Upload continuous evaluation checkpoints, batch 17
Browse filesThis view is limited to 50 files because it contains too many changes. See raw diff
- .gitattributes +3 -0
- continuous/qwen3/mc2_s16_224_mt5/pretrain/mm_projector.bin +3 -0
- continuous/qwen3/mc2_s16_224_mt5/pretrain/trainer_state.json +421 -0
- continuous/qwen3/mc2_s16_384/finetune/added_tokens.json +28 -0
- continuous/qwen3/mc2_s16_384/finetune/config.json +59 -0
- continuous/qwen3/mc2_s16_384/finetune/generation_config.json +13 -0
- continuous/qwen3/mc2_s16_384/finetune/merges.txt +0 -0
- continuous/qwen3/mc2_s16_384/finetune/model.safetensors +3 -0
- continuous/qwen3/mc2_s16_384/finetune/special_tokens_map.json +31 -0
- continuous/qwen3/mc2_s16_384/finetune/tokenizer.json +3 -0
- continuous/qwen3/mc2_s16_384/finetune/tokenizer_config.json +241 -0
- continuous/qwen3/mc2_s16_384/finetune/trainer_state.json +1856 -0
- continuous/qwen3/mc2_s16_384/finetune/training_args.bin +3 -0
- continuous/qwen3/mc2_s16_384/finetune/vocab.json +0 -0
- continuous/qwen3/mc2_s16_384/pretrain/config.json +60 -0
- continuous/qwen3/mc2_s16_384/pretrain/mm_projector.bin +3 -0
- continuous/qwen3/mc2_s16_384/pretrain/trainer_state.json +421 -0
- continuous/qwen3/pe_core_b16_224/finetune/added_tokens.json +28 -0
- continuous/qwen3/pe_core_b16_224/finetune/chat_template.jinja +89 -0
- continuous/qwen3/pe_core_b16_224/finetune/config.json +89 -0
- continuous/qwen3/pe_core_b16_224/finetune/generation_config.json +12 -0
- continuous/qwen3/pe_core_b16_224/finetune/merges.txt +0 -0
- continuous/qwen3/pe_core_b16_224/finetune/model.safetensors +3 -0
- continuous/qwen3/pe_core_b16_224/finetune/special_tokens_map.json +31 -0
- continuous/qwen3/pe_core_b16_224/finetune/tokenizer.json +3 -0
- continuous/qwen3/pe_core_b16_224/finetune/tokenizer_config.json +240 -0
- continuous/qwen3/pe_core_b16_224/finetune/trainer_state.json +1856 -0
- continuous/qwen3/pe_core_b16_224/finetune/training_args.bin +3 -0
- continuous/qwen3/pe_core_b16_224/finetune/vocab.json +0 -0
- continuous/qwen3/pe_core_b16_224/pretrain/config.json +89 -0
- continuous/qwen3/pe_core_b16_224/pretrain/mm_projector.bin +3 -0
- continuous/qwen3/pe_core_b16_224/pretrain/trainer_state.json +421 -0
- continuous/qwen3/pe_core_g14_448/finetune/added_tokens.json +28 -0
- continuous/qwen3/pe_core_g14_448/finetune/chat_template.jinja +89 -0
- continuous/qwen3/pe_core_g14_448/finetune/config.json +89 -0
- continuous/qwen3/pe_core_g14_448/finetune/generation_config.json +12 -0
- continuous/qwen3/pe_core_g14_448/finetune/merges.txt +0 -0
- continuous/qwen3/pe_core_g14_448/finetune/model-00001-of-00002.safetensors +3 -0
- continuous/qwen3/pe_core_g14_448/finetune/model-00002-of-00002.safetensors +3 -0
- continuous/qwen3/pe_core_g14_448/finetune/model.safetensors.index.json +941 -0
- continuous/qwen3/pe_core_g14_448/finetune/special_tokens_map.json +31 -0
- continuous/qwen3/pe_core_g14_448/finetune/tokenizer.json +3 -0
- continuous/qwen3/pe_core_g14_448/finetune/tokenizer_config.json +240 -0
- continuous/qwen3/pe_core_g14_448/finetune/trainer_state.json +1856 -0
- continuous/qwen3/pe_core_g14_448/finetune/training_args.bin +3 -0
- continuous/qwen3/pe_core_g14_448/finetune/vocab.json +0 -0
- continuous/qwen3/pe_core_g14_448/pretrain/config.json +89 -0
- continuous/qwen3/pe_core_g14_448/pretrain/mm_projector.bin +3 -0
- continuous/qwen3/pe_core_g14_448/pretrain/trainer_state.json +421 -0
- continuous/qwen3/pe_lang_l14_448/finetune/added_tokens.json +28 -0
.gitattributes
CHANGED
|
@@ -149,3 +149,6 @@ continuous/qwen3/mc2_m16_224_mt5/finetune/tokenizer.json filter=lfs diff=lfs mer
|
|
| 149 |
continuous/qwen3/mc2_m16_384/finetune/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 150 |
continuous/qwen3/mc2_s16_224/finetune/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 151 |
continuous/qwen3/mc2_s16_224_mt5/finetune/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
| 149 |
continuous/qwen3/mc2_m16_384/finetune/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 150 |
continuous/qwen3/mc2_s16_224/finetune/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 151 |
continuous/qwen3/mc2_s16_224_mt5/finetune/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 152 |
+
continuous/qwen3/mc2_s16_384/finetune/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 153 |
+
continuous/qwen3/pe_core_b16_224/finetune/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 154 |
+
continuous/qwen3/pe_core_g14_448/finetune/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
continuous/qwen3/mc2_s16_224_mt5/pretrain/mm_projector.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:97998c2b693843bb961eda09416823fc80ff2ec4544903950b194c9fc1564ab4
|
| 3 |
+
size 19941432
|
continuous/qwen3/mc2_s16_224_mt5/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": 6.127491474151611,
|
| 15 |
+
"learning_rate": 0.00032142857142857147,
|
| 16 |
+
"loss": 8.9796,
|
| 17 |
+
"step": 10
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.03669724770642202,
|
| 21 |
+
"grad_norm": 0.5910182595252991,
|
| 22 |
+
"learning_rate": 0.0006785714285714287,
|
| 23 |
+
"loss": 5.503,
|
| 24 |
+
"step": 20
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.05504587155963303,
|
| 28 |
+
"grad_norm": 0.15893113613128662,
|
| 29 |
+
"learning_rate": 0.0009999907688176173,
|
| 30 |
+
"loss": 4.8302,
|
| 31 |
+
"step": 30
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.07339449541284404,
|
| 35 |
+
"grad_norm": 0.07155502587556839,
|
| 36 |
+
"learning_rate": 0.0009988834393115766,
|
| 37 |
+
"loss": 4.7132,
|
| 38 |
+
"step": 40
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.09174311926605505,
|
| 42 |
+
"grad_norm": 0.06990324705839157,
|
| 43 |
+
"learning_rate": 0.0009959345572940772,
|
| 44 |
+
"loss": 4.6607,
|
| 45 |
+
"step": 50
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.11009174311926606,
|
| 49 |
+
"grad_norm": 0.06187174469232559,
|
| 50 |
+
"learning_rate": 0.0009911550081155983,
|
| 51 |
+
"loss": 4.6276,
|
| 52 |
+
"step": 60
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.12844036697247707,
|
| 56 |
+
"grad_norm": 0.08483840525150299,
|
| 57 |
+
"learning_rate": 0.0009845624347566433,
|
| 58 |
+
"loss": 4.5822,
|
| 59 |
+
"step": 70
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.14678899082568808,
|
| 63 |
+
"grad_norm": 0.09943336993455887,
|
| 64 |
+
"learning_rate": 0.0009761811727013547,
|
| 65 |
+
"loss": 4.553,
|
| 66 |
+
"step": 80
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.1651376146788991,
|
| 70 |
+
"grad_norm": 0.11089316010475159,
|
| 71 |
+
"learning_rate": 0.0009660421601067666,
|
| 72 |
+
"loss": 4.5093,
|
| 73 |
+
"step": 90
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.1834862385321101,
|
| 77 |
+
"grad_norm": 0.20225423574447632,
|
| 78 |
+
"learning_rate": 0.0009541828235992926,
|
| 79 |
+
"loss": 4.4871,
|
| 80 |
+
"step": 100
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.2018348623853211,
|
| 84 |
+
"grad_norm": 0.11876742541790009,
|
| 85 |
+
"learning_rate": 0.0009406469401200151,
|
| 86 |
+
"loss": 4.4504,
|
| 87 |
+
"step": 110
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.22018348623853212,
|
| 91 |
+
"grad_norm": 0.11455609649419785,
|
| 92 |
+
"learning_rate": 0.0009254844753287492,
|
| 93 |
+
"loss": 4.4311,
|
| 94 |
+
"step": 120
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.23853211009174313,
|
| 98 |
+
"grad_norm": 0.11466437578201294,
|
| 99 |
+
"learning_rate": 0.0009087513991633924,
|
| 100 |
+
"loss": 4.3897,
|
| 101 |
+
"step": 130
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.25688073394495414,
|
| 105 |
+
"grad_norm": 0.12935182452201843,
|
| 106 |
+
"learning_rate": 0.0008905094792353917,
|
| 107 |
+
"loss": 4.3639,
|
| 108 |
+
"step": 140
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.27522935779816515,
|
| 112 |
+
"grad_norm": 0.09726376831531525,
|
| 113 |
+
"learning_rate": 0.0008708260528239789,
|
| 114 |
+
"loss": 4.3518,
|
| 115 |
+
"step": 150
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.29357798165137616,
|
| 119 |
+
"grad_norm": 0.12793773412704468,
|
| 120 |
+
"learning_rate": 0.0008497737783108237,
|
| 121 |
+
"loss": 4.3369,
|
| 122 |
+
"step": 160
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.3119266055045872,
|
| 126 |
+
"grad_norm": 0.1168447956442833,
|
| 127 |
+
"learning_rate": 0.0008274303669726426,
|
| 128 |
+
"loss": 4.3182,
|
| 129 |
+
"step": 170
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.3302752293577982,
|
| 133 |
+
"grad_norm": 0.12720541656017303,
|
| 134 |
+
"learning_rate": 0.0008038782961218137,
|
| 135 |
+
"loss": 4.3001,
|
| 136 |
+
"step": 180
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.3486238532110092,
|
| 140 |
+
"grad_norm": 0.1099531278014183,
|
| 141 |
+
"learning_rate": 0.000779204504653894,
|
| 142 |
+
"loss": 4.2901,
|
| 143 |
+
"step": 190
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.3669724770642202,
|
| 147 |
+
"grad_norm": 0.1324494183063507,
|
| 148 |
+
"learning_rate": 0.0007535000721258791,
|
| 149 |
+
"loss": 4.2685,
|
| 150 |
+
"step": 200
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.3853211009174312,
|
| 154 |
+
"grad_norm": 0.13128875195980072,
|
| 155 |
+
"learning_rate": 0.00072685988254984,
|
| 156 |
+
"loss": 4.2584,
|
| 157 |
+
"step": 210
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.4036697247706422,
|
| 161 |
+
"grad_norm": 0.1253524273633957,
|
| 162 |
+
"learning_rate": 0.0006993822741429906,
|
| 163 |
+
"loss": 4.2635,
|
| 164 |
+
"step": 220
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.42201834862385323,
|
| 168 |
+
"grad_norm": 0.12984363734722137,
|
| 169 |
+
"learning_rate": 0.0006711686763270818,
|
| 170 |
+
"loss": 4.2482,
|
| 171 |
+
"step": 230
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.44036697247706424,
|
| 175 |
+
"grad_norm": 0.11397641152143478,
|
| 176 |
+
"learning_rate": 0.0006423232353170831,
|
| 177 |
+
"loss": 4.2239,
|
| 178 |
+
"step": 240
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.45871559633027525,
|
| 182 |
+
"grad_norm": 0.1253732293844223,
|
| 183 |
+
"learning_rate": 0.0006129524296812335,
|
| 184 |
+
"loss": 4.1942,
|
| 185 |
+
"step": 250
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.47706422018348627,
|
| 189 |
+
"grad_norm": 0.12103944271802902,
|
| 190 |
+
"learning_rate": 0.0005831646772915651,
|
| 191 |
+
"loss": 4.196,
|
| 192 |
+
"step": 260
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.4954128440366973,
|
| 196 |
+
"grad_norm": 0.11593898385763168,
|
| 197 |
+
"learning_rate": 0.0005530699351157809,
|
| 198 |
+
"loss": 4.1712,
|
| 199 |
+
"step": 270
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.5137614678899083,
|
| 203 |
+
"grad_norm": 0.10606931895017624,
|
| 204 |
+
"learning_rate": 0.0005227792933277943,
|
| 205 |
+
"loss": 4.1641,
|
| 206 |
+
"step": 280
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.5321100917431193,
|
| 210 |
+
"grad_norm": 0.11027190089225769,
|
| 211 |
+
"learning_rate": 0.0004924045652352092,
|
| 212 |
+
"loss": 4.1445,
|
| 213 |
+
"step": 290
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.5504587155963303,
|
| 217 |
+
"grad_norm": 0.11084482818841934,
|
| 218 |
+
"learning_rate": 0.0004620578745374633,
|
| 219 |
+
"loss": 4.1383,
|
| 220 |
+
"step": 300
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.5688073394495413,
|
| 224 |
+
"grad_norm": 0.1078275740146637,
|
| 225 |
+
"learning_rate": 0.0004318512414382059,
|
| 226 |
+
"loss": 4.1487,
|
| 227 |
+
"step": 310
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.5871559633027523,
|
| 231 |
+
"grad_norm": 0.09912154823541641,
|
| 232 |
+
"learning_rate": 0.0004018961691397148,
|
| 233 |
+
"loss": 4.1374,
|
| 234 |
+
"step": 320
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.6055045871559633,
|
| 238 |
+
"grad_norm": 0.10998658835887909,
|
| 239 |
+
"learning_rate": 0.0003723032322457458,
|
| 240 |
+
"loss": 4.1188,
|
| 241 |
+
"step": 330
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.6238532110091743,
|
| 245 |
+
"grad_norm": 0.11064264178276062,
|
| 246 |
+
"learning_rate": 0.0003431816685921625,
|
| 247 |
+
"loss": 4.1175,
|
| 248 |
+
"step": 340
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.6422018348623854,
|
| 252 |
+
"grad_norm": 0.11228351294994354,
|
| 253 |
+
"learning_rate": 0.0003146389760120416,
|
| 254 |
+
"loss": 4.1197,
|
| 255 |
+
"step": 350
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.6605504587155964,
|
| 259 |
+
"grad_norm": 0.12546762824058533,
|
| 260 |
+
"learning_rate": 0.00028678051552373485,
|
| 261 |
+
"loss": 4.1217,
|
| 262 |
+
"step": 360
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.6788990825688074,
|
| 266 |
+
"grad_norm": 0.10941796749830246,
|
| 267 |
+
"learning_rate": 0.0002597091224066581,
|
| 268 |
+
"loss": 4.1087,
|
| 269 |
+
"step": 370
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.6972477064220184,
|
| 273 |
+
"grad_norm": 0.09463196247816086,
|
| 274 |
+
"learning_rate": 0.0002335247266004629,
|
| 275 |
+
"loss": 4.1189,
|
| 276 |
+
"step": 380
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.7155963302752294,
|
| 280 |
+
"grad_norm": 0.11178228259086609,
|
| 281 |
+
"learning_rate": 0.000208323983828828,
|
| 282 |
+
"loss": 4.1019,
|
| 283 |
+
"step": 390
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.7339449541284404,
|
| 287 |
+
"grad_norm": 0.1187169998884201,
|
| 288 |
+
"learning_rate": 0.0001841999188095224,
|
| 289 |
+
"loss": 4.1014,
|
| 290 |
+
"step": 400
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.7522935779816514,
|
| 294 |
+
"grad_norm": 0.10276882350444794,
|
| 295 |
+
"learning_rate": 0.00016124158186777676,
|
| 296 |
+
"loss": 4.1031,
|
| 297 |
+
"step": 410
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.7706422018348624,
|
| 301 |
+
"grad_norm": 0.09792952984571457,
|
| 302 |
+
"learning_rate": 0.0001395337202205211,
|
| 303 |
+
"loss": 4.0944,
|
| 304 |
+
"step": 420
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.7889908256880734,
|
| 308 |
+
"grad_norm": 0.09643371403217316,
|
| 309 |
+
"learning_rate": 0.00011915646514489292,
|
| 310 |
+
"loss": 4.0979,
|
| 311 |
+
"step": 430
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.8073394495412844,
|
| 315 |
+
"grad_norm": 0.110744409263134,
|
| 316 |
+
"learning_rate": 0.00010018503618578818,
|
| 317 |
+
"loss": 4.1046,
|
| 318 |
+
"step": 440
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.8256880733944955,
|
| 322 |
+
"grad_norm": 0.10068485140800476,
|
| 323 |
+
"learning_rate": 8.268946349432583e-05,
|
| 324 |
+
"loss": 4.0954,
|
| 325 |
+
"step": 450
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.8440366972477065,
|
| 329 |
+
"grad_norm": 0.10407047718763351,
|
| 330 |
+
"learning_rate": 6.673432932217117e-05,
|
| 331 |
+
"loss": 4.089,
|
| 332 |
+
"step": 460
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.8623853211009175,
|
| 336 |
+
"grad_norm": 0.09457176923751831,
|
| 337 |
+
"learning_rate": 5.2378529625954684e-05,
|
| 338 |
+
"loss": 4.0745,
|
| 339 |
+
"step": 470
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.8807339449541285,
|
| 343 |
+
"grad_norm": 0.0950651615858078,
|
| 344 |
+
"learning_rate": 3.9675056661785556e-05,
|
| 345 |
+
"loss": 4.083,
|
| 346 |
+
"step": 480
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.8990825688073395,
|
| 350 |
+
"grad_norm": 0.0962802842259407,
|
| 351 |
+
"learning_rate": 2.8670803372379538e-05,
|
| 352 |
+
"loss": 4.0865,
|
| 353 |
+
"step": 490
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.9174311926605505,
|
| 357 |
+
"grad_norm": 0.10092651098966599,
|
| 358 |
+
"learning_rate": 1.9406390288876586e-05,
|
| 359 |
+
"loss": 4.0982,
|
| 360 |
+
"step": 500
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.9357798165137615,
|
| 364 |
+
"grad_norm": 0.0951826348900795,
|
| 365 |
+
"learning_rate": 1.191601558631461e-05,
|
| 366 |
+
"loss": 4.0885,
|
| 367 |
+
"step": 510
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.9541284403669725,
|
| 371 |
+
"grad_norm": 0.10214207321405411,
|
| 372 |
+
"learning_rate": 6.2273288462559305e-06,
|
| 373 |
+
"loss": 4.0813,
|
| 374 |
+
"step": 520
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.9724770642201835,
|
| 378 |
+
"grad_norm": 0.09521793574094772,
|
| 379 |
+
"learning_rate": 2.361328992552314e-06,
|
| 380 |
+
"loss": 4.0855,
|
| 381 |
+
"step": 530
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.9908256880733946,
|
| 385 |
+
"grad_norm": 0.09772378206253052,
|
| 386 |
+
"learning_rate": 3.322867770044202e-07,
|
| 387 |
+
"loss": 4.0839,
|
| 388 |
+
"step": 540
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 1.0,
|
| 392 |
+
"step": 545,
|
| 393 |
+
"total_flos": 2.856007673923502e+17,
|
| 394 |
+
"train_loss": 4.3573867447879335,
|
| 395 |
+
"train_runtime": 5607.7405,
|
| 396 |
+
"train_samples_per_second": 99.528,
|
| 397 |
+
"train_steps_per_second": 0.097
|
| 398 |
+
}
|
| 399 |
+
],
|
| 400 |
+
"logging_steps": 10,
|
| 401 |
+
"max_steps": 545,
|
| 402 |
+
"num_input_tokens_seen": 0,
|
| 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": 2.856007673923502e+17,
|
| 418 |
+
"train_batch_size": 64,
|
| 419 |
+
"trial_name": null,
|
| 420 |
+
"trial_params": null
|
| 421 |
+
}
|
continuous/qwen3/mc2_s16_384/finetune/added_tokens.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</think>": 151668,
|
| 3 |
+
"</tool_call>": 151658,
|
| 4 |
+
"</tool_response>": 151666,
|
| 5 |
+
"<think>": 151667,
|
| 6 |
+
"<tool_call>": 151657,
|
| 7 |
+
"<tool_response>": 151665,
|
| 8 |
+
"<|box_end|>": 151649,
|
| 9 |
+
"<|box_start|>": 151648,
|
| 10 |
+
"<|endoftext|>": 151643,
|
| 11 |
+
"<|file_sep|>": 151664,
|
| 12 |
+
"<|fim_middle|>": 151660,
|
| 13 |
+
"<|fim_pad|>": 151662,
|
| 14 |
+
"<|fim_prefix|>": 151659,
|
| 15 |
+
"<|fim_suffix|>": 151661,
|
| 16 |
+
"<|im_end|>": 151645,
|
| 17 |
+
"<|im_start|>": 151644,
|
| 18 |
+
"<|image_pad|>": 151655,
|
| 19 |
+
"<|object_ref_end|>": 151647,
|
| 20 |
+
"<|object_ref_start|>": 151646,
|
| 21 |
+
"<|quad_end|>": 151651,
|
| 22 |
+
"<|quad_start|>": 151650,
|
| 23 |
+
"<|repo_name|>": 151663,
|
| 24 |
+
"<|video_pad|>": 151656,
|
| 25 |
+
"<|vision_end|>": 151653,
|
| 26 |
+
"<|vision_pad|>": 151654,
|
| 27 |
+
"<|vision_start|>": 151652
|
| 28 |
+
}
|
continuous/qwen3/mc2_s16_384/finetune/config.json
ADDED
|
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_faster_video": false,
|
| 3 |
+
"add_time_instruction": false,
|
| 4 |
+
"architectures": [
|
| 5 |
+
"LlavaQwen3ForCausalLM"
|
| 6 |
+
],
|
| 7 |
+
"attention_bias": false,
|
| 8 |
+
"attention_dropout": 0.0,
|
| 9 |
+
"bos_token_id": 151643,
|
| 10 |
+
"eos_token_id": 151645,
|
| 11 |
+
"faster_token_stride": 10,
|
| 12 |
+
"force_sample": false,
|
| 13 |
+
"head_dim": 128,
|
| 14 |
+
"hidden_act": "silu",
|
| 15 |
+
"hidden_size": 2048,
|
| 16 |
+
"image_aspect_ratio": "square",
|
| 17 |
+
"image_crop_resolution": null,
|
| 18 |
+
"image_grid_pinpoints": null,
|
| 19 |
+
"image_split_resolution": null,
|
| 20 |
+
"initializer_range": 0.02,
|
| 21 |
+
"intermediate_size": 6144,
|
| 22 |
+
"max_position_embeddings": 40960,
|
| 23 |
+
"max_window_layers": 28,
|
| 24 |
+
"mm_hidden_size": 384,
|
| 25 |
+
"mm_newline_position": "grid",
|
| 26 |
+
"mm_patch_merge_type": "flat",
|
| 27 |
+
"mm_projector_lr": 0.0001,
|
| 28 |
+
"mm_projector_type": "mlp2x_gelu",
|
| 29 |
+
"mm_resampler_type": null,
|
| 30 |
+
"mm_spatial_pool_mode": "bilinear",
|
| 31 |
+
"mm_spatial_pool_stride": null,
|
| 32 |
+
"mm_tunable_parts": "mm_mlp_adapter,mm_language_model",
|
| 33 |
+
"mm_use_im_patch_token": false,
|
| 34 |
+
"mm_use_im_start_end": false,
|
| 35 |
+
"mm_vision_select_feature": "patch",
|
| 36 |
+
"mm_vision_select_layer": -2,
|
| 37 |
+
"mm_vision_tower": "open_clip_hub:ViT-S-16",
|
| 38 |
+
"mm_vision_tower_lr": null,
|
| 39 |
+
"model_type": "qwen3",
|
| 40 |
+
"num_attention_heads": 16,
|
| 41 |
+
"num_hidden_layers": 28,
|
| 42 |
+
"num_key_value_heads": 8,
|
| 43 |
+
"pos_skipping_range": 4096,
|
| 44 |
+
"rms_norm_eps": 1e-06,
|
| 45 |
+
"rope_scaling": null,
|
| 46 |
+
"rope_theta": 1000000,
|
| 47 |
+
"sliding_window": null,
|
| 48 |
+
"tie_word_embeddings": true,
|
| 49 |
+
"tokenizer_model_max_length": 8192,
|
| 50 |
+
"tokenizer_padding_side": "right",
|
| 51 |
+
"torch_dtype": "bfloat16",
|
| 52 |
+
"transformers_version": "4.51.3",
|
| 53 |
+
"use_cache": true,
|
| 54 |
+
"use_mm_proj": true,
|
| 55 |
+
"use_pos_skipping": false,
|
| 56 |
+
"use_sliding_window": false,
|
| 57 |
+
"vision_tower_pretrained": "/cache/ckpt/download/tokenizer/continuous/mc2/mc2_s16_384.pt",
|
| 58 |
+
"vocab_size": 151936
|
| 59 |
+
}
|
continuous/qwen3/mc2_s16_384/finetune/generation_config.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 151643,
|
| 3 |
+
"do_sample": true,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
151645,
|
| 6 |
+
151643
|
| 7 |
+
],
|
| 8 |
+
"pad_token_id": 151643,
|
| 9 |
+
"temperature": 0.6,
|
| 10 |
+
"top_k": 20,
|
| 11 |
+
"top_p": 0.95,
|
| 12 |
+
"transformers_version": "4.51.3"
|
| 13 |
+
}
|
continuous/qwen3/mc2_s16_384/finetune/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
continuous/qwen3/mc2_s16_384/finetune/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9b092fd8bf732407ef64044decafbe3ded8bf2b1b2f46eafa14e205589cad5cc
|
| 3 |
+
size 4127396088
|
continuous/qwen3/mc2_s16_384/finetune/special_tokens_map.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|im_start|>",
|
| 4 |
+
"<|im_end|>",
|
| 5 |
+
"<|object_ref_start|>",
|
| 6 |
+
"<|object_ref_end|>",
|
| 7 |
+
"<|box_start|>",
|
| 8 |
+
"<|box_end|>",
|
| 9 |
+
"<|quad_start|>",
|
| 10 |
+
"<|quad_end|>",
|
| 11 |
+
"<|vision_start|>",
|
| 12 |
+
"<|vision_end|>",
|
| 13 |
+
"<|vision_pad|>",
|
| 14 |
+
"<|image_pad|>",
|
| 15 |
+
"<|video_pad|>"
|
| 16 |
+
],
|
| 17 |
+
"eos_token": {
|
| 18 |
+
"content": "<|im_end|>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
},
|
| 24 |
+
"pad_token": {
|
| 25 |
+
"content": "<|endoftext|>",
|
| 26 |
+
"lstrip": false,
|
| 27 |
+
"normalized": false,
|
| 28 |
+
"rstrip": false,
|
| 29 |
+
"single_word": false
|
| 30 |
+
}
|
| 31 |
+
}
|
continuous/qwen3/mc2_s16_384/finetune/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
|
| 3 |
+
size 11422654
|
continuous/qwen3/mc2_s16_384/finetune/tokenizer_config.json
ADDED
|
@@ -0,0 +1,241 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_prefix_space": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"151643": {
|
| 6 |
+
"content": "<|endoftext|>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"151644": {
|
| 14 |
+
"content": "<|im_start|>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"151645": {
|
| 22 |
+
"content": "<|im_end|>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
},
|
| 29 |
+
"151646": {
|
| 30 |
+
"content": "<|object_ref_start|>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false,
|
| 35 |
+
"special": true
|
| 36 |
+
},
|
| 37 |
+
"151647": {
|
| 38 |
+
"content": "<|object_ref_end|>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false,
|
| 43 |
+
"special": true
|
| 44 |
+
},
|
| 45 |
+
"151648": {
|
| 46 |
+
"content": "<|box_start|>",
|
| 47 |
+
"lstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"rstrip": false,
|
| 50 |
+
"single_word": false,
|
| 51 |
+
"special": true
|
| 52 |
+
},
|
| 53 |
+
"151649": {
|
| 54 |
+
"content": "<|box_end|>",
|
| 55 |
+
"lstrip": false,
|
| 56 |
+
"normalized": false,
|
| 57 |
+
"rstrip": false,
|
| 58 |
+
"single_word": false,
|
| 59 |
+
"special": true
|
| 60 |
+
},
|
| 61 |
+
"151650": {
|
| 62 |
+
"content": "<|quad_start|>",
|
| 63 |
+
"lstrip": false,
|
| 64 |
+
"normalized": false,
|
| 65 |
+
"rstrip": false,
|
| 66 |
+
"single_word": false,
|
| 67 |
+
"special": true
|
| 68 |
+
},
|
| 69 |
+
"151651": {
|
| 70 |
+
"content": "<|quad_end|>",
|
| 71 |
+
"lstrip": false,
|
| 72 |
+
"normalized": false,
|
| 73 |
+
"rstrip": false,
|
| 74 |
+
"single_word": false,
|
| 75 |
+
"special": true
|
| 76 |
+
},
|
| 77 |
+
"151652": {
|
| 78 |
+
"content": "<|vision_start|>",
|
| 79 |
+
"lstrip": false,
|
| 80 |
+
"normalized": false,
|
| 81 |
+
"rstrip": false,
|
| 82 |
+
"single_word": false,
|
| 83 |
+
"special": true
|
| 84 |
+
},
|
| 85 |
+
"151653": {
|
| 86 |
+
"content": "<|vision_end|>",
|
| 87 |
+
"lstrip": false,
|
| 88 |
+
"normalized": false,
|
| 89 |
+
"rstrip": false,
|
| 90 |
+
"single_word": false,
|
| 91 |
+
"special": true
|
| 92 |
+
},
|
| 93 |
+
"151654": {
|
| 94 |
+
"content": "<|vision_pad|>",
|
| 95 |
+
"lstrip": false,
|
| 96 |
+
"normalized": false,
|
| 97 |
+
"rstrip": false,
|
| 98 |
+
"single_word": false,
|
| 99 |
+
"special": true
|
| 100 |
+
},
|
| 101 |
+
"151655": {
|
| 102 |
+
"content": "<|image_pad|>",
|
| 103 |
+
"lstrip": false,
|
| 104 |
+
"normalized": false,
|
| 105 |
+
"rstrip": false,
|
| 106 |
+
"single_word": false,
|
| 107 |
+
"special": true
|
| 108 |
+
},
|
| 109 |
+
"151656": {
|
| 110 |
+
"content": "<|video_pad|>",
|
| 111 |
+
"lstrip": false,
|
| 112 |
+
"normalized": false,
|
| 113 |
+
"rstrip": false,
|
| 114 |
+
"single_word": false,
|
| 115 |
+
"special": true
|
| 116 |
+
},
|
| 117 |
+
"151657": {
|
| 118 |
+
"content": "<tool_call>",
|
| 119 |
+
"lstrip": false,
|
| 120 |
+
"normalized": false,
|
| 121 |
+
"rstrip": false,
|
| 122 |
+
"single_word": false,
|
| 123 |
+
"special": false
|
| 124 |
+
},
|
| 125 |
+
"151658": {
|
| 126 |
+
"content": "</tool_call>",
|
| 127 |
+
"lstrip": false,
|
| 128 |
+
"normalized": false,
|
| 129 |
+
"rstrip": false,
|
| 130 |
+
"single_word": false,
|
| 131 |
+
"special": false
|
| 132 |
+
},
|
| 133 |
+
"151659": {
|
| 134 |
+
"content": "<|fim_prefix|>",
|
| 135 |
+
"lstrip": false,
|
| 136 |
+
"normalized": false,
|
| 137 |
+
"rstrip": false,
|
| 138 |
+
"single_word": false,
|
| 139 |
+
"special": false
|
| 140 |
+
},
|
| 141 |
+
"151660": {
|
| 142 |
+
"content": "<|fim_middle|>",
|
| 143 |
+
"lstrip": false,
|
| 144 |
+
"normalized": false,
|
| 145 |
+
"rstrip": false,
|
| 146 |
+
"single_word": false,
|
| 147 |
+
"special": false
|
| 148 |
+
},
|
| 149 |
+
"151661": {
|
| 150 |
+
"content": "<|fim_suffix|>",
|
| 151 |
+
"lstrip": false,
|
| 152 |
+
"normalized": false,
|
| 153 |
+
"rstrip": false,
|
| 154 |
+
"single_word": false,
|
| 155 |
+
"special": false
|
| 156 |
+
},
|
| 157 |
+
"151662": {
|
| 158 |
+
"content": "<|fim_pad|>",
|
| 159 |
+
"lstrip": false,
|
| 160 |
+
"normalized": false,
|
| 161 |
+
"rstrip": false,
|
| 162 |
+
"single_word": false,
|
| 163 |
+
"special": false
|
| 164 |
+
},
|
| 165 |
+
"151663": {
|
| 166 |
+
"content": "<|repo_name|>",
|
| 167 |
+
"lstrip": false,
|
| 168 |
+
"normalized": false,
|
| 169 |
+
"rstrip": false,
|
| 170 |
+
"single_word": false,
|
| 171 |
+
"special": false
|
| 172 |
+
},
|
| 173 |
+
"151664": {
|
| 174 |
+
"content": "<|file_sep|>",
|
| 175 |
+
"lstrip": false,
|
| 176 |
+
"normalized": false,
|
| 177 |
+
"rstrip": false,
|
| 178 |
+
"single_word": false,
|
| 179 |
+
"special": false
|
| 180 |
+
},
|
| 181 |
+
"151665": {
|
| 182 |
+
"content": "<tool_response>",
|
| 183 |
+
"lstrip": false,
|
| 184 |
+
"normalized": false,
|
| 185 |
+
"rstrip": false,
|
| 186 |
+
"single_word": false,
|
| 187 |
+
"special": false
|
| 188 |
+
},
|
| 189 |
+
"151666": {
|
| 190 |
+
"content": "</tool_response>",
|
| 191 |
+
"lstrip": false,
|
| 192 |
+
"normalized": false,
|
| 193 |
+
"rstrip": false,
|
| 194 |
+
"single_word": false,
|
| 195 |
+
"special": false
|
| 196 |
+
},
|
| 197 |
+
"151667": {
|
| 198 |
+
"content": "<think>",
|
| 199 |
+
"lstrip": false,
|
| 200 |
+
"normalized": false,
|
| 201 |
+
"rstrip": false,
|
| 202 |
+
"single_word": false,
|
| 203 |
+
"special": false
|
| 204 |
+
},
|
| 205 |
+
"151668": {
|
| 206 |
+
"content": "</think>",
|
| 207 |
+
"lstrip": false,
|
| 208 |
+
"normalized": false,
|
| 209 |
+
"rstrip": false,
|
| 210 |
+
"single_word": false,
|
| 211 |
+
"special": false
|
| 212 |
+
}
|
| 213 |
+
},
|
| 214 |
+
"additional_special_tokens": [
|
| 215 |
+
"<|im_start|>",
|
| 216 |
+
"<|im_end|>",
|
| 217 |
+
"<|object_ref_start|>",
|
| 218 |
+
"<|object_ref_end|>",
|
| 219 |
+
"<|box_start|>",
|
| 220 |
+
"<|box_end|>",
|
| 221 |
+
"<|quad_start|>",
|
| 222 |
+
"<|quad_end|>",
|
| 223 |
+
"<|vision_start|>",
|
| 224 |
+
"<|vision_end|>",
|
| 225 |
+
"<|vision_pad|>",
|
| 226 |
+
"<|image_pad|>",
|
| 227 |
+
"<|video_pad|>"
|
| 228 |
+
],
|
| 229 |
+
"bos_token": null,
|
| 230 |
+
"chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0].role == 'system' %}\n {{- messages[0].content + '\\n\\n' }}\n {%- endif %}\n {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0].role == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0].content + '<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n {%- set index = (messages|length - 1) - loop.index0 %}\n {%- if ns.multi_step_tool and message.role == \"user\" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}\n {%- set ns.multi_step_tool = false %}\n {%- set ns.last_query_index = index %}\n {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n {%- if message.content is string %}\n {%- set content = message.content %}\n {%- else %}\n {%- set content = '' %}\n {%- endif %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n {{- '<|im_start|>' + message.role + '\\n' + content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {%- set reasoning_content = '' %}\n {%- if message.reasoning_content is string %}\n {%- set reasoning_content = message.reasoning_content %}\n {%- else %}\n {%- if '</think>' in content %}\n {%- set reasoning_content = content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n {%- set content = content.split('</think>')[-1].lstrip('\\n') %}\n {%- endif %}\n {%- endif %}\n {%- if loop.index0 > ns.last_query_index %}\n {%- if loop.last or (not loop.last and reasoning_content) %}\n {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content.strip('\\n') + '\\n</think>\\n\\n' + content.lstrip('\\n') }}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- if message.tool_calls %}\n {%- for tool_call in message.tool_calls %}\n {%- if (loop.first and content) or (not loop.first) %}\n {{- '\\n' }}\n {%- endif %}\n {%- if tool_call.function %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {%- if tool_call.arguments is string %}\n {{- tool_call.arguments }}\n {%- else %}\n {{- tool_call.arguments | tojson }}\n {%- endif %}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n {%- if enable_thinking is defined and enable_thinking is false %}\n {{- '<think>\\n\\n</think>\\n\\n' }}\n {%- endif %}\n{%- endif %}",
|
| 231 |
+
"clean_up_tokenization_spaces": false,
|
| 232 |
+
"eos_token": "<|im_end|>",
|
| 233 |
+
"errors": "replace",
|
| 234 |
+
"extra_special_tokens": {},
|
| 235 |
+
"model_max_length": 8192,
|
| 236 |
+
"pad_token": "<|endoftext|>",
|
| 237 |
+
"padding_side": "right",
|
| 238 |
+
"split_special_tokens": false,
|
| 239 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 240 |
+
"unk_token": null
|
| 241 |
+
}
|
continuous/qwen3/mc2_s16_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": 0.9999037443449803,
|
| 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": 0.003850226200789296,
|
| 14 |
+
"grad_norm": 6.308640480041504,
|
| 15 |
+
"learning_rate": 1.153846153846154e-06,
|
| 16 |
+
"loss": 2.9248,
|
| 17 |
+
"step": 10
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.007700452401578592,
|
| 21 |
+
"grad_norm": 2.5847158432006836,
|
| 22 |
+
"learning_rate": 2.435897435897436e-06,
|
| 23 |
+
"loss": 2.1532,
|
| 24 |
+
"step": 20
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.01155067860236789,
|
| 28 |
+
"grad_norm": 1.4427826404571533,
|
| 29 |
+
"learning_rate": 3.7179487179487184e-06,
|
| 30 |
+
"loss": 1.5385,
|
| 31 |
+
"step": 30
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.015400904803157185,
|
| 35 |
+
"grad_norm": 0.4339388310909271,
|
| 36 |
+
"learning_rate": 5e-06,
|
| 37 |
+
"loss": 1.1302,
|
| 38 |
+
"step": 40
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.019251131003946483,
|
| 42 |
+
"grad_norm": 0.277953177690506,
|
| 43 |
+
"learning_rate": 6.282051282051282e-06,
|
| 44 |
+
"loss": 1.006,
|
| 45 |
+
"step": 50
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.02310135720473578,
|
| 49 |
+
"grad_norm": 0.1529337465763092,
|
| 50 |
+
"learning_rate": 7.564102564102564e-06,
|
| 51 |
+
"loss": 0.935,
|
| 52 |
+
"step": 60
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.026951583405525073,
|
| 56 |
+
"grad_norm": 0.11944018304347992,
|
| 57 |
+
"learning_rate": 8.846153846153847e-06,
|
| 58 |
+
"loss": 0.9005,
|
| 59 |
+
"step": 70
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.03080180960631437,
|
| 63 |
+
"grad_norm": 0.11309627443552017,
|
| 64 |
+
"learning_rate": 9.999996111488723e-06,
|
| 65 |
+
"loss": 0.9141,
|
| 66 |
+
"step": 80
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.034652035807103666,
|
| 70 |
+
"grad_norm": 0.10875039547681808,
|
| 71 |
+
"learning_rate": 9.999529497453782e-06,
|
| 72 |
+
"loss": 0.8789,
|
| 73 |
+
"step": 90
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.038502262007892966,
|
| 77 |
+
"grad_norm": 0.09998256713151932,
|
| 78 |
+
"learning_rate": 9.998285264324193e-06,
|
| 79 |
+
"loss": 0.8541,
|
| 80 |
+
"step": 100
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.04235248820868226,
|
| 84 |
+
"grad_norm": 0.10317328572273254,
|
| 85 |
+
"learning_rate": 9.996263605626052e-06,
|
| 86 |
+
"loss": 0.849,
|
| 87 |
+
"step": 110
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.04620271440947156,
|
| 91 |
+
"grad_norm": 0.08659590780735016,
|
| 92 |
+
"learning_rate": 9.99346483580503e-06,
|
| 93 |
+
"loss": 0.8407,
|
| 94 |
+
"step": 120
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.05005294061026085,
|
| 98 |
+
"grad_norm": 0.08782156556844711,
|
| 99 |
+
"learning_rate": 9.989889390177467e-06,
|
| 100 |
+
"loss": 0.8213,
|
| 101 |
+
"step": 130
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.053903166811050146,
|
| 105 |
+
"grad_norm": 0.09811824560165405,
|
| 106 |
+
"learning_rate": 9.985537824862647e-06,
|
| 107 |
+
"loss": 0.8262,
|
| 108 |
+
"step": 140
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.057753393011839446,
|
| 112 |
+
"grad_norm": 0.09446346014738083,
|
| 113 |
+
"learning_rate": 9.980410816696317e-06,
|
| 114 |
+
"loss": 0.8259,
|
| 115 |
+
"step": 150
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.06160361921262874,
|
| 119 |
+
"grad_norm": 0.09506165236234665,
|
| 120 |
+
"learning_rate": 9.97450916312541e-06,
|
| 121 |
+
"loss": 0.8251,
|
| 122 |
+
"step": 160
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.06545384541341803,
|
| 126 |
+
"grad_norm": 0.0758913978934288,
|
| 127 |
+
"learning_rate": 9.967833782084004e-06,
|
| 128 |
+
"loss": 0.8015,
|
| 129 |
+
"step": 170
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.06930407161420733,
|
| 133 |
+
"grad_norm": 0.07873956114053726,
|
| 134 |
+
"learning_rate": 9.960385711850554e-06,
|
| 135 |
+
"loss": 0.8308,
|
| 136 |
+
"step": 180
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.07315429781499663,
|
| 140 |
+
"grad_norm": 0.07836099714040756,
|
| 141 |
+
"learning_rate": 9.952166110886394e-06,
|
| 142 |
+
"loss": 0.8292,
|
| 143 |
+
"step": 190
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.07700452401578593,
|
| 147 |
+
"grad_norm": 0.09721947461366653,
|
| 148 |
+
"learning_rate": 9.943176257655567e-06,
|
| 149 |
+
"loss": 0.7973,
|
| 150 |
+
"step": 200
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.08085475021657522,
|
| 154 |
+
"grad_norm": 0.08586981892585754,
|
| 155 |
+
"learning_rate": 9.933417550425952e-06,
|
| 156 |
+
"loss": 0.8149,
|
| 157 |
+
"step": 210
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.08470497641736452,
|
| 161 |
+
"grad_norm": 0.0750044509768486,
|
| 162 |
+
"learning_rate": 9.9228915070518e-06,
|
| 163 |
+
"loss": 0.7967,
|
| 164 |
+
"step": 220
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.08855520261815382,
|
| 168 |
+
"grad_norm": 0.08416061103343964,
|
| 169 |
+
"learning_rate": 9.911599764737632e-06,
|
| 170 |
+
"loss": 0.7872,
|
| 171 |
+
"step": 230
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.09240542881894312,
|
| 175 |
+
"grad_norm": 0.07834203541278839,
|
| 176 |
+
"learning_rate": 9.899544079783606e-06,
|
| 177 |
+
"loss": 0.7843,
|
| 178 |
+
"step": 240
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.0962556550197324,
|
| 182 |
+
"grad_norm": 0.08211181312799454,
|
| 183 |
+
"learning_rate": 9.886726327312338e-06,
|
| 184 |
+
"loss": 0.7912,
|
| 185 |
+
"step": 250
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.1001058812205217,
|
| 189 |
+
"grad_norm": 0.0735074058175087,
|
| 190 |
+
"learning_rate": 9.87314850097724e-06,
|
| 191 |
+
"loss": 0.7995,
|
| 192 |
+
"step": 260
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.103956107421311,
|
| 196 |
+
"grad_norm": 0.07501552253961563,
|
| 197 |
+
"learning_rate": 9.858812712652452e-06,
|
| 198 |
+
"loss": 0.7925,
|
| 199 |
+
"step": 270
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.10780633362210029,
|
| 203 |
+
"grad_norm": 0.07213450968265533,
|
| 204 |
+
"learning_rate": 9.843721192104341e-06,
|
| 205 |
+
"loss": 0.7821,
|
| 206 |
+
"step": 280
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.11165655982288959,
|
| 210 |
+
"grad_norm": 0.07265755534172058,
|
| 211 |
+
"learning_rate": 9.827876286644698e-06,
|
| 212 |
+
"loss": 0.7993,
|
| 213 |
+
"step": 290
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.11550678602367889,
|
| 217 |
+
"grad_norm": 0.06689946353435516,
|
| 218 |
+
"learning_rate": 9.811280460765643e-06,
|
| 219 |
+
"loss": 0.772,
|
| 220 |
+
"step": 300
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.11935701222446819,
|
| 224 |
+
"grad_norm": 0.07571283727884293,
|
| 225 |
+
"learning_rate": 9.793936295756292e-06,
|
| 226 |
+
"loss": 0.782,
|
| 227 |
+
"step": 310
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.12320723842525748,
|
| 231 |
+
"grad_norm": 0.07211190462112427,
|
| 232 |
+
"learning_rate": 9.775846489301279e-06,
|
| 233 |
+
"loss": 0.7793,
|
| 234 |
+
"step": 320
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.12705746462604678,
|
| 238 |
+
"grad_norm": 0.09759286791086197,
|
| 239 |
+
"learning_rate": 9.757013855061157e-06,
|
| 240 |
+
"loss": 0.7832,
|
| 241 |
+
"step": 330
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.13090769082683607,
|
| 245 |
+
"grad_norm": 0.07327476143836975,
|
| 246 |
+
"learning_rate": 9.737441322234758e-06,
|
| 247 |
+
"loss": 0.787,
|
| 248 |
+
"step": 340
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.13475791702762538,
|
| 252 |
+
"grad_norm": 0.07534275203943253,
|
| 253 |
+
"learning_rate": 9.717131935103605e-06,
|
| 254 |
+
"loss": 0.7888,
|
| 255 |
+
"step": 350
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.13860814322841467,
|
| 259 |
+
"grad_norm": 0.07545823603868484,
|
| 260 |
+
"learning_rate": 9.696088852558398e-06,
|
| 261 |
+
"loss": 0.7774,
|
| 262 |
+
"step": 360
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.14245836942920398,
|
| 266 |
+
"grad_norm": 0.0741923525929451,
|
| 267 |
+
"learning_rate": 9.674315347607686e-06,
|
| 268 |
+
"loss": 0.813,
|
| 269 |
+
"step": 370
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.14630859562999327,
|
| 273 |
+
"grad_norm": 0.06941606104373932,
|
| 274 |
+
"learning_rate": 9.651814806868796e-06,
|
| 275 |
+
"loss": 0.7635,
|
| 276 |
+
"step": 380
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.15015882183078255,
|
| 280 |
+
"grad_norm": 0.07769839465618134,
|
| 281 |
+
"learning_rate": 9.62859073004107e-06,
|
| 282 |
+
"loss": 0.7744,
|
| 283 |
+
"step": 390
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.15400904803157187,
|
| 287 |
+
"grad_norm": 0.07188887894153595,
|
| 288 |
+
"learning_rate": 9.604646729361547e-06,
|
| 289 |
+
"loss": 0.7691,
|
| 290 |
+
"step": 400
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.15785927423236115,
|
| 294 |
+
"grad_norm": 0.07589484006166458,
|
| 295 |
+
"learning_rate": 9.579986529043099e-06,
|
| 296 |
+
"loss": 0.7618,
|
| 297 |
+
"step": 410
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.16170950043315044,
|
| 301 |
+
"grad_norm": 0.06861350685358047,
|
| 302 |
+
"learning_rate": 9.554613964695189e-06,
|
| 303 |
+
"loss": 0.7705,
|
| 304 |
+
"step": 420
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.16555972663393975,
|
| 308 |
+
"grad_norm": 0.07460866123437881,
|
| 309 |
+
"learning_rate": 9.528532982727281e-06,
|
| 310 |
+
"loss": 0.7693,
|
| 311 |
+
"step": 430
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.16940995283472904,
|
| 315 |
+
"grad_norm": 0.07515470683574677,
|
| 316 |
+
"learning_rate": 9.501747639735018e-06,
|
| 317 |
+
"loss": 0.7739,
|
| 318 |
+
"step": 440
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.17326017903551832,
|
| 322 |
+
"grad_norm": 0.0740383192896843,
|
| 323 |
+
"learning_rate": 9.474262101869272e-06,
|
| 324 |
+
"loss": 0.7525,
|
| 325 |
+
"step": 450
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.17711040523630764,
|
| 329 |
+
"grad_norm": 0.06898532062768936,
|
| 330 |
+
"learning_rate": 9.446080644188141e-06,
|
| 331 |
+
"loss": 0.7694,
|
| 332 |
+
"step": 460
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.18096063143709692,
|
| 336 |
+
"grad_norm": 0.07487062364816666,
|
| 337 |
+
"learning_rate": 9.417207649992017e-06,
|
| 338 |
+
"loss": 0.78,
|
| 339 |
+
"step": 470
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.18481085763788624,
|
| 343 |
+
"grad_norm": 0.0696675106883049,
|
| 344 |
+
"learning_rate": 9.387647610141816e-06,
|
| 345 |
+
"loss": 0.7589,
|
| 346 |
+
"step": 480
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.18866108383867553,
|
| 350 |
+
"grad_norm": 0.07098115235567093,
|
| 351 |
+
"learning_rate": 9.35740512236047e-06,
|
| 352 |
+
"loss": 0.7659,
|
| 353 |
+
"step": 490
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.1925113100394648,
|
| 357 |
+
"grad_norm": 0.06924096494913101,
|
| 358 |
+
"learning_rate": 9.326484890517809e-06,
|
| 359 |
+
"loss": 0.7626,
|
| 360 |
+
"step": 500
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.19636153624025413,
|
| 364 |
+
"grad_norm": 0.06881636381149292,
|
| 365 |
+
"learning_rate": 9.294891723898926e-06,
|
| 366 |
+
"loss": 0.7411,
|
| 367 |
+
"step": 510
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.2002117624410434,
|
| 371 |
+
"grad_norm": 0.06723500043153763,
|
| 372 |
+
"learning_rate": 9.262630536456153e-06,
|
| 373 |
+
"loss": 0.7848,
|
| 374 |
+
"step": 520
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.2040619886418327,
|
| 378 |
+
"grad_norm": 0.068511001765728,
|
| 379 |
+
"learning_rate": 9.229706346044749e-06,
|
| 380 |
+
"loss": 0.7418,
|
| 381 |
+
"step": 530
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.207912214842622,
|
| 385 |
+
"grad_norm": 0.07416897267103195,
|
| 386 |
+
"learning_rate": 9.196124273642422e-06,
|
| 387 |
+
"loss": 0.7677,
|
| 388 |
+
"step": 540
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.2117624410434113,
|
| 392 |
+
"grad_norm": 0.0669788047671318,
|
| 393 |
+
"learning_rate": 9.161889542552842e-06,
|
| 394 |
+
"loss": 0.7792,
|
| 395 |
+
"step": 550
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.21561266724420058,
|
| 399 |
+
"grad_norm": 0.07825101912021637,
|
| 400 |
+
"learning_rate": 9.127007477593193e-06,
|
| 401 |
+
"loss": 0.7745,
|
| 402 |
+
"step": 560
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.2194628934449899,
|
| 406 |
+
"grad_norm": 0.07543376833200455,
|
| 407 |
+
"learning_rate": 9.091483504265974e-06,
|
| 408 |
+
"loss": 0.7811,
|
| 409 |
+
"step": 570
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.22331311964577918,
|
| 413 |
+
"grad_norm": 0.06942735612392426,
|
| 414 |
+
"learning_rate": 9.055323147915116e-06,
|
| 415 |
+
"loss": 0.7581,
|
| 416 |
+
"step": 580
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.2271633458465685,
|
| 420 |
+
"grad_norm": 0.07834360748529434,
|
| 421 |
+
"learning_rate": 9.018532032866585e-06,
|
| 422 |
+
"loss": 0.7787,
|
| 423 |
+
"step": 590
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.23101357204735778,
|
| 427 |
+
"grad_norm": 0.07512736320495605,
|
| 428 |
+
"learning_rate": 8.981115881553579e-06,
|
| 429 |
+
"loss": 0.772,
|
| 430 |
+
"step": 600
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.23486379824814707,
|
| 434 |
+
"grad_norm": 0.07322967797517776,
|
| 435 |
+
"learning_rate": 8.943080513626476e-06,
|
| 436 |
+
"loss": 0.7913,
|
| 437 |
+
"step": 610
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.23871402444893638,
|
| 441 |
+
"grad_norm": 0.07357323914766312,
|
| 442 |
+
"learning_rate": 8.904431845047641e-06,
|
| 443 |
+
"loss": 0.7837,
|
| 444 |
+
"step": 620
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.24256425064972567,
|
| 448 |
+
"grad_norm": 0.07543937116861343,
|
| 449 |
+
"learning_rate": 8.86517588717128e-06,
|
| 450 |
+
"loss": 0.778,
|
| 451 |
+
"step": 630
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.24641447685051496,
|
| 455 |
+
"grad_norm": 0.06823491305112839,
|
| 456 |
+
"learning_rate": 8.82531874580844e-06,
|
| 457 |
+
"loss": 0.7798,
|
| 458 |
+
"step": 640
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.25026470305130427,
|
| 462 |
+
"grad_norm": 0.06259387731552124,
|
| 463 |
+
"learning_rate": 8.784866620277314e-06,
|
| 464 |
+
"loss": 0.7434,
|
| 465 |
+
"step": 650
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.25411492925209356,
|
| 469 |
+
"grad_norm": 0.07385433465242386,
|
| 470 |
+
"learning_rate": 8.743825802439018e-06,
|
| 471 |
+
"loss": 0.7637,
|
| 472 |
+
"step": 660
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 0.25796515545288284,
|
| 476 |
+
"grad_norm": 0.06853603571653366,
|
| 477 |
+
"learning_rate": 8.702202675718956e-06,
|
| 478 |
+
"loss": 0.7751,
|
| 479 |
+
"step": 670
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 0.26181538165367213,
|
