
| 1410 |
+
"step": 2000
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"epoch": 0.7739699653446284,
|
| 1414 |
+
"grad_norm": 0.1635913997888565,
|
| 1415 |
+
"learning_rate": 1.2852496272942877e-06,
|
| 1416 |
+
"loss": 0.7119,
|
| 1417 |
+
"step": 2010
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 0.777820562187139,
|
| 1421 |
+
"grad_norm": 0.16007636487483978,
|
| 1422 |
+
"learning_rate": 1.2438005175707396e-06,
|
| 1423 |
+
"loss": 0.69,
|
| 1424 |
+
"step": 2020
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 0.7816711590296496,
|
| 1428 |
+
"grad_norm": 0.1649429053068161,
|
| 1429 |
+
"learning_rate": 1.2029356413120297e-06,
|
| 1430 |
+
"loss": 0.6857,
|
| 1431 |
+
"step": 2030
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 0.7855217558721602,
|
| 1435 |
+
"grad_norm": 0.16562587022781372,
|
| 1436 |
+
"learning_rate": 1.1626613545778786e-06,
|
| 1437 |
+
"loss": 0.7009,
|
| 1438 |
+
"step": 2040
|
| 1439 |
+
},
|
| 1440 |
+
{
|
| 1441 |
+
"epoch": 0.7893723527146708,
|
| 1442 |
+
"grad_norm": 0.16341805458068848,
|
| 1443 |
+
"learning_rate": 1.1229839215686294e-06,
|
| 1444 |
+
"loss": 0.7034,
|
| 1445 |
+
"step": 2050
|
| 1446 |
+
},
|
| 1447 |
+
{
|
| 1448 |
+
"epoch": 0.7932229495571813,
|
| 1449 |
+
"grad_norm": 0.15445926785469055,
|
| 1450 |
+
"learning_rate": 1.0839095136509188e-06,
|
| 1451 |
+
"loss": 0.6885,
|
| 1452 |
+
"step": 2060
|
| 1453 |
+
},
|
| 1454 |
+
{
|
| 1455 |
+
"epoch": 0.797073546399692,
|
| 1456 |
+
"grad_norm": 0.17346835136413574,
|
| 1457 |
+
"learning_rate": 1.045444208397791e-06,
|
| 1458 |
+
"loss": 0.703,
|
| 1459 |
+
"step": 2070
|
| 1460 |
+
},
|
| 1461 |
+
{
|
| 1462 |
+
"epoch": 0.8009241432422025,
|
| 1463 |
+
"grad_norm": 0.16035494208335876,
|
| 1464 |
+
"learning_rate": 1.007593988643402e-06,
|
| 1465 |
+
"loss": 0.6815,
|
| 1466 |
+
"step": 2080
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 0.8047747400847132,
|
| 1470 |
+
"grad_norm": 0.15932025015354156,
|
| 1471 |
+
"learning_rate": 9.703647415524613e-07,
|
| 1472 |
+
"loss": 0.7098,
|
| 1473 |
+
"step": 2090
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 0.8086253369272237,
|
| 1477 |
+
"grad_norm": 0.1552928388118744,
|
| 1478 |
+
"learning_rate": 9.337622577045485e-07,
|
| 1479 |
+
"loss": 0.6982,
|
| 1480 |
+
"step": 2100
|
| 1481 |
+
},
|
| 1482 |
+
{
|
| 1483 |
+
"epoch": 0.8124759337697343,
|
| 1484 |
+
"grad_norm": 0.16585995256900787,
|
| 1485 |
+
"learning_rate": 8.977922301934588e-07,
|
| 1486 |
+
"loss": 0.7059,
|
| 1487 |
+
"step": 2110
|
| 1488 |
+
},
|
| 1489 |
+
{
|
| 1490 |
+
"epoch": 0.8163265306122449,
|
| 1491 |
+
"grad_norm": 0.18186955153942108,
|
| 1492 |
+
"learning_rate": 8.624602537417009e-07,
|
| 1493 |
+
"loss": 0.7213,
|
| 1494 |
+
"step": 2120
|
| 1495 |
+
},
|
| 1496 |
+
{
|
| 1497 |
+
"epoch": 0.8201771274547555,
|
| 1498 |
+
"grad_norm": 0.17050586640834808,
|
| 1499 |
+
"learning_rate": 8.277718238303123e-07,
|
| 1500 |
+
"loss": 0.7009,
|
| 1501 |
+
"step": 2130
|
| 1502 |
+
},
|
| 1503 |
+
{
|
| 1504 |
+
"epoch": 0.8240277242972661,
|
| 1505 |
+
"grad_norm": 0.17324888706207275,
|
| 1506 |
+
"learning_rate": 7.937323358440935e-07,
|
| 1507 |
+
"loss": 0.7038,
|
| 1508 |
+
"step": 2140
|
| 1509 |
+
},
|
| 1510 |
+
{
|
| 1511 |
+
"epoch": 0.8278783211397767,
|
| 1512 |
+
"grad_norm": 0.16615530848503113,
|
| 1513 |
+
"learning_rate": 7.603470842324223e-07,
|
| 1514 |
+
"loss": 0.6908,
|
| 1515 |
+
"step": 2150
|
| 1516 |
+
},
|
| 1517 |
+
{
|
| 1518 |
+
"epoch": 0.8317289179822872,
|
| 1519 |
+
"grad_norm": 0.16606472432613373,
|
| 1520 |
+
"learning_rate": 7.276212616857575e-07,
|
| 1521 |
+
"loss": 0.7133,
|
| 1522 |
+
"step": 2160
|
| 1523 |
+
},
|
| 1524 |
+
{
|
| 1525 |
+
"epoch": 0.8355795148247979,
|
| 1526 |
+
"grad_norm": 0.17113108932971954,
|
| 1527 |
+
"learning_rate": 6.955599583279837e-07,
|
| 1528 |
+
"loss": 0.7061,
|
| 1529 |
+
"step": 2170
|
| 1530 |
+
},
|
| 1531 |
+
{
|
| 1532 |
+
"epoch": 0.8394301116673084,
|
| 1533 |
+
"grad_norm": 0.16189050674438477,
|
| 1534 |
+
"learning_rate": 6.641681609246981e-07,
|
| 1535 |
+
"loss": 0.7033,
|
| 1536 |
+
"step": 2180
|
| 1537 |
+
},
|
| 1538 |
+
{
|
| 1539 |
+
"epoch": 0.8432807085098191,
|
| 1540 |
+
"grad_norm": 0.17607297003269196,
|
| 1541 |
+
"learning_rate": 6.334507521075711e-07,
|
| 1542 |
+
"loss": 0.7008,
|
| 1543 |
+
"step": 2190
|
| 1544 |
+
},
|
| 1545 |
+
{
|
| 1546 |
+
"epoch": 0.8471313053523296,
|
| 1547 |
+
"grad_norm": 0.1705499291419983,
|
| 1548 |
+
"learning_rate": 6.034125096149179e-07,
|
| 1549 |
+
"loss": 0.7053,
|
| 1550 |
+
"step": 2200
|
| 1551 |
+
},
|
| 1552 |
+
{
|
| 1553 |
+
"epoch": 0.8509819021948402,
|
| 1554 |
+
"grad_norm": 0.1633322685956955,
|
| 1555 |
+
"learning_rate": 5.740581055485722e-07,
|
| 1556 |
+
"loss": 0.6766,
|
| 1557 |
+
"step": 2210
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"epoch": 0.8548324990373508,
|
| 1561 |
+
"grad_norm": 0.1573982536792755,
|
| 1562 |
+
"learning_rate": 5.453921056471961e-07,
|
| 1563 |
+
"loss": 0.7089,
|
| 1564 |
+
"step": 2220
|
| 1565 |
+
},
|
| 1566 |
+
{
|
| 1567 |
+
"epoch": 0.8586830958798614,
|
| 1568 |
+
"grad_norm": 0.17870159447193146,
|
| 1569 |
+
"learning_rate": 5.174189685761288e-07,
|
| 1570 |
+
"loss": 0.7026,
|
| 1571 |
+
"step": 2230
|
| 1572 |
+
},
|
| 1573 |
+
{
|
| 1574 |
+
"epoch": 0.862533692722372,
|
| 1575 |
+
"grad_norm": 0.16059012711048126,
|
| 1576 |
+
"learning_rate": 4.901430452338979e-07,
|
| 1577 |
+
"loss": 0.7159,
|
| 1578 |
+
"step": 2240
|
| 1579 |
+
},
|
| 1580 |
+
{
|
| 1581 |
+
"epoch": 0.8663842895648826,
|
| 1582 |
+
"grad_norm": 0.1665360927581787,
|
| 1583 |
+
"learning_rate": 4.6356857807548286e-07,
|
| 1584 |
+
"loss": 0.7025,
|
| 1585 |
+
"step": 2250
|
| 1586 |
+
},
|
| 1587 |
+
{
|
| 1588 |
+
"epoch": 0.8702348864073931,
|
| 1589 |
+
"grad_norm": 0.19583630561828613,
|
| 1590 |
+
"learning_rate": 4.376997004524541e-07,
|
| 1591 |
+
"loss": 0.6848,
|
| 1592 |
+
"step": 2260
|
| 1593 |
+
},
|
| 1594 |
+
{
|
| 1595 |
+
"epoch": 0.8740854832499038,
|
| 1596 |
+
"grad_norm": 0.163571298122406,
|
| 1597 |
+
"learning_rate": 4.12540435970073e-07,
|
| 1598 |
+
"loss": 0.7017,
|
| 1599 |
+
"step": 2270
|
| 1600 |
+
},
|
| 1601 |
+
{
|
| 1602 |
+
"epoch": 0.8779360800924143,
|
| 1603 |
+
"grad_norm": 0.1585300862789154,
|
| 1604 |
+
"learning_rate": 3.880946978614703e-07,
|
| 1605 |
+
"loss": 0.7118,
|
| 1606 |
+
"step": 2280
|
| 1607 |
+
},
|
| 1608 |
+
{
|
| 1609 |
+
"epoch": 0.881786676934925,
|
| 1610 |
+
"grad_norm": 0.16494940221309662,
|
| 1611 |
+
"learning_rate": 3.643662883789878e-07,
|
| 1612 |
+
"loss": 0.707,
|
| 1613 |
+
"step": 2290
|
| 1614 |
+
},
|
| 1615 |
+
{
|
| 1616 |
+
"epoch": 0.8856372737774355,
|
| 1617 |
+
"grad_norm": 0.15584588050842285,
|
| 1618 |
+
"learning_rate": 3.41358898202781e-07,
|
| 1619 |
+
"loss": 0.6915,
|
| 1620 |
+
"step": 2300
|
| 1621 |
+
},
|
| 1622 |
+
{
|
| 1623 |
+
"epoch": 0.889487870619946,
|
| 1624 |
+
"grad_norm": 0.1628124862909317,
|
| 1625 |
+
"learning_rate": 3.190761058667741e-07,
|
| 1626 |
+
"loss": 0.7046,
|
| 1627 |
+
"step": 2310
|
| 1628 |
+
},
|
| 1629 |
+
{
|
| 1630 |
+
"epoch": 0.8933384674624567,
|
| 1631 |
+
"grad_norm": 0.15710744261741638,
|
| 1632 |
+
"learning_rate": 2.9752137720206463e-07,
|
| 1633 |
+
"loss": 0.7043,
|
| 1634 |
+
"step": 2320
|
| 1635 |
+
},
|
| 1636 |
+
{
|
| 1637 |
+
"epoch": 0.8971890643049673,
|
| 1638 |
+
"grad_norm": 0.17206671833992004,
|
| 1639 |
+
"learning_rate": 2.7669806479785067e-07,
|
| 1640 |
+
"loss": 0.7156,
|
| 1641 |
+
"step": 2330
|
| 1642 |
+
},
|
| 1643 |
+
{
|
| 1644 |
+
"epoch": 0.9010396611474779,
|
| 1645 |
+
"grad_norm": 0.16215048730373383,
|
| 1646 |
+
"learning_rate": 2.566094074799763e-07,
|
| 1647 |
+
"loss": 0.7063,
|
| 1648 |
+
"step": 2340
|
| 1649 |
+
},
|
| 1650 |
+
{
|
| 1651 |
+
"epoch": 0.9048902579899885,
|
| 1652 |
+
"grad_norm": 0.16844867169857025,
|
| 1653 |
+
"learning_rate": 2.3725852980716557e-07,
|
| 1654 |
+
"loss": 0.6901,
|
| 1655 |
+
"step": 2350
|
| 1656 |
+
},
|
| 1657 |
+
{
|
| 1658 |
+
"epoch": 0.908740854832499,
|
| 1659 |
+
"grad_norm": 0.16436974704265594,
|
| 1660 |
+
"learning_rate": 2.1864844158503983e-07,
|
| 1661 |
+
"loss": 0.7027,
|
| 1662 |
+
"step": 2360
|
| 1663 |
+
},
|
| 1664 |
+
{
|
| 1665 |
+
"epoch": 0.9125914516750097,
|
| 1666 |
+
"grad_norm": 0.1829797774553299,
|
| 1667 |
+
"learning_rate": 2.007820373979702e-07,
|
| 1668 |
+
"loss": 0.6954,
|
| 1669 |
+
"step": 2370
|
| 1670 |
+
},
|
| 1671 |
+
{
|
| 1672 |
+
"epoch": 0.9164420485175202,
|
| 1673 |
+
"grad_norm": 0.16536568105220795,
|
| 1674 |
+
"learning_rate": 1.8366209615886532e-07,
|
| 1675 |
+
"loss": 0.7081,
|
| 1676 |
+
"step": 2380
|
| 1677 |
+
},
|
| 1678 |
+
{
|
| 1679 |
+
"epoch": 0.9202926453600309,
|
| 1680 |
+
"grad_norm": 0.16364867985248566,
|
| 1681 |
+
"learning_rate": 1.6729128067693613e-07,
|
| 1682 |
+
"loss": 0.7208,
|
| 1683 |
+
"step": 2390
|
| 1684 |
+
},
|
| 1685 |
+
{
|
| 1686 |
+
"epoch": 0.9241432422025414,
|
| 1687 |
+
"grad_norm": 0.1829371154308319,
|
| 1688 |
+
"learning_rate": 1.5167213724353426e-07,
|
| 1689 |
+
"loss": 0.7148,
|
| 1690 |
+
"step": 2400
|
| 1691 |
+
},
|
| 1692 |
+
{
|
| 1693 |
+
"epoch": 0.927993839045052,
|
| 1694 |
+
"grad_norm": 0.16254135966300964,
|
| 1695 |
+
"learning_rate": 1.3680709523610058e-07,
|
| 1696 |
+
"loss": 0.691,
|
| 1697 |
+
"step": 2410
|
| 1698 |
+
},
|
| 1699 |
+
{
|
| 1700 |
+
"epoch": 0.9318444358875626,
|
| 1701 |
+
"grad_norm": 0.15962396562099457,
|
| 1702 |
+
"learning_rate": 1.2269846674030418e-07,
|
| 1703 |
+
"loss": 0.7201,
|
| 1704 |
+
"step": 2420
|
| 1705 |
+
},
|
| 1706 |
+
{
|
| 1707 |
+
"epoch": 0.9356950327300732,
|
| 1708 |
+
"grad_norm": 0.17247094213962555,
|
| 1709 |
+
"learning_rate": 1.0934844619042595e-07,
|
| 1710 |
+
"loss": 0.7141,
|
| 1711 |
+
"step": 2430
|
| 1712 |
+
},
|
| 1713 |
+
{
|
| 1714 |
+
"epoch": 0.9395456295725837,
|
| 1715 |
+
"grad_norm": 0.16553886234760284,
|
| 1716 |
+
"learning_rate": 9.675911002803961e-08,
|
| 1717 |
+
"loss": 0.7013,
|
| 1718 |
+
"step": 2440
|
| 1719 |
+
},
|
| 1720 |
+
{
|
| 1721 |
+
"epoch": 0.9433962264150944,
|
| 1722 |
+
"grad_norm": 0.17495064437389374,
|
| 1723 |
+
"learning_rate": 8.493241637904381e-08,
|
| 1724 |
+
"loss": 0.6909,
|
| 1725 |
+
"step": 2450
|
| 1726 |
+
},
|
| 1727 |
+
{
|
| 1728 |
+
"epoch": 0.9472468232576049,
|
| 1729 |
+
"grad_norm": 0.17975077033042908,
|
| 1730 |
+
"learning_rate": 7.387020474909689e-08,
|
| 1731 |
+
"loss": 0.7179,
|
| 1732 |
+
"step": 2460
|
| 1733 |
+
},
|
| 1734 |
+
{
|
| 1735 |
+
"epoch": 0.9510974201001156,
|
| 1736 |
+
"grad_norm": 0.17712494730949402,
|
| 1737 |
+
"learning_rate": 6.357419573750856e-08,
|
| 1738 |
+
"loss": 0.7138,
|
| 1739 |
+
"step": 2470
|
| 1740 |
+
},
|
| 1741 |
+
{
|
| 1742 |
+
"epoch": 0.9549480169426261,
|
| 1743 |
+
"grad_norm": 0.16331307590007782,
|
| 1744 |
+
"learning_rate": 5.4045990769613365e-08,
|
| 1745 |
+
"loss": 0.6997,
|
| 1746 |
+
"step": 2480
|
| 1747 |
+
},
|
| 1748 |
+
{
|
| 1749 |
+
"epoch": 0.9587986137851366,
|
| 1750 |
+
"grad_norm": 0.16845199465751648,
|
| 1751 |
+
"learning_rate": 4.5287071847694434e-08,
|
| 1752 |
+
"loss": 0.7005,
|
| 1753 |
+
"step": 2490
|
| 1754 |
+
},
|
| 1755 |
+
{
|
| 1756 |
+
"epoch": 0.9626492106276473,
|
| 1757 |
+
"grad_norm": 0.16327671706676483,
|
| 1758 |
+
"learning_rate": 3.7298801320467817e-08,
|
| 1759 |
+
"loss": 0.7048,
|
| 1760 |
+
"step": 2500
|
| 1761 |
+
},
|
| 1762 |
+
{
|
| 1763 |
+
"epoch": 0.9664998074701578,
|
| 1764 |
+
"grad_norm": 0.16070720553398132,
|
| 1765 |
+
"learning_rate": 3.0082421671192576e-08,
|
| 1766 |
+
"loss": 0.7037,
|
| 1767 |
+
"step": 2510
|
| 1768 |
+
},
|
| 1769 |
+
{
|
| 1770 |
+
"epoch": 0.9703504043126685,
|
| 1771 |
+
"grad_norm": 0.16713014245033264,
|
| 1772 |
+
"learning_rate": 2.3639055324410355e-08,
|
| 1773 |
+
"loss": 0.7182,
|
| 1774 |
+
"step": 2520
|
| 1775 |
+
},
|
| 1776 |
+
{
|
| 1777 |
+
"epoch": 0.974201001155179,
|
| 1778 |
+
"grad_norm": 0.16765789687633514,
|
| 1779 |
+
"learning_rate": 1.7969704471369477e-08,
|
| 1780 |
+
"loss": 0.697,
|
| 1781 |
+
"step": 2530
|
| 1782 |
+
},
|
| 1783 |
+
{
|
| 1784 |
+
"epoch": 0.9780515979976896,
|
| 1785 |
+
"grad_norm": 0.15935397148132324,
|
| 1786 |
+
"learning_rate": 1.3075250914142413e-08,
|
| 1787 |
+
"loss": 0.6996,
|
| 1788 |
+
"step": 2540
|
| 1789 |
+
},
|
| 1790 |
+
{
|
| 1791 |
+
"epoch": 0.9819021948402002,
|
| 1792 |
+
"grad_norm": 0.157880499958992,
|
| 1793 |
+
"learning_rate": 8.956455928476049e-09,
|
| 1794 |
+
"loss": 0.7128,
|
| 1795 |
+
"step": 2550
|
| 1796 |
+
},
|
| 1797 |
+
{
|
| 1798 |
+
"epoch": 0.9857527916827108,
|
| 1799 |
+
"grad_norm": 0.16229602694511414,
|
| 1800 |
+
"learning_rate": 5.6139601453786275e-09,
|
| 1801 |
+
"loss": 0.6972,
|
| 1802 |
+
"step": 2560
|
| 1803 |
+
},
|
| 1804 |
+
{
|
| 1805 |
+
"epoch": 0.9896033885252215,
|
| 1806 |
+
"grad_norm": 0.160829097032547,
|
| 1807 |
+
"learning_rate": 3.0482834514805602e-09,
|
| 1808 |
+
"loss": 0.695,
|
| 1809 |
+
"step": 2570
|
| 1810 |
+
},
|
| 1811 |
+
{
|
| 1812 |
+
"epoch": 0.993453985367732,
|
| 1813 |
+
"grad_norm": 0.1596262902021408,
|
| 1814 |
+
"learning_rate": 1.2598249081713366e-09,
|
| 1815 |
+
"loss": 0.6831,
|
| 1816 |
+
"step": 2580
|
| 1817 |
+
},
|
| 1818 |
+
{
|
| 1819 |
+
"epoch": 0.9973045822102425,
|
| 1820 |
+
"grad_norm": 0.17300502955913544,
|
| 1821 |
+
"learning_rate": 2.488626895302826e-10,
|
| 1822 |
+
"loss": 0.7198,
|
| 1823 |
+
"step": 2590
|
| 1824 |
+
},
|
| 1825 |
+
{
|
| 1826 |
+
"epoch": 1.0,
|
| 1827 |
+
"step": 2597,
|
| 1828 |
+
"total_flos": 9.750706250999398e+18,
|
| 1829 |
+
"train_loss": 0.7212214379940393,
|
| 1830 |
+
"train_runtime": 15117.4614,
|
| 1831 |
+
"train_samples_per_second": 43.982,
|
| 1832 |
+
"train_steps_per_second": 0.172
|
| 1833 |
+
}
|
| 1834 |
+
],
|
| 1835 |
+
"logging_steps": 10,
|
| 1836 |
+
"max_steps": 2597,
|
| 1837 |
+
"num_input_tokens_seen": 584317136,
|
| 1838 |
+
"num_train_epochs": 1,
|
| 1839 |
+
"save_steps": 500,
|
| 1840 |
+
"stateful_callbacks": {
|
| 1841 |
+
"TrainerControl": {
|
| 1842 |
+
"args": {
|
| 1843 |
+
"should_epoch_stop": false,
|
| 1844 |
+
"should_evaluate": false,
|
| 1845 |
+
"should_log": false,
|
| 1846 |
+
"should_save": true,
|
| 1847 |
+
"should_training_stop": true
|
| 1848 |
+
},
|
| 1849 |
+
"attributes": {}
|
| 1850 |
+
}
|
| 1851 |
+
},
|
| 1852 |
+
"total_flos": 9.750706250999398e+18,
|
| 1853 |
+
"train_batch_size": 16,
|
| 1854 |
+
"trial_name": null,
|
| 1855 |
+
"trial_params": null
|
| 1856 |
+
}
|
continuous/smollm2/siglip2_g16_256/finetune/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:72b81bb0b063f3ab6c00556a7bed681065cc5114b0f966b01a258aec68918bc9
|
| 3 |
+
size 6264
|
continuous/smollm2/siglip2_g16_256/finetune/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
continuous/smollm2/siglip2_g16_256/pretrain/config.json
ADDED
|
@@ -0,0 +1,70 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_faster_video": false,
|
| 3 |
+
"add_time_instruction": false,
|
| 4 |
+
"architectures": [
|
| 5 |
+
"LlamaForCausalLM"
|
| 6 |
+
],
|
| 7 |
+
"attention_bias": false,
|
| 8 |
+
"attention_dropout": 0.0,
|
| 9 |
+
"bos_token_id": 1,
|
| 10 |
+
"dtype": "bfloat16",
|
| 11 |
+
"eos_token_id": 2,
|
| 12 |
+
"faster_token_stride": 10,
|
| 13 |
+
"force_sample": false,
|
| 14 |
+
"head_dim": 64,
|
| 15 |
+
"hidden_act": "silu",
|
| 16 |
+
"hidden_size": 2048,
|
| 17 |
+
"image_aspect_ratio": "square",
|
| 18 |
+
"image_crop_resolution": null,
|
| 19 |
+
"image_grid_pinpoints": null,
|
| 20 |
+
"image_split_resolution": null,
|
| 21 |
+
"initializer_range": 0.02,
|
| 22 |
+
"intermediate_size": 8192,
|
| 23 |
+
"max_position_embeddings": 8192,
|
| 24 |
+
"mlp_bias": false,
|
| 25 |
+
"mm_hidden_size": 1536,
|
| 26 |
+
"mm_newline_position": "grid",
|
| 27 |
+
"mm_patch_merge_type": "flat",
|
| 28 |
+
"mm_projector_lr": null,
|
| 29 |
+
"mm_projector_type": "mlp2x_gelu",
|
| 30 |
+
"mm_resampler_type": null,
|
| 31 |
+
"mm_spatial_pool_mode": "bilinear",
|
| 32 |
+
"mm_spatial_pool_stride": null,
|
| 33 |
+
"mm_tunable_parts": "mm_mlp_adapter",
|
| 34 |
+
"mm_use_im_patch_token": false,
|
| 35 |
+
"mm_use_im_start_end": false,
|
| 36 |
+
"mm_vision_select_feature": "patch",
|
| 37 |
+
"mm_vision_select_layer": -2,
|
| 38 |
+
"mm_vision_tower": "open_clip_hub:ViT-gopt-16-SigLIP2-256",
|
| 39 |
+
"mm_vision_tower_lr": null,
|
| 40 |
+
"model_type": "llama",
|
| 41 |
+
"num_attention_heads": 32,
|
| 42 |
+
"num_hidden_layers": 24,
|
| 43 |
+
"num_key_value_heads": 32,
|
| 44 |
+
"pad_token_id": 0,
|
| 45 |
+
"pos_skipping_range": 4096,
|
| 46 |
+
"pretraining_tp": 1,
|
| 47 |
+
"rms_norm_eps": 1e-05,
|
| 48 |
+
"rope_scaling": null,
|
| 49 |
+
"rope_theta": 130000,
|
| 50 |
+
"tie_word_embeddings": true,
|
| 51 |
+
"tokenizer_model_max_length": 8192,
|
| 52 |
+
"tokenizer_padding_side": "right",
|
| 53 |
+
"transformers.js_config": {
|
| 54 |
+
"dtype": "q4",
|
| 55 |
+
"kv_cache_dtype": {
|
| 56 |
+
"fp16": "float16",
|
| 57 |
+
"q4f16": "float16"
|
| 58 |
+
},
|
| 59 |
+
"use_external_data_format": {
|
| 60 |
+
"model.onnx": true,
|
| 61 |
+
"model_fp16.onnx": true
|
| 62 |
+
}
|
| 63 |
+
},
|
| 64 |
+
"transformers_version": "4.57.6",
|
| 65 |
+
"use_cache": true,
|
| 66 |
+
"use_mm_proj": true,
|
| 67 |
+
"use_pos_skipping": false,
|
| 68 |
+
"vision_tower_pretrained": "/cache/ckpt/download/tokenizer/continuous/siglip2/siglip2_g16_256.npz",
|
| 69 |
+
"vocab_size": 49152
|
| 70 |
+
}
|
continuous/smollm2/siglip2_g16_256/pretrain/mm_projector.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:17b68fc018a2d2fc98ff994bc5152b73bce53b8b436dab13acd4b00653b128d5
|
| 3 |
+
size 29378616
|
continuous/smollm2/siglip2_g16_256/pretrain/trainer_state.json
ADDED
|
@@ -0,0 +1,421 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 1.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 545,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.01834862385321101,
|
| 14 |
+
"grad_norm": 1.154370665550232,
|
| 15 |
+
"learning_rate": 0.00032142857142857147,
|
| 16 |
+
"loss": 3.697,
|
| 17 |
+
"step": 10
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.03669724770642202,
|
| 21 |
+
"grad_norm": 0.1400030255317688,
|
| 22 |
+
"learning_rate": 0.0006785714285714287,
|
| 23 |
+
"loss": 2.8948,
|
| 24 |
+
"step": 20
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.05504587155963303,
|
| 28 |
+
"grad_norm": 0.14337831735610962,
|
| 29 |
+
"learning_rate": 0.0009999907688176173,
|
| 30 |
+
"loss": 2.799,
|
| 31 |
+
"step": 30
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.07339449541284404,
|
| 35 |
+
"grad_norm": 0.07451479136943817,
|
| 36 |
+
"learning_rate": 0.0009988834393115766,
|
| 37 |
+
"loss": 2.7519,
|
| 38 |
+
"step": 40
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.09174311926605505,
|
| 42 |
+
"grad_norm": 0.09933579713106155,
|
| 43 |
+
"learning_rate": 0.0009959345572940772,
|
| 44 |
+
"loss": 2.7344,
|
| 45 |
+
"step": 50
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.11009174311926606,
|
| 49 |
+
"grad_norm": 0.09251748770475388,
|
| 50 |
+
"learning_rate": 0.0009911550081155983,
|
| 51 |
+
"loss": 2.7244,
|
| 52 |
+
"step": 60
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.12844036697247707,
|
| 56 |
+
"grad_norm": 0.10974935442209244,
|
| 57 |
+
"learning_rate": 0.0009845624347566433,
|
| 58 |
+
"loss": 2.683,
|
| 59 |
+
"step": 70
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.14678899082568808,
|
| 63 |
+
"grad_norm": 0.1494440734386444,
|
| 64 |
+
"learning_rate": 0.0009761811727013547,
|
| 65 |
+
"loss": 2.6299,
|
| 66 |
+
"step": 80
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.1651376146788991,
|
| 70 |
+
"grad_norm": 0.10966784507036209,
|
| 71 |
+
"learning_rate": 0.0009660421601067666,
|
| 72 |
+
"loss": 2.5755,
|
| 73 |
+
"step": 90
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.1834862385321101,
|
| 77 |
+
"grad_norm": 0.13996370136737823,
|
| 78 |
+
"learning_rate": 0.0009541828235992926,
|
| 79 |
+
"loss": 2.5201,
|
| 80 |
+
"step": 100
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.2018348623853211,
|
| 84 |
+
"grad_norm": 0.1730082780122757,
|
| 85 |
+
"learning_rate": 0.0009406469401200151,
|
| 86 |
+
"loss": 2.456,
|
| 87 |
+
"step": 110
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.22018348623853212,
|
| 91 |
+
"grad_norm": 0.13626356422901154,
|
| 92 |
+
"learning_rate": 0.0009254844753287492,
|
| 93 |
+
"loss": 2.4078,
|
| 94 |
+
"step": 120
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.23853211009174313,
|
| 98 |
+
"grad_norm": 0.2038114219903946,
|
| 99 |
+
"learning_rate": 0.0009087513991633924,
|
| 100 |
+
"loss": 2.3576,
|
| 101 |
+
"step": 130
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.25688073394495414,
|
| 105 |
+
"grad_norm": 0.15440590679645538,
|
| 106 |
+
"learning_rate": 0.0008905094792353917,
|
| 107 |
+
"loss": 2.3236,
|
| 108 |
+
"step": 140
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.27522935779816515,
|
| 112 |
+
"grad_norm": 0.12773527204990387,
|
| 113 |
+
"learning_rate": 0.0008708260528239789,
|
| 114 |
+
"loss": 2.3047,
|
| 115 |
+
"step": 150
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.29357798165137616,
|
| 119 |
+
"grad_norm": 0.12827540934085846,
|
| 120 |
+
"learning_rate": 0.0008497737783108237,
|
| 121 |
+
"loss": 2.271,
|
| 122 |
+
"step": 160
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.3119266055045872,
|
| 126 |
+
"grad_norm": 0.12428344041109085,
|
| 127 |
+
"learning_rate": 0.0008274303669726426,
|
| 128 |
+
"loss": 2.2538,
|
| 129 |
+
"step": 170
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.3302752293577982,
|
| 133 |
+
"grad_norm": 0.17380541563034058,
|
| 134 |
+
"learning_rate": 0.0008038782961218137,
|
| 135 |
+
"loss": 2.2261,
|
| 136 |
+
"step": 180
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.3486238532110092,
|
| 140 |
+
"grad_norm": 0.17269816994667053,
|
| 141 |
+
"learning_rate": 0.000779204504653894,
|
| 142 |
+
"loss": 2.1934,
|
| 143 |
+
"step": 190
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.3669724770642202,
|
| 147 |
+
"grad_norm": 0.14062820374965668,
|
| 148 |
+
"learning_rate": 0.0007535000721258791,
|
| 149 |
+
"loss": 2.1434,
|
| 150 |
+
"step": 200
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.3853211009174312,
|
| 154 |
+
"grad_norm": 0.13783247768878937,
|
| 155 |
+
"learning_rate": 0.00072685988254984,
|
| 156 |
+
"loss": 2.119,
|
| 157 |
+
"step": 210
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.4036697247706422,
|
| 161 |
+
"grad_norm": 0.1178269237279892,
|
| 162 |
+
"learning_rate": 0.0006993822741429906,
|
| 163 |
+
"loss": 2.1086,
|
| 164 |
+
"step": 220
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.42201834862385323,
|
| 168 |
+
"grad_norm": 0.120763398706913,
|
| 169 |
+
"learning_rate": 0.0006711686763270818,
|
| 170 |
+
"loss": 2.0854,
|
| 171 |
+
"step": 230
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.44036697247706424,
|
| 175 |
+
"grad_norm": 0.11457717418670654,
|
| 176 |
+
"learning_rate": 0.0006423232353170831,
|
| 177 |
+
"loss": 2.0704,
|
| 178 |
+
"step": 240
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.45871559633027525,
|
| 182 |
+
"grad_norm": 0.11524111777544022,
|
| 183 |
+
"learning_rate": 0.0006129524296812335,
|
| 184 |
+
"loss": 2.0696,
|
| 185 |
+
"step": 250
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.47706422018348627,
|
| 189 |
+
"grad_norm": 0.10100659728050232,
|