| 483 |
+
"grad_norm": 0.0685543492436409,
|
| 484 |
+
"learning_rate": 8.660003714113959e-06,
|
| 485 |
+
"loss": 0.7409,
|
| 486 |
+
"step": 680
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 0.26566560785446147,
|
| 490 |
+
"grad_norm": 0.0667787492275238,
|
| 491 |
+
"learning_rate": 8.617235481185323e-06,
|
| 492 |
+
"loss": 0.7762,
|
| 493 |
+
"step": 690
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 0.26951583405525076,
|
| 497 |
+
"grad_norm": 0.07184694707393646,
|
| 498 |
+
"learning_rate": 8.573904629037931e-06,
|
| 499 |
+
"loss": 0.7697,
|
| 500 |
+
"step": 700
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.27336606025604004,
|
| 504 |
+
"grad_norm": 0.06656844168901443,
|
| 505 |
+
"learning_rate": 8.530017897285585e-06,
|
| 506 |
+
"loss": 0.7576,
|
| 507 |
+
"step": 710
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.27721628645682933,
|
| 511 |
+
"grad_norm": 0.06692864000797272,
|
| 512 |
+
"learning_rate": 8.485582112002746e-06,
|
| 513 |
+
"loss": 0.7624,
|
| 514 |
+
"step": 720
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.2810665126576186,
|
| 518 |
+
"grad_norm": 0.07258488982915878,
|
| 519 |
+
"learning_rate": 8.440604184662811e-06,
|
| 520 |
+
"loss": 0.7694,
|
| 521 |
+
"step": 730
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.28491673885840796,
|
| 525 |
+
"grad_norm": 0.07097339630126953,
|
| 526 |
+
"learning_rate": 8.395091111063118e-06,
|
| 527 |
+
"loss": 0.7456,
|
| 528 |
+
"step": 740
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 0.28876696505919724,
|
| 532 |
+
"grad_norm": 0.07409051060676575,
|
| 533 |
+
"learning_rate": 8.349049970236822e-06,
|
| 534 |
+
"loss": 0.7564,
|
| 535 |
+
"step": 750
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 0.29261719125998653,
|
| 539 |
+
"grad_norm": 0.08230583369731903,
|
| 540 |
+
"learning_rate": 8.302487923351842e-06,
|
| 541 |
+
"loss": 0.7471,
|
| 542 |
+
"step": 760
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.2964674174607758,
|
| 546 |
+
"grad_norm": 0.07281503081321716,
|
| 547 |
+
"learning_rate": 8.255412212597021e-06,
|
| 548 |
+
"loss": 0.7611,
|
| 549 |
+
"step": 770
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.3003176436615651,
|
| 553 |
+
"grad_norm": 0.07959206402301788,
|
| 554 |
+
"learning_rate": 8.207830160055688e-06,
|
| 555 |
+
"loss": 0.7561,
|
| 556 |
+
"step": 780
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.3041678698623544,
|
| 560 |
+
"grad_norm": 0.0733444094657898,
|
| 561 |
+
"learning_rate": 8.159749166566786e-06,
|
| 562 |
+
"loss": 0.7484,
|
| 563 |
+
"step": 790
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 0.30801809606314373,
|
| 567 |
+
"grad_norm": 0.06978779286146164,
|
| 568 |
+
"learning_rate": 8.11117671057377e-06,
|
| 569 |
+
"loss": 0.7652,
|
| 570 |
+
"step": 800
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.311868322263933,
|
| 574 |
+
"grad_norm": 0.0733194574713707,
|
| 575 |
+
"learning_rate": 8.062120346961404e-06,
|
| 576 |
+
"loss": 0.7503,
|
| 577 |
+
"step": 810
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 0.3157185484647223,
|
| 581 |
+
"grad_norm": 0.072224460542202,
|
| 582 |
+
"learning_rate": 8.012587705880705e-06,
|
| 583 |
+
"loss": 0.7606,
|
| 584 |
+
"step": 820
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 0.3195687746655116,
|
| 588 |
+
"grad_norm": 0.07441503554582596,
|
| 589 |
+
"learning_rate": 7.962586491562146e-06,
|
| 590 |
+
"loss": 0.7444,
|
| 591 |
+
"step": 830
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.3234190008663009,
|
| 595 |
+
"grad_norm": 0.07344556599855423,
|
| 596 |
+
"learning_rate": 7.912124481117357e-06,
|
| 597 |
+
"loss": 0.7376,
|
| 598 |
+
"step": 840
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 0.3272692270670902,
|
| 602 |
+
"grad_norm": 0.07554022967815399,
|
| 603 |
+
"learning_rate": 7.861209523329494e-06,
|
| 604 |
+
"loss": 0.759,
|
| 605 |
+
"step": 850
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 0.3311194532678795,
|
| 609 |
+
"grad_norm": 0.07729160040616989,
|
| 610 |
+
"learning_rate": 7.809849537432432e-06,
|
| 611 |
+
"loss": 0.7401,
|
| 612 |
+
"step": 860
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 0.3349696794686688,
|
| 616 |
+
"grad_norm": 0.06814920157194138,
|
| 617 |
+
"learning_rate": 7.758052511879035e-06,
|
| 618 |
+
"loss": 0.7428,
|
| 619 |
+
"step": 870
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 0.3388199056694581,
|
| 623 |
+
"grad_norm": 0.06341473013162613,
|
| 624 |
+
"learning_rate": 7.705826503098642e-06,
|
| 625 |
+
"loss": 0.748,
|
| 626 |
+
"step": 880
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 0.34267013187024736,
|
| 630 |
+
"grad_norm": 0.06933379918336868,
|
| 631 |
+
"learning_rate": 7.653179634243979e-06,
|
| 632 |
+
"loss": 0.7373,
|
| 633 |
+
"step": 890
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 0.34652035807103665,
|
| 637 |
+
"grad_norm": 0.06370389461517334,
|
| 638 |
+
"learning_rate": 7.600120093927696e-06,
|
| 639 |
+
"loss": 0.7538,
|
| 640 |
+
"step": 900
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 0.350370584271826,
|
| 644 |
+
"grad_norm": 0.08098312467336655,
|
| 645 |
+
"learning_rate": 7.546656134948729e-06,
|
| 646 |
+
"loss": 0.7369,
|
| 647 |
+
"step": 910
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 0.3542208104726153,
|
| 651 |
+
"grad_norm": 0.07235325872898102,
|
| 652 |
+
"learning_rate": 7.492796073008661e-06,
|
| 653 |
+
"loss": 0.7364,
|
| 654 |
+
"step": 920
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 0.35807103667340456,
|
| 658 |
+
"grad_norm": 0.07728346437215805,
|
| 659 |
+
"learning_rate": 7.438548285418326e-06,
|
| 660 |
+
"loss": 0.7315,
|
| 661 |
+
"step": 930
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 0.36192126287419385,
|
| 665 |
+
"grad_norm": 0.0741061270236969,
|
| 666 |
+
"learning_rate": 7.3839212097948e-06,
|
| 667 |
+
"loss": 0.7603,
|
| 668 |
+
"step": 940
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 0.36577148907498314,
|
| 672 |
+
"grad_norm": 0.0634770393371582,
|
| 673 |
+
"learning_rate": 7.328923342749039e-06,
|
| 674 |
+
"loss": 0.7675,
|
| 675 |
+
"step": 950
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 0.3696217152757725,
|
| 679 |
+
"grad_norm": 0.07253805547952652,
|
| 680 |
+
"learning_rate": 7.273563238564319e-06,
|
| 681 |
+
"loss": 0.7464,
|
| 682 |
+
"step": 960
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 0.37347194147656176,
|
| 686 |
+
"grad_norm": 0.06686242669820786,
|
| 687 |
+
"learning_rate": 7.217849507865724e-06,
|
| 688 |
+
"loss": 0.7359,
|
| 689 |
+
"step": 970
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 0.37732216767735105,
|
| 693 |
+
"grad_norm": 0.07822775840759277,
|
| 694 |
+
"learning_rate": 7.161790816280858e-06,
|
| 695 |
+
"loss": 0.7428,
|
| 696 |
+
"step": 980
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 0.38117239387814034,
|
| 700 |
+
"grad_norm": 0.07445020973682404,
|
| 701 |
+
"learning_rate": 7.1053958830920125e-06,
|
| 702 |
+
"loss": 0.7339,
|
| 703 |
+
"step": 990
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 0.3850226200789296,
|
| 707 |
+
"grad_norm": 0.07064179331064224,
|
| 708 |
+
"learning_rate": 7.0486734798799715e-06,
|
| 709 |
+
"loss": 0.7548,
|
| 710 |
+
"step": 1000
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 0.3888728462797189,
|
| 714 |
+
"grad_norm": 0.07442362606525421,
|
| 715 |
+
"learning_rate": 6.991632429159708e-06,
|
| 716 |
+
"loss": 0.7618,
|
| 717 |
+
"step": 1010
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 0.39272307248050825,
|
| 721 |
+
"grad_norm": 0.06724119186401367,
|
| 722 |
+
"learning_rate": 6.934281603008132e-06,
|
| 723 |
+
"loss": 0.7549,
|
| 724 |
+
"step": 1020
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 0.39657329868129754,
|
| 728 |
+
"grad_norm": 0.06703875958919525,
|
| 729 |
+
"learning_rate": 6.876629921684143e-06,
|
| 730 |
+
"loss": 0.7597,
|
| 731 |
+
"step": 1030
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 0.4004235248820868,
|
| 735 |
+
"grad_norm": 0.06956903636455536,
|
| 736 |
+
"learning_rate": 6.818686352241199e-06,
|
| 737 |
+
"loss": 0.7594,
|
| 738 |
+
"step": 1040
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 0.4042737510828761,
|
| 742 |
+
"grad_norm": 0.07332294434309006,
|
| 743 |
+
"learning_rate": 6.760459907132573e-06,
|
| 744 |
+
"loss": 0.7528,
|
| 745 |
+
"step": 1050
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 0.4081239772836654,
|
| 749 |
+
"grad_norm": 0.07626087218523026,
|
| 750 |
+
"learning_rate": 6.701959642809589e-06,
|
| 751 |
+
"loss": 0.7439,
|
| 752 |
+
"step": 1060
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 0.41197420348445474,
|
| 756 |
+
"grad_norm": 0.07587289810180664,
|
| 757 |
+
"learning_rate": 6.643194658312987e-06,
|
| 758 |
+
"loss": 0.731,
|
| 759 |
+
"step": 1070
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 0.415824429685244,
|
| 763 |
+
"grad_norm": 0.06777501106262207,
|
| 764 |
+
"learning_rate": 6.584174093857676e-06,
|
| 765 |
+
"loss": 0.7687,
|
| 766 |
+
"step": 1080
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 0.4196746558860333,
|
| 770 |
+
"grad_norm": 0.0798393189907074,
|
| 771 |
+
"learning_rate": 6.5249071294110735e-06,
|
| 772 |
+
"loss": 0.7387,
|
| 773 |
+
"step": 1090
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 0.4235248820868226,
|
| 777 |
+
"grad_norm": 0.07735718041658401,
|
| 778 |
+
"learning_rate": 6.465402983265274e-06,
|
| 779 |
+
"loss": 0.762,
|
| 780 |
+
"step": 1100
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 0.4273751082876119,
|
| 784 |
+
"grad_norm": 0.0681850016117096,
|
| 785 |
+
"learning_rate": 6.405670910603243e-06,
|
| 786 |
+
"loss": 0.7561,
|
| 787 |
+
"step": 1110
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 0.43122533448840117,
|
| 791 |
+
"grad_norm": 0.07813802361488342,
|
| 792 |
+
"learning_rate": 6.345720202059291e-06,
|
| 793 |
+
"loss": 0.7477,
|
| 794 |
+
"step": 1120
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 0.4350755606891905,
|
| 798 |
+
"grad_norm": 0.07095205038785934,
|
| 799 |
+
"learning_rate": 6.285560182274008e-06,
|
| 800 |
+
"loss": 0.7495,
|
| 801 |
+
"step": 1130
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 0.4389257868899798,
|
| 805 |
+
"grad_norm": 0.06447798758745193,
|
| 806 |
+
"learning_rate": 6.225200208443936e-06,
|
| 807 |
+
"loss": 0.7423,
|
| 808 |
+
"step": 1140
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 0.4427760130907691,
|
| 812 |
+
"grad_norm": 0.06721104681491852,
|
| 813 |
+
"learning_rate": 6.16464966886616e-06,
|
| 814 |
+
"loss": 0.7401,
|
| 815 |
+
"step": 1150
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 0.44662623929155837,
|
| 819 |
+
"grad_norm": 0.0804838016629219,
|
| 820 |
+
"learning_rate": 6.103917981478065e-06,
|
| 821 |
+
"loss": 0.7666,
|
| 822 |
+
"step": 1160
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 0.45047646549234766,
|
| 826 |
+
"grad_norm": 0.06928126513957977,
|
| 827 |
+
"learning_rate": 6.043014592392489e-06,
|
| 828 |
+
"loss": 0.7703,
|
| 829 |
+
"step": 1170
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 0.454326691693137,
|
| 833 |
+
"grad_norm": 0.06598833203315735,
|
| 834 |
+
"learning_rate": 5.981948974428485e-06,
|
| 835 |
+
"loss": 0.7425,
|
| 836 |
+
"step": 1180
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 0.4581769178939263,
|
| 840 |
+
"grad_norm": 0.07492036372423172,
|
| 841 |
+
"learning_rate": 5.920730625637934e-06,
|
| 842 |
+
"loss": 0.7212,
|
| 843 |
+
"step": 1190
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 0.46202714409471557,
|
| 847 |
+
"grad_norm": 0.06907598674297333,
|
| 848 |
+
"learning_rate": 5.8593690678282355e-06,
|
| 849 |
+
"loss": 0.7361,
|
| 850 |
+
"step": 1200
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 0.46587737029550486,
|
| 854 |
+
"grad_norm": 0.07385518401861191,
|
| 855 |
+
"learning_rate": 5.797873845081301e-06,
|
| 856 |
+
"loss": 0.7373,
|
| 857 |
+
"step": 1210
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 0.46972759649629414,
|
| 861 |
+
"grad_norm": 0.06967263668775558,
|
| 862 |
+
"learning_rate": 5.736254522269075e-06,
|
| 863 |
+
"loss": 0.761,
|
| 864 |
+
"step": 1220
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 0.47357782269708343,
|
| 868 |
+
"grad_norm": 0.07001042366027832,
|
| 869 |
+
"learning_rate": 5.6745206835658386e-06,
|
| 870 |
+
"loss": 0.7537,
|
| 871 |
+
"step": 1230
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 0.47742804889787277,
|
| 875 |
+
"grad_norm": 0.06711170077323914,
|
| 876 |
+
"learning_rate": 5.612681930957495e-06,
|
| 877 |
+
"loss": 0.7376,
|
| 878 |
+
"step": 1240
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 0.48127827509866206,
|
| 882 |
+
"grad_norm": 0.07146608829498291,
|
| 883 |
+
"learning_rate": 5.550747882748095e-06,
|
| 884 |
+
"loss": 0.7334,
|
| 885 |
+
"step": 1250
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 0.48512850129945134,
|
| 889 |
+
"grad_norm": 0.07281909883022308,
|
| 890 |
+
"learning_rate": 5.4887281720638195e-06,
|
| 891 |
+
"loss": 0.7404,
|
| 892 |
+
"step": 1260
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 0.48897872750024063,
|
| 896 |
+
"grad_norm": 0.08118748664855957,
|
| 897 |
+
"learning_rate": 5.42663244535466e-06,
|
| 898 |
+
"loss": 0.7225,
|
| 899 |
+
"step": 1270
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 0.4928289537010299,
|
| 903 |
+
"grad_norm": 0.06507953256368637,
|
| 904 |
+
"learning_rate": 5.3644703608940205e-06,
|
| 905 |
+
"loss": 0.7319,
|
| 906 |
+
"step": 1280
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 0.49667917990181926,
|
| 910 |
+
"grad_norm": 0.06873860210180283,
|
| 911 |
+
"learning_rate": 5.302251587276491e-06,
|
| 912 |
+
"loss": 0.7606,
|
| 913 |
+
"step": 1290
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 0.5005294061026085,
|
| 917 |
+
"grad_norm": 0.06670668721199036,
|
| 918 |
+
"learning_rate": 5.2399858019140005e-06,
|
| 919 |
+
"loss": 0.7439,
|
| 920 |
+
"step": 1300
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 0.5043796323033978,
|
| 924 |
+
"grad_norm": 0.06808660179376602,
|
| 925 |
+
"learning_rate": 5.177682689530615e-06,
|
| 926 |
+
"loss": 0.7571,
|
| 927 |
+
"step": 1310
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 0.5082298585041871,
|
| 931 |
+
"grad_norm": 0.07164818793535233,
|
| 932 |
+
"learning_rate": 5.11535194065619e-06,
|
| 933 |
+
"loss": 0.7373,
|
| 934 |
+
"step": 1320
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 0.5120800847049765,
|
| 938 |
+
"grad_norm": 0.07662923634052277,
|
| 939 |
+
"learning_rate": 5.053003250119113e-06,
|
| 940 |
+
"loss": 0.7387,
|
| 941 |
+
"step": 1330
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 0.5159303109057657,
|
| 945 |
+
"grad_norm": 0.06713004410266876,
|
| 946 |
+
"learning_rate": 4.9906463155383925e-06,
|
| 947 |
+
"loss": 0.7514,
|
| 948 |
+
"step": 1340
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 0.519780537106555,
|
| 952 |
+
"grad_norm": 0.07243505120277405,
|
| 953 |
+
"learning_rate": 4.9282908358153046e-06,
|
| 954 |
+
"loss": 0.7426,
|
| 955 |
+
"step": 1350
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 0.5236307633073443,
|
| 959 |
+
"grad_norm": 0.07103867828845978,
|
| 960 |
+
"learning_rate": 4.8659465096248345e-06,
|
| 961 |
+
"loss": 0.7444,
|
| 962 |
+
"step": 1360
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 0.5274809895081336,
|
| 966 |
+
"grad_norm": 0.07568763941526413,
|
| 967 |
+
"learning_rate": 4.803623033907169e-06,
|
| 968 |
+
"loss": 0.7484,
|
| 969 |
+
"step": 1370
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 0.5313312157089229,
|
| 973 |
+
"grad_norm": 0.06465796381235123,
|
| 974 |
+
"learning_rate": 4.741330102359441e-06,
|
| 975 |
+
"loss": 0.7628,
|
| 976 |
+
"step": 1380
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 0.5351814419097122,
|
| 980 |
+
"grad_norm": 0.07062087208032608,
|
| 981 |
+
"learning_rate": 4.679077403927996e-06,
|
| 982 |
+
"loss": 0.7284,
|
| 983 |
+
"step": 1390
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 0.5390316681105015,
|
| 987 |
+
"grad_norm": 0.07353247702121735,
|
| 988 |
+
"learning_rate": 4.616874621301373e-06,
|
| 989 |
+
"loss": 0.734,
|
| 990 |
+
"step": 1400
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 0.5428818943112907,
|
| 994 |
+
"grad_norm": 0.07063065469264984,
|
| 995 |
+
"learning_rate": 4.554731429404293e-06,
|
| 996 |
+
"loss": 0.7613,
|
| 997 |
+
"step": 1410
|
| 998 |
+
},
|
| 999 |
+
{
|
| 1000 |
+
"epoch": 0.5467321205120801,
|
| 1001 |
+
"grad_norm": 0.07993867248296738,
|
| 1002 |
+
"learning_rate": 4.492657493892822e-06,
|
| 1003 |
+
"loss": 0.737,
|
| 1004 |
+
"step": 1420
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 0.5505823467128694,
|
| 1008 |
+
"grad_norm": 0.07402441650629044,
|
| 1009 |
+
"learning_rate": 4.430662469650999e-06,
|
| 1010 |
+
"loss": 0.7445,
|
| 1011 |
+
"step": 1430
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 0.5544325729136587,
|
| 1015 |
+
"grad_norm": 0.07528981566429138,
|
| 1016 |
+
"learning_rate": 4.368755999289118e-06,
|
| 1017 |
+
"loss": 0.7589,
|
| 1018 |
+
"step": 1440
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 0.558282799114448,
|
| 1022 |
+
"grad_norm": 0.07637014985084534,
|
| 1023 |
+
"learning_rate": 4.306947711643949e-06,
|
| 1024 |
+
"loss": 0.7391,
|
| 1025 |
+
"step": 1450
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 0.5621330253152372,
|
| 1029 |
+
"grad_norm": 0.07221734523773193,
|
| 1030 |
+
"learning_rate": 4.245247220281068e-06,
|
| 1031 |
+
"loss": 0.7427,
|
| 1032 |
+
"step": 1460
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 0.5659832515160266,
|
| 1036 |
+
"grad_norm": 0.07177842408418655,
|
| 1037 |
+
"learning_rate": 4.183664121999587e-06,
|
| 1038 |
+
"loss": 0.736,
|
| 1039 |
+
"step": 1470
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"epoch": 0.5698334777168159,
|
| 1043 |
+
"grad_norm": 0.06895086169242859,
|
| 1044 |
+
"learning_rate": 4.122207995339474e-06,
|
| 1045 |
+
"loss": 0.7341,
|
| 1046 |
+
"step": 1480
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 0.5736837039176051,
|
| 1050 |
+
"grad_norm": 0.07454396039247513,
|
| 1051 |
+
"learning_rate": 4.060888399091734e-06,
|
| 1052 |
+
"loss": 0.7393,
|
| 1053 |
+
"step": 1490
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 0.5775339301183945,
|
| 1057 |
+
"grad_norm": 0.08206804096698761,
|
| 1058 |
+
"learning_rate": 3.999714870811639e-06,
|
| 1059 |
+
"loss": 0.7562,
|
| 1060 |
+
"step": 1500
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 0.5813841563191837,
|
| 1064 |
+
"grad_norm": 0.0654543787240982,
|
| 1065 |
+
"learning_rate": 3.938696925335275e-06,
|
| 1066 |
+
"loss": 0.7505,
|
| 1067 |
+
"step": 1510
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 0.5852343825199731,
|
| 1071 |
+
"grad_norm": 0.07797487825155258,
|
| 1072 |
+
"learning_rate": 3.87784405329962e-06,
|
| 1073 |
+
"loss": 0.7478,
|
| 1074 |
+
"step": 1520
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 0.5890846087207623,
|
| 1078 |
+
"grad_norm": 0.0727035254240036,
|
| 1079 |
+
"learning_rate": 3.817165719666382e-06,
|
| 1080 |
+
"loss": 0.7535,
|
| 1081 |
+
"step": 1530
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 0.5929348349215516,
|
| 1085 |
+
"grad_norm": 0.06716539710760117,
|
| 1086 |
+
"learning_rate": 3.756671362249841e-06,
|
| 1087 |
+
"loss": 0.7516,
|
| 1088 |
+
"step": 1540
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 0.596785061122341,
|
| 1092 |
+
"grad_norm": 0.07274585217237473,
|
| 1093 |
+
"learning_rate": 3.6963703902488907e-06,
|
| 1094 |
+
"loss": 0.7567,
|
| 1095 |
+
"step": 1550
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 0.6006352873231302,
|
| 1099 |
+
"grad_norm": 0.07420727610588074,
|
| 1100 |
+
"learning_rate": 3.6362721827835655e-06,
|
| 1101 |
+
"loss": 0.7574,
|
| 1102 |
+
"step": 1560
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 0.6044855135239195,
|
| 1106 |
+
"grad_norm": 0.07219205796718597,
|
| 1107 |
+
"learning_rate": 3.576386087436212e-06,
|
| 1108 |
+
"loss": 0.7449,
|
| 1109 |
+
"step": 1570
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 0.6083357397247088,
|
| 1113 |
+
"grad_norm": 0.07114338129758835,
|
| 1114 |
+
"learning_rate": 3.5167214187975913e-06,
|
| 1115 |
+
"loss": 0.7465,
|
| 1116 |
+
"step": 1580
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 0.6121859659254981,
|
| 1120 |
+
"grad_norm": 0.06271539628505707,
|
| 1121 |
+
"learning_rate": 3.457287457018086e-06,
|
| 1122 |
+
"loss": 0.7582,
|
| 1123 |
+
"step": 1590
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 0.6160361921262875,
|
| 1127 |
+
"grad_norm": 0.070709228515625,
|
| 1128 |
+
"learning_rate": 3.3980934463643003e-06,
|
| 1129 |
+
"loss": 0.7407,
|
| 1130 |
+
"step": 1600
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 0.6198864183270767,
|
| 1134 |
+
"grad_norm": 0.062089335173368454,
|
| 1135 |
+
"learning_rate": 3.3391485937812053e-06,
|
| 1136 |
+
"loss": 0.72,
|
| 1137 |
+
"step": 1610
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 0.623736644527866,
|
| 1141 |
+
"grad_norm": 0.07222044467926025,
|
| 1142 |
+
"learning_rate": 3.280462067460115e-06,
|
| 1143 |
+
"loss": 0.7142,
|
| 1144 |
+
"step": 1620
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 0.6275868707286553,
|
| 1148 |
+
"grad_norm": 0.07260554283857346,
|
| 1149 |
+
"learning_rate": 3.222042995412669e-06,
|
| 1150 |
+
"loss": 0.7528,
|
| 1151 |
+
"step": 1630
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 0.6314370969294446,
|
| 1155 |
+
"grad_norm": 0.06356589496135712,
|
| 1156 |
+
"learning_rate": 3.163900464051089e-06,
|
| 1157 |
+
"loss": 0.7383,
|
| 1158 |
+
"step": 1640
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 0.635287323130234,
|
| 1162 |
+
"grad_norm": 0.0713791698217392,
|
| 1163 |
+
"learning_rate": 3.1060435167748826e-06,
|
| 1164 |
+
"loss": 0.7483,
|
| 1165 |
+
"step": 1650
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 0.6391375493310232,
|
| 1169 |
+
"grad_norm": 0.0672735646367073,
|
| 1170 |
+
"learning_rate": 3.048481152564253e-06,
|
| 1171 |
+
"loss": 0.7273,
|
| 1172 |
+
"step": 1660
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 0.6429877755318125,
|
| 1176 |
+
"grad_norm": 0.06842087209224701,
|
| 1177 |
+
"learning_rate": 2.9912223245804017e-06,
|
| 1178 |
+
"loss": 0.7565,
|
| 1179 |
+
"step": 1670
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 0.6468380017326018,
|
| 1183 |
+
"grad_norm": 0.07105045765638351,
|
| 1184 |
+
"learning_rate": 2.934275938772981e-06,
|
| 1185 |
+
"loss": 0.7394,
|
| 1186 |
+
"step": 1680
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 0.6506882279333911,
|
| 1190 |
+
"grad_norm": 0.06719069927930832,
|
| 1191 |
+
"learning_rate": 2.8776508524948676e-06,
|
| 1192 |
+
"loss": 0.7338,
|
| 1193 |
+
"step": 1690
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 0.6545384541341804,
|
| 1197 |
+
"grad_norm": 0.07177069038152695,
|
| 1198 |
+
"learning_rate": 2.821355873124503e-06,
|
| 1199 |
+
"loss": 0.7322,
|
| 1200 |
+
"step": 1700
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 0.6583886803349697,
|
| 1204 |
+
"grad_norm": 0.07624438405036926,
|
| 1205 |
+
"learning_rate": 2.7653997566960144e-06,
|
| 1206 |
+
"loss": 0.751,
|
| 1207 |
+
"step": 1710
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"epoch": 0.662238906535759,
|
| 1211 |
+
"grad_norm": 0.07313289493322372,
|
| 1212 |
+
"learning_rate": 2.709791206537309e-06,
|
| 1213 |
+
"loss": 0.7393,
|
| 1214 |
+
"step": 1720
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 0.6660891327365482,
|
| 1218 |
+
"grad_norm": 0.06753606349229813,
|
| 1219 |
+
"learning_rate": 2.6545388719163747e-06,
|
| 1220 |
+
"loss": 0.7423,
|
| 1221 |
+
"step": 1730
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 0.6699393589373376,
|
| 1225 |
+
"grad_norm": 0.06922229379415512,
|
| 1226 |
+
"learning_rate": 2.599651346695979e-06,
|
| 1227 |
+
"loss": 0.7453,
|
| 1228 |
+
"step": 1740
|
| 1229 |
+
},
|
| 1230 |
+
{
|
| 1231 |
+
"epoch": 0.6737895851381268,
|
| 1232 |
+
"grad_norm": 0.06969853490591049,
|
| 1233 |
+
"learning_rate": 2.545137167997007e-06,
|
| 1234 |
+
"loss": 0.7434,
|
| 1235 |
+
"step": 1750
|
| 1236 |
+
},
|
| 1237 |
+
{
|
| 1238 |
+
"epoch": 0.6776398113389162,
|
| 1239 |
+
"grad_norm": 0.06989492475986481,
|
| 1240 |
+
"learning_rate": 2.4910048148705972e-06,
|
| 1241 |
+
"loss": 0.7308,
|
| 1242 |
+
"step": 1760
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 0.6814900375397055,
|
| 1246 |
+
"grad_norm": 0.07058797031641006,
|
| 1247 |
+
"learning_rate": 2.4372627069793327e-06,
|
| 1248 |
+
"loss": 0.7669,
|
| 1249 |
+
"step": 1770
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 0.6853402637404947,
|
| 1253 |
+
"grad_norm": 0.06551698595285416,
|
| 1254 |
+
"learning_rate": 2.3839192032876486e-06,
|
| 1255 |
+
"loss": 0.7536,
|
| 1256 |
+
"step": 1780
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 0.6891904899412841,
|
| 1260 |
+
"grad_norm": 0.06864619255065918,
|
| 1261 |
+
"learning_rate": 2.3309826007617047e-06,
|
| 1262 |
+
"loss": 0.7658,
|
| 1263 |
+
"step": 1790
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 0.6930407161420733,
|
| 1267 |
+
"grad_norm": 0.06568137556314468,
|
| 1268 |
+
"learning_rate": 2.278461133078881e-06,
|
| 1269 |
+
"loss": 0.728,
|
| 1270 |
+
"step": 1800
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 0.6968909423428626,
|
| 1274 |
+
"grad_norm": 0.06711228936910629,
|
| 1275 |
+
"learning_rate": 2.2263629693471258e-06,
|
| 1276 |
+
"loss": 0.7298,
|
| 1277 |
+
"step": 1810
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 0.700741168543652,
|
| 1281 |
+
"grad_norm": 0.07150524854660034,
|
| 1282 |
+
"learning_rate": 2.1746962128343414e-06,
|
| 1283 |
+
"loss": 0.7547,
|
| 1284 |
+
"step": 1820
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 0.7045913947444412,
|
| 1288 |
+
"grad_norm": 0.06610579043626785,
|
| 1289 |
+
"learning_rate": 2.1234688997080183e-06,
|
| 1290 |
+
"loss": 0.7478,
|
| 1291 |
+
"step": 1830
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 0.7084416209452306,
|
| 1295 |
+
"grad_norm": 0.07242002338171005,
|
| 1296 |
+
"learning_rate": 2.0726889977853053e-06,
|
| 1297 |
+
"loss": 0.7395,
|
| 1298 |
+
"step": 1840
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 0.7122918471460198,
|
| 1302 |
+
"grad_norm": 0.0772794708609581,
|
| 1303 |
+
"learning_rate": 2.022364405293703e-06,
|
| 1304 |
+
"loss": 0.7482,
|
| 1305 |
+
"step": 1850
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 0.7161420733468091,
|
| 1309 |
+
"grad_norm": 0.06792398542165756,
|
| 1310 |
+
"learning_rate": 1.9725029496425814e-06,
|
| 1311 |
+
"loss": 0.7523,
|
| 1312 |
+
"step": 1860
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 0.7199922995475985,
|
| 1316 |
+
"grad_norm": 0.07056572288274765,
|
| 1317 |
+
"learning_rate": 1.923112386205727e-06,
|
| 1318 |
+
"loss": 0.7454,
|
| 1319 |
+
"step": 1870
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 0.7238425257483877,
|
| 1323 |
+
"grad_norm": 0.07687123864889145,
|
| 1324 |
+
"learning_rate": 1.874200397115079e-06,
|
| 1325 |
+
"loss": 0.7512,
|
| 1326 |
+
"step": 1880
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 0.727692751949177,
|
| 1330 |
+
"grad_norm": 0.0694878101348877,
|
| 1331 |
+
"learning_rate": 1.825774590065857e-06,
|
| 1332 |
+
"loss": 0.7267,
|
| 1333 |
+
"step": 1890
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 0.7315429781499663,
|
| 1337 |
+
"grad_norm": 0.07745741307735443,
|
| 1338 |
+
"learning_rate": 1.7778424971332813e-06,
|
| 1339 |
+
"loss": 0.7498,
|
| 1340 |
+
"step": 1900
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 0.7353932043507556,
|
| 1344 |
+
"grad_norm": 0.06358810514211655,
|
| 1345 |
+
"learning_rate": 1.7304115736010407e-06,
|
| 1346 |
+
"loss": 0.7414,
|
| 1347 |
+
"step": 1910
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 0.739243430551545,
|
| 1351 |
+
"grad_norm": 0.06944147497415543,
|
| 1352 |
+
"learning_rate": 1.6834891968017108e-06,
|
| 1353 |
+
"loss": 0.7277,
|
| 1354 |
+
"step": 1920
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 0.7430936567523342,
|
| 1358 |
+
"grad_norm": 0.07573969662189484,
|
| 1359 |
+
"learning_rate": 1.6370826649692884e-06,
|
| 1360 |
+
"loss": 0.7501,
|
| 1361 |
+
"step": 1930
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 0.7469438829531235,
|
| 1365 |
+
"grad_norm": 0.06564056873321533,
|
| 1366 |
+
"learning_rate": 1.5911991961040463e-06,
|
| 1367 |
+
"loss": 0.7523,
|
| 1368 |
+
"step": 1940
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 0.7507941091539128,
|
| 1372 |
+
"grad_norm": 0.07056824117898941,
|
| 1373 |
+
"learning_rate": 1.545845926849851e-06,
|
| 1374 |
+
"loss": 0.748,
|
| 1375 |
+
"step": 1950
|
| 1376 |
+
},
|
| 1377 |
+
{
|
| 1378 |
+
"epoch": 0.7546443353547021,
|
| 1379 |
+
"grad_norm": 0.0733201876282692,
|
| 1380 |
+
"learning_rate": 1.5010299113841397e-06,
|
| 1381 |
+
"loss": 0.7679,
|
| 1382 |
+
"step": 1960
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 0.7584945615554913,
|
| 1386 |
+
"grad_norm": 0.06656578183174133,
|
| 1387 |
+
"learning_rate": 1.4567581203207238e-06,
|
| 1388 |
+
"loss": 0.7489,
|
| 1389 |
+
"step": 1970
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 0.7623447877562807,
|
| 1393 |
+
"grad_norm": 0.06954676657915115,
|
| 1394 |
+
"learning_rate": 1.413037439625593e-06,
|
| 1395 |
+
"loss": 0.7368,
|
| 1396 |
+
"step": 1980
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 0.76619501395707,
|
| 1400 |
+
"grad_norm": 0.07772701978683472,
|
| 1401 |
+
"learning_rate": 1.3698746695458847e-06,
|
| 1402 |
+
"loss": 0.757,
|
| 1403 |
+
"step": 1990
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 0.7700452401578592,
|
| 1407 |
+
"grad_norm": 0.0641447901725769,
|
| 1408 |
+
"learning_rate": 1.3272765235521745e-06,
|
| 1409 |
+
"loss": 0.7424,
|
| 1410 |
+
"step": 2000
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"epoch": 0.7738954663586486,
|
| 1414 |
+
"grad_norm": 0.07367745786905289,
|
| 1415 |
+
"learning_rate": 1.2852496272942877e-06,
|
| 1416 |
+
"loss": 0.7444,
|
| 1417 |
+
"step": 2010
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 0.7777456925594378,
|
| 1421 |
+
"grad_norm": 0.06400757282972336,
|
| 1422 |
+
"learning_rate": 1.2438005175707396e-06,
|
| 1423 |
+
"loss": 0.7383,
|
| 1424 |
+
"step": 2020
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 0.7815959187602272,
|
| 1428 |
+
"grad_norm": 0.06991060823202133,
|
| 1429 |
+
"learning_rate": 1.2029356413120297e-06,
|
| 1430 |
+
"loss": 0.7247,
|
| 1431 |
+
"step": 2030
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 0.7854461449610165,
|
| 1435 |
+
"grad_norm": 0.07018636912107468,
|
| 1436 |
+
"learning_rate": 1.1626613545778786e-06,
|
| 1437 |
+
"loss": 0.7431,
|
| 1438 |
+
"step": 2040
|
| 1439 |
+
},
|
| 1440 |
+
{
|
| 1441 |
+
"epoch": 0.7892963711618057,
|
| 1442 |
+
"grad_norm": 0.06760720163583755,
|
| 1443 |
+
"learning_rate": 1.1229839215686294e-06,
|
| 1444 |
+
"loss": 0.744,
|
| 1445 |
+
"step": 2050
|
| 1446 |
+
},
|
| 1447 |
+
{
|
| 1448 |
+
"epoch": 0.7931465973625951,
|
| 1449 |
+
"grad_norm": 0.06212307885289192,
|
| 1450 |
+
"learning_rate": 1.0839095136509188e-06,
|
| 1451 |
+
"loss": 0.7271,
|
| 1452 |
+
"step": 2060
|
| 1453 |
+
},
|
| 1454 |
+
{
|
| 1455 |
+
"epoch": 0.7969968235633843,
|
| 1456 |
+
"grad_norm": 0.06936890631914139,
|
| 1457 |
+
"learning_rate": 1.045444208397791e-06,
|
| 1458 |
+
"loss": 0.7455,
|
| 1459 |
+
"step": 2070
|
| 1460 |
+
},
|
| 1461 |
+
{
|
| 1462 |
+
"epoch": 0.8008470497641736,
|
| 1463 |
+
"grad_norm": 0.07344169169664383,
|
| 1464 |
+
"learning_rate": 1.007593988643402e-06,
|
| 1465 |
+
"loss": 0.7226,
|
| 1466 |
+
"step": 2080
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 0.804697275964963,
|
| 1470 |
+
"grad_norm": 0.06512684375047684,
|
| 1471 |
+
"learning_rate": 9.703647415524613e-07,
|
| 1472 |
+
"loss": 0.7465,
|
| 1473 |
+
"step": 2090
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 0.8085475021657522,
|
| 1477 |
+
"grad_norm": 0.06548954546451569,
|
| 1478 |
+
"learning_rate": 9.337622577045485e-07,
|
| 1479 |
+
"loss": 0.7447,
|
| 1480 |
+
"step": 2100
|
| 1481 |
+
},
|
| 1482 |
+
{
|
| 1483 |
+
"epoch": 0.8123977283665416,
|
| 1484 |
+
"grad_norm": 0.06839491426944733,
|
| 1485 |
+
"learning_rate": 8.977922301934588e-07,
|
| 1486 |
+
"loss": 0.7431,
|
| 1487 |
+
"step": 2110
|
| 1488 |
+
},
|
| 1489 |
+
{
|
| 1490 |
+
"epoch": 0.8162479545673308,
|
| 1491 |
+
"grad_norm": 0.06651673465967178,
|
| 1492 |
+
"learning_rate": 8.624602537417009e-07,
|
| 1493 |
+
"loss": 0.7427,
|
| 1494 |
+
"step": 2120
|
| 1495 |
+
},
|
| 1496 |
+
{
|
| 1497 |
+
"epoch": 0.8200981807681201,
|
| 1498 |
+
"grad_norm": 0.06899440288543701,
|
| 1499 |
+
"learning_rate": 8.277718238303123e-07,
|
| 1500 |
+
"loss": 0.7402,
|
| 1501 |
+
"step": 2130
|
| 1502 |
+
},
|
| 1503 |
+
{
|
| 1504 |
+
"epoch": 0.8239484069689095,
|
| 1505 |
+
"grad_norm": 0.06695971637964249,
|
| 1506 |
+
"learning_rate": 7.937323358440935e-07,
|
| 1507 |
+
"loss": 0.7444,
|
| 1508 |
+
"step": 2140
|
| 1509 |
+
},
|
| 1510 |
+
{
|
| 1511 |
+
"epoch": 0.8277986331696987,
|
| 1512 |
+
"grad_norm": 0.07596660405397415,
|
| 1513 |
+
"learning_rate": 7.603470842324223e-07,
|
| 1514 |
+
"loss": 0.7369,
|
| 1515 |
+
"step": 2150
|
| 1516 |
+
},
|
| 1517 |
+
{
|
| 1518 |
+
"epoch": 0.831648859370488,
|
| 1519 |
+
"grad_norm": 0.06523437798023224,
|
| 1520 |
+
"learning_rate": 7.276212616857575e-07,
|
| 1521 |
+
"loss": 0.7549,
|
| 1522 |
+
"step": 2160
|
| 1523 |
+
},
|
| 1524 |
+
{
|
| 1525 |
+
"epoch": 0.8354990855712773,
|
| 1526 |
+
"grad_norm": 0.06935063749551773,
|
| 1527 |
+
"learning_rate": 6.955599583279837e-07,
|
| 1528 |
+
"loss": 0.7495,
|
| 1529 |
+
"step": 2170
|
| 1530 |
+
},
|
| 1531 |
+
{
|
| 1532 |
+
"epoch": 0.8393493117720666,
|
| 1533 |
+
"grad_norm": 0.06569609045982361,
|
| 1534 |
+
"learning_rate": 6.641681609246981e-07,
|
| 1535 |
+
"loss": 0.7393,
|
| 1536 |
+
"step": 2180
|
| 1537 |
+
},
|
| 1538 |
+
{
|
| 1539 |
+
"epoch": 0.8431995379728559,
|
| 1540 |
+
"grad_norm": 0.06958740204572678,
|
| 1541 |
+
"learning_rate": 6.334507521075711e-07,
|
| 1542 |
+
"loss": 0.7414,
|
| 1543 |
+
"step": 2190
|
| 1544 |
+
},
|
| 1545 |
+
{
|
| 1546 |
+
"epoch": 0.8470497641736452,
|
| 1547 |
+
"grad_norm": 0.0760483592748642,
|
| 1548 |
+
"learning_rate": 6.034125096149179e-07,
|
| 1549 |
+
"loss": 0.7376,
|
| 1550 |
+
"step": 2200
|
| 1551 |
+
},
|
| 1552 |
+
{
|
| 1553 |
+
"epoch": 0.8508999903744345,
|
| 1554 |
+
"grad_norm": 0.07844917476177216,
|
| 1555 |
+
"learning_rate": 5.740581055485722e-07,
|
| 1556 |
+
"loss": 0.7181,
|
| 1557 |
+
"step": 2210
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"epoch": 0.8547502165752238,
|
| 1561 |
+
"grad_norm": 0.06118838116526604,
|
| 1562 |
+
"learning_rate": 5.453921056471961e-07,
|
| 1563 |
+
"loss": 0.7549,
|
| 1564 |
+
"step": 2220
|
| 1565 |
+
},
|
| 1566 |
+
{
|
| 1567 |
+
"epoch": 0.8586004427760131,
|
| 1568 |
+
"grad_norm": 0.07115840166807175,
|
| 1569 |
+
"learning_rate": 5.174189685761288e-07,
|
| 1570 |
+
"loss": 0.7318,
|
| 1571 |
+
"step": 2230
|
| 1572 |
+
},
|
| 1573 |
+
{
|
| 1574 |
+
"epoch": 0.8624506689768023,
|
| 1575 |
+
"grad_norm": 0.06986364722251892,
|
| 1576 |
+
"learning_rate": 4.901430452338979e-07,
|
| 1577 |
+
"loss": 0.7569,
|
| 1578 |
+
"step": 2240
|
| 1579 |
+
},
|
| 1580 |
+
{
|
| 1581 |
+
"epoch": 0.8663008951775917,
|
| 1582 |
+
"grad_norm": 0.0683031976222992,
|
| 1583 |
+
"learning_rate": 4.6356857807548286e-07,
|
| 1584 |
+
"loss": 0.7373,
|
| 1585 |
+
"step": 2250
|
| 1586 |
+
},
|
| 1587 |
+
{
|
| 1588 |
+
"epoch": 0.870151121378381,
|
| 1589 |
+
"grad_norm": 0.0682525783777237,
|
| 1590 |
+
"learning_rate": 4.376997004524541e-07,
|
| 1591 |
+
"loss": 0.7303,
|
| 1592 |
+
"step": 2260
|
| 1593 |
+
},
|
| 1594 |
+
{
|
| 1595 |
+
"epoch": 0.8740013475791703,
|
| 1596 |
+
"grad_norm": 0.0686335638165474,
|
| 1597 |
+
"learning_rate": 4.12540435970073e-07,
|
| 1598 |
+
"loss": 0.7388,
|
| 1599 |
+
"step": 2270
|
| 1600 |
+
},
|
| 1601 |
+
{
|
| 1602 |
+
"epoch": 0.8778515737799596,
|
| 1603 |
+
"grad_norm": 0.06467821449041367,
|
| 1604 |
+
"learning_rate": 3.880946978614703e-07,
|
| 1605 |
+
"loss": 0.7497,
|
| 1606 |
+
"step": 2280
|
| 1607 |
+
},
|
| 1608 |
+
{
|
| 1609 |
+
"epoch": 0.8817017999807488,
|
| 1610 |
+
"grad_norm": 0.06672674417495728,
|
| 1611 |
+
"learning_rate": 3.643662883789878e-07,
|
| 1612 |
+
"loss": 0.7557,
|
| 1613 |
+
"step": 2290
|
| 1614 |
+
},
|
| 1615 |
+
{
|
| 1616 |
+
"epoch": 0.8855520261815382,
|
| 1617 |
+
"grad_norm": 0.06286139041185379,
|
| 1618 |
+
"learning_rate": 3.41358898202781e-07,
|
| 1619 |
+
"loss": 0.7328,
|
| 1620 |
+
"step": 2300
|
| 1621 |
+
},
|
| 1622 |
+
{
|
| 1623 |
+
"epoch": 0.8894022523823275,
|
| 1624 |
+
"grad_norm": 0.06739514321088791,
|
| 1625 |
+
"learning_rate": 3.190761058667741e-07,
|
| 1626 |
+
"loss": 0.7365,
|
| 1627 |
+
"step": 2310
|
| 1628 |
+
},
|
| 1629 |
+
{
|
| 1630 |
+
"epoch": 0.8932524785831167,
|
| 1631 |
+
"grad_norm": 0.06293594837188721,
|
| 1632 |
+
"learning_rate": 2.9752137720206463e-07,
|
| 1633 |
+
"loss": 0.7432,
|
| 1634 |
+
"step": 2320
|
| 1635 |
+
},
|
| 1636 |
+
{
|
| 1637 |
+
"epoch": 0.8971027047839061,
|
| 1638 |
+
"grad_norm": 0.0680164024233818,
|
| 1639 |
+
"learning_rate": 2.7669806479785067e-07,
|
| 1640 |
+
"loss": 0.7539,
|
| 1641 |
+
"step": 2330
|
| 1642 |
+
},
|
| 1643 |
+
{
|
| 1644 |
+
"epoch": 0.9009529309846953,
|
| 1645 |
+
"grad_norm": 0.06629924476146698,
|
| 1646 |
+
"learning_rate": 2.566094074799763e-07,
|
| 1647 |
+
"loss": 0.7365,
|
| 1648 |
+
"step": 2340
|
| 1649 |
+
},
|
| 1650 |
+
{
|
| 1651 |
+
"epoch": 0.9048031571854847,
|
| 1652 |
+
"grad_norm": 0.06269390136003494,
|
| 1653 |
+
"learning_rate": 2.3725852980716557e-07,
|
| 1654 |
+
"loss": 0.7233,
|
| 1655 |
+
"step": 2350
|
| 1656 |
+
},
|
| 1657 |
+
{
|
| 1658 |
+
"epoch": 0.908653383386274,
|
| 1659 |
+
"grad_norm": 0.06634767353534698,
|
| 1660 |
+
"learning_rate": 2.1864844158503983e-07,
|
| 1661 |
+
"loss": 0.7455,
|
| 1662 |
+
"step": 2360
|
| 1663 |
+
},
|
| 1664 |
+
{
|
| 1665 |
+
"epoch": 0.9125036095870632,
|
| 1666 |
+
"grad_norm": 0.07190650701522827,
|
| 1667 |
+
"learning_rate": 2.007820373979702e-07,
|
| 1668 |
+
"loss": 0.729,
|
| 1669 |
+
"step": 2370
|
| 1670 |
+
},
|
| 1671 |
+
{
|
| 1672 |
+
"epoch": 0.9163538357878526,
|
| 1673 |
+
"grad_norm": 0.06970971077680588,
|
| 1674 |
+
"learning_rate": 1.8366209615886532e-07,
|
| 1675 |
+
"loss": 0.7356,
|
| 1676 |
+
"step": 2380
|
| 1677 |
+
},
|
| 1678 |
+
{
|
| 1679 |
+
"epoch": 0.9202040619886418,
|
| 1680 |
+
"grad_norm": 0.07159341126680374,
|
| 1681 |
+
"learning_rate": 1.6729128067693613e-07,
|
| 1682 |
+
"loss": 0.7608,
|
| 1683 |
+
"step": 2390
|
| 1684 |
+
},
|
| 1685 |
+
{
|
| 1686 |
+
"epoch": 0.9240542881894311,
|
| 1687 |
+
"grad_norm": 0.07011713832616806,
|
| 1688 |
+
"learning_rate": 1.5167213724353426e-07,
|
| 1689 |
+
"loss": 0.7432,
|
| 1690 |
+
"step": 2400
|
| 1691 |
+
},
|
| 1692 |
+
{
|
| 1693 |
+
"epoch": 0.9279045143902205,
|
| 1694 |
+
"grad_norm": 0.06952998042106628,
|
| 1695 |
+
"learning_rate": 1.3680709523610058e-07,
|
| 1696 |
+
"loss": 0.7323,
|
| 1697 |
+
"step": 2410
|
| 1698 |
+
},
|
| 1699 |
+
{
|
| 1700 |
+
"epoch": 0.9317547405910097,
|
| 1701 |
+
"grad_norm": 0.06370339542627335,
|
| 1702 |
+
"learning_rate": 1.2269846674030418e-07,
|
| 1703 |
+
"loss": 0.7611,
|
| 1704 |
+
"step": 2420
|
| 1705 |
+
},
|
| 1706 |
+
{
|
| 1707 |
+
"epoch": 0.935604966791799,
|
| 1708 |
+
"grad_norm": 0.06706968694925308,
|
| 1709 |
+
"learning_rate": 1.0934844619042595e-07,
|
| 1710 |
+
"loss": 0.7541,
|
| 1711 |
+
"step": 2430
|
| 1712 |
+
},
|
| 1713 |
+
{
|
| 1714 |
+
"epoch": 0.9394551929925883,
|
| 1715 |
+
"grad_norm": 0.06853428483009338,
|
| 1716 |
+
"learning_rate": 9.675911002803961e-08,
|
| 1717 |
+
"loss": 0.7357,
|
| 1718 |
+
"step": 2440
|
| 1719 |
+
},
|
| 1720 |
+
{
|
| 1721 |
+
"epoch": 0.9433054191933776,
|
| 1722 |
+
"grad_norm": 0.06982247531414032,
|
| 1723 |
+
"learning_rate": 8.493241637904381e-08,
|
| 1724 |
+
"loss": 0.7283,
|
| 1725 |
+
"step": 2450
|
| 1726 |
+
},
|
| 1727 |
+
{
|
| 1728 |
+
"epoch": 0.9471556453941669,
|
| 1729 |
+
"grad_norm": 0.06830031424760818,
|
| 1730 |
+
"learning_rate": 7.387020474909689e-08,
|
| 1731 |
+
"loss": 0.7593,
|
| 1732 |
+
"step": 2460
|
| 1733 |
+
},
|
| 1734 |
+
{
|
| 1735 |
+
"epoch": 0.9510058715949562,
|
| 1736 |
+
"grad_norm": 0.06465063244104385,
|
| 1737 |
+
"learning_rate": 6.357419573750856e-08,
|
| 1738 |
+
"loss": 0.7346,
|
| 1739 |
+
"step": 2470
|
| 1740 |
+
},
|
| 1741 |
+
{
|
| 1742 |
+
"epoch": 0.9548560977957455,
|
| 1743 |
+
"grad_norm": 0.07008907943964005,
|
| 1744 |
+
"learning_rate": 5.4045990769613365e-08,
|
| 1745 |
+
"loss": 0.7425,
|
| 1746 |
+
"step": 2480
|
| 1747 |
+
},
|
| 1748 |
+
{
|
| 1749 |
+
"epoch": 0.9587063239965348,
|
| 1750 |
+
"grad_norm": 0.07458672672510147,
|
| 1751 |
+
"learning_rate": 4.5287071847694434e-08,
|
| 1752 |
+
"loss": 0.7414,
|
| 1753 |
+
"step": 2490
|
| 1754 |
+
},
|
| 1755 |
+
{
|
| 1756 |
+
"epoch": 0.9625565501973241,
|
| 1757 |
+
"grad_norm": 0.07294522225856781,
|
| 1758 |
+
"learning_rate": 3.7298801320467817e-08,
|
| 1759 |
+
"loss": 0.7345,
|
| 1760 |
+
"step": 2500
|
| 1761 |
+
},
|
| 1762 |
+
{
|
| 1763 |
+
"epoch": 0.9664067763981133,
|
| 1764 |
+
"grad_norm": 0.06674882024526596,
|
| 1765 |
+
"learning_rate": 3.0082421671192576e-08,
|
| 1766 |
+
"loss": 0.7412,
|
| 1767 |
+
"step": 2510
|
| 1768 |
+
},
|
| 1769 |
+
{
|
| 1770 |
+
"epoch": 0.9702570025989027,
|
| 1771 |
+
"grad_norm": 0.0676782876253128,
|
| 1772 |
+
"learning_rate": 2.3639055324410355e-08,
|
| 1773 |
+
"loss": 0.7409,
|
| 1774 |
+
"step": 2520
|
| 1775 |
+
},
|
| 1776 |
+
{
|
| 1777 |
+
"epoch": 0.974107228799692,
|
| 1778 |
+
"grad_norm": 0.07628905028104782,
|
| 1779 |
+
"learning_rate": 1.7969704471369477e-08,
|
| 1780 |
+
"loss": 0.7305,
|
| 1781 |
+
"step": 2530
|
| 1782 |
+
},
|
| 1783 |
+
{
|
| 1784 |
+
"epoch": 0.9779574550004813,
|
| 1785 |
+
"grad_norm": 0.06842445582151413,
|
| 1786 |
+
"learning_rate": 1.3075250914142413e-08,
|
| 1787 |
+
"loss": 0.7392,
|
| 1788 |
+
"step": 2540
|
| 1789 |
+
},
|
| 1790 |
+
{
|
| 1791 |
+
"epoch": 0.9818076812012706,
|
| 1792 |
+
"grad_norm": 0.0656604990363121,
|
| 1793 |
+
"learning_rate": 8.956455928476049e-09,
|
| 1794 |
+
"loss": 0.7484,
|
| 1795 |
+
"step": 2550
|
| 1796 |
+
},
|
| 1797 |
+
{
|
| 1798 |
+
"epoch": 0.9856579074020598,
|
| 1799 |
+
"grad_norm": 0.06109290570020676,
|
| 1800 |
+
"learning_rate": 5.6139601453786275e-09,
|
| 1801 |
+
"loss": 0.7283,
|
| 1802 |
+
"step": 2560
|
| 1803 |
+
},
|
| 1804 |
+
{
|
| 1805 |
+
"epoch": 0.9895081336028492,
|
| 1806 |
+
"grad_norm": 0.07294800132513046,
|
| 1807 |
+
"learning_rate": 3.0482834514805602e-09,
|
| 1808 |
+
"loss": 0.727,
|
| 1809 |
+
"step": 2570
|
| 1810 |
+
},
|
| 1811 |
+
{
|
| 1812 |
+
"epoch": 0.9933583598036385,
|
| 1813 |
+
"grad_norm": 0.06452541798353195,
|
| 1814 |
+
"learning_rate": 1.2598249081713366e-09,
|
| 1815 |
+
"loss": 0.7141,
|
| 1816 |
+
"step": 2580
|
| 1817 |
+
},
|
| 1818 |
+
{
|
| 1819 |
+
"epoch": 0.9972085860044277,
|
| 1820 |
+
"grad_norm": 0.066843181848526,
|
| 1821 |
+
"learning_rate": 2.488626895302826e-10,
|
| 1822 |
+
"loss": 0.7516,
|
| 1823 |
+
"step": 2590
|
| 1824 |
+
},
|
| 1825 |
+
{
|
| 1826 |
+
"epoch": 0.9999037443449803,
|
| 1827 |
+
"step": 2597,
|
| 1828 |
+
"total_flos": 2.1240486249533276e+18,
|
| 1829 |
+
"train_loss": 0.7760205771953361,
|
| 1830 |
+
"train_runtime": 14095.8195,
|
| 1831 |
+
"train_samples_per_second": 47.17,
|
| 1832 |
+
"train_steps_per_second": 0.184
|
| 1833 |
+
}
|
| 1834 |
+
],
|
| 1835 |
+
"logging_steps": 10,
|
| 1836 |
+
"max_steps": 2597,
|
| 1837 |
+
"num_input_tokens_seen": 0,
|
| 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": 2.1240486249533276e+18,
|
| 1853 |
+
"train_batch_size": 2,
|
| 1854 |
+
"trial_name": null,
|
| 1855 |
+
"trial_params": null
|
| 1856 |
+
}
|
continuous/qwen3/mc2_s16_384/finetune/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:35ae382bcfe589bdb7c3bab2dbcbb38bf560185553605b47e853944c17ed2374
|
| 3 |
+
size 6136
|
continuous/qwen3/mc2_s16_384/finetune/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
continuous/qwen3/mc2_s16_384/pretrain/config.json
ADDED
|
@@ -0,0 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_attn_implementation_autoset": true,
|
| 3 |
+
"add_faster_video": false,
|
| 4 |
+
"add_time_instruction": false,
|
| 5 |
+
"architectures": [
|
| 6 |
+
"Qwen3ForCausalLM"
|
| 7 |
+
],
|
| 8 |
+
"attention_bias": false,
|
| 9 |
+
"attention_dropout": 0.0,
|
| 10 |
+
"bos_token_id": 151643,
|
| 11 |
+
"eos_token_id": 151645,
|
| 12 |
+
"faster_token_stride": 10,
|
| 13 |
+
"force_sample": false,
|
| 14 |
+
"head_dim": 128,
|
| 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": 6144,
|
| 23 |
+
"max_position_embeddings": 40960,
|
| 24 |
+
"max_window_layers": 28,
|
| 25 |
+
"mm_hidden_size": 384,
|
| 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-S-16",
|
| 39 |
+
"mm_vision_tower_lr": null,
|
| 40 |
+
"model_type": "qwen3",
|
| 41 |
+
"num_attention_heads": 16,
|
| 42 |
+
"num_hidden_layers": 28,
|
| 43 |
+
"num_key_value_heads": 8,
|
| 44 |
+
"pos_skipping_range": 4096,
|
| 45 |
+
"rms_norm_eps": 1e-06,
|
| 46 |
+
"rope_scaling": null,
|
| 47 |
+
"rope_theta": 1000000,
|
| 48 |
+
"sliding_window": null,
|
| 49 |
+
"tie_word_embeddings": true,
|
| 50 |
+
"tokenizer_model_max_length": 8192,
|
| 51 |
+
"tokenizer_padding_side": "right",
|
| 52 |
+
"torch_dtype": "bfloat16",
|
| 53 |
+
"transformers_version": "4.51.3",
|
| 54 |
+
"use_cache": true,
|
| 55 |
+
"use_mm_proj": true,
|
| 56 |
+
"use_pos_skipping": false,
|
| 57 |
+
"use_sliding_window": false,
|
| 58 |
+
"vision_tower_pretrained": "/cache/ckpt/download/tokenizer/continuous/mc2/mc2_s16_384.pt",