| 190 |
+
"learning_rate": 0.0005831646772915651,
|
| 191 |
+
"loss": 2.0648,
|
| 192 |
+
"step": 260
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.4954128440366973,
|
| 196 |
+
"grad_norm": 0.11115681380033493,
|
| 197 |
+
"learning_rate": 0.0005530699351157809,
|
| 198 |
+
"loss": 2.0433,
|
| 199 |
+
"step": 270
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.5137614678899083,
|
| 203 |
+
"grad_norm": 0.09984961897134781,
|
| 204 |
+
"learning_rate": 0.0005227792933277943,
|
| 205 |
+
"loss": 2.0435,
|
| 206 |
+
"step": 280
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.5321100917431193,
|
| 210 |
+
"grad_norm": 0.10181327164173126,
|
| 211 |
+
"learning_rate": 0.0004924045652352092,
|
| 212 |
+
"loss": 2.0337,
|
| 213 |
+
"step": 290
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.5504587155963303,
|
| 217 |
+
"grad_norm": 0.09787877649068832,
|
| 218 |
+
"learning_rate": 0.0004620578745374633,
|
| 219 |
+
"loss": 2.0322,
|
| 220 |
+
"step": 300
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.5688073394495413,
|
| 224 |
+
"grad_norm": 0.14764176309108734,
|
| 225 |
+
"learning_rate": 0.0004318512414382059,
|
| 226 |
+
"loss": 2.0336,
|
| 227 |
+
"step": 310
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.5871559633027523,
|
| 231 |
+
"grad_norm": 0.09683510661125183,
|
| 232 |
+
"learning_rate": 0.0004018961691397148,
|
| 233 |
+
"loss": 2.0354,
|
| 234 |
+
"step": 320
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.6055045871559633,
|
| 238 |
+
"grad_norm": 0.10796148329973221,
|
| 239 |
+
"learning_rate": 0.0003723032322457458,
|
| 240 |
+
"loss": 2.0208,
|
| 241 |
+
"step": 330
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.6238532110091743,
|
| 245 |
+
"grad_norm": 0.11749578267335892,
|
| 246 |
+
"learning_rate": 0.0003431816685921625,
|
| 247 |
+
"loss": 2.021,
|
| 248 |
+
"step": 340
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.6422018348623854,
|
| 252 |
+
"grad_norm": 0.10644900053739548,
|
| 253 |
+
"learning_rate": 0.0003146389760120416,
|
| 254 |
+
"loss": 2.0171,
|
| 255 |
+
"step": 350
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.6605504587155964,
|
| 259 |
+
"grad_norm": 0.11325008422136307,
|
| 260 |
+
"learning_rate": 0.00028678051552373485,
|
| 261 |
+
"loss": 2.0171,
|
| 262 |
+
"step": 360
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.6788990825688074,
|
| 266 |
+
"grad_norm": 0.10159306228160858,
|
| 267 |
+
"learning_rate": 0.0002597091224066581,
|
| 268 |
+
"loss": 2.0085,
|
| 269 |
+
"step": 370
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.6972477064220184,
|
| 273 |
+
"grad_norm": 0.10147041827440262,
|
| 274 |
+
"learning_rate": 0.0002335247266004629,
|
| 275 |
+
"loss": 2.0153,
|
| 276 |
+
"step": 380
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.7155963302752294,
|
| 280 |
+
"grad_norm": 0.09809926152229309,
|
| 281 |
+
"learning_rate": 0.000208323983828828,
|
| 282 |
+
"loss": 2.0063,
|
| 283 |
+
"step": 390
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.7339449541284404,
|
| 287 |
+
"grad_norm": 0.09260130673646927,
|
| 288 |
+
"learning_rate": 0.0001841999188095224,
|
| 289 |
+
"loss": 2.0012,
|
| 290 |
+
"step": 400
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.7522935779816514,
|
| 294 |
+
"grad_norm": 0.09866929799318314,
|
| 295 |
+
"learning_rate": 0.00016124158186777676,
|
| 296 |
+
"loss": 2.0049,
|
| 297 |
+
"step": 410
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.7706422018348624,
|
| 301 |
+
"grad_norm": 0.09974569082260132,
|
| 302 |
+
"learning_rate": 0.0001395337202205211,
|
| 303 |
+
"loss": 1.9986,
|
| 304 |
+
"step": 420
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.7889908256880734,
|
| 308 |
+
"grad_norm": 0.0901578962802887,
|
| 309 |
+
"learning_rate": 0.00011915646514489292,
|
| 310 |
+
"loss": 1.9965,
|
| 311 |
+
"step": 430
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.8073394495412844,
|
| 315 |
+
"grad_norm": 0.10801990330219269,
|
| 316 |
+
"learning_rate": 0.00010018503618578818,
|
| 317 |
+
"loss": 2.0021,
|
| 318 |
+
"step": 440
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.8256880733944955,
|
| 322 |
+
"grad_norm": 0.09899371862411499,
|
| 323 |
+
"learning_rate": 8.268946349432583e-05,
|
| 324 |
+
"loss": 1.9965,
|
| 325 |
+
"step": 450
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.8440366972477065,
|
| 329 |
+
"grad_norm": 0.09687667340040207,
|
| 330 |
+
"learning_rate": 6.673432932217117e-05,
|
| 331 |
+
"loss": 1.9918,
|
| 332 |
+
"step": 460
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.8623853211009175,
|
| 336 |
+
"grad_norm": 0.09539948403835297,
|
| 337 |
+
"learning_rate": 5.2378529625954684e-05,
|
| 338 |
+
"loss": 1.9855,
|
| 339 |
+
"step": 470
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.8807339449541285,
|
| 343 |
+
"grad_norm": 0.08905789256095886,
|
| 344 |
+
"learning_rate": 3.9675056661785556e-05,
|
| 345 |
+
"loss": 1.9875,
|
| 346 |
+
"step": 480
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.8990825688073395,
|
| 350 |
+
"grad_norm": 0.09143490344285965,
|
| 351 |
+
"learning_rate": 2.8670803372379538e-05,
|
| 352 |
+
"loss": 1.9917,
|
| 353 |
+
"step": 490
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.9174311926605505,
|
| 357 |
+
"grad_norm": 0.09183184802532196,
|
| 358 |
+
"learning_rate": 1.9406390288876586e-05,
|
| 359 |
+
"loss": 1.9964,
|
| 360 |
+
"step": 500
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.9357798165137615,
|
| 364 |
+
"grad_norm": 0.09096000343561172,
|
| 365 |
+
"learning_rate": 1.191601558631461e-05,
|
| 366 |
+
"loss": 1.9878,
|
| 367 |
+
"step": 510
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.9541284403669725,
|
| 371 |
+
"grad_norm": 0.0909690335392952,
|
| 372 |
+
"learning_rate": 6.2273288462559305e-06,
|
| 373 |
+
"loss": 1.9846,
|
| 374 |
+
"step": 520
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.9724770642201835,
|
| 378 |
+
"grad_norm": 0.09225740283727646,
|
| 379 |
+
"learning_rate": 2.361328992552314e-06,
|
| 380 |
+
"loss": 1.9882,
|
| 381 |
+
"step": 530
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.9908256880733946,
|
| 385 |
+
"grad_norm": 0.09476163238286972,
|
| 386 |
+
"learning_rate": 3.322867770044202e-07,
|
| 387 |
+
"loss": 1.9848,
|
| 388 |
+
"step": 540
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 1.0,
|
| 392 |
+
"step": 545,
|
| 393 |
+
"total_flos": 5.783532109939343e+17,
|
| 394 |
+
"train_loss": 2.21468380569318,
|
| 395 |
+
"train_runtime": 1819.165,
|
| 396 |
+
"train_samples_per_second": 306.805,
|
| 397 |
+
"train_steps_per_second": 0.3
|
| 398 |
+
}
|
| 399 |
+
],
|
| 400 |
+
"logging_steps": 10,
|
| 401 |
+
"max_steps": 545,
|
| 402 |
+
"num_input_tokens_seen": 34658176,
|
| 403 |
+
"num_train_epochs": 1,
|
| 404 |
+
"save_steps": 500,
|
| 405 |
+
"stateful_callbacks": {
|
| 406 |
+
"TrainerControl": {
|
| 407 |
+
"args": {
|
| 408 |
+
"should_epoch_stop": false,
|
| 409 |
+
"should_evaluate": false,
|
| 410 |
+
"should_log": false,
|
| 411 |
+
"should_save": false,
|
| 412 |
+
"should_training_stop": false
|
| 413 |
+
},
|
| 414 |
+
"attributes": {}
|
| 415 |
+
}
|
| 416 |
+
},
|
| 417 |
+
"total_flos": 5.783532109939343e+17,
|
| 418 |
+
"train_batch_size": 64,
|
| 419 |
+
"trial_name": null,
|
| 420 |
+
"trial_params": null
|
| 421 |
+
}
|
continuous/smollm2/siglip2_g16_384/finetune/chat_template.jinja
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system
|
| 2 |
+
You are a helpful AI assistant named SmolLM, trained by Hugging Face<|im_end|>
|
| 3 |
+
' }}{% endif %}{{'<|im_start|>' + message['role'] + '
|
| 4 |
+
' + message['content'] + '<|im_end|>' + '
|
| 5 |
+
'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
|
| 6 |
+
' }}{% endif %}
|
continuous/smollm2/siglip2_g16_384/finetune/config.json
ADDED
|
@@ -0,0 +1,70 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_faster_video": false,
|
| 3 |
+
"add_time_instruction": false,
|
| 4 |
+
"architectures": [
|
| 5 |
+
"LlavaLlamaForCausalLM"
|
| 6 |
+
],
|
| 7 |
+
"attention_bias": false,
|
| 8 |
+
"attention_dropout": 0.0,
|
| 9 |
+
"bos_token_id": 1,
|
| 10 |
+
"dtype": "bfloat16",
|
| 11 |
+
"eos_token_id": 2,
|
| 12 |
+
"faster_token_stride": 10,
|
| 13 |
+
"force_sample": false,
|
| 14 |
+
"head_dim": 64,
|
| 15 |
+
"hidden_act": "silu",
|
| 16 |
+
"hidden_size": 2048,
|
| 17 |
+
"image_aspect_ratio": "square",
|
| 18 |
+
"image_crop_resolution": null,
|
| 19 |
+
"image_grid_pinpoints": null,
|
| 20 |
+
"image_split_resolution": null,
|
| 21 |
+
"initializer_range": 0.02,
|
| 22 |
+
"intermediate_size": 8192,
|
| 23 |
+
"max_position_embeddings": 8192,
|
| 24 |
+
"mlp_bias": false,
|
| 25 |
+
"mm_hidden_size": 1536,
|
| 26 |
+
"mm_newline_position": "grid",
|
| 27 |
+
"mm_patch_merge_type": "flat",
|
| 28 |
+
"mm_projector_lr": 0.0001,
|
| 29 |
+
"mm_projector_type": "mlp2x_gelu",
|
| 30 |
+
"mm_resampler_type": null,
|
| 31 |
+
"mm_spatial_pool_mode": "bilinear",
|
| 32 |
+
"mm_spatial_pool_stride": null,
|
| 33 |
+
"mm_tunable_parts": "mm_mlp_adapter,mm_language_model",
|
| 34 |
+
"mm_use_im_patch_token": false,
|
| 35 |
+
"mm_use_im_start_end": false,
|
| 36 |
+
"mm_vision_select_feature": "patch",
|
| 37 |
+
"mm_vision_select_layer": -2,
|
| 38 |
+
"mm_vision_tower": "open_clip_hub:ViT-gopt-16-SigLIP2-384",
|
| 39 |
+
"mm_vision_tower_lr": null,
|
| 40 |
+
"model_type": "llama",
|
| 41 |
+
"num_attention_heads": 32,
|
| 42 |
+
"num_hidden_layers": 24,
|
| 43 |
+
"num_key_value_heads": 32,
|
| 44 |
+
"pad_token_id": 0,
|
| 45 |
+
"pos_skipping_range": 4096,
|
| 46 |
+
"pretraining_tp": 1,
|
| 47 |
+
"rms_norm_eps": 1e-05,
|
| 48 |
+
"rope_scaling": null,
|
| 49 |
+
"rope_theta": 130000,
|
| 50 |
+
"tie_word_embeddings": true,
|
| 51 |
+
"tokenizer_model_max_length": 8192,
|
| 52 |
+
"tokenizer_padding_side": "right",
|
| 53 |
+
"transformers.js_config": {
|
| 54 |
+
"dtype": "q4",
|
| 55 |
+
"kv_cache_dtype": {
|
| 56 |
+
"fp16": "float16",
|
| 57 |
+
"q4f16": "float16"
|
| 58 |
+
},
|
| 59 |
+
"use_external_data_format": {
|
| 60 |
+
"model.onnx": true,
|
| 61 |
+
"model_fp16.onnx": true
|
| 62 |
+
}
|
| 63 |
+
},
|
| 64 |
+
"transformers_version": "4.57.6",
|
| 65 |
+
"use_cache": true,
|
| 66 |
+
"use_mm_proj": true,
|
| 67 |
+
"use_pos_skipping": false,
|
| 68 |
+
"vision_tower_pretrained": "/cache/ckpt/download/tokenizer/continuous/siglip2/siglip2_g16_384.npz",
|
| 69 |
+
"vocab_size": 49152
|
| 70 |
+
}
|
continuous/smollm2/siglip2_g16_384/finetune/generation_config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 1,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
2
|
| 6 |
+
],
|
| 7 |
+
"pad_token_id": 0,
|
| 8 |
+
"transformers_version": "4.57.6"
|
| 9 |
+
}
|
continuous/smollm2/siglip2_g16_384/finetune/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
continuous/smollm2/siglip2_g16_384/finetune/model-00001-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a735f809819956921ba0b39bb44eaccd8274377fc9d75e4a30eef107ab97df55
|
| 3 |
+
size 4994643344
|
continuous/smollm2/siglip2_g16_384/finetune/model-00002-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:669cec17577a09a251796652d05d843218e47f960fe271b01c766a605b5786b7
|
| 3 |
+
size 986225240
|
continuous/smollm2/siglip2_g16_384/finetune/model.safetensors.index.json
ADDED
|
@@ -0,0 +1,729 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_parameters": 2882380288,
|
| 4 |
+
"total_size": 5980775424
|
| 5 |
+
},
|
| 6 |
+
"weight_map": {
|
| 7 |
+
"lm_head.weight": "model-00002-of-00002.safetensors",
|
| 8 |
+
"model.embed_tokens.weight": "model-00001-of-00002.safetensors",
|
| 9 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 10 |
+
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 11 |
+
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 12 |
+
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 13 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 14 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 15 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 16 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 17 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 18 |
+
"model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 19 |
+
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 20 |
+
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 21 |
+
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 22 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 23 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 24 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 25 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 26 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 27 |
+
"model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 28 |
+
"model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 29 |
+
"model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 30 |
+
"model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 31 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 32 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 33 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 34 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 35 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 36 |
+
"model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 37 |
+
"model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 38 |
+
"model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 39 |
+
"model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 40 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 41 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 42 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 43 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 44 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 45 |
+
"model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 46 |
+
"model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 47 |
+
"model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 48 |
+
"model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 49 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 50 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 51 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 52 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 53 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 54 |
+
"model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 55 |
+
"model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 56 |
+
"model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 57 |
+
"model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 58 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 59 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 60 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 61 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 62 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 63 |
+
"model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 64 |
+
"model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 65 |
+
"model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 66 |
+
"model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 67 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 68 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 69 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 70 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 71 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 72 |
+
"model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 73 |
+
"model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 74 |
+
"model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 75 |
+
"model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 76 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 77 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 78 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 79 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 80 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 81 |
+
"model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 82 |
+
"model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 83 |
+
"model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 84 |
+
"model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 85 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 86 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 87 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 88 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 89 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 90 |
+
"model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 91 |
+
"model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 92 |
+
"model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 93 |
+
"model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 94 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 95 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 96 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 97 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 98 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 99 |
+
"model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 100 |
+
"model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 101 |
+
"model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 102 |
+
"model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 103 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 104 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 105 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 106 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 107 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 108 |
+
"model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 109 |
+
"model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 110 |
+
"model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 111 |
+
"model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 112 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 113 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 114 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 115 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 116 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 117 |
+
"model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 118 |
+
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 119 |
+
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 120 |
+
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 121 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 122 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 123 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 124 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 125 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 126 |
+
"model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 127 |
+
"model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 128 |
+
"model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 129 |
+
"model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 130 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 131 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 132 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 133 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 134 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 135 |
+
"model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 136 |
+
"model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 137 |
+
"model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 138 |
+
"model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 139 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 140 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 141 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 142 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 143 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 144 |
+
"model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 145 |
+
"model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 146 |
+
"model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 147 |
+
"model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 148 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 149 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 150 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 151 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 152 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 153 |
+
"model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 154 |
+
"model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 155 |
+
"model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 156 |
+
"model.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 157 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 158 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 159 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 160 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 161 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 162 |
+
"model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 163 |
+
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 164 |
+
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 165 |
+
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 166 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 167 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 168 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 169 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 170 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 171 |
+
"model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 172 |
+
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 173 |
+
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 174 |
+
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 175 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 176 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 177 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 178 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 179 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 180 |
+
"model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 181 |
+
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 182 |
+
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 183 |
+
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 184 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 185 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 186 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 187 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 188 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 189 |
+
"model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 190 |
+
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 191 |
+
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 192 |
+
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 193 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 194 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 195 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 196 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 197 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 198 |
+
"model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 199 |
+
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 200 |
+
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 201 |
+
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 202 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 203 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 204 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 205 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 206 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 207 |
+
"model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 208 |
+
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 209 |
+
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 210 |
+
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 211 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 212 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 213 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 214 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 215 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 216 |
+
"model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 217 |
+
"model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 218 |
+
"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 219 |
+
"model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 220 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 221 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 222 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 223 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 224 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 225 |
+
"model.mm_projector.0.bias": "model-00002-of-00002.safetensors",
|
| 226 |
+
"model.mm_projector.0.weight": "model-00002-of-00002.safetensors",
|
| 227 |
+
"model.mm_projector.2.bias": "model-00002-of-00002.safetensors",
|
| 228 |
+
"model.mm_projector.2.weight": "model-00002-of-00002.safetensors",
|
| 229 |
+
"model.norm.weight": "model-00001-of-00002.safetensors",
|
| 230 |
+
"model.vision_tower.vision_tower.trunk.attn_pool.kv.bias": "model-00002-of-00002.safetensors",
|
| 231 |
+
"model.vision_tower.vision_tower.trunk.attn_pool.kv.weight": "model-00002-of-00002.safetensors",
|
| 232 |
+
"model.vision_tower.vision_tower.trunk.attn_pool.latent": "model-00002-of-00002.safetensors",
|
| 233 |
+
"model.vision_tower.vision_tower.trunk.attn_pool.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
| 234 |
+
"model.vision_tower.vision_tower.trunk.attn_pool.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
| 235 |
+
"model.vision_tower.vision_tower.trunk.attn_pool.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
| 236 |
+
"model.vision_tower.vision_tower.trunk.attn_pool.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
| 237 |
+
"model.vision_tower.vision_tower.trunk.attn_pool.norm.bias": "model-00002-of-00002.safetensors",
|
| 238 |
+
"model.vision_tower.vision_tower.trunk.attn_pool.norm.weight": "model-00002-of-00002.safetensors",
|
| 239 |
+
"model.vision_tower.vision_tower.trunk.attn_pool.proj.bias": "model-00002-of-00002.safetensors",
|
| 240 |
+
"model.vision_tower.vision_tower.trunk.attn_pool.proj.weight": "model-00002-of-00002.safetensors",
|
| 241 |
+
"model.vision_tower.vision_tower.trunk.attn_pool.q.bias": "model-00002-of-00002.safetensors",
|
| 242 |
+
"model.vision_tower.vision_tower.trunk.attn_pool.q.weight": "model-00002-of-00002.safetensors",
|
| 243 |
+
"model.vision_tower.vision_tower.trunk.blocks.0.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 244 |
+
"model.vision_tower.vision_tower.trunk.blocks.0.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 245 |
+
"model.vision_tower.vision_tower.trunk.blocks.0.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 246 |
+
"model.vision_tower.vision_tower.trunk.blocks.0.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 247 |
+
"model.vision_tower.vision_tower.trunk.blocks.0.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 248 |
+
"model.vision_tower.vision_tower.trunk.blocks.0.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 249 |
+
"model.vision_tower.vision_tower.trunk.blocks.0.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 250 |
+
"model.vision_tower.vision_tower.trunk.blocks.0.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 251 |
+
"model.vision_tower.vision_tower.trunk.blocks.0.norm1.bias": "model-00001-of-00002.safetensors",
|
| 252 |
+
"model.vision_tower.vision_tower.trunk.blocks.0.norm1.weight": "model-00001-of-00002.safetensors",
|
| 253 |
+
"model.vision_tower.vision_tower.trunk.blocks.0.norm2.bias": "model-00001-of-00002.safetensors",
|
| 254 |
+
"model.vision_tower.vision_tower.trunk.blocks.0.norm2.weight": "model-00001-of-00002.safetensors",
|
| 255 |
+
"model.vision_tower.vision_tower.trunk.blocks.1.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 256 |
+
"model.vision_tower.vision_tower.trunk.blocks.1.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 257 |
+
"model.vision_tower.vision_tower.trunk.blocks.1.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 258 |
+
"model.vision_tower.vision_tower.trunk.blocks.1.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 259 |
+
"model.vision_tower.vision_tower.trunk.blocks.1.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 260 |
+
"model.vision_tower.vision_tower.trunk.blocks.1.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 261 |
+
"model.vision_tower.vision_tower.trunk.blocks.1.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 262 |
+
"model.vision_tower.vision_tower.trunk.blocks.1.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 263 |
+
"model.vision_tower.vision_tower.trunk.blocks.1.norm1.bias": "model-00001-of-00002.safetensors",
|
| 264 |
+
"model.vision_tower.vision_tower.trunk.blocks.1.norm1.weight": "model-00001-of-00002.safetensors",
|
| 265 |
+
"model.vision_tower.vision_tower.trunk.blocks.1.norm2.bias": "model-00001-of-00002.safetensors",
|
| 266 |
+
"model.vision_tower.vision_tower.trunk.blocks.1.norm2.weight": "model-00001-of-00002.safetensors",
|
| 267 |
+
"model.vision_tower.vision_tower.trunk.blocks.10.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 268 |
+
"model.vision_tower.vision_tower.trunk.blocks.10.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 269 |
+
"model.vision_tower.vision_tower.trunk.blocks.10.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 270 |
+
"model.vision_tower.vision_tower.trunk.blocks.10.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 271 |
+
"model.vision_tower.vision_tower.trunk.blocks.10.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 272 |
+
"model.vision_tower.vision_tower.trunk.blocks.10.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 273 |
+
"model.vision_tower.vision_tower.trunk.blocks.10.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 274 |
+
"model.vision_tower.vision_tower.trunk.blocks.10.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 275 |
+
"model.vision_tower.vision_tower.trunk.blocks.10.norm1.bias": "model-00001-of-00002.safetensors",
|
| 276 |
+
"model.vision_tower.vision_tower.trunk.blocks.10.norm1.weight": "model-00001-of-00002.safetensors",
|
| 277 |
+
"model.vision_tower.vision_tower.trunk.blocks.10.norm2.bias": "model-00001-of-00002.safetensors",
|
| 278 |
+
"model.vision_tower.vision_tower.trunk.blocks.10.norm2.weight": "model-00001-of-00002.safetensors",
|
| 279 |
+
"model.vision_tower.vision_tower.trunk.blocks.11.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 280 |
+
"model.vision_tower.vision_tower.trunk.blocks.11.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 281 |
+
"model.vision_tower.vision_tower.trunk.blocks.11.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 282 |
+
"model.vision_tower.vision_tower.trunk.blocks.11.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 283 |
+
"model.vision_tower.vision_tower.trunk.blocks.11.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 284 |
+
"model.vision_tower.vision_tower.trunk.blocks.11.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 285 |
+
"model.vision_tower.vision_tower.trunk.blocks.11.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 286 |
+
"model.vision_tower.vision_tower.trunk.blocks.11.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 287 |
+
"model.vision_tower.vision_tower.trunk.blocks.11.norm1.bias": "model-00001-of-00002.safetensors",
|
| 288 |
+
"model.vision_tower.vision_tower.trunk.blocks.11.norm1.weight": "model-00001-of-00002.safetensors",
|
| 289 |
+
"model.vision_tower.vision_tower.trunk.blocks.11.norm2.bias": "model-00001-of-00002.safetensors",
|
| 290 |
+
"model.vision_tower.vision_tower.trunk.blocks.11.norm2.weight": "model-00001-of-00002.safetensors",
|
| 291 |
+
"model.vision_tower.vision_tower.trunk.blocks.12.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 292 |
+
"model.vision_tower.vision_tower.trunk.blocks.12.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 293 |
+
"model.vision_tower.vision_tower.trunk.blocks.12.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 294 |
+
"model.vision_tower.vision_tower.trunk.blocks.12.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 295 |
+
"model.vision_tower.vision_tower.trunk.blocks.12.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 296 |
+
"model.vision_tower.vision_tower.trunk.blocks.12.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 297 |
+
"model.vision_tower.vision_tower.trunk.blocks.12.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 298 |
+
"model.vision_tower.vision_tower.trunk.blocks.12.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 299 |
+
"model.vision_tower.vision_tower.trunk.blocks.12.norm1.bias": "model-00001-of-00002.safetensors",
|
| 300 |
+
"model.vision_tower.vision_tower.trunk.blocks.12.norm1.weight": "model-00001-of-00002.safetensors",
|
| 301 |
+
"model.vision_tower.vision_tower.trunk.blocks.12.norm2.bias": "model-00001-of-00002.safetensors",
|
| 302 |
+
"model.vision_tower.vision_tower.trunk.blocks.12.norm2.weight": "model-00001-of-00002.safetensors",
|
| 303 |
+
"model.vision_tower.vision_tower.trunk.blocks.13.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 304 |
+
"model.vision_tower.vision_tower.trunk.blocks.13.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 305 |
+
"model.vision_tower.vision_tower.trunk.blocks.13.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 306 |
+
"model.vision_tower.vision_tower.trunk.blocks.13.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 307 |
+
"model.vision_tower.vision_tower.trunk.blocks.13.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 308 |
+
"model.vision_tower.vision_tower.trunk.blocks.13.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 309 |
+
"model.vision_tower.vision_tower.trunk.blocks.13.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 310 |
+
"model.vision_tower.vision_tower.trunk.blocks.13.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 311 |
+
"model.vision_tower.vision_tower.trunk.blocks.13.norm1.bias": "model-00001-of-00002.safetensors",
|
| 312 |
+
"model.vision_tower.vision_tower.trunk.blocks.13.norm1.weight": "model-00001-of-00002.safetensors",
|
| 313 |
+
"model.vision_tower.vision_tower.trunk.blocks.13.norm2.bias": "model-00001-of-00002.safetensors",
|
| 314 |
+
"model.vision_tower.vision_tower.trunk.blocks.13.norm2.weight": "model-00001-of-00002.safetensors",
|
| 315 |
+
"model.vision_tower.vision_tower.trunk.blocks.14.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 316 |
+
"model.vision_tower.vision_tower.trunk.blocks.14.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 317 |
+
"model.vision_tower.vision_tower.trunk.blocks.14.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 318 |
+
"model.vision_tower.vision_tower.trunk.blocks.14.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 319 |
+
"model.vision_tower.vision_tower.trunk.blocks.14.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 320 |
+
"model.vision_tower.vision_tower.trunk.blocks.14.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 321 |
+
"model.vision_tower.vision_tower.trunk.blocks.14.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 322 |
+
"model.vision_tower.vision_tower.trunk.blocks.14.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 323 |
+
"model.vision_tower.vision_tower.trunk.blocks.14.norm1.bias": "model-00001-of-00002.safetensors",
|
| 324 |
+
"model.vision_tower.vision_tower.trunk.blocks.14.norm1.weight": "model-00001-of-00002.safetensors",
|
| 325 |
+
"model.vision_tower.vision_tower.trunk.blocks.14.norm2.bias": "model-00001-of-00002.safetensors",
|
| 326 |
+
"model.vision_tower.vision_tower.trunk.blocks.14.norm2.weight": "model-00001-of-00002.safetensors",
|
| 327 |
+
"model.vision_tower.vision_tower.trunk.blocks.15.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 328 |
+
"model.vision_tower.vision_tower.trunk.blocks.15.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 329 |
+
"model.vision_tower.vision_tower.trunk.blocks.15.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 330 |
+
"model.vision_tower.vision_tower.trunk.blocks.15.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 331 |
+
"model.vision_tower.vision_tower.trunk.blocks.15.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 332 |
+
"model.vision_tower.vision_tower.trunk.blocks.15.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 333 |
+
"model.vision_tower.vision_tower.trunk.blocks.15.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 334 |
+
"model.vision_tower.vision_tower.trunk.blocks.15.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 335 |
+
"model.vision_tower.vision_tower.trunk.blocks.15.norm1.bias": "model-00001-of-00002.safetensors",
|
| 336 |
+
"model.vision_tower.vision_tower.trunk.blocks.15.norm1.weight": "model-00001-of-00002.safetensors",
|
| 337 |
+
"model.vision_tower.vision_tower.trunk.blocks.15.norm2.bias": "model-00001-of-00002.safetensors",
|
| 338 |
+
"model.vision_tower.vision_tower.trunk.blocks.15.norm2.weight": "model-00001-of-00002.safetensors",
|
| 339 |
+
"model.vision_tower.vision_tower.trunk.blocks.16.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 340 |
+
"model.vision_tower.vision_tower.trunk.blocks.16.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 341 |
+
"model.vision_tower.vision_tower.trunk.blocks.16.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 342 |
+
"model.vision_tower.vision_tower.trunk.blocks.16.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 343 |
+
"model.vision_tower.vision_tower.trunk.blocks.16.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 344 |
+
"model.vision_tower.vision_tower.trunk.blocks.16.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 345 |
+
"model.vision_tower.vision_tower.trunk.blocks.16.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 346 |
+
"model.vision_tower.vision_tower.trunk.blocks.16.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 347 |
+
"model.vision_tower.vision_tower.trunk.blocks.16.norm1.bias": "model-00001-of-00002.safetensors",
|
| 348 |
+
"model.vision_tower.vision_tower.trunk.blocks.16.norm1.weight": "model-00001-of-00002.safetensors",
|
| 349 |
+
"model.vision_tower.vision_tower.trunk.blocks.16.norm2.bias": "model-00001-of-00002.safetensors",
|
| 350 |
+
"model.vision_tower.vision_tower.trunk.blocks.16.norm2.weight": "model-00001-of-00002.safetensors",
|
| 351 |
+
"model.vision_tower.vision_tower.trunk.blocks.17.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 352 |
+
"model.vision_tower.vision_tower.trunk.blocks.17.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 353 |
+
"model.vision_tower.vision_tower.trunk.blocks.17.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 354 |
+
"model.vision_tower.vision_tower.trunk.blocks.17.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 355 |
+
"model.vision_tower.vision_tower.trunk.blocks.17.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 356 |
+
"model.vision_tower.vision_tower.trunk.blocks.17.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 357 |
+
"model.vision_tower.vision_tower.trunk.blocks.17.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 358 |
+
"model.vision_tower.vision_tower.trunk.blocks.17.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 359 |
+
"model.vision_tower.vision_tower.trunk.blocks.17.norm1.bias": "model-00001-of-00002.safetensors",
|
| 360 |
+
"model.vision_tower.vision_tower.trunk.blocks.17.norm1.weight": "model-00001-of-00002.safetensors",
|
| 361 |
+
"model.vision_tower.vision_tower.trunk.blocks.17.norm2.bias": "model-00001-of-00002.safetensors",
|
| 362 |
+
"model.vision_tower.vision_tower.trunk.blocks.17.norm2.weight": "model-00001-of-00002.safetensors",
|
| 363 |
+
"model.vision_tower.vision_tower.trunk.blocks.18.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 364 |
+
"model.vision_tower.vision_tower.trunk.blocks.18.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 365 |
+
"model.vision_tower.vision_tower.trunk.blocks.18.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 366 |
+
"model.vision_tower.vision_tower.trunk.blocks.18.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 367 |
+
"model.vision_tower.vision_tower.trunk.blocks.18.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 368 |
+
"model.vision_tower.vision_tower.trunk.blocks.18.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 369 |
+
"model.vision_tower.vision_tower.trunk.blocks.18.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 370 |
+
"model.vision_tower.vision_tower.trunk.blocks.18.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 371 |
+
"model.vision_tower.vision_tower.trunk.blocks.18.norm1.bias": "model-00001-of-00002.safetensors",
|
| 372 |
+
"model.vision_tower.vision_tower.trunk.blocks.18.norm1.weight": "model-00001-of-00002.safetensors",
|
| 373 |
+
"model.vision_tower.vision_tower.trunk.blocks.18.norm2.bias": "model-00001-of-00002.safetensors",
|
| 374 |
+
"model.vision_tower.vision_tower.trunk.blocks.18.norm2.weight": "model-00001-of-00002.safetensors",
|
| 375 |
+
"model.vision_tower.vision_tower.trunk.blocks.19.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 376 |
+
"model.vision_tower.vision_tower.trunk.blocks.19.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 377 |
+
"model.vision_tower.vision_tower.trunk.blocks.19.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 378 |
+
"model.vision_tower.vision_tower.trunk.blocks.19.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 379 |
+
"model.vision_tower.vision_tower.trunk.blocks.19.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 380 |
+
"model.vision_tower.vision_tower.trunk.blocks.19.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 381 |
+
"model.vision_tower.vision_tower.trunk.blocks.19.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 382 |
+
"model.vision_tower.vision_tower.trunk.blocks.19.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 383 |
+
"model.vision_tower.vision_tower.trunk.blocks.19.norm1.bias": "model-00001-of-00002.safetensors",
|
| 384 |
+
"model.vision_tower.vision_tower.trunk.blocks.19.norm1.weight": "model-00001-of-00002.safetensors",
|
| 385 |
+
"model.vision_tower.vision_tower.trunk.blocks.19.norm2.bias": "model-00001-of-00002.safetensors",
|
| 386 |
+
"model.vision_tower.vision_tower.trunk.blocks.19.norm2.weight": "model-00001-of-00002.safetensors",
|
| 387 |
+
"model.vision_tower.vision_tower.trunk.blocks.2.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 388 |
+
"model.vision_tower.vision_tower.trunk.blocks.2.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 389 |
+
"model.vision_tower.vision_tower.trunk.blocks.2.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 390 |
+
"model.vision_tower.vision_tower.trunk.blocks.2.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 391 |
+
"model.vision_tower.vision_tower.trunk.blocks.2.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 392 |
+
"model.vision_tower.vision_tower.trunk.blocks.2.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 393 |
+
"model.vision_tower.vision_tower.trunk.blocks.2.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 394 |
+
"model.vision_tower.vision_tower.trunk.blocks.2.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 395 |
+
"model.vision_tower.vision_tower.trunk.blocks.2.norm1.bias": "model-00001-of-00002.safetensors",
|
| 396 |
+
"model.vision_tower.vision_tower.trunk.blocks.2.norm1.weight": "model-00001-of-00002.safetensors",
|
| 397 |
+
"model.vision_tower.vision_tower.trunk.blocks.2.norm2.bias": "model-00001-of-00002.safetensors",
|
| 398 |
+
"model.vision_tower.vision_tower.trunk.blocks.2.norm2.weight": "model-00001-of-00002.safetensors",
|
| 399 |
+
"model.vision_tower.vision_tower.trunk.blocks.20.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 400 |
+
"model.vision_tower.vision_tower.trunk.blocks.20.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 401 |
+
"model.vision_tower.vision_tower.trunk.blocks.20.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 402 |
+
"model.vision_tower.vision_tower.trunk.blocks.20.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 403 |
+
"model.vision_tower.vision_tower.trunk.blocks.20.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 404 |
+
"model.vision_tower.vision_tower.trunk.blocks.20.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 405 |
+
"model.vision_tower.vision_tower.trunk.blocks.20.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 406 |
+
"model.vision_tower.vision_tower.trunk.blocks.20.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 407 |
+
"model.vision_tower.vision_tower.trunk.blocks.20.norm1.bias": "model-00001-of-00002.safetensors",
|
| 408 |
+
"model.vision_tower.vision_tower.trunk.blocks.20.norm1.weight": "model-00001-of-00002.safetensors",
|
| 409 |
+
"model.vision_tower.vision_tower.trunk.blocks.20.norm2.bias": "model-00001-of-00002.safetensors",
|
| 410 |
+
"model.vision_tower.vision_tower.trunk.blocks.20.norm2.weight": "model-00001-of-00002.safetensors",
|
| 411 |
+
"model.vision_tower.vision_tower.trunk.blocks.21.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 412 |
+
"model.vision_tower.vision_tower.trunk.blocks.21.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 413 |
+
"model.vision_tower.vision_tower.trunk.blocks.21.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 414 |
+
"model.vision_tower.vision_tower.trunk.blocks.21.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 415 |
+
"model.vision_tower.vision_tower.trunk.blocks.21.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 416 |
+
"model.vision_tower.vision_tower.trunk.blocks.21.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 417 |
+
"model.vision_tower.vision_tower.trunk.blocks.21.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 418 |
+
"model.vision_tower.vision_tower.trunk.blocks.21.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 419 |
+
"model.vision_tower.vision_tower.trunk.blocks.21.norm1.bias": "model-00001-of-00002.safetensors",
|
| 420 |
+
"model.vision_tower.vision_tower.trunk.blocks.21.norm1.weight": "model-00001-of-00002.safetensors",
|
| 421 |
+
"model.vision_tower.vision_tower.trunk.blocks.21.norm2.bias": "model-00001-of-00002.safetensors",
|
| 422 |
+
"model.vision_tower.vision_tower.trunk.blocks.21.norm2.weight": "model-00001-of-00002.safetensors",
|
| 423 |
+
"model.vision_tower.vision_tower.trunk.blocks.22.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 424 |
+
"model.vision_tower.vision_tower.trunk.blocks.22.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 425 |
+
"model.vision_tower.vision_tower.trunk.blocks.22.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 426 |
+
"model.vision_tower.vision_tower.trunk.blocks.22.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 427 |