|
| 59 |
+
"vocab_size": 151936
|
| 60 |
+
}
|
continuous/qwen3/mc2_s16_384/pretrain/mm_projector.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:48acea083b5918b2cb990280a84ea4138ba59b215fa0f7b8bed577150d2fbe9e
|
| 3 |
+
size 19941432
|
continuous/qwen3/mc2_s16_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": 15.087932586669922,
|
| 15 |
+
"learning_rate": 0.00032142857142857147,
|
| 16 |
+
"loss": 9.121,
|
| 17 |
+
"step": 10
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.03669724770642202,
|
| 21 |
+
"grad_norm": 0.5315393805503845,
|
| 22 |
+
"learning_rate": 0.0006785714285714287,
|
| 23 |
+
"loss": 5.7781,
|
| 24 |
+
"step": 20
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.05504587155963303,
|
| 28 |
+
"grad_norm": 0.07223573327064514,
|
| 29 |
+
"learning_rate": 0.0009999907688176173,
|
| 30 |
+
"loss": 4.8608,
|
| 31 |
+
"step": 30
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.07339449541284404,
|
| 35 |
+
"grad_norm": 0.05675940215587616,
|
| 36 |
+
"learning_rate": 0.0009988834393115766,
|
| 37 |
+
"loss": 4.7234,
|
| 38 |
+
"step": 40
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.09174311926605505,
|
| 42 |
+
"grad_norm": 0.0373048298060894,
|
| 43 |
+
"learning_rate": 0.0009959345572940772,
|
| 44 |
+
"loss": 4.6706,
|
| 45 |
+
"step": 50
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.11009174311926606,
|
| 49 |
+
"grad_norm": 0.027401618659496307,
|
| 50 |
+
"learning_rate": 0.0009911550081155983,
|
| 51 |
+
"loss": 4.6421,
|
| 52 |
+
"step": 60
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.12844036697247707,
|
| 56 |
+
"grad_norm": 0.03538146987557411,
|
| 57 |
+
"learning_rate": 0.0009845624347566433,
|
| 58 |
+
"loss": 4.6032,
|
| 59 |
+
"step": 70
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.14678899082568808,
|
| 63 |
+
"grad_norm": 0.046699196100234985,
|
| 64 |
+
"learning_rate": 0.0009761811727013547,
|
| 65 |
+
"loss": 4.5784,
|
| 66 |
+
"step": 80
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.1651376146788991,
|
| 70 |
+
"grad_norm": 0.051177363842725754,
|
| 71 |
+
"learning_rate": 0.0009660421601067666,
|
| 72 |
+
"loss": 4.5338,
|
| 73 |
+
"step": 90
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.1834862385321101,
|
| 77 |
+
"grad_norm": 0.07339658588171005,
|
| 78 |
+
"learning_rate": 0.0009541828235992926,
|
| 79 |
+
"loss": 4.4961,
|
| 80 |
+
"step": 100
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.2018348623853211,
|
| 84 |
+
"grad_norm": 0.04790649190545082,
|
| 85 |
+
"learning_rate": 0.0009406469401200151,
|
| 86 |
+
"loss": 4.4511,
|
| 87 |
+
"step": 110
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.22018348623853212,
|
| 91 |
+
"grad_norm": 0.0588734932243824,
|
| 92 |
+
"learning_rate": 0.0009254844753287492,
|
| 93 |
+
"loss": 4.4234,
|
| 94 |
+
"step": 120
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.23853211009174313,
|
| 98 |
+
"grad_norm": 0.06230953708291054,
|
| 99 |
+
"learning_rate": 0.0009087513991633924,
|
| 100 |
+
"loss": 4.3767,
|
| 101 |
+
"step": 130
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.25688073394495414,
|
| 105 |
+
"grad_norm": 0.05862278863787651,
|
| 106 |
+
"learning_rate": 0.0008905094792353917,
|
| 107 |
+
"loss": 4.3458,
|
| 108 |
+
"step": 140
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.27522935779816515,
|
| 112 |
+
"grad_norm": 0.07138340175151825,
|
| 113 |
+
"learning_rate": 0.0008708260528239789,
|
| 114 |
+
"loss": 4.3241,
|
| 115 |
+
"step": 150
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.29357798165137616,
|
| 119 |
+
"grad_norm": 0.06975489109754562,
|
| 120 |
+
"learning_rate": 0.0008497737783108237,
|
| 121 |
+
"loss": 4.279,
|
| 122 |
+
"step": 160
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.3119266055045872,
|
| 126 |
+
"grad_norm": 0.06288320571184158,
|
| 127 |
+
"learning_rate": 0.0008274303669726426,
|
| 128 |
+
"loss": 4.2417,
|
| 129 |
+
"step": 170
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.3302752293577982,
|
| 133 |
+
"grad_norm": 0.0787409171462059,
|
| 134 |
+
"learning_rate": 0.0008038782961218137,
|
| 135 |
+
"loss": 4.2118,
|
| 136 |
+
"step": 180
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.3486238532110092,
|
| 140 |
+
"grad_norm": 0.07247050106525421,
|
| 141 |
+
"learning_rate": 0.000779204504653894,
|
| 142 |
+
"loss": 4.1905,
|
| 143 |
+
"step": 190
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.3669724770642202,
|
| 147 |
+
"grad_norm": 0.06460707634687424,
|
| 148 |
+
"learning_rate": 0.0007535000721258791,
|
| 149 |
+
"loss": 4.1548,
|
| 150 |
+
"step": 200
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.3853211009174312,
|
| 154 |
+
"grad_norm": 0.07124781608581543,
|
| 155 |
+
"learning_rate": 0.00072685988254984,
|
| 156 |
+
"loss": 4.1396,
|
| 157 |
+
"step": 210
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.4036697247706422,
|
| 161 |
+
"grad_norm": 0.11520535498857498,
|
| 162 |
+
"learning_rate": 0.0006993822741429906,
|
| 163 |
+
"loss": 4.1447,
|
| 164 |
+
"step": 220
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.42201834862385323,
|
| 168 |
+
"grad_norm": 0.09266217797994614,
|
| 169 |
+
"learning_rate": 0.0006711686763270818,
|
| 170 |
+
"loss": 4.133,
|
| 171 |
+
"step": 230
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.44036697247706424,
|
| 175 |
+
"grad_norm": 0.05807582288980484,
|
| 176 |
+
"learning_rate": 0.0006423232353170831,
|
| 177 |
+
"loss": 4.116,
|
| 178 |
+
"step": 240
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.45871559633027525,
|
| 182 |
+
"grad_norm": 0.055580880492925644,
|
| 183 |
+
"learning_rate": 0.0006129524296812335,
|
| 184 |
+
"loss": 4.1054,
|
| 185 |
+
"step": 250
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.47706422018348627,
|
| 189 |
+
"grad_norm": 0.05364931374788284,
|
| 190 |
+
"learning_rate": 0.0005831646772915651,
|
| 191 |
+
"loss": 4.1122,
|
| 192 |
+
"step": 260
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.4954128440366973,
|
| 196 |
+
"grad_norm": 0.0562313012778759,
|
| 197 |
+
"learning_rate": 0.0005530699351157809,
|
| 198 |
+
"loss": 4.0895,
|
| 199 |
+
"step": 270
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.5137614678899083,
|
| 203 |
+
"grad_norm": 0.06269027292728424,
|
| 204 |
+
"learning_rate": 0.0005227792933277943,
|
| 205 |
+
"loss": 4.0875,
|
| 206 |
+
"step": 280
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.5321100917431193,
|
| 210 |
+
"grad_norm": 0.0548752062022686,
|
| 211 |
+
"learning_rate": 0.0004924045652352092,
|
| 212 |
+
"loss": 4.0772,
|
| 213 |
+
"step": 290
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.5504587155963303,
|
| 217 |
+
"grad_norm": 0.05760270729660988,
|
| 218 |
+
"learning_rate": 0.0004620578745374633,
|
| 219 |
+
"loss": 4.0748,
|
| 220 |
+
"step": 300
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.5688073394495413,
|
| 224 |
+
"grad_norm": 0.06886083632707596,
|
| 225 |
+
"learning_rate": 0.0004318512414382059,
|
| 226 |
+
"loss": 4.0847,
|
| 227 |
+
"step": 310
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.5871559633027523,
|
| 231 |
+
"grad_norm": 0.059646397829055786,
|
| 232 |
+
"learning_rate": 0.0004018961691397148,
|
| 233 |
+
"loss": 4.0744,
|
| 234 |
+
"step": 320
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.6055045871559633,
|
| 238 |
+
"grad_norm": 0.06500433385372162,
|
| 239 |
+
"learning_rate": 0.0003723032322457458,
|
| 240 |
+
"loss": 4.0612,
|
| 241 |
+
"step": 330
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.6238532110091743,
|
| 245 |
+
"grad_norm": 0.07700828462839127,
|
| 246 |
+
"learning_rate": 0.0003431816685921625,
|
| 247 |
+
"loss": 4.0593,
|
| 248 |
+
"step": 340
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.6422018348623854,
|
| 252 |
+
"grad_norm": 0.07953937351703644,
|
| 253 |
+
"learning_rate": 0.0003146389760120416,
|
| 254 |
+
"loss": 4.0633,
|
| 255 |
+
"step": 350
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.6605504587155964,
|
| 259 |
+
"grad_norm": 0.07670940458774567,
|
| 260 |
+
"learning_rate": 0.00028678051552373485,
|
| 261 |
+
"loss": 4.0682,
|
| 262 |
+
"step": 360
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.6788990825688074,
|
| 266 |
+
"grad_norm": 0.0604778528213501,
|
| 267 |
+
"learning_rate": 0.0002597091224066581,
|
| 268 |
+
"loss": 4.0548,
|
| 269 |
+
"step": 370
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.6972477064220184,
|
| 273 |
+
"grad_norm": 0.0554187074303627,
|
| 274 |
+
"learning_rate": 0.0002335247266004629,
|
| 275 |
+
"loss": 4.0648,
|
| 276 |
+
"step": 380
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.7155963302752294,
|
| 280 |
+
"grad_norm": 0.05654866620898247,
|
| 281 |
+
"learning_rate": 0.000208323983828828,
|
| 282 |
+
"loss": 4.0523,
|
| 283 |
+
"step": 390
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.7339449541284404,
|
| 287 |
+
"grad_norm": 0.054225873202085495,
|
| 288 |
+
"learning_rate": 0.0001841999188095224,
|
| 289 |
+
"loss": 4.0453,
|
| 290 |
+
"step": 400
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.7522935779816514,
|
| 294 |
+
"grad_norm": 0.053239792585372925,
|
| 295 |
+
"learning_rate": 0.00016124158186777676,
|
| 296 |
+
"loss": 4.0545,
|
| 297 |
+
"step": 410
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.7706422018348624,
|
| 301 |
+
"grad_norm": 0.05615616217255592,
|
| 302 |
+
"learning_rate": 0.0001395337202205211,
|
| 303 |
+
"loss": 4.0466,
|
| 304 |
+
"step": 420
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.7889908256880734,
|
| 308 |
+
"grad_norm": 0.05280233919620514,
|
| 309 |
+
"learning_rate": 0.00011915646514489292,
|
| 310 |
+
"loss": 4.048,
|
| 311 |
+
"step": 430
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.8073394495412844,
|
| 315 |
+
"grad_norm": 0.0660538598895073,
|
| 316 |
+
"learning_rate": 0.00010018503618578818,
|
| 317 |
+
"loss": 4.055,
|
| 318 |
+
"step": 440
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.8256880733944955,
|
| 322 |
+
"grad_norm": 0.05061858519911766,
|
| 323 |
+
"learning_rate": 8.268946349432583e-05,
|
| 324 |
+
"loss": 4.0433,
|
| 325 |
+
"step": 450
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.8440366972477065,
|
| 329 |
+
"grad_norm": 0.051582396030426025,
|
| 330 |
+
"learning_rate": 6.673432932217117e-05,
|
| 331 |
+
"loss": 4.0409,
|
| 332 |
+
"step": 460
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.8623853211009175,
|
| 336 |
+
"grad_norm": 0.050865210592746735,
|
| 337 |
+
"learning_rate": 5.2378529625954684e-05,
|
| 338 |
+
"loss": 4.028,
|
| 339 |
+
"step": 470
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.8807339449541285,
|
| 343 |
+
"grad_norm": 0.05118555575609207,
|
| 344 |
+
"learning_rate": 3.9675056661785556e-05,
|
| 345 |
+
"loss": 4.0342,
|
| 346 |
+
"step": 480
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.8990825688073395,
|
| 350 |
+
"grad_norm": 0.048118945211172104,
|
| 351 |
+
"learning_rate": 2.8670803372379538e-05,
|
| 352 |
+
"loss": 4.0373,
|
| 353 |
+
"step": 490
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.9174311926605505,
|
| 357 |
+
"grad_norm": 0.048261284828186035,
|
| 358 |
+
"learning_rate": 1.9406390288876586e-05,
|
| 359 |
+
"loss": 4.049,
|
| 360 |
+
"step": 500
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.9357798165137615,
|
| 364 |
+
"grad_norm": 0.04812069982290268,
|
| 365 |
+
"learning_rate": 1.191601558631461e-05,
|
| 366 |
+
"loss": 4.0391,
|
| 367 |
+
"step": 510
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.9541284403669725,
|
| 371 |
+
"grad_norm": 0.04683320224285126,
|
| 372 |
+
"learning_rate": 6.2273288462559305e-06,
|
| 373 |
+
"loss": 4.0341,
|
| 374 |
+
"step": 520
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.9724770642201835,
|
| 378 |
+
"grad_norm": 0.04895312339067459,
|
| 379 |
+
"learning_rate": 2.361328992552314e-06,
|
| 380 |
+
"loss": 4.0379,
|
| 381 |
+
"step": 530
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.9908256880733946,
|
| 385 |
+
"grad_norm": 0.04693363979458809,
|
| 386 |
+
"learning_rate": 3.322867770044202e-07,
|
| 387 |
+
"loss": 4.0342,
|
| 388 |
+
"step": 540
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 1.0,
|
| 392 |
+
"step": 545,
|
| 393 |
+
"total_flos": 2.7488842854013338e+17,
|
| 394 |
+
"train_loss": 4.317927855745368,
|
| 395 |
+
"train_runtime": 5741.7592,
|
| 396 |
+
"train_samples_per_second": 97.205,
|
| 397 |
+
"train_steps_per_second": 0.095
|
| 398 |
+
}
|
| 399 |
+
],
|
| 400 |
+
"logging_steps": 10,
|
| 401 |
+
"max_steps": 545,
|
| 402 |
+
"num_input_tokens_seen": 0,
|
| 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": 2.7488842854013338e+17,
|
| 418 |
+
"train_batch_size": 32,
|
| 419 |
+
"trial_name": null,
|
| 420 |
+
"trial_params": null
|
| 421 |
+
}
|
continuous/qwen3/pe_core_b16_224/finetune/added_tokens.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</think>": 151668,
|
| 3 |
+
"</tool_call>": 151658,
|
| 4 |
+
"</tool_response>": 151666,
|
| 5 |
+
"<think>": 151667,
|
| 6 |
+
"<tool_call>": 151657,
|
| 7 |
+
"<tool_response>": 151665,
|
| 8 |
+
"<|box_end|>": 151649,
|
| 9 |
+
"<|box_start|>": 151648,
|
| 10 |
+
"<|endoftext|>": 151643,
|
| 11 |
+
"<|file_sep|>": 151664,
|
| 12 |
+
"<|fim_middle|>": 151660,
|
| 13 |
+
"<|fim_pad|>": 151662,
|
| 14 |
+
"<|fim_prefix|>": 151659,
|
| 15 |
+
"<|fim_suffix|>": 151661,
|
| 16 |
+
"<|im_end|>": 151645,
|
| 17 |
+
"<|im_start|>": 151644,
|
| 18 |
+
"<|image_pad|>": 151655,
|
| 19 |
+
"<|object_ref_end|>": 151647,
|
| 20 |
+
"<|object_ref_start|>": 151646,
|
| 21 |
+
"<|quad_end|>": 151651,
|
| 22 |
+
"<|quad_start|>": 151650,
|
| 23 |
+
"<|repo_name|>": 151663,
|
| 24 |
+
"<|video_pad|>": 151656,
|
| 25 |
+
"<|vision_end|>": 151653,
|
| 26 |
+
"<|vision_pad|>": 151654,
|
| 27 |
+
"<|vision_start|>": 151652
|
| 28 |
+
}
|
continuous/qwen3/pe_core_b16_224/finetune/chat_template.jinja
ADDED
|
@@ -0,0 +1,89 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- if tools %}
|
| 2 |
+
{{- '<|im_start|>system\n' }}
|
| 3 |
+
{%- if messages[0].role == 'system' %}
|
| 4 |
+
{{- messages[0].content + '\n\n' }}
|
| 5 |
+
{%- endif %}
|
| 6 |
+
{{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
|
| 7 |
+
{%- for tool in tools %}
|
| 8 |
+
{{- "\n" }}
|
| 9 |
+
{{- tool | tojson }}
|
| 10 |
+
{%- endfor %}
|
| 11 |
+
{{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
|
| 12 |
+
{%- else %}
|
| 13 |
+
{%- if messages[0].role == 'system' %}
|
| 14 |
+
{{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
|
| 15 |
+
{%- endif %}
|
| 16 |
+
{%- endif %}
|
| 17 |
+
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
|
| 18 |
+
{%- for message in messages[::-1] %}
|
| 19 |
+
{%- set index = (messages|length - 1) - loop.index0 %}
|
| 20 |
+
{%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
|
| 21 |
+
{%- set ns.multi_step_tool = false %}
|
| 22 |
+
{%- set ns.last_query_index = index %}
|
| 23 |
+
{%- endif %}
|
| 24 |
+
{%- endfor %}
|
| 25 |
+
{%- for message in messages %}
|
| 26 |
+
{%- if message.content is string %}
|
| 27 |
+
{%- set content = message.content %}
|
| 28 |
+
{%- else %}
|
| 29 |
+
{%- set content = '' %}
|
| 30 |
+
{%- endif %}
|
| 31 |
+
{%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
|
| 32 |
+
{{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
|
| 33 |
+
{%- elif message.role == "assistant" %}
|
| 34 |
+
{%- set reasoning_content = '' %}
|
| 35 |
+
{%- if message.reasoning_content is string %}
|
| 36 |
+
{%- set reasoning_content = message.reasoning_content %}
|
| 37 |
+
{%- else %}
|
| 38 |
+
{%- if '</think>' in content %}
|
| 39 |
+
{%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
|
| 40 |
+
{%- set content = content.split('</think>')[-1].lstrip('\n') %}
|
| 41 |
+
{%- endif %}
|
| 42 |
+
{%- endif %}
|
| 43 |
+
{%- if loop.index0 > ns.last_query_index %}
|
| 44 |
+
{%- if loop.last or (not loop.last and reasoning_content) %}
|
| 45 |
+
{{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
|
| 46 |
+
{%- else %}
|
| 47 |
+
{{- '<|im_start|>' + message.role + '\n' + content }}
|
| 48 |
+
{%- endif %}
|
| 49 |
+
{%- else %}
|
| 50 |
+
{{- '<|im_start|>' + message.role + '\n' + content }}
|
| 51 |
+
{%- endif %}
|
| 52 |
+
{%- if message.tool_calls %}
|
| 53 |
+
{%- for tool_call in message.tool_calls %}
|
| 54 |
+
{%- if (loop.first and content) or (not loop.first) %}
|
| 55 |
+
{{- '\n' }}
|
| 56 |
+
{%- endif %}
|
| 57 |
+
{%- if tool_call.function %}
|
| 58 |
+
{%- set tool_call = tool_call.function %}
|
| 59 |
+
{%- endif %}
|
| 60 |
+
{{- '<tool_call>\n{"name": "' }}
|
| 61 |
+
{{- tool_call.name }}
|
| 62 |
+
{{- '", "arguments": ' }}
|
| 63 |
+
{%- if tool_call.arguments is string %}
|
| 64 |
+
{{- tool_call.arguments }}
|
| 65 |
+
{%- else %}
|
| 66 |
+
{{- tool_call.arguments | tojson }}
|
| 67 |
+
{%- endif %}
|
| 68 |
+
{{- '}\n</tool_call>' }}
|
| 69 |
+
{%- endfor %}
|
| 70 |
+
{%- endif %}
|
| 71 |
+
{{- '<|im_end|>\n' }}
|
| 72 |
+
{%- elif message.role == "tool" %}
|
| 73 |
+
{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
|
| 74 |
+
{{- '<|im_start|>user' }}
|
| 75 |
+
{%- endif %}
|
| 76 |
+
{{- '\n<tool_response>\n' }}
|
| 77 |
+
{{- content }}
|
| 78 |
+
{{- '\n</tool_response>' }}
|
| 79 |
+
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
| 80 |
+
{{- '<|im_end|>\n' }}
|
| 81 |
+
{%- endif %}
|
| 82 |
+
{%- endif %}
|
| 83 |
+
{%- endfor %}
|
| 84 |
+
{%- if add_generation_prompt %}
|
| 85 |
+
{{- '<|im_start|>assistant\n' }}
|
| 86 |
+
{%- if enable_thinking is defined and enable_thinking is false %}
|
| 87 |
+
{{- '<think>\n\n</think>\n\n' }}
|
| 88 |
+
{%- endif %}
|
| 89 |
+
{%- endif %}
|
continuous/qwen3/pe_core_b16_224/finetune/config.json
ADDED
|
@@ -0,0 +1,89 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_faster_video": false,
|
| 3 |
+
"add_time_instruction": false,
|
| 4 |
+
"architectures": [
|
| 5 |
+
"LlavaQwen3ForCausalLM"
|
| 6 |
+
],
|
| 7 |
+
"attention_bias": false,
|
| 8 |
+
"attention_dropout": 0.0,
|
| 9 |
+
"dtype": "bfloat16",
|
| 10 |
+
"eos_token_id": 151645,
|
| 11 |
+
"faster_token_stride": 10,
|
| 12 |
+
"force_sample": false,
|
| 13 |
+
"head_dim": 128,
|
| 14 |
+
"hidden_act": "silu",
|
| 15 |
+
"hidden_size": 2048,
|
| 16 |
+
"image_aspect_ratio": "square",
|
| 17 |
+
"image_crop_resolution": null,
|
| 18 |
+
"image_grid_pinpoints": null,
|
| 19 |
+
"image_split_resolution": null,
|
| 20 |
+
"initializer_range": 0.02,
|
| 21 |
+
"intermediate_size": 6144,
|
| 22 |
+
"layer_types": [
|
| 23 |
+
"full_attention",
|
| 24 |
+
"full_attention",
|
| 25 |
+
"full_attention",
|
| 26 |
+
"full_attention",
|
| 27 |
+
"full_attention",
|
| 28 |
+
"full_attention",
|
| 29 |
+
"full_attention",
|
| 30 |
+
"full_attention",
|
| 31 |
+
"full_attention",
|
| 32 |
+
"full_attention",
|
| 33 |
+
"full_attention",
|
| 34 |
+
"full_attention",
|
| 35 |
+
"full_attention",
|
| 36 |
+
"full_attention",
|
| 37 |
+
"full_attention",
|
| 38 |
+
"full_attention",
|
| 39 |
+
"full_attention",
|
| 40 |
+
"full_attention",
|
| 41 |
+
"full_attention",
|
| 42 |
+
"full_attention",
|
| 43 |
+
"full_attention",
|
| 44 |
+
"full_attention",
|
| 45 |
+
"full_attention",
|
| 46 |
+
"full_attention",
|
| 47 |
+
"full_attention",
|
| 48 |
+
"full_attention",
|
| 49 |
+
"full_attention",
|
| 50 |
+
"full_attention"
|
| 51 |
+
],
|
| 52 |
+
"max_position_embeddings": 40960,
|
| 53 |
+
"max_window_layers": 28,
|
| 54 |
+
"mm_hidden_size": 768,
|
| 55 |
+
"mm_newline_position": "grid",
|
| 56 |
+
"mm_patch_merge_type": "flat",
|
| 57 |
+
"mm_projector_lr": 0.0001,
|
| 58 |
+
"mm_projector_type": "mlp2x_gelu",
|
| 59 |
+
"mm_resampler_type": null,
|
| 60 |
+
"mm_spatial_pool_mode": "bilinear",
|
| 61 |
+
"mm_spatial_pool_stride": null,
|
| 62 |
+
"mm_tunable_parts": "mm_mlp_adapter,mm_language_model",
|
| 63 |
+
"mm_use_im_patch_token": false,
|
| 64 |
+
"mm_use_im_start_end": false,
|
| 65 |
+
"mm_vision_select_feature": "patch",
|
| 66 |
+
"mm_vision_select_layer": -1,
|
| 67 |
+
"mm_vision_tower": "vtb_ssl:pe",
|
| 68 |
+
"mm_vision_tower_lr": null,
|
| 69 |
+
"model_type": "qwen3",
|
| 70 |
+
"num_attention_heads": 16,
|
| 71 |
+
"num_hidden_layers": 28,
|
| 72 |
+
"num_key_value_heads": 8,
|
| 73 |
+
"pad_token_id": 151643,
|
| 74 |
+
"pos_skipping_range": 4096,
|
| 75 |
+
"rms_norm_eps": 1e-06,
|
| 76 |
+
"rope_scaling": null,
|
| 77 |
+
"rope_theta": 1000000,
|
| 78 |
+
"sliding_window": null,
|
| 79 |
+
"tie_word_embeddings": true,
|
| 80 |
+
"tokenizer_model_max_length": 8192,
|
| 81 |
+
"tokenizer_padding_side": "right",
|
| 82 |
+
"transformers_version": "4.57.6",
|
| 83 |
+
"use_cache": true,
|
| 84 |
+
"use_mm_proj": true,
|
| 85 |
+
"use_pos_skipping": false,
|
| 86 |
+
"use_sliding_window": false,
|
| 87 |
+
"vision_tower_pretrained": "/cache/ckpt/download/tokenizer/continuous/pe/PE-Core-B16-224/PE-Core-B16-224.pt",
|
| 88 |
+
"vocab_size": 151936
|
| 89 |
+
}
|
continuous/qwen3/pe_core_b16_224/finetune/generation_config.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_sample": true,
|
| 3 |
+
"eos_token_id": [
|
| 4 |
+
151645,
|
| 5 |
+
151643
|
| 6 |
+
],
|
| 7 |
+
"pad_token_id": 151643,
|
| 8 |
+
"temperature": 0.6,
|
| 9 |
+
"top_k": 20,
|
| 10 |
+
"top_p": 0.95,
|
| 11 |
+
"transformers_version": "4.57.6"
|
| 12 |
+
}
|
continuous/qwen3/pe_core_b16_224/finetune/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
continuous/qwen3/pe_core_b16_224/finetune/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d7329bde6613820acd818c1dbddb7d6c0d3ee82d452d738dbdca1b425335e2d5
|
| 3 |
+
size 4273970352
|
continuous/qwen3/pe_core_b16_224/finetune/special_tokens_map.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|im_start|>",
|
| 4 |
+
"<|im_end|>",
|
| 5 |
+
"<|object_ref_start|>",
|
| 6 |
+
"<|object_ref_end|>",
|
| 7 |
+
"<|box_start|>",
|
| 8 |
+
"<|box_end|>",
|
| 9 |
+
"<|quad_start|>",
|
| 10 |
+
"<|quad_end|>",
|
| 11 |
+
"<|vision_start|>",
|
| 12 |
+
"<|vision_end|>",
|
| 13 |
+
"<|vision_pad|>",
|
| 14 |
+
"<|image_pad|>",
|
| 15 |
+
"<|video_pad|>"
|
| 16 |
+
],
|
| 17 |
+
"eos_token": {
|
| 18 |
+
"content": "<|im_end|>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
},
|
| 24 |
+
"pad_token": {
|
| 25 |
+
"content": "<|endoftext|>",
|
| 26 |
+
"lstrip": false,
|
| 27 |
+
"normalized": false,
|
| 28 |
+
"rstrip": false,
|
| 29 |
+
"single_word": false
|
| 30 |
+
}
|
| 31 |
+
}
|
continuous/qwen3/pe_core_b16_224/finetune/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
|
| 3 |
+
size 11422654
|
continuous/qwen3/pe_core_b16_224/finetune/tokenizer_config.json
ADDED
|
@@ -0,0 +1,240 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_prefix_space": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"151643": {
|
| 6 |
+
"content": "<|endoftext|>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"151644": {
|
| 14 |
+
"content": "<|im_start|>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"151645": {
|
| 22 |
+
"content": "<|im_end|>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
},
|
| 29 |
+
"151646": {
|
| 30 |
+
"content": "<|object_ref_start|>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false,
|
| 35 |
+
"special": true
|
| 36 |
+
},
|
| 37 |
+
"151647": {
|
| 38 |
+
"content": "<|object_ref_end|>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false,
|
| 43 |
+
"special": true
|
| 44 |
+
},
|
| 45 |
+
"151648": {
|
| 46 |
+
"content": "<|box_start|>",
|
| 47 |
+
"lstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"rstrip": false,
|
| 50 |
+
"single_word": false,
|
| 51 |
+
"special": true
|
| 52 |
+
},
|
| 53 |
+
"151649": {
|
| 54 |
+
"content": "<|box_end|>",
|
| 55 |
+
"lstrip": false,
|
| 56 |
+
"normalized": false,
|
| 57 |
+
"rstrip": false,
|
| 58 |
+
"single_word": false,
|
| 59 |
+
"special": true
|
| 60 |
+
},
|
| 61 |
+
"151650": {
|
| 62 |
+
"content": "<|quad_start|>",
|
| 63 |
+
"lstrip": false,
|
| 64 |
+
"normalized": false,
|
| 65 |
+
"rstrip": false,
|
| 66 |
+
"single_word": false,
|
| 67 |
+
"special": true
|
| 68 |
+
},
|
| 69 |
+
"151651": {
|
| 70 |
+
"content": "<|quad_end|>",
|
| 71 |
+
"lstrip": false,
|
| 72 |
+
"normalized": false,
|
| 73 |
+
"rstrip": false,
|
| 74 |
+
"single_word": false,
|
| 75 |
+
"special": true
|
| 76 |
+
},
|
| 77 |
+
"151652": {
|
| 78 |
+
"content": "<|vision_start|>",
|
| 79 |
+
"lstrip": false,
|
| 80 |
+
"normalized": false,
|
| 81 |
+
"rstrip": false,
|
| 82 |
+
"single_word": false,
|
| 83 |
+
"special": true
|
| 84 |
+
},
|
| 85 |
+
"151653": {
|
| 86 |
+
"content": "<|vision_end|>",
|
| 87 |
+
"lstrip": false,
|
| 88 |
+
"normalized": false,
|
| 89 |
+
"rstrip": false,
|
| 90 |
+
"single_word": false,
|
| 91 |
+
"special": true
|
| 92 |
+
},
|
| 93 |
+
"151654": {
|
| 94 |
+
"content": "<|vision_pad|>",
|
| 95 |
+
"lstrip": false,
|
| 96 |
+
"normalized": false,
|
| 97 |
+
"rstrip": false,
|
| 98 |
+
"single_word": false,
|
| 99 |
+
"special": true
|
| 100 |
+
},
|
| 101 |
+
"151655": {
|
| 102 |
+
"content": "<|image_pad|>",
|
| 103 |
+
"lstrip": false,
|
| 104 |
+
"normalized": false,
|
| 105 |
+
"rstrip": false,
|
| 106 |
+
"single_word": false,
|
| 107 |
+
"special": true
|
| 108 |
+
},
|
| 109 |
+
"151656": {
|
| 110 |
+
"content": "<|video_pad|>",
|
| 111 |
+
"lstrip": false,
|
| 112 |
+
"normalized": false,
|
| 113 |
+
"rstrip": false,
|
| 114 |
+
"single_word": false,
|
| 115 |
+
"special": true
|
| 116 |
+
},
|
| 117 |
+
"151657": {
|
| 118 |
+
"content": "<tool_call>",
|
| 119 |
+
"lstrip": false,
|
| 120 |
+
"normalized": false,
|
| 121 |
+
"rstrip": false,
|
| 122 |
+
"single_word": false,
|
| 123 |
+
"special": false
|
| 124 |
+
},
|
| 125 |
+
"151658": {
|
| 126 |
+
"content": "</tool_call>",
|
| 127 |
+
"lstrip": false,
|
| 128 |
+
"normalized": false,
|
| 129 |
+
"rstrip": false,
|
| 130 |
+
"single_word": false,
|
| 131 |
+
"special": false
|
| 132 |
+
},
|
| 133 |
+
"151659": {
|
| 134 |
+
"content": "<|fim_prefix|>",
|
| 135 |
+
"lstrip": false,
|
| 136 |
+
"normalized": false,
|
| 137 |
+
"rstrip": false,
|
| 138 |
+
"single_word": false,
|
| 139 |
+
"special": false
|
| 140 |
+
},
|
| 141 |
+
"151660": {
|
| 142 |
+
"content": "<|fim_middle|>",
|
| 143 |
+
"lstrip": false,
|
| 144 |
+
"normalized": false,
|
| 145 |
+
"rstrip": false,
|
| 146 |
+
"single_word": false,
|
| 147 |
+
"special": false
|
| 148 |
+
},
|
| 149 |
+
"151661": {
|
| 150 |
+
"content": "<|fim_suffix|>",
|
| 151 |
+
"lstrip": false,
|
| 152 |
+
"normalized": false,
|
| 153 |
+
"rstrip": false,
|
| 154 |
+
"single_word": false,
|
| 155 |
+
"special": false
|
| 156 |
+
},
|
| 157 |
+
"151662": {
|
| 158 |
+
"content": "<|fim_pad|>",
|
| 159 |
+
"lstrip": false,
|
| 160 |
+
"normalized": false,
|
| 161 |
+
"rstrip": false,
|
| 162 |
+
"single_word": false,
|
| 163 |
+
"special": false
|
| 164 |
+
},
|
| 165 |
+
"151663": {
|
| 166 |
+
"content": "<|repo_name|>",
|
| 167 |
+
"lstrip": false,
|
| 168 |
+
"normalized": false,
|
| 169 |
+
"rstrip": false,
|
| 170 |
+
"single_word": false,
|
| 171 |
+
"special": false
|
| 172 |
+
},
|
| 173 |
+
"151664": {
|
| 174 |
+
"content": "<|file_sep|>",
|
| 175 |
+
"lstrip": false,
|
| 176 |
+
"normalized": false,
|
| 177 |
+
"rstrip": false,
|
| 178 |
+
"single_word": false,
|
| 179 |
+
"special": false
|
| 180 |
+
},
|
| 181 |
+
"151665": {
|
| 182 |
+
"content": "<tool_response>",
|
| 183 |
+
"lstrip": false,
|
| 184 |
+
"normalized": false,
|
| 185 |
+
"rstrip": false,
|
| 186 |
+
"single_word": false,
|
| 187 |
+
"special": false
|
| 188 |
+
},
|
| 189 |
+
"151666": {
|
| 190 |
+
"content": "</tool_response>",
|
| 191 |
+
"lstrip": false,
|
| 192 |
+
"normalized": false,
|
| 193 |
+
"rstrip": false,
|
| 194 |
+
"single_word": false,
|
| 195 |
+
"special": false
|
| 196 |
+
},
|
| 197 |
+
"151667": {
|
| 198 |
+
"content": "<think>",
|
| 199 |
+
"lstrip": false,
|
| 200 |
+
"normalized": false,
|
| 201 |
+
"rstrip": false,
|
| 202 |
+
"single_word": false,
|
| 203 |
+
"special": false
|
| 204 |
+
},
|
| 205 |
+
"151668": {
|
| 206 |
+
"content": "</think>",
|
| 207 |
+
"lstrip": false,
|
| 208 |
+
"normalized": false,
|
| 209 |
+
"rstrip": false,
|
| 210 |
+
"single_word": false,
|
| 211 |
+
"special": false
|
| 212 |
+
}
|
| 213 |
+
},
|
| 214 |
+
"additional_special_tokens": [
|
| 215 |
+
"<|im_start|>",
|
| 216 |
+
"<|im_end|>",
|
| 217 |
+
"<|object_ref_start|>",
|
| 218 |
+
"<|object_ref_end|>",
|
| 219 |
+
"<|box_start|>",
|
| 220 |
+
"<|box_end|>",
|
| 221 |
+
"<|quad_start|>",
|
| 222 |
+
"<|quad_end|>",
|
| 223 |
+
"<|vision_start|>",
|
| 224 |
+
"<|vision_end|>",
|
| 225 |
+
"<|vision_pad|>",
|
| 226 |
+
"<|image_pad|>",
|
| 227 |
+
"<|video_pad|>"
|
| 228 |
+
],
|
| 229 |
+
"bos_token": null,
|
| 230 |
+
"clean_up_tokenization_spaces": false,
|
| 231 |
+
"eos_token": "<|im_end|>",
|
| 232 |
+
"errors": "replace",
|
| 233 |
+
"extra_special_tokens": {},
|
| 234 |
+
"model_max_length": 8192,
|
| 235 |
+
"pad_token": "<|endoftext|>",
|
| 236 |
+
"padding_side": "right",
|
| 237 |
+
"split_special_tokens": false,
|
| 238 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 239 |
+
"unk_token": null
|
| 240 |
+
}
|
continuous/qwen3/pe_core_b16_224/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": 0.9999037443449803,
|
| 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": 0.003850226200789296,
|
| 14 |
+
"grad_norm": 18.601266860961914,
|
| 15 |
+
"learning_rate": 1.153846153846154e-06,
|
| 16 |
+
"loss": 2.411,
|
| 17 |
+
"step": 10
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.007700452401578592,
|
| 21 |
+
"grad_norm": 6.594840049743652,
|
| 22 |
+
"learning_rate": 2.435897435897436e-06,
|
| 23 |
+
"loss": 1.9194,
|
| 24 |
+
"step": 20
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.01155067860236789,
|
| 28 |
+
"grad_norm": 4.476524829864502,
|
| 29 |
+
"learning_rate": 3.7179487179487184e-06,
|
| 30 |
+
"loss": 1.4834,
|
| 31 |
+
"step": 30
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.015400904803157185,
|
| 35 |
+
"grad_norm": 1.4338889122009277,
|
| 36 |
+
"learning_rate": 5e-06,
|
| 37 |
+
"loss": 1.1481,
|
| 38 |
+
"step": 40
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.019251131003946483,
|
| 42 |
+
"grad_norm": 0.8596493601799011,
|
| 43 |
+
"learning_rate": 6.282051282051282e-06,
|
| 44 |
+
"loss": 1.0391,
|
| 45 |
+
"step": 50
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.02310135720473578,
|
| 49 |
+
"grad_norm": 0.44551515579223633,
|
| 50 |
+
"learning_rate": 7.564102564102564e-06,
|
| 51 |
+
"loss": 0.9511,
|
| 52 |
+
"step": 60
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.026951583405525073,
|
| 56 |
+
"grad_norm": 0.31331655383110046,
|
| 57 |
+
"learning_rate": 8.846153846153847e-06,
|
| 58 |
+
"loss": 0.9035,
|
| 59 |
+
"step": 70
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.03080180960631437,
|
| 63 |
+
"grad_norm": 0.31821209192276,
|
| 64 |
+
"learning_rate": 9.999996111488723e-06,
|
| 65 |
+
"loss": 0.901,
|
| 66 |
+
"step": 80
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.034652035807103666,
|
| 70 |
+
"grad_norm": 0.28289878368377686,
|
| 71 |
+
"learning_rate": 9.999529497453782e-06,
|
| 72 |
+
"loss": 0.8695,
|
| 73 |
+
"step": 90
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.038502262007892966,
|
| 77 |
+
"grad_norm": 0.26264265179634094,
|
| 78 |
+
"learning_rate": 9.998285264324193e-06,
|
| 79 |
+
"loss": 0.8453,
|
| 80 |
+
"step": 100
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.04235248820868226,
|
| 84 |
+
"grad_norm": 0.25294750928878784,
|
| 85 |
+
"learning_rate": 9.996263605626052e-06,
|
| 86 |
+
"loss": 0.8303,
|
| 87 |
+
"step": 110
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.04620271440947156,
|
| 91 |
+
"grad_norm": 0.2548220455646515,
|
| 92 |
+
"learning_rate": 9.99346483580503e-06,
|
| 93 |
+
"loss": 0.8398,
|
| 94 |
+
"step": 120
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.05005294061026085,
|
| 98 |
+
"grad_norm": 0.25303879380226135,
|
| 99 |
+
"learning_rate": 9.989889390177467e-06,
|
| 100 |
+
"loss": 0.8326,
|
| 101 |
+
"step": 130
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.053903166811050146,
|
| 105 |
+
"grad_norm": 0.28731656074523926,
|
| 106 |
+
"learning_rate": 9.985537824862647e-06,
|
| 107 |
+
"loss": 0.828,
|
| 108 |
+
"step": 140
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.057753393011839446,
|
| 112 |
+
"grad_norm": 0.3096223771572113,
|
| 113 |
+
"learning_rate": 9.980410816696317e-06,
|
| 114 |
+
"loss": 0.8108,
|
| 115 |
+
"step": 150
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.06160361921262874,
|
| 119 |
+
"grad_norm": 0.26844507455825806,
|
| 120 |
+
"learning_rate": 9.97450916312541e-06,
|
| 121 |
+
"loss": 0.8184,
|
| 122 |
+
"step": 160
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.06545384541341803,
|
| 126 |
+
"grad_norm": 0.22823196649551392,
|
| 127 |
+
"learning_rate": 9.967833782084004e-06,
|
| 128 |
+
"loss": 0.8191,
|
| 129 |
+
"step": 170
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.06930407161420733,
|
| 133 |
+
"grad_norm": 0.2661473751068115,
|
| 134 |
+
"learning_rate": 9.960385711850554e-06,
|
| 135 |
+
"loss": 0.8443,
|
| 136 |
+
"step": 180
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.07315429781499663,
|
| 140 |
+
"grad_norm": 0.2666216194629669,
|
| 141 |
+
"learning_rate": 9.952166110886394e-06,
|
| 142 |
+
"loss": 0.8355,
|
| 143 |
+
"step": 190
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.07700452401578593,
|
| 147 |
+
"grad_norm": 0.2895265221595764,
|
| 148 |
+
"learning_rate": 9.943176257655567e-06,
|
| 149 |
+
"loss": 0.8235,
|
| 150 |
+
"step": 200
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.08085475021657522,
|
| 154 |
+
"grad_norm": 0.2677616477012634,
|
| 155 |
+
"learning_rate": 9.933417550425952e-06,
|
| 156 |
+
"loss": 0.822,
|
| 157 |
+
"step": 210
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.08470497641736452,
|
| 161 |
+
"grad_norm": 0.2594129145145416,
|
| 162 |
+
"learning_rate": 9.9228915070518e-06,
|
| 163 |
+
"loss": 0.8039,
|
| 164 |
+
"step": 220
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.08855520261815382,
|
| 168 |
+
"grad_norm": 0.2500189542770386,
|
| 169 |
+
"learning_rate": 9.911599764737632e-06,
|
| 170 |
+
"loss": 0.8046,
|
| 171 |
+
"step": 230
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.09240542881894312,
|
| 175 |
+
"grad_norm": 0.25193896889686584,
|
| 176 |
+
"learning_rate": 9.899544079783606e-06,
|
| 177 |
+
"loss": 0.7998,
|
| 178 |
+
"step": 240
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.0962556550197324,
|
| 182 |
+
"grad_norm": 0.2930992543697357,
|
| 183 |
+
"learning_rate": 9.886726327312338e-06,
|
| 184 |
+
"loss": 0.818,
|
| 185 |
+
"step": 250
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.1001058812205217,
|
| 189 |
+
"grad_norm": 0.23861034214496613,
|
| 190 |
+
"learning_rate": 9.87314850097724e-06,
|
| 191 |
+
"loss": 0.8116,
|
| 192 |
+
"step": 260
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.103956107421311,
|
| 196 |
+
"grad_norm": 0.2649678587913513,
|
| 197 |
+
"learning_rate": 9.858812712652452e-06,
|
| 198 |
+
"loss": 0.8013,
|
| 199 |
+
"step": 270
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.10780633362210029,
|
| 203 |
+
"grad_norm": 0.23949167132377625,
|
| 204 |
+
"learning_rate": 9.843721192104341e-06,
|
| 205 |
+
"loss": 0.7994,
|
| 206 |
+
"step": 280
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.11165655982288959,
|
| 210 |
+
"grad_norm": 0.24424909055233002,
|
| 211 |
+
"learning_rate": 9.827876286644698e-06,
|
| 212 |
+
"loss": 0.8175,
|
| 213 |
+
"step": 290
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.11550678602367889,
|
| 217 |
+
"grad_norm": 0.22762100398540497,
|
| 218 |
+
"learning_rate": 9.811280460765643e-06,
|
| 219 |
+
"loss": 0.7805,
|
| 220 |
+
"step": 300
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.11935701222446819,
|
| 224 |
+
"grad_norm": 0.24314872920513153,
|
| 225 |
+
"learning_rate": 9.793936295756292e-06,
|
| 226 |
+
"loss": 0.79,
|
| 227 |
+
"step": 310
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.12320723842525748,
|
| 231 |
+
"grad_norm": 0.2564857602119446,
|
| 232 |
+
"learning_rate": 9.775846489301279e-06,
|
| 233 |
+
"loss": 0.795,
|
| 234 |
+
"step": 320
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.12705746462604678,
|
| 238 |
+
"grad_norm": 0.26168394088745117,
|
| 239 |
+
"learning_rate": 9.757013855061157e-06,
|
| 240 |
+
"loss": 0.7924,
|
| 241 |
+
"step": 330
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.13090769082683607,
|
| 245 |
+
"grad_norm": 0.25357916951179504,
|
| 246 |
+
"learning_rate": 9.737441322234758e-06,
|
| 247 |
+
"loss": 0.8027,
|
| 248 |
+
"step": 340
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.13475791702762538,
|
| 252 |
+
"grad_norm": 0.2723337709903717,
|
| 253 |
+
"learning_rate": 9.717131935103605e-06,
|
| 254 |
+
"loss": 0.805,
|
| 255 |
+
"step": 350
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.13860814322841467,
|
| 259 |
+
"grad_norm": 0.2506951093673706,
|
| 260 |
+
"learning_rate": 9.696088852558398e-06,
|
| 261 |
+
"loss": 0.7906,
|
| 262 |
+
"step": 360
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.14245836942920398,
|
| 266 |
+
"grad_norm": 0.26283377408981323,
|
| 267 |
+
"learning_rate": 9.674315347607686e-06,
|
| 268 |
+
"loss": 0.8189,
|
| 269 |
+
"step": 370
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.14630859562999327,
|
| 273 |
+
"grad_norm": 0.250810831785202,
|
| 274 |
+
"learning_rate": 9.651814806868796e-06,
|
| 275 |
+
"loss": 0.7781,
|
| 276 |
+
"step": 380
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.15015882183078255,
|
| 280 |
+
"grad_norm": 0.24987666308879852,
|
| 281 |
+
"learning_rate": 9.62859073004107e-06,
|
| 282 |
+
"loss": 0.7816,
|
| 283 |
+
"step": 390
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.15400904803157187,
|
| 287 |
+
"grad_norm": 0.23988209664821625,
|
| 288 |
+
"learning_rate": 9.604646729361547e-06,
|
| 289 |
+
"loss": 0.7813,
|
| 290 |
+
"step": 400
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.15785927423236115,
|
| 294 |
+
"grad_norm": 0.2439575344324112,
|
| 295 |
+
"learning_rate": 9.579986529043099e-06,
|
| 296 |
+
"loss": 0.7709,
|
| 297 |
+
"step": 410
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.16170950043315044,
|
| 301 |
+
"grad_norm": 0.243331640958786,
|
| 302 |
+
"learning_rate": 9.554613964695189e-06,
|
| 303 |
+
"loss": 0.7911,
|
| 304 |
+
"step": 420
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.16555972663393975,
|
| 308 |
+
"grad_norm": 0.23910652101039886,
|
| 309 |
+
"learning_rate": 9.528532982727281e-06,
|
| 310 |
+
"loss": 0.7838,
|
| 311 |
+
"step": 430
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.16940995283472904,
|
| 315 |
+
"grad_norm": 0.24082092940807343,
|
| 316 |
+
"learning_rate": 9.501747639735018e-06,
|
| 317 |
+
"loss": 0.7772,
|
| 318 |
+
"step": 440
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.17326017903551832,
|
| 322 |
+
"grad_norm": 0.25332874059677124,
|
| 323 |
+
"learning_rate": 9.474262101869272e-06,
|
| 324 |
+
"loss": 0.7682,
|
| 325 |
+
"step": 450
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.17711040523630764,
|
| 329 |
+
"grad_norm": 0.24217262864112854,
|
| 330 |
+
"learning_rate": 9.446080644188141e-06,
|
| 331 |
+
"loss": 0.7748,
|
| 332 |
+
"step": 460
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.18096063143709692,
|
| 336 |
+
"grad_norm": 0.2428387850522995,
|
| 337 |
+
"learning_rate": 9.417207649992017e-06,
|
| 338 |
+
"loss": 0.7796,
|
| 339 |
+
"step": 470
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.18481085763788624,
|
| 343 |
+
"grad_norm": 0.24994313716888428,
|
| 344 |
+
"learning_rate": 9.387647610141816e-06,
|
| 345 |
+
"loss": 0.7786,
|
| 346 |
+
"step": 480
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.18866108383867553,
|
| 350 |
+
"grad_norm": 0.23981821537017822,
|
| 351 |
+
"learning_rate": 9.35740512236047e-06,
|
| 352 |
+
"loss": 0.7674,
|
| 353 |
+
"step": 490
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.1925113100394648,
|
| 357 |
+
"grad_norm": 0.22889547049999237,
|
| 358 |
+
"learning_rate": 9.326484890517809e-06,
|
| 359 |
+
"loss": 0.7741,
|
| 360 |
+
"step": 500
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.19636153624025413,
|
| 364 |
+
"grad_norm": 0.24829640984535217,
|
| 365 |
+
"learning_rate": 9.294891723898926e-06,
|
| 366 |
+
"loss": 0.7671,
|
| 367 |
+
"step": 510
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.2002117624410434,
|
| 371 |
+
"grad_norm": 0.2536601722240448,
|
| 372 |
+
"learning_rate": 9.262630536456153e-06,
|
| 373 |
+
"loss": 0.7973,
|
| 374 |
+
"step": 520
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.2040619886418327,
|
| 378 |
+
"grad_norm": 0.25520169734954834,
|
| 379 |
+
"learning_rate": 9.229706346044749e-06,
|
| 380 |
+
"loss": 0.77,
|
| 381 |
+
"step": 530
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.207912214842622,
|
| 385 |
+
"grad_norm": 0.25755634903907776,
|
| 386 |
+
"learning_rate": 9.196124273642422e-06,
|
| 387 |
+
"loss": 0.7819,
|
| 388 |
+
"step": 540
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.2117624410434113,
|
| 392 |
+
"grad_norm": 0.22771431505680084,
|
| 393 |
+
"learning_rate": 9.161889542552842e-06,
|
| 394 |
+
"loss": 0.7885,
|
| 395 |
+
"step": 550
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.21561266724420058,
|
| 399 |
+
"grad_norm": 0.22946420311927795,
|
| 400 |
+
"learning_rate": 9.127007477593193e-06,
|
| 401 |
+
"loss": 0.7865,
|
| 402 |
+
"step": 560
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.2194628934449899,
|
| 406 |
+
"grad_norm": 0.25921815633773804,
|
| 407 |
+
"learning_rate": 9.091483504265974e-06,
|
| 408 |
+
"loss": 0.7938,
|
| 409 |
+
"step": 570
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.22331311964577918,
|
| 413 |
+
"grad_norm": 0.2639017701148987,
|
| 414 |
+
"learning_rate": 9.055323147915116e-06,
|
| 415 |
+
"loss": 0.7766,
|
| 416 |
+
"step": 580
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.2271633458465685,
|
| 420 |
+
"grad_norm": 0.25042617321014404,
|
| 421 |
+
"learning_rate": 9.018532032866585e-06,
|
| 422 |
+
"loss": 0.7843,
|
| 423 |
+
"step": 590
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.23101357204735778,
|
| 427 |
+
"grad_norm": 0.22383998334407806,
|
| 428 |
+
"learning_rate": 8.981115881553579e-06,
|
| 429 |
+
"loss": 0.7775,
|
| 430 |
+
"step": 600
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.23486379824814707,
|
| 434 |
+
"grad_norm": 0.25766512751579285,
|
| 435 |
+
"learning_rate": 8.943080513626476e-06,
|
| 436 |
+
"loss": 0.7962,
|
| 437 |
+
"step": 610
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.23871402444893638,
|
| 441 |
+
"grad_norm": 0.2413119226694107,
|
| 442 |
+
"learning_rate": 8.904431845047641e-06,
|
| 443 |
+
"loss": 0.7824,
|
| 444 |
+
"step": 620
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.24256425064972567,
|
| 448 |
+
"grad_norm": 0.251710444688797,
|
| 449 |
+
"learning_rate": 8.86517588717128e-06,
|
| 450 |
+
"loss": 0.7977,
|
| 451 |
+
"step": 630
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.24641447685051496,
|
| 455 |
+
"grad_norm": 0.23447160422801971,
|
| 456 |
+
"learning_rate": 8.82531874580844e-06,
|
| 457 |
+
"loss": 0.7917,
|
| 458 |
+
"step": 640
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.25026470305130427,
|
| 462 |
+
"grad_norm": 0.22067581117153168,
|
| 463 |
+
"learning_rate": 8.784866620277314e-06,
|
| 464 |
+
"loss": 0.7469,
|
| 465 |
+
"step": 650
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.25411492925209356,
|
| 469 |
+
"grad_norm": 0.24895554780960083,
|
| 470 |
+
"learning_rate": 8.743825802439018e-06,
|
| 471 |
+
"loss": 0.7775,
|
| 472 |
+
"step": 660
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 0.25796515545288284,
|
| 476 |
+
"grad_norm": 0.2578534185886383,
|
| 477 |
+
"learning_rate": 8.702202675718956e-06,
|
| 478 |
+
"loss": 0.789,
|
| 479 |
+
"step": 670
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 0.26181538165367213,
|
| 483 |
+
"grad_norm": 0.2349572777748108,
|
| 484 |
+
"learning_rate": 8.660003714113959e-06,
|
| 485 |
+
"loss": 0.7552,
|
| 486 |
+
"step": 680
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 0.26566560785446147,
|
| 490 |
+
"grad_norm": 0.23312516510486603,
|
| 491 |
+
"learning_rate": 8.617235481185323e-06,
|
| 492 |
+
"loss": 0.7785,
|
| 493 |
+
"step": 690
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 0.26951583405525076,
|
| 497 |
+
"grad_norm": 0.2431761473417282,
|
| 498 |
+
"learning_rate": 8.573904629037931e-06,
|
| 499 |
+
"loss": 0.7858,
|
| 500 |
+
"step": 700
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.27336606025604004,
|
| 504 |
+
"grad_norm": 0.24302168190479279,
|
| 505 |
+
"learning_rate": 8.530017897285585e-06,
|
| 506 |
+
"loss": 0.7685,
|
| 507 |
+
"step": 710
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.27721628645682933,
|
| 511 |
+
"grad_norm": 0.21465668082237244,
|
| 512 |
+
"learning_rate": 8.485582112002746e-06,
|
| 513 |
+
"loss": 0.7749,
|
| 514 |
+
"step": 720
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.2810665126576186,
|
| 518 |
+
"grad_norm": 0.2448873072862625,
|
| 519 |
+
"learning_rate": 8.440604184662811e-06,
|
| 520 |
+
"loss": 0.7752,
|
| 521 |
+
"step": 730
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.28491673885840796,
|
| 525 |
+
"grad_norm": 0.23837928473949432,
|
| 526 |
+
"learning_rate": 8.395091111063118e-06,
|
| 527 |
+
"loss": 0.7637,
|
| 528 |
+
"step": 740
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 0.28876696505919724,
|
| 532 |
+
"grad_norm": 0.22772470116615295,
|
| 533 |
+
"learning_rate": 8.349049970236822e-06,
|
| 534 |
+
"loss": 0.7642,
|
| 535 |
+
"step": 750
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 0.29261719125998653,
|
| 539 |
+
"grad_norm": 0.23509541153907776,
|
| 540 |
+
"learning_rate": 8.302487923351842e-06,
|
| 541 |
+
"loss": 0.7563,
|
| 542 |
+
"step": 760
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.2964674174607758,
|
| 546 |
+
"grad_norm": 0.23899006843566895,
|
| 547 |
+
"learning_rate": 8.255412212597021e-06,
|
| 548 |
+
"loss": 0.7761,
|
| 549 |
+
"step": 770
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.3003176436615651,
|
| 553 |
+
"grad_norm": 0.22757065296173096,
|
| 554 |
+
"learning_rate": 8.207830160055688e-06,
|
| 555 |
+
"loss": 0.7733,
|
| 556 |
+
"step": 780
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.3041678698623544,
|
| 560 |
+
"grad_norm": 0.2535107135772705,
|
| 561 |
+
"learning_rate": 8.159749166566786e-06,
|
| 562 |
+
"loss": 0.7554,
|
| 563 |
+
"step": 790
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 0.30801809606314373,
|
| 567 |
+
"grad_norm": 0.22724972665309906,
|
| 568 |
+
"learning_rate": 8.11117671057377e-06,
|
| 569 |
+
"loss": 0.7818,
|
| 570 |
+
"step": 800
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.311868322263933,
|
| 574 |
+
"grad_norm": 0.24206353724002838,
|
| 575 |
+
"learning_rate": 8.062120346961404e-06,
|
| 576 |
+
"loss": 0.7717,
|
| 577 |
+
"step": 810
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 0.3157185484647223,
|
| 581 |
+
"grad_norm": 0.23109108209609985,
|
| 582 |
+
"learning_rate": 8.012587705880705e-06,
|
| 583 |
+
"loss": 0.7665,
|
| 584 |
+
"step": 820
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 0.3195687746655116,
|
| 588 |
+
"grad_norm": 0.2429497390985489,
|
| 589 |
+
"learning_rate": 7.962586491562146e-06,
|
| 590 |
+
"loss": 0.753,
|
| 591 |
+
"step": 830
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.3234190008663009,
|
| 595 |
+
"grad_norm": 0.23983578383922577,
|
| 596 |
+
"learning_rate": 7.912124481117357e-06,
|
| 597 |
+
"loss": 0.759,
|
| 598 |
+
"step": 840
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 0.3272692270670902,
|
| 602 |
+
"grad_norm": 0.24616838991641998,
|
| 603 |
+
"learning_rate": 7.861209523329494e-06,
|
| 604 |
+
"loss": 0.7741,
|
| 605 |
+
"step": 850
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 0.3311194532678795,
|
| 609 |
+
"grad_norm": 0.22543199360370636,
|
| 610 |
+
"learning_rate": 7.809849537432432e-06,
|
| 611 |
+
"loss": 0.7529,
|
| 612 |
+
"step": 860
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 0.3349696794686688,
|
| 616 |
+
"grad_norm": 0.23518025875091553,
|
| 617 |
+
"learning_rate": 7.758052511879035e-06,
|
| 618 |
+
"loss": 0.7652,
|
| 619 |
+
"step": 870
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 0.3388199056694581,
|
| 623 |
+
"grad_norm": 0.22514653205871582,
|
| 624 |
+
"learning_rate": 7.705826503098642e-06,
|
| 625 |
+
"loss": 0.758,
|
| 626 |
+
"step": 880
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 0.34267013187024736,
|
| 630 |
+
"grad_norm": 0.2287670075893402,
|
| 631 |
+
"learning_rate": 7.653179634243979e-06,
|
| 632 |
+
"loss": 0.7627,
|
| 633 |
+
"step": 890
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 0.34652035807103665,
|
| 637 |
+
"grad_norm": 0.21468885242938995,
|
| 638 |
+
"learning_rate": 7.600120093927696e-06,
|
| 639 |
+
"loss": 0.7636,
|
| 640 |
+
"step": 900
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 0.350370584271826,
|
| 644 |
+
"grad_norm": 0.24565058946609497,
|
| 645 |
+
"learning_rate": 7.546656134948729e-06,
|
| 646 |
+
"loss": 0.7519,
|
| 647 |
+
"step": 910
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 0.3542208104726153,
|
| 651 |
+
"grad_norm": 0.23755872249603271,
|
| 652 |
+
"learning_rate": 7.492796073008661e-06,
|
| 653 |
+
"loss": 0.7544,
|
| 654 |
+
"step": 920
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 0.35807103667340456,
|
| 658 |
+
"grad_norm": 0.2522193491458893,
|
| 659 |
+
"learning_rate": 7.438548285418326e-06,
|
| 660 |
+
"loss": 0.7406,
|
| 661 |
+
"step": 930
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 0.36192126287419385,
|
| 665 |
+
"grad_norm": 0.2579192519187927,
|
| 666 |
+
"learning_rate": 7.3839212097948e-06,
|
| 667 |
+
"loss": 0.7729,
|
| 668 |
+
"step": 940
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 0.36577148907498314,
|
| 672 |
+
"grad_norm": 0.24068011343479156,
|
| 673 |
+
"learning_rate": 7.328923342749039e-06,
|
| 674 |
+
"loss": 0.7917,
|
| 675 |
+
"step": 950
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 0.3696217152757725,
|
| 679 |
+
"grad_norm": 0.2562777101993561,
|
| 680 |
+
"learning_rate": 7.273563238564319e-06,
|
| 681 |
+
"loss": 0.7744,
|
| 682 |
+
"step": 960
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 0.37347194147656176,
|
| 686 |
+
"grad_norm": 0.24042698740959167,
|
| 687 |
+
"learning_rate": 7.217849507865724e-06,
|
| 688 |
+
"loss": 0.7517,
|
| 689 |
+
"step": 970
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 0.37732216767735105,
|
| 693 |
+
"grad_norm": 0.240844264626503,
|
| 694 |
+
"learning_rate": 7.161790816280858e-06,
|
| 695 |
+
"loss": 0.7618,
|
| 696 |
+
"step": 980
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 0.38117239387814034,
|
| 700 |
+
"grad_norm": 0.2328229546546936,
|
| 701 |
+
"learning_rate": 7.1053958830920125e-06,
|
| 702 |
+
"loss": 0.7401,
|
| 703 |
+
"step": 990
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 0.3850226200789296,
|
| 707 |
+
"grad_norm": 0.23246172070503235,
|
| 708 |
+
"learning_rate": 7.0486734798799715e-06,
|
| 709 |
+
"loss": 0.7634,
|
| 710 |
+
"step": 1000
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 0.3888728462797189,
|
| 714 |
+
"grad_norm": 0.23934893310070038,
|
| 715 |
+
"learning_rate": 6.991632429159708e-06,
|
| 716 |
+
"loss": 0.786,
|
| 717 |
+
"step": 1010
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 0.39272307248050825,
|
| 721 |
+
"grad_norm": 0.2531433403491974,
|
| 722 |
+
"learning_rate": 6.934281603008132e-06,
|
| 723 |
+
"loss": 0.7738,
|
| 724 |
+
"step": 1020
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 0.39657329868129754,
|
| 728 |
+
"grad_norm": 0.2364783138036728,
|
| 729 |
+
"learning_rate": 6.876629921684143e-06,
|
| 730 |
+
"loss": 0.7726,
|
| 731 |
+
"step": 1030
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 0.4004235248820868,
|
| 735 |
+
"grad_norm": 0.23890864849090576,
|
| 736 |
+
"learning_rate": 6.818686352241199e-06,
|
| 737 |
+
"loss": 0.7625,
|
| 738 |
+
"step": 1040
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 0.4042737510828761,
|
| 742 |
+
"grad_norm": 0.21614810824394226,
|
| 743 |
+
"learning_rate": 6.760459907132573e-06,
|
| 744 |
+
"loss": 0.7594,
|
| 745 |
+
"step": 1050
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 0.4081239772836654,
|
| 749 |
+
"grad_norm": 0.22180728614330292,
|
| 750 |
+
"learning_rate": 6.701959642809589e-06,
|
| 751 |
+
"loss": 0.7628,
|
| 752 |
+
"step": 1060
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 0.41197420348445474,
|
| 756 |
+
"grad_norm": 0.2396186739206314,
|
| 757 |
+
"learning_rate": 6.643194658312987e-06,
|
| 758 |
+
"loss": 0.7543,
|
| 759 |
+
"step": 1070
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 0.415824429685244,
|
| 763 |
+
"grad_norm": 0.22794750332832336,
|
| 764 |
+
"learning_rate": 6.584174093857676e-06,
|
| 765 |
+
"loss": 0.7808,
|
| 766 |
+
"step": 1080
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 0.4196746558860333,
|
| 770 |
+
"grad_norm": 0.2619093358516693,
|
| 771 |
+
"learning_rate": 6.5249071294110735e-06,
|
| 772 |
+
"loss": 0.7616,
|
| 773 |
+
"step": 1090
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 0.4235248820868226,
|
| 777 |
+
"grad_norm": 0.2484857141971588,
|
| 778 |
+
"learning_rate": 6.465402983265274e-06,
|
| 779 |
+
"loss": 0.7761,
|
| 780 |
+
"step": 1100
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 0.4273751082876119,
|
| 784 |
+
"grad_norm": 0.24430029094219208,
|
| 785 |
+
"learning_rate": 6.405670910603243e-06,
|
| 786 |
+
"loss": 0.7703,
|
| 787 |
+
"step": 1110
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 0.43122533448840117,
|
| 791 |
+
"grad_norm": 0.2506420612335205,
|
| 792 |
+
"learning_rate": 6.345720202059291e-06,
|
| 793 |
+
"loss": 0.7672,
|
| 794 |
+
"step": 1120
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 0.4350755606891905,
|
| 798 |
+
"grad_norm": 0.24518220126628876,
|
| 799 |
+
"learning_rate": 6.285560182274008e-06,
|
| 800 |
+
"loss": 0.7454,
|
| 801 |
+
"step": 1130
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 0.4389257868899798,
|
| 805 |
+
"grad_norm": 0.23789294064044952,
|
| 806 |
+
"learning_rate": 6.225200208443936e-06,
|
| 807 |
+
"loss": 0.7697,
|
| 808 |
+
"step": 1140
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 0.4427760130907691,
|
| 812 |
+
"grad_norm": 0.22249692678451538,
|
| 813 |
+
"learning_rate": 6.16464966886616e-06,
|
| 814 |
+
"loss": 0.7564,
|
| 815 |
+
"step": 1150
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 0.44662623929155837,
|
| 819 |
+
"grad_norm": 0.2623715102672577,
|
| 820 |
+
"learning_rate": 6.103917981478065e-06,
|
| 821 |
+
"loss": 0.7817,
|
| 822 |
+
"step": 1160
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 0.45047646549234766,
|
| 826 |
+
"grad_norm": 0.23076386749744415,
|
| 827 |
+
"learning_rate": 6.043014592392489e-06,
|
| 828 |
+
"loss": 0.7904,
|
| 829 |
+
"step": 1170
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 0.454326691693137,
|
| 833 |
+
"grad_norm": 0.2323404997587204,
|
| 834 |
+
"learning_rate": 5.981948974428485e-06,
|
| 835 |
+
"loss": 0.7673,
|
| 836 |
+
"step": 1180
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 0.4581769178939263,
|
| 840 |
+
"grad_norm": 0.24977314472198486,
|
| 841 |
+
"learning_rate": 5.920730625637934e-06,
|
| 842 |
+
"loss": 0.7439,
|
| 843 |
+
"step": 1190
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 0.46202714409471557,
|
| 847 |
+
"grad_norm": 0.2500133514404297,
|
| 848 |
+
"learning_rate": 5.8593690678282355e-06,
|
| 849 |
+
"loss": 0.7581,
|
| 850 |
+
"step": 1200
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 0.46587737029550486,
|
| 854 |
+
"grad_norm": 0.24718685448169708,
|
| 855 |
+
"learning_rate": 5.797873845081301e-06,
|
| 856 |
+
"loss": 0.7615,
|
| 857 |
+
"step": 1210
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 0.46972759649629414,
|
| 861 |
+
"grad_norm": 0.24358779191970825,
|
| 862 |
+
"learning_rate": 5.736254522269075e-06,
|
| 863 |
+
"loss": 0.7777,
|
| 864 |
+
"step": 1220
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 0.47357782269708343,
|
| 868 |
+
"grad_norm": 0.24189019203186035,
|
| 869 |
+
"learning_rate": 5.6745206835658386e-06,
|
| 870 |
+
"loss": 0.7794,
|
| 871 |
+
"step": 1230
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 0.47742804889787277,
|
| 875 |
+
"grad_norm": 0.23626597225666046,
|
| 876 |
+
"learning_rate": 5.612681930957495e-06,
|
| 877 |
+
"loss": 0.7509,
|
| 878 |
+
"step": 1240
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 0.48127827509866206,
|
| 882 |
+
"grad_norm": 0.22233301401138306,
|
| 883 |
+
"learning_rate": 5.550747882748095e-06,
|
| 884 |
+
"loss": 0.7467,
|
| 885 |
+
"step": 1250
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 0.48512850129945134,
|
| 889 |
+
"grad_norm": 0.25179582834243774,
|
| 890 |
+
"learning_rate": 5.4887281720638195e-06,
|
| 891 |
+
"loss": 0.7578,
|
| 892 |
+
"step": 1260
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 0.48897872750024063,
|
| 896 |
+
"grad_norm": 0.2636166512966156,
|
| 897 |
+
"learning_rate": 5.42663244535466e-06,
|
| 898 |
+
"loss": 0.7403,
|
| 899 |
+
"step": 1270
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 0.4928289537010299,
|
| 903 |
+
"grad_norm": 0.25524747371673584,
|
| 904 |
+
"learning_rate": 5.3644703608940205e-06,
|
| 905 |
+
"loss": 0.7492,
|
| 906 |
+
"step": 1280
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 0.49667917990181926,
|
| 910 |
+
"grad_norm": 0.23699313402175903,
|
| 911 |
+
"learning_rate": 5.302251587276491e-06,
|
| 912 |
+
"loss": 0.7596,
|
| 913 |
+
"step": 1290
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 0.5005294061026085,
|
| 917 |
+
"grad_norm": 0.2265048623085022,
|
| 918 |
+
"learning_rate": 5.2399858019140005e-06,
|
| 919 |
+
"loss": 0.7599,
|
| 920 |
+
"step": 1300
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 0.5043796323033978,
|
| 924 |
+
"grad_norm": 0.23031096160411835,
|
| 925 |
+
"learning_rate": 5.177682689530615e-06,
|
| 926 |
+
"loss": 0.7768,
|
| 927 |
+
"step": 1310
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 0.5082298585041871,
|
| 931 |
+
"grad_norm": 0.24787990748882294,
|
| 932 |
+
"learning_rate": 5.11535194065619e-06,
|
| 933 |
+
"loss": 0.7404,
|
| 934 |
+
"step": 1320
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 0.5120800847049765,
|
| 938 |
+
"grad_norm": 0.25422990322113037,
|
| 939 |
+
"learning_rate": 5.053003250119113e-06,
|
| 940 |
+
"loss": 0.7496,
|
| 941 |
+
"step": 1330
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 0.5159303109057657,
|
| 945 |
+
"grad_norm": 0.24249306321144104,
|
| 946 |
+
"learning_rate": 4.9906463155383925e-06,
|
| 947 |
+
"loss": 0.7609,
|
| 948 |
+
"step": 1340
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 0.519780537106555,
|
| 952 |
+
"grad_norm": 0.23759698867797852,
|
| 953 |
+
"learning_rate": 4.9282908358153046e-06,
|
| 954 |
+
"loss": 0.7549,
|
| 955 |
+
"step": 1350
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 0.5236307633073443,
|
| 959 |
+
"grad_norm": 0.2560427784919739,
|
| 960 |
+
"learning_rate": 4.8659465096248345e-06,
|
| 961 |
+
"loss": 0.768,
|
| 962 |
+
"step": 1360
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 0.5274809895081336,
|
| 966 |
+
"grad_norm": 0.2503182888031006,
|
| 967 |
+
"learning_rate": 4.803623033907169e-06,
|
| 968 |
+
"loss": 0.7657,
|
| 969 |
+
"step": 1370
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 0.5313312157089229,
|
| 973 |
+
"grad_norm": 0.22810465097427368,
|
| 974 |
+
"learning_rate": 4.741330102359441e-06,
|
| 975 |
+
"loss": 0.774,
|
| 976 |
+
"step": 1380
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 0.5351814419097122,
|
| 980 |
+
"grad_norm": 0.2515629529953003,
|
| 981 |
+
"learning_rate": 4.679077403927996e-06,
|
| 982 |
+
"loss": 0.7532,
|
| 983 |
+
"step": 1390
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 0.5390316681105015,
|
| 987 |
+
"grad_norm": 0.2372962087392807,
|
| 988 |
+
"learning_rate": 4.616874621301373e-06,
|
| 989 |
+
"loss": 0.7536,
|
| 990 |
+
"step": 1400
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 0.5428818943112907,
|
| 994 |
+
"grad_norm": 0.23705841600894928,
|
| 995 |
+
"learning_rate": 4.554731429404293e-06,
|
| 996 |
+
"loss": 0.7697,
|
| 997 |
+
"step": 1410
|
| 998 |
+
},
|
| 999 |
+
{
|
| 1000 |
+
"epoch": 0.5467321205120801,
|
| 1001 |
+
"grad_norm": 0.26210638880729675,
|
| 1002 |
+
"learning_rate": 4.492657493892822e-06,
|
| 1003 |
+
"loss": 0.7503,
|
| 1004 |
+
"step": 1420
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 0.5505823467128694,
|
| 1008 |
+
"grad_norm": 0.26863837242126465,
|
| 1009 |
+
"learning_rate": 4.430662469650999e-06,
|
| 1010 |
+
"loss": 0.7663,
|
| 1011 |
+
"step": 1430
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 0.5544325729136587,
|
| 1015 |
+
"grad_norm": 0.25926119089126587,
|
| 1016 |
+
"learning_rate": 4.368755999289118e-06,
|
| 1017 |
+
"loss": 0.7731,
|
| 1018 |
+
"step": 1440
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 0.558282799114448,
|
| 1022 |
+
"grad_norm": 0.25884661078453064,
|
| 1023 |
+
"learning_rate": 4.306947711643949e-06,
|
| 1024 |
+
"loss": 0.7544,
|
| 1025 |
+
"step": 1450
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 0.5621330253152372,
|
| 1029 |
+
"grad_norm": 0.24227623641490936,
|
| 1030 |
+
"learning_rate": 4.245247220281068e-06,
|
| 1031 |
+
"loss": 0.7583,
|
| 1032 |
+
"step": 1460
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 0.5659832515160266,
|
| 1036 |
+
"grad_norm": 0.23320548236370087,
|
| 1037 |
+
"learning_rate": 4.183664121999587e-06,
|
| 1038 |
+
"loss": 0.7542,
|
| 1039 |
+
"step": 1470
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"epoch": 0.5698334777168159,
|
| 1043 |
+
"grad_norm": 0.24014511704444885,
|
| 1044 |
+
"learning_rate": 4.122207995339474e-06,
|
| 1045 |
+
"loss": 0.752,
|
| 1046 |
+
"step": 1480
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 0.5736837039176051,
|
| 1050 |
+
"grad_norm": 0.2313404083251953,
|
| 1051 |
+
"learning_rate": 4.060888399091734e-06,
|
| 1052 |
+
"loss": 0.7574,
|
| 1053 |
+
"step": 1490
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 0.5775339301183945,
|
| 1057 |
+
"grad_norm": 0.236407071352005,
|
| 1058 |
+
"learning_rate": 3.999714870811639e-06,
|
| 1059 |
+
"loss": 0.7685,
|
| 1060 |
+
"step": 1500
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 0.5813841563191837,
|
| 1064 |
+
"grad_norm": 0.23830799758434296,
|
| 1065 |
+
"learning_rate": 3.938696925335275e-06,
|
| 1066 |
+
"loss": 0.7594,
|
| 1067 |
+
"step": 1510
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 0.5852343825199731,
|
| 1071 |
+
"grad_norm": 0.24205642938613892,
|
| 1072 |
+
"learning_rate": 3.87784405329962e-06,
|
| 1073 |
+
"loss": 0.7674,
|
| 1074 |
+
"step": 1520
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 0.5890846087207623,
|
| 1078 |
+
"grad_norm": 0.247783362865448,
|
| 1079 |
+
"learning_rate": 3.817165719666382e-06,
|
| 1080 |
+
"loss": 0.768,
|
| 1081 |
+
"step": 1530
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 0.5929348349215516,
|
| 1085 |
+
"grad_norm": 0.2341381013393402,
|
| 1086 |
+
"learning_rate": 3.756671362249841e-06,
|
| 1087 |
+
"loss": 0.7745,
|
| 1088 |
+
"step": 1540
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 0.596785061122341,
|
| 1092 |
+
"grad_norm": 0.23542188107967377,
|
| 1093 |
+
"learning_rate": 3.6963703902488907e-06,
|
| 1094 |
+
"loss": 0.7592,
|
| 1095 |
+
"step": 1550
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 0.6006352873231302,
|
| 1099 |
+
"grad_norm": 0.22824819386005402,
|
| 1100 |
+
"learning_rate": 3.6362721827835655e-06,
|
| 1101 |
+
"loss": 0.774,
|
| 1102 |
+
"step": 1560
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 0.6044855135239195,
|
| 1106 |
+
"grad_norm": 0.2504114806652069,
|
| 1107 |
+
"learning_rate": 3.576386087436212e-06,
|
| 1108 |
+
"loss": 0.7703,
|
| 1109 |
+
"step": 1570
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 0.6083357397247088,
|
| 1113 |
+
"grad_norm": 0.24489541351795197,
|
| 1114 |
+
"learning_rate": 3.5167214187975913e-06,
|
| 1115 |
+
"loss": 0.7625,
|
| 1116 |
+
"step": 1580
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 0.6121859659254981,
|
| 1120 |
+
"grad_norm": 0.21409688889980316,
|
| 1121 |
+
"learning_rate": 3.457287457018086e-06,
|
| 1122 |
+
"loss": 0.7635,
|
| 1123 |
+
"step": 1590
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 0.6160361921262875,
|
| 1127 |
+
"grad_norm": 0.22820313274860382,
|
| 1128 |
+
"learning_rate": 3.3980934463643003e-06,
|
| 1129 |
+
"loss": 0.7532,
|
| 1130 |
+
"step": 1600
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 0.6198864183270767,
|
| 1134 |
+
"grad_norm": 0.21876536309719086,
|
| 1135 |
+
"learning_rate": 3.3391485937812053e-06,
|
| 1136 |
+
"loss": 0.7345,
|
| 1137 |
+
"step": 1610
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 0.623736644527866,
|
| 1141 |
+
"grad_norm": 0.2417830526828766,
|
| 1142 |
+
"learning_rate": 3.280462067460115e-06,
|
| 1143 |
+
"loss": 0.7331,
|
| 1144 |
+
"step": 1620
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 0.6275868707286553,
|
| 1148 |
+
"grad_norm": 0.23136956989765167,
|
| 1149 |
+
"learning_rate": 3.222042995412669e-06,
|
| 1150 |
+
"loss": 0.7642,
|
| 1151 |
+
"step": 1630
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 0.6314370969294446,
|
| 1155 |
+
"grad_norm": 0.2156856656074524,
|
| 1156 |
+
"learning_rate": 3.163900464051089e-06,
|
| 1157 |
+
"loss": 0.7527,
|
| 1158 |
+
"step": 1640
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 0.635287323130234,
|
| 1162 |
+
"grad_norm": 0.23670411109924316,
|
| 1163 |
+
"learning_rate": 3.1060435167748826e-06,
|
| 1164 |
+
"loss": 0.7626,
|
| 1165 |
+
"step": 1650
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 0.6391375493310232,
|
| 1169 |
+
"grad_norm": 0.23069879412651062,
|
| 1170 |
+
"learning_rate": 3.048481152564253e-06,
|
| 1171 |
+
"loss": 0.7446,
|
| 1172 |
+
"step": 1660
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 0.6429877755318125,
|
| 1176 |
+
"grad_norm": 0.2509981095790863,
|
| 1177 |
+
"learning_rate": 2.9912223245804017e-06,
|
| 1178 |
+
"loss": 0.7692,
|
| 1179 |
+
"step": 1670
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 0.6468380017326018,
|
| 1183 |
+
"grad_norm": 0.25031816959381104,
|
| 1184 |
+
"learning_rate": 2.934275938772981e-06,
|
| 1185 |
+
"loss": 0.7613,
|
| 1186 |
+
"step": 1680
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 0.6506882279333911,
|
| 1190 |
+
"grad_norm": 0.24770256876945496,
|
| 1191 |
+
"learning_rate": 2.8776508524948676e-06,
|
| 1192 |
+
"loss": 0.7521,
|
| 1193 |
+
"step": 1690
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 0.6545384541341804,
|
| 1197 |
+
"grad_norm": 0.21454933285713196,
|
| 1198 |
+
"learning_rate": 2.821355873124503e-06,
|
| 1199 |
+
"loss": 0.7481,
|
| 1200 |
+
"step": 1700
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 0.6583886803349697,
|
| 1204 |
+
"grad_norm": 0.252678781747818,
|
| 1205 |
+
"learning_rate": 2.7653997566960144e-06,
|
| 1206 |
+
"loss": 0.7649,
|
| 1207 |
+
"step": 1710
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"epoch": 0.662238906535759,
|
| 1211 |
+
"grad_norm": 0.24547457695007324,
|
| 1212 |
+
"learning_rate": 2.709791206537309e-06,
|
| 1213 |
+
"loss": 0.7555,
|
| 1214 |
+
"step": 1720
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 0.6660891327365482,
|
| 1218 |
+
"grad_norm": 0.2342885583639145,
|
| 1219 |
+
"learning_rate": 2.6545388719163747e-06,
|
| 1220 |
+
"loss": 0.7577,
|
| 1221 |
+
"step": 1730
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 0.6699393589373376,
|
| 1225 |
+
"grad_norm": 0.23225654661655426,
|
| 1226 |
+
"learning_rate": 2.599651346695979e-06,
|
| 1227 |
+
"loss": 0.7569,
|
| 1228 |
+
"step": 1740
|
| 1229 |
+
},
|
| 1230 |
+
{
|
| 1231 |
+
"epoch": 0.6737895851381268,
|
| 1232 |
+
"grad_norm": 0.254669725894928,
|
| 1233 |
+
"learning_rate": 2.545137167997007e-06,
|
| 1234 |
+
"loss": 0.7553,
|
| 1235 |
+
"step": 1750
|
| 1236 |
+
},
|
| 1237 |
+
{
|
| 1238 |
+
"epoch": 0.6776398113389162,
|
| 1239 |
+
"grad_norm": 0.22782470285892487,
|
| 1240 |
+
"learning_rate": 2.4910048148705972e-06,
|
| 1241 |
+
"loss": 0.7414,
|
| 1242 |
+
"step": 1760
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 0.6814900375397055,
|
| 1246 |
+
"grad_norm": 0.25679144263267517,
|
| 1247 |
+
"learning_rate": 2.4372627069793327e-06,
|
| 1248 |
+
"loss": 0.7868,
|
| 1249 |
+
"step": 1770
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 0.6853402637404947,
|
| 1253 |
+
"grad_norm": 0.24696899950504303,
|
| 1254 |
+
"learning_rate": 2.3839192032876486e-06,
|
| 1255 |
+
"loss": 0.7729,
|
| 1256 |
+
"step": 1780
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 0.6891904899412841,
|
| 1260 |
+
"grad_norm": 0.23328854143619537,
|
| 1261 |
+
"learning_rate": 2.3309826007617047e-06,
|
| 1262 |
+
"loss": 0.7817,
|
| 1263 |
+
"step": 1790
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 0.6930407161420733,
|
| 1267 |
+
"grad_norm": 0.23823405802249908,
|
| 1268 |
+
"learning_rate": 2.278461133078881e-06,
|
| 1269 |
+
"loss": 0.746,
|
| 1270 |
+
"step": 1800
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 0.6968909423428626,
|
| 1274 |
+
"grad_norm": 0.23754258453845978,
|
| 1275 |
+
"learning_rate": 2.2263629693471258e-06,
|
| 1276 |
+
"loss": 0.737,
|
| 1277 |
+
"step": 1810
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 0.700741168543652,
|
| 1281 |
+
"grad_norm": 0.2240985482931137,
|
| 1282 |
+
"learning_rate": 2.1746962128343414e-06,
|
| 1283 |
+
"loss": 0.7604,
|
| 1284 |
+
"step": 1820
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 0.7045913947444412,
|
| 1288 |
+
"grad_norm": 0.22775784134864807,
|
| 1289 |
+
"learning_rate": 2.1234688997080183e-06,
|
| 1290 |
+
"loss": 0.7516,
|
| 1291 |
+
"step": 1830
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 0.7084416209452306,
|
| 1295 |
+
"grad_norm": 0.25864312052726746,
|
| 1296 |
+
"learning_rate": 2.0726889977853053e-06,
|
| 1297 |
+
"loss": 0.7557,
|
| 1298 |
+
"step": 1840
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 0.7122918471460198,
|
| 1302 |
+
"grad_norm": 0.2498953938484192,
|
| 1303 |
+
"learning_rate": 2.022364405293703e-06,
|
| 1304 |
+
"loss": 0.7699,
|
| 1305 |
+
"step": 1850
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 0.7161420733468091,
|
| 1309 |
+
"grad_norm": 0.23552842438220978,
|
| 1310 |
+
"learning_rate": 1.9725029496425814e-06,
|
| 1311 |
+
"loss": 0.7605,
|
| 1312 |
+
"step": 1860
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 0.7199922995475985,
|
| 1316 |
+
"grad_norm": 0.24568232893943787,
|
| 1317 |
+
"learning_rate": 1.923112386205727e-06,
|
| 1318 |
+
"loss": 0.756,
|
| 1319 |
+
"step": 1870
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 0.7238425257483877,
|
| 1323 |
+
"grad_norm": 0.2301597148180008,
|
| 1324 |
+
"learning_rate": 1.874200397115079e-06,
|
| 1325 |
+
"loss": 0.7652,
|
| 1326 |
+
"step": 1880
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 0.727692751949177,
|
| 1330 |
+
"grad_norm": 0.24586783349514008,
|
| 1331 |
+
"learning_rate": 1.825774590065857e-06,
|
| 1332 |
+
"loss": 0.7495,
|
| 1333 |
+
"step": 1890
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 0.7315429781499663,
|
| 1337 |
+
"grad_norm": 0.2348000705242157,
|
| 1338 |
+
"learning_rate": 1.7778424971332813e-06,
|
| 1339 |
+
"loss": 0.7562,
|
| 1340 |
+
"step": 1900
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 0.7353932043507556,
|
| 1344 |
+
"grad_norm": 0.2347402274608612,
|
| 1345 |
+
"learning_rate": 1.7304115736010407e-06,
|
| 1346 |
+
"loss": 0.7535,
|
| 1347 |
+
"step": 1910
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 0.739243430551545,
|
| 1351 |
+
"grad_norm": 0.23078101873397827,
|
| 1352 |
+
"learning_rate": 1.6834891968017108e-06,
|
| 1353 |
+
"loss": 0.7489,
|
| 1354 |
+
"step": 1920
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 0.7430936567523342,
|
| 1358 |
+
"grad_norm": 0.24828383326530457,
|
| 1359 |
+
"learning_rate": 1.6370826649692884e-06,
|
| 1360 |
+
"loss": 0.7636,
|
| 1361 |
+
"step": 1930
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 0.7469438829531235,
|
| 1365 |
+
"grad_norm": 0.24161219596862793,
|
| 1366 |
+
"learning_rate": 1.5911991961040463e-06,
|
| 1367 |
+
"loss": 0.7746,
|
| 1368 |
+
"step": 1940
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 0.7507941091539128,
|
| 1372 |
+
"grad_norm": 0.24320563673973083,
|
| 1373 |
+
"learning_rate": 1.545845926849851e-06,
|
| 1374 |
+
"loss": 0.7623,
|
| 1375 |
+
"step": 1950
|
| 1376 |
+
},
|
| 1377 |
+
{
|
| 1378 |
+
"epoch": 0.7546443353547021,
|
| 1379 |
+
"grad_norm": 0.25379008054733276,
|
| 1380 |
+
"learning_rate": 1.5010299113841397e-06,
|
| 1381 |
+
"loss": 0.7777,
|
| 1382 |
+
"step": 1960
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 0.7584945615554913,
|
| 1386 |
+
"grad_norm": 0.24440984427928925,
|
| 1387 |
+
"learning_rate": 1.4567581203207238e-06,
|
| 1388 |
+
"loss": 0.7678,
|
| 1389 |
+
"step": 1970
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 0.7623447877562807,
|
| 1393 |
+
"grad_norm": 0.2449347972869873,
|
| 1394 |
+
"learning_rate": 1.413037439625593e-06,
|
| 1395 |
+
"loss": 0.7641,
|
| 1396 |
+
"step": 1980
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 0.76619501395707,
|
| 1400 |
+
"grad_norm": 0.2560170292854309,
|
| 1401 |
+
"learning_rate": 1.3698746695458847e-06,
|
| 1402 |
+
"loss": 0.7614,
|
| 1403 |
+
"step": 1990
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 0.7700452401578592,
|
| 1407 |
+
"grad_norm": 0.2309785783290863,
|
| 1408 |
+
"learning_rate": 1.3272765235521745e-06,
|
| 1409 |
+
"loss": 0.7527,
|
| 1410 |
+
"step": 2000
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"epoch": 0.7738954663586486,
|
| 1414 |
+
"grad_norm": 0.23603381216526031,
|
| 1415 |
+
"learning_rate": 1.2852496272942877e-06,
|
| 1416 |
+
"loss": 0.7614,
|
| 1417 |
+
"step": 2010
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 0.7777456925594378,
|
| 1421 |
+
"grad_norm": 0.22288930416107178,
|
| 1422 |
+
"learning_rate": 1.2438005175707396e-06,
|
| 1423 |
+
"loss": 0.7469,
|
| 1424 |
+
"step": 2020
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 0.7815959187602272,
|
| 1428 |
+
"grad_norm": 0.23629863560199738,
|
| 1429 |
+
"learning_rate": 1.2029356413120297e-06,
|
| 1430 |
+
"loss": 0.732,
|
| 1431 |
+
"step": 2030
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 0.7854461449610165,
|
| 1435 |
+
"grad_norm": 0.23546653985977173,
|
| 1436 |
+
"learning_rate": 1.1626613545778786e-06,
|
| 1437 |
+
"loss": 0.749,
|
| 1438 |
+
"step": 2040
|
| 1439 |
+
},
|
| 1440 |
+
{
|
| 1441 |
+
"epoch": 0.7892963711618057,
|
| 1442 |
+
"grad_norm": 0.22603429853916168,
|
| 1443 |
+
"learning_rate": 1.1229839215686294e-06,
|
| 1444 |
+
"loss": 0.7545,
|
| 1445 |
+
"step": 2050
|
| 1446 |
+
},
|
| 1447 |
+
{
|
| 1448 |
+
"epoch": 0.7931465973625951,
|
| 1449 |
+
"grad_norm": 0.22663159668445587,
|
| 1450 |
+
"learning_rate": 1.0839095136509188e-06,
|
| 1451 |
+
"loss": 0.737,
|
| 1452 |
+
"step": 2060
|
| 1453 |
+
},
|
| 1454 |
+
{
|
| 1455 |
+
"epoch": 0.7969968235633843,
|
| 1456 |
+
"grad_norm": 0.2564626932144165,
|
| 1457 |
+
"learning_rate": 1.045444208397791e-06,
|
| 1458 |
+
"loss": 0.7589,
|
| 1459 |
+
"step": 2070
|
| 1460 |
+
},
|
| 1461 |
+
{
|
| 1462 |
+
"epoch": 0.8008470497641736,
|
| 1463 |
+
"grad_norm": 0.23842985928058624,
|
| 1464 |
+
"learning_rate": 1.007593988643402e-06,
|
| 1465 |
+
"loss": 0.7409,
|
| 1466 |
+
"step": 2080
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 0.804697275964963,
|
| 1470 |
+
"grad_norm": 0.2320801317691803,
|
| 1471 |
+
"learning_rate": 9.703647415524613e-07,
|
| 1472 |
+
"loss": 0.7643,
|
| 1473 |
+
"step": 2090
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 0.8085475021657522,
|
| 1477 |
+
"grad_norm": 0.23661433160305023,
|
| 1478 |
+
"learning_rate": 9.337622577045485e-07,
|
| 1479 |
+
"loss": 0.7509,
|
| 1480 |
+
"step": 2100
|
| 1481 |
+
},
|
| 1482 |
+
{
|
| 1483 |
+
"epoch": 0.8123977283665416,
|
| 1484 |
+
"grad_norm": 0.23141908645629883,
|
| 1485 |
+
"learning_rate": 8.977922301934588e-07,
|
| 1486 |
+
"loss": 0.7642,
|
| 1487 |
+
"step": 2110
|
| 1488 |
+
},
|
| 1489 |
+
{
|
| 1490 |
+
"epoch": 0.8162479545673308,
|
| 1491 |
+
"grad_norm": 0.23851235210895538,
|
| 1492 |
+
"learning_rate": 8.624602537417009e-07,
|
| 1493 |
+
"loss": 0.7661,
|
| 1494 |
+
"step": 2120
|
| 1495 |
+
},
|
| 1496 |
+
{
|
| 1497 |
+
"epoch": 0.8200981807681201,
|
| 1498 |
+
"grad_norm": 0.24803584814071655,
|
| 1499 |
+
"learning_rate": 8.277718238303123e-07,
|
| 1500 |
+
"loss": 0.7527,
|
| 1501 |
+
"step": 2130
|
| 1502 |
+
},
|
| 1503 |
+
{
|
| 1504 |
+
"epoch": 0.8239484069689095,
|
| 1505 |
+
"grad_norm": 0.22837524116039276,
|
| 1506 |
+
"learning_rate": 7.937323358440935e-07,
|
| 1507 |
+
"loss": 0.7554,
|
| 1508 |
+
"step": 2140
|
| 1509 |
+
},
|
| 1510 |
+
{
|
| 1511 |
+
"epoch": 0.8277986331696987,
|
| 1512 |
+
"grad_norm": 0.2467511147260666,
|
| 1513 |
+
"learning_rate": 7.603470842324223e-07,
|
| 1514 |
+
"loss": 0.7466,
|
| 1515 |
+
"step": 2150
|
| 1516 |
+
},
|
| 1517 |
+
{
|
| 1518 |
+
"epoch": 0.831648859370488,
|
| 1519 |
+
"grad_norm": 0.23033268749713898,
|
| 1520 |
+
"learning_rate": 7.276212616857575e-07,
|
| 1521 |
+
"loss": 0.7642,
|
| 1522 |
+
"step": 2160
|
| 1523 |
+
},
|
| 1524 |
+
{
|
| 1525 |
+
"epoch": 0.8354990855712773,
|
| 1526 |
+
"grad_norm": 0.23807430267333984,
|
| 1527 |
+
"learning_rate": 6.955599583279837e-07,
|
| 1528 |
+
"loss": 0.7623,
|
| 1529 |
+
"step": 2170
|
| 1530 |
+
},
|
| 1531 |
+
{
|
| 1532 |
+
"epoch": 0.8393493117720666,
|
| 1533 |
+
"grad_norm": 0.2437126189470291,
|
| 1534 |
+
"learning_rate": 6.641681609246981e-07,
|
| 1535 |
+
"loss": 0.7556,
|
| 1536 |
+
"step": 2180
|
| 1537 |
+
},
|
| 1538 |
+
{
|
| 1539 |
+
"epoch": 0.8431995379728559,
|
| 1540 |
+
"grad_norm": 0.2291203886270523,
|
| 1541 |
+
"learning_rate": 6.334507521075711e-07,
|
| 1542 |
+
"loss": 0.7594,
|
| 1543 |
+
"step": 2190
|
| 1544 |
+
},
|
| 1545 |
+
{
|
| 1546 |
+
"epoch": 0.8470497641736452,
|
| 1547 |
+
"grad_norm": 0.24804344773292542,
|
| 1548 |
+
"learning_rate": 6.034125096149179e-07,
|
| 1549 |
+
"loss": 0.7565,
|
| 1550 |
+
"step": 2200
|
| 1551 |
+
},
|
| 1552 |
+
{
|
| 1553 |
+
"epoch": 0.8508999903744345,
|
| 1554 |
+
"grad_norm": 0.23557762801647186,
|
| 1555 |
+
"learning_rate": 5.740581055485722e-07,
|
| 1556 |
+
"loss": 0.728,
|
| 1557 |
+
"step": 2210
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"epoch": 0.8547502165752238,
|
| 1561 |
+
"grad_norm": 0.22532354295253754,
|
| 1562 |
+
"learning_rate": 5.453921056471961e-07,
|
| 1563 |
+
"loss": 0.7628,
|
| 1564 |
+
"step": 2220
|
| 1565 |
+
},
|
| 1566 |
+
{
|
| 1567 |
+
"epoch": 0.8586004427760131,
|
| 1568 |
+
"grad_norm": 0.24155783653259277,
|
| 1569 |
+
"learning_rate": 5.174189685761288e-07,
|
| 1570 |
+
"loss": 0.7559,
|
| 1571 |
+
"step": 2230
|
| 1572 |
+
},
|
| 1573 |
+
{
|
| 1574 |
+
"epoch": 0.8624506689768023,
|
| 1575 |
+
"grad_norm": 0.23015546798706055,
|
| 1576 |
+
"learning_rate": 4.901430452338979e-07,
|
| 1577 |
+
"loss": 0.7694,
|
| 1578 |
+
"step": 2240
|
| 1579 |
+
},
|
| 1580 |
+
{
|
| 1581 |
+
"epoch": 0.8663008951775917,
|
| 1582 |
+
"grad_norm": 0.2345588505268097,
|
| 1583 |
+
"learning_rate": 4.6356857807548286e-07,
|
| 1584 |
+
"loss": 0.7499,
|
| 1585 |
+
"step": 2250
|
| 1586 |
+
},
|
| 1587 |
+
{
|
| 1588 |
+
"epoch": 0.870151121378381,
|
| 1589 |
+
"grad_norm": 0.24153974652290344,
|
| 1590 |
+
"learning_rate": 4.376997004524541e-07,
|
| 1591 |
+
"loss": 0.7398,
|
| 1592 |
+
"step": 2260
|
| 1593 |
+
},
|
| 1594 |
+
{
|
| 1595 |
+
"epoch": 0.8740013475791703,
|
| 1596 |
+
"grad_norm": 0.23157089948654175,
|
| 1597 |
+
"learning_rate": 4.12540435970073e-07,
|
| 1598 |
+
"loss": 0.7477,
|
| 1599 |
+
"step": 2270
|
| 1600 |
+
},
|
| 1601 |
+
{
|
| 1602 |
+
"epoch": 0.8778515737799596,
|
| 1603 |
+
"grad_norm": 0.2279880940914154,
|
| 1604 |
+
"learning_rate": 3.880946978614703e-07,
|
| 1605 |
+
"loss": 0.763,
|
| 1606 |
+
"step": 2280
|
| 1607 |
+
},
|
| 1608 |
+
{
|
| 1609 |
+
"epoch": 0.8817017999807488,
|
| 1610 |
+
"grad_norm": 0.2315739095211029,
|
| 1611 |
+
"learning_rate": 3.643662883789878e-07,
|
| 1612 |
+
"loss": 0.7618,
|
| 1613 |
+
"step": 2290
|
| 1614 |
+
},
|
| 1615 |
+
{
|
| 1616 |
+
"epoch": 0.8855520261815382,
|
| 1617 |
+
"grad_norm": 0.2234123945236206,
|
| 1618 |
+
"learning_rate": 3.41358898202781e-07,
|
| 1619 |
+
"loss": 0.7411,
|
| 1620 |
+
"step": 2300
|
| 1621 |
+
},
|
| 1622 |
+
{
|
| 1623 |
+
"epoch": 0.8894022523823275,
|
| 1624 |
+
"grad_norm": 0.22567197680473328,
|
| 1625 |
+
"learning_rate": 3.190761058667741e-07,
|
| 1626 |
+
"loss": 0.7518,
|
| 1627 |
+
"step": 2310
|
| 1628 |
+
},
|
| 1629 |
+
{
|
| 1630 |
+
"epoch": 0.8932524785831167,
|
| 1631 |
+
"grad_norm": 0.22968308627605438,
|
| 1632 |
+
"learning_rate": 2.9752137720206463e-07,
|
| 1633 |
+
"loss": 0.7581,
|
| 1634 |
+
"step": 2320
|
| 1635 |
+
},
|
| 1636 |
+
{
|
| 1637 |
+
"epoch": 0.8971027047839061,
|
| 1638 |
+
"grad_norm": 0.23181907832622528,
|
| 1639 |
+
"learning_rate": 2.7669806479785067e-07,
|
| 1640 |
+
"loss": 0.7636,
|
| 1641 |
+
"step": 2330
|
| 1642 |
+
},
|
| 1643 |
+
{
|
| 1644 |
+
"epoch": 0.9009529309846953,
|
| 1645 |
+
"grad_norm": 0.24179787933826447,
|
| 1646 |
+
"learning_rate": 2.566094074799763e-07,
|
| 1647 |
+
"loss": 0.7552,
|
| 1648 |
+
"step": 2340
|
| 1649 |
+
},
|
| 1650 |
+
{
|
| 1651 |
+
"epoch": 0.9048031571854847,
|
| 1652 |
+
"grad_norm": 0.23164206743240356,
|
| 1653 |
+
"learning_rate": 2.3725852980716557e-07,
|
| 1654 |
+
"loss": 0.7411,
|
| 1655 |
+
"step": 2350
|
| 1656 |
+
},
|
| 1657 |
+
{
|
| 1658 |
+
"epoch": 0.908653383386274,
|
| 1659 |
+
"grad_norm": 0.23103295266628265,
|
| 1660 |
+
"learning_rate": 2.1864844158503983e-07,
|
| 1661 |
+
"loss": 0.7516,
|
| 1662 |
+
"step": 2360
|
| 1663 |
+
},
|
| 1664 |
+
{
|
| 1665 |
+
"epoch": 0.9125036095870632,
|
| 1666 |
+
"grad_norm": 0.2618662714958191,
|
| 1667 |
+
"learning_rate": 2.007820373979702e-07,
|
| 1668 |
+
"loss": 0.7437,
|
| 1669 |
+
"step": 2370
|
| 1670 |
+
},
|
| 1671 |
+
{
|
| 1672 |
+
"epoch": 0.9163538357878526,
|
| 1673 |
+
"grad_norm": 0.23214994370937347,
|
| 1674 |
+
"learning_rate": 1.8366209615886532e-07,
|
| 1675 |
+
"loss": 0.7531,
|
| 1676 |
+
"step": 2380
|
| 1677 |
+
},
|
| 1678 |
+
{
|
| 1679 |
+
"epoch": 0.9202040619886418,
|
| 1680 |
+
"grad_norm": 0.23422080278396606,
|
| 1681 |
+
"learning_rate": 1.6729128067693613e-07,
|
| 1682 |
+
"loss": 0.7685,
|
| 1683 |
+
"step": 2390
|
| 1684 |
+
},
|
| 1685 |
+
{
|
| 1686 |
+
"epoch": 0.9240542881894311,
|
| 1687 |
+
"grad_norm": 0.2521064877510071,
|
| 1688 |
+
"learning_rate": 1.5167213724353426e-07,
|
| 1689 |
+
"loss": 0.7672,
|
| 1690 |
+
"step": 2400
|
| 1691 |
+
},
|
| 1692 |
+
{
|
| 1693 |
+
"epoch": 0.9279045143902205,
|
| 1694 |
+
"grad_norm": 0.22870303690433502,
|
| 1695 |
+
"learning_rate": 1.3680709523610058e-07,
|
| 1696 |
+
"loss": 0.747,
|
| 1697 |
+
"step": 2410
|
| 1698 |
+
},
|
| 1699 |
+
{
|
| 1700 |
+
"epoch": 0.9317547405910097,
|
| 1701 |
+
"grad_norm": 0.22660335898399353,
|
| 1702 |
+
"learning_rate": 1.2269846674030418e-07,
|
| 1703 |
+
"loss": 0.7692,
|
| 1704 |
+
"step": 2420
|
| 1705 |
+
},
|
| 1706 |
+
{
|
| 1707 |
+
"epoch": 0.935604966791799,
|
| 1708 |
+
"grad_norm": 0.23384304344654083,
|
| 1709 |
+
"learning_rate": 1.0934844619042595e-07,
|
| 1710 |
+
"loss": 0.7682,
|
| 1711 |
+
"step": 2430
|
| 1712 |
+
},
|
| 1713 |
+
{
|
| 1714 |
+
"epoch": 0.9394551929925883,
|
| 1715 |
+
"grad_norm": 0.24547424912452698,
|
| 1716 |
+
"learning_rate": 9.675911002803961e-08,
|
| 1717 |
+
"loss": 0.7542,
|
| 1718 |
+
"step": 2440
|
| 1719 |
+
},
|
| 1720 |
+
{
|
| 1721 |
+
"epoch": 0.9433054191933776,
|
| 1722 |
+
"grad_norm": 0.24687761068344116,
|
| 1723 |
+
"learning_rate": 8.493241637904381e-08,
|
| 1724 |
+
"loss": 0.7504,
|
| 1725 |
+
"step": 2450
|
| 1726 |
+
},
|
| 1727 |
+
{
|
| 1728 |
+
"epoch": 0.9471556453941669,
|
| 1729 |
+
"grad_norm": 0.24258267879486084,
|
| 1730 |
+
"learning_rate": 7.387020474909689e-08,
|
| 1731 |
+
"loss": 0.7746,
|
| 1732 |
+
"step": 2460
|
| 1733 |
+
},
|
| 1734 |
+
{
|
| 1735 |
+
"epoch": 0.9510058715949562,
|
| 1736 |
+
"grad_norm": 0.2534377872943878,
|
| 1737 |
+
"learning_rate": 6.357419573750856e-08,
|
| 1738 |
+
"loss": 0.7672,
|
| 1739 |
+
"step": 2470
|
| 1740 |
+
},
|
| 1741 |
+
{
|
| 1742 |
+
"epoch": 0.9548560977957455,
|
| 1743 |
+
"grad_norm": 0.24380412697792053,
|
| 1744 |
+
"learning_rate": 5.4045990769613365e-08,
|
| 1745 |
+
"loss": 0.7503,
|
| 1746 |
+
"step": 2480
|
| 1747 |
+
},
|
| 1748 |
+
{
|
| 1749 |
+
"epoch": 0.9587063239965348,
|
| 1750 |
+
"grad_norm": 0.28361064195632935,
|
| 1751 |
+
"learning_rate": 4.5287071847694434e-08,
|
| 1752 |
+
"loss": 0.7529,
|
| 1753 |
+
"step": 2490
|
| 1754 |
+
},
|
| 1755 |
+
{
|
| 1756 |
+
"epoch": 0.9625565501973241,
|
| 1757 |
+
"grad_norm": 0.23728692531585693,
|
| 1758 |
+
"learning_rate": 3.7298801320467817e-08,
|
| 1759 |
+
"loss": 0.7514,
|
| 1760 |
+
"step": 2500
|
| 1761 |
+
},
|
| 1762 |
+
{
|
| 1763 |
+
"epoch": 0.9664067763981133,
|
| 1764 |
+
"grad_norm": 0.23339828848838806,
|
| 1765 |
+
"learning_rate": 3.0082421671192576e-08,
|
| 1766 |
+
"loss": 0.7436,
|
| 1767 |
+
"step": 2510
|
| 1768 |
+
},
|
| 1769 |
+
{
|
| 1770 |
+
"epoch": 0.9702570025989027,
|
| 1771 |
+
"grad_norm": 0.23636238276958466,
|
| 1772 |
+
"learning_rate": 2.3639055324410355e-08,
|
| 1773 |
+
"loss": 0.768,
|
| 1774 |
+
"step": 2520
|
| 1775 |
+
},
|
| 1776 |
+
{
|
| 1777 |
+
"epoch": 0.974107228799692,
|
| 1778 |
+
"grad_norm": 0.23512426018714905,
|
| 1779 |
+
"learning_rate": 1.7969704471369477e-08,
|
| 1780 |
+
"loss": 0.7484,
|
| 1781 |
+
"step": 2530
|
| 1782 |
+
},
|
| 1783 |
+
{
|
| 1784 |
+
"epoch": 0.9779574550004813,
|
| 1785 |
+
"grad_norm": 0.2289874106645584,
|
| 1786 |
+
"learning_rate": 1.3075250914142413e-08,
|
| 1787 |
+
"loss": 0.7549,
|
| 1788 |
+
"step": 2540
|
| 1789 |
+
},
|
| 1790 |
+
{
|
| 1791 |
+
"epoch": 0.9818076812012706,
|
| 1792 |
+
"grad_norm": 0.22720544040203094,
|
| 1793 |
+
"learning_rate": 8.956455928476049e-09,
|
| 1794 |
+
"loss": 0.7614,
|
| 1795 |
+
"step": 2550
|
| 1796 |
+
},
|
| 1797 |
+
{
|
| 1798 |
+
"epoch": 0.9856579074020598,
|
| 1799 |
+
"grad_norm": 0.24226929247379303,
|
| 1800 |
+
"learning_rate": 5.6139601453786275e-09,
|
| 1801 |
+
"loss": 0.752,
|
| 1802 |
+
"step": 2560
|
| 1803 |
+
},
|
| 1804 |
+
{
|
| 1805 |
+
"epoch": 0.9895081336028492,
|
| 1806 |
+
"grad_norm": 0.23664113879203796,
|
| 1807 |
+
"learning_rate": 3.0482834514805602e-09,
|
| 1808 |
+
"loss": 0.743,
|
| 1809 |
+
"step": 2570
|
| 1810 |
+
},
|
| 1811 |
+
{
|
| 1812 |
+
"epoch": 0.9933583598036385,
|
| 1813 |
+
"grad_norm": 0.21075785160064697,
|
| 1814 |
+
"learning_rate": 1.2598249081713366e-09,
|
| 1815 |
+
"loss": 0.7336,
|
| 1816 |
+
"step": 2580
|
| 1817 |
+
},
|
| 1818 |
+
{
|
| 1819 |
+
"epoch": 0.9972085860044277,
|
| 1820 |
+
"grad_norm": 0.24603694677352905,
|
| 1821 |
+
"learning_rate": 2.488626895302826e-10,
|
| 1822 |
+
"loss": 0.768,
|
| 1823 |
+
"step": 2590
|
| 1824 |
+
},
|
| 1825 |
+
{
|
| 1826 |
+
"epoch": 0.9999037443449803,
|
| 1827 |
+
"step": 2597,
|
| 1828 |
+
"total_flos": 3.791950126902149e+18,
|
| 1829 |
+
"train_loss": 0.7861541728584134,
|
| 1830 |
+
"train_runtime": 12688.5905,
|
| 1831 |
+
"train_samples_per_second": 52.402,
|
| 1832 |
+
"train_steps_per_second": 0.205
|
| 1833 |
+
}
|
| 1834 |
+
],
|
| 1835 |
+
"logging_steps": 10,
|
| 1836 |
+
"max_steps": 2597,
|
| 1837 |
+
"num_input_tokens_seen": 418855352,
|
| 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": 3.791950126902149e+18,
|
| 1853 |
+
"train_batch_size": 8,
|
| 1854 |
+
"trial_name": null,
|
| 1855 |
+
"trial_params": null
|
| 1856 |
+
}
|
continuous/qwen3/pe_core_b16_224/finetune/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ed91ea90b2b7424efb897b2ec10674d3b2e299c9fe0c6b4b97bd636dda58612d
|
| 3 |
+
size 6264
|
continuous/qwen3/pe_core_b16_224/finetune/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
continuous/qwen3/pe_core_b16_224/pretrain/config.json
ADDED
|
@@ -0,0 +1,89 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_faster_video": false,
|
| 3 |
+
"add_time_instruction": false,
|
| 4 |
+
"architectures": [
|
| 5 |
+
"Qwen3ForCausalLM"
|
| 6 |
+
],
|
| 7 |
+
"attention_bias": false,
|
| 8 |
+
"attention_dropout": 0.0,
|
| 9 |
+
"dtype": "bfloat16",
|
| 10 |
+
"eos_token_id": 151645,
|
| 11 |
+
"faster_token_stride": 10,
|
| 12 |
+
"force_sample": false,
|
| 13 |
+
"head_dim": 128,
|
| 14 |
+
"hidden_act": "silu",
|
| 15 |
+
"hidden_size": 2048,
|
| 16 |
+
"image_aspect_ratio": "square",
|
| 17 |
+
"image_crop_resolution": null,
|
| 18 |
+
"image_grid_pinpoints": null,
|
| 19 |
+
"image_split_resolution": null,
|
| 20 |
+
"initializer_range": 0.02,
|
| 21 |
+
"intermediate_size": 6144,
|
| 22 |
+
"layer_types": [
|
| 23 |
+
"full_attention",
|
| 24 |
+
"full_attention",
|
| 25 |
+
"full_attention",
|
| 26 |
+
"full_attention",
|
| 27 |
+
"full_attention",
|
| 28 |
+
"full_attention",
|
| 29 |
+
"full_attention",
|
| 30 |
+
"full_attention",
|
| 31 |
+
"full_attention",
|
| 32 |
+
"full_attention",
|
| 33 |
+
"full_attention",
|
| 34 |
+
"full_attention",
|
| 35 |
+
"full_attention",
|
| 36 |
+
"full_attention",
|
| 37 |
+
"full_attention",
|
| 38 |
+
"full_attention",
|
| 39 |
+
"full_attention",
|
| 40 |
+
"full_attention",
|
| 41 |
+
"full_attention",
|
| 42 |
+
"full_attention",
|
| 43 |
+
"full_attention",
|
| 44 |
+
"full_attention",
|
| 45 |
+
"full_attention",
|
| 46 |
+
"full_attention",
|
| 47 |
+
"full_attention",
|
| 48 |
+
"full_attention",
|
| 49 |
+
"full_attention",
|
| 50 |
+
"full_attention"
|
| 51 |
+
],
|
| 52 |
+
"max_position_embeddings": 40960,
|
| 53 |
+
"max_window_layers": 28,
|
| 54 |
+
"mm_hidden_size": 768,
|
| 55 |
+
"mm_newline_position": "grid",
|
| 56 |
+
"mm_patch_merge_type": "flat",
|
| 57 |
+
"mm_projector_lr": null,
|
| 58 |
+
"mm_projector_type": "mlp2x_gelu",
|
| 59 |
+
"mm_resampler_type": null,
|
| 60 |
+
"mm_spatial_pool_mode": "bilinear",
|
| 61 |
+
"mm_spatial_pool_stride": null,
|
| 62 |
+
"mm_tunable_parts": "mm_mlp_adapter",
|
| 63 |
+
"mm_use_im_patch_token": false,
|
| 64 |
+
"mm_use_im_start_end": false,
|
| 65 |
+
"mm_vision_select_feature": "patch",
|
| 66 |
+
"mm_vision_select_layer": -1,
|
| 67 |
+
"mm_vision_tower": "vtb_ssl:pe",
|
| 68 |
+
"mm_vision_tower_lr": null,
|
| 69 |
+
"model_type": "qwen3",
|
| 70 |
+
"num_attention_heads": 16,
|
| 71 |
+
"num_hidden_layers": 28,
|
| 72 |
+
"num_key_value_heads": 8,
|
| 73 |
+
"pad_token_id": 151643,
|
| 74 |
+
"pos_skipping_range": 4096,
|
| 75 |
+
"rms_norm_eps": 1e-06,
|
| 76 |
+
"rope_scaling": null,
|
| 77 |
+
"rope_theta": 1000000,
|
| 78 |
+
"sliding_window": null,
|
| 79 |
+
"tie_word_embeddings": true,
|
| 80 |
+
"tokenizer_model_max_length": 8192,
|
| 81 |
+
"tokenizer_padding_side": "right",
|
| 82 |
+
"transformers_version": "4.57.6",
|
| 83 |
+
"use_cache": true,
|
| 84 |
+
"use_mm_proj": true,
|
| 85 |
+
"use_pos_skipping": false,
|
| 86 |
+
"use_sliding_window": false,
|
| 87 |
+
"vision_tower_pretrained": "/cache/ckpt/download/tokenizer/continuous/pe/PE-Core-B16-224/PE-Core-B16-224.pt",
|
| 88 |
+
"vocab_size": 151936
|
| 89 |
+
}
|
continuous/qwen3/pe_core_b16_224/pretrain/mm_projector.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:88e6947475a5223ed03990d9cbf04a569cf15aa0334e0656dba137e4417446a5
|
| 3 |
+
size 23087160
|
continuous/qwen3/pe_core_b16_224/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": 14.848555564880371,
|
| 15 |
+