+
"model.vision_tower.vision_tower.trunk.blocks.22.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 428 |
+
"model.vision_tower.vision_tower.trunk.blocks.22.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 429 |
+
"model.vision_tower.vision_tower.trunk.blocks.22.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 430 |
+
"model.vision_tower.vision_tower.trunk.blocks.22.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 431 |
+
"model.vision_tower.vision_tower.trunk.blocks.22.norm1.bias": "model-00001-of-00002.safetensors",
|
| 432 |
+
"model.vision_tower.vision_tower.trunk.blocks.22.norm1.weight": "model-00001-of-00002.safetensors",
|
| 433 |
+
"model.vision_tower.vision_tower.trunk.blocks.22.norm2.bias": "model-00001-of-00002.safetensors",
|
| 434 |
+
"model.vision_tower.vision_tower.trunk.blocks.22.norm2.weight": "model-00001-of-00002.safetensors",
|
| 435 |
+
"model.vision_tower.vision_tower.trunk.blocks.23.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 436 |
+
"model.vision_tower.vision_tower.trunk.blocks.23.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 437 |
+
"model.vision_tower.vision_tower.trunk.blocks.23.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 438 |
+
"model.vision_tower.vision_tower.trunk.blocks.23.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 439 |
+
"model.vision_tower.vision_tower.trunk.blocks.23.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 440 |
+
"model.vision_tower.vision_tower.trunk.blocks.23.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 441 |
+
"model.vision_tower.vision_tower.trunk.blocks.23.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 442 |
+
"model.vision_tower.vision_tower.trunk.blocks.23.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 443 |
+
"model.vision_tower.vision_tower.trunk.blocks.23.norm1.bias": "model-00001-of-00002.safetensors",
|
| 444 |
+
"model.vision_tower.vision_tower.trunk.blocks.23.norm1.weight": "model-00001-of-00002.safetensors",
|
| 445 |
+
"model.vision_tower.vision_tower.trunk.blocks.23.norm2.bias": "model-00001-of-00002.safetensors",
|
| 446 |
+
"model.vision_tower.vision_tower.trunk.blocks.23.norm2.weight": "model-00001-of-00002.safetensors",
|
| 447 |
+
"model.vision_tower.vision_tower.trunk.blocks.24.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 448 |
+
"model.vision_tower.vision_tower.trunk.blocks.24.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 449 |
+
"model.vision_tower.vision_tower.trunk.blocks.24.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 450 |
+
"model.vision_tower.vision_tower.trunk.blocks.24.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 451 |
+
"model.vision_tower.vision_tower.trunk.blocks.24.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 452 |
+
"model.vision_tower.vision_tower.trunk.blocks.24.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 453 |
+
"model.vision_tower.vision_tower.trunk.blocks.24.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 454 |
+
"model.vision_tower.vision_tower.trunk.blocks.24.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 455 |
+
"model.vision_tower.vision_tower.trunk.blocks.24.norm1.bias": "model-00001-of-00002.safetensors",
|
| 456 |
+
"model.vision_tower.vision_tower.trunk.blocks.24.norm1.weight": "model-00001-of-00002.safetensors",
|
| 457 |
+
"model.vision_tower.vision_tower.trunk.blocks.24.norm2.bias": "model-00001-of-00002.safetensors",
|
| 458 |
+
"model.vision_tower.vision_tower.trunk.blocks.24.norm2.weight": "model-00001-of-00002.safetensors",
|
| 459 |
+
"model.vision_tower.vision_tower.trunk.blocks.25.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 460 |
+
"model.vision_tower.vision_tower.trunk.blocks.25.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 461 |
+
"model.vision_tower.vision_tower.trunk.blocks.25.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 462 |
+
"model.vision_tower.vision_tower.trunk.blocks.25.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 463 |
+
"model.vision_tower.vision_tower.trunk.blocks.25.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 464 |
+
"model.vision_tower.vision_tower.trunk.blocks.25.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 465 |
+
"model.vision_tower.vision_tower.trunk.blocks.25.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 466 |
+
"model.vision_tower.vision_tower.trunk.blocks.25.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 467 |
+
"model.vision_tower.vision_tower.trunk.blocks.25.norm1.bias": "model-00001-of-00002.safetensors",
|
| 468 |
+
"model.vision_tower.vision_tower.trunk.blocks.25.norm1.weight": "model-00001-of-00002.safetensors",
|
| 469 |
+
"model.vision_tower.vision_tower.trunk.blocks.25.norm2.bias": "model-00001-of-00002.safetensors",
|
| 470 |
+
"model.vision_tower.vision_tower.trunk.blocks.25.norm2.weight": "model-00001-of-00002.safetensors",
|
| 471 |
+
"model.vision_tower.vision_tower.trunk.blocks.26.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 472 |
+
"model.vision_tower.vision_tower.trunk.blocks.26.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 473 |
+
"model.vision_tower.vision_tower.trunk.blocks.26.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 474 |
+
"model.vision_tower.vision_tower.trunk.blocks.26.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 475 |
+
"model.vision_tower.vision_tower.trunk.blocks.26.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 476 |
+
"model.vision_tower.vision_tower.trunk.blocks.26.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 477 |
+
"model.vision_tower.vision_tower.trunk.blocks.26.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 478 |
+
"model.vision_tower.vision_tower.trunk.blocks.26.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 479 |
+
"model.vision_tower.vision_tower.trunk.blocks.26.norm1.bias": "model-00001-of-00002.safetensors",
|
| 480 |
+
"model.vision_tower.vision_tower.trunk.blocks.26.norm1.weight": "model-00001-of-00002.safetensors",
|
| 481 |
+
"model.vision_tower.vision_tower.trunk.blocks.26.norm2.bias": "model-00001-of-00002.safetensors",
|
| 482 |
+
"model.vision_tower.vision_tower.trunk.blocks.26.norm2.weight": "model-00001-of-00002.safetensors",
|
| 483 |
+
"model.vision_tower.vision_tower.trunk.blocks.27.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 484 |
+
"model.vision_tower.vision_tower.trunk.blocks.27.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 485 |
+
"model.vision_tower.vision_tower.trunk.blocks.27.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 486 |
+
"model.vision_tower.vision_tower.trunk.blocks.27.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 487 |
+
"model.vision_tower.vision_tower.trunk.blocks.27.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 488 |
+
"model.vision_tower.vision_tower.trunk.blocks.27.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 489 |
+
"model.vision_tower.vision_tower.trunk.blocks.27.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
| 490 |
+
"model.vision_tower.vision_tower.trunk.blocks.27.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
| 491 |
+
"model.vision_tower.vision_tower.trunk.blocks.27.norm1.bias": "model-00001-of-00002.safetensors",
|
| 492 |
+
"model.vision_tower.vision_tower.trunk.blocks.27.norm1.weight": "model-00001-of-00002.safetensors",
|
| 493 |
+
"model.vision_tower.vision_tower.trunk.blocks.27.norm2.bias": "model-00001-of-00002.safetensors",
|
| 494 |
+
"model.vision_tower.vision_tower.trunk.blocks.27.norm2.weight": "model-00001-of-00002.safetensors",
|
| 495 |
+
"model.vision_tower.vision_tower.trunk.blocks.28.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 496 |
+
"model.vision_tower.vision_tower.trunk.blocks.28.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 497 |
+
"model.vision_tower.vision_tower.trunk.blocks.28.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 498 |
+
"model.vision_tower.vision_tower.trunk.blocks.28.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 499 |
+
"model.vision_tower.vision_tower.trunk.blocks.28.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
| 500 |
+
"model.vision_tower.vision_tower.trunk.blocks.28.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
| 501 |
+
"model.vision_tower.vision_tower.trunk.blocks.28.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
| 502 |
+
"model.vision_tower.vision_tower.trunk.blocks.28.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
| 503 |
+
"model.vision_tower.vision_tower.trunk.blocks.28.norm1.bias": "model-00002-of-00002.safetensors",
|
| 504 |
+
"model.vision_tower.vision_tower.trunk.blocks.28.norm1.weight": "model-00002-of-00002.safetensors",
|
| 505 |
+
"model.vision_tower.vision_tower.trunk.blocks.28.norm2.bias": "model-00002-of-00002.safetensors",
|
| 506 |
+
"model.vision_tower.vision_tower.trunk.blocks.28.norm2.weight": "model-00002-of-00002.safetensors",
|
| 507 |
+
"model.vision_tower.vision_tower.trunk.blocks.29.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 508 |
+
"model.vision_tower.vision_tower.trunk.blocks.29.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 509 |
+
"model.vision_tower.vision_tower.trunk.blocks.29.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 510 |
+
"model.vision_tower.vision_tower.trunk.blocks.29.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 511 |
+
"model.vision_tower.vision_tower.trunk.blocks.29.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
| 512 |
+
"model.vision_tower.vision_tower.trunk.blocks.29.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
| 513 |
+
"model.vision_tower.vision_tower.trunk.blocks.29.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
| 514 |
+
"model.vision_tower.vision_tower.trunk.blocks.29.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
| 515 |
+
"model.vision_tower.vision_tower.trunk.blocks.29.norm1.bias": "model-00002-of-00002.safetensors",
|
| 516 |
+
"model.vision_tower.vision_tower.trunk.blocks.29.norm1.weight": "model-00002-of-00002.safetensors",
|
| 517 |
+
"model.vision_tower.vision_tower.trunk.blocks.29.norm2.bias": "model-00002-of-00002.safetensors",
|
| 518 |
+
"model.vision_tower.vision_tower.trunk.blocks.29.norm2.weight": "model-00002-of-00002.safetensors",
|
| 519 |
+
"model.vision_tower.vision_tower.trunk.blocks.3.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 520 |
+
"model.vision_tower.vision_tower.trunk.blocks.3.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 521 |
+
"model.vision_tower.vision_tower.trunk.blocks.3.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 522 |
+
"model.vision_tower.vision_tower.trunk.blocks.3.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 523 |
+
"model.vision_tower.vision_tower.trunk.blocks.3.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 524 |
+
"model.vision_tower.vision_tower.trunk.blocks.3.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 525 |
+
"model.vision_tower.vision_tower.trunk.blocks.3.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 526 |
+
"model.vision_tower.vision_tower.trunk.blocks.3.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 527 |
+
"model.vision_tower.vision_tower.trunk.blocks.3.norm1.bias": "model-00001-of-00002.safetensors",
|
| 528 |
+
"model.vision_tower.vision_tower.trunk.blocks.3.norm1.weight": "model-00001-of-00002.safetensors",
|
| 529 |
+
"model.vision_tower.vision_tower.trunk.blocks.3.norm2.bias": "model-00001-of-00002.safetensors",
|
| 530 |
+
"model.vision_tower.vision_tower.trunk.blocks.3.norm2.weight": "model-00001-of-00002.safetensors",
|
| 531 |
+
"model.vision_tower.vision_tower.trunk.blocks.30.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 532 |
+
"model.vision_tower.vision_tower.trunk.blocks.30.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 533 |
+
"model.vision_tower.vision_tower.trunk.blocks.30.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 534 |
+
"model.vision_tower.vision_tower.trunk.blocks.30.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 535 |
+
"model.vision_tower.vision_tower.trunk.blocks.30.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
| 536 |
+
"model.vision_tower.vision_tower.trunk.blocks.30.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
| 537 |
+
"model.vision_tower.vision_tower.trunk.blocks.30.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
| 538 |
+
"model.vision_tower.vision_tower.trunk.blocks.30.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
| 539 |
+
"model.vision_tower.vision_tower.trunk.blocks.30.norm1.bias": "model-00002-of-00002.safetensors",
|
| 540 |
+
"model.vision_tower.vision_tower.trunk.blocks.30.norm1.weight": "model-00002-of-00002.safetensors",
|
| 541 |
+
"model.vision_tower.vision_tower.trunk.blocks.30.norm2.bias": "model-00002-of-00002.safetensors",
|
| 542 |
+
"model.vision_tower.vision_tower.trunk.blocks.30.norm2.weight": "model-00002-of-00002.safetensors",
|
| 543 |
+
"model.vision_tower.vision_tower.trunk.blocks.31.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 544 |
+
"model.vision_tower.vision_tower.trunk.blocks.31.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 545 |
+
"model.vision_tower.vision_tower.trunk.blocks.31.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 546 |
+
"model.vision_tower.vision_tower.trunk.blocks.31.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 547 |
+
"model.vision_tower.vision_tower.trunk.blocks.31.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
| 548 |
+
"model.vision_tower.vision_tower.trunk.blocks.31.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
| 549 |
+
"model.vision_tower.vision_tower.trunk.blocks.31.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
| 550 |
+
"model.vision_tower.vision_tower.trunk.blocks.31.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
| 551 |
+
"model.vision_tower.vision_tower.trunk.blocks.31.norm1.bias": "model-00002-of-00002.safetensors",
|
| 552 |
+
"model.vision_tower.vision_tower.trunk.blocks.31.norm1.weight": "model-00002-of-00002.safetensors",
|
| 553 |
+
"model.vision_tower.vision_tower.trunk.blocks.31.norm2.bias": "model-00002-of-00002.safetensors",
|
| 554 |
+
"model.vision_tower.vision_tower.trunk.blocks.31.norm2.weight": "model-00002-of-00002.safetensors",
|
| 555 |
+
"model.vision_tower.vision_tower.trunk.blocks.32.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 556 |
+
"model.vision_tower.vision_tower.trunk.blocks.32.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 557 |
+
"model.vision_tower.vision_tower.trunk.blocks.32.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 558 |
+
"model.vision_tower.vision_tower.trunk.blocks.32.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 559 |
+
"model.vision_tower.vision_tower.trunk.blocks.32.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
| 560 |
+
"model.vision_tower.vision_tower.trunk.blocks.32.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
| 561 |
+
"model.vision_tower.vision_tower.trunk.blocks.32.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
| 562 |
+
"model.vision_tower.vision_tower.trunk.blocks.32.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
| 563 |
+
"model.vision_tower.vision_tower.trunk.blocks.32.norm1.bias": "model-00002-of-00002.safetensors",
|
| 564 |
+
"model.vision_tower.vision_tower.trunk.blocks.32.norm1.weight": "model-00002-of-00002.safetensors",
|
| 565 |
+
"model.vision_tower.vision_tower.trunk.blocks.32.norm2.bias": "model-00002-of-00002.safetensors",
|
| 566 |
+
"model.vision_tower.vision_tower.trunk.blocks.32.norm2.weight": "model-00002-of-00002.safetensors",
|
| 567 |
+
"model.vision_tower.vision_tower.trunk.blocks.33.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 568 |
+
"model.vision_tower.vision_tower.trunk.blocks.33.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 569 |
+
"model.vision_tower.vision_tower.trunk.blocks.33.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 570 |
+
"model.vision_tower.vision_tower.trunk.blocks.33.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 571 |
+
"model.vision_tower.vision_tower.trunk.blocks.33.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
| 572 |
+
"model.vision_tower.vision_tower.trunk.blocks.33.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
| 573 |
+
"model.vision_tower.vision_tower.trunk.blocks.33.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
| 574 |
+
"model.vision_tower.vision_tower.trunk.blocks.33.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
| 575 |
+
"model.vision_tower.vision_tower.trunk.blocks.33.norm1.bias": "model-00002-of-00002.safetensors",
|
| 576 |
+
"model.vision_tower.vision_tower.trunk.blocks.33.norm1.weight": "model-00002-of-00002.safetensors",
|
| 577 |
+
"model.vision_tower.vision_tower.trunk.blocks.33.norm2.bias": "model-00002-of-00002.safetensors",
|
| 578 |
+
"model.vision_tower.vision_tower.trunk.blocks.33.norm2.weight": "model-00002-of-00002.safetensors",
|
| 579 |
+
"model.vision_tower.vision_tower.trunk.blocks.34.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 580 |
+
"model.vision_tower.vision_tower.trunk.blocks.34.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 581 |
+
"model.vision_tower.vision_tower.trunk.blocks.34.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 582 |
+
"model.vision_tower.vision_tower.trunk.blocks.34.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 583 |
+
"model.vision_tower.vision_tower.trunk.blocks.34.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
| 584 |
+
"model.vision_tower.vision_tower.trunk.blocks.34.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
| 585 |
+
"model.vision_tower.vision_tower.trunk.blocks.34.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
| 586 |
+
"model.vision_tower.vision_tower.trunk.blocks.34.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
| 587 |
+
"model.vision_tower.vision_tower.trunk.blocks.34.norm1.bias": "model-00002-of-00002.safetensors",
|
| 588 |
+
"model.vision_tower.vision_tower.trunk.blocks.34.norm1.weight": "model-00002-of-00002.safetensors",
|
| 589 |
+
"model.vision_tower.vision_tower.trunk.blocks.34.norm2.bias": "model-00002-of-00002.safetensors",
|
| 590 |
+
"model.vision_tower.vision_tower.trunk.blocks.34.norm2.weight": "model-00002-of-00002.safetensors",
|
| 591 |
+
"model.vision_tower.vision_tower.trunk.blocks.35.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 592 |
+
"model.vision_tower.vision_tower.trunk.blocks.35.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 593 |
+
"model.vision_tower.vision_tower.trunk.blocks.35.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 594 |
+
"model.vision_tower.vision_tower.trunk.blocks.35.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 595 |
+
"model.vision_tower.vision_tower.trunk.blocks.35.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
| 596 |
+
"model.vision_tower.vision_tower.trunk.blocks.35.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
| 597 |
+
"model.vision_tower.vision_tower.trunk.blocks.35.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
| 598 |
+
"model.vision_tower.vision_tower.trunk.blocks.35.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
| 599 |
+
"model.vision_tower.vision_tower.trunk.blocks.35.norm1.bias": "model-00002-of-00002.safetensors",
|
| 600 |
+
"model.vision_tower.vision_tower.trunk.blocks.35.norm1.weight": "model-00002-of-00002.safetensors",
|
| 601 |
+
"model.vision_tower.vision_tower.trunk.blocks.35.norm2.bias": "model-00002-of-00002.safetensors",
|
| 602 |
+
"model.vision_tower.vision_tower.trunk.blocks.35.norm2.weight": "model-00002-of-00002.safetensors",
|
| 603 |
+
"model.vision_tower.vision_tower.trunk.blocks.36.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 604 |
+
"model.vision_tower.vision_tower.trunk.blocks.36.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 605 |
+
"model.vision_tower.vision_tower.trunk.blocks.36.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 606 |
+
"model.vision_tower.vision_tower.trunk.blocks.36.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 607 |
+
"model.vision_tower.vision_tower.trunk.blocks.36.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
| 608 |
+
"model.vision_tower.vision_tower.trunk.blocks.36.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
| 609 |
+
"model.vision_tower.vision_tower.trunk.blocks.36.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
| 610 |
+
"model.vision_tower.vision_tower.trunk.blocks.36.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
| 611 |
+
"model.vision_tower.vision_tower.trunk.blocks.36.norm1.bias": "model-00002-of-00002.safetensors",
|
| 612 |
+
"model.vision_tower.vision_tower.trunk.blocks.36.norm1.weight": "model-00002-of-00002.safetensors",
|
| 613 |
+
"model.vision_tower.vision_tower.trunk.blocks.36.norm2.bias": "model-00002-of-00002.safetensors",
|
| 614 |
+
"model.vision_tower.vision_tower.trunk.blocks.36.norm2.weight": "model-00002-of-00002.safetensors",
|
| 615 |
+
"model.vision_tower.vision_tower.trunk.blocks.37.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 616 |
+
"model.vision_tower.vision_tower.trunk.blocks.37.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 617 |
+
"model.vision_tower.vision_tower.trunk.blocks.37.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 618 |
+
"model.vision_tower.vision_tower.trunk.blocks.37.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 619 |
+
"model.vision_tower.vision_tower.trunk.blocks.37.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
| 620 |
+
"model.vision_tower.vision_tower.trunk.blocks.37.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
| 621 |
+
"model.vision_tower.vision_tower.trunk.blocks.37.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
| 622 |
+
"model.vision_tower.vision_tower.trunk.blocks.37.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
| 623 |
+
"model.vision_tower.vision_tower.trunk.blocks.37.norm1.bias": "model-00002-of-00002.safetensors",
|
| 624 |
+
"model.vision_tower.vision_tower.trunk.blocks.37.norm1.weight": "model-00002-of-00002.safetensors",
|
| 625 |
+
"model.vision_tower.vision_tower.trunk.blocks.37.norm2.bias": "model-00002-of-00002.safetensors",
|
| 626 |
+
"model.vision_tower.vision_tower.trunk.blocks.37.norm2.weight": "model-00002-of-00002.safetensors",
|
| 627 |
+
"model.vision_tower.vision_tower.trunk.blocks.38.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 628 |
+
"model.vision_tower.vision_tower.trunk.blocks.38.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 629 |
+
"model.vision_tower.vision_tower.trunk.blocks.38.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 630 |
+
"model.vision_tower.vision_tower.trunk.blocks.38.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 631 |
+
"model.vision_tower.vision_tower.trunk.blocks.38.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
| 632 |
+
"model.vision_tower.vision_tower.trunk.blocks.38.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
| 633 |
+
"model.vision_tower.vision_tower.trunk.blocks.38.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
| 634 |
+
"model.vision_tower.vision_tower.trunk.blocks.38.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
| 635 |
+
"model.vision_tower.vision_tower.trunk.blocks.38.norm1.bias": "model-00002-of-00002.safetensors",
|
| 636 |
+
"model.vision_tower.vision_tower.trunk.blocks.38.norm1.weight": "model-00002-of-00002.safetensors",
|
| 637 |
+
"model.vision_tower.vision_tower.trunk.blocks.38.norm2.bias": "model-00002-of-00002.safetensors",