"learning_rate": 0.00032142857142857147,
|
| 16 |
+
"loss": 9.071,
|
| 17 |
+
"step": 10
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.03669724770642202,
|
| 21 |
+
"grad_norm": 2.2846062183380127,
|
| 22 |
+
"learning_rate": 0.0006785714285714287,
|
| 23 |
+
"loss": 5.768,
|
| 24 |
+
"step": 20
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.05504587155963303,
|
| 28 |
+
"grad_norm": 0.23683582246303558,
|
| 29 |
+
"learning_rate": 0.0009999907688176173,
|
| 30 |
+
"loss": 4.9311,
|
| 31 |
+
"step": 30
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.07339449541284404,
|
| 35 |
+
"grad_norm": 0.13984356820583344,
|
| 36 |
+
"learning_rate": 0.0009988834393115766,
|
| 37 |
+
"loss": 4.742,
|
| 38 |
+
"step": 40
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.09174311926605505,
|
| 42 |
+
"grad_norm": 0.08682197332382202,
|
| 43 |
+
"learning_rate": 0.0009959345572940772,
|
| 44 |
+
"loss": 4.6695,
|
| 45 |
+
"step": 50
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.11009174311926606,
|
| 49 |
+
"grad_norm": 0.09992959350347519,
|
| 50 |
+
"learning_rate": 0.0009911550081155983,
|
| 51 |
+
"loss": 4.6254,
|
| 52 |
+
"step": 60
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.12844036697247707,
|
| 56 |
+
"grad_norm": 0.09532742202281952,
|
| 57 |
+
"learning_rate": 0.0009845624347566433,
|
| 58 |
+
"loss": 4.5703,
|
| 59 |
+
"step": 70
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.14678899082568808,
|
| 63 |
+
"grad_norm": 0.12469860911369324,
|
| 64 |
+
"learning_rate": 0.0009761811727013547,
|
| 65 |
+
"loss": 4.5337,
|
| 66 |
+
"step": 80
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.1651376146788991,
|
| 70 |
+
"grad_norm": 0.14084723591804504,
|
| 71 |
+
"learning_rate": 0.0009660421601067666,
|
| 72 |
+
"loss": 4.4921,
|
| 73 |
+
"step": 90
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.1834862385321101,
|
| 77 |
+
"grad_norm": 0.10449090600013733,
|
| 78 |
+
"learning_rate": 0.0009541828235992926,
|
| 79 |
+
"loss": 4.4672,
|
| 80 |
+
"step": 100
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.2018348623853211,
|
| 84 |
+
"grad_norm": 0.10983335971832275,
|
| 85 |
+
"learning_rate": 0.0009406469401200151,
|
| 86 |
+
"loss": 4.4312,
|
| 87 |
+
"step": 110
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.22018348623853212,
|
| 91 |
+
"grad_norm": 0.1307608187198639,
|
| 92 |
+
"learning_rate": 0.0009254844753287492,
|
| 93 |
+
"loss": 4.419,
|
| 94 |
+
"step": 120
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.23853211009174313,
|
| 98 |
+
"grad_norm": 0.10518930852413177,
|
| 99 |
+
"learning_rate": 0.0009087513991633924,
|
| 100 |
+
"loss": 4.3853,
|
| 101 |
+
"step": 130
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.25688073394495414,
|
| 105 |
+
"grad_norm": 0.11196020245552063,
|
| 106 |
+
"learning_rate": 0.0008905094792353917,
|
| 107 |
+
"loss": 4.366,
|
| 108 |
+
"step": 140
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.27522935779816515,
|
| 112 |
+
"grad_norm": 0.11456306278705597,
|
| 113 |
+
"learning_rate": 0.0008708260528239789,
|
| 114 |
+
"loss": 4.3548,
|
| 115 |
+
"step": 150
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.29357798165137616,
|
| 119 |
+
"grad_norm": 0.12357474863529205,
|
| 120 |
+
"learning_rate": 0.0008497737783108237,
|
| 121 |
+
"loss": 4.3376,
|
| 122 |
+
"step": 160
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.3119266055045872,
|
| 126 |
+
"grad_norm": 0.10735972970724106,
|
| 127 |
+
"learning_rate": 0.0008274303669726426,
|
| 128 |
+
"loss": 4.3167,
|
| 129 |
+
"step": 170
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.3302752293577982,
|
| 133 |
+
"grad_norm": 0.09685471653938293,
|
| 134 |
+
"learning_rate": 0.0008038782961218137,
|
| 135 |
+
"loss": 4.2947,
|
| 136 |
+
"step": 180
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.3486238532110092,
|
| 140 |
+
"grad_norm": 0.13542482256889343,
|
| 141 |
+
"learning_rate": 0.000779204504653894,
|
| 142 |
+
"loss": 4.2851,
|
| 143 |
+
"step": 190
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.3669724770642202,
|
| 147 |
+
"grad_norm": 0.10696586221456528,
|
| 148 |
+
"learning_rate": 0.0007535000721258791,
|
| 149 |
+
"loss": 4.2589,
|
| 150 |
+
"step": 200
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.3853211009174312,
|
| 154 |
+
"grad_norm": 0.10972768813371658,
|
| 155 |
+
"learning_rate": 0.00072685988254984,
|
| 156 |
+
"loss": 4.2463,
|
| 157 |
+
"step": 210
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.4036697247706422,
|
| 161 |
+
"grad_norm": 0.1329732984304428,
|
| 162 |
+
"learning_rate": 0.0006993822741429906,
|
| 163 |
+
"loss": 4.2565,
|
| 164 |
+
"step": 220
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.42201834862385323,
|
| 168 |
+
"grad_norm": 0.13366855680942535,
|
| 169 |
+
"learning_rate": 0.0006711686763270818,
|
| 170 |
+
"loss": 4.2447,
|
| 171 |
+
"step": 230
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.44036697247706424,
|
| 175 |
+
"grad_norm": 0.10914227366447449,
|
| 176 |
+
"learning_rate": 0.0006423232353170831,
|
| 177 |
+
"loss": 4.2283,
|
| 178 |
+
"step": 240
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.45871559633027525,
|
| 182 |
+
"grad_norm": 0.09854667633771896,
|
| 183 |
+
"learning_rate": 0.0006129524296812335,
|
| 184 |
+
"loss": 4.2061,
|
| 185 |
+
"step": 250
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.47706422018348627,
|
| 189 |
+
"grad_norm": 0.10421120375394821,
|
| 190 |
+
"learning_rate": 0.0005831646772915651,
|
| 191 |
+
"loss": 4.2132,
|
| 192 |
+
"step": 260
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.4954128440366973,
|
| 196 |
+
"grad_norm": 0.12050673365592957,
|
| 197 |
+
"learning_rate": 0.0005530699351157809,
|
| 198 |
+
"loss": 4.188,
|
| 199 |
+
"step": 270
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.5137614678899083,
|
| 203 |
+
"grad_norm": 0.10723162442445755,
|
| 204 |
+
"learning_rate": 0.0005227792933277943,
|
| 205 |
+
"loss": 4.1814,
|
| 206 |
+
"step": 280
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.5321100917431193,
|
| 210 |
+
"grad_norm": 0.10146716237068176,
|
| 211 |
+
"learning_rate": 0.0004924045652352092,
|
| 212 |
+
"loss": 4.1636,
|
| 213 |
+
"step": 290
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.5504587155963303,
|
| 217 |
+
"grad_norm": 0.10685907304286957,
|
| 218 |
+
"learning_rate": 0.0004620578745374633,
|
| 219 |
+
"loss": 4.1604,
|
| 220 |
+
"step": 300
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.5688073394495413,
|
| 224 |
+
"grad_norm": 0.1345967799425125,
|
| 225 |
+
"learning_rate": 0.0004318512414382059,
|
| 226 |
+
"loss": 4.1697,
|
| 227 |
+
"step": 310
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.5871559633027523,
|
| 231 |
+
"grad_norm": 0.10651794821023941,
|
| 232 |
+
"learning_rate": 0.0004018961691397148,
|
| 233 |
+
"loss": 4.1555,
|
| 234 |
+
"step": 320
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.6055045871559633,
|
| 238 |
+
"grad_norm": 0.10365713387727737,
|
| 239 |
+
"learning_rate": 0.0003723032322457458,
|
| 240 |
+
"loss": 4.1337,
|
| 241 |
+
"step": 330
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.6238532110091743,
|
| 245 |
+
"grad_norm": 0.10856533795595169,
|
| 246 |
+
"learning_rate": 0.0003431816685921625,
|
| 247 |
+
"loss": 4.1322,
|
| 248 |
+
"step": 340
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.6422018348623854,
|
| 252 |
+
"grad_norm": 0.11530889570713043,
|
| 253 |
+
"learning_rate": 0.0003146389760120416,
|
| 254 |
+
"loss": 4.1278,
|
| 255 |
+
"step": 350
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.6605504587155964,
|
| 259 |
+
"grad_norm": 0.1376655548810959,
|
| 260 |
+
"learning_rate": 0.00028678051552373485,
|
| 261 |
+
"loss": 4.1324,
|
| 262 |
+
"step": 360
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.6788990825688074,
|
| 266 |
+
"grad_norm": 0.1260441690683365,
|
| 267 |
+
"learning_rate": 0.0002597091224066581,
|
| 268 |
+
"loss": 4.1033,
|
| 269 |
+
"step": 370
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.6972477064220184,
|
| 273 |
+
"grad_norm": 0.11406981199979782,
|
| 274 |
+
"learning_rate": 0.0002335247266004629,
|
| 275 |
+
"loss": 4.1109,
|
| 276 |
+
"step": 380
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.7155963302752294,
|
| 280 |
+
"grad_norm": 0.1317819356918335,
|
| 281 |
+
"learning_rate": 0.000208323983828828,
|
| 282 |
+
"loss": 4.082,
|
| 283 |
+
"step": 390
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.7339449541284404,
|
| 287 |
+
"grad_norm": 0.12050173431634903,
|
| 288 |
+
"learning_rate": 0.0001841999188095224,
|
| 289 |
+
"loss": 4.0745,
|
| 290 |
+
"step": 400
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.7522935779816514,
|
| 294 |
+
"grad_norm": 0.11743027716875076,
|
| 295 |
+
"learning_rate": 0.00016124158186777676,
|
| 296 |
+
"loss": 4.0657,
|
| 297 |
+
"step": 410
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.7706422018348624,
|
| 301 |
+
"grad_norm": 0.10950251668691635,
|
| 302 |
+
"learning_rate": 0.0001395337202205211,
|
| 303 |
+
"loss": 4.0518,
|
| 304 |
+
"step": 420
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.7889908256880734,
|
| 308 |
+
"grad_norm": 0.12341891974210739,
|
| 309 |
+
"learning_rate": 0.00011915646514489292,
|
| 310 |
+
"loss": 4.0489,
|
| 311 |
+
"step": 430
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.8073394495412844,
|
| 315 |
+
"grad_norm": 0.1230662390589714,
|
| 316 |
+
"learning_rate": 0.00010018503618578818,
|
| 317 |
+
"loss": 4.0521,
|
| 318 |
+
"step": 440
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.8256880733944955,
|
| 322 |
+
"grad_norm": 0.11481540650129318,
|
| 323 |
+
"learning_rate": 8.268946349432583e-05,
|
| 324 |
+
"loss": 4.0387,
|
| 325 |
+
"step": 450
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.8440366972477065,
|
| 329 |
+
"grad_norm": 0.12142534554004669,
|
| 330 |
+
"learning_rate": 6.673432932217117e-05,
|
| 331 |
+
"loss": 4.0271,
|
| 332 |
+
"step": 460
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.8623853211009175,
|
| 336 |
+
"grad_norm": 0.11267606168985367,
|
| 337 |
+
"learning_rate": 5.2378529625954684e-05,
|
| 338 |
+
"loss": 4.0148,
|
| 339 |
+
"step": 470
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.8807339449541285,
|
| 343 |
+
"grad_norm": 0.11580978333950043,
|
| 344 |
+
"learning_rate": 3.9675056661785556e-05,
|
| 345 |
+
"loss": 4.0204,
|
| 346 |
+
"step": 480
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.8990825688073395,
|
| 350 |
+
"grad_norm": 0.11536998301744461,
|
| 351 |
+
"learning_rate": 2.8670803372379538e-05,
|
| 352 |
+
"loss": 4.0212,
|
| 353 |
+
"step": 490
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.9174311926605505,
|
| 357 |
+
"grad_norm": 0.11305123567581177,
|
| 358 |
+
"learning_rate": 1.9406390288876586e-05,
|
| 359 |
+
"loss": 4.0338,
|
| 360 |
+
"step": 500
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.9357798165137615,
|
| 364 |
+
"grad_norm": 0.11489968001842499,
|
| 365 |
+
"learning_rate": 1.191601558631461e-05,
|
| 366 |
+
"loss": 4.0183,
|
| 367 |
+
"step": 510
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.9541284403669725,
|
| 371 |
+
"grad_norm": 0.11660202592611313,
|
| 372 |
+
"learning_rate": 6.2273288462559305e-06,
|
| 373 |
+
"loss": 4.0134,
|
| 374 |
+
"step": 520
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.9724770642201835,
|
| 378 |
+
"grad_norm": 0.11198528856039047,
|
| 379 |
+
"learning_rate": 2.361328992552314e-06,
|
| 380 |
+
"loss": 4.0151,
|
| 381 |
+
"step": 530
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.9908256880733946,
|
| 385 |
+
"grad_norm": 0.11058159917593002,
|
| 386 |
+
"learning_rate": 3.322867770044202e-07,
|
| 387 |
+
"loss": 4.0158,
|
| 388 |
+
"step": 540
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 1.0,
|
| 392 |
+
"step": 545,
|
| 393 |
+
"total_flos": 3.000469449217147e+17,
|
| 394 |
+
"train_loss": 4.350436037396072,
|
| 395 |
+
"train_runtime": 5063.3799,
|
| 396 |
+
"train_samples_per_second": 110.228,
|
| 397 |
+
"train_steps_per_second": 0.108
|
| 398 |
+
}
|
| 399 |
+
],
|
| 400 |
+
"logging_steps": 10,
|
| 401 |
+
"max_steps": 545,
|
| 402 |
+
"num_input_tokens_seen": 33142912,
|
| 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": 3.000469449217147e+17,
|
| 418 |
+
"train_batch_size": 64,
|
| 419 |
+
"trial_name": null,
|
| 420 |
+
"trial_params": null
|
| 421 |
+
}
|
continuous/qwen3/pe_core_g14_448/finetune/added_tokens.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</think>": 151668,
|
| 3 |
+
"</tool_call>": 151658,
|
| 4 |
+
"</tool_response>": 151666,
|
| 5 |
+
"<think>": 151667,
|
| 6 |
+
"<tool_call>": 151657,
|
| 7 |
+
"<tool_response>": 151665,
|
| 8 |
+
"<|box_end|>": 151649,
|
| 9 |
+
"<|box_start|>": 151648,
|
| 10 |
+
"<|endoftext|>": 151643,
|
| 11 |
+
"<|file_sep|>": 151664,
|
| 12 |
+
"<|fim_middle|>": 151660,
|
| 13 |
+
"<|fim_pad|>": 151662,
|
| 14 |
+
"<|fim_prefix|>": 151659,
|
| 15 |
+
"<|fim_suffix|>": 151661,
|
| 16 |
+
"<|im_end|>": 151645,
|
| 17 |
+
"<|im_start|>": 151644,
|
| 18 |
+
"<|image_pad|>": 151655,
|
| 19 |
+
"<|object_ref_end|>": 151647,
|
| 20 |
+
"<|object_ref_start|>": 151646,
|
| 21 |
+
"<|quad_end|>": 151651,
|
| 22 |
+
"<|quad_start|>": 151650,
|
| 23 |
+
"<|repo_name|>": 151663,
|
| 24 |
+
"<|video_pad|>": 151656,
|
| 25 |
+
"<|vision_end|>": 151653,
|
| 26 |
+
"<|vision_pad|>": 151654,
|
| 27 |
+
"<|vision_start|>": 151652
|
| 28 |
+
}
|
continuous/qwen3/pe_core_g14_448/finetune/chat_template.jinja
ADDED
|
@@ -0,0 +1,89 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- if tools %}
|
| 2 |
+
{{- '<|im_start|>system\n' }}
|
| 3 |
+
{%- if messages[0].role == 'system' %}
|
| 4 |
+
{{- messages[0].content + '\n\n' }}
|
| 5 |
+
{%- endif %}
|
| 6 |
+
{{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
|
| 7 |
+
{%- for tool in tools %}
|
| 8 |
+
{{- "\n" }}
|
| 9 |
+
{{- tool | tojson }}
|
| 10 |
+
{%- endfor %}
|
| 11 |
+
{{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
|
| 12 |
+
{%- else %}
|
| 13 |
+
{%- if messages[0].role == 'system' %}
|
| 14 |
+
{{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
|
| 15 |
+
{%- endif %}
|
| 16 |
+
{%- endif %}
|
| 17 |
+
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
|
| 18 |
+
{%- for message in messages[::-1] %}
|
| 19 |
+
{%- set index = (messages|length - 1) - loop.index0 %}
|
| 20 |
+
{%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
|
| 21 |
+
{%- set ns.multi_step_tool = false %}
|
| 22 |
+
{%- set ns.last_query_index = index %}
|
| 23 |
+
{%- endif %}
|
| 24 |
+
{%- endfor %}
|
| 25 |
+
{%- for message in messages %}
|
| 26 |
+
{%- if message.content is string %}
|
| 27 |
+
{%- set content = message.content %}
|
| 28 |
+
{%- else %}
|
| 29 |
+
{%- set content = '' %}
|
| 30 |
+
{%- endif %}
|
| 31 |
+
{%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
|
| 32 |
+
{{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
|
| 33 |
+
{%- elif message.role == "assistant" %}
|
| 34 |
+
{%- set reasoning_content = '' %}
|
| 35 |
+
{%- if message.reasoning_content is string %}
|
| 36 |
+
{%- set reasoning_content = message.reasoning_content %}
|
| 37 |
+
{%- else %}
|
| 38 |
+
{%- if '</think>' in content %}
|
| 39 |
+
{%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
|
| 40 |
+
{%- set content = content.split('</think>')[-1].lstrip('\n') %}
|
| 41 |
+
{%- endif %}
|
| 42 |
+
{%- endif %}
|
| 43 |
+
{%- if loop.index0 > ns.last_query_index %}
|
| 44 |
+
{%- if loop.last or (not loop.last and reasoning_content) %}
|
| 45 |
+
{{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
|
| 46 |
+
{%- else %}
|
| 47 |
+
{{- '<|im_start|>' + message.role + '\n' + content }}
|
| 48 |
+
{%- endif %}
|
| 49 |
+
{%- else %}
|
| 50 |
+
{{- '<|im_start|>' + message.role + '\n' + content }}
|
| 51 |
+
{%- endif %}
|
| 52 |
+
{%- if message.tool_calls %}
|
| 53 |
+
{%- for tool_call in message.tool_calls %}
|
| 54 |
+
{%- if (loop.first and content) or (not loop.first) %}
|
| 55 |
+
{{- '\n' }}
|
| 56 |
+
{%- endif %}
|
| 57 |
+
{%- if tool_call.function %}
|
| 58 |
+
{%- set tool_call = tool_call.function %}
|
| 59 |
+
{%- endif %}
|
| 60 |
+
{{- '<tool_call>\n{"name": "' }}
|
| 61 |
+
{{- tool_call.name }}
|
| 62 |
+
{{- '", "arguments": ' }}
|
| 63 |
+
{%- if tool_call.arguments is string %}
|
| 64 |
+
{{- tool_call.arguments }}
|
| 65 |
+
{%- else %}
|
| 66 |
+
{{- tool_call.arguments | tojson }}
|
| 67 |
+
{%- endif %}
|
| 68 |
+
{{- '}\n</tool_call>' }}
|
| 69 |
+
{%- endfor %}
|
| 70 |
+
{%- endif %}
|
| 71 |
+
{{- '<|im_end|>\n' }}
|
| 72 |
+
{%- elif message.role == "tool" %}
|
| 73 |
+
{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
|
| 74 |
+
{{- '<|im_start|>user' }}
|
| 75 |
+
{%- endif %}
|
| 76 |
+
{{- '\n<tool_response>\n' }}
|
| 77 |
+
{{- content }}
|
| 78 |
+
{{- '\n</tool_response>' }}
|
| 79 |
+
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
| 80 |
+
{{- '<|im_end|>\n' }}
|
| 81 |
+
{%- endif %}
|
| 82 |
+
{%- endif %}
|
| 83 |
+
{%- endfor %}
|
| 84 |
+
{%- if add_generation_prompt %}
|
| 85 |
+
{{- '<|im_start|>assistant\n' }}
|
| 86 |
+
{%- if enable_thinking is defined and enable_thinking is false %}
|
| 87 |
+
{{- '<think>\n\n</think>\n\n' }}
|
| 88 |
+
{%- endif %}
|
| 89 |
+
{%- endif %}
|
continuous/qwen3/pe_core_g14_448/finetune/config.json
ADDED
|
@@ -0,0 +1,89 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_faster_video": false,
|
| 3 |
+
"add_time_instruction": false,
|
| 4 |
+
"architectures": [
|
| 5 |
+
"LlavaQwen3ForCausalLM"
|
| 6 |
+
],
|
| 7 |
+
"attention_bias": false,
|
| 8 |
+
"attention_dropout": 0.0,
|
| 9 |
+
"dtype": "bfloat16",
|
| 10 |
+
"eos_token_id": 151645,
|
| 11 |
+
"faster_token_stride": 10,
|
| 12 |
+
"force_sample": false,
|
| 13 |
+
"head_dim": 128,
|
| 14 |
+
"hidden_act": "silu",
|
| 15 |
+
"hidden_size": 2048,
|
| 16 |
+
"image_aspect_ratio": "square",
|
| 17 |
+
"image_crop_resolution": null,
|
| 18 |
+
"image_grid_pinpoints": null,
|
| 19 |
+
"image_split_resolution": null,
|
| 20 |
+
"initializer_range": 0.02,
|
| 21 |
+
"intermediate_size": 6144,
|
| 22 |
+
"layer_types": [
|
| 23 |
+
"full_attention",
|
| 24 |
+
"full_attention",
|
| 25 |
+
"full_attention",
|
| 26 |
+
"full_attention",
|
| 27 |
+
"full_attention",
|
| 28 |
+
"full_attention",
|
| 29 |
+
"full_attention",
|
| 30 |
+
"full_attention",
|
| 31 |
+
"full_attention",
|
| 32 |
+
"full_attention",
|
| 33 |
+
"full_attention",
|
| 34 |
+
"full_attention",
|
| 35 |
+
"full_attention",
|
| 36 |
+
"full_attention",
|
| 37 |
+
"full_attention",
|
| 38 |
+
"full_attention",
|
| 39 |
+
"full_attention",
|
| 40 |
+
"full_attention",
|
| 41 |
+
"full_attention",
|
| 42 |
+
"full_attention",
|
| 43 |
+
"full_attention",
|
| 44 |
+
"full_attention",
|
| 45 |
+
"full_attention",
|
| 46 |
+
"full_attention",
|
| 47 |
+
"full_attention",
|
| 48 |
+
"full_attention",
|
| 49 |
+
"full_attention",
|
| 50 |
+
"full_attention"
|
| 51 |
+
],
|
| 52 |
+
"max_position_embeddings": 40960,
|
| 53 |
+
"max_window_layers": 28,
|
| 54 |
+
"mm_hidden_size": 1536,
|
| 55 |
+
"mm_newline_position": "grid",
|
| 56 |
+
"mm_patch_merge_type": "flat",
|
| 57 |
+
"mm_projector_lr": 0.0001,
|
| 58 |
+
"mm_projector_type": "mlp2x_gelu",
|
| 59 |
+
"mm_resampler_type": null,
|
| 60 |
+
"mm_spatial_pool_mode": "bilinear",
|
| 61 |
+
"mm_spatial_pool_stride": null,
|
| 62 |
+
"mm_tunable_parts": "mm_mlp_adapter,mm_language_model",
|
| 63 |
+
"mm_use_im_patch_token": false,
|
| 64 |
+
"mm_use_im_start_end": false,
|
| 65 |
+
"mm_vision_select_feature": "patch",
|
| 66 |
+
"mm_vision_select_layer": -1,
|
| 67 |
+
"mm_vision_tower": "vtb_ssl:pe",
|
| 68 |
+
"mm_vision_tower_lr": null,
|
| 69 |
+
"model_type": "qwen3",
|
| 70 |
+
"num_attention_heads": 16,
|
| 71 |
+
"num_hidden_layers": 28,
|
| 72 |
+
"num_key_value_heads": 8,
|
| 73 |
+
"pad_token_id": 151643,
|
| 74 |
+
"pos_skipping_range": 4096,
|
| 75 |
+
"rms_norm_eps": 1e-06,
|
| 76 |
+
"rope_scaling": null,
|
| 77 |
+
"rope_theta": 1000000,
|
| 78 |
+
"sliding_window": null,
|
| 79 |
+
"tie_word_embeddings": true,
|
| 80 |
+
"tokenizer_model_max_length": 8192,
|
| 81 |
+
"tokenizer_padding_side": "right",
|
| 82 |
+
"transformers_version": "4.57.6",
|
| 83 |
+
"use_cache": true,
|
| 84 |
+
"use_mm_proj": true,
|
| 85 |
+
"use_pos_skipping": false,
|
| 86 |
+
"use_sliding_window": false,
|
| 87 |
+
"vision_tower_pretrained": "/cache/ckpt/download/tokenizer/continuous/pe/PE-Core-G14-448/PE-Core-G14-448.pt",
|
| 88 |
+
"vocab_size": 151936
|
| 89 |
+
}
|
continuous/qwen3/pe_core_g14_448/finetune/generation_config.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_sample": true,
|
| 3 |
+
"eos_token_id": [
|
| 4 |
+
151645,
|
| 5 |
+
151643
|
| 6 |
+
],
|
| 7 |
+
"pad_token_id": 151643,
|
| 8 |
+
"temperature": 0.6,
|
| 9 |
+
"top_k": 20,
|
| 10 |
+
"top_p": 0.95,
|
| 11 |
+
"transformers_version": "4.57.6"
|
| 12 |
+
}
|
continuous/qwen3/pe_core_g14_448/finetune/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
continuous/qwen3/pe_core_g14_448/finetune/model-00001-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e12cb2b5ff7486cf677de00b23a936cf9e3ac69ac66a0c91fbf46faf3cc14668
|
| 3 |
+
size 4975965136
|
continuous/qwen3/pe_core_g14_448/finetune/model-00002-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:94eadf0a7a823b23bb0b3555846c72c54aeb41d2e27d7487c02d03b4c2b29690
|
| 3 |
+
size 2881083008
|
continuous/qwen3/pe_core_g14_448/finetune/model.safetensors.index.json
ADDED
|
@@ -0,0 +1,941 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_parameters": 3609951744,
|
| 4 |
+
"total_size": 7856921600
|
| 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_norm.weight": "model-00001-of-00002.safetensors",
|
| 15 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 16 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 17 |
+
"model.layers.0.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 18 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 19 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 20 |
+
"model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 21 |
+
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 22 |
+
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 23 |
+
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 24 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 25 |
+
"model.layers.1.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 26 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 27 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 28 |
+
"model.layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 29 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 30 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 31 |
+
"model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 32 |
+
"model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 33 |
+
"model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 34 |
+
"model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 35 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 36 |
+
"model.layers.10.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 37 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 38 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 39 |
+
"model.layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 40 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 41 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 42 |
+
"model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 43 |
+
"model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 44 |
+
"model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 45 |
+
"model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 46 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 47 |
+
"model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 48 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 49 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 50 |
+
"model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 51 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 52 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 53 |
+
"model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 54 |
+
"model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 55 |
+
"model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 56 |
+
"model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 57 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 58 |
+
"model.layers.12.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 59 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 60 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 61 |
+
"model.layers.12.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 62 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 63 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 64 |
+
"model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 65 |
+
"model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 66 |
+
"model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 67 |
+
"model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 68 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 69 |
+
"model.layers.13.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 70 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 71 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 72 |
+
"model.layers.13.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 73 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 74 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 75 |
+
"model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 76 |
+
"model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 77 |
+
"model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 78 |
+
"model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 79 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 80 |
+
"model.layers.14.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 81 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 82 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 83 |
+
"model.layers.14.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 84 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 85 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 86 |
+
"model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 87 |
+
"model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 88 |
+
"model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 89 |
+
"model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 90 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 91 |
+
"model.layers.15.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 92 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 93 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 94 |
+
"model.layers.15.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 95 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 96 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 97 |
+
"model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 98 |
+
"model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 99 |
+
"model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 100 |
+
"model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 101 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 102 |
+
"model.layers.16.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 103 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 104 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 105 |
+
"model.layers.16.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 106 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 107 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 108 |
+
"model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 109 |
+
"model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 110 |
+
"model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 111 |
+
"model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 112 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 113 |
+
"model.layers.17.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 114 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 115 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 116 |
+
"model.layers.17.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 117 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 118 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 119 |
+
"model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 120 |
+
"model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 121 |
+
"model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 122 |
+
"model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 123 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 124 |
+
"model.layers.18.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 125 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 126 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 127 |
+
"model.layers.18.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 128 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 129 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 130 |
+
"model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 131 |
+
"model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 132 |
+
"model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 133 |
+
"model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 134 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 135 |
+
"model.layers.19.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 136 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 137 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 138 |
+
"model.layers.19.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 139 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 140 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 141 |
+
"model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 142 |
+
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 143 |
+
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 144 |
+
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 145 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 146 |
+
"model.layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 147 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 148 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 149 |
+
"model.layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 150 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 151 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 152 |
+
"model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 153 |
+
"model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 154 |
+
"model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 155 |
+
"model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 156 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 157 |
+
"model.layers.20.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 158 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 159 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 160 |
+
"model.layers.20.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 161 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 162 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 163 |
+
"model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 164 |
+
"model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 165 |
+
"model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 166 |
+
"model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 167 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 168 |
+
"model.layers.21.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 169 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 170 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 171 |
+
"model.layers.21.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 172 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 173 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 174 |
+
"model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 175 |
+
"model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 176 |
+
"model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 177 |
+
"model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 178 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 179 |
+
"model.layers.22.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 180 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 181 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 182 |
+
"model.layers.22.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 183 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 184 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 185 |
+
"model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 186 |
+
"model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 187 |
+
"model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 188 |
+
"model.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 189 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 190 |
+
"model.layers.23.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 191 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 192 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 193 |
+
"model.layers.23.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 194 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 195 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 196 |
+
"model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 197 |
+
"model.layers.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 198 |
+
"model.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 199 |
+
"model.layers.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 200 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 201 |
+
"model.layers.24.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 202 |
+
"model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 203 |
+
"model.layers.24.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 204 |
+
"model.layers.24.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 205 |
+
"model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 206 |
+
"model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 207 |
+
"model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 208 |
+
"model.layers.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 209 |
+
"model.layers.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 210 |
+
"model.layers.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 211 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 212 |
+
"model.layers.25.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 213 |
+
"model.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 214 |
+
"model.layers.25.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 215 |
+
"model.layers.25.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 216 |
+
"model.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 217 |
+
"model.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 218 |
+
"model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 219 |
+
"model.layers.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 220 |
+
"model.layers.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 221 |
+
"model.layers.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 222 |
+
"model.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 223 |
+
"model.layers.26.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 224 |
+
"model.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 225 |
+
"model.layers.26.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 226 |
+
"model.layers.26.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 227 |
+
"model.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 228 |
+
"model.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 229 |
+
"model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 230 |
+
"model.layers.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 231 |
+
"model.layers.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 232 |
+
"model.layers.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 233 |
+
"model.layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 234 |
+
"model.layers.27.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 235 |
+
"model.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 236 |
+
"model.layers.27.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 237 |
+
"model.layers.27.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 238 |
+
"model.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 239 |
+
"model.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 240 |
+
"model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 241 |
+
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 242 |
+
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 243 |
+
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 244 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 245 |
+
"model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 246 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 247 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 248 |
+
"model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 249 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 250 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 251 |
+
"model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 252 |
+
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 253 |
+
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 254 |
+
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 255 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 256 |
+
"model.layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 257 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 258 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 259 |
+
"model.layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 260 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 261 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 262 |
+
"model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 263 |
+
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 264 |
+
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 265 |
+
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 266 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 267 |
+
"model.layers.5.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 268 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 269 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 270 |
+
"model.layers.5.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 271 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 272 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 273 |
+
"model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 274 |
+
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 275 |
+
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 276 |
+
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 277 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 278 |
+
"model.layers.6.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 279 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 280 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 281 |
+
"model.layers.6.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 282 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 283 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 284 |
+
"model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 285 |
+
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 286 |
+
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 287 |
+
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 288 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 289 |
+
"model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 290 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 291 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 292 |
+
"model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 293 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 294 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 295 |
+
"model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 296 |
+
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 297 |
+
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 298 |
+
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 299 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 300 |
+
"model.layers.8.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 301 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 302 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 303 |
+
"model.layers.8.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 304 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 305 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 306 |
+
"model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 307 |
+
"model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 308 |
+
"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 309 |
+
"model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 310 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 311 |
+
"model.layers.9.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 312 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 313 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 314 |
+
"model.layers.9.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 315 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 316 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 317 |
+
"model.mm_projector.0.bias": "model-00002-of-00002.safetensors",
|
| 318 |
+
"model.mm_projector.0.weight": "model-00002-of-00002.safetensors",
|
| 319 |
+
"model.mm_projector.2.bias": "model-00002-of-00002.safetensors",
|
| 320 |
+
"model.mm_projector.2.weight": "model-00002-of-00002.safetensors",
|
| 321 |
+
"model.norm.weight": "model-00001-of-00002.safetensors",
|
| 322 |
+
"model.vision_tower.vision_tower.attn_pool.attn.in_proj_bias": "model-00002-of-00002.safetensors",
|
| 323 |
+
"model.vision_tower.vision_tower.attn_pool.attn.in_proj_weight": "model-00002-of-00002.safetensors",
|
| 324 |
+
"model.vision_tower.vision_tower.attn_pool.attn.out_proj.bias": "model-00002-of-00002.safetensors",
|
| 325 |
+
"model.vision_tower.vision_tower.attn_pool.attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 326 |
+
"model.vision_tower.vision_tower.attn_pool.layernorm.bias": "model-00002-of-00002.safetensors",
|
| 327 |
+
"model.vision_tower.vision_tower.attn_pool.layernorm.weight": "model-00002-of-00002.safetensors",
|
| 328 |
+
"model.vision_tower.vision_tower.attn_pool.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
|
| 329 |
+
"model.vision_tower.vision_tower.attn_pool.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
|
| 330 |
+
"model.vision_tower.vision_tower.attn_pool.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
|
| 331 |
+
"model.vision_tower.vision_tower.attn_pool.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
|
| 332 |
+
"model.vision_tower.vision_tower.attn_pool.probe": "model-00002-of-00002.safetensors",
|
| 333 |
+
"model.vision_tower.vision_tower.conv1.weight": "model-00001-of-00002.safetensors",
|
| 334 |
+
"model.vision_tower.vision_tower.ln_post.bias": "model-00001-of-00002.safetensors",
|
| 335 |
+
"model.vision_tower.vision_tower.ln_post.weight": "model-00001-of-00002.safetensors",
|
| 336 |
+
"model.vision_tower.vision_tower.ln_pre.bias": "model-00001-of-00002.safetensors",
|
| 337 |
+
"model.vision_tower.vision_tower.ln_pre.weight": "model-00001-of-00002.safetensors",
|
| 338 |
+
"model.vision_tower.vision_tower.positional_embedding": "model-00001-of-00002.safetensors",
|
| 339 |
+
"model.vision_tower.vision_tower.proj": "model-00001-of-00002.safetensors",
|
| 340 |
+
"model.vision_tower.vision_tower.transformer.resblocks.0.attn.in_proj_bias": "model-00001-of-00002.safetensors",
|
| 341 |
+
"model.vision_tower.vision_tower.transformer.resblocks.0.attn.in_proj_weight": "model-00001-of-00002.safetensors",
|
| 342 |
+
"model.vision_tower.vision_tower.transformer.resblocks.0.attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 343 |
+
"model.vision_tower.vision_tower.transformer.resblocks.0.attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 344 |
+
"model.vision_tower.vision_tower.transformer.resblocks.0.ln_1.bias": "model-00001-of-00002.safetensors",
|
| 345 |
+
"model.vision_tower.vision_tower.transformer.resblocks.0.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 346 |
+
"model.vision_tower.vision_tower.transformer.resblocks.0.ln_2.bias": "model-00001-of-00002.safetensors",
|
| 347 |
+
"model.vision_tower.vision_tower.transformer.resblocks.0.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 348 |
+
"model.vision_tower.vision_tower.transformer.resblocks.0.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
| 349 |
+
"model.vision_tower.vision_tower.transformer.resblocks.0.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
|
| 350 |
+
"model.vision_tower.vision_tower.transformer.resblocks.0.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 351 |
+
"model.vision_tower.vision_tower.transformer.resblocks.0.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
|
| 352 |
+
"model.vision_tower.vision_tower.transformer.resblocks.1.attn.in_proj_bias": "model-00001-of-00002.safetensors",
|
| 353 |
+
"model.vision_tower.vision_tower.transformer.resblocks.1.attn.in_proj_weight": "model-00001-of-00002.safetensors",
|
| 354 |
+
"model.vision_tower.vision_tower.transformer.resblocks.1.attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 355 |
+
"model.vision_tower.vision_tower.transformer.resblocks.1.attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 356 |
+
"model.vision_tower.vision_tower.transformer.resblocks.1.ln_1.bias": "model-00001-of-00002.safetensors",
|
| 357 |
+
"model.vision_tower.vision_tower.transformer.resblocks.1.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 358 |
+
"model.vision_tower.vision_tower.transformer.resblocks.1.ln_2.bias": "model-00001-of-00002.safetensors",
|
| 359 |
+