|
| 638 |
+
"model.vision_tower.vision_tower.trunk.blocks.38.norm2.weight": "model-00002-of-00002.safetensors",
|
| 639 |
+
"model.vision_tower.vision_tower.trunk.blocks.39.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 640 |
+
"model.vision_tower.vision_tower.trunk.blocks.39.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 641 |
+
"model.vision_tower.vision_tower.trunk.blocks.39.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 642 |
+
"model.vision_tower.vision_tower.trunk.blocks.39.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 643 |
+
"model.vision_tower.vision_tower.trunk.blocks.39.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
| 644 |
+
"model.vision_tower.vision_tower.trunk.blocks.39.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
| 645 |
+
"model.vision_tower.vision_tower.trunk.blocks.39.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
| 646 |
+
"model.vision_tower.vision_tower.trunk.blocks.39.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
| 647 |
+
"model.vision_tower.vision_tower.trunk.blocks.39.norm1.bias": "model-00002-of-00002.safetensors",
|
| 648 |
+
"model.vision_tower.vision_tower.trunk.blocks.39.norm1.weight": "model-00002-of-00002.safetensors",
|
| 649 |
+
"model.vision_tower.vision_tower.trunk.blocks.39.norm2.bias": "model-00002-of-00002.safetensors",
|
| 650 |
+
"model.vision_tower.vision_tower.trunk.blocks.39.norm2.weight": "model-00002-of-00002.safetensors",
|
| 651 |
+
"model.vision_tower.vision_tower.trunk.blocks.4.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 652 |
+
"model.vision_tower.vision_tower.trunk.blocks.4.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 653 |
+
"model.vision_tower.vision_tower.trunk.blocks.4.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 654 |
+
"model.vision_tower.vision_tower.trunk.blocks.4.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 655 |
+
"model.vision_tower.vision_tower.trunk.blocks.4.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 656 |
+
"model.vision_tower.vision_tower.trunk.blocks.4.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 657 |
+
"model.vision_tower.vision_tower.trunk.blocks.4.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 658 |
+
"model.vision_tower.vision_tower.trunk.blocks.4.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 659 |
+
"model.vision_tower.vision_tower.trunk.blocks.4.norm1.bias": "model-00001-of-00002.safetensors",
|
| 660 |
+
"model.vision_tower.vision_tower.trunk.blocks.4.norm1.weight": "model-00001-of-00002.safetensors",
|
| 661 |
+
"model.vision_tower.vision_tower.trunk.blocks.4.norm2.bias": "model-00001-of-00002.safetensors",
|
| 662 |
+
"model.vision_tower.vision_tower.trunk.blocks.4.norm2.weight": "model-00001-of-00002.safetensors",
|
| 663 |
+
"model.vision_tower.vision_tower.trunk.blocks.5.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 664 |
+
"model.vision_tower.vision_tower.trunk.blocks.5.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 665 |
+
"model.vision_tower.vision_tower.trunk.blocks.5.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 666 |
+
"model.vision_tower.vision_tower.trunk.blocks.5.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 667 |
+
"model.vision_tower.vision_tower.trunk.blocks.5.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 668 |
+
"model.vision_tower.vision_tower.trunk.blocks.5.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 669 |
+
"model.vision_tower.vision_tower.trunk.blocks.5.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 670 |
+
"model.vision_tower.vision_tower.trunk.blocks.5.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 671 |
+
"model.vision_tower.vision_tower.trunk.blocks.5.norm1.bias": "model-00001-of-00002.safetensors",
|
| 672 |
+
"model.vision_tower.vision_tower.trunk.blocks.5.norm1.weight": "model-00001-of-00002.safetensors",
|
| 673 |
+
"model.vision_tower.vision_tower.trunk.blocks.5.norm2.bias": "model-00001-of-00002.safetensors",
|
| 674 |
+
"model.vision_tower.vision_tower.trunk.blocks.5.norm2.weight": "model-00001-of-00002.safetensors",
|
| 675 |
+
"model.vision_tower.vision_tower.trunk.blocks.6.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 676 |
+
"model.vision_tower.vision_tower.trunk.blocks.6.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 677 |
+
"model.vision_tower.vision_tower.trunk.blocks.6.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 678 |
+
"model.vision_tower.vision_tower.trunk.blocks.6.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 679 |
+
"model.vision_tower.vision_tower.trunk.blocks.6.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 680 |
+
"model.vision_tower.vision_tower.trunk.blocks.6.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 681 |
+
"model.vision_tower.vision_tower.trunk.blocks.6.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 682 |
+
"model.vision_tower.vision_tower.trunk.blocks.6.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 683 |
+
"model.vision_tower.vision_tower.trunk.blocks.6.norm1.bias": "model-00001-of-00002.safetensors",
|
| 684 |
+
"model.vision_tower.vision_tower.trunk.blocks.6.norm1.weight": "model-00001-of-00002.safetensors",
|
| 685 |
+
"model.vision_tower.vision_tower.trunk.blocks.6.norm2.bias": "model-00001-of-00002.safetensors",
|
| 686 |
+
"model.vision_tower.vision_tower.trunk.blocks.6.norm2.weight": "model-00001-of-00002.safetensors",
|
| 687 |
+
"model.vision_tower.vision_tower.trunk.blocks.7.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 688 |
+
"model.vision_tower.vision_tower.trunk.blocks.7.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 689 |
+
"model.vision_tower.vision_tower.trunk.blocks.7.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 690 |
+
"model.vision_tower.vision_tower.trunk.blocks.7.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 691 |
+
"model.vision_tower.vision_tower.trunk.blocks.7.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 692 |
+
"model.vision_tower.vision_tower.trunk.blocks.7.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 693 |
+
"model.vision_tower.vision_tower.trunk.blocks.7.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 694 |
+
"model.vision_tower.vision_tower.trunk.blocks.7.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 695 |
+
"model.vision_tower.vision_tower.trunk.blocks.7.norm1.bias": "model-00001-of-00002.safetensors",
|
| 696 |
+
"model.vision_tower.vision_tower.trunk.blocks.7.norm1.weight": "model-00001-of-00002.safetensors",
|
| 697 |
+
"model.vision_tower.vision_tower.trunk.blocks.7.norm2.bias": "model-00001-of-00002.safetensors",
|
| 698 |
+
"model.vision_tower.vision_tower.trunk.blocks.7.norm2.weight": "model-00001-of-00002.safetensors",
|
| 699 |
+
"model.vision_tower.vision_tower.trunk.blocks.8.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 700 |
+
"model.vision_tower.vision_tower.trunk.blocks.8.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 701 |
+
"model.vision_tower.vision_tower.trunk.blocks.8.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 702 |
+
"model.vision_tower.vision_tower.trunk.blocks.8.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 703 |
+
"model.vision_tower.vision_tower.trunk.blocks.8.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 704 |
+
"model.vision_tower.vision_tower.trunk.blocks.8.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 705 |
+
"model.vision_tower.vision_tower.trunk.blocks.8.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 706 |
+
"model.vision_tower.vision_tower.trunk.blocks.8.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 707 |
+
"model.vision_tower.vision_tower.trunk.blocks.8.norm1.bias": "model-00001-of-00002.safetensors",
|
| 708 |
+
"model.vision_tower.vision_tower.trunk.blocks.8.norm1.weight": "model-00001-of-00002.safetensors",
|
| 709 |
+
"model.vision_tower.vision_tower.trunk.blocks.8.norm2.bias": "model-00001-of-00002.safetensors",
|
| 710 |
+
"model.vision_tower.vision_tower.trunk.blocks.8.norm2.weight": "model-00001-of-00002.safetensors",
|
| 711 |
+
"model.vision_tower.vision_tower.trunk.blocks.9.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 712 |
+
"model.vision_tower.vision_tower.trunk.blocks.9.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 713 |
+
"model.vision_tower.vision_tower.trunk.blocks.9.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 714 |
+
"model.vision_tower.vision_tower.trunk.blocks.9.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 715 |
+
"model.vision_tower.vision_tower.trunk.blocks.9.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 716 |
+
"model.vision_tower.vision_tower.trunk.blocks.9.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 717 |
+
"model.vision_tower.vision_tower.trunk.blocks.9.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 718 |
+
"model.vision_tower.vision_tower.trunk.blocks.9.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 719 |
+
"model.vision_tower.vision_tower.trunk.blocks.9.norm1.bias": "model-00001-of-00002.safetensors",
|
| 720 |
+
"model.vision_tower.vision_tower.trunk.blocks.9.norm1.weight": "model-00001-of-00002.safetensors",
|
| 721 |
+
"model.vision_tower.vision_tower.trunk.blocks.9.norm2.bias": "model-00001-of-00002.safetensors",
|
| 722 |
+
"model.vision_tower.vision_tower.trunk.blocks.9.norm2.weight": "model-00001-of-00002.safetensors",
|
| 723 |
+
"model.vision_tower.vision_tower.trunk.norm.bias": "model-00002-of-00002.safetensors",
|
| 724 |
+
"model.vision_tower.vision_tower.trunk.norm.weight": "model-00002-of-00002.safetensors",
|
| 725 |
+
"model.vision_tower.vision_tower.trunk.patch_embed.proj.bias": "model-00001-of-00002.safetensors",
|
| 726 |
+
"model.vision_tower.vision_tower.trunk.patch_embed.proj.weight": "model-00001-of-00002.safetensors",
|
| 727 |
+
"model.vision_tower.vision_tower.trunk.pos_embed": "model-00001-of-00002.safetensors"
|
| 728 |
+
}
|
| 729 |
+
}
|
continuous/smollm2/siglip2_g16_384/finetune/special_tokens_map.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|im_start|>",
|
| 4 |
+
"<|im_end|>"
|
| 5 |
+
],
|
| 6 |
+
"bos_token": {
|
| 7 |
+
"content": "<|im_start|>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": false,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false
|
| 12 |
+
},
|
| 13 |
+
"eos_token": {
|
| 14 |
+
"content": "<|im_end|>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false
|
| 19 |
+
},
|
| 20 |
+
"pad_token": "<|endoftext|>",
|
| 21 |
+
"unk_token": {
|
| 22 |
+
"content": "<|endoftext|>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false
|
| 27 |
+
}
|
| 28 |
+
}
|
continuous/smollm2/siglip2_g16_384/finetune/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
continuous/smollm2/siglip2_g16_384/finetune/tokenizer_config.json
ADDED
|
@@ -0,0 +1,155 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"0": {
|
| 5 |
+
"content": "<|endoftext|>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": false,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"1": {
|
| 13 |
+
"content": "<|im_start|>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": false,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"2": {
|
| 21 |
+
"content": "<|im_end|>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": false,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
},
|
| 28 |
+
"3": {
|
| 29 |
+
"content": "<repo_name>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": false,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": true
|
| 35 |
+
},
|
| 36 |
+
"4": {
|
| 37 |
+
"content": "<reponame>",
|
| 38 |
+
"lstrip": false,
|
| 39 |
+
"normalized": false,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": true
|
| 43 |
+
},
|
| 44 |
+
"5": {
|
| 45 |
+
"content": "<file_sep>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": false,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false,
|
| 50 |
+
"special": true
|
| 51 |
+
},
|
| 52 |
+
"6": {
|
| 53 |
+
"content": "<filename>",
|
| 54 |
+
"lstrip": false,
|
| 55 |
+
"normalized": false,
|
| 56 |
+
"rstrip": false,
|
| 57 |
+
"single_word": false,
|
| 58 |
+
"special": true
|
| 59 |
+
},
|
| 60 |
+
"7": {
|
| 61 |
+
"content": "<gh_stars>",
|
| 62 |
+
"lstrip": false,
|
| 63 |
+
"normalized": false,
|
| 64 |
+
"rstrip": false,
|
| 65 |
+
"single_word": false,
|
| 66 |
+
"special": true
|
| 67 |
+
},
|
| 68 |
+
"8": {
|
| 69 |
+
"content": "<issue_start>",
|
| 70 |
+
"lstrip": false,
|
| 71 |
+
"normalized": false,
|
| 72 |
+
"rstrip": false,
|
| 73 |
+
"single_word": false,
|
| 74 |
+
"special": true
|
| 75 |
+
},
|
| 76 |
+
"9": {
|
| 77 |
+
"content": "<issue_comment>",
|
| 78 |
+
"lstrip": false,
|
| 79 |
+
"normalized": false,
|
| 80 |
+
"rstrip": false,
|
| 81 |
+
"single_word": false,
|
| 82 |
+
"special": true
|
| 83 |
+
},
|
| 84 |
+
"10": {
|
| 85 |
+
"content": "<issue_closed>",
|
| 86 |
+
"lstrip": false,
|
| 87 |
+
"normalized": false,
|
| 88 |
+
"rstrip": false,
|
| 89 |
+
"single_word": false,
|
| 90 |
+
"special": true
|
| 91 |
+
},
|
| 92 |
+
"11": {
|
| 93 |
+
"content": "<jupyter_start>",
|
| 94 |
+
"lstrip": false,
|
| 95 |
+
"normalized": false,
|
| 96 |
+
"rstrip": false,
|
| 97 |
+
"single_word": false,
|
| 98 |
+
"special": true
|
| 99 |
+
},
|
| 100 |
+
"12": {
|
| 101 |
+
"content": "<jupyter_text>",
|
| 102 |
+
"lstrip": false,
|
| 103 |
+
"normalized": false,
|
| 104 |
+
"rstrip": false,
|
| 105 |
+
"single_word": false,
|
| 106 |
+
"special": true
|
| 107 |
+
},
|
| 108 |
+
"13": {
|
| 109 |
+
"content": "<jupyter_code>",
|
| 110 |
+
"lstrip": false,
|
| 111 |
+
"normalized": false,
|
| 112 |
+
"rstrip": false,
|
| 113 |
+
"single_word": false,
|
| 114 |
+
"special": true
|
| 115 |
+
},
|
| 116 |
+
"14": {
|
| 117 |
+
"content": "<jupyter_output>",
|
| 118 |
+
"lstrip": false,
|
| 119 |
+
"normalized": false,
|
| 120 |
+
"rstrip": false,
|
| 121 |
+
"single_word": false,
|
| 122 |
+
"special": true
|
| 123 |
+
},
|
| 124 |
+
"15": {
|
| 125 |
+
"content": "<jupyter_script>",
|
| 126 |
+
"lstrip": false,
|
| 127 |
+
"normalized": false,
|
| 128 |
+
"rstrip": false,
|
| 129 |
+
"single_word": false,
|
| 130 |
+
"special": true
|
| 131 |
+
},
|
| 132 |
+
"16": {
|
| 133 |
+
"content": "<empty_output>",
|
| 134 |
+
"lstrip": false,
|
| 135 |
+
"normalized": false,
|
| 136 |
+
"rstrip": false,
|
| 137 |
+
"single_word": false,
|
| 138 |
+
"special": true
|
| 139 |
+
}
|
| 140 |
+
},
|
| 141 |
+
"additional_special_tokens": [
|
| 142 |
+
"<|im_start|>",
|
| 143 |
+
"<|im_end|>"
|
| 144 |
+
],
|
| 145 |
+
"bos_token": "<|im_start|>",
|
| 146 |
+
"clean_up_tokenization_spaces": false,
|
| 147 |
+
"eos_token": "<|im_end|>",
|
| 148 |
+
"extra_special_tokens": {},
|
| 149 |
+
"model_max_length": 8192,
|
| 150 |
+
"pad_token": "<|endoftext|>",
|
| 151 |
+
"padding_side": "right",
|
| 152 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 153 |
+
"unk_token": "<|endoftext|>",
|
| 154 |
+
"vocab_size": 49152
|
| 155 |
+
}
|
continuous/smollm2/siglip2_g16_384/finetune/trainer_state.json
ADDED
|
@@ -0,0 +1,1856 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 1.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 2597,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.003850596842510589,
|
| 14 |
+
"grad_norm": 2.9142417907714844,
|
| 15 |
+
"learning_rate": 1.153846153846154e-06,
|
| 16 |
+
"loss": 1.2393,
|
| 17 |
+
"step": 10
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.007701193685021178,
|
| 21 |
+
"grad_norm": 2.0541627407073975,
|
| 22 |
+
"learning_rate": 2.435897435897436e-06,
|
| 23 |
+
"loss": 1.0888,
|
| 24 |
+
"step": 20
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.011551790527531768,
|
| 28 |
+
"grad_norm": 1.9111473560333252,
|
| 29 |
+
"learning_rate": 3.7179487179487184e-06,
|
| 30 |
+
"loss": 0.9662,
|
| 31 |
+
"step": 30
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.015402387370042356,
|
| 35 |
+
"grad_norm": 1.3401178121566772,
|
| 36 |
+
"learning_rate": 5e-06,
|
| 37 |
+
"loss": 0.9154,
|
| 38 |
+
"step": 40
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.019252984212552945,
|
| 42 |
+
"grad_norm": 1.3163000345230103,
|
| 43 |
+
"learning_rate": 6.282051282051282e-06,
|
| 44 |
+
"loss": 0.904,
|
| 45 |
+
"step": 50
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.023103581055063535,
|
| 49 |
+
"grad_norm": 0.262821763753891,
|
| 50 |
+
"learning_rate": 7.564102564102564e-06,
|
| 51 |
+
"loss": 0.8338,
|
| 52 |
+
"step": 60
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.026954177897574125,
|
| 56 |
+
"grad_norm": 0.21480818092823029,
|
| 57 |
+
"learning_rate": 8.846153846153847e-06,
|
| 58 |
+
"loss": 0.7891,
|
| 59 |
+
"step": 70
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.030804774740084712,
|
| 63 |
+
"grad_norm": 0.2710026502609253,
|
| 64 |
+
"learning_rate": 9.999996111488723e-06,
|
| 65 |
+
"loss": 0.8028,
|
| 66 |
+
"step": 80
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.0346553715825953,
|
| 70 |
+
"grad_norm": 0.2025301307439804,
|
| 71 |
+
"learning_rate": 9.999529497453782e-06,
|
| 72 |
+
"loss": 0.7885,
|
| 73 |
+
"step": 90
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.03850596842510589,
|
| 77 |
+
"grad_norm": 0.19458404183387756,
|
| 78 |
+
"learning_rate": 9.998285264324193e-06,
|
| 79 |
+
"loss": 0.7524,
|
| 80 |
+
"step": 100
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.04235656526761648,
|
| 84 |
+
"grad_norm": 0.19452360272407532,
|
| 85 |
+
"learning_rate": 9.996263605626052e-06,
|
| 86 |
+
"loss": 0.7477,
|
| 87 |
+
"step": 110
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.04620716211012707,
|
| 91 |
+
"grad_norm": 0.19636134803295135,
|
| 92 |
+
"learning_rate": 9.99346483580503e-06,
|
| 93 |
+
"loss": 0.7661,
|
| 94 |
+
"step": 120
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.05005775895263766,
|
| 98 |
+
"grad_norm": 0.20872493088245392,
|
| 99 |
+
"learning_rate": 9.989889390177467e-06,
|
| 100 |
+
"loss": 0.7396,
|
| 101 |
+
"step": 130
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.05390835579514825,
|
| 105 |
+
"grad_norm": 0.21385635435581207,
|
| 106 |
+
"learning_rate": 9.985537824862647e-06,
|
| 107 |
+
"loss": 0.7567,
|
| 108 |
+
"step": 140
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.05775895263765884,
|
| 112 |
+
"grad_norm": 0.21978318691253662,
|
| 113 |
+
"learning_rate": 9.980410816696317e-06,
|
| 114 |
+
"loss": 0.7323,
|
| 115 |
+
"step": 150
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.061609549480169425,
|
| 119 |
+
"grad_norm": 0.18900537490844727,
|
| 120 |
+
"learning_rate": 9.97450916312541e-06,
|
| 121 |
+
"loss": 0.7399,
|
| 122 |
+
"step": 160
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.06546014632268002,
|
| 126 |
+
"grad_norm": 0.20102500915527344,
|
| 127 |
+
"learning_rate": 9.967833782084004e-06,
|
| 128 |
+
"loss": 0.7427,
|
| 129 |
+
"step": 170
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.0693107431651906,
|
| 133 |
+
"grad_norm": 0.22923654317855835,
|
| 134 |
+
"learning_rate": 9.960385711850554e-06,
|
| 135 |
+
"loss": 0.7714,
|
| 136 |
+
"step": 180
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.07316134000770119,
|
| 140 |
+
"grad_norm": 0.21737904846668243,
|
| 141 |
+
"learning_rate": 9.952166110886394e-06,
|
| 142 |
+
"loss": 0.7578,
|
| 143 |
+
"step": 190
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.07701193685021178,
|
| 147 |
+
"grad_norm": 0.19425249099731445,
|
| 148 |
+
"learning_rate": 9.943176257655567e-06,
|
| 149 |
+
"loss": 0.7557,
|
| 150 |
+
"step": 200
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.08086253369272237,
|
| 154 |
+
"grad_norm": 0.20930607616901398,
|
| 155 |
+
"learning_rate": 9.933417550425952e-06,
|
| 156 |
+
"loss": 0.7481,
|
| 157 |
+
"step": 210
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.08471313053523297,
|
| 161 |
+
"grad_norm": 0.1832045465707779,
|
| 162 |
+
"learning_rate": 9.9228915070518e-06,
|
| 163 |
+
"loss": 0.7322,
|
| 164 |
+
"step": 220
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.08856372737774355,
|
| 168 |
+
"grad_norm": 0.1815759539604187,
|
| 169 |
+
"learning_rate": 9.911599764737632e-06,
|
| 170 |
+
"loss": 0.7299,
|
| 171 |
+
"step": 230
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.09241432422025414,
|
| 175 |
+
"grad_norm": 0.18203112483024597,
|
| 176 |
+
"learning_rate": 9.899544079783606e-06,
|
| 177 |
+
"loss": 0.7272,
|
| 178 |
+
"step": 240
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.09626492106276473,
|
| 182 |
+
"grad_norm": 0.18773828446865082,
|
| 183 |
+
"learning_rate": 9.886726327312338e-06,
|
| 184 |
+
"loss": 0.7434,
|
| 185 |
+
"step": 250
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.10011551790527531,
|
| 189 |
+
"grad_norm": 0.16709110140800476,
|
| 190 |
+
"learning_rate": 9.87314850097724e-06,
|
| 191 |
+
"loss": 0.7393,
|
| 192 |
+
"step": 260
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.1039661147477859,
|
| 196 |
+
"grad_norm": 0.1801353394985199,
|
| 197 |
+
"learning_rate": 9.858812712652452e-06,
|
| 198 |
+
"loss": 0.7235,
|
| 199 |
+
"step": 270
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.1078167115902965,
|
| 203 |
+
"grad_norm": 0.1710759699344635,
|
| 204 |
+
"learning_rate": 9.843721192104341e-06,
|
| 205 |
+
"loss": 0.7202,
|
| 206 |
+
"step": 280
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.11166730843280709,
|
| 210 |
+
"grad_norm": 0.17623569071292877,
|
| 211 |
+
"learning_rate": 9.827876286644698e-06,
|
| 212 |
+
"loss": 0.7517,
|
| 213 |
+
"step": 290
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.11551790527531768,
|
| 217 |
+
"grad_norm": 0.16104072332382202,
|
| 218 |
+
"learning_rate": 9.811280460765643e-06,
|
| 219 |
+
"loss": 0.7113,
|
| 220 |
+
"step": 300
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.11936850211782826,
|
| 224 |
+
"grad_norm": 0.18242064118385315,
|
| 225 |
+
"learning_rate": 9.793936295756292e-06,
|
| 226 |
+
"loss": 0.7153,
|
| 227 |
+
"step": 310
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.12321909896033885,
|
| 231 |
+
"grad_norm": 0.18239641189575195,
|
| 232 |
+
"learning_rate": 9.775846489301279e-06,
|
| 233 |
+
"loss": 0.7282,
|
| 234 |
+
"step": 320
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.12706969580284944,
|
| 238 |
+
"grad_norm": 0.1704111248254776,
|
| 239 |
+
"learning_rate": 9.757013855061157e-06,
|
| 240 |
+
"loss": 0.7264,
|
| 241 |
+
"step": 330
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.13092029264536004,
|
| 245 |
+
"grad_norm": 0.17295658588409424,
|
| 246 |
+
"learning_rate": 9.737441322234758e-06,
|
| 247 |
+
"loss": 0.7302,
|
| 248 |
+
"step": 340
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.1347708894878706,
|
| 252 |
+
"grad_norm": 0.18797776103019714,
|
| 253 |
+
"learning_rate": 9.717131935103605e-06,
|
| 254 |
+
"loss": 0.7362,
|
| 255 |
+
"step": 350
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.1386214863303812,
|
| 259 |
+
"grad_norm": 0.18222379684448242,
|
| 260 |
+
"learning_rate": 9.696088852558398e-06,
|
| 261 |
+
"loss": 0.7193,
|
| 262 |
+
"step": 360
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.1424720831728918,
|
| 266 |
+
"grad_norm": 0.19290311634540558,
|
| 267 |
+
"learning_rate": 9.674315347607686e-06,
|
| 268 |
+
"loss": 0.748,
|
| 269 |
+
"step": 370
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.14632268001540238,
|
| 273 |
+
"grad_norm": 0.1845366358757019,
|
| 274 |
+
"learning_rate": 9.651814806868796e-06,
|
| 275 |
+
"loss": 0.7124,
|
| 276 |
+
"step": 380
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.15017327685791299,
|
| 280 |
+
"grad_norm": 0.1924031525850296,
|
| 281 |
+
"learning_rate": 9.62859073004107e-06,
|
| 282 |
+
"loss": 0.7123,
|
| 283 |
+
"step": 390
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.15402387370042356,
|
| 287 |
+
"grad_norm": 0.16410619020462036,
|
| 288 |
+
"learning_rate": 9.604646729361547e-06,
|
| 289 |
+
"loss": 0.7195,
|
| 290 |
+
"step": 400
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.15787447054293416,
|
| 294 |
+
"grad_norm": 0.19144852459430695,
|
| 295 |
+
"learning_rate": 9.579986529043099e-06,
|
| 296 |
+
"loss": 0.7156,
|
| 297 |
+
"step": 410
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.16172506738544473,
|
| 301 |
+
"grad_norm": 0.18101990222930908,
|
| 302 |
+
"learning_rate": 9.554613964695189e-06,
|
| 303 |
+
"loss": 0.7327,
|
| 304 |
+
"step": 420
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.16557566422795533,
|
| 308 |
+
"grad_norm": 0.18334269523620605,
|
| 309 |
+
"learning_rate": 9.528532982727281e-06,
|
| 310 |
+
"loss": 0.7168,
|
| 311 |
+
"step": 430
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.16942626107046593,
|
| 315 |
+
"grad_norm": 0.18282140791416168,
|
| 316 |
+
"learning_rate": 9.501747639735018e-06,
|
| 317 |
+
"loss": 0.7185,
|
| 318 |
+
"step": 440
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.1732768579129765,
|
| 322 |
+
"grad_norm": 0.1754767745733261,
|
| 323 |
+
"learning_rate": 9.474262101869272e-06,
|
| 324 |
+
"loss": 0.7065,
|
| 325 |
+
"step": 450
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.1771274547554871,
|
| 329 |
+
"grad_norm": 0.18223142623901367,
|
| 330 |
+
"learning_rate": 9.446080644188141e-06,
|
| 331 |
+
"loss": 0.7159,
|
| 332 |
+
"step": 460
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.18097805159799768,
|
| 336 |
+
"grad_norm": 0.16544201970100403,
|
| 337 |
+
"learning_rate": 9.417207649992017e-06,
|
| 338 |
+
"loss": 0.7178,
|
| 339 |
+
"step": 470
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.18482864844050828,
|
| 343 |
+
"grad_norm": 0.1844622939825058,
|
| 344 |
+
"learning_rate": 9.387647610141816e-06,
|
| 345 |
+
"loss": 0.7129,
|
| 346 |
+
"step": 480
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.18867924528301888,
|
| 350 |
+
"grad_norm": 0.17724567651748657,
|
| 351 |
+
"learning_rate": 9.35740512236047e-06,
|
| 352 |
+
"loss": 0.7109,
|
| 353 |
+
"step": 490
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.19252984212552945,
|
| 357 |
+
"grad_norm": 0.16237564384937286,
|
| 358 |
+
"learning_rate": 9.326484890517809e-06,
|
| 359 |
+
"loss": 0.717,
|
| 360 |
+
"step": 500
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.19638043896804006,
|
| 364 |
+
"grad_norm": 0.18763963878154755,
|
| 365 |
+
"learning_rate": 9.294891723898926e-06,
|
| 366 |
+
"loss": 0.7045,
|
| 367 |
+
"step": 510
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.20023103581055063,
|
| 371 |
+
"grad_norm": 0.17531366646289825,
|
| 372 |
+
"learning_rate": 9.262630536456153e-06,
|
| 373 |
+
"loss": 0.7265,
|
| 374 |
+
"step": 520
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.20408163265306123,
|
| 378 |
+
"grad_norm": 0.18135705590248108,
|
| 379 |
+
"learning_rate": 9.229706346044749e-06,
|
| 380 |
+
"loss": 0.7122,
|
| 381 |
+
"step": 530
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.2079322294955718,
|
| 385 |
+
"grad_norm": 0.17952333390712738,
|
| 386 |
+
"learning_rate": 9.196124273642422e-06,
|
| 387 |
+
"loss": 0.7206,
|
| 388 |
+
"step": 540
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.2117828263380824,
|
| 392 |
+
"grad_norm": 0.18271654844284058,
|
| 393 |
+
"learning_rate": 9.161889542552842e-06,
|
| 394 |
+
"loss": 0.7296,
|
| 395 |
+
"step": 550
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.215633423180593,
|
| 399 |
+
"grad_norm": 0.17444677650928497,
|
| 400 |
+
"learning_rate": 9.127007477593193e-06,
|
| 401 |
+
"loss": 0.7284,
|
| 402 |
+
"step": 560
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.21948402002310358,
|
| 406 |
+
"grad_norm": 0.18151609599590302,
|
| 407 |
+
"learning_rate": 9.091483504265974e-06,
|
| 408 |
+
"loss": 0.7383,
|
| 409 |
+
"step": 570
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.22333461686561418,
|
| 413 |
+
"grad_norm": 0.18532995879650116,
|
| 414 |
+
"learning_rate": 9.055323147915116e-06,
|
| 415 |
+
"loss": 0.7105,
|
| 416 |
+
"step": 580
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.22718521370812475,
|
| 420 |
+
"grad_norm": 0.1781291514635086,
|
| 421 |
+
"learning_rate": 9.018532032866585e-06,
|
| 422 |
+
"loss": 0.723,
|
| 423 |
+
"step": 590
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.23103581055063535,
|
| 427 |
+
"grad_norm": 0.1669803261756897,
|
| 428 |
+
"learning_rate": 8.981115881553579e-06,
|
| 429 |
+
"loss": 0.7208,
|
| 430 |
+
"step": 600
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.23488640739314592,
|
| 434 |
+
"grad_norm": 0.18248358368873596,
|
| 435 |
+
"learning_rate": 8.943080513626476e-06,
|
| 436 |
+
"loss": 0.7394,
|
| 437 |
+
"step": 610
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.23873700423565652,
|
| 441 |
+
"grad_norm": 0.16534510254859924,
|
| 442 |
+
"learning_rate": 8.904431845047641e-06,
|
| 443 |
+
"loss": 0.7194,
|
| 444 |
+
"step": 620
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.24258760107816713,
|
| 448 |
+
"grad_norm": 0.17150017619132996,
|
| 449 |
+
"learning_rate": 8.86517588717128e-06,
|
| 450 |
+
"loss": 0.7304,
|
| 451 |
+
"step": 630
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.2464381979206777,
|
| 455 |
+
"grad_norm": 0.18155935406684875,
|
| 456 |
+
"learning_rate": 8.82531874580844e-06,
|
| 457 |
+
"loss": 0.7332,
|
| 458 |
+
"step": 640
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.25028879476318827,
|
| 462 |
+
"grad_norm": 0.169594407081604,
|
| 463 |
+
"learning_rate": 8.784866620277314e-06,
|
| 464 |
+
"loss": 0.6915,
|
| 465 |
+
"step": 650
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.25413939160569887,
|
| 469 |
+
"grad_norm": 0.18374741077423096,
|
| 470 |
+
"learning_rate": 8.743825802439018e-06,
|
| 471 |
+
"loss": 0.7132,
|
| 472 |
+
"step": 660
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 0.2579899884482095,
|
| 476 |
+
"grad_norm": 0.1737452745437622,
|
| 477 |
+
"learning_rate": 8.702202675718956e-06,
|
| 478 |
+
"loss": 0.7279,
|
| 479 |
+
"step": 670
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 0.2618405852907201,
|
| 483 |
+
"grad_norm": 0.16240206360816956,
|
| 484 |
+
"learning_rate": 8.660003714113959e-06,
|
| 485 |
+
"loss": 0.7052,
|
| 486 |
+
"step": 680
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 0.2656911821332307,
|
| 490 |
+
"grad_norm": 0.17804403603076935,
|
| 491 |
+
"learning_rate": 8.617235481185323e-06,
|
| 492 |
+
"loss": 0.7152,
|
| 493 |
+
"step": 690
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 0.2695417789757412,
|
| 497 |
+
"grad_norm": 0.18384522199630737,
|
| 498 |
+
"learning_rate": 8.573904629037931e-06,
|
| 499 |
+
"loss": 0.729,
|
| 500 |
+
"step": 700
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.2733923758182518,
|
| 504 |
+
"grad_norm": 0.1588274985551834,
|
| 505 |
+
"learning_rate": 8.530017897285585e-06,
|
| 506 |
+
"loss": 0.711,
|
| 507 |
+
"step": 710
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.2772429726607624,
|
| 511 |
+
"grad_norm": 0.1637342870235443,
|
| 512 |
+
"learning_rate": 8.485582112002746e-06,
|
| 513 |
+
"loss": 0.713,
|
| 514 |
+
"step": 720
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.281093569503273,
|
| 518 |
+
"grad_norm": 0.17060382664203644,
|
| 519 |
+
"learning_rate": 8.440604184662811e-06,
|
| 520 |
+
"loss": 0.7196,
|
| 521 |
+
"step": 730
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.2849441663457836,
|
| 525 |
+
"grad_norm": 0.17551182210445404,
|
| 526 |
+
"learning_rate": 8.395091111063118e-06,
|
| 527 |
+
"loss": 0.7056,
|
| 528 |
+
"step": 740
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 0.28879476318829417,
|
| 532 |
+
"grad_norm": 0.1632164865732193,
|
| 533 |
+
"learning_rate": 8.349049970236822e-06,
|
| 534 |
+
"loss": 0.7055,
|
| 535 |
+
"step": 750
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 0.29264536003080477,
|
| 539 |
+
"grad_norm": 0.16247999668121338,
|
| 540 |
+
"learning_rate": 8.302487923351842e-06,
|
| 541 |
+
"loss": 0.6988,
|
| 542 |
+
"step": 760
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.29649595687331537,
|
| 546 |
+
"grad_norm": 0.16760048270225525,
|
| 547 |
+
"learning_rate": 8.255412212597021e-06,
|
| 548 |
+
"loss": 0.719,
|
| 549 |
+
"step": 770
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.30034655371582597,
|
| 553 |
+
"grad_norm": 0.17747509479522705,
|
| 554 |
+
"learning_rate": 8.207830160055688e-06,
|
| 555 |
+
"loss": 0.7155,
|
| 556 |
+
"step": 780
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.3041971505583365,
|
| 560 |
+
"grad_norm": 0.16879913210868835,
|
| 561 |
+
"learning_rate": 8.159749166566786e-06,
|
| 562 |
+
"loss": 0.6965,
|
| 563 |
+
"step": 790
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 0.3080477474008471,
|
| 567 |
+
"grad_norm": 0.17139500379562378,
|
| 568 |
+
"learning_rate": 8.11117671057377e-06,
|
| 569 |
+
"loss": 0.7176,
|
| 570 |
+
"step": 800
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.3118983442433577,
|
| 574 |
+
"grad_norm": 0.16713155806064606,
|
| 575 |
+
"learning_rate": 8.062120346961404e-06,
|
| 576 |
+
"loss": 0.7152,
|
| 577 |
+
"step": 810
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 0.3157489410858683,
|
| 581 |
+
"grad_norm": 0.16678746044635773,
|
| 582 |
+
"learning_rate": 8.012587705880705e-06,
|
| 583 |
+
"loss": 0.7128,
|
| 584 |
+
"step": 820
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 0.3195995379283789,
|
| 588 |
+
"grad_norm": 0.17417281866073608,
|
| 589 |
+
"learning_rate": 7.962586491562146e-06,
|
| 590 |
+
"loss": 0.7002,
|
| 591 |
+
"step": 830
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.32345013477088946,
|
| 595 |
+
"grad_norm": 0.16764125227928162,
|
| 596 |
+
"learning_rate": 7.912124481117357e-06,
|
| 597 |
+
"loss": 0.6997,
|
| 598 |
+
"step": 840
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 0.32730073161340006,
|
| 602 |
+
"grad_norm": 0.16431812942028046,
|
| 603 |
+
"learning_rate": 7.861209523329494e-06,
|
| 604 |
+
"loss": 0.7126,
|
| 605 |
+
"step": 850
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 0.33115132845591067,
|
| 609 |
+
"grad_norm": 0.1751641482114792,
|
| 610 |
+
"learning_rate": 7.809849537432432e-06,
|
| 611 |
+
"loss": 0.7021,
|
| 612 |
+
"step": 860
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 0.33500192529842127,
|
| 616 |
+
"grad_norm": 0.16682732105255127,
|
| 617 |
+
"learning_rate": 7.758052511879035e-06,
|
| 618 |
+
"loss": 0.7045,
|
| 619 |
+
"step": 870
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 0.33885252214093187,
|
| 623 |
+
"grad_norm": 0.18426546454429626,
|
| 624 |
+
"learning_rate": 7.705826503098642e-06,
|
| 625 |
+
"loss": 0.7078,
|
| 626 |
+
"step": 880
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 0.3427031189834424,
|
| 630 |
+
"grad_norm": 0.1815270483493805,
|
| 631 |
+
"learning_rate": 7.653179634243979e-06,
|
| 632 |
+
"loss": 0.7029,
|
| 633 |
+
"step": 890
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 0.346553715825953,
|
| 637 |
+
"grad_norm": 0.16254037618637085,
|
| 638 |
+
"learning_rate": 7.600120093927696e-06,
|
| 639 |
+
"loss": 0.7007,
|
| 640 |
+
"step": 900
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 0.3504043126684636,
|
| 644 |
+
"grad_norm": 0.18891233205795288,
|
| 645 |
+
"learning_rate": 7.546656134948729e-06,
|
| 646 |
+
"loss": 0.6927,
|
| 647 |
+
"step": 910
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 0.3542549095109742,
|
| 651 |
+
"grad_norm": 0.17492014169692993,
|
| 652 |
+
"learning_rate": 7.492796073008661e-06,
|
| 653 |
+
"loss": 0.7042,
|
| 654 |
+
"step": 920
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 0.3581055063534848,
|
| 658 |
+
"grad_norm": 0.1897849142551422,
|
| 659 |
+
"learning_rate": 7.438548285418326e-06,
|
| 660 |
+
"loss": 0.6845,
|
| 661 |
+
"step": 930
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 0.36195610319599536,
|
| 665 |
+
"grad_norm": 0.17478424310684204,
|
| 666 |
+
"learning_rate": 7.3839212097948e-06,
|
| 667 |
+
"loss": 0.715,
|
| 668 |
+
"step": 940
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 0.36580670003850596,
|
| 672 |
+
"grad_norm": 0.1779967099428177,
|
| 673 |
+
"learning_rate": 7.328923342749039e-06,
|
| 674 |
+
"loss": 0.7326,
|
| 675 |
+
"step": 950
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 0.36965729688101656,
|
| 679 |
+
"grad_norm": 0.17002563178539276,
|
| 680 |
+
"learning_rate": 7.273563238564319e-06,
|
| 681 |
+
"loss": 0.7264,
|
| 682 |
+
"step": 960
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 0.37350789372352716,
|
| 686 |
+
"grad_norm": 0.16416078805923462,
|
| 687 |
+
"learning_rate": 7.217849507865724e-06,
|
| 688 |
+
"loss": 0.693,
|
| 689 |
+
"step": 970
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 0.37735849056603776,
|
| 693 |
+
"grad_norm": 0.16735586524009705,
|
| 694 |
+
"learning_rate": 7.161790816280858e-06,
|
| 695 |
+
"loss": 0.7072,
|
| 696 |
+
"step": 980
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 0.3812090874085483,
|
| 700 |
+
"grad_norm": 0.1897168904542923,
|
| 701 |
+
"learning_rate": 7.1053958830920125e-06,
|
| 702 |
+
"loss": 0.6878,
|
| 703 |
+
"step": 990
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 0.3850596842510589,
|
| 707 |
+
"grad_norm": 0.17407897114753723,
|
| 708 |
+
"learning_rate": 7.0486734798799715e-06,
|
| 709 |
+
"loss": 0.7039,
|
| 710 |
+
"step": 1000
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 0.3889102810935695,
|
| 714 |
+
"grad_norm": 0.16519960761070251,
|
| 715 |
+
"learning_rate": 6.991632429159708e-06,
|
| 716 |
+
"loss": 0.7242,
|
| 717 |
+
"step": 1010
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 0.3927608779360801,
|
| 721 |
+
"grad_norm": 0.1803567260503769,
|
| 722 |
+
"learning_rate": 6.934281603008132e-06,
|
| 723 |
+
"loss": 0.7192,
|
| 724 |
+
"step": 1020
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 0.39661147477859066,
|
| 728 |
+
"grad_norm": 0.1546667069196701,
|
| 729 |
+
"learning_rate": 6.876629921684143e-06,
|
| 730 |
+
"loss": 0.7156,
|
| 731 |
+
"step": 1030
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 0.40046207162110126,
|
| 735 |
+
"grad_norm": 0.1790485680103302,
|
| 736 |
+
"learning_rate": 6.818686352241199e-06,
|
| 737 |
+
"loss": 0.7031,
|
| 738 |
+
"step": 1040
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 0.40431266846361186,
|
| 742 |
+
"grad_norm": 0.15841026604175568,
|
| 743 |
+
"learning_rate": 6.760459907132573e-06,
|
| 744 |
+
"loss": 0.697,
|
| 745 |
+
"step": 1050
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 0.40816326530612246,
|
| 749 |
+
"grad_norm": 0.15854841470718384,
|
| 750 |
+
"learning_rate": 6.701959642809589e-06,
|
| 751 |
+
"loss": 0.7035,
|
| 752 |
+
"step": 1060
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 0.41201386214863306,
|
| 756 |
+
"grad_norm": 0.1689213365316391,
|
| 757 |
+
"learning_rate": 6.643194658312987e-06,
|
| 758 |
+
"loss": 0.6939,
|
| 759 |
+
"step": 1070
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 0.4158644589911436,
|
| 763 |
+
"grad_norm": 0.16699495911598206,
|
| 764 |
+
"learning_rate": 6.584174093857676e-06,
|
| 765 |
+
"loss": 0.7226,
|
| 766 |
+
"step": 1080
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 0.4197150558336542,
|
| 770 |
+
"grad_norm": 0.17862121760845184,
|
| 771 |
+
"learning_rate": 6.5249071294110735e-06,
|
| 772 |
+
"loss": 0.7049,
|
| 773 |
+
"step": 1090
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 0.4235656526761648,
|
| 777 |
+
"grad_norm": 0.16872388124465942,
|
| 778 |
+
"learning_rate": 6.465402983265274e-06,
|
| 779 |
+
"loss": 0.7166,
|
| 780 |
+
"step": 1100
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 0.4274162495186754,
|
| 784 |
+
"grad_norm": 0.18065886199474335,
|
| 785 |
+
"learning_rate": 6.405670910603243e-06,
|
| 786 |
+
"loss": 0.7065,
|
| 787 |
+
"step": 1110
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 0.431266846361186,
|
| 791 |
+
"grad_norm": 0.1705770641565323,
|
| 792 |
+
"learning_rate": 6.345720202059291e-06,
|
| 793 |
+
"loss": 0.7048,
|
| 794 |
+
"step": 1120
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 0.43511744320369655,
|
| 798 |
+
"grad_norm": 0.17197449505329132,
|
| 799 |
+
"learning_rate": 6.285560182274008e-06,
|
| 800 |
+
"loss": 0.6856,
|
| 801 |
+
"step": 1130
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 0.43896804004620715,
|
| 805 |
+
"grad_norm": 0.18615709245204926,
|
| 806 |
+
"learning_rate": 6.225200208443936e-06,
|
| 807 |
+
"loss": 0.7117,
|
| 808 |
+
"step": 1140
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 0.44281863688871775,
|
| 812 |
+
"grad_norm": 0.1772347241640091,
|
| 813 |
+
"learning_rate": 6.16464966886616e-06,
|
| 814 |
+
"loss": 0.6944,
|
| 815 |
+
"step": 1150
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 0.44666923373122835,
|
| 819 |
+
"grad_norm": 0.19707347452640533,
|
| 820 |
+
"learning_rate": 6.103917981478065e-06,
|
| 821 |
+
"loss": 0.726,
|
| 822 |
+
"step": 1160
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 0.45051983057373896,
|
| 826 |
+
"grad_norm": 0.1603589653968811,
|
| 827 |
+
"learning_rate": 6.043014592392489e-06,
|
| 828 |
+
"loss": 0.7312,
|
| 829 |
+
"step": 1170
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 0.4543704274162495,
|
| 833 |
+
"grad_norm": 0.1719568818807602,
|
| 834 |
+
"learning_rate": 5.981948974428485e-06,
|
| 835 |
+
"loss": 0.7136,
|
| 836 |
+
"step": 1180
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 0.4582210242587601,
|
| 840 |
+
"grad_norm": 0.1617663949728012,
|
| 841 |
+
"learning_rate": 5.920730625637934e-06,
|
| 842 |
+
"loss": 0.6867,
|
| 843 |
+
"step": 1190
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 0.4620716211012707,
|
| 847 |
+
"grad_norm": 0.16839517652988434,
|
| 848 |
+
"learning_rate": 5.8593690678282355e-06,
|
| 849 |
+
"loss": 0.6979,
|
| 850 |
+
"step": 1200
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 0.4659222179437813,
|
| 854 |
+
"grad_norm": 0.17323677241802216,
|
| 855 |
+
"learning_rate": 5.797873845081301e-06,
|
| 856 |
+
"loss": 0.6961,
|
| 857 |
+
"step": 1210
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 0.46977281478629185,
|
| 861 |
+
"grad_norm": 0.1799406111240387,
|
| 862 |
+
"learning_rate": 5.736254522269075e-06,
|
| 863 |
+
"loss": 0.7199,
|
| 864 |
+
"step": 1220
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 0.47362341162880245,
|
| 868 |
+
"grad_norm": 0.16394339501857758,
|
| 869 |
+
"learning_rate": 5.6745206835658386e-06,
|
| 870 |
+
"loss": 0.718,
|
| 871 |
+
"step": 1230
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 0.47747400847131305,
|
| 875 |
+
"grad_norm": 0.16483105719089508,
|
| 876 |
+
"learning_rate": 5.612681930957495e-06,
|
| 877 |
+
"loss": 0.6969,
|
| 878 |
+
"step": 1240
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 0.48132460531382365,
|
| 882 |
+
"grad_norm": 0.15977324545383453,
|
| 883 |
+
"learning_rate": 5.550747882748095e-06,
|
| 884 |
+
"loss": 0.6862,
|
| 885 |
+
"step": 1250
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 0.48517520215633425,
|
| 889 |
+
"grad_norm": 0.1724676489830017,
|
| 890 |
+
"learning_rate": 5.4887281720638195e-06,
|
| 891 |
+
"loss": 0.7028,
|
| 892 |
+
"step": 1260
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 0.4890257989988448,
|
| 896 |
+
"grad_norm": 0.1862214058637619,
|
| 897 |
+
"learning_rate": 5.42663244535466e-06,
|
| 898 |
+
"loss": 0.6776,
|
| 899 |
+
"step": 1270
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 0.4928763958413554,
|
| 903 |
+
"grad_norm": 0.17221327126026154,
|
| 904 |
+
"learning_rate": 5.3644703608940205e-06,
|
| 905 |
+
"loss": 0.6967,
|
| 906 |
+
"step": 1280
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 0.496726992683866,
|
| 910 |
+
"grad_norm": 0.16380909085273743,
|
| 911 |
+
"learning_rate": 5.302251587276491e-06,
|
| 912 |
+
"loss": 0.7073,
|
| 913 |
+
"step": 1290
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 0.5005775895263765,
|
| 917 |
+
"grad_norm": 0.17249345779418945,
|
| 918 |
+
"learning_rate": 5.2399858019140005e-06,
|
| 919 |
+
"loss": 0.6977,
|
| 920 |
+
"step": 1300
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 0.5044281863688872,
|
| 924 |
+
"grad_norm": 0.17457708716392517,
|
| 925 |
+
"learning_rate": 5.177682689530615e-06,
|
| 926 |
+
"loss": 0.7212,
|
| 927 |
+
"step": 1310
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 0.5082787832113977,
|
| 931 |
+
"grad_norm": 0.18851138651371002,
|
| 932 |
+
"learning_rate": 5.11535194065619e-06,
|
| 933 |
+
"loss": 0.6867,
|
| 934 |
+
"step": 1320
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 0.5121293800539084,
|
| 938 |
+
"grad_norm": 0.18209236860275269,
|
| 939 |
+
"learning_rate": 5.053003250119113e-06,
|
| 940 |
+
"loss": 0.6935,
|
| 941 |
+
"step": 1330
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 0.515979976896419,
|
| 945 |
+
"grad_norm": 0.16967567801475525,
|
| 946 |
+
"learning_rate": 4.9906463155383925e-06,
|
| 947 |
+
"loss": 0.7006,
|
| 948 |
+
"step": 1340
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 0.5198305737389295,
|
| 952 |
+
"grad_norm": 0.16124916076660156,
|
| 953 |
+
"learning_rate": 4.9282908358153046e-06,
|
| 954 |
+
"loss": 0.7021,
|
| 955 |
+
"step": 1350
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 0.5236811705814401,
|
| 959 |
+
"grad_norm": 0.1844058781862259,
|
| 960 |
+
"learning_rate": 4.8659465096248345e-06,
|
| 961 |
+
"loss": 0.7134,
|
| 962 |
+
"step": 1360
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 0.5275317674239507,
|
| 966 |
+
"grad_norm": 0.17944683134555817,
|
| 967 |
+
"learning_rate": 4.803623033907169e-06,
|
| 968 |
+
"loss": 0.7036,
|
| 969 |
+
"step": 1370
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 0.5313823642664613,
|
| 973 |
+
"grad_norm": 0.1604098379611969,
|
| 974 |
+
"learning_rate": 4.741330102359441e-06,
|
| 975 |
+
"loss": 0.7196,
|
| 976 |
+
"step": 1380
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 0.5352329611089719,
|
| 980 |
+
"grad_norm": 0.17696373164653778,
|
| 981 |
+
"learning_rate": 4.679077403927996e-06,
|
| 982 |
+
"loss": 0.6936,
|
| 983 |
+
"step": 1390
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 0.5390835579514824,
|
| 987 |
+
"grad_norm": 0.16297078132629395,
|
| 988 |
+
"learning_rate": 4.616874621301373e-06,
|
| 989 |
+
"loss": 0.6971,
|
| 990 |
+
"step": 1400
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 0.5429341547939931,
|
| 994 |
+
"grad_norm": 0.18022415041923523,
|
| 995 |
+
"learning_rate": 4.554731429404293e-06,
|
| 996 |
+
"loss": 0.7169,
|
| 997 |
+
"step": 1410
|
| 998 |
+
},
|
| 999 |
+
{
|
| 1000 |
+
"epoch": 0.5467847516365036,
|
| 1001 |
+
"grad_norm": 0.1754227578639984,
|
| 1002 |
+
"learning_rate": 4.492657493892822e-06,
|
| 1003 |
+
"loss": 0.6951,
|
| 1004 |
+
"step": 1420
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 0.5506353484790143,
|
| 1008 |
+
"grad_norm": 0.1756308525800705,
|
| 1009 |
+
"learning_rate": 4.430662469650999e-06,
|
| 1010 |
+
"loss": 0.71,
|
| 1011 |
+
"step": 1430