"model.vision_tower.vision_tower.transformer.resblocks.1.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 360 |
+
"model.vision_tower.vision_tower.transformer.resblocks.1.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
| 361 |
+
"model.vision_tower.vision_tower.transformer.resblocks.1.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
|
| 362 |
+
"model.vision_tower.vision_tower.transformer.resblocks.1.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 363 |
+
"model.vision_tower.vision_tower.transformer.resblocks.1.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
|
| 364 |
+
"model.vision_tower.vision_tower.transformer.resblocks.10.attn.in_proj_bias": "model-00001-of-00002.safetensors",
|
| 365 |
+
"model.vision_tower.vision_tower.transformer.resblocks.10.attn.in_proj_weight": "model-00001-of-00002.safetensors",
|
| 366 |
+
"model.vision_tower.vision_tower.transformer.resblocks.10.attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 367 |
+
"model.vision_tower.vision_tower.transformer.resblocks.10.attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 368 |
+
"model.vision_tower.vision_tower.transformer.resblocks.10.ln_1.bias": "model-00001-of-00002.safetensors",
|
| 369 |
+
"model.vision_tower.vision_tower.transformer.resblocks.10.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 370 |
+
"model.vision_tower.vision_tower.transformer.resblocks.10.ln_2.bias": "model-00001-of-00002.safetensors",
|
| 371 |
+
"model.vision_tower.vision_tower.transformer.resblocks.10.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 372 |
+
"model.vision_tower.vision_tower.transformer.resblocks.10.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
| 373 |
+
"model.vision_tower.vision_tower.transformer.resblocks.10.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
|
| 374 |
+
"model.vision_tower.vision_tower.transformer.resblocks.10.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 375 |
+
"model.vision_tower.vision_tower.transformer.resblocks.10.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
|
| 376 |
+
"model.vision_tower.vision_tower.transformer.resblocks.11.attn.in_proj_bias": "model-00001-of-00002.safetensors",
|
| 377 |
+
"model.vision_tower.vision_tower.transformer.resblocks.11.attn.in_proj_weight": "model-00001-of-00002.safetensors",
|
| 378 |
+
"model.vision_tower.vision_tower.transformer.resblocks.11.attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 379 |
+
"model.vision_tower.vision_tower.transformer.resblocks.11.attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 380 |
+
"model.vision_tower.vision_tower.transformer.resblocks.11.ln_1.bias": "model-00001-of-00002.safetensors",
|
| 381 |
+
"model.vision_tower.vision_tower.transformer.resblocks.11.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 382 |
+
"model.vision_tower.vision_tower.transformer.resblocks.11.ln_2.bias": "model-00001-of-00002.safetensors",
|
| 383 |
+
"model.vision_tower.vision_tower.transformer.resblocks.11.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 384 |
+
"model.vision_tower.vision_tower.transformer.resblocks.11.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
| 385 |
+
"model.vision_tower.vision_tower.transformer.resblocks.11.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
|
| 386 |
+
"model.vision_tower.vision_tower.transformer.resblocks.11.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 387 |
+
"model.vision_tower.vision_tower.transformer.resblocks.11.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
|
| 388 |
+
"model.vision_tower.vision_tower.transformer.resblocks.12.attn.in_proj_bias": "model-00001-of-00002.safetensors",
|
| 389 |
+
"model.vision_tower.vision_tower.transformer.resblocks.12.attn.in_proj_weight": "model-00001-of-00002.safetensors",
|
| 390 |
+
"model.vision_tower.vision_tower.transformer.resblocks.12.attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 391 |
+
"model.vision_tower.vision_tower.transformer.resblocks.12.attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 392 |
+
"model.vision_tower.vision_tower.transformer.resblocks.12.ln_1.bias": "model-00001-of-00002.safetensors",
|
| 393 |
+
"model.vision_tower.vision_tower.transformer.resblocks.12.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 394 |
+
"model.vision_tower.vision_tower.transformer.resblocks.12.ln_2.bias": "model-00001-of-00002.safetensors",
|
| 395 |
+
"model.vision_tower.vision_tower.transformer.resblocks.12.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 396 |
+
"model.vision_tower.vision_tower.transformer.resblocks.12.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
| 397 |
+
"model.vision_tower.vision_tower.transformer.resblocks.12.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
|
| 398 |
+
"model.vision_tower.vision_tower.transformer.resblocks.12.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 399 |
+
"model.vision_tower.vision_tower.transformer.resblocks.12.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
|
| 400 |
+
"model.vision_tower.vision_tower.transformer.resblocks.13.attn.in_proj_bias": "model-00001-of-00002.safetensors",
|
| 401 |
+
"model.vision_tower.vision_tower.transformer.resblocks.13.attn.in_proj_weight": "model-00001-of-00002.safetensors",
|
| 402 |
+
"model.vision_tower.vision_tower.transformer.resblocks.13.attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 403 |
+
"model.vision_tower.vision_tower.transformer.resblocks.13.attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 404 |
+
"model.vision_tower.vision_tower.transformer.resblocks.13.ln_1.bias": "model-00001-of-00002.safetensors",
|
| 405 |
+
"model.vision_tower.vision_tower.transformer.resblocks.13.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 406 |
+
"model.vision_tower.vision_tower.transformer.resblocks.13.ln_2.bias": "model-00001-of-00002.safetensors",
|
| 407 |
+
"model.vision_tower.vision_tower.transformer.resblocks.13.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 408 |
+
"model.vision_tower.vision_tower.transformer.resblocks.13.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
| 409 |
+
"model.vision_tower.vision_tower.transformer.resblocks.13.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
|
| 410 |
+
"model.vision_tower.vision_tower.transformer.resblocks.13.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 411 |
+
"model.vision_tower.vision_tower.transformer.resblocks.13.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
|
| 412 |
+
"model.vision_tower.vision_tower.transformer.resblocks.14.attn.in_proj_bias": "model-00001-of-00002.safetensors",
|
| 413 |
+
"model.vision_tower.vision_tower.transformer.resblocks.14.attn.in_proj_weight": "model-00001-of-00002.safetensors",
|
| 414 |
+
"model.vision_tower.vision_tower.transformer.resblocks.14.attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 415 |
+
"model.vision_tower.vision_tower.transformer.resblocks.14.attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 416 |
+
"model.vision_tower.vision_tower.transformer.resblocks.14.ln_1.bias": "model-00001-of-00002.safetensors",
|
| 417 |
+
"model.vision_tower.vision_tower.transformer.resblocks.14.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 418 |
+
"model.vision_tower.vision_tower.transformer.resblocks.14.ln_2.bias": "model-00001-of-00002.safetensors",
|
| 419 |
+
"model.vision_tower.vision_tower.transformer.resblocks.14.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 420 |
+
"model.vision_tower.vision_tower.transformer.resblocks.14.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
| 421 |
+
"model.vision_tower.vision_tower.transformer.resblocks.14.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
|
| 422 |
+
"model.vision_tower.vision_tower.transformer.resblocks.14.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 423 |
+
"model.vision_tower.vision_tower.transformer.resblocks.14.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
|
| 424 |
+
"model.vision_tower.vision_tower.transformer.resblocks.15.attn.in_proj_bias": "model-00001-of-00002.safetensors",
|
| 425 |
+
"model.vision_tower.vision_tower.transformer.resblocks.15.attn.in_proj_weight": "model-00001-of-00002.safetensors",
|
| 426 |
+
"model.vision_tower.vision_tower.transformer.resblocks.15.attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 427 |
+
"model.vision_tower.vision_tower.transformer.resblocks.15.attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 428 |
+
"model.vision_tower.vision_tower.transformer.resblocks.15.ln_1.bias": "model-00001-of-00002.safetensors",
|
| 429 |
+
"model.vision_tower.vision_tower.transformer.resblocks.15.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 430 |
+
"model.vision_tower.vision_tower.transformer.resblocks.15.ln_2.bias": "model-00001-of-00002.safetensors",
|
| 431 |
+
"model.vision_tower.vision_tower.transformer.resblocks.15.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 432 |
+
"model.vision_tower.vision_tower.transformer.resblocks.15.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
| 433 |
+
"model.vision_tower.vision_tower.transformer.resblocks.15.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
|
| 434 |
+
"model.vision_tower.vision_tower.transformer.resblocks.15.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 435 |
+
"model.vision_tower.vision_tower.transformer.resblocks.15.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
|
| 436 |
+
"model.vision_tower.vision_tower.transformer.resblocks.16.attn.in_proj_bias": "model-00001-of-00002.safetensors",
|
| 437 |
+
"model.vision_tower.vision_tower.transformer.resblocks.16.attn.in_proj_weight": "model-00001-of-00002.safetensors",
|
| 438 |
+
"model.vision_tower.vision_tower.transformer.resblocks.16.attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 439 |
+
"model.vision_tower.vision_tower.transformer.resblocks.16.attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 440 |
+
"model.vision_tower.vision_tower.transformer.resblocks.16.ln_1.bias": "model-00001-of-00002.safetensors",
|
| 441 |
+
"model.vision_tower.vision_tower.transformer.resblocks.16.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 442 |
+
"model.vision_tower.vision_tower.transformer.resblocks.16.ln_2.bias": "model-00001-of-00002.safetensors",
|
| 443 |
+
"model.vision_tower.vision_tower.transformer.resblocks.16.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 444 |
+
"model.vision_tower.vision_tower.transformer.resblocks.16.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
| 445 |
+
"model.vision_tower.vision_tower.transformer.resblocks.16.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
|
| 446 |
+
"model.vision_tower.vision_tower.transformer.resblocks.16.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 447 |
+
"model.vision_tower.vision_tower.transformer.resblocks.16.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
|
| 448 |
+
"model.vision_tower.vision_tower.transformer.resblocks.17.attn.in_proj_bias": "model-00001-of-00002.safetensors",
|
| 449 |
+
"model.vision_tower.vision_tower.transformer.resblocks.17.attn.in_proj_weight": "model-00001-of-00002.safetensors",
|
| 450 |
+
"model.vision_tower.vision_tower.transformer.resblocks.17.attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 451 |
+
"model.vision_tower.vision_tower.transformer.resblocks.17.attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 452 |
+
"model.vision_tower.vision_tower.transformer.resblocks.17.ln_1.bias": "model-00001-of-00002.safetensors",
|
| 453 |
+
"model.vision_tower.vision_tower.transformer.resblocks.17.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 454 |
+
"model.vision_tower.vision_tower.transformer.resblocks.17.ln_2.bias": "model-00001-of-00002.safetensors",
|
| 455 |
+
"model.vision_tower.vision_tower.transformer.resblocks.17.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 456 |
+
"model.vision_tower.vision_tower.transformer.resblocks.17.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
| 457 |
+
"model.vision_tower.vision_tower.transformer.resblocks.17.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
|
| 458 |
+
"model.vision_tower.vision_tower.transformer.resblocks.17.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 459 |
+
"model.vision_tower.vision_tower.transformer.resblocks.17.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
|
| 460 |
+
"model.vision_tower.vision_tower.transformer.resblocks.18.attn.in_proj_bias": "model-00001-of-00002.safetensors",
|
| 461 |
+
"model.vision_tower.vision_tower.transformer.resblocks.18.attn.in_proj_weight": "model-00001-of-00002.safetensors",
|
| 462 |
+
"model.vision_tower.vision_tower.transformer.resblocks.18.attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 463 |
+
"model.vision_tower.vision_tower.transformer.resblocks.18.attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 464 |
+
"model.vision_tower.vision_tower.transformer.resblocks.18.ln_1.bias": "model-00001-of-00002.safetensors",
|
| 465 |
+
"model.vision_tower.vision_tower.transformer.resblocks.18.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 466 |
+
"model.vision_tower.vision_tower.transformer.resblocks.18.ln_2.bias": "model-00001-of-00002.safetensors",
|
| 467 |
+
"model.vision_tower.vision_tower.transformer.resblocks.18.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 468 |
+
"model.vision_tower.vision_tower.transformer.resblocks.18.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
| 469 |
+
"model.vision_tower.vision_tower.transformer.resblocks.18.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
|
| 470 |
+
"model.vision_tower.vision_tower.transformer.resblocks.18.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 471 |
+
"model.vision_tower.vision_tower.transformer.resblocks.18.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
|
| 472 |
+
"model.vision_tower.vision_tower.transformer.resblocks.19.attn.in_proj_bias": "model-00001-of-00002.safetensors",
|
| 473 |
+
"model.vision_tower.vision_tower.transformer.resblocks.19.attn.in_proj_weight": "model-00001-of-00002.safetensors",
|
| 474 |
+
"model.vision_tower.vision_tower.transformer.resblocks.19.attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 475 |
+
"model.vision_tower.vision_tower.transformer.resblocks.19.attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 476 |
+
"model.vision_tower.vision_tower.transformer.resblocks.19.ln_1.bias": "model-00001-of-00002.safetensors",
|
| 477 |
+
"model.vision_tower.vision_tower.transformer.resblocks.19.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 478 |
+
"model.vision_tower.vision_tower.transformer.resblocks.19.ln_2.bias": "model-00001-of-00002.safetensors",
|
| 479 |
+
"model.vision_tower.vision_tower.transformer.resblocks.19.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 480 |
+
"model.vision_tower.vision_tower.transformer.resblocks.19.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
| 481 |
+
"model.vision_tower.vision_tower.transformer.resblocks.19.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
|
| 482 |
+
"model.vision_tower.vision_tower.transformer.resblocks.19.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 483 |
+
"model.vision_tower.vision_tower.transformer.resblocks.19.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
|
| 484 |
+
"model.vision_tower.vision_tower.transformer.resblocks.2.attn.in_proj_bias": "model-00001-of-00002.safetensors",
|
| 485 |
+
"model.vision_tower.vision_tower.transformer.resblocks.2.attn.in_proj_weight": "model-00001-of-00002.safetensors",
|
| 486 |
+
"model.vision_tower.vision_tower.transformer.resblocks.2.attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 487 |
+
"model.vision_tower.vision_tower.transformer.resblocks.2.attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 488 |
+
"model.vision_tower.vision_tower.transformer.resblocks.2.ln_1.bias": "model-00001-of-00002.safetensors",
|
| 489 |
+
"model.vision_tower.vision_tower.transformer.resblocks.2.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 490 |
+
"model.vision_tower.vision_tower.transformer.resblocks.2.ln_2.bias": "model-00001-of-00002.safetensors",
|
| 491 |
+
"model.vision_tower.vision_tower.transformer.resblocks.2.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 492 |
+
"model.vision_tower.vision_tower.transformer.resblocks.2.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
| 493 |
+
"model.vision_tower.vision_tower.transformer.resblocks.2.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
|
| 494 |
+
"model.vision_tower.vision_tower.transformer.resblocks.2.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 495 |
+
"model.vision_tower.vision_tower.transformer.resblocks.2.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
|
| 496 |
+
"model.vision_tower.vision_tower.transformer.resblocks.20.attn.in_proj_bias": "model-00001-of-00002.safetensors",
|
| 497 |
+
"model.vision_tower.vision_tower.transformer.resblocks.20.attn.in_proj_weight": "model-00001-of-00002.safetensors",
|
| 498 |
+
"model.vision_tower.vision_tower.transformer.resblocks.20.attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 499 |
+
"model.vision_tower.vision_tower.transformer.resblocks.20.attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 500 |
+
"model.vision_tower.vision_tower.transformer.resblocks.20.ln_1.bias": "model-00001-of-00002.safetensors",
|
| 501 |
+
"model.vision_tower.vision_tower.transformer.resblocks.20.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 502 |
+
"model.vision_tower.vision_tower.transformer.resblocks.20.ln_2.bias": "model-00001-of-00002.safetensors",
|
| 503 |
+
"model.vision_tower.vision_tower.transformer.resblocks.20.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 504 |
+
"model.vision_tower.vision_tower.transformer.resblocks.20.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
| 505 |
+
"model.vision_tower.vision_tower.transformer.resblocks.20.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
|
| 506 |
+
"model.vision_tower.vision_tower.transformer.resblocks.20.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
|
| 507 |
+
"model.vision_tower.vision_tower.transformer.resblocks.20.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
|
| 508 |
+
"model.vision_tower.vision_tower.transformer.resblocks.21.attn.in_proj_bias": "model-00002-of-00002.safetensors",
|
| 509 |
+
"model.vision_tower.vision_tower.transformer.resblocks.21.attn.in_proj_weight": "model-00002-of-00002.safetensors",
|
| 510 |
+
"model.vision_tower.vision_tower.transformer.resblocks.21.attn.out_proj.bias": "model-00002-of-00002.safetensors",
|
| 511 |
+
"model.vision_tower.vision_tower.transformer.resblocks.21.attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 512 |
+
"model.vision_tower.vision_tower.transformer.resblocks.21.ln_1.bias": "model-00002-of-00002.safetensors",
|
| 513 |
+
"model.vision_tower.vision_tower.transformer.resblocks.21.ln_1.weight": "model-00002-of-00002.safetensors",
|
| 514 |
+
"model.vision_tower.vision_tower.transformer.resblocks.21.ln_2.bias": "model-00002-of-00002.safetensors",
|
| 515 |
+
"model.vision_tower.vision_tower.transformer.resblocks.21.ln_2.weight": "model-00002-of-00002.safetensors",
|
| 516 |
+
"model.vision_tower.vision_tower.transformer.resblocks.21.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
|
| 517 |
+
"model.vision_tower.vision_tower.transformer.resblocks.21.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
|
| 518 |
+
"model.vision_tower.vision_tower.transformer.resblocks.21.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
|
| 519 |
+
"model.vision_tower.vision_tower.transformer.resblocks.21.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
|
| 520 |
+
"model.vision_tower.vision_tower.transformer.resblocks.22.attn.in_proj_bias": "model-00002-of-00002.safetensors",
|
| 521 |
+
"model.vision_tower.vision_tower.transformer.resblocks.22.attn.in_proj_weight": "model-00002-of-00002.safetensors",
|
| 522 |
+
"model.vision_tower.vision_tower.transformer.resblocks.22.attn.out_proj.bias": "model-00002-of-00002.safetensors",
|
| 523 |
+
"model.vision_tower.vision_tower.transformer.resblocks.22.attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 524 |
+
"model.vision_tower.vision_tower.transformer.resblocks.22.ln_1.bias": "model-00002-of-00002.safetensors",
|
| 525 |
+
"model.vision_tower.vision_tower.transformer.resblocks.22.ln_1.weight": "model-00002-of-00002.safetensors",
|
| 526 |
+
"model.vision_tower.vision_tower.transformer.resblocks.22.ln_2.bias": "model-00002-of-00002.safetensors",
|
| 527 |
+
"model.vision_tower.vision_tower.transformer.resblocks.22.ln_2.weight": "model-00002-of-00002.safetensors",
|
| 528 |
+
"model.vision_tower.vision_tower.transformer.resblocks.22.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
|
| 529 |
+
"model.vision_tower.vision_tower.transformer.resblocks.22.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
|
| 530 |
+
"model.vision_tower.vision_tower.transformer.resblocks.22.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
|
| 531 |
+
"model.vision_tower.vision_tower.transformer.resblocks.22.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
|
| 532 |
+
"model.vision_tower.vision_tower.transformer.resblocks.23.attn.in_proj_bias": "model-00002-of-00002.safetensors",
|
| 533 |
+
"model.vision_tower.vision_tower.transformer.resblocks.23.attn.in_proj_weight": "model-00002-of-00002.safetensors",
|
| 534 |
+
"model.vision_tower.vision_tower.transformer.resblocks.23.attn.out_proj.bias": "model-00002-of-00002.safetensors",
|
| 535 |
+
"model.vision_tower.vision_tower.transformer.resblocks.23.attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 536 |
+
"model.vision_tower.vision_tower.transformer.resblocks.23.ln_1.bias": "model-00002-of-00002.safetensors",
|
| 537 |
+
"model.vision_tower.vision_tower.transformer.resblocks.23.ln_1.weight": "model-00002-of-00002.safetensors",
|
| 538 |
+
"model.vision_tower.vision_tower.transformer.resblocks.23.ln_2.bias": "model-00002-of-00002.safetensors",
|
| 539 |
+
"model.vision_tower.vision_tower.transformer.resblocks.23.ln_2.weight": "model-00002-of-00002.safetensors",
|
| 540 |
+
"model.vision_tower.vision_tower.transformer.resblocks.23.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
|
| 541 |
+
"model.vision_tower.vision_tower.transformer.resblocks.23.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
|
| 542 |
+
"model.vision_tower.vision_tower.transformer.resblocks.23.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
|
| 543 |
+
"model.vision_tower.vision_tower.transformer.resblocks.23.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
|
| 544 |
+
"model.vision_tower.vision_tower.transformer.resblocks.24.attn.in_proj_bias": "model-00002-of-00002.safetensors",
|
| 545 |
+
"model.vision_tower.vision_tower.transformer.resblocks.24.attn.in_proj_weight": "model-00002-of-00002.safetensors",
|
| 546 |
+
"model.vision_tower.vision_tower.transformer.resblocks.24.attn.out_proj.bias": "model-00002-of-00002.safetensors",
|
| 547 |
+
"model.vision_tower.vision_tower.transformer.resblocks.24.attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 548 |
+
"model.vision_tower.vision_tower.transformer.resblocks.24.ln_1.bias": "model-00002-of-00002.safetensors",
|
| 549 |
+
"model.vision_tower.vision_tower.transformer.resblocks.24.ln_1.weight": "model-00002-of-00002.safetensors",
|
| 550 |
+
"model.vision_tower.vision_tower.transformer.resblocks.24.ln_2.bias": "model-00002-of-00002.safetensors",
|
| 551 |
+
"model.vision_tower.vision_tower.transformer.resblocks.24.ln_2.weight": "model-00002-of-00002.safetensors",
|
| 552 |
+
"model.vision_tower.vision_tower.transformer.resblocks.24.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
|
| 553 |
+
"model.vision_tower.vision_tower.transformer.resblocks.24.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
|
| 554 |
+
"model.vision_tower.vision_tower.transformer.resblocks.24.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
|
| 555 |
+
"model.vision_tower.vision_tower.transformer.resblocks.24.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
|
| 556 |
+
"model.vision_tower.vision_tower.transformer.resblocks.25.attn.in_proj_bias": "model-00002-of-00002.safetensors",
|
| 557 |
+
"model.vision_tower.vision_tower.transformer.resblocks.25.attn.in_proj_weight": "model-00002-of-00002.safetensors",
|
| 558 |
+
"model.vision_tower.vision_tower.transformer.resblocks.25.attn.out_proj.bias": "model-00002-of-00002.safetensors",
|
| 559 |
+
"model.vision_tower.vision_tower.transformer.resblocks.25.attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 560 |
+
"model.vision_tower.vision_tower.transformer.resblocks.25.ln_1.bias": "model-00002-of-00002.safetensors",
|
| 561 |
+
"model.vision_tower.vision_tower.transformer.resblocks.25.ln_1.weight": "model-00002-of-00002.safetensors",
|
| 562 |
+
"model.vision_tower.vision_tower.transformer.resblocks.25.ln_2.bias": "model-00002-of-00002.safetensors",
|
| 563 |
+
"model.vision_tower.vision_tower.transformer.resblocks.25.ln_2.weight": "model-00002-of-00002.safetensors",
|
| 564 |
+
"model.vision_tower.vision_tower.transformer.resblocks.25.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
|
| 565 |
+
"model.vision_tower.vision_tower.transformer.resblocks.25.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
|
| 566 |
+
"model.vision_tower.vision_tower.transformer.resblocks.25.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
|
| 567 |
+
"model.vision_tower.vision_tower.transformer.resblocks.25.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
|
| 568 |
+
"model.vision_tower.vision_tower.transformer.resblocks.26.attn.in_proj_bias": "model-00002-of-00002.safetensors",
|
| 569 |
+
"model.vision_tower.vision_tower.transformer.resblocks.26.attn.in_proj_weight": "model-00002-of-00002.safetensors",
|
| 570 |
+
"model.vision_tower.vision_tower.transformer.resblocks.26.attn.out_proj.bias": "model-00002-of-00002.safetensors",
|
| 571 |
+
"model.vision_tower.vision_tower.transformer.resblocks.26.attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 572 |
+
"model.vision_tower.vision_tower.transformer.resblocks.26.ln_1.bias": "model-00002-of-00002.safetensors",
|
| 573 |
+
"model.vision_tower.vision_tower.transformer.resblocks.26.ln_1.weight": "model-00002-of-00002.safetensors",
|
| 574 |
+
"model.vision_tower.vision_tower.transformer.resblocks.26.ln_2.bias": "model-00002-of-00002.safetensors",
|
| 575 |
+
"model.vision_tower.vision_tower.transformer.resblocks.26.ln_2.weight": "model-00002-of-00002.safetensors",
|
| 576 |
+
"model.vision_tower.vision_tower.transformer.resblocks.26.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
|
| 577 |
+
"model.vision_tower.vision_tower.transformer.resblocks.26.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
|
| 578 |
+
"model.vision_tower.vision_tower.transformer.resblocks.26.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
|
| 579 |
+
"model.vision_tower.vision_tower.transformer.resblocks.26.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
|
| 580 |
+
"model.vision_tower.vision_tower.transformer.resblocks.27.attn.in_proj_bias": "model-00002-of-00002.safetensors",
|
| 581 |
+
"model.vision_tower.vision_tower.transformer.resblocks.27.attn.in_proj_weight": "model-00002-of-00002.safetensors",
|
| 582 |
+
"model.vision_tower.vision_tower.transformer.resblocks.27.attn.out_proj.bias": "model-00002-of-00002.safetensors",
|
| 583 |
+
"model.vision_tower.vision_tower.transformer.resblocks.27.attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 584 |
+
"model.vision_tower.vision_tower.transformer.resblocks.27.ln_1.bias": "model-00002-of-00002.safetensors",
|
| 585 |
+
"model.vision_tower.vision_tower.transformer.resblocks.27.ln_1.weight": "model-00002-of-00002.safetensors",
|
| 586 |
+
"model.vision_tower.vision_tower.transformer.resblocks.27.ln_2.bias": "model-00002-of-00002.safetensors",
|
| 587 |
+
"model.vision_tower.vision_tower.transformer.resblocks.27.ln_2.weight": "model-00002-of-00002.safetensors",
|
| 588 |
+
"model.vision_tower.vision_tower.transformer.resblocks.27.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
|
| 589 |
+
"model.vision_tower.vision_tower.transformer.resblocks.27.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
|
| 590 |
+
"model.vision_tower.vision_tower.transformer.resblocks.27.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
|
| 591 |
+
"model.vision_tower.vision_tower.transformer.resblocks.27.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
|
| 592 |
+
"model.vision_tower.vision_tower.transformer.resblocks.28.attn.in_proj_bias": "model-00002-of-00002.safetensors",
|
| 593 |
+
"model.vision_tower.vision_tower.transformer.resblocks.28.attn.in_proj_weight": "model-00002-of-00002.safetensors",
|
| 594 |
+
"model.vision_tower.vision_tower.transformer.resblocks.28.attn.out_proj.bias": "model-00002-of-00002.safetensors",
|
| 595 |
+
"model.vision_tower.vision_tower.transformer.resblocks.28.attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 596 |
+
"model.vision_tower.vision_tower.transformer.resblocks.28.ln_1.bias": "model-00002-of-00002.safetensors",
|
| 597 |
+
"model.vision_tower.vision_tower.transformer.resblocks.28.ln_1.weight": "model-00002-of-00002.safetensors",
|
| 598 |
+
"model.vision_tower.vision_tower.transformer.resblocks.28.ln_2.bias": "model-00002-of-00002.safetensors",
|
| 599 |
+
"model.vision_tower.vision_tower.transformer.resblocks.28.ln_2.weight": "model-00002-of-00002.safetensors",
|
| 600 |
+
"model.vision_tower.vision_tower.transformer.resblocks.28.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
|
| 601 |
+
"model.vision_tower.vision_tower.transformer.resblocks.28.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
|
| 602 |
+
"model.vision_tower.vision_tower.transformer.resblocks.28.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
|
| 603 |
+
"model.vision_tower.vision_tower.transformer.resblocks.28.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
|
| 604 |
+
"model.vision_tower.vision_tower.transformer.resblocks.29.attn.in_proj_bias": "model-00002-of-00002.safetensors",
|
| 605 |
+
"model.vision_tower.vision_tower.transformer.resblocks.29.attn.in_proj_weight": "model-00002-of-00002.safetensors",
|
| 606 |
+
"model.vision_tower.vision_tower.transformer.resblocks.29.attn.out_proj.bias": "model-00002-of-00002.safetensors",
|
| 607 |
+
"model.vision_tower.vision_tower.transformer.resblocks.29.attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 608 |
+
"model.vision_tower.vision_tower.transformer.resblocks.29.ln_1.bias": "model-00002-of-00002.safetensors",
|
| 609 |
+
"model.vision_tower.vision_tower.transformer.resblocks.29.ln_1.weight": "model-00002-of-00002.safetensors",
|
| 610 |
+
"model.vision_tower.vision_tower.transformer.resblocks.29.ln_2.bias": "model-00002-of-00002.safetensors",
|
| 611 |
+
"model.vision_tower.vision_tower.transformer.resblocks.29.ln_2.weight": "model-00002-of-00002.safetensors",
|
| 612 |
+
"model.vision_tower.vision_tower.transformer.resblocks.29.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
|
| 613 |
+
"model.vision_tower.vision_tower.transformer.resblocks.29.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
|
| 614 |
+
"model.vision_tower.vision_tower.transformer.resblocks.29.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
|
| 615 |
+
"model.vision_tower.vision_tower.transformer.resblocks.29.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
|
| 616 |
+
"model.vision_tower.vision_tower.transformer.resblocks.3.attn.in_proj_bias": "model-00001-of-00002.safetensors",
|
| 617 |
+
"model.vision_tower.vision_tower.transformer.resblocks.3.attn.in_proj_weight": "model-00001-of-00002.safetensors",
|
| 618 |
+
"model.vision_tower.vision_tower.transformer.resblocks.3.attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 619 |
+
"model.vision_tower.vision_tower.transformer.resblocks.3.attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 620 |
+
"model.vision_tower.vision_tower.transformer.resblocks.3.ln_1.bias": "model-00001-of-00002.safetensors",
|
| 621 |
+
"model.vision_tower.vision_tower.transformer.resblocks.3.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 622 |
+
"model.vision_tower.vision_tower.transformer.resblocks.3.ln_2.bias": "model-00001-of-00002.safetensors",
|
| 623 |
+
"model.vision_tower.vision_tower.transformer.resblocks.3.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 624 |
+
"model.vision_tower.vision_tower.transformer.resblocks.3.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
| 625 |
+
"model.vision_tower.vision_tower.transformer.resblocks.3.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
|
| 626 |
+
"model.vision_tower.vision_tower.transformer.resblocks.3.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 627 |
+
"model.vision_tower.vision_tower.transformer.resblocks.3.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
|
| 628 |
+
"model.vision_tower.vision_tower.transformer.resblocks.30.attn.in_proj_bias": "model-00002-of-00002.safetensors",
|
| 629 |
+
"model.vision_tower.vision_tower.transformer.resblocks.30.attn.in_proj_weight": "model-00002-of-00002.safetensors",
|
| 630 |
+
"model.vision_tower.vision_tower.transformer.resblocks.30.attn.out_proj.bias": "model-00002-of-00002.safetensors",
|
| 631 |
+
"model.vision_tower.vision_tower.transformer.resblocks.30.attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 632 |
+
"model.vision_tower.vision_tower.transformer.resblocks.30.ln_1.bias": "model-00002-of-00002.safetensors",
|
| 633 |
+
"model.vision_tower.vision_tower.transformer.resblocks.30.ln_1.weight": "model-00002-of-00002.safetensors",
|
| 634 |
+
"model.vision_tower.vision_tower.transformer.resblocks.30.ln_2.bias": "model-00002-of-00002.safetensors",
|
| 635 |
+
"model.vision_tower.vision_tower.transformer.resblocks.30.ln_2.weight": "model-00002-of-00002.safetensors",
|
| 636 |
+
"model.vision_tower.vision_tower.transformer.resblocks.30.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
|
| 637 |
+
"model.vision_tower.vision_tower.transformer.resblocks.30.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
|
| 638 |
+
"model.vision_tower.vision_tower.transformer.resblocks.30.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
|
| 639 |
+
"model.vision_tower.vision_tower.transformer.resblocks.30.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
|
| 640 |
+
"model.vision_tower.vision_tower.transformer.resblocks.31.attn.in_proj_bias": "model-00002-of-00002.safetensors",
|
| 641 |
+
"model.vision_tower.vision_tower.transformer.resblocks.31.attn.in_proj_weight": "model-00002-of-00002.safetensors",
|
| 642 |
+
"model.vision_tower.vision_tower.transformer.resblocks.31.attn.out_proj.bias": "model-00002-of-00002.safetensors",
|
| 643 |
+
"model.vision_tower.vision_tower.transformer.resblocks.31.attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 644 |
+
"model.vision_tower.vision_tower.transformer.resblocks.31.ln_1.bias": "model-00002-of-00002.safetensors",
|
| 645 |
+
"model.vision_tower.vision_tower.transformer.resblocks.31.ln_1.weight": "model-00002-of-00002.safetensors",
|
| 646 |
+
"model.vision_tower.vision_tower.transformer.resblocks.31.ln_2.bias": "model-00002-of-00002.safetensors",
|
| 647 |
+
"model.vision_tower.vision_tower.transformer.resblocks.31.ln_2.weight": "model-00002-of-00002.safetensors",
|
| 648 |
+
"model.vision_tower.vision_tower.transformer.resblocks.31.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
|
| 649 |
+
"model.vision_tower.vision_tower.transformer.resblocks.31.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
|
| 650 |
+
"model.vision_tower.vision_tower.transformer.resblocks.31.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
|
| 651 |
+
"model.vision_tower.vision_tower.transformer.resblocks.31.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
|
| 652 |
+
"model.vision_tower.vision_tower.transformer.resblocks.32.attn.in_proj_bias": "model-00002-of-00002.safetensors",
|
| 653 |
+
"model.vision_tower.vision_tower.transformer.resblocks.32.attn.in_proj_weight": "model-00002-of-00002.safetensors",
|
| 654 |
+
"model.vision_tower.vision_tower.transformer.resblocks.32.attn.out_proj.bias": "model-00002-of-00002.safetensors",
|
| 655 |
+
"model.vision_tower.vision_tower.transformer.resblocks.32.attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 656 |
+
"model.vision_tower.vision_tower.transformer.resblocks.32.ln_1.bias": "model-00002-of-00002.safetensors",
|
| 657 |
+
"model.vision_tower.vision_tower.transformer.resblocks.32.ln_1.weight": "model-00002-of-00002.safetensors",
|
| 658 |
+
"model.vision_tower.vision_tower.transformer.resblocks.32.ln_2.bias": "model-00002-of-00002.safetensors",
|
| 659 |
+
"model.vision_tower.vision_tower.transformer.resblocks.32.ln_2.weight": "model-00002-of-00002.safetensors",
|
| 660 |
+
"model.vision_tower.vision_tower.transformer.resblocks.32.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
|
| 661 |
+
"model.vision_tower.vision_tower.transformer.resblocks.32.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
|
| 662 |
+
"model.vision_tower.vision_tower.transformer.resblocks.32.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
|
| 663 |
+
"model.vision_tower.vision_tower.transformer.resblocks.32.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
|
| 664 |
+
"model.vision_tower.vision_tower.transformer.resblocks.33.attn.in_proj_bias": "model-00002-of-00002.safetensors",
|
| 665 |
+
"model.vision_tower.vision_tower.transformer.resblocks.33.attn.in_proj_weight": "model-00002-of-00002.safetensors",
|
| 666 |
+
"model.vision_tower.vision_tower.transformer.resblocks.33.attn.out_proj.bias": "model-00002-of-00002.safetensors",
|
| 667 |
+
"model.vision_tower.vision_tower.transformer.resblocks.33.attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 668 |
+
"model.vision_tower.vision_tower.transformer.resblocks.33.ln_1.bias": "model-00002-of-00002.safetensors",
|
| 669 |
+
"model.vision_tower.vision_tower.transformer.resblocks.33.ln_1.weight": "model-00002-of-00002.safetensors",
|
| 670 |
+
"model.vision_tower.vision_tower.transformer.resblocks.33.ln_2.bias": "model-00002-of-00002.safetensors",
|
| 671 |
+
"model.vision_tower.vision_tower.transformer.resblocks.33.ln_2.weight": "model-00002-of-00002.safetensors",
|
| 672 |
+
"model.vision_tower.vision_tower.transformer.resblocks.33.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
|
| 673 |
+
"model.vision_tower.vision_tower.transformer.resblocks.33.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
|
| 674 |
+
"model.vision_tower.vision_tower.transformer.resblocks.33.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
|
| 675 |
+
"model.vision_tower.vision_tower.transformer.resblocks.33.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
|
| 676 |
+
"model.vision_tower.vision_tower.transformer.resblocks.34.attn.in_proj_bias": "model-00002-of-00002.safetensors",
|
| 677 |
+
"model.vision_tower.vision_tower.transformer.resblocks.34.attn.in_proj_weight": "model-00002-of-00002.safetensors",
|
| 678 |
+
"model.vision_tower.vision_tower.transformer.resblocks.34.attn.out_proj.bias": "model-00002-of-00002.safetensors",
|
| 679 |
+
"model.vision_tower.vision_tower.transformer.resblocks.34.attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 680 |
+
"model.vision_tower.vision_tower.transformer.resblocks.34.ln_1.bias": "model-00002-of-00002.safetensors",
|
| 681 |
+
"model.vision_tower.vision_tower.transformer.resblocks.34.ln_1.weight": "model-00002-of-00002.safetensors",
|
| 682 |
+
"model.vision_tower.vision_tower.transformer.resblocks.34.ln_2.bias": "model-00002-of-00002.safetensors",
|
| 683 |
+
"model.vision_tower.vision_tower.transformer.resblocks.34.ln_2.weight": "model-00002-of-00002.safetensors",
|
| 684 |
+
"model.vision_tower.vision_tower.transformer.resblocks.34.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
|
| 685 |
+
"model.vision_tower.vision_tower.transformer.resblocks.34.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
|
| 686 |
+
"model.vision_tower.vision_tower.transformer.resblocks.34.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
|
| 687 |
+
"model.vision_tower.vision_tower.transformer.resblocks.34.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
|
| 688 |
+
"model.vision_tower.vision_tower.transformer.resblocks.35.attn.in_proj_bias": "model-00002-of-00002.safetensors",
|
| 689 |
+
"model.vision_tower.vision_tower.transformer.resblocks.35.attn.in_proj_weight": "model-00002-of-00002.safetensors",
|
| 690 |
+
"model.vision_tower.vision_tower.transformer.resblocks.35.attn.out_proj.bias": "model-00002-of-00002.safetensors",
|
| 691 |
+
"model.vision_tower.vision_tower.transformer.resblocks.35.attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 692 |
+
"model.vision_tower.vision_tower.transformer.resblocks.35.ln_1.bias": "model-00002-of-00002.safetensors",
|
| 693 |
+
"model.vision_tower.vision_tower.transformer.resblocks.35.ln_1.weight": "model-00002-of-00002.safetensors",
|
| 694 |
+
"model.vision_tower.vision_tower.transformer.resblocks.35.ln_2.bias": "model-00002-of-00002.safetensors",
|
| 695 |
+
"model.vision_tower.vision_tower.transformer.resblocks.35.ln_2.weight": "model-00002-of-00002.safetensors",
|
| 696 |
+
"model.vision_tower.vision_tower.transformer.resblocks.35.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
|
| 697 |
+
"model.vision_tower.vision_tower.transformer.resblocks.35.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
|
| 698 |
+
"model.vision_tower.vision_tower.transformer.resblocks.35.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
|
| 699 |
+
"model.vision_tower.vision_tower.transformer.resblocks.35.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
|
| 700 |
+
"model.vision_tower.vision_tower.transformer.resblocks.36.attn.in_proj_bias": "model-00002-of-00002.safetensors",
|
| 701 |
+
"model.vision_tower.vision_tower.transformer.resblocks.36.attn.in_proj_weight": "model-00002-of-00002.safetensors",
|
| 702 |
+
"model.vision_tower.vision_tower.transformer.resblocks.36.attn.out_proj.bias": "model-00002-of-00002.safetensors",
|
| 703 |
+
"model.vision_tower.vision_tower.transformer.resblocks.36.attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 704 |
+
"model.vision_tower.vision_tower.transformer.resblocks.36.ln_1.bias": "model-00002-of-00002.safetensors",
|
| 705 |
+
"model.vision_tower.vision_tower.transformer.resblocks.36.ln_1.weight": "model-00002-of-00002.safetensors",
|
| 706 |
+
"model.vision_tower.vision_tower.transformer.resblocks.36.ln_2.bias": "model-00002-of-00002.safetensors",
|
| 707 |
+
"model.vision_tower.vision_tower.transformer.resblocks.36.ln_2.weight": "model-00002-of-00002.safetensors",
|
| 708 |
+
"model.vision_tower.vision_tower.transformer.resblocks.36.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
|
| 709 |
+
"model.vision_tower.vision_tower.transformer.resblocks.36.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
|
| 710 |
+
"model.vision_tower.vision_tower.transformer.resblocks.36.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
|
| 711 |
+
"model.vision_tower.vision_tower.transformer.resblocks.36.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
|
| 712 |
+
"model.vision_tower.vision_tower.transformer.resblocks.37.attn.in_proj_bias": "model-00002-of-00002.safetensors",
|
| 713 |
+
"model.vision_tower.vision_tower.transformer.resblocks.37.attn.in_proj_weight": "model-00002-of-00002.safetensors",
|
| 714 |
+
"model.vision_tower.vision_tower.transformer.resblocks.37.attn.out_proj.bias": "model-00002-of-00002.safetensors",
|
| 715 |
+
"model.vision_tower.vision_tower.transformer.resblocks.37.attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 716 |
+
"model.vision_tower.vision_tower.transformer.resblocks.37.ln_1.bias": "model-00002-of-00002.safetensors",
|
| 717 |
+
"model.vision_tower.vision_tower.transformer.resblocks.37.ln_1.weight": "model-00002-of-00002.safetensors",
|
| 718 |
+
"model.vision_tower.vision_tower.transformer.resblocks.37.ln_2.bias": "model-00002-of-00002.safetensors",
|
| 719 |
+
"model.vision_tower.vision_tower.transformer.resblocks.37.ln_2.weight": "model-00002-of-00002.safetensors",
|
| 720 |
+
"model.vision_tower.vision_tower.transformer.resblocks.37.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
|
| 721 |
+
"model.vision_tower.vision_tower.transformer.resblocks.37.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
|
| 722 |
+
"model.vision_tower.vision_tower.transformer.resblocks.37.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
|
| 723 |
+
"model.vision_tower.vision_tower.transformer.resblocks.37.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
|
| 724 |
+
"model.vision_tower.vision_tower.transformer.resblocks.38.attn.in_proj_bias": "model-00002-of-00002.safetensors",
|
| 725 |
+
"model.vision_tower.vision_tower.transformer.resblocks.38.attn.in_proj_weight": "model-00002-of-00002.safetensors",
|
| 726 |
+
"model.vision_tower.vision_tower.transformer.resblocks.38.attn.out_proj.bias": "model-00002-of-00002.safetensors",
|
| 727 |
+
"model.vision_tower.vision_tower.transformer.resblocks.38.attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 728 |
+
"model.vision_tower.vision_tower.transformer.resblocks.38.ln_1.bias": "model-00002-of-00002.safetensors",
|
| 729 |
+
"model.vision_tower.vision_tower.transformer.resblocks.38.ln_1.weight": "model-00002-of-00002.safetensors",
|
| 730 |
+
"model.vision_tower.vision_tower.transformer.resblocks.38.ln_2.bias": "model-00002-of-00002.safetensors",
|
| 731 |
+
"model.vision_tower.vision_tower.transformer.resblocks.38.ln_2.weight": "model-00002-of-00002.safetensors",
|
| 732 |
+
"model.vision_tower.vision_tower.transformer.resblocks.38.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
|
| 733 |
+
"model.vision_tower.vision_tower.transformer.resblocks.38.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
|
| 734 |
+
"model.vision_tower.vision_tower.transformer.resblocks.38.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
|
| 735 |
+