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 0.5544859453215248,
|
| 1015 |
+
"grad_norm": 0.18049348890781403,
|
| 1016 |
+
"learning_rate": 4.368755999289118e-06,
|
| 1017 |
+
"loss": 0.7138,
|
| 1018 |
+
"step": 1440
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 0.5583365421640354,
|
| 1022 |
+
"grad_norm": 0.175794318318367,
|
| 1023 |
+
"learning_rate": 4.306947711643949e-06,
|
| 1024 |
+
"loss": 0.6959,
|
| 1025 |
+
"step": 1450
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 0.562187139006546,
|
| 1029 |
+
"grad_norm": 0.17080669105052948,
|
| 1030 |
+
"learning_rate": 4.245247220281068e-06,
|
| 1031 |
+
"loss": 0.7011,
|
| 1032 |
+
"step": 1460
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 0.5660377358490566,
|
| 1036 |
+
"grad_norm": 0.1691768318414688,
|
| 1037 |
+
"learning_rate": 4.183664121999587e-06,
|
| 1038 |
+
"loss": 0.6947,
|
| 1039 |
+
"step": 1470
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"epoch": 0.5698883326915672,
|
| 1043 |
+
"grad_norm": 0.17025159299373627,
|
| 1044 |
+
"learning_rate": 4.122207995339474e-06,
|
| 1045 |
+
"loss": 0.6906,
|
| 1046 |
+
"step": 1480
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 0.5737389295340778,
|
| 1050 |
+
"grad_norm": 0.1658715456724167,
|
| 1051 |
+
"learning_rate": 4.060888399091734e-06,
|
| 1052 |
+
"loss": 0.6976,
|
| 1053 |
+
"step": 1490
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 0.5775895263765883,
|
| 1057 |
+
"grad_norm": 0.16862015426158905,
|
| 1058 |
+
"learning_rate": 3.999714870811639e-06,
|
| 1059 |
+
"loss": 0.7115,
|
| 1060 |
+
"step": 1500
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 0.581440123219099,
|
| 1064 |
+
"grad_norm": 0.16632480919361115,
|
| 1065 |
+
"learning_rate": 3.938696925335275e-06,
|
| 1066 |
+
"loss": 0.7052,
|
| 1067 |
+
"step": 1510
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 0.5852907200616095,
|
| 1071 |
+
"grad_norm": 0.16602368652820587,
|
| 1072 |
+
"learning_rate": 3.87784405329962e-06,
|
| 1073 |
+
"loss": 0.7113,
|
| 1074 |
+
"step": 1520
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 0.5891413169041202,
|
| 1078 |
+
"grad_norm": 0.1559973806142807,
|
| 1079 |
+
"learning_rate": 3.817165719666382e-06,
|
| 1080 |
+
"loss": 0.7099,
|
| 1081 |
+
"step": 1530
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 0.5929919137466307,
|
| 1085 |
+
"grad_norm": 0.17381811141967773,
|
| 1086 |
+
"learning_rate": 3.756671362249841e-06,
|
| 1087 |
+
"loss": 0.7155,
|
| 1088 |
+
"step": 1540
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 0.5968425105891413,
|
| 1092 |
+
"grad_norm": 0.162495955824852,
|
| 1093 |
+
"learning_rate": 3.6963703902488907e-06,
|
| 1094 |
+
"loss": 0.7015,
|
| 1095 |
+
"step": 1550
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 0.6006931074316519,
|
| 1099 |
+
"grad_norm": 0.1628260314464569,
|
| 1100 |
+
"learning_rate": 3.6362721827835655e-06,
|
| 1101 |
+
"loss": 0.7089,
|
| 1102 |
+
"step": 1560
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 0.6045437042741625,
|
| 1106 |
+
"grad_norm": 0.17701296508312225,
|
| 1107 |
+
"learning_rate": 3.576386087436212e-06,
|
| 1108 |
+
"loss": 0.7187,
|
| 1109 |
+
"step": 1570
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 0.608394301116673,
|
| 1113 |
+
"grad_norm": 0.18130819499492645,
|
| 1114 |
+
"learning_rate": 3.5167214187975913e-06,
|
| 1115 |
+
"loss": 0.7084,
|
| 1116 |
+
"step": 1580
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 0.6122448979591837,
|
| 1120 |
+
"grad_norm": 0.1512155383825302,
|
| 1121 |
+
"learning_rate": 3.457287457018086e-06,
|
| 1122 |
+
"loss": 0.7055,
|
| 1123 |
+
"step": 1590
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 0.6160954948016942,
|
| 1127 |
+
"grad_norm": 0.17101088166236877,
|
| 1128 |
+
"learning_rate": 3.3980934463643003e-06,
|
| 1129 |
+
"loss": 0.7025,
|
| 1130 |
+
"step": 1600
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 0.6199460916442049,
|
| 1134 |
+
"grad_norm": 0.1557779312133789,
|
| 1135 |
+
"learning_rate": 3.3391485937812053e-06,
|
| 1136 |
+
"loss": 0.6785,
|
| 1137 |
+
"step": 1610
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 0.6237966884867154,
|
| 1141 |
+
"grad_norm": 0.16954319179058075,
|
| 1142 |
+
"learning_rate": 3.280462067460115e-06,
|
| 1143 |
+
"loss": 0.6809,
|
| 1144 |
+
"step": 1620
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 0.627647285329226,
|
| 1148 |
+
"grad_norm": 0.16687047481536865,
|
| 1149 |
+
"learning_rate": 3.222042995412669e-06,
|
| 1150 |
+
"loss": 0.7055,
|
| 1151 |
+
"step": 1630
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 0.6314978821717366,
|
| 1155 |
+
"grad_norm": 0.16040469706058502,
|
| 1156 |
+
"learning_rate": 3.163900464051089e-06,
|
| 1157 |
+
"loss": 0.6955,
|
| 1158 |
+
"step": 1640
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 0.6353484790142472,
|
| 1162 |
+
"grad_norm": 0.17264583706855774,
|
| 1163 |
+
"learning_rate": 3.1060435167748826e-06,
|
| 1164 |
+
"loss": 0.7121,
|
| 1165 |
+
"step": 1650
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 0.6391990758567578,
|
| 1169 |
+
"grad_norm": 0.16581034660339355,
|
| 1170 |
+
"learning_rate": 3.048481152564253e-06,
|
| 1171 |
+
"loss": 0.6906,
|
| 1172 |
+
"step": 1660
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 0.6430496726992684,
|
| 1176 |
+
"grad_norm": 0.17659030854701996,
|
| 1177 |
+
"learning_rate": 2.9912223245804017e-06,
|
| 1178 |
+
"loss": 0.7073,
|
| 1179 |
+
"step": 1670
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 0.6469002695417789,
|
| 1183 |
+
"grad_norm": 0.16722996532917023,
|
| 1184 |
+
"learning_rate": 2.934275938772981e-06,
|
| 1185 |
+
"loss": 0.6962,
|
| 1186 |
+
"step": 1680
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 0.6507508663842896,
|
| 1190 |
+
"grad_norm": 0.17351670563220978,
|
| 1191 |
+
"learning_rate": 2.8776508524948676e-06,
|
| 1192 |
+
"loss": 0.6925,
|
| 1193 |
+
"step": 1690
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 0.6546014632268001,
|
| 1197 |
+
"grad_norm": 0.16747066378593445,
|
| 1198 |
+
"learning_rate": 2.821355873124503e-06,
|
| 1199 |
+
"loss": 0.6938,
|
| 1200 |
+
"step": 1700
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 0.6584520600693108,
|
| 1204 |
+
"grad_norm": 0.17646241188049316,
|
| 1205 |
+
"learning_rate": 2.7653997566960144e-06,
|
| 1206 |
+
"loss": 0.7036,
|
| 1207 |
+
"step": 1710
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"epoch": 0.6623026569118213,
|
| 1211 |
+
"grad_norm": 0.18416836857795715,
|
| 1212 |
+
"learning_rate": 2.709791206537309e-06,
|
| 1213 |
+
"loss": 0.696,
|
| 1214 |
+
"step": 1720
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 0.6661532537543319,
|
| 1218 |
+
"grad_norm": 0.1874733418226242,
|
| 1219 |
+
"learning_rate": 2.6545388719163747e-06,
|
| 1220 |
+
"loss": 0.6963,
|
| 1221 |
+
"step": 1730
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 0.6700038505968425,
|
| 1225 |
+
"grad_norm": 0.17073266208171844,
|
| 1226 |
+
"learning_rate": 2.599651346695979e-06,
|
| 1227 |
+
"loss": 0.7063,
|
| 1228 |
+
"step": 1740
|
| 1229 |
+
},
|
| 1230 |
+
{
|
| 1231 |
+
"epoch": 0.6738544474393531,
|
| 1232 |
+
"grad_norm": 0.1676231324672699,
|
| 1233 |
+
"learning_rate": 2.545137167997007e-06,
|
| 1234 |
+
"loss": 0.704,
|
| 1235 |
+
"step": 1750
|
| 1236 |
+
},
|
| 1237 |
+
{
|
| 1238 |
+
"epoch": 0.6777050442818637,
|
| 1239 |
+
"grad_norm": 0.16232071816921234,
|
| 1240 |
+
"learning_rate": 2.4910048148705972e-06,
|
| 1241 |
+
"loss": 0.6922,
|
| 1242 |
+
"step": 1760
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 0.6815556411243743,
|
| 1246 |
+
"grad_norm": 0.17695116996765137,
|
| 1247 |
+
"learning_rate": 2.4372627069793327e-06,
|
| 1248 |
+
"loss": 0.7303,
|
| 1249 |
+
"step": 1770
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 0.6854062379668848,
|
| 1253 |
+
"grad_norm": 0.16578374803066254,
|
| 1254 |
+
"learning_rate": 2.3839192032876486e-06,
|
| 1255 |
+
"loss": 0.7063,
|
| 1256 |
+
"step": 1780
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 0.6892568348093955,
|
| 1260 |
+
"grad_norm": 0.17820556461811066,
|
| 1261 |
+
"learning_rate": 2.3309826007617047e-06,
|
| 1262 |
+
"loss": 0.7219,
|
| 1263 |
+
"step": 1790
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 0.693107431651906,
|
| 1267 |
+
"grad_norm": 0.16577781736850739,
|
| 1268 |
+
"learning_rate": 2.278461133078881e-06,
|
| 1269 |
+
"loss": 0.691,
|
| 1270 |
+
"step": 1800
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 0.6969580284944167,
|
| 1274 |
+
"grad_norm": 0.17584054172039032,
|
| 1275 |
+
"learning_rate": 2.2263629693471258e-06,
|
| 1276 |
+
"loss": 0.6833,
|
| 1277 |
+
"step": 1810
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 0.7008086253369272,
|
| 1281 |
+
"grad_norm": 0.1699700653553009,
|
| 1282 |
+
"learning_rate": 2.1746962128343414e-06,
|
| 1283 |
+
"loss": 0.7052,
|
| 1284 |
+
"step": 1820
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 0.7046592221794378,
|
| 1288 |
+
"grad_norm": 0.17122994363307953,
|
| 1289 |
+
"learning_rate": 2.1234688997080183e-06,
|
| 1290 |
+
"loss": 0.6897,
|
| 1291 |
+
"step": 1830
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 0.7085098190219484,
|
| 1295 |
+
"grad_norm": 0.16685925424098969,
|
| 1296 |
+
"learning_rate": 2.0726889977853053e-06,
|
| 1297 |
+
"loss": 0.6964,
|
| 1298 |
+
"step": 1840
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 0.712360415864459,
|
| 1302 |
+
"grad_norm": 0.17214512825012207,
|
| 1303 |
+
"learning_rate": 2.022364405293703e-06,
|
| 1304 |
+
"loss": 0.7122,
|
| 1305 |
+
"step": 1850
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 0.7162110127069696,
|
| 1309 |
+
"grad_norm": 0.1642850935459137,
|
| 1310 |
+
"learning_rate": 1.9725029496425814e-06,
|
| 1311 |
+
"loss": 0.7079,
|
| 1312 |
+
"step": 1860
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 0.7200616095494802,
|
| 1316 |
+
"grad_norm": 0.17247553169727325,
|
| 1317 |
+
"learning_rate": 1.923112386205727e-06,
|
| 1318 |
+
"loss": 0.6991,
|
| 1319 |
+
"step": 1870
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 0.7239122063919907,
|
| 1323 |
+
"grad_norm": 0.1647931933403015,
|
| 1324 |
+
"learning_rate": 1.874200397115079e-06,
|
| 1325 |
+
"loss": 0.7089,
|
| 1326 |
+
"step": 1880
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 0.7277628032345014,
|
| 1330 |
+
"grad_norm": 0.16767974197864532,
|
| 1331 |
+
"learning_rate": 1.825774590065857e-06,
|
| 1332 |
+
"loss": 0.6945,
|
| 1333 |
+
"step": 1890
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 0.7316134000770119,
|
| 1337 |
+
"grad_norm": 0.17836961150169373,
|
| 1338 |
+
"learning_rate": 1.7778424971332813e-06,
|
| 1339 |
+
"loss": 0.7061,
|
| 1340 |
+
"step": 1900
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 0.7354639969195226,
|
| 1344 |
+
"grad_norm": 0.16519540548324585,
|
| 1345 |
+
"learning_rate": 1.7304115736010407e-06,
|
| 1346 |
+
"loss": 0.7005,
|
| 1347 |
+
"step": 1910
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 0.7393145937620331,
|
| 1351 |
+
"grad_norm": 0.16629011929035187,
|
| 1352 |
+
"learning_rate": 1.6834891968017108e-06,
|
| 1353 |
+
"loss": 0.6938,
|
| 1354 |
+
"step": 1920
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 0.7431651906045437,
|
| 1358 |
+
"grad_norm": 0.17523150146007538,
|
| 1359 |
+
"learning_rate": 1.6370826649692884e-06,
|
| 1360 |
+
"loss": 0.7074,
|
| 1361 |
+
"step": 1930
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 0.7470157874470543,
|
| 1365 |
+
"grad_norm": 0.16631020605564117,
|
| 1366 |
+
"learning_rate": 1.5911991961040463e-06,
|
| 1367 |
+
"loss": 0.7113,
|
| 1368 |
+
"step": 1940
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 0.7508663842895649,
|
| 1372 |
+
"grad_norm": 0.17316487431526184,
|
| 1373 |
+
"learning_rate": 1.545845926849851e-06,
|
| 1374 |
+
"loss": 0.696,
|
| 1375 |
+
"step": 1950
|
| 1376 |
+
},
|
| 1377 |
+
{
|
| 1378 |
+
"epoch": 0.7547169811320755,
|
| 1379 |
+
"grad_norm": 0.17692646384239197,
|
| 1380 |
+
"learning_rate": 1.5010299113841397e-06,
|
| 1381 |
+
"loss": 0.7187,
|
| 1382 |
+
"step": 1960
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 0.7585675779745861,
|
| 1386 |
+
"grad_norm": 0.1740504652261734,
|
| 1387 |
+
"learning_rate": 1.4567581203207238e-06,
|
| 1388 |
+
"loss": 0.7082,
|
| 1389 |
+
"step": 1970
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 0.7624181748170966,
|
| 1393 |
+
"grad_norm": 0.1808023303747177,
|
| 1394 |
+
"learning_rate": 1.413037439625593e-06,
|
| 1395 |
+
"loss": 0.7091,
|
| 1396 |
+
"step": 1980
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 0.7662687716596073,
|
| 1400 |
+
"grad_norm": 0.18813244998455048,
|
| 1401 |
+
"learning_rate": 1.3698746695458847e-06,
|
| 1402 |
+
"loss": 0.6979,
|
| 1403 |
+
"step": 1990
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 0.7701193685021178,
|
| 1407 |
+
"grad_norm": 0.16877439618110657,
|
| 1408 |
+
"learning_rate": 1.3272765235521745e-06,
|
| 1409 |
+
"loss": 0.6972,
|
| 1410 |
+
"step": 2000
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"epoch": 0.7739699653446284,
|
| 1414 |
+
"grad_norm": 0.1595691740512848,
|
| 1415 |
+
"learning_rate": 1.2852496272942877e-06,
|
| 1416 |
+
"loss": 0.7066,
|
| 1417 |
+
"step": 2010
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 0.777820562187139,
|
| 1421 |
+
"grad_norm": 0.1613588035106659,
|
| 1422 |
+
"learning_rate": 1.2438005175707396e-06,
|
| 1423 |
+
"loss": 0.6842,
|
| 1424 |
+
"step": 2020
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 0.7816711590296496,
|
| 1428 |
+
"grad_norm": 0.16661356389522552,
|
| 1429 |
+
"learning_rate": 1.2029356413120297e-06,
|
| 1430 |
+
"loss": 0.6792,
|
| 1431 |
+
"step": 2030
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 0.7855217558721602,
|
| 1435 |
+
"grad_norm": 0.1660688817501068,
|
| 1436 |
+
"learning_rate": 1.1626613545778786e-06,
|
| 1437 |
+
"loss": 0.6938,
|
| 1438 |
+
"step": 2040
|
| 1439 |
+
},
|
| 1440 |
+
{
|
| 1441 |
+
"epoch": 0.7893723527146708,
|
| 1442 |
+
"grad_norm": 0.16068504750728607,
|
| 1443 |
+
"learning_rate": 1.1229839215686294e-06,
|
| 1444 |
+
"loss": 0.6975,
|
| 1445 |
+
"step": 2050
|
| 1446 |
+
},
|
| 1447 |
+
{
|
| 1448 |
+
"epoch": 0.7932229495571813,
|
| 1449 |
+
"grad_norm": 0.15124838054180145,
|
| 1450 |
+
"learning_rate": 1.0839095136509188e-06,
|
| 1451 |
+
"loss": 0.6818,
|
| 1452 |
+
"step": 2060
|
| 1453 |
+
},
|
| 1454 |
+
{
|
| 1455 |
+
"epoch": 0.797073546399692,
|
| 1456 |
+
"grad_norm": 0.17471782863140106,
|
| 1457 |
+
"learning_rate": 1.045444208397791e-06,
|
| 1458 |
+
"loss": 0.6974,
|
| 1459 |
+
"step": 2070
|
| 1460 |
+
},
|
| 1461 |
+
{
|
| 1462 |
+
"epoch": 0.8009241432422025,
|
| 1463 |
+
"grad_norm": 0.1578342765569687,
|
| 1464 |
+
"learning_rate": 1.007593988643402e-06,
|
| 1465 |
+
"loss": 0.6754,
|
| 1466 |
+
"step": 2080
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 0.8047747400847132,
|
| 1470 |
+
"grad_norm": 0.15967877209186554,
|
| 1471 |
+
"learning_rate": 9.703647415524613e-07,
|
| 1472 |
+
"loss": 0.7039,
|
| 1473 |
+
"step": 2090
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 0.8086253369272237,
|
| 1477 |
+
"grad_norm": 0.15967068076133728,
|
| 1478 |
+
"learning_rate": 9.337622577045485e-07,
|
| 1479 |
+
"loss": 0.6927,
|
| 1480 |
+
"step": 2100
|
| 1481 |
+
},
|
| 1482 |
+
{
|
| 1483 |
+
"epoch": 0.8124759337697343,
|
| 1484 |
+
"grad_norm": 0.1655718982219696,
|
| 1485 |
+
"learning_rate": 8.977922301934588e-07,
|
| 1486 |
+
"loss": 0.7,
|
| 1487 |
+
"step": 2110
|
| 1488 |
+
},
|
| 1489 |
+
{
|
| 1490 |
+
"epoch": 0.8163265306122449,
|
| 1491 |
+
"grad_norm": 0.18796202540397644,
|
| 1492 |
+
"learning_rate": 8.624602537417009e-07,
|
| 1493 |
+
"loss": 0.7152,
|
| 1494 |
+
"step": 2120
|
| 1495 |
+
},
|
| 1496 |
+
{
|
| 1497 |
+
"epoch": 0.8201771274547555,
|
| 1498 |
+
"grad_norm": 0.17137093842029572,
|
| 1499 |
+
"learning_rate": 8.277718238303123e-07,
|
| 1500 |
+
"loss": 0.694,
|
| 1501 |
+
"step": 2130
|
| 1502 |
+
},
|
| 1503 |
+
{
|
| 1504 |
+
"epoch": 0.8240277242972661,
|
| 1505 |
+
"grad_norm": 0.175109401345253,
|
| 1506 |
+
"learning_rate": 7.937323358440935e-07,
|
| 1507 |
+
"loss": 0.6979,
|
| 1508 |
+
"step": 2140
|
| 1509 |
+
},
|
| 1510 |
+
{
|
| 1511 |
+
"epoch": 0.8278783211397767,
|
| 1512 |
+
"grad_norm": 0.16768725216388702,
|
| 1513 |
+
"learning_rate": 7.603470842324223e-07,
|
| 1514 |
+
"loss": 0.6846,
|
| 1515 |
+
"step": 2150
|
| 1516 |
+
},
|
| 1517 |
+
{
|
| 1518 |
+
"epoch": 0.8317289179822872,
|
| 1519 |
+
"grad_norm": 0.16405871510505676,
|
| 1520 |
+
"learning_rate": 7.276212616857575e-07,
|
| 1521 |
+
"loss": 0.7063,
|
| 1522 |
+
"step": 2160
|
| 1523 |
+
},
|
| 1524 |
+
{
|
| 1525 |
+
"epoch": 0.8355795148247979,
|
| 1526 |
+
"grad_norm": 0.17136284708976746,
|
| 1527 |
+
"learning_rate": 6.955599583279837e-07,
|
| 1528 |
+
"loss": 0.6999,
|
| 1529 |
+
"step": 2170
|
| 1530 |
+
},
|
| 1531 |
+
{
|
| 1532 |
+
"epoch": 0.8394301116673084,
|
| 1533 |
+
"grad_norm": 0.16541741788387299,
|
| 1534 |
+
"learning_rate": 6.641681609246981e-07,
|
| 1535 |
+
"loss": 0.697,
|
| 1536 |
+
"step": 2180
|
| 1537 |
+
},
|
| 1538 |
+
{
|
| 1539 |
+
"epoch": 0.8432807085098191,
|
| 1540 |
+
"grad_norm": 0.17600226402282715,
|
| 1541 |
+
"learning_rate": 6.334507521075711e-07,
|
| 1542 |
+
"loss": 0.6947,
|
| 1543 |
+
"step": 2190
|
| 1544 |
+
},
|
| 1545 |
+
{
|
| 1546 |
+
"epoch": 0.8471313053523296,
|
| 1547 |
+
"grad_norm": 0.17553023993968964,
|
| 1548 |
+
"learning_rate": 6.034125096149179e-07,
|
| 1549 |
+
"loss": 0.6995,
|
| 1550 |
+
"step": 2200
|
| 1551 |
+
},
|
| 1552 |
+
{
|
| 1553 |
+
"epoch": 0.8509819021948402,
|
| 1554 |
+
"grad_norm": 0.15961281955242157,
|
| 1555 |
+
"learning_rate": 5.740581055485722e-07,
|
| 1556 |
+
"loss": 0.6707,
|
| 1557 |
+
"step": 2210
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"epoch": 0.8548324990373508,
|
| 1561 |
+
"grad_norm": 0.1552964746952057,
|
| 1562 |
+
"learning_rate": 5.453921056471961e-07,
|
| 1563 |
+
"loss": 0.7026,
|
| 1564 |
+
"step": 2220
|
| 1565 |
+
},
|
| 1566 |
+
{
|
| 1567 |
+
"epoch": 0.8586830958798614,
|
| 1568 |
+
"grad_norm": 0.17954207956790924,
|
| 1569 |
+
"learning_rate": 5.174189685761288e-07,
|
| 1570 |
+
"loss": 0.6966,
|
| 1571 |
+
"step": 2230
|
| 1572 |
+
},
|
| 1573 |
+
{
|
| 1574 |
+
"epoch": 0.862533692722372,
|
| 1575 |
+
"grad_norm": 0.16110995411872864,
|
| 1576 |
+
"learning_rate": 4.901430452338979e-07,
|
| 1577 |
+
"loss": 0.7091,
|
| 1578 |
+
"step": 2240
|
| 1579 |
+
},
|
| 1580 |
+
{
|
| 1581 |
+
"epoch": 0.8663842895648826,
|
| 1582 |
+
"grad_norm": 0.16718992590904236,
|
| 1583 |
+
"learning_rate": 4.6356857807548286e-07,
|
| 1584 |
+
"loss": 0.6959,
|
| 1585 |
+
"step": 2250
|
| 1586 |
+
},
|
| 1587 |
+
{
|
| 1588 |
+
"epoch": 0.8702348864073931,
|
| 1589 |
+
"grad_norm": 0.19240498542785645,
|
| 1590 |
+
"learning_rate": 4.376997004524541e-07,
|
| 1591 |
+
"loss": 0.6787,
|
| 1592 |
+
"step": 2260
|
| 1593 |
+
},
|
| 1594 |
+
{
|
| 1595 |
+
"epoch": 0.8740854832499038,
|
| 1596 |
+
"grad_norm": 0.16465157270431519,
|
| 1597 |
+
"learning_rate": 4.12540435970073e-07,
|
| 1598 |
+
"loss": 0.6946,
|
| 1599 |
+
"step": 2270
|
| 1600 |
+
},
|
| 1601 |
+
{
|
| 1602 |
+
"epoch": 0.8779360800924143,
|
| 1603 |
+
"grad_norm": 0.16203908622264862,
|
| 1604 |
+
"learning_rate": 3.880946978614703e-07,
|
| 1605 |
+
"loss": 0.7065,
|
| 1606 |
+
"step": 2280
|
| 1607 |
+
},
|
| 1608 |
+
{
|
| 1609 |
+
"epoch": 0.881786676934925,
|
| 1610 |
+
"grad_norm": 0.16478382050991058,
|
| 1611 |
+
"learning_rate": 3.643662883789878e-07,
|
| 1612 |
+
"loss": 0.6997,
|
| 1613 |
+
"step": 2290
|
| 1614 |
+
},
|
| 1615 |
+
{
|
| 1616 |
+
"epoch": 0.8856372737774355,
|
| 1617 |
+
"grad_norm": 0.15493306517601013,
|
| 1618 |
+
"learning_rate": 3.41358898202781e-07,
|
| 1619 |
+
"loss": 0.6855,
|
| 1620 |
+
"step": 2300
|
| 1621 |
+
},
|
| 1622 |
+
{
|
| 1623 |
+
"epoch": 0.889487870619946,
|
| 1624 |
+
"grad_norm": 0.15804365277290344,
|
| 1625 |
+
"learning_rate": 3.190761058667741e-07,
|
| 1626 |
+
"loss": 0.6983,
|
| 1627 |
+
"step": 2310
|
| 1628 |
+
},
|
| 1629 |
+
{
|
| 1630 |
+
"epoch": 0.8933384674624567,
|
| 1631 |
+
"grad_norm": 0.1593165248632431,
|
| 1632 |
+
"learning_rate": 2.9752137720206463e-07,
|
| 1633 |
+
"loss": 0.6985,
|
| 1634 |
+
"step": 2320
|
| 1635 |
+
},
|
| 1636 |
+
{
|
| 1637 |
+
"epoch": 0.8971890643049673,
|
| 1638 |
+
"grad_norm": 0.16890248656272888,
|
| 1639 |
+
"learning_rate": 2.7669806479785067e-07,
|
| 1640 |
+
"loss": 0.7093,
|
| 1641 |
+
"step": 2330
|
| 1642 |
+
},
|
| 1643 |
+
{
|
| 1644 |
+
"epoch": 0.9010396611474779,
|
| 1645 |
+
"grad_norm": 0.16377796232700348,
|
| 1646 |
+
"learning_rate": 2.566094074799763e-07,
|
| 1647 |
+
"loss": 0.6998,
|
| 1648 |
+
"step": 2340
|
| 1649 |
+
},
|
| 1650 |
+
{
|
| 1651 |
+
"epoch": 0.9048902579899885,
|
| 1652 |
+
"grad_norm": 0.16985422372817993,
|
| 1653 |
+
"learning_rate": 2.3725852980716557e-07,
|
| 1654 |
+
"loss": 0.6835,
|
| 1655 |
+
"step": 2350
|
| 1656 |
+
},
|
| 1657 |
+
{
|
| 1658 |
+
"epoch": 0.908740854832499,
|
| 1659 |
+
"grad_norm": 0.16713611781597137,
|
| 1660 |
+
"learning_rate": 2.1864844158503983e-07,
|
| 1661 |
+
"loss": 0.6968,
|
| 1662 |
+
"step": 2360
|
| 1663 |
+
},
|
| 1664 |
+
{
|
| 1665 |
+
"epoch": 0.9125914516750097,
|
| 1666 |
+
"grad_norm": 0.1823073774576187,
|
| 1667 |
+
"learning_rate": 2.007820373979702e-07,
|
| 1668 |
+
"loss": 0.6887,
|
| 1669 |
+
"step": 2370
|
| 1670 |
+
},
|
| 1671 |
+
{
|
| 1672 |
+
"epoch": 0.9164420485175202,
|
| 1673 |
+
"grad_norm": 0.16002987325191498,
|
| 1674 |
+
"learning_rate": 1.8366209615886532e-07,
|
| 1675 |
+
"loss": 0.7017,
|
| 1676 |
+
"step": 2380
|
| 1677 |
+
},
|
| 1678 |
+
{
|
| 1679 |
+
"epoch": 0.9202926453600309,
|
| 1680 |
+
"grad_norm": 0.16956821084022522,
|
| 1681 |
+
"learning_rate": 1.6729128067693613e-07,
|
| 1682 |
+
"loss": 0.715,
|
| 1683 |
+
"step": 2390
|
| 1684 |
+
},
|
| 1685 |
+
{
|
| 1686 |
+
"epoch": 0.9241432422025414,
|
| 1687 |
+
"grad_norm": 0.17862294614315033,
|
| 1688 |
+
"learning_rate": 1.5167213724353426e-07,
|
| 1689 |
+
"loss": 0.7083,
|
| 1690 |
+
"step": 2400
|
| 1691 |
+
},
|
| 1692 |
+
{
|
| 1693 |
+
"epoch": 0.927993839045052,
|
| 1694 |
+
"grad_norm": 0.1596314162015915,
|
| 1695 |
+
"learning_rate": 1.3680709523610058e-07,
|
| 1696 |
+
"loss": 0.6853,
|
| 1697 |
+
"step": 2410
|
| 1698 |
+
},
|
| 1699 |
+
{
|
| 1700 |
+
"epoch": 0.9318444358875626,
|
| 1701 |
+
"grad_norm": 0.1634788066148758,
|
| 1702 |
+
"learning_rate": 1.2269846674030418e-07,
|
| 1703 |
+
"loss": 0.713,
|
| 1704 |
+
"step": 2420
|
| 1705 |
+
},
|
| 1706 |
+
{
|
| 1707 |
+
"epoch": 0.9356950327300732,
|
| 1708 |
+
"grad_norm": 0.16745539009571075,
|
| 1709 |
+
"learning_rate": 1.0934844619042595e-07,
|
| 1710 |
+
"loss": 0.7084,
|
| 1711 |
+
"step": 2430
|
| 1712 |
+
},
|
| 1713 |
+
{
|
| 1714 |
+
"epoch": 0.9395456295725837,
|
| 1715 |
+
"grad_norm": 0.16835206747055054,
|
| 1716 |
+
"learning_rate": 9.675911002803961e-08,
|
| 1717 |
+
"loss": 0.695,
|
| 1718 |
+
"step": 2440
|
| 1719 |
+
},
|
| 1720 |
+
{
|
| 1721 |
+
"epoch": 0.9433962264150944,
|
| 1722 |
+
"grad_norm": 0.17235875129699707,
|
| 1723 |
+
"learning_rate": 8.493241637904381e-08,
|
| 1724 |
+
"loss": 0.6844,
|
| 1725 |
+
"step": 2450
|
| 1726 |
+
},
|
| 1727 |
+
{
|
| 1728 |
+
"epoch": 0.9472468232576049,
|
| 1729 |
+
"grad_norm": 0.182292178273201,
|
| 1730 |
+
"learning_rate": 7.387020474909689e-08,