"model.vision_tower.vision_tower.transformer.resblocks.38.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
|
| 736 |
+
"model.vision_tower.vision_tower.transformer.resblocks.39.attn.in_proj_bias": "model-00002-of-00002.safetensors",
|
| 737 |
+
"model.vision_tower.vision_tower.transformer.resblocks.39.attn.in_proj_weight": "model-00002-of-00002.safetensors",
|
| 738 |
+
"model.vision_tower.vision_tower.transformer.resblocks.39.attn.out_proj.bias": "model-00002-of-00002.safetensors",
|
| 739 |
+
"model.vision_tower.vision_tower.transformer.resblocks.39.attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 740 |
+
"model.vision_tower.vision_tower.transformer.resblocks.39.ln_1.bias": "model-00002-of-00002.safetensors",
|
| 741 |
+
"model.vision_tower.vision_tower.transformer.resblocks.39.ln_1.weight": "model-00002-of-00002.safetensors",
|
| 742 |
+
"model.vision_tower.vision_tower.transformer.resblocks.39.ln_2.bias": "model-00002-of-00002.safetensors",
|
| 743 |
+
"model.vision_tower.vision_tower.transformer.resblocks.39.ln_2.weight": "model-00002-of-00002.safetensors",
|
| 744 |
+
"model.vision_tower.vision_tower.transformer.resblocks.39.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
|
| 745 |
+
"model.vision_tower.vision_tower.transformer.resblocks.39.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
|
| 746 |
+
"model.vision_tower.vision_tower.transformer.resblocks.39.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
|
| 747 |
+
"model.vision_tower.vision_tower.transformer.resblocks.39.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
|
| 748 |
+
"model.vision_tower.vision_tower.transformer.resblocks.4.attn.in_proj_bias": "model-00001-of-00002.safetensors",
|
| 749 |
+
"model.vision_tower.vision_tower.transformer.resblocks.4.attn.in_proj_weight": "model-00001-of-00002.safetensors",
|
| 750 |
+
"model.vision_tower.vision_tower.transformer.resblocks.4.attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 751 |
+
"model.vision_tower.vision_tower.transformer.resblocks.4.attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 752 |
+
"model.vision_tower.vision_tower.transformer.resblocks.4.ln_1.bias": "model-00001-of-00002.safetensors",
|
| 753 |
+
"model.vision_tower.vision_tower.transformer.resblocks.4.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 754 |
+
"model.vision_tower.vision_tower.transformer.resblocks.4.ln_2.bias": "model-00001-of-00002.safetensors",
|
| 755 |
+
"model.vision_tower.vision_tower.transformer.resblocks.4.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 756 |
+
"model.vision_tower.vision_tower.transformer.resblocks.4.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
| 757 |
+
"model.vision_tower.vision_tower.transformer.resblocks.4.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
|
| 758 |
+
"model.vision_tower.vision_tower.transformer.resblocks.4.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 759 |
+
"model.vision_tower.vision_tower.transformer.resblocks.4.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
|
| 760 |
+
"model.vision_tower.vision_tower.transformer.resblocks.40.attn.in_proj_bias": "model-00002-of-00002.safetensors",
|
| 761 |
+
"model.vision_tower.vision_tower.transformer.resblocks.40.attn.in_proj_weight": "model-00002-of-00002.safetensors",
|
| 762 |
+
"model.vision_tower.vision_tower.transformer.resblocks.40.attn.out_proj.bias": "model-00002-of-00002.safetensors",
|
| 763 |
+
"model.vision_tower.vision_tower.transformer.resblocks.40.attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 764 |
+
"model.vision_tower.vision_tower.transformer.resblocks.40.ln_1.bias": "model-00002-of-00002.safetensors",
|
| 765 |
+
"model.vision_tower.vision_tower.transformer.resblocks.40.ln_1.weight": "model-00002-of-00002.safetensors",
|
| 766 |
+
"model.vision_tower.vision_tower.transformer.resblocks.40.ln_2.bias": "model-00002-of-00002.safetensors",
|
| 767 |
+
"model.vision_tower.vision_tower.transformer.resblocks.40.ln_2.weight": "model-00002-of-00002.safetensors",
|
| 768 |
+
"model.vision_tower.vision_tower.transformer.resblocks.40.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
|
| 769 |
+
"model.vision_tower.vision_tower.transformer.resblocks.40.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
|
| 770 |
+
"model.vision_tower.vision_tower.transformer.resblocks.40.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
|
| 771 |
+
"model.vision_tower.vision_tower.transformer.resblocks.40.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
|
| 772 |
+
"model.vision_tower.vision_tower.transformer.resblocks.41.attn.in_proj_bias": "model-00002-of-00002.safetensors",
|
| 773 |
+
"model.vision_tower.vision_tower.transformer.resblocks.41.attn.in_proj_weight": "model-00002-of-00002.safetensors",
|
| 774 |
+
"model.vision_tower.vision_tower.transformer.resblocks.41.attn.out_proj.bias": "model-00002-of-00002.safetensors",
|
| 775 |
+
"model.vision_tower.vision_tower.transformer.resblocks.41.attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 776 |
+
"model.vision_tower.vision_tower.transformer.resblocks.41.ln_1.bias": "model-00002-of-00002.safetensors",
|
| 777 |
+
"model.vision_tower.vision_tower.transformer.resblocks.41.ln_1.weight": "model-00002-of-00002.safetensors",
|
| 778 |
+
"model.vision_tower.vision_tower.transformer.resblocks.41.ln_2.bias": "model-00002-of-00002.safetensors",
|
| 779 |
+
"model.vision_tower.vision_tower.transformer.resblocks.41.ln_2.weight": "model-00002-of-00002.safetensors",
|
| 780 |
+
"model.vision_tower.vision_tower.transformer.resblocks.41.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
|
| 781 |
+
"model.vision_tower.vision_tower.transformer.resblocks.41.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
|
| 782 |
+
"model.vision_tower.vision_tower.transformer.resblocks.41.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
|
| 783 |
+
"model.vision_tower.vision_tower.transformer.resblocks.41.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
|
| 784 |
+
"model.vision_tower.vision_tower.transformer.resblocks.42.attn.in_proj_bias": "model-00002-of-00002.safetensors",
|
| 785 |
+
"model.vision_tower.vision_tower.transformer.resblocks.42.attn.in_proj_weight": "model-00002-of-00002.safetensors",
|
| 786 |
+
"model.vision_tower.vision_tower.transformer.resblocks.42.attn.out_proj.bias": "model-00002-of-00002.safetensors",
|
| 787 |
+
"model.vision_tower.vision_tower.transformer.resblocks.42.attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 788 |
+
"model.vision_tower.vision_tower.transformer.resblocks.42.ln_1.bias": "model-00002-of-00002.safetensors",
|
| 789 |
+
"model.vision_tower.vision_tower.transformer.resblocks.42.ln_1.weight": "model-00002-of-00002.safetensors",
|
| 790 |
+
"model.vision_tower.vision_tower.transformer.resblocks.42.ln_2.bias": "model-00002-of-00002.safetensors",
|
| 791 |
+
"model.vision_tower.vision_tower.transformer.resblocks.42.ln_2.weight": "model-00002-of-00002.safetensors",
|
| 792 |
+
"model.vision_tower.vision_tower.transformer.resblocks.42.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
|
| 793 |
+
"model.vision_tower.vision_tower.transformer.resblocks.42.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
|
| 794 |
+
"model.vision_tower.vision_tower.transformer.resblocks.42.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
|
| 795 |
+
"model.vision_tower.vision_tower.transformer.resblocks.42.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
|
| 796 |
+
"model.vision_tower.vision_tower.transformer.resblocks.43.attn.in_proj_bias": "model-00002-of-00002.safetensors",
|
| 797 |
+
"model.vision_tower.vision_tower.transformer.resblocks.43.attn.in_proj_weight": "model-00002-of-00002.safetensors",
|
| 798 |
+
"model.vision_tower.vision_tower.transformer.resblocks.43.attn.out_proj.bias": "model-00002-of-00002.safetensors",
|
| 799 |
+
"model.vision_tower.vision_tower.transformer.resblocks.43.attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 800 |
+
"model.vision_tower.vision_tower.transformer.resblocks.43.ln_1.bias": "model-00002-of-00002.safetensors",
|
| 801 |
+
"model.vision_tower.vision_tower.transformer.resblocks.43.ln_1.weight": "model-00002-of-00002.safetensors",
|
| 802 |
+
"model.vision_tower.vision_tower.transformer.resblocks.43.ln_2.bias": "model-00002-of-00002.safetensors",
|
| 803 |
+
"model.vision_tower.vision_tower.transformer.resblocks.43.ln_2.weight": "model-00002-of-00002.safetensors",
|
| 804 |
+
"model.vision_tower.vision_tower.transformer.resblocks.43.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
|
| 805 |
+
"model.vision_tower.vision_tower.transformer.resblocks.43.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
|
| 806 |
+
"model.vision_tower.vision_tower.transformer.resblocks.43.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
|
| 807 |
+
"model.vision_tower.vision_tower.transformer.resblocks.43.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
|
| 808 |
+
"model.vision_tower.vision_tower.transformer.resblocks.44.attn.in_proj_bias": "model-00002-of-00002.safetensors",
|
| 809 |
+
"model.vision_tower.vision_tower.transformer.resblocks.44.attn.in_proj_weight": "model-00002-of-00002.safetensors",
|
| 810 |
+
"model.vision_tower.vision_tower.transformer.resblocks.44.attn.out_proj.bias": "model-00002-of-00002.safetensors",
|
| 811 |
+
"model.vision_tower.vision_tower.transformer.resblocks.44.attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 812 |
+
"model.vision_tower.vision_tower.transformer.resblocks.44.ln_1.bias": "model-00002-of-00002.safetensors",
|
| 813 |
+
"model.vision_tower.vision_tower.transformer.resblocks.44.ln_1.weight": "model-00002-of-00002.safetensors",
|
| 814 |
+
"model.vision_tower.vision_tower.transformer.resblocks.44.ln_2.bias": "model-00002-of-00002.safetensors",
|
| 815 |
+
"model.vision_tower.vision_tower.transformer.resblocks.44.ln_2.weight": "model-00002-of-00002.safetensors",
|
| 816 |
+
"model.vision_tower.vision_tower.transformer.resblocks.44.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
|
| 817 |
+
"model.vision_tower.vision_tower.transformer.resblocks.44.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
|
| 818 |
+
"model.vision_tower.vision_tower.transformer.resblocks.44.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
|
| 819 |
+
"model.vision_tower.vision_tower.transformer.resblocks.44.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
|
| 820 |
+
"model.vision_tower.vision_tower.transformer.resblocks.45.attn.in_proj_bias": "model-00002-of-00002.safetensors",
|
| 821 |
+
"model.vision_tower.vision_tower.transformer.resblocks.45.attn.in_proj_weight": "model-00002-of-00002.safetensors",
|
| 822 |
+
"model.vision_tower.vision_tower.transformer.resblocks.45.attn.out_proj.bias": "model-00002-of-00002.safetensors",
|
| 823 |
+
"model.vision_tower.vision_tower.transformer.resblocks.45.attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 824 |
+
"model.vision_tower.vision_tower.transformer.resblocks.45.ln_1.bias": "model-00002-of-00002.safetensors",
|
| 825 |
+
"model.vision_tower.vision_tower.transformer.resblocks.45.ln_1.weight": "model-00002-of-00002.safetensors",
|
| 826 |
+
"model.vision_tower.vision_tower.transformer.resblocks.45.ln_2.bias": "model-00002-of-00002.safetensors",
|
| 827 |
+
"model.vision_tower.vision_tower.transformer.resblocks.45.ln_2.weight": "model-00002-of-00002.safetensors",
|
| 828 |
+
"model.vision_tower.vision_tower.transformer.resblocks.45.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
|
| 829 |
+
"model.vision_tower.vision_tower.transformer.resblocks.45.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
|
| 830 |
+
"model.vision_tower.vision_tower.transformer.resblocks.45.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
|
| 831 |
+
"model.vision_tower.vision_tower.transformer.resblocks.45.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
|
| 832 |
+
"model.vision_tower.vision_tower.transformer.resblocks.46.attn.in_proj_bias": "model-00002-of-00002.safetensors",
|
| 833 |
+
"model.vision_tower.vision_tower.transformer.resblocks.46.attn.in_proj_weight": "model-00002-of-00002.safetensors",
|
| 834 |
+
"model.vision_tower.vision_tower.transformer.resblocks.46.attn.out_proj.bias": "model-00002-of-00002.safetensors",
|
| 835 |
+
"model.vision_tower.vision_tower.transformer.resblocks.46.attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 836 |
+
"model.vision_tower.vision_tower.transformer.resblocks.46.ln_1.bias": "model-00002-of-00002.safetensors",
|
| 837 |
+
"model.vision_tower.vision_tower.transformer.resblocks.46.ln_1.weight": "model-00002-of-00002.safetensors",
|
| 838 |
+
"model.vision_tower.vision_tower.transformer.resblocks.46.ln_2.bias": "model-00002-of-00002.safetensors",
|
| 839 |
+
"model.vision_tower.vision_tower.transformer.resblocks.46.ln_2.weight": "model-00002-of-00002.safetensors",
|
| 840 |
+
"model.vision_tower.vision_tower.transformer.resblocks.46.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
|
| 841 |
+
"model.vision_tower.vision_tower.transformer.resblocks.46.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
|
| 842 |
+
"model.vision_tower.vision_tower.transformer.resblocks.46.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
|
| 843 |
+
"model.vision_tower.vision_tower.transformer.resblocks.46.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
|
| 844 |
+
"model.vision_tower.vision_tower.transformer.resblocks.47.attn.in_proj_bias": "model-00002-of-00002.safetensors",
|
| 845 |
+
"model.vision_tower.vision_tower.transformer.resblocks.47.attn.in_proj_weight": "model-00002-of-00002.safetensors",
|
| 846 |
+
"model.vision_tower.vision_tower.transformer.resblocks.47.attn.out_proj.bias": "model-00002-of-00002.safetensors",
|
| 847 |
+
"model.vision_tower.vision_tower.transformer.resblocks.47.attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 848 |
+
"model.vision_tower.vision_tower.transformer.resblocks.47.ln_1.bias": "model-00002-of-00002.safetensors",
|
| 849 |
+
"model.vision_tower.vision_tower.transformer.resblocks.47.ln_1.weight": "model-00002-of-00002.safetensors",
|
| 850 |
+
"model.vision_tower.vision_tower.transformer.resblocks.47.ln_2.bias": "model-00002-of-00002.safetensors",
|
| 851 |
+
"model.vision_tower.vision_tower.transformer.resblocks.47.ln_2.weight": "model-00002-of-00002.safetensors",
|
| 852 |
+
"model.vision_tower.vision_tower.transformer.resblocks.47.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
|
| 853 |
+
"model.vision_tower.vision_tower.transformer.resblocks.47.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
|
| 854 |
+
"model.vision_tower.vision_tower.transformer.resblocks.47.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
|
| 855 |
+
"model.vision_tower.vision_tower.transformer.resblocks.47.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
|
| 856 |
+
"model.vision_tower.vision_tower.transformer.resblocks.48.attn.in_proj_bias": "model-00002-of-00002.safetensors",
|
| 857 |
+
"model.vision_tower.vision_tower.transformer.resblocks.48.attn.in_proj_weight": "model-00002-of-00002.safetensors",
|
| 858 |
+
"model.vision_tower.vision_tower.transformer.resblocks.48.attn.out_proj.bias": "model-00002-of-00002.safetensors",
|
| 859 |
+
"model.vision_tower.vision_tower.transformer.resblocks.48.attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 860 |
+
"model.vision_tower.vision_tower.transformer.resblocks.48.ln_1.bias": "model-00002-of-00002.safetensors",
|
| 861 |
+
"model.vision_tower.vision_tower.transformer.resblocks.48.ln_1.weight": "model-00002-of-00002.safetensors",
|
| 862 |
+
"model.vision_tower.vision_tower.transformer.resblocks.48.ln_2.bias": "model-00002-of-00002.safetensors",
|
| 863 |
+
"model.vision_tower.vision_tower.transformer.resblocks.48.ln_2.weight": "model-00002-of-00002.safetensors",
|
| 864 |
+
"model.vision_tower.vision_tower.transformer.resblocks.48.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
|
| 865 |
+
"model.vision_tower.vision_tower.transformer.resblocks.48.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
|
| 866 |
+
"model.vision_tower.vision_tower.transformer.resblocks.48.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
|
| 867 |
+
"model.vision_tower.vision_tower.transformer.resblocks.48.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
|
| 868 |
+
"model.vision_tower.vision_tower.transformer.resblocks.49.attn.in_proj_bias": "model-00002-of-00002.safetensors",
|
| 869 |
+
"model.vision_tower.vision_tower.transformer.resblocks.49.attn.in_proj_weight": "model-00002-of-00002.safetensors",
|
| 870 |
+
"model.vision_tower.vision_tower.transformer.resblocks.49.attn.out_proj.bias": "model-00002-of-00002.safetensors",
|
| 871 |
+
"model.vision_tower.vision_tower.transformer.resblocks.49.attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 872 |
+
"model.vision_tower.vision_tower.transformer.resblocks.49.ln_1.bias": "model-00002-of-00002.safetensors",
|
| 873 |
+
"model.vision_tower.vision_tower.transformer.resblocks.49.ln_1.weight": "model-00002-of-00002.safetensors",
|
| 874 |
+
"model.vision_tower.vision_tower.transformer.resblocks.49.ln_2.bias": "model-00002-of-00002.safetensors",
|
| 875 |
+
"model.vision_tower.vision_tower.transformer.resblocks.49.ln_2.weight": "model-00002-of-00002.safetensors",
|
| 876 |
+
"model.vision_tower.vision_tower.transformer.resblocks.49.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
|
| 877 |
+
"model.vision_tower.vision_tower.transformer.resblocks.49.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
|
| 878 |
+
"model.vision_tower.vision_tower.transformer.resblocks.49.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
|
| 879 |
+
"model.vision_tower.vision_tower.transformer.resblocks.49.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
|
| 880 |
+
"model.vision_tower.vision_tower.transformer.resblocks.5.attn.in_proj_bias": "model-00001-of-00002.safetensors",
|
| 881 |
+
"model.vision_tower.vision_tower.transformer.resblocks.5.attn.in_proj_weight": "model-00001-of-00002.safetensors",
|
| 882 |
+
"model.vision_tower.vision_tower.transformer.resblocks.5.attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 883 |
+
"model.vision_tower.vision_tower.transformer.resblocks.5.attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 884 |
+
"model.vision_tower.vision_tower.transformer.resblocks.5.ln_1.bias": "model-00001-of-00002.safetensors",
|
| 885 |
+
"model.vision_tower.vision_tower.transformer.resblocks.5.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 886 |
+
"model.vision_tower.vision_tower.transformer.resblocks.5.ln_2.bias": "model-00001-of-00002.safetensors",
|
| 887 |
+
"model.vision_tower.vision_tower.transformer.resblocks.5.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 888 |
+
"model.vision_tower.vision_tower.transformer.resblocks.5.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
| 889 |
+
"model.vision_tower.vision_tower.transformer.resblocks.5.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
|
| 890 |
+
"model.vision_tower.vision_tower.transformer.resblocks.5.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 891 |
+
"model.vision_tower.vision_tower.transformer.resblocks.5.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
|
| 892 |
+
"model.vision_tower.vision_tower.transformer.resblocks.6.attn.in_proj_bias": "model-00001-of-00002.safetensors",
|
| 893 |
+
"model.vision_tower.vision_tower.transformer.resblocks.6.attn.in_proj_weight": "model-00001-of-00002.safetensors",
|
| 894 |
+
"model.vision_tower.vision_tower.transformer.resblocks.6.attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 895 |
+
"model.vision_tower.vision_tower.transformer.resblocks.6.attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 896 |
+
"model.vision_tower.vision_tower.transformer.resblocks.6.ln_1.bias": "model-00001-of-00002.safetensors",
|
| 897 |
+
"model.vision_tower.vision_tower.transformer.resblocks.6.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 898 |
+
"model.vision_tower.vision_tower.transformer.resblocks.6.ln_2.bias": "model-00001-of-00002.safetensors",
|
| 899 |
+
"model.vision_tower.vision_tower.transformer.resblocks.6.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 900 |
+
"model.vision_tower.vision_tower.transformer.resblocks.6.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
| 901 |
+
"model.vision_tower.vision_tower.transformer.resblocks.6.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
|
| 902 |
+
"model.vision_tower.vision_tower.transformer.resblocks.6.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 903 |
+
"model.vision_tower.vision_tower.transformer.resblocks.6.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
|
| 904 |
+
"model.vision_tower.vision_tower.transformer.resblocks.7.attn.in_proj_bias": "model-00001-of-00002.safetensors",
|
| 905 |
+
"model.vision_tower.vision_tower.transformer.resblocks.7.attn.in_proj_weight": "model-00001-of-00002.safetensors",
|
| 906 |
+
"model.vision_tower.vision_tower.transformer.resblocks.7.attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 907 |
+
"model.vision_tower.vision_tower.transformer.resblocks.7.attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 908 |
+
"model.vision_tower.vision_tower.transformer.resblocks.7.ln_1.bias": "model-00001-of-00002.safetensors",
|
| 909 |
+
"model.vision_tower.vision_tower.transformer.resblocks.7.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 910 |
+
"model.vision_tower.vision_tower.transformer.resblocks.7.ln_2.bias": "model-00001-of-00002.safetensors",
|
| 911 |
+
"model.vision_tower.vision_tower.transformer.resblocks.7.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 912 |
+
"model.vision_tower.vision_tower.transformer.resblocks.7.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
| 913 |
+
"model.vision_tower.vision_tower.transformer.resblocks.7.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
|
| 914 |
+
"model.vision_tower.vision_tower.transformer.resblocks.7.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 915 |
+
"model.vision_tower.vision_tower.transformer.resblocks.7.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
|
| 916 |
+
"model.vision_tower.vision_tower.transformer.resblocks.8.attn.in_proj_bias": "model-00001-of-00002.safetensors",
|
| 917 |
+
"model.vision_tower.vision_tower.transformer.resblocks.8.attn.in_proj_weight": "model-00001-of-00002.safetensors",
|
| 918 |
+
"model.vision_tower.vision_tower.transformer.resblocks.8.attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 919 |
+
"model.vision_tower.vision_tower.transformer.resblocks.8.attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 920 |
+
"model.vision_tower.vision_tower.transformer.resblocks.8.ln_1.bias": "model-00001-of-00002.safetensors",
|
| 921 |
+
"model.vision_tower.vision_tower.transformer.resblocks.8.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 922 |
+
"model.vision_tower.vision_tower.transformer.resblocks.8.ln_2.bias": "model-00001-of-00002.safetensors",
|
| 923 |
+
"model.vision_tower.vision_tower.transformer.resblocks.8.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 924 |
+
"model.vision_tower.vision_tower.transformer.resblocks.8.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
| 925 |
+
"model.vision_tower.vision_tower.transformer.resblocks.8.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
|
| 926 |
+
"model.vision_tower.vision_tower.transformer.resblocks.8.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 927 |
+
"model.vision_tower.vision_tower.transformer.resblocks.8.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
|
| 928 |
+
"model.vision_tower.vision_tower.transformer.resblocks.9.attn.in_proj_bias": "model-00001-of-00002.safetensors",
|
| 929 |
+
"model.vision_tower.vision_tower.transformer.resblocks.9.attn.in_proj_weight": "model-00001-of-00002.safetensors",
|
| 930 |
+
"model.vision_tower.vision_tower.transformer.resblocks.9.attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 931 |
+
"model.vision_tower.vision_tower.transformer.resblocks.9.attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 932 |
+
"model.vision_tower.vision_tower.transformer.resblocks.9.ln_1.bias": "model-00001-of-00002.safetensors",
|
| 933 |
+
"model.vision_tower.vision_tower.transformer.resblocks.9.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 934 |
+
"model.vision_tower.vision_tower.transformer.resblocks.9.ln_2.bias": "model-00001-of-00002.safetensors",
|
| 935 |
+
"model.vision_tower.vision_tower.transformer.resblocks.9.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 936 |
+
"model.vision_tower.vision_tower.transformer.resblocks.9.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
| 937 |
+
"model.vision_tower.vision_tower.transformer.resblocks.9.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
|
| 938 |
+
"model.vision_tower.vision_tower.transformer.resblocks.9.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 939 |
+
"model.vision_tower.vision_tower.transformer.resblocks.9.mlp.c_proj.weight": "model-00001-of-00002.safetensors"
|
| 940 |
+
}
|
| 941 |
+
}
|
continuous/qwen3/pe_core_g14_448/finetune/special_tokens_map.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|im_start|>",
|
| 4 |
+
"<|im_end|>",
|
| 5 |
+
"<|object_ref_start|>",
|
| 6 |
+
"<|object_ref_end|>",
|
| 7 |
+
"<|box_start|>",
|
| 8 |
+
"<|box_end|>",
|
| 9 |
+
"<|quad_start|>",
|
| 10 |
+
"<|quad_end|>",
|
| 11 |
+
"<|vision_start|>",
|
| 12 |
+
"<|vision_end|>",
|
| 13 |
+
"<|vision_pad|>",
|
| 14 |
+
"<|image_pad|>",
|
| 15 |
+
"<|video_pad|>"
|
| 16 |
+
],
|
| 17 |
+
"eos_token": {
|
| 18 |
+
"content": "<|im_end|>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
},
|
| 24 |
+
"pad_token": {
|
| 25 |
+
"content": "<|endoftext|>",
|
| 26 |
+
"lstrip": false,
|
| 27 |
+
"normalized": false,
|
| 28 |
+
"rstrip": false,
|
| 29 |
+
"single_word": false
|
| 30 |
+
}
|
| 31 |
+
}
|
continuous/qwen3/pe_core_g14_448/finetune/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
|
| 3 |
+
size 11422654
|
continuous/qwen3/pe_core_g14_448/finetune/tokenizer_config.json
ADDED
|
@@ -0,0 +1,240 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_prefix_space": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"151643": {
|
| 6 |
+
"content": "<|endoftext|>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"151644": {
|
| 14 |
+
"content": "<|im_start|>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"151645": {
|
| 22 |
+
"content": "<|im_end|>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
},
|
| 29 |
+
"151646": {
|
| 30 |
+
"content": "<|object_ref_start|>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false,
|
| 35 |
+
"special": true
|
| 36 |
+
},
|
| 37 |
+
"151647": {
|
| 38 |
+
"content": "<|object_ref_end|>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false,
|
| 43 |
+
"special": true
|
| 44 |
+
},
|
| 45 |
+
"151648": {
|
| 46 |
+
"content": "<|box_start|>",
|
| 47 |
+
"lstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"rstrip": false,
|
| 50 |
+
"single_word": false,
|
| 51 |
+
"special": true
|
| 52 |
+
},
|
| 53 |
+
"151649": {
|
| 54 |
+
"content": "<|box_end|>",
|
| 55 |
+
"lstrip": false,
|
| 56 |
+
"normalized": false,
|
| 57 |
+
"rstrip": false,
|
| 58 |
+
"single_word": false,
|
| 59 |
+
"special": true
|
| 60 |
+
},
|
| 61 |
+
"151650": {
|
| 62 |
+
"content": "<|quad_start|>",
|
| 63 |
+
"lstrip": false,
|
| 64 |
+
"normalized": false,
|
| 65 |
+
"rstrip": false,
|
| 66 |
+
"single_word": false,
|
| 67 |
+
"special": true
|
| 68 |
+
},
|
| 69 |
+
"151651": {
|
| 70 |
+
"content": "<|quad_end|>",
|
| 71 |
+
"lstrip": false,
|
| 72 |
+
"normalized": false,
|
| 73 |
+
"rstrip": false,
|
| 74 |
+
"single_word": false,
|
| 75 |
+
"special": true
|
| 76 |
+
},
|
| 77 |
+
"151652": {
|
| 78 |
+
"content": "<|vision_start|>",
|
| 79 |
+
"lstrip": false,
|
| 80 |
+
"normalized": false,
|
| 81 |
+
"rstrip": false,
|
| 82 |
+
"single_word": false,
|
| 83 |
+
"special": true
|
| 84 |
+
},
|
| 85 |
+
"151653": {
|
| 86 |
+
"content": "<|vision_end|>",
|
| 87 |
+
"lstrip": false,
|
| 88 |
+
"normalized": false,
|
| 89 |
+
"rstrip": false,
|
| 90 |
+
"single_word": false,
|
| 91 |
+
"special": true
|
| 92 |
+
},
|
| 93 |
+
"151654": {
|
| 94 |
+
"content": "<|vision_pad|>",
|
| 95 |
+
"lstrip": false,
|
| 96 |
+
"normalized": false,
|
| 97 |
+
"rstrip": false,
|
| 98 |
+
"single_word": false,
|
| 99 |
+
"special": true
|
| 100 |
+
},
|
| 101 |
+
"151655": {
|
| 102 |
+
"content": "<|image_pad|>",
|
| 103 |
+
"lstrip": false,
|
| 104 |
+
"normalized": false,
|
| 105 |
+
"rstrip": false,
|
| 106 |
+
"single_word": false,
|
| 107 |
+
"special": true
|
| 108 |
+
},
|
| 109 |
+
"151656": {
|
| 110 |
+
"content": "<|video_pad|>",
|
| 111 |
+
"lstrip": false,
|
| 112 |
+
"normalized": false,
|
| 113 |
+
"rstrip": false,
|
| 114 |
+
"single_word": false,
|
| 115 |
+
"special": true
|
| 116 |
+
},
|
| 117 |
+
"151657": {
|
| 118 |
+
"content": "<tool_call>",
|
| 119 |
+
"lstrip": false,
|
| 120 |
+
"normalized": false,
|
| 121 |
+
"rstrip": false,
|
| 122 |
+
"single_word": false,
|
| 123 |
+
"special": false
|
| 124 |
+
},
|
| 125 |
+
"151658": {
|
| 126 |
+
"content": "</tool_call>",
|
| 127 |
+
"lstrip": false,
|
| 128 |
+
"normalized": false,
|
| 129 |
+
"rstrip": false,
|
| 130 |
+
"single_word": false,
|
| 131 |
+
"special": false
|
| 132 |
+
},
|
| 133 |
+
"151659": {
|
| 134 |
+
"content": "<|fim_prefix|>",
|
| 135 |
+
"lstrip": false,
|
| 136 |
+
"normalized": false,
|
| 137 |
+
"rstrip": false,
|
| 138 |
+
"single_word": false,
|
| 139 |
+
"special": false
|
| 140 |
+
},
|
| 141 |
+
"151660": {
|
| 142 |
+
"content": "<|fim_middle|>",
|
| 143 |
+
"lstrip": false,
|
| 144 |
+
"normalized": false,
|
| 145 |
+
"rstrip": false,
|
| 146 |
+
"single_word": false,
|
| 147 |
+
"special": false
|
| 148 |
+
},
|
| 149 |
+
"151661": {
|
| 150 |
+
"content": "<|fim_suffix|>",
|
| 151 |
+
"lstrip": false,
|
| 152 |
+
"normalized": false,
|
| 153 |
+
"rstrip": false,
|
| 154 |
+
"single_word": false,
|
| 155 |
+
"special": false
|
| 156 |
+
},
|
| 157 |
+
"151662": {
|
| 158 |
+
"content": "<|fim_pad|>",
|
| 159 |
+
"lstrip": false,
|
| 160 |
+
"normalized": false,
|
| 161 |
+
"rstrip": false,
|
| 162 |
+
"single_word": false,
|
| 163 |
+
"special": false
|
| 164 |
+
},
|
| 165 |
+
"151663": {
|
| 166 |
+
"content": "<|repo_name|>",
|
| 167 |
+
"lstrip": false,
|
| 168 |
+
"normalized": false,
|
| 169 |
+
"rstrip": false,
|
| 170 |
+
"single_word": false,
|
| 171 |
+
"special": false
|
| 172 |
+
},
|
| 173 |
+
"151664": {
|
| 174 |
+
"content": "<|file_sep|>",
|
| 175 |
+
"lstrip": false,
|
| 176 |
+
"normalized": false,
|
| 177 |
+
"rstrip": false,
|
| 178 |
+
"single_word": false,
|
| 179 |
+
"special": false
|
| 180 |
+
},
|
| 181 |
+
"151665": {
|
| 182 |
+
"content": "<tool_response>",
|
| 183 |
+
"lstrip": false,
|
| 184 |
+
"normalized": false,
|
| 185 |
+
"rstrip": false,
|
| 186 |
+
"single_word": false,
|
| 187 |
+
"special": false
|
| 188 |
+
},
|
| 189 |
+
"151666": {
|
| 190 |
+
"content": "</tool_response>",
|
| 191 |
+
"lstrip": false,
|
| 192 |
+
"normalized": false,
|
| 193 |
+
"rstrip": false,
|
| 194 |
+
"single_word": false,
|
| 195 |
+
"special": false
|
| 196 |
+
},
|
| 197 |
+
"151667": {
|
| 198 |
+
"content": "<think>",
|
| 199 |
+
"lstrip": false,
|
| 200 |
+
"normalized": false,
|
| 201 |
+
"rstrip": false,
|
| 202 |
+
"single_word": false,
|
| 203 |
+
"special": false
|
| 204 |
+
},
|
| 205 |
+
"151668": {
|
| 206 |
+
"content": "</think>",
|
| 207 |
+
"lstrip": false,
|
| 208 |
+
"normalized": false,
|
| 209 |
+
"rstrip": false,
|
| 210 |
+
"single_word": false,
|
| 211 |
+
"special": false
|
| 212 |
+
}
|
| 213 |
+
},
|
| 214 |
+
"additional_special_tokens": [
|
| 215 |
+
"<|im_start|>",
|
| 216 |
+
"<|im_end|>",
|
| 217 |
+
"<|object_ref_start|>",
|
| 218 |
+
"<|object_ref_end|>",
|
| 219 |
+
"<|box_start|>",
|
| 220 |
+
"<|box_end|>",
|
| 221 |
+
"<|quad_start|>",
|
| 222 |
+
"<|quad_end|>",
|
| 223 |
+
"<|vision_start|>",
|
| 224 |
+
"<|vision_end|>",
|
| 225 |
+
"<|vision_pad|>",
|
| 226 |
+
"<|image_pad|>",
|
| 227 |
+
"<|video_pad|>"
|
| 228 |
+
],
|
| 229 |
+
"bos_token": null,
|
| 230 |
+
"clean_up_tokenization_spaces": false,
|
| 231 |
+
"eos_token": "<|im_end|>",
|
| 232 |
+
"errors": "replace",
|
| 233 |
+
"extra_special_tokens": {},
|
| 234 |
+
"model_max_length": 8192,
|
| 235 |
+
"pad_token": "<|endoftext|>",
|
| 236 |
+
"padding_side": "right",
|
| 237 |
+
"split_special_tokens": false,
|
| 238 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 239 |
+
"unk_token": null
|
| 240 |
+
}
|
continuous/qwen3/pe_core_g14_448/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": 0.9999037443449803,
|
| 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": 0.003850226200789296,
|
| 14 |
+
"grad_norm": 9.435739517211914,
|
| 15 |
+
"learning_rate": 1.153846153846154e-06,
|
| 16 |
+
"loss": 2.424,
|
| 17 |
+
"step": 10
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.007700452401578592,
|
| 21 |
+
"grad_norm": 3.794184446334839,
|
| 22 |
+
"learning_rate": 2.435897435897436e-06,
|
| 23 |
+
"loss": 1.8675,
|
| 24 |
+
"step": 20
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.01155067860236789,
|
| 28 |
+
"grad_norm": 2.268695116043091,
|
| 29 |
+
"learning_rate": 3.7179487179487184e-06,
|
| 30 |
+
"loss": 1.4604,
|
| 31 |
+
"step": 30
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.015400904803157185,
|
| 35 |
+
"grad_norm": 0.5613528490066528,
|
| 36 |
+
"learning_rate": 5e-06,
|
| 37 |
+
"loss": 1.15,
|
| 38 |
+
"step": 40
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.019251131003946483,
|
| 42 |
+
"grad_norm": 0.4810701906681061,
|
| 43 |
+
"learning_rate": 6.282051282051282e-06,
|
| 44 |
+
"loss": 1.0542,
|
| 45 |
+
"step": 50
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.02310135720473578,
|
| 49 |
+
"grad_norm": 0.24929043650627136,
|
| 50 |
+
"learning_rate": 7.564102564102564e-06,
|
| 51 |
+
"loss": 0.9827,
|
| 52 |
+
"step": 60
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.026951583405525073,
|
| 56 |
+
"grad_norm": 0.20601968467235565,
|
| 57 |
+
"learning_rate": 8.846153846153847e-06,
|
| 58 |
+
"loss": 0.945,
|
| 59 |
+
"step": 70
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.03080180960631437,
|
| 63 |
+
"grad_norm": 0.17354556918144226,
|
| 64 |
+
"learning_rate": 9.999996111488723e-06,
|
| 65 |
+
"loss": 0.9446,
|
| 66 |
+
"step": 80
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.034652035807103666,
|
| 70 |
+
"grad_norm": 0.1718161255121231,
|
| 71 |
+
"learning_rate": 9.999529497453782e-06,
|
| 72 |
+
"loss": 0.9178,
|
| 73 |
+
"step": 90
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.038502262007892966,
|
| 77 |
+
"grad_norm": 0.15491124987602234,
|
| 78 |
+
"learning_rate": 9.998285264324193e-06,
|
| 79 |
+
"loss": 0.8927,
|
| 80 |
+
"step": 100
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.04235248820868226,
|
| 84 |
+
"grad_norm": 0.17049922049045563,
|
| 85 |
+
"learning_rate": 9.996263605626052e-06,
|
| 86 |
+
"loss": 0.8692,
|
| 87 |
+
"step": 110
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.04620271440947156,
|
| 91 |
+
"grad_norm": 0.15067844092845917,
|
| 92 |
+
"learning_rate": 9.99346483580503e-06,
|
| 93 |
+
"loss": 0.8767,
|
| 94 |
+
"step": 120
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.05005294061026085,
|
| 98 |
+
"grad_norm": 0.1451946645975113,
|
| 99 |
+
"learning_rate": 9.989889390177467e-06,
|
| 100 |
+
"loss": 0.8689,
|
| 101 |
+
"step": 130
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.053903166811050146,
|
| 105 |
+
"grad_norm": 0.16659963130950928,
|
| 106 |
+
"learning_rate": 9.985537824862647e-06,
|
| 107 |
+
"loss": 0.8649,
|
| 108 |
+
"step": 140
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.057753393011839446,
|
| 112 |
+
"grad_norm": 0.1841450184583664,
|
| 113 |
+
"learning_rate": 9.980410816696317e-06,
|
| 114 |
+
"loss": 0.8609,
|
| 115 |
+
"step": 150
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.06160361921262874,
|
| 119 |
+
"grad_norm": 0.1552504152059555,
|
| 120 |
+
"learning_rate": 9.97450916312541e-06,
|
| 121 |
+
"loss": 0.8541,
|
| 122 |
+
"step": 160
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.06545384541341803,
|
| 126 |
+
"grad_norm": 0.13316723704338074,
|
| 127 |
+
"learning_rate": 9.967833782084004e-06,
|
| 128 |
+
"loss": 0.851,
|
| 129 |
+
"step": 170
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.06930407161420733,
|
| 133 |
+
"grad_norm": 0.15093068778514862,
|
| 134 |
+
"learning_rate": 9.960385711850554e-06,
|
| 135 |
+
"loss": 0.875,
|
| 136 |
+
"step": 180
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.07315429781499663,
|
| 140 |
+
"grad_norm": 0.14531384408473969,
|
| 141 |
+
"learning_rate": 9.952166110886394e-06,
|
| 142 |
+
"loss": 0.8742,
|
| 143 |
+
"step": 190
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.07700452401578593,
|
| 147 |
+
"grad_norm": 0.15620416402816772,
|
| 148 |
+
"learning_rate": 9.943176257655567e-06,
|
| 149 |
+
"loss": 0.8543,
|
| 150 |
+
"step": 200
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.08085475021657522,
|
| 154 |
+
"grad_norm": 0.13953383266925812,
|
| 155 |
+
"learning_rate": 9.933417550425952e-06,
|
| 156 |
+
"loss": 0.8592,
|
| 157 |
+
"step": 210
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.08470497641736452,
|
| 161 |
+
"grad_norm": 0.14324381947517395,
|
| 162 |
+
"learning_rate": 9.9228915070518e-06,
|
| 163 |
+
"loss": 0.8371,
|
| 164 |
+
"step": 220
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.08855520261815382,
|
| 168 |
+
"grad_norm": 0.16467928886413574,
|
| 169 |
+
"learning_rate": 9.911599764737632e-06,
|
| 170 |
+
"loss": 0.8428,
|
| 171 |
+
"step": 230
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.09240542881894312,
|
| 175 |
+
"grad_norm": 0.14859159290790558,
|
| 176 |
+
"learning_rate": 9.899544079783606e-06,
|
| 177 |
+
"loss": 0.8305,
|
| 178 |
+
"step": 240
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.0962556550197324,
|
| 182 |
+
"grad_norm": 0.1543932408094406,
|
| 183 |
+
"learning_rate": 9.886726327312338e-06,
|
| 184 |
+
"loss": 0.8457,
|
| 185 |
+
"step": 250
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.1001058812205217,
|
| 189 |
+
"grad_norm": 0.13385950028896332,
|
| 190 |
+
"learning_rate": 9.87314850097724e-06,
|
| 191 |
+
"loss": 0.8497,
|
| 192 |
+
"step": 260
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.103956107421311,
|
| 196 |
+
"grad_norm": 0.1405632346868515,
|
| 197 |
+
"learning_rate": 9.858812712652452e-06,
|
| 198 |
+
"loss": 0.8354,
|
| 199 |
+
"step": 270
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.10780633362210029,
|
| 203 |
+
"grad_norm": 0.13767807185649872,
|
| 204 |
+
"learning_rate": 9.843721192104341e-06,
|
| 205 |
+
"loss": 0.8383,
|
| 206 |
+
"step": 280
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.11165655982288959,
|
| 210 |
+
"grad_norm": 0.14439624547958374,
|
| 211 |
+
"learning_rate": 9.827876286644698e-06,
|
| 212 |
+
"loss": 0.8492,
|
| 213 |
+
"step": 290
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.11550678602367889,
|
| 217 |
+
"grad_norm": 0.14066632091999054,
|
| 218 |
+
"learning_rate": 9.811280460765643e-06,
|
| 219 |
+
"loss": 0.8106,
|
| 220 |
+
"step": 300
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.11935701222446819,
|
| 224 |
+
"grad_norm": 0.13475865125656128,
|
| 225 |
+
"learning_rate": 9.793936295756292e-06,
|
| 226 |
+
"loss": 0.8272,
|
| 227 |
+
"step": 310
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.12320723842525748,
|
| 231 |
+
"grad_norm": 0.15705211460590363,
|
| 232 |
+
"learning_rate": 9.775846489301279e-06,
|
| 233 |
+
"loss": 0.8233,
|
| 234 |
+
"step": 320
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.12705746462604678,
|
| 238 |
+
"grad_norm": 0.14314797520637512,
|
| 239 |
+
"learning_rate": 9.757013855061157e-06,
|
| 240 |
+
"loss": 0.8251,
|
| 241 |
+
"step": 330
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.13090769082683607,
|
| 245 |
+
"grad_norm": 0.15106570720672607,
|
| 246 |
+
"learning_rate": 9.737441322234758e-06,
|
| 247 |
+
"loss": 0.834,
|
| 248 |
+
"step": 340
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.13475791702762538,
|
| 252 |
+
"grad_norm": 0.15736834704875946,
|
| 253 |
+
"learning_rate": 9.717131935103605e-06,
|
| 254 |
+
"loss": 0.8395,
|
| 255 |
+
"step": 350
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.13860814322841467,
|
| 259 |
+
"grad_norm": 0.13403145968914032,
|
| 260 |
+
"learning_rate": 9.696088852558398e-06,
|
| 261 |
+
"loss": 0.8229,
|
| 262 |
+
"step": 360
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.14245836942920398,
|
| 266 |
+
"grad_norm": 0.13138502836227417,
|
| 267 |
+
"learning_rate": 9.674315347607686e-06,
|
| 268 |
+
"loss": 0.8473,
|
| 269 |
+
"step": 370
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.14630859562999327,
|
| 273 |
+
"grad_norm": 0.12875759601593018,
|
| 274 |
+
"learning_rate": 9.651814806868796e-06,
|
| 275 |
+
"loss": 0.8155,
|
| 276 |
+
"step": 380
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.15015882183078255,
|
| 280 |
+
"grad_norm": 0.14245353639125824,
|
| 281 |
+
"learning_rate": 9.62859073004107e-06,
|
| 282 |
+
"loss": 0.8213,
|
| 283 |
+
"step": 390
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.15400904803157187,
|
| 287 |
+
"grad_norm": 0.13375554978847504,
|
| 288 |
+
"learning_rate": 9.604646729361547e-06,
|
| 289 |
+
"loss": 0.8219,
|
| 290 |
+
"step": 400
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.15785927423236115,
|
| 294 |
+
"grad_norm": 0.13487441837787628,
|
| 295 |
+
"learning_rate": 9.579986529043099e-06,
|
| 296 |
+
"loss": 0.8035,
|
| 297 |
+
"step": 410
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.16170950043315044,
|
| 301 |
+
"grad_norm": 0.1288229376077652,
|
| 302 |
+
"learning_rate": 9.554613964695189e-06,
|
| 303 |
+
"loss": 0.8189,
|
| 304 |
+
"step": 420
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.16555972663393975,
|
| 308 |
+
"grad_norm": 0.14412334561347961,
|
| 309 |
+
"learning_rate": 9.528532982727281e-06,
|
| 310 |
+
"loss": 0.8113,
|
| 311 |
+
"step": 430
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.16940995283472904,
|
| 315 |
+
"grad_norm": 0.15547718107700348,
|
| 316 |
+
"learning_rate": 9.501747639735018e-06,
|
| 317 |
+
"loss": 0.8103,
|
| 318 |
+
"step": 440
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.17326017903551832,
|
| 322 |
+
"grad_norm": 0.1391555368900299,
|
| 323 |
+
"learning_rate": 9.474262101869272e-06,
|
| 324 |
+
"loss": 0.7947,
|
| 325 |
+
"step": 450
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.17711040523630764,
|
| 329 |
+
"grad_norm": 0.1463460922241211,
|
| 330 |
+
"learning_rate": 9.446080644188141e-06,
|
| 331 |
+
"loss": 0.8099,
|
| 332 |
+
"step": 460
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.18096063143709692,
|
| 336 |
+
"grad_norm": 0.14823774993419647,
|
| 337 |
+
"learning_rate": 9.417207649992017e-06,
|
| 338 |
+
"loss": 0.8152,
|
| 339 |
+
"step": 470
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.18481085763788624,
|
| 343 |
+
"grad_norm": 0.13786010444164276,
|
| 344 |
+
"learning_rate": 9.387647610141816e-06,
|
| 345 |
+
"loss": 0.8074,
|
| 346 |
+
"step": 480
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.18866108383867553,
|
| 350 |
+
"grad_norm": 0.13171127438545227,
|
| 351 |
+
"learning_rate": 9.35740512236047e-06,
|
| 352 |
+
"loss": 0.7987,
|
| 353 |
+
"step": 490
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.1925113100394648,
|
| 357 |
+
"grad_norm": 0.13139913976192474,
|
| 358 |
+
"learning_rate": 9.326484890517809e-06,
|
| 359 |
+
"loss": 0.8004,
|
| 360 |
+
"step": 500
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.19636153624025413,
|
| 364 |
+
"grad_norm": 0.13557177782058716,
|
| 365 |
+
"learning_rate": 9.294891723898926e-06,
|
| 366 |
+
"loss": 0.7865,
|
| 367 |
+
"step": 510
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.2002117624410434,
|
| 371 |
+
"grad_norm": 0.13781975209712982,
|
| 372 |
+
"learning_rate": 9.262630536456153e-06,
|
| 373 |
+
"loss": 0.8277,
|
| 374 |
+
"step": 520
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.2040619886418327,
|
| 378 |
+
"grad_norm": 0.1527281105518341,
|
| 379 |
+
"learning_rate": 9.229706346044749e-06,
|
| 380 |
+
"loss": 0.7944,
|
| 381 |
+
"step": 530
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.207912214842622,
|
| 385 |
+
"grad_norm": 0.14717428386211395,
|
| 386 |
+
"learning_rate": 9.196124273642422e-06,
|
| 387 |
+
"loss": 0.814,
|
| 388 |
+
"step": 540
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.2117624410434113,
|
| 392 |
+
"grad_norm": 0.12914511561393738,
|
| 393 |
+
"learning_rate": 9.161889542552842e-06,
|
| 394 |
+
"loss": 0.8182,
|
| 395 |
+
"step": 550
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.21561266724420058,
|
| 399 |
+
"grad_norm": 0.14167293906211853,
|
| 400 |
+
"learning_rate": 9.127007477593193e-06,
|
| 401 |
+
"loss": 0.8178,
|
| 402 |
+
"step": 560
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.2194628934449899,
|
| 406 |
+
"grad_norm": 0.14688290655612946,
|
| 407 |
+
"learning_rate": 9.091483504265974e-06,
|
| 408 |
+
"loss": 0.8269,
|
| 409 |
+
"step": 570
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.22331311964577918,
|
| 413 |
+
"grad_norm": 0.14312759041786194,
|
| 414 |
+
"learning_rate": 9.055323147915116e-06,
|
| 415 |
+
"loss": 0.8025,
|
| 416 |
+
"step": 580
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.2271633458465685,
|
| 420 |
+
"grad_norm": 0.14312411844730377,
|
| 421 |
+
"learning_rate": 9.018532032866585e-06,
|
| 422 |
+
"loss": 0.8192,
|
| 423 |
+
"step": 590
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.23101357204735778,
|
| 427 |
+
"grad_norm": 0.14288924634456635,
|
| 428 |
+
"learning_rate": 8.981115881553579e-06,
|
| 429 |
+
"loss": 0.8139,
|
| 430 |
+
"step": 600
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.23486379824814707,
|