|
| 1731 |
+
"loss": 0.7114,
|
| 1732 |
+
"step": 2460
|
| 1733 |
+
},
|
| 1734 |
+
{
|
| 1735 |
+
"epoch": 0.9510974201001156,
|
| 1736 |
+
"grad_norm": 0.17998866736888885,
|
| 1737 |
+
"learning_rate": 6.357419573750856e-08,
|
| 1738 |
+
"loss": 0.7074,
|
| 1739 |
+
"step": 2470
|
| 1740 |
+
},
|
| 1741 |
+
{
|
| 1742 |
+
"epoch": 0.9549480169426261,
|
| 1743 |
+
"grad_norm": 0.16659916937351227,
|
| 1744 |
+
"learning_rate": 5.4045990769613365e-08,
|
| 1745 |
+
"loss": 0.6936,
|
| 1746 |
+
"step": 2480
|
| 1747 |
+
},
|
| 1748 |
+
{
|
| 1749 |
+
"epoch": 0.9587986137851366,
|
| 1750 |
+
"grad_norm": 0.16647593677043915,
|
| 1751 |
+
"learning_rate": 4.5287071847694434e-08,
|
| 1752 |
+
"loss": 0.6937,
|
| 1753 |
+
"step": 2490
|
| 1754 |
+
},
|
| 1755 |
+
{
|
| 1756 |
+
"epoch": 0.9626492106276473,
|
| 1757 |
+
"grad_norm": 0.1657545566558838,
|
| 1758 |
+
"learning_rate": 3.7298801320467817e-08,
|
| 1759 |
+
"loss": 0.6983,
|
| 1760 |
+
"step": 2500
|
| 1761 |
+
},
|
| 1762 |
+
{
|
| 1763 |
+
"epoch": 0.9664998074701578,
|
| 1764 |
+
"grad_norm": 0.16262629628181458,
|
| 1765 |
+
"learning_rate": 3.0082421671192576e-08,
|
| 1766 |
+
"loss": 0.6971,
|
| 1767 |
+
"step": 2510
|
| 1768 |
+
},
|
| 1769 |
+
{
|
| 1770 |
+
"epoch": 0.9703504043126685,
|
| 1771 |
+
"grad_norm": 0.16971834003925323,
|
| 1772 |
+
"learning_rate": 2.3639055324410355e-08,
|
| 1773 |
+
"loss": 0.7126,
|
| 1774 |
+
"step": 2520
|
| 1775 |
+
},
|
| 1776 |
+
{
|
| 1777 |
+
"epoch": 0.974201001155179,
|
| 1778 |
+
"grad_norm": 0.16947486996650696,
|
| 1779 |
+
"learning_rate": 1.7969704471369477e-08,
|
| 1780 |
+
"loss": 0.6912,
|
| 1781 |
+
"step": 2530
|
| 1782 |
+
},
|
| 1783 |
+
{
|
| 1784 |
+
"epoch": 0.9780515979976896,
|
| 1785 |
+
"grad_norm": 0.15726545453071594,
|
| 1786 |
+
"learning_rate": 1.3075250914142413e-08,
|
| 1787 |
+
"loss": 0.6936,
|
| 1788 |
+
"step": 2540
|
| 1789 |
+
},
|
| 1790 |
+
{
|
| 1791 |
+
"epoch": 0.9819021948402002,
|
| 1792 |
+
"grad_norm": 0.1518152803182602,
|
| 1793 |
+
"learning_rate": 8.956455928476049e-09,
|
| 1794 |
+
"loss": 0.7069,
|
| 1795 |
+
"step": 2550
|
| 1796 |
+
},
|
| 1797 |
+
{
|
| 1798 |
+
"epoch": 0.9857527916827108,
|
| 1799 |
+
"grad_norm": 0.16311034560203552,
|
| 1800 |
+
"learning_rate": 5.6139601453786275e-09,
|
| 1801 |
+
"loss": 0.6906,
|
| 1802 |
+
"step": 2560
|
| 1803 |
+
},
|
| 1804 |
+
{
|
| 1805 |
+
"epoch": 0.9896033885252215,
|
| 1806 |
+
"grad_norm": 0.16555126011371613,
|
| 1807 |
+
"learning_rate": 3.0482834514805602e-09,
|
| 1808 |
+
"loss": 0.6894,
|
| 1809 |
+
"step": 2570
|
| 1810 |
+
},
|
| 1811 |
+
{
|
| 1812 |
+
"epoch": 0.993453985367732,
|
| 1813 |
+
"grad_norm": 0.15799234807491302,
|
| 1814 |
+
"learning_rate": 1.2598249081713366e-09,
|
| 1815 |
+
"loss": 0.677,
|
| 1816 |
+
"step": 2580
|
| 1817 |
+
},
|
| 1818 |
+
{
|
| 1819 |
+
"epoch": 0.9973045822102425,
|
| 1820 |
+
"grad_norm": 0.17236219346523285,
|
| 1821 |
+
"learning_rate": 2.488626895302826e-10,
|
| 1822 |
+
"loss": 0.7136,
|
| 1823 |
+
"step": 2590
|
| 1824 |
+
},
|
| 1825 |
+
{
|
| 1826 |
+
"epoch": 1.0,
|
| 1827 |
+
"step": 2597,
|
| 1828 |
+
"total_flos": 9.7524294777779e+18,
|
| 1829 |
+
"train_loss": 0.7156461167436496,
|
| 1830 |
+
"train_runtime": 16534.4323,
|
| 1831 |
+
"train_samples_per_second": 40.213,
|
| 1832 |
+
"train_steps_per_second": 0.157
|
| 1833 |
+
}
|
| 1834 |
+
],
|
| 1835 |
+
"logging_steps": 10,
|
| 1836 |
+
"max_steps": 2597,
|
| 1837 |
+
"num_input_tokens_seen": 584317136,
|
| 1838 |
+
"num_train_epochs": 1,
|
| 1839 |
+
"save_steps": 500,
|
| 1840 |
+
"stateful_callbacks": {
|
| 1841 |
+
"TrainerControl": {
|
| 1842 |
+
"args": {
|
| 1843 |
+
"should_epoch_stop": false,
|
| 1844 |
+
"should_evaluate": false,
|
| 1845 |
+
"should_log": false,
|
| 1846 |
+
"should_save": true,
|
| 1847 |
+
"should_training_stop": true
|
| 1848 |
+
},
|
| 1849 |
+
"attributes": {}
|
| 1850 |
+
}
|
| 1851 |
+
},
|
| 1852 |
+
"total_flos": 9.7524294777779e+18,
|
| 1853 |
+
"train_batch_size": 16,
|
| 1854 |
+
"trial_name": null,
|
| 1855 |
+
"trial_params": null
|
| 1856 |
+
}
|
continuous/smollm2/siglip2_g16_384/finetune/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:69f2a9aafe81f25668b9bfa49dd031612c6d5c8165d4a191443bb156dec77b57
|
| 3 |
+
size 6264
|
continuous/smollm2/siglip2_g16_384/finetune/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
continuous/smollm2/siglip2_g16_384/pretrain/config.json
ADDED
|
@@ -0,0 +1,70 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_faster_video": false,
|
| 3 |
+
"add_time_instruction": false,
|
| 4 |
+
"architectures": [
|
| 5 |
+
"LlamaForCausalLM"
|
| 6 |
+
],
|
| 7 |
+
"attention_bias": false,
|
| 8 |
+
"attention_dropout": 0.0,
|
| 9 |
+
"bos_token_id": 1,
|
| 10 |
+
"dtype": "bfloat16",
|
| 11 |
+
"eos_token_id": 2,
|
| 12 |
+
"faster_token_stride": 10,
|
| 13 |
+
"force_sample": false,
|
| 14 |
+
"head_dim": 64,
|
| 15 |
+
"hidden_act": "silu",
|
| 16 |
+
"hidden_size": 2048,
|
| 17 |
+
"image_aspect_ratio": "square",
|
| 18 |
+
"image_crop_resolution": null,
|
| 19 |
+
"image_grid_pinpoints": null,
|
| 20 |
+
"image_split_resolution": null,
|
| 21 |
+
"initializer_range": 0.02,
|
| 22 |
+
"intermediate_size": 8192,
|
| 23 |
+
"max_position_embeddings": 8192,
|
| 24 |
+
"mlp_bias": false,
|
| 25 |
+
"mm_hidden_size": 1536,
|
| 26 |
+
"mm_newline_position": "grid",
|
| 27 |
+
"mm_patch_merge_type": "flat",
|
| 28 |
+
"mm_projector_lr": null,
|
| 29 |
+
"mm_projector_type": "mlp2x_gelu",
|
| 30 |
+
"mm_resampler_type": null,
|
| 31 |
+
"mm_spatial_pool_mode": "bilinear",
|
| 32 |
+
"mm_spatial_pool_stride": null,
|
| 33 |
+
"mm_tunable_parts": "mm_mlp_adapter",
|
| 34 |
+
"mm_use_im_patch_token": false,
|
| 35 |
+
"mm_use_im_start_end": false,
|
| 36 |
+
"mm_vision_select_feature": "patch",
|
| 37 |
+
"mm_vision_select_layer": -2,
|
| 38 |
+
"mm_vision_tower": "open_clip_hub:ViT-gopt-16-SigLIP2-384",
|
| 39 |
+
"mm_vision_tower_lr": null,
|
| 40 |
+
"model_type": "llama",
|
| 41 |
+
"num_attention_heads": 32,
|
| 42 |
+
"num_hidden_layers": 24,
|
| 43 |
+
"num_key_value_heads": 32,
|
| 44 |
+
"pad_token_id": 0,
|
| 45 |
+
"pos_skipping_range": 4096,
|
| 46 |
+
"pretraining_tp": 1,
|
| 47 |
+
"rms_norm_eps": 1e-05,
|
| 48 |
+
"rope_scaling": null,
|
| 49 |
+
"rope_theta": 130000,
|
| 50 |
+
"tie_word_embeddings": true,
|
| 51 |
+
"tokenizer_model_max_length": 8192,
|
| 52 |
+
"tokenizer_padding_side": "right",
|
| 53 |
+
"transformers.js_config": {
|
| 54 |
+
"dtype": "q4",
|
| 55 |
+
"kv_cache_dtype": {
|
| 56 |
+
"fp16": "float16",
|
| 57 |
+
"q4f16": "float16"
|
| 58 |
+
},
|
| 59 |
+
"use_external_data_format": {
|
| 60 |
+
"model.onnx": true,
|
| 61 |
+
"model_fp16.onnx": true
|
| 62 |
+
}
|
| 63 |
+
},
|
| 64 |
+
"transformers_version": "4.57.6",
|
| 65 |
+
"use_cache": true,
|
| 66 |
+
"use_mm_proj": true,
|
| 67 |
+
"use_pos_skipping": false,
|
| 68 |
+
"vision_tower_pretrained": "/cache/ckpt/download/tokenizer/continuous/siglip2/siglip2_g16_384.npz",
|
| 69 |
+
"vocab_size": 49152
|
| 70 |
+
}
|
continuous/smollm2/siglip2_g16_384/pretrain/mm_projector.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fe33b2884c412e493fe102f82df74911acc8fef2699ac92dd822669e0bbd05d0
|
| 3 |
+
size 29378616
|
continuous/smollm2/siglip2_g16_384/pretrain/trainer_state.json
ADDED
|
@@ -0,0 +1,421 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 1.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 545,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.01834862385321101,
|
| 14 |
+
"grad_norm": 0.9113195538520813,
|
| 15 |
+
"learning_rate": 0.00032142857142857147,
|
| 16 |
+
"loss": 3.6679,
|
| 17 |
+
"step": 10
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.03669724770642202,
|
| 21 |
+
"grad_norm": 0.08317351341247559,
|
| 22 |
+
"learning_rate": 0.0006785714285714287,
|
| 23 |
+
"loss": 2.8898,
|
| 24 |
+
"step": 20
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.05504587155963303,
|
| 28 |
+
"grad_norm": 0.047663673758506775,
|
| 29 |
+
"learning_rate": 0.0009999907688176173,
|
| 30 |
+
"loss": 2.785,
|
| 31 |
+
"step": 30
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.07339449541284404,
|
| 35 |
+
"grad_norm": 0.0399208627641201,
|
| 36 |
+
"learning_rate": 0.0009988834393115766,
|
| 37 |
+
"loss": 2.7355,
|
| 38 |
+
"step": 40
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.09174311926605505,
|
| 42 |
+
"grad_norm": 0.0388350747525692,
|
| 43 |
+
"learning_rate": 0.0009959345572940772,
|
| 44 |
+
"loss": 2.7197,
|
| 45 |
+
"step": 50
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.11009174311926606,
|
| 49 |
+
"grad_norm": 0.21425148844718933,
|
| 50 |
+
"learning_rate": 0.0009911550081155983,
|
| 51 |
+
"loss": 2.6919,
|
| 52 |
+
"step": 60
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.12844036697247707,
|
| 56 |
+
"grad_norm": 0.07428966462612152,
|
| 57 |
+
"learning_rate": 0.0009845624347566433,
|
| 58 |
+
"loss": 2.6992,
|
| 59 |
+
"step": 70
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.14678899082568808,
|
| 63 |
+
"grad_norm": 0.05982556939125061,
|
| 64 |
+
"learning_rate": 0.0009761811727013547,
|
| 65 |
+
"loss": 2.6448,
|
| 66 |
+
"step": 80
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.1651376146788991,
|
| 70 |
+
"grad_norm": 0.05266672745347023,
|
| 71 |
+
"learning_rate": 0.0009660421601067666,
|
| 72 |
+
"loss": 2.5862,
|
| 73 |
+
"step": 90
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.1834862385321101,
|
| 77 |
+
"grad_norm": 0.055668871849775314,
|
| 78 |
+
"learning_rate": 0.0009541828235992926,
|
| 79 |
+
"loss": 2.5357,
|
| 80 |
+
"step": 100
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.2018348623853211,
|
| 84 |
+
"grad_norm": 0.0839756578207016,
|
| 85 |
+
"learning_rate": 0.0009406469401200151,
|
| 86 |
+
"loss": 2.4736,
|
| 87 |
+
"step": 110
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.22018348623853212,
|
| 91 |
+
"grad_norm": 0.0678265243768692,
|
| 92 |
+
"learning_rate": 0.0009254844753287492,
|
| 93 |
+
"loss": 2.4291,
|
| 94 |
+
"step": 120
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.23853211009174313,
|
| 98 |
+
"grad_norm": 0.08557083457708359,
|
| 99 |
+
"learning_rate": 0.0009087513991633924,
|
| 100 |
+
"loss": 2.3777,
|
| 101 |
+
"step": 130
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.25688073394495414,
|
| 105 |
+
"grad_norm": 0.06767208129167557,
|
| 106 |
+
"learning_rate": 0.0008905094792353917,
|
| 107 |
+
"loss": 2.3374,
|
| 108 |
+
"step": 140
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.27522935779816515,
|
| 112 |
+
"grad_norm": 0.05961655080318451,
|
| 113 |
+
"learning_rate": 0.0008708260528239789,
|
| 114 |
+
"loss": 2.3164,
|
| 115 |
+
"step": 150
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.29357798165137616,
|
| 119 |
+
"grad_norm": 0.09093103557825089,
|
| 120 |
+
"learning_rate": 0.0008497737783108237,
|
| 121 |
+
"loss": 2.2812,
|
| 122 |
+
"step": 160
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.3119266055045872,
|
| 126 |
+
"grad_norm": 0.07911451905965805,
|
| 127 |
+
"learning_rate": 0.0008274303669726426,
|
| 128 |
+
"loss": 2.2628,
|
| 129 |
+
"step": 170
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.3302752293577982,
|
| 133 |
+
"grad_norm": 0.07302707433700562,
|
| 134 |
+
"learning_rate": 0.0008038782961218137,
|
| 135 |
+
"loss": 2.2339,
|
| 136 |
+
"step": 180
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.3486238532110092,
|
| 140 |
+
"grad_norm": 0.07446488738059998,
|
| 141 |
+
"learning_rate": 0.000779204504653894,
|
| 142 |
+
"loss": 2.2095,
|
| 143 |
+
"step": 190
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.3669724770642202,
|
| 147 |
+
"grad_norm": 0.07363136112689972,
|
| 148 |
+
"learning_rate": 0.0007535000721258791,
|
| 149 |
+
"loss": 2.1637,
|
| 150 |
+
"step": 200
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.3853211009174312,
|
| 154 |
+
"grad_norm": 0.07623874396085739,
|
| 155 |
+
"learning_rate": 0.00072685988254984,
|
| 156 |
+
"loss": 2.1335,
|
| 157 |
+
"step": 210
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.4036697247706422,
|
| 161 |
+
"grad_norm": 0.07555881142616272,
|
| 162 |
+
"learning_rate": 0.0006993822741429906,
|
| 163 |
+
"loss": 2.1219,
|
| 164 |
+
"step": 220
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.42201834862385323,
|
| 168 |
+
"grad_norm": 0.06503073126077652,
|
| 169 |
+
"learning_rate": 0.0006711686763270818,
|
| 170 |
+
"loss": 2.0951,
|
| 171 |
+
"step": 230
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.44036697247706424,
|
| 175 |
+
"grad_norm": 0.07019004225730896,
|
| 176 |
+
"learning_rate": 0.0006423232353170831,
|
| 177 |
+
"loss": 2.0773,
|
| 178 |
+
"step": 240
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.45871559633027525,
|
| 182 |
+
"grad_norm": 0.060492951422929764,
|
| 183 |
+
"learning_rate": 0.0006129524296812335,
|
| 184 |
+
"loss": 2.0735,
|
| 185 |
+
"step": 250
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.47706422018348627,
|
| 189 |
+
"grad_norm": 0.06488218903541565,
|
| 190 |
+
"learning_rate": 0.0005831646772915651,
|
| 191 |
+
"loss": 2.0675,
|
| 192 |
+
"step": 260
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.4954128440366973,
|
| 196 |
+
"grad_norm": 0.0568191334605217,
|
| 197 |
+
"learning_rate": 0.0005530699351157809,
|
| 198 |
+
"loss": 2.045,
|
| 199 |
+
"step": 270
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.5137614678899083,
|
| 203 |
+
"grad_norm": 0.05380536615848541,
|
| 204 |
+
"learning_rate": 0.0005227792933277943,
|
| 205 |
+
"loss": 2.0448,
|
| 206 |
+
"step": 280
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.5321100917431193,
|
| 210 |
+
"grad_norm": 0.05986635386943817,
|
| 211 |
+
"learning_rate": 0.0004924045652352092,
|
| 212 |
+
"loss": 2.0325,
|
| 213 |
+
"step": 290
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.5504587155963303,
|
| 217 |
+
"grad_norm": 0.05633961409330368,
|
| 218 |
+
"learning_rate": 0.0004620578745374633,
|
| 219 |
+
"loss": 2.0336,
|
| 220 |
+
"step": 300
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.5688073394495413,
|
| 224 |
+
"grad_norm": 0.07091421633958817,
|
| 225 |
+
"learning_rate": 0.0004318512414382059,
|
| 226 |
+
"loss": 2.0319,
|
| 227 |
+
"step": 310
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.5871559633027523,
|
| 231 |
+
"grad_norm": 0.06183741241693497,
|
| 232 |
+
"learning_rate": 0.0004018961691397148,
|
| 233 |
+
"loss": 2.0334,
|
| 234 |
+
"step": 320
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.6055045871559633,
|
| 238 |
+
"grad_norm": 0.06812781095504761,
|
| 239 |
+
"learning_rate": 0.0003723032322457458,
|
| 240 |
+
"loss": 2.0188,
|
| 241 |
+
"step": 330
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.6238532110091743,
|
| 245 |
+
"grad_norm": 0.07636991143226624,
|
| 246 |
+
"learning_rate": 0.0003431816685921625,
|
| 247 |
+
"loss": 2.0179,
|
| 248 |
+
"step": 340
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.6422018348623854,
|
| 252 |
+
"grad_norm": 0.06623748689889908,
|
| 253 |
+
"learning_rate": 0.0003146389760120416,
|
| 254 |
+
"loss": 2.0149,
|
| 255 |
+
"step": 350
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.6605504587155964,
|
| 259 |
+
"grad_norm": 0.06370998173952103,
|
| 260 |
+
"learning_rate": 0.00028678051552373485,
|
| 261 |
+
"loss": 2.0155,
|
| 262 |
+
"step": 360
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.6788990825688074,
|
| 266 |
+
"grad_norm": 0.05421222001314163,
|
| 267 |
+
"learning_rate": 0.0002597091224066581,
|
| 268 |
+
"loss": 2.0085,
|
| 269 |
+
"step": 370
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.6972477064220184,
|
| 273 |
+
"grad_norm": 0.05421486124396324,
|
| 274 |
+
"learning_rate": 0.0002335247266004629,
|
| 275 |
+
"loss": 2.0124,
|
| 276 |
+
"step": 380
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.7155963302752294,
|
| 280 |
+
"grad_norm": 0.0552508644759655,
|
| 281 |
+
"learning_rate": 0.000208323983828828,
|
| 282 |
+
"loss": 2.0032,
|
| 283 |
+
"step": 390
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.7339449541284404,
|
| 287 |
+
"grad_norm": 0.05354559049010277,
|
| 288 |
+
"learning_rate": 0.0001841999188095224,
|
| 289 |
+
"loss": 1.9981,
|
| 290 |
+
"step": 400
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.7522935779816514,
|
| 294 |
+
"grad_norm": 0.05415147915482521,
|
| 295 |
+
"learning_rate": 0.00016124158186777676,
|
| 296 |
+
"loss": 2.0038,
|
| 297 |
+
"step": 410
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.7706422018348624,
|
| 301 |
+
"grad_norm": 0.06252424418926239,
|
| 302 |
+
"learning_rate": 0.0001395337202205211,
|
| 303 |
+
"loss": 1.997,
|
| 304 |
+
"step": 420
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.7889908256880734,
|
| 308 |
+
"grad_norm": 0.05192065238952637,
|
| 309 |
+
"learning_rate": 0.00011915646514489292,
|
| 310 |
+
"loss": 1.9962,
|
| 311 |
+
"step": 430
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.8073394495412844,
|
| 315 |
+
"grad_norm": 0.06241815537214279,
|
| 316 |
+
"learning_rate": 0.00010018503618578818,
|
| 317 |
+
"loss": 2.0005,
|
| 318 |
+
"step": 440
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.8256880733944955,
|
| 322 |
+
"grad_norm": 0.05685234069824219,
|
| 323 |
+
"learning_rate": 8.268946349432583e-05,
|
| 324 |
+
"loss": 1.9941,
|
| 325 |
+
"step": 450
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.8440366972477065,
|
| 329 |
+
"grad_norm": 0.054390374571084976,
|
| 330 |
+
"learning_rate": 6.673432932217117e-05,
|
| 331 |
+
"loss": 1.9892,
|
| 332 |
+
"step": 460
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.8623853211009175,
|
| 336 |
+
"grad_norm": 0.05205181986093521,
|
| 337 |
+
"learning_rate": 5.2378529625954684e-05,
|
| 338 |
+
"loss": 1.9831,
|
| 339 |
+
"step": 470
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.8807339449541285,
|
| 343 |
+
"grad_norm": 0.05071956664323807,
|
| 344 |
+
"learning_rate": 3.9675056661785556e-05,
|
| 345 |
+
"loss": 1.9859,
|
| 346 |
+
"step": 480
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.8990825688073395,
|
| 350 |
+
"grad_norm": 0.050324246287345886,
|
| 351 |
+
"learning_rate": 2.8670803372379538e-05,
|
| 352 |
+
"loss": 1.99,
|
| 353 |
+
"step": 490
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.9174311926605505,
|
| 357 |
+
"grad_norm": 0.0528382807970047,
|
| 358 |
+
"learning_rate": 1.9406390288876586e-05,
|
| 359 |
+
"loss": 1.994,
|
| 360 |
+
"step": 500
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.9357798165137615,
|
| 364 |
+
"grad_norm": 0.04993043094873428,
|
| 365 |
+
"learning_rate": 1.191601558631461e-05,
|
| 366 |
+
"loss": 1.9854,
|
| 367 |
+
"step": 510
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.9541284403669725,
|
| 371 |
+
"grad_norm": 0.04993810877203941,
|
| 372 |
+
"learning_rate": 6.2273288462559305e-06,
|
| 373 |
+
"loss": 1.9833,
|
| 374 |
+
"step": 520
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.9724770642201835,
|
| 378 |
+
"grad_norm": 0.049382567405700684,
|
| 379 |
+
"learning_rate": 2.361328992552314e-06,
|
| 380 |
+
"loss": 1.9862,
|
| 381 |
+
"step": 530
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.9908256880733946,
|
| 385 |
+
"grad_norm": 0.04873710125684738,
|
| 386 |
+
"learning_rate": 3.322867770044202e-07,
|
| 387 |
+
"loss": 1.9834,
|
| 388 |
+
"step": 540
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 1.0,
|
| 392 |
+
"step": 545,
|
| 393 |
+
"total_flos": 5.5510075143775846e+17,
|
| 394 |
+
"train_loss": 2.21631690209065,
|
| 395 |
+
"train_runtime": 3356.9073,
|
| 396 |
+
"train_samples_per_second": 166.263,
|
| 397 |
+
"train_steps_per_second": 0.162
|
| 398 |
+
}
|
| 399 |
+
],
|
| 400 |
+
"logging_steps": 10,
|
| 401 |
+
"max_steps": 545,
|
| 402 |
+
"num_input_tokens_seen": 33258880,
|
| 403 |
+
"num_train_epochs": 1,
|
| 404 |
+
"save_steps": 500,
|
| 405 |
+
"stateful_callbacks": {
|
| 406 |
+
"TrainerControl": {
|
| 407 |
+
"args": {
|
| 408 |
+
"should_epoch_stop": false,
|
| 409 |
+
"should_evaluate": false,
|
| 410 |
+
"should_log": false,
|
| 411 |
+
"should_save": false,
|
| 412 |
+
"should_training_stop": false
|
| 413 |
+
},
|
| 414 |
+
"attributes": {}
|
| 415 |
+
}
|
| 416 |
+
},
|
| 417 |
+
"total_flos": 5.5510075143775846e+17,
|
| 418 |
+
"train_batch_size": 32,
|
| 419 |
+
"trial_name": null,
|
| 420 |
+
"trial_params": null
|
| 421 |
+
}
|
continuous/smollm2/siglip2_l16_256/finetune/chat_template.jinja
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system
|
| 2 |
+
You are a helpful AI assistant named SmolLM, trained by Hugging Face<|im_end|>
|
| 3 |
+
' }}{% endif %}{{'<|im_start|>' + message['role'] + '
|
| 4 |
+
' + message['content'] + '<|im_end|>' + '
|
| 5 |
+
'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
|
| 6 |
+
' }}{% endif %}
|
continuous/smollm2/siglip2_l16_256/finetune/config.json
ADDED
|
@@ -0,0 +1,70 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_faster_video": false,
|
| 3 |
+
"add_time_instruction": false,
|
| 4 |
+
"architectures": [
|
| 5 |
+
"LlavaLlamaForCausalLM"
|
| 6 |
+
],
|
| 7 |
+
"attention_bias": false,
|
| 8 |
+
"attention_dropout": 0.0,
|
| 9 |
+
"bos_token_id": 1,
|
| 10 |
+
"dtype": "bfloat16",
|
| 11 |
+
"eos_token_id": 2,
|
| 12 |
+
"faster_token_stride": 10,
|
| 13 |
+
"force_sample": false,
|
| 14 |
+
"head_dim": 64,
|
| 15 |
+
"hidden_act": "silu",
|
| 16 |
+
"hidden_size": 2048,
|
| 17 |
+
"image_aspect_ratio": "square",
|
| 18 |
+
"image_crop_resolution": null,
|
| 19 |
+
"image_grid_pinpoints": null,
|
| 20 |
+
"image_split_resolution": null,
|
| 21 |
+
"initializer_range": 0.02,
|
| 22 |
+
"intermediate_size": 8192,
|
| 23 |
+
"max_position_embeddings": 8192,
|
| 24 |
+
"mlp_bias": false,
|
| 25 |
+
"mm_hidden_size": 1024,
|
| 26 |
+
"mm_newline_position": "grid",
|
| 27 |
+
"mm_patch_merge_type": "flat",
|
| 28 |
+
"mm_projector_lr": 0.0001,
|
| 29 |
+
"mm_projector_type": "mlp2x_gelu",
|
| 30 |
+
"mm_resampler_type": null,
|
| 31 |
+
"mm_spatial_pool_mode": "bilinear",
|
| 32 |
+
"mm_spatial_pool_stride": null,
|
| 33 |
+
"mm_tunable_parts": "mm_mlp_adapter,mm_language_model",
|
| 34 |
+
"mm_use_im_patch_token": false,
|
| 35 |
+
"mm_use_im_start_end": false,
|
| 36 |
+
"mm_vision_select_feature": "patch",
|
| 37 |
+
"mm_vision_select_layer": -2,
|
| 38 |
+
"mm_vision_tower": "open_clip_hub:ViT-L-16-SigLIP2-256",
|
| 39 |
+
"mm_vision_tower_lr": null,
|
| 40 |
+
"model_type": "llama",
|
| 41 |
+
"num_attention_heads": 32,
|
| 42 |
+
"num_hidden_layers": 24,
|
| 43 |
+
"num_key_value_heads": 32,
|
| 44 |
+
"pad_token_id": 0,
|
| 45 |
+
"pos_skipping_range": 4096,
|
| 46 |
+
"pretraining_tp": 1,
|
| 47 |
+
"rms_norm_eps": 1e-05,
|
| 48 |
+
"rope_scaling": null,
|
| 49 |
+
"rope_theta": 130000,
|
| 50 |
+
"tie_word_embeddings": true,
|
| 51 |
+
"tokenizer_model_max_length": 8192,
|
| 52 |
+
"tokenizer_padding_side": "right",
|
| 53 |
+
"transformers.js_config": {
|
| 54 |
+
"dtype": "q4",
|
| 55 |
+
"kv_cache_dtype": {
|
| 56 |
+
"fp16": "float16",
|
| 57 |
+
"q4f16": "float16"
|
| 58 |
+
},
|
| 59 |
+
"use_external_data_format": {
|
| 60 |
+
"model.onnx": true,
|
| 61 |
+
"model_fp16.onnx": true
|
| 62 |
+
}
|
| 63 |
+
},
|
| 64 |
+
"transformers_version": "4.57.6",
|
| 65 |
+
"use_cache": true,
|
| 66 |
+
"use_mm_proj": true,
|
| 67 |
+
"use_pos_skipping": false,
|
| 68 |
+
"vision_tower_pretrained": "/cache/ckpt/download/tokenizer/continuous/siglip2/siglip2_l16_256.npz",
|
| 69 |
+
"vocab_size": 49152
|
| 70 |
+
}
|