| 434 |
+
"grad_norm": 0.142152339220047,
|
| 435 |
+
"learning_rate": 8.943080513626476e-06,
|
| 436 |
+
"loss": 0.8249,
|
| 437 |
+
"step": 610
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.23871402444893638,
|
| 441 |
+
"grad_norm": 0.14002802968025208,
|
| 442 |
+
"learning_rate": 8.904431845047641e-06,
|
| 443 |
+
"loss": 0.8162,
|
| 444 |
+
"step": 620
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.24256425064972567,
|
| 448 |
+
"grad_norm": 0.1490638554096222,
|
| 449 |
+
"learning_rate": 8.86517588717128e-06,
|
| 450 |
+
"loss": 0.8218,
|
| 451 |
+
"step": 630
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.24641447685051496,
|
| 455 |
+
"grad_norm": 0.13497404754161835,
|
| 456 |
+
"learning_rate": 8.82531874580844e-06,
|
| 457 |
+
"loss": 0.8156,
|
| 458 |
+
"step": 640
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.25026470305130427,
|
| 462 |
+
"grad_norm": 0.12539586424827576,
|
| 463 |
+
"learning_rate": 8.784866620277314e-06,
|
| 464 |
+
"loss": 0.772,
|
| 465 |
+
"step": 650
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.25411492925209356,
|
| 469 |
+
"grad_norm": 0.13903266191482544,
|
| 470 |
+
"learning_rate": 8.743825802439018e-06,
|
| 471 |
+
"loss": 0.7992,
|
| 472 |
+
"step": 660
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 0.25796515545288284,
|
| 476 |
+
"grad_norm": 0.14258940517902374,
|
| 477 |
+
"learning_rate": 8.702202675718956e-06,
|
| 478 |
+
"loss": 0.8144,
|
| 479 |
+
"step": 670
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 0.26181538165367213,
|
| 483 |
+
"grad_norm": 0.14176000654697418,
|
| 484 |
+
"learning_rate": 8.660003714113959e-06,
|
| 485 |
+
"loss": 0.7891,
|
| 486 |
+
"step": 680
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 0.26566560785446147,
|
| 490 |
+
"grad_norm": 0.13687004148960114,
|
| 491 |
+
"learning_rate": 8.617235481185323e-06,
|
| 492 |
+
"loss": 0.8022,
|
| 493 |
+
"step": 690
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 0.26951583405525076,
|
| 497 |
+
"grad_norm": 0.16582779586315155,
|
| 498 |
+
"learning_rate": 8.573904629037931e-06,
|
| 499 |
+
"loss": 0.8086,
|
| 500 |
+
"step": 700
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.27336606025604004,
|
| 504 |
+
"grad_norm": 0.1273442953824997,
|
| 505 |
+
"learning_rate": 8.530017897285585e-06,
|
| 506 |
+
"loss": 0.7935,
|
| 507 |
+
"step": 710
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.27721628645682933,
|
| 511 |
+
"grad_norm": 0.12787044048309326,
|
| 512 |
+
"learning_rate": 8.485582112002746e-06,
|
| 513 |
+
"loss": 0.7971,
|
| 514 |
+
"step": 720
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.2810665126576186,
|
| 518 |
+
"grad_norm": 0.1488957554101944,
|
| 519 |
+
"learning_rate": 8.440604184662811e-06,
|
| 520 |
+
"loss": 0.8067,
|
| 521 |
+
"step": 730
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.28491673885840796,
|
| 525 |
+
"grad_norm": 0.14077402651309967,
|
| 526 |
+
"learning_rate": 8.395091111063118e-06,
|
| 527 |
+
"loss": 0.788,
|
| 528 |
+
"step": 740
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 0.28876696505919724,
|
| 532 |
+
"grad_norm": 0.13430221378803253,
|
| 533 |
+
"learning_rate": 8.349049970236822e-06,
|
| 534 |
+
"loss": 0.7877,
|
| 535 |
+
"step": 750
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 0.29261719125998653,
|
| 539 |
+
"grad_norm": 0.1429181694984436,
|
| 540 |
+
"learning_rate": 8.302487923351842e-06,
|
| 541 |
+
"loss": 0.78,
|
| 542 |
+
"step": 760
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.2964674174607758,
|
| 546 |
+
"grad_norm": 0.1387336403131485,
|
| 547 |
+
"learning_rate": 8.255412212597021e-06,
|
| 548 |
+
"loss": 0.7978,
|
| 549 |
+
"step": 770
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.3003176436615651,
|
| 553 |
+
"grad_norm": 0.15097860991954803,
|
| 554 |
+
"learning_rate": 8.207830160055688e-06,
|
| 555 |
+
"loss": 0.7914,
|
| 556 |
+
"step": 780
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.3041678698623544,
|
| 560 |
+
"grad_norm": 0.17374400794506073,
|
| 561 |
+
"learning_rate": 8.159749166566786e-06,
|
| 562 |
+
"loss": 0.7801,
|
| 563 |
+
"step": 790
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 0.30801809606314373,
|
| 567 |
+
"grad_norm": 0.14019973576068878,
|
| 568 |
+
"learning_rate": 8.11117671057377e-06,
|
| 569 |
+
"loss": 0.8052,
|
| 570 |
+
"step": 800
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.311868322263933,
|
| 574 |
+
"grad_norm": 0.13665975630283356,
|
| 575 |
+
"learning_rate": 8.062120346961404e-06,
|
| 576 |
+
"loss": 0.7923,
|
| 577 |
+
"step": 810
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 0.3157185484647223,
|
| 581 |
+
"grad_norm": 0.13014604151248932,
|
| 582 |
+
"learning_rate": 8.012587705880705e-06,
|
| 583 |
+
"loss": 0.793,
|
| 584 |
+
"step": 820
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 0.3195687746655116,
|
| 588 |
+
"grad_norm": 0.14099819958209991,
|
| 589 |
+
"learning_rate": 7.962586491562146e-06,
|
| 590 |
+
"loss": 0.7819,
|
| 591 |
+
"step": 830
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.3234190008663009,
|
| 595 |
+
"grad_norm": 0.1439497470855713,
|
| 596 |
+
"learning_rate": 7.912124481117357e-06,
|
| 597 |
+
"loss": 0.7862,
|
| 598 |
+
"step": 840
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 0.3272692270670902,
|
| 602 |
+
"grad_norm": 0.12797777354717255,
|
| 603 |
+
"learning_rate": 7.861209523329494e-06,
|
| 604 |
+
"loss": 0.7872,
|
| 605 |
+
"step": 850
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 0.3311194532678795,
|
| 609 |
+
"grad_norm": 0.14950233697891235,
|
| 610 |
+
"learning_rate": 7.809849537432432e-06,
|
| 611 |
+
"loss": 0.7797,
|
| 612 |
+
"step": 860
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 0.3349696794686688,
|
| 616 |
+
"grad_norm": 0.129901722073555,
|
| 617 |
+
"learning_rate": 7.758052511879035e-06,
|
| 618 |
+
"loss": 0.7773,
|
| 619 |
+
"step": 870
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 0.3388199056694581,
|
| 623 |
+
"grad_norm": 0.12637965381145477,
|
| 624 |
+
"learning_rate": 7.705826503098642e-06,
|
| 625 |
+
"loss": 0.7833,
|
| 626 |
+
"step": 880
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 0.34267013187024736,
|
| 630 |
+
"grad_norm": 0.13842502236366272,
|
| 631 |
+
"learning_rate": 7.653179634243979e-06,
|
| 632 |
+
"loss": 0.7756,
|
| 633 |
+
"step": 890
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 0.34652035807103665,
|
| 637 |
+
"grad_norm": 0.12800097465515137,
|
| 638 |
+
"learning_rate": 7.600120093927696e-06,
|
| 639 |
+
"loss": 0.7779,
|
| 640 |
+
"step": 900
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 0.350370584271826,
|
| 644 |
+
"grad_norm": 0.1420220285654068,
|
| 645 |
+
"learning_rate": 7.546656134948729e-06,
|
| 646 |
+
"loss": 0.7776,
|
| 647 |
+
"step": 910
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 0.3542208104726153,
|
| 651 |
+
"grad_norm": 0.1427285075187683,
|
| 652 |
+
"learning_rate": 7.492796073008661e-06,
|
| 653 |
+
"loss": 0.7666,
|
| 654 |
+
"step": 920
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 0.35807103667340456,
|
| 658 |
+
"grad_norm": 0.14316914975643158,
|
| 659 |
+
"learning_rate": 7.438548285418326e-06,
|
| 660 |
+
"loss": 0.7582,
|
| 661 |
+
"step": 930
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 0.36192126287419385,
|
| 665 |
+
"grad_norm": 0.14717115461826324,
|
| 666 |
+
"learning_rate": 7.3839212097948e-06,
|
| 667 |
+
"loss": 0.7964,
|
| 668 |
+
"step": 940
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 0.36577148907498314,
|
| 672 |
+
"grad_norm": 0.12921909987926483,
|
| 673 |
+
"learning_rate": 7.328923342749039e-06,
|
| 674 |
+
"loss": 0.8082,
|
| 675 |
+
"step": 950
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 0.3696217152757725,
|
| 679 |
+
"grad_norm": 0.14943553507328033,
|
| 680 |
+
"learning_rate": 7.273563238564319e-06,
|
| 681 |
+
"loss": 0.7849,
|
| 682 |
+
"step": 960
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 0.37347194147656176,
|
| 686 |
+
"grad_norm": 0.14357143640518188,
|
| 687 |
+
"learning_rate": 7.217849507865724e-06,
|
| 688 |
+
"loss": 0.7644,
|
| 689 |
+
"step": 970
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 0.37732216767735105,
|
| 693 |
+
"grad_norm": 0.13181054592132568,
|
| 694 |
+
"learning_rate": 7.161790816280858e-06,
|
| 695 |
+
"loss": 0.774,
|
| 696 |
+
"step": 980
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 0.38117239387814034,
|
| 700 |
+
"grad_norm": 0.14563539624214172,
|
| 701 |
+
"learning_rate": 7.1053958830920125e-06,
|
| 702 |
+
"loss": 0.7588,
|
| 703 |
+
"step": 990
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 0.3850226200789296,
|
| 707 |
+
"grad_norm": 0.1431891769170761,
|
| 708 |
+
"learning_rate": 7.0486734798799715e-06,
|
| 709 |
+
"loss": 0.7842,
|
| 710 |
+
"step": 1000
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 0.3888728462797189,
|
| 714 |
+
"grad_norm": 0.15157684683799744,
|
| 715 |
+
"learning_rate": 6.991632429159708e-06,
|
| 716 |
+
"loss": 0.803,
|
| 717 |
+
"step": 1010
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 0.39272307248050825,
|
| 721 |
+
"grad_norm": 0.1447536051273346,
|
| 722 |
+
"learning_rate": 6.934281603008132e-06,
|
| 723 |
+
"loss": 0.7791,
|
| 724 |
+
"step": 1020
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 0.39657329868129754,
|
| 728 |
+
"grad_norm": 0.13399897515773773,
|
| 729 |
+
"learning_rate": 6.876629921684143e-06,
|
| 730 |
+
"loss": 0.7897,
|
| 731 |
+
"step": 1030
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 0.4004235248820868,
|
| 735 |
+
"grad_norm": 0.13826017081737518,
|
| 736 |
+
"learning_rate": 6.818686352241199e-06,
|
| 737 |
+
"loss": 0.7867,
|
| 738 |
+
"step": 1040
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 0.4042737510828761,
|
| 742 |
+
"grad_norm": 0.12641464173793793,
|
| 743 |
+
"learning_rate": 6.760459907132573e-06,
|
| 744 |
+
"loss": 0.7771,
|
| 745 |
+
"step": 1050
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 0.4081239772836654,
|
| 749 |
+
"grad_norm": 0.1430540829896927,
|
| 750 |
+
"learning_rate": 6.701959642809589e-06,
|
| 751 |
+
"loss": 0.7811,
|
| 752 |
+
"step": 1060
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 0.41197420348445474,
|
| 756 |
+
"grad_norm": 0.14188537001609802,
|
| 757 |
+
"learning_rate": 6.643194658312987e-06,
|
| 758 |
+
"loss": 0.7626,
|
| 759 |
+
"step": 1070
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 0.415824429685244,
|
| 763 |
+
"grad_norm": 0.14755818247795105,
|
| 764 |
+
"learning_rate": 6.584174093857676e-06,
|
| 765 |
+
"loss": 0.7959,
|
| 766 |
+
"step": 1080
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 0.4196746558860333,
|
| 770 |
+
"grad_norm": 0.15593458712100983,
|
| 771 |
+
"learning_rate": 6.5249071294110735e-06,
|
| 772 |
+
"loss": 0.7702,
|
| 773 |
+
"step": 1090
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 0.4235248820868226,
|
| 777 |
+
"grad_norm": 0.15618066489696503,
|
| 778 |
+
"learning_rate": 6.465402983265274e-06,
|
| 779 |
+
"loss": 0.7907,
|
| 780 |
+
"step": 1100
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 0.4273751082876119,
|
| 784 |
+
"grad_norm": 0.14127320051193237,
|
| 785 |
+
"learning_rate": 6.405670910603243e-06,
|
| 786 |
+
"loss": 0.7823,
|
| 787 |
+
"step": 1110
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 0.43122533448840117,
|
| 791 |
+
"grad_norm": 0.16318608820438385,
|
| 792 |
+
"learning_rate": 6.345720202059291e-06,
|
| 793 |
+
"loss": 0.7768,
|
| 794 |
+
"step": 1120
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 0.4350755606891905,
|
| 798 |
+
"grad_norm": 0.14298468828201294,
|
| 799 |
+
"learning_rate": 6.285560182274008e-06,
|
| 800 |
+
"loss": 0.7649,
|
| 801 |
+
"step": 1130
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 0.4389257868899798,
|
| 805 |
+
"grad_norm": 0.12975069880485535,
|
| 806 |
+
"learning_rate": 6.225200208443936e-06,
|
| 807 |
+
"loss": 0.7697,
|
| 808 |
+
"step": 1140
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 0.4427760130907691,
|
| 812 |
+
"grad_norm": 0.12298456579446793,
|
| 813 |
+
"learning_rate": 6.16464966886616e-06,
|
| 814 |
+
"loss": 0.7646,
|
| 815 |
+
"step": 1150
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 0.44662623929155837,
|
| 819 |
+
"grad_norm": 0.1551104038953781,
|
| 820 |
+
"learning_rate": 6.103917981478065e-06,
|
| 821 |
+
"loss": 0.7918,
|
| 822 |
+
"step": 1160
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 0.45047646549234766,
|
| 826 |
+
"grad_norm": 0.14019982516765594,
|
| 827 |
+
"learning_rate": 6.043014592392489e-06,
|
| 828 |
+
"loss": 0.7974,
|
| 829 |
+
"step": 1170
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 0.454326691693137,
|
| 833 |
+
"grad_norm": 0.12948989868164062,
|
| 834 |
+
"learning_rate": 5.981948974428485e-06,
|
| 835 |
+
"loss": 0.7701,
|
| 836 |
+
"step": 1180
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 0.4581769178939263,
|
| 840 |
+
"grad_norm": 0.14848271012306213,
|
| 841 |
+
"learning_rate": 5.920730625637934e-06,
|
| 842 |
+
"loss": 0.7503,
|
| 843 |
+
"step": 1190
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 0.46202714409471557,
|
| 847 |
+
"grad_norm": 0.14486414194107056,
|
| 848 |
+
"learning_rate": 5.8593690678282355e-06,
|
| 849 |
+
"loss": 0.7584,
|
| 850 |
+
"step": 1200
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 0.46587737029550486,
|
| 854 |
+
"grad_norm": 0.14319123327732086,
|
| 855 |
+
"learning_rate": 5.797873845081301e-06,
|
| 856 |
+
"loss": 0.7625,
|
| 857 |
+
"step": 1210
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 0.46972759649629414,
|
| 861 |
+
"grad_norm": 0.1461380422115326,
|
| 862 |
+
"learning_rate": 5.736254522269075e-06,
|
| 863 |
+
"loss": 0.7748,
|
| 864 |
+
"step": 1220
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 0.47357782269708343,
|
| 868 |
+
"grad_norm": 0.13281452655792236,
|
| 869 |
+
"learning_rate": 5.6745206835658386e-06,
|
| 870 |
+
"loss": 0.7766,
|
| 871 |
+
"step": 1230
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 0.47742804889787277,
|
| 875 |
+
"grad_norm": 0.1348012238740921,
|
| 876 |
+
"learning_rate": 5.612681930957495e-06,
|
| 877 |
+
"loss": 0.7543,
|
| 878 |
+
"step": 1240
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 0.48127827509866206,
|
| 882 |
+
"grad_norm": 0.13633175194263458,
|
| 883 |
+
"learning_rate": 5.550747882748095e-06,
|
| 884 |
+
"loss": 0.7483,
|
| 885 |
+
"step": 1250
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 0.48512850129945134,
|
| 889 |
+
"grad_norm": 0.1510327309370041,
|
| 890 |
+
"learning_rate": 5.4887281720638195e-06,
|
| 891 |
+
"loss": 0.7531,
|
| 892 |
+
"step": 1260
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 0.48897872750024063,
|
| 896 |
+
"grad_norm": 0.15555381774902344,
|
| 897 |
+
"learning_rate": 5.42663244535466e-06,
|
| 898 |
+
"loss": 0.739,
|
| 899 |
+
"step": 1270
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 0.4928289537010299,
|
| 903 |
+
"grad_norm": 0.15309809148311615,
|
| 904 |
+
"learning_rate": 5.3644703608940205e-06,
|
| 905 |
+
"loss": 0.7435,
|
| 906 |
+
"step": 1280
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 0.49667917990181926,
|
| 910 |
+
"grad_norm": 0.141266867518425,
|
| 911 |
+
"learning_rate": 5.302251587276491e-06,
|
| 912 |
+
"loss": 0.765,
|
| 913 |
+
"step": 1290
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 0.5005294061026085,
|
| 917 |
+
"grad_norm": 0.1511782854795456,
|
| 918 |
+
"learning_rate": 5.2399858019140005e-06,
|
| 919 |
+
"loss": 0.7562,
|
| 920 |
+
"step": 1300
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 0.5043796323033978,
|
| 924 |
+
"grad_norm": 0.13981935381889343,
|
| 925 |
+
"learning_rate": 5.177682689530615e-06,
|
| 926 |
+
"loss": 0.7726,
|
| 927 |
+
"step": 1310
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 0.5082298585041871,
|
| 931 |
+
"grad_norm": 0.15519477427005768,
|
| 932 |
+
"learning_rate": 5.11535194065619e-06,
|
| 933 |
+
"loss": 0.7431,
|
| 934 |
+
"step": 1320
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 0.5120800847049765,
|
| 938 |
+
"grad_norm": 0.1570388674736023,
|
| 939 |
+
"learning_rate": 5.053003250119113e-06,
|
| 940 |
+
"loss": 0.7447,
|
| 941 |
+
"step": 1330
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 0.5159303109057657,
|
| 945 |
+
"grad_norm": 0.14974111318588257,
|
| 946 |
+
"learning_rate": 4.9906463155383925e-06,
|
| 947 |
+
"loss": 0.7546,
|
| 948 |
+
"step": 1340
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 0.519780537106555,
|
| 952 |
+
"grad_norm": 0.14333444833755493,
|
| 953 |
+
"learning_rate": 4.9282908358153046e-06,
|
| 954 |
+
"loss": 0.7457,
|
| 955 |
+
"step": 1350
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 0.5236307633073443,
|
| 959 |
+
"grad_norm": 0.16136881709098816,
|
| 960 |
+
"learning_rate": 4.8659465096248345e-06,
|
| 961 |
+
"loss": 0.752,
|
| 962 |
+
"step": 1360
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 0.5274809895081336,
|
| 966 |
+
"grad_norm": 0.1495814174413681,
|
| 967 |
+
"learning_rate": 4.803623033907169e-06,
|
| 968 |
+
"loss": 0.7564,
|
| 969 |
+
"step": 1370
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 0.5313312157089229,
|
| 973 |
+
"grad_norm": 0.13003823161125183,
|
| 974 |
+
"learning_rate": 4.741330102359441e-06,
|
| 975 |
+
"loss": 0.7642,
|
| 976 |
+
"step": 1380
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 0.5351814419097122,
|
| 980 |
+
"grad_norm": 0.1502760797739029,
|
| 981 |
+
"learning_rate": 4.679077403927996e-06,
|
| 982 |
+
"loss": 0.7368,
|
| 983 |
+
"step": 1390
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 0.5390316681105015,
|
| 987 |
+
"grad_norm": 0.13693521916866302,
|
| 988 |
+
"learning_rate": 4.616874621301373e-06,
|
| 989 |
+
"loss": 0.7454,
|
| 990 |
+
"step": 1400
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 0.5428818943112907,
|
| 994 |
+
"grad_norm": 0.14563089609146118,
|
| 995 |
+
"learning_rate": 4.554731429404293e-06,
|
| 996 |
+
"loss": 0.7612,
|
| 997 |
+
"step": 1410
|
| 998 |
+
},
|
| 999 |
+
{
|
| 1000 |
+
"epoch": 0.5467321205120801,
|
| 1001 |
+
"grad_norm": 0.15451177954673767,
|
| 1002 |
+
"learning_rate": 4.492657493892822e-06,
|
| 1003 |
+
"loss": 0.7414,
|
| 1004 |
+
"step": 1420
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 0.5505823467128694,
|
| 1008 |
+
"grad_norm": 0.16380903124809265,
|
| 1009 |
+
"learning_rate": 4.430662469650999e-06,
|
| 1010 |
+
"loss": 0.7537,
|
| 1011 |
+
"step": 1430
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 0.5544325729136587,
|
| 1015 |
+
"grad_norm": 0.1391625702381134,
|
| 1016 |
+
"learning_rate": 4.368755999289118e-06,
|
| 1017 |
+
"loss": 0.7559,
|
| 1018 |
+
"step": 1440
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 0.558282799114448,
|
| 1022 |
+
"grad_norm": 0.16195157170295715,
|
| 1023 |
+
"learning_rate": 4.306947711643949e-06,
|
| 1024 |
+
"loss": 0.7381,
|
| 1025 |
+
"step": 1450
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 0.5621330253152372,
|
| 1029 |
+
"grad_norm": 0.14465484023094177,
|
| 1030 |
+
"learning_rate": 4.245247220281068e-06,
|
| 1031 |
+
"loss": 0.7447,
|
| 1032 |
+
"step": 1460
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 0.5659832515160266,
|
| 1036 |
+
"grad_norm": 0.13382038474082947,
|
| 1037 |
+
"learning_rate": 4.183664121999587e-06,
|
| 1038 |
+
"loss": 0.739,
|
| 1039 |
+
"step": 1470
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"epoch": 0.5698334777168159,
|
| 1043 |
+
"grad_norm": 0.13878868520259857,
|
| 1044 |
+
"learning_rate": 4.122207995339474e-06,
|
| 1045 |
+
"loss": 0.7365,
|
| 1046 |
+
"step": 1480
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 0.5736837039176051,
|
| 1050 |
+
"grad_norm": 0.14558042585849762,
|
| 1051 |
+
"learning_rate": 4.060888399091734e-06,
|
| 1052 |
+
"loss": 0.7441,
|
| 1053 |
+
"step": 1490
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 0.5775339301183945,
|
| 1057 |
+
"grad_norm": 0.14093123376369476,
|
| 1058 |
+
"learning_rate": 3.999714870811639e-06,
|
| 1059 |
+
"loss": 0.7561,
|
| 1060 |
+
"step": 1500
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 0.5813841563191837,
|
| 1064 |
+
"grad_norm": 0.13405482470989227,
|
| 1065 |
+
"learning_rate": 3.938696925335275e-06,
|
| 1066 |
+
"loss": 0.7439,
|
| 1067 |
+
"step": 1510
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 0.5852343825199731,
|
| 1071 |
+
"grad_norm": 0.1446416974067688,
|
| 1072 |
+
"learning_rate": 3.87784405329962e-06,
|
| 1073 |
+
"loss": 0.7505,
|
| 1074 |
+
"step": 1520
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 0.5890846087207623,
|
| 1078 |
+
"grad_norm": 0.15154443681240082,
|
| 1079 |
+
"learning_rate": 3.817165719666382e-06,
|
| 1080 |
+
"loss": 0.7484,
|
| 1081 |
+
"step": 1530
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 0.5929348349215516,
|
| 1085 |
+
"grad_norm": 0.13240064680576324,
|
| 1086 |
+
"learning_rate": 3.756671362249841e-06,
|
| 1087 |
+
"loss": 0.7591,
|
| 1088 |
+
"step": 1540
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 0.596785061122341,
|
| 1092 |
+
"grad_norm": 0.14146126806735992,
|
| 1093 |
+
"learning_rate": 3.6963703902488907e-06,
|
| 1094 |
+
"loss": 0.7489,
|
| 1095 |
+
"step": 1550
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 0.6006352873231302,
|
| 1099 |
+
"grad_norm": 0.1354767084121704,
|
| 1100 |
+
"learning_rate": 3.6362721827835655e-06,
|
| 1101 |
+
"loss": 0.7585,
|
| 1102 |
+
"step": 1560
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 0.6044855135239195,
|
| 1106 |
+
"grad_norm": 0.14563101530075073,
|
| 1107 |
+
"learning_rate": 3.576386087436212e-06,
|
| 1108 |
+
"loss": 0.7489,
|
| 1109 |
+
"step": 1570
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 0.6083357397247088,
|
| 1113 |
+
"grad_norm": 0.13970331847667694,
|
| 1114 |
+
"learning_rate": 3.5167214187975913e-06,
|
| 1115 |
+
"loss": 0.7521,
|
| 1116 |
+
"step": 1580
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 0.6121859659254981,
|
| 1120 |
+
"grad_norm": 0.12202169001102448,
|
| 1121 |
+
"learning_rate": 3.457287457018086e-06,
|
| 1122 |
+
"loss": 0.747,
|
| 1123 |
+
"step": 1590
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 0.6160361921262875,
|
| 1127 |
+
"grad_norm": 0.12871259450912476,
|
| 1128 |
+
"learning_rate": 3.3980934463643003e-06,
|
| 1129 |
+
"loss": 0.7332,
|
| 1130 |
+
"step": 1600
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 0.6198864183270767,
|
| 1134 |
+
"grad_norm": 0.12659740447998047,
|
| 1135 |
+
"learning_rate": 3.3391485937812053e-06,
|
| 1136 |
+
"loss": 0.7128,
|
| 1137 |
+
"step": 1610
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 0.623736644527866,
|
| 1141 |
+
"grad_norm": 0.13491244614124298,
|
| 1142 |
+
"learning_rate": 3.280462067460115e-06,
|
| 1143 |
+
"loss": 0.716,
|
| 1144 |
+
"step": 1620
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 0.6275868707286553,
|
| 1148 |
+
"grad_norm": 0.1250947117805481,
|
| 1149 |
+
"learning_rate": 3.222042995412669e-06,
|
| 1150 |
+
"loss": 0.7542,
|
| 1151 |
+
"step": 1630
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 0.6314370969294446,
|
| 1155 |
+
"grad_norm": 0.12391701340675354,
|
| 1156 |
+
"learning_rate": 3.163900464051089e-06,
|
| 1157 |
+
"loss": 0.7333,
|
| 1158 |
+
"step": 1640
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 0.635287323130234,
|
| 1162 |
+
"grad_norm": 0.13705404102802277,
|
| 1163 |
+
"learning_rate": 3.1060435167748826e-06,
|
| 1164 |
+
"loss": 0.7462,
|
| 1165 |
+
"step": 1650
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 0.6391375493310232,
|
| 1169 |
+
"grad_norm": 0.13799619674682617,
|
| 1170 |
+
"learning_rate": 3.048481152564253e-06,
|
| 1171 |
+
"loss": 0.7334,
|
| 1172 |
+
"step": 1660
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 0.6429877755318125,
|
| 1176 |
+
"grad_norm": 0.14441215991973877,
|
| 1177 |
+
"learning_rate": 2.9912223245804017e-06,
|
| 1178 |
+
"loss": 0.7573,
|
| 1179 |
+
"step": 1670
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 0.6468380017326018,
|
| 1183 |
+
"grad_norm": 0.13752642273902893,
|
| 1184 |
+
"learning_rate": 2.934275938772981e-06,
|
| 1185 |
+
"loss": 0.7361,
|
| 1186 |
+
"step": 1680
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 0.6506882279333911,
|
| 1190 |
+
"grad_norm": 0.14676566421985626,
|
| 1191 |
+
"learning_rate": 2.8776508524948676e-06,
|
| 1192 |
+
"loss": 0.726,
|
| 1193 |
+
"step": 1690
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 0.6545384541341804,
|
| 1197 |
+
"grad_norm": 0.12551912665367126,
|
| 1198 |
+
"learning_rate": 2.821355873124503e-06,
|
| 1199 |
+
"loss": 0.7233,
|
| 1200 |
+
"step": 1700
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 0.6583886803349697,
|
| 1204 |
+
"grad_norm": 0.13812437653541565,
|
| 1205 |
+
"learning_rate": 2.7653997566960144e-06,
|
| 1206 |
+
"loss": 0.7453,
|
| 1207 |
+
"step": 1710
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"epoch": 0.662238906535759,
|
| 1211 |
+
"grad_norm": 0.1325712651014328,
|
| 1212 |
+
"learning_rate": 2.709791206537309e-06,
|
| 1213 |
+
"loss": 0.7351,
|
| 1214 |
+
"step": 1720
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 0.6660891327365482,
|
| 1218 |
+
"grad_norm": 0.130569189786911,
|
| 1219 |
+
"learning_rate": 2.6545388719163747e-06,
|
| 1220 |
+
"loss": 0.7335,
|
| 1221 |
+
"step": 1730
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 0.6699393589373376,
|
| 1225 |
+
"grad_norm": 0.13003569841384888,
|
| 1226 |
+
"learning_rate": 2.599651346695979e-06,
|
| 1227 |
+
"loss": 0.743,
|
| 1228 |
+
"step": 1740
|
| 1229 |
+
},
|
| 1230 |
+
{
|
| 1231 |
+
"epoch": 0.6737895851381268,
|
| 1232 |
+
"grad_norm": 0.14079348742961884,
|
| 1233 |
+
"learning_rate": 2.545137167997007e-06,
|
| 1234 |
+
"loss": 0.7378,
|
| 1235 |
+
"step": 1750
|
| 1236 |
+
},
|
| 1237 |
+
{
|
| 1238 |
+
"epoch": 0.6776398113389162,
|
| 1239 |
+
"grad_norm": 0.12829728424549103,
|
| 1240 |
+
"learning_rate": 2.4910048148705972e-06,
|
| 1241 |
+
"loss": 0.7223,
|
| 1242 |
+
"step": 1760
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 0.6814900375397055,
|
| 1246 |
+
"grad_norm": 0.14342281222343445,
|
| 1247 |
+
"learning_rate": 2.4372627069793327e-06,
|
| 1248 |
+
"loss": 0.7669,
|
| 1249 |
+
"step": 1770
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 0.6853402637404947,
|
| 1253 |
+
"grad_norm": 0.13588860630989075,
|
| 1254 |
+
"learning_rate": 2.3839192032876486e-06,
|
| 1255 |
+
"loss": 0.749,
|
| 1256 |
+
"step": 1780
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 0.6891904899412841,
|
| 1260 |
+
"grad_norm": 0.13018709421157837,
|
| 1261 |
+
"learning_rate": 2.3309826007617047e-06,
|
| 1262 |
+
"loss": 0.7604,
|
| 1263 |
+
"step": 1790
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 0.6930407161420733,
|
| 1267 |
+
"grad_norm": 0.1287711262702942,
|
| 1268 |
+
"learning_rate": 2.278461133078881e-06,
|
| 1269 |
+
"loss": 0.7248,
|
| 1270 |
+
"step": 1800
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 0.6968909423428626,
|
| 1274 |
+
"grad_norm": 0.13316252827644348,
|
| 1275 |
+
"learning_rate": 2.2263629693471258e-06,
|
| 1276 |
+
"loss": 0.7199,
|
| 1277 |
+
"step": 1810
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 0.700741168543652,
|
| 1281 |
+
"grad_norm": 0.13107992708683014,
|
| 1282 |
+
"learning_rate": 2.1746962128343414e-06,
|
| 1283 |
+
"loss": 0.7436,
|
| 1284 |
+
"step": 1820
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 0.7045913947444412,
|
| 1288 |
+
"grad_norm": 0.1293720155954361,
|
| 1289 |
+
"learning_rate": 2.1234688997080183e-06,
|
| 1290 |
+
"loss": 0.7415,
|
| 1291 |
+
"step": 1830
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 0.7084416209452306,
|
| 1295 |
+
"grad_norm": 0.14652466773986816,
|
| 1296 |
+
"learning_rate": 2.0726889977853053e-06,
|
| 1297 |
+
"loss": 0.737,
|
| 1298 |
+
"step": 1840
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 0.7122918471460198,
|
| 1302 |
+
"grad_norm": 0.14027106761932373,
|
| 1303 |
+
"learning_rate": 2.022364405293703e-06,
|
| 1304 |
+
"loss": 0.7489,
|
| 1305 |
+
"step": 1850
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 0.7161420733468091,
|
| 1309 |
+
"grad_norm": 0.12798205018043518,
|
| 1310 |
+
"learning_rate": 1.9725029496425814e-06,
|
| 1311 |
+
"loss": 0.745,
|
| 1312 |
+
"step": 1860
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 0.7199922995475985,
|
| 1316 |
+
"grad_norm": 0.13873092830181122,
|
| 1317 |
+
"learning_rate": 1.923112386205727e-06,
|
| 1318 |
+
"loss": 0.7408,
|
| 1319 |
+
"step": 1870
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 0.7238425257483877,
|
| 1323 |
+
"grad_norm": 0.13162294030189514,
|
| 1324 |
+
"learning_rate": 1.874200397115079e-06,
|
| 1325 |
+
"loss": 0.7462,
|
| 1326 |
+
"step": 1880
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 0.727692751949177,
|
| 1330 |
+
"grad_norm": 0.13253897428512573,
|
| 1331 |
+
"learning_rate": 1.825774590065857e-06,
|
| 1332 |
+
"loss": 0.7331,
|
| 1333 |
+
"step": 1890
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 0.7315429781499663,
|
| 1337 |
+
"grad_norm": 0.14175915718078613,
|
| 1338 |
+
"learning_rate": 1.7778424971332813e-06,
|
| 1339 |
+
"loss": 0.7399,
|
| 1340 |
+
"step": 1900
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 0.7353932043507556,
|
| 1344 |
+
"grad_norm": 0.13126352429389954,
|
| 1345 |
+
"learning_rate": 1.7304115736010407e-06,
|
| 1346 |
+
"loss": 0.741,
|
| 1347 |
+
"step": 1910
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 0.739243430551545,
|
| 1351 |
+
"grad_norm": 0.13206543028354645,
|
| 1352 |
+
"learning_rate": 1.6834891968017108e-06,
|
| 1353 |
+
"loss": 0.7324,
|
| 1354 |
+
"step": 1920
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 0.7430936567523342,
|
| 1358 |
+
"grad_norm": 0.13869385421276093,
|
| 1359 |
+
"learning_rate": 1.6370826649692884e-06,
|
| 1360 |
+
"loss": 0.7431,
|
| 1361 |
+
"step": 1930
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 0.7469438829531235,
|
| 1365 |
+
"grad_norm": 0.14449474215507507,
|
| 1366 |
+
"learning_rate": 1.5911991961040463e-06,
|
| 1367 |
+
"loss": 0.7577,
|
| 1368 |
+
"step": 1940
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 0.7507941091539128,
|
| 1372 |
+
"grad_norm": 0.13642597198486328,
|
| 1373 |
+
"learning_rate": 1.545845926849851e-06,
|
| 1374 |
+
"loss": 0.7444,
|
| 1375 |
+
"step": 1950
|
| 1376 |
+
},
|
| 1377 |
+
{
|
| 1378 |
+
"epoch": 0.7546443353547021,
|
| 1379 |
+
"grad_norm": 0.13580723106861115,
|
| 1380 |
+
"learning_rate": 1.5010299113841397e-06,
|
| 1381 |
+
"loss": 0.7585,
|
| 1382 |
+
"step": 1960
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 0.7584945615554913,
|
| 1386 |
+
"grad_norm": 0.1363590508699417,
|
| 1387 |
+
"learning_rate": 1.4567581203207238e-06,
|
| 1388 |
+
"loss": 0.7565,
|
| 1389 |
+
"step": 1970
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 0.7623447877562807,
|
| 1393 |
+
"grad_norm": 0.1385650783777237,
|
| 1394 |
+
"learning_rate": 1.413037439625593e-06,
|
| 1395 |
+
"loss": 0.7378,
|
| 1396 |
+
"step": 1980
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 0.76619501395707,
|
| 1400 |
+
"grad_norm": 0.15039239823818207,
|
| 1401 |
+
"learning_rate": 1.3698746695458847e-06,
|
| 1402 |
+
"loss": 0.7406,
|
| 1403 |
+
"step": 1990
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 0.7700452401578592,
|
| 1407 |
+
"grad_norm": 0.12879180908203125,
|
| 1408 |
+
"learning_rate": 1.3272765235521745e-06,
|
| 1409 |
+
"loss": 0.7417,
|
| 1410 |
+
"step": 2000
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"epoch": 0.7738954663586486,
|
| 1414 |
+
"grad_norm": 0.13226978480815887,
|
| 1415 |
+
"learning_rate": 1.2852496272942877e-06,
|
| 1416 |
+
"loss": 0.7404,
|
| 1417 |
+
"step": 2010
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 0.7777456925594378,
|
| 1421 |
+
"grad_norm": 0.1269710808992386,
|
| 1422 |
+
"learning_rate": 1.2438005175707396e-06,
|
| 1423 |
+
"loss": 0.7261,
|
| 1424 |
+
"step": 2020
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 0.7815959187602272,
|
| 1428 |
+
"grad_norm": 0.13727910816669464,
|
| 1429 |
+
"learning_rate": 1.2029356413120297e-06,
|
| 1430 |
+
"loss": 0.7122,
|
| 1431 |
+
"step": 2030
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 0.7854461449610165,
|
| 1435 |
+
"grad_norm": 0.13390226662158966,
|
| 1436 |
+
"learning_rate": 1.1626613545778786e-06,
|
| 1437 |
+
"loss": 0.7315,
|
| 1438 |
+
"step": 2040
|
| 1439 |
+
},
|
| 1440 |
+
{
|
| 1441 |
+
"epoch": 0.7892963711618057,
|
| 1442 |
+
"grad_norm": 0.12796558439731598,
|
| 1443 |
+
"learning_rate": 1.1229839215686294e-06,
|
| 1444 |
+
"loss": 0.7398,
|
| 1445 |
+
"step": 2050
|
| 1446 |
+
},
|
| 1447 |
+
{
|
| 1448 |
+
"epoch": 0.7931465973625951,
|
| 1449 |
+
"grad_norm": 0.13517889380455017,
|
| 1450 |
+
"learning_rate": 1.0839095136509188e-06,
|
| 1451 |
+
"loss": 0.7177,
|
| 1452 |
+
"step": 2060
|
| 1453 |
+
},
|
| 1454 |
+
{
|
| 1455 |
+
"epoch": 0.7969968235633843,
|
| 1456 |
+
"grad_norm": 0.14495965838432312,
|
| 1457 |
+
"learning_rate": 1.045444208397791e-06,
|
| 1458 |
+
"loss": 0.7298,
|
| 1459 |
+
"step": 2070
|
| 1460 |
+
},
|
| 1461 |
+
{
|
| 1462 |
+
"epoch": 0.8008470497641736,
|
| 1463 |
+
"grad_norm": 0.13551703095436096,
|
| 1464 |
+
"learning_rate": 1.007593988643402e-06,
|
| 1465 |
+
"loss": 0.7176,
|
| 1466 |
+
"step": 2080
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 0.804697275964963,
|
| 1470 |
+
"grad_norm": 0.12823078036308289,
|
| 1471 |
+
"learning_rate": 9.703647415524613e-07,
|
| 1472 |
+
"loss": 0.741,
|
| 1473 |
+
"step": 2090
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 0.8085475021657522,
|
| 1477 |
+
"grad_norm": 0.12874028086662292,
|
| 1478 |
+
"learning_rate": 9.337622577045485e-07,
|
| 1479 |
+
"loss": 0.7349,
|
| 1480 |
+
"step": 2100
|
| 1481 |
+
},
|
| 1482 |
+
{
|
| 1483 |
+
"epoch": 0.8123977283665416,
|
| 1484 |
+
"grad_norm": 0.1297380030155182,
|
| 1485 |
+
"learning_rate": 8.977922301934588e-07,
|
| 1486 |
+
"loss": 0.7492,
|
| 1487 |
+
"step": 2110
|
| 1488 |
+
},
|
| 1489 |
+
{
|
| 1490 |
+
"epoch": 0.8162479545673308,
|
| 1491 |
+
"grad_norm": 0.1361517459154129,
|
| 1492 |
+
"learning_rate": 8.624602537417009e-07,
|
| 1493 |
+
"loss": 0.7471,
|
| 1494 |
+
"step": 2120
|
| 1495 |
+
},
|
| 1496 |
+
{
|
| 1497 |
+
"epoch": 0.8200981807681201,
|
| 1498 |
+
"grad_norm": 0.13480858504772186,
|
| 1499 |
+
"learning_rate": 8.277718238303123e-07,
|
| 1500 |
+
"loss": 0.7305,
|
| 1501 |
+
"step": 2130
|
| 1502 |
+
},
|
| 1503 |
+
{
|
| 1504 |
+
"epoch": 0.8239484069689095,
|
| 1505 |
+
"grad_norm": 0.12938202917575836,
|
| 1506 |
+
"learning_rate": 7.937323358440935e-07,
|
| 1507 |
+
"loss": 0.741,
|
| 1508 |
+
"step": 2140
|
| 1509 |
+
},
|
| 1510 |
+
{
|
| 1511 |
+
"epoch": 0.8277986331696987,
|
| 1512 |
+
"grad_norm": 0.14773258566856384,
|
| 1513 |
+
"learning_rate": 7.603470842324223e-07,
|
| 1514 |
+
"loss": 0.7251,
|
| 1515 |
+
"step": 2150
|
| 1516 |
+
},
|
| 1517 |
+
{
|
| 1518 |
+
"epoch": 0.831648859370488,
|
| 1519 |
+
"grad_norm": 0.12063921988010406,
|
| 1520 |
+
"learning_rate": 7.276212616857575e-07,
|
| 1521 |
+
"loss": 0.7426,
|
| 1522 |
+
"step": 2160
|
| 1523 |
+
},
|
| 1524 |
+
{
|
| 1525 |
+
"epoch": 0.8354990855712773,
|
| 1526 |
+
"grad_norm": 0.1360403150320053,
|
| 1527 |
+
"learning_rate": 6.955599583279837e-07,
|
| 1528 |
+
"loss": 0.7443,
|
| 1529 |
+
"step": 2170
|
| 1530 |
+
},
|
| 1531 |
+
{
|
| 1532 |
+
"epoch": 0.8393493117720666,
|
| 1533 |
+
"grad_norm": 0.1347588300704956,
|
| 1534 |
+
"learning_rate": 6.641681609246981e-07,
|
| 1535 |
+
"loss": 0.7348,
|
| 1536 |
+
"step": 2180
|
| 1537 |
+
},
|
| 1538 |
+
{
|
| 1539 |
+
"epoch": 0.8431995379728559,
|
| 1540 |
+
"grad_norm": 0.13563336431980133,
|
| 1541 |
+
"learning_rate": 6.334507521075711e-07,
|
| 1542 |
+
"loss": 0.7422,
|
| 1543 |
+
"step": 2190
|
| 1544 |
+
},
|
| 1545 |
+
{
|
| 1546 |
+
"epoch": 0.8470497641736452,
|
| 1547 |
+
"grad_norm": 0.14780844748020172,
|
| 1548 |
+
"learning_rate": 6.034125096149179e-07,
|
| 1549 |
+
"loss": 0.7298,
|
| 1550 |
+
"step": 2200
|
| 1551 |
+
},
|
| 1552 |
+
{
|
| 1553 |
+
"epoch": 0.8508999903744345,
|
| 1554 |
+
"grad_norm": 0.15709814429283142,
|
| 1555 |
+
"learning_rate": 5.740581055485722e-07,
|
| 1556 |
+
"loss": 0.7177,
|
| 1557 |
+
"step": 2210
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"epoch": 0.8547502165752238,
|
| 1561 |
+
"grad_norm": 0.12437284737825394,
|
| 1562 |
+
"learning_rate": 5.453921056471961e-07,
|
| 1563 |
+
"loss": 0.7395,
|
| 1564 |
+
"step": 2220
|
| 1565 |
+
},
|
| 1566 |
+
{
|
| 1567 |
+
"epoch": 0.8586004427760131,
|
| 1568 |
+
"grad_norm": 0.14509905874729156,
|
| 1569 |
+
"learning_rate": 5.174189685761288e-07,
|
| 1570 |
+
"loss": 0.7321,
|
| 1571 |
+
"step": 2230
|
| 1572 |
+
},
|
| 1573 |
+
{
|
| 1574 |
+
"epoch": 0.8624506689768023,
|
| 1575 |
+
"grad_norm": 0.12840333580970764,
|
| 1576 |
+
"learning_rate": 4.901430452338979e-07,
|
| 1577 |
+
"loss": 0.7515,
|
| 1578 |
+
"step": 2240
|
| 1579 |
+
},
|
| 1580 |
+
{
|
| 1581 |
+
"epoch": 0.8663008951775917,
|
| 1582 |
+
"grad_norm": 0.14008638262748718,
|
| 1583 |
+
"learning_rate": 4.6356857807548286e-07,
|
| 1584 |
+
"loss": 0.7311,
|
| 1585 |
+
"step": 2250
|
| 1586 |
+
},
|
| 1587 |
+
{
|
| 1588 |
+
"epoch": 0.870151121378381,
|
| 1589 |
+
"grad_norm": 0.14244788885116577,
|
| 1590 |
+
"learning_rate": 4.376997004524541e-07,
|
| 1591 |
+
"loss": 0.7202,
|
| 1592 |
+
"step": 2260
|
| 1593 |
+
},
|
| 1594 |
+
{
|
| 1595 |
+
"epoch": 0.8740013475791703,
|
| 1596 |
+
"grad_norm": 0.1272694617509842,
|
| 1597 |
+
"learning_rate": 4.12540435970073e-07,
|
| 1598 |
+
"loss": 0.7216,
|
| 1599 |
+
"step": 2270
|
| 1600 |
+
},
|
| 1601 |
+
{
|
| 1602 |
+
"epoch": 0.8778515737799596,
|
| 1603 |
+
"grad_norm": 0.12792038917541504,
|
| 1604 |
+
"learning_rate": 3.880946978614703e-07,
|
| 1605 |
+
"loss": 0.7441,
|
| 1606 |
+
"step": 2280
|
| 1607 |
+
},
|
| 1608 |
+
{
|
| 1609 |
+
"epoch": 0.8817017999807488,
|
| 1610 |
+
"grad_norm": 0.1292717158794403,
|
| 1611 |
+
"learning_rate": 3.643662883789878e-07,
|
| 1612 |
+
"loss": 0.7414,
|
| 1613 |
+
"step": 2290
|
| 1614 |
+
},
|
| 1615 |
+
{
|
| 1616 |
+
"epoch": 0.8855520261815382,
|
| 1617 |
+
"grad_norm": 0.12878689169883728,
|
| 1618 |
+
"learning_rate": 3.41358898202781e-07,
|
| 1619 |
+
"loss": 0.7253,
|
| 1620 |
+
"step": 2300
|
| 1621 |
+
},
|
| 1622 |
+
{
|
| 1623 |
+
"epoch": 0.8894022523823275,
|
| 1624 |
+
"grad_norm": 0.12738415598869324,
|
| 1625 |
+
"learning_rate": 3.190761058667741e-07,
|
| 1626 |
+
"loss": 0.7268,
|
| 1627 |
+
"step": 2310
|
| 1628 |
+
},
|
| 1629 |
+
{
|
| 1630 |
+
"epoch": 0.8932524785831167,
|
| 1631 |
+
"grad_norm": 0.1236555427312851,
|
| 1632 |
+
"learning_rate": 2.9752137720206463e-07,
|
| 1633 |
+
"loss": 0.7361,
|
| 1634 |
+
"step": 2320
|
| 1635 |
+
},
|
| 1636 |
+
{
|
| 1637 |
+
"epoch": 0.8971027047839061,
|
| 1638 |
+
"grad_norm": 0.13710542023181915,
|
| 1639 |
+
"learning_rate": 2.7669806479785067e-07,
|
| 1640 |
+
"loss": 0.7476,
|
| 1641 |
+
"step": 2330
|
| 1642 |
+
},
|
| 1643 |
+
{
|
| 1644 |
+
"epoch": 0.9009529309846953,
|
| 1645 |
+
"grad_norm": 0.13367974758148193,
|
| 1646 |
+
"learning_rate": 2.566094074799763e-07,
|
| 1647 |
+
"loss": 0.7367,
|
| 1648 |
+
"step": 2340
|
| 1649 |
+
},
|
| 1650 |
+
{
|
| 1651 |
+
"epoch": 0.9048031571854847,
|
| 1652 |
+
"grad_norm": 0.12953899800777435,
|
| 1653 |
+
"learning_rate": 2.3725852980716557e-07,
|
| 1654 |
+
"loss": 0.7235,
|
| 1655 |
+
"step": 2350
|
| 1656 |
+
},
|
| 1657 |
+
{
|
| 1658 |
+
"epoch": 0.908653383386274,
|
| 1659 |
+
"grad_norm": 0.1292690932750702,
|
| 1660 |
+
"learning_rate": 2.1864844158503983e-07,
|
| 1661 |
+
"loss": 0.7366,
|
| 1662 |
+
"step": 2360
|
| 1663 |
+
},
|
| 1664 |
+
{
|
| 1665 |
+
"epoch": 0.9125036095870632,
|
| 1666 |
+
"grad_norm": 0.14230944216251373,
|
| 1667 |
+
"learning_rate": 2.007820373979702e-07,
|
| 1668 |
+
"loss": 0.7242,
|
| 1669 |
+
"step": 2370
|
| 1670 |
+
},
|
| 1671 |
+
{
|
| 1672 |
+
"epoch": 0.9163538357878526,
|
| 1673 |
+
"grad_norm": 0.14069274067878723,
|
| 1674 |
+
"learning_rate": 1.8366209615886532e-07,
|
| 1675 |
+
"loss": 0.73,
|
| 1676 |
+
"step": 2380
|
| 1677 |
+
},
|
| 1678 |
+
{
|
| 1679 |
+
"epoch": 0.9202040619886418,
|
| 1680 |
+
"grad_norm": 0.12800656259059906,
|
| 1681 |
+
"learning_rate": 1.6729128067693613e-07,
|
| 1682 |
+
"loss": 0.7519,
|
| 1683 |
+
"step": 2390
|
| 1684 |
+
},
|
| 1685 |
+
{
|
| 1686 |
+
"epoch": 0.9240542881894311,
|
| 1687 |
+
"grad_norm": 0.13675320148468018,
|
| 1688 |
+
"learning_rate": 1.5167213724353426e-07,
|
| 1689 |
+
"loss": 0.741,
|
| 1690 |
+
"step": 2400
|
| 1691 |
+
},
|
| 1692 |
+
{
|
| 1693 |
+
"epoch": 0.9279045143902205,
|
| 1694 |
+
"grad_norm": 0.13248597085475922,
|
| 1695 |
+
"learning_rate": 1.3680709523610058e-07,
|
| 1696 |
+
"loss": 0.7259,
|
| 1697 |
+
"step": 2410
|
| 1698 |
+
},
|
| 1699 |
+
{
|
| 1700 |
+
"epoch": 0.9317547405910097,
|
| 1701 |
+
"grad_norm": 0.12239091098308563,
|
| 1702 |
+
"learning_rate": 1.2269846674030418e-07,
|
| 1703 |
+
"loss": 0.7523,
|
| 1704 |
+
"step": 2420
|
| 1705 |
+
},
|
| 1706 |
+
{
|
| 1707 |
+
"epoch": 0.935604966791799,
|
| 1708 |
+
"grad_norm": 0.13336412608623505,
|
| 1709 |
+
"learning_rate": 1.0934844619042595e-07,
|
| 1710 |
+
"loss": 0.7464,
|
| 1711 |
+
"step": 2430
|
| 1712 |
+
},
|
| 1713 |
+
{
|
| 1714 |
+
"epoch": 0.9394551929925883,
|
| 1715 |
+
"grad_norm": 0.1355394870042801,
|
| 1716 |
+
"learning_rate": 9.675911002803961e-08,
|
| 1717 |
+
"loss": 0.7324,
|
| 1718 |
+
"step": 2440
|
| 1719 |
+
},
|
| 1720 |
+
{
|
| 1721 |
+
"epoch": 0.9433054191933776,
|
| 1722 |
+
"grad_norm": 0.14172327518463135,
|
| 1723 |
+
"learning_rate": 8.493241637904381e-08,
|
| 1724 |
+
"loss": 0.7303,
|
| 1725 |
+
"step": 2450
|
| 1726 |
+
},
|
| 1727 |
+
{
|
| 1728 |
+
"epoch": 0.9471556453941669,
|
| 1729 |
+
"grad_norm": 0.15374283492565155,
|
| 1730 |
+
"learning_rate": 7.387020474909689e-08,
|
| 1731 |
+
"loss": 0.7544,
|
| 1732 |
+
"step": 2460
|
| 1733 |
+
},
|
| 1734 |
+
{
|
| 1735 |
+
"epoch": 0.9510058715949562,
|
| 1736 |
+
"grad_norm": 0.14511826634407043,
|
| 1737 |
+
"learning_rate": 6.357419573750856e-08,
|
| 1738 |
+
"loss": 0.7382,
|
| 1739 |
+
"step": 2470
|
| 1740 |
+
},
|
| 1741 |
+
{
|
| 1742 |
+
"epoch": 0.9548560977957455,
|
| 1743 |
+
"grad_norm": 0.13343992829322815,
|
| 1744 |
+
"learning_rate": 5.4045990769613365e-08,
|
| 1745 |
+
"loss": 0.7325,
|
| 1746 |
+
"step": 2480
|
| 1747 |
+
},
|
| 1748 |
+
{
|
| 1749 |
+
"epoch": 0.9587063239965348,
|
| 1750 |
+
"grad_norm": 0.15269556641578674,
|
| 1751 |
+
"learning_rate": 4.5287071847694434e-08,
|
| 1752 |
+
"loss": 0.7313,
|
| 1753 |
+
"step": 2490
|
| 1754 |
+
},
|
| 1755 |
+
{
|
| 1756 |
+
"epoch": 0.9625565501973241,
|
| 1757 |
+
"grad_norm": 0.13471044600009918,
|
| 1758 |
+
"learning_rate": 3.7298801320467817e-08,
|
| 1759 |
+
"loss": 0.7317,
|
| 1760 |
+
"step": 2500
|
| 1761 |
+
},
|
| 1762 |
+
{
|
| 1763 |
+
"epoch": 0.9664067763981133,
|
| 1764 |
+
"grad_norm": 0.13945548236370087,
|
| 1765 |
+
"learning_rate": 3.0082421671192576e-08,
|
| 1766 |
+
"loss": 0.7242,
|
| 1767 |
+
"step": 2510
|
| 1768 |
+
},
|
| 1769 |
+
{
|
| 1770 |
+
"epoch": 0.9702570025989027,
|
| 1771 |
+
"grad_norm": 0.1254354566335678,
|
| 1772 |
+
"learning_rate": 2.3639055324410355e-08,
|
| 1773 |
+
"loss": 0.7439,
|
| 1774 |
+
"step": 2520
|
| 1775 |
+
},
|
| 1776 |
+
{
|
| 1777 |
+
"epoch": 0.974107228799692,
|
| 1778 |
+
"grad_norm": 0.13077786564826965,
|
| 1779 |
+
"learning_rate": 1.7969704471369477e-08,
|
| 1780 |
+
"loss": 0.7275,
|
| 1781 |
+
"step": 2530
|
| 1782 |
+
},
|
| 1783 |
+
{
|
| 1784 |
+
"epoch": 0.9779574550004813,
|
| 1785 |
+
"grad_norm": 0.1236303374171257,
|
| 1786 |
+
"learning_rate": 1.3075250914142413e-08,
|
| 1787 |
+
"loss": 0.7352,
|
| 1788 |
+
"step": 2540
|
| 1789 |
+
},
|
| 1790 |
+
{
|
| 1791 |
+
"epoch": 0.9818076812012706,
|
| 1792 |
+
"grad_norm": 0.12779894471168518,
|
| 1793 |
+
"learning_rate": 8.956455928476049e-09,
|
| 1794 |
+
"loss": 0.7461,
|
| 1795 |
+
"step": 2550
|
| 1796 |
+
},
|
| 1797 |
+
{
|
| 1798 |
+
"epoch": 0.9856579074020598,
|
| 1799 |
+
"grad_norm": 0.12238665670156479,
|
| 1800 |
+
"learning_rate": 5.6139601453786275e-09,
|
| 1801 |
+
"loss": 0.7223,
|
| 1802 |
+
"step": 2560
|
| 1803 |
+
},
|
| 1804 |
+
{
|
| 1805 |
+
"epoch": 0.9895081336028492,
|
| 1806 |
+
"grad_norm": 0.14039477705955505,
|
| 1807 |
+
"learning_rate": 3.0482834514805602e-09,
|
| 1808 |
+
"loss": 0.7277,
|
| 1809 |
+
"step": 2570
|
| 1810 |
+
},
|
| 1811 |
+
{
|
| 1812 |
+
"epoch": 0.9933583598036385,
|
| 1813 |
+
"grad_norm": 0.11777046322822571,
|
| 1814 |
+
"learning_rate": 1.2598249081713366e-09,
|
| 1815 |
+
"loss": 0.7116,
|
| 1816 |
+
"step": 2580
|
| 1817 |
+
},
|
| 1818 |
+
{
|
| 1819 |
+
"epoch": 0.9972085860044277,
|
| 1820 |
+
"grad_norm": 0.13140827417373657,
|
| 1821 |
+
"learning_rate": 2.488626895302826e-10,
|
| 1822 |
+
"loss": 0.7452,
|
| 1823 |
+
"step": 2590
|
| 1824 |
+
},
|
| 1825 |
+
{
|
| 1826 |
+
"epoch": 0.9999037443449803,
|
| 1827 |
+
"step": 2597,
|
| 1828 |
+
"total_flos": 6.574630501712134e+18,
|
| 1829 |
+
"train_loss": 0.788680609253952,
|
| 1830 |
+
"train_runtime": 22327.0315,
|
| 1831 |
+
"train_samples_per_second": 29.78,
|
| 1832 |
+
"train_steps_per_second": 0.116
|
| 1833 |
+
}
|
| 1834 |
+
],
|
| 1835 |
+
"logging_steps": 10,
|
| 1836 |
+
"max_steps": 2597,
|
| 1837 |
+
"num_input_tokens_seen": 332174164,
|
| 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": 6.574630501712134e+18,
|
| 1853 |
+
"train_batch_size": 4,
|
| 1854 |
+
"trial_name": null,
|
| 1855 |
+
"trial_params": null
|
| 1856 |
+
}
|
continuous/qwen3/pe_core_g14_448/finetune/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2f28671e8cfb18da93f94bf2bdde800ea373fc89c2fe182c47301aded59ca2aa
|
| 3 |
+
size 6264
|
continuous/qwen3/pe_core_g14_448/finetune/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
continuous/qwen3/pe_core_g14_448/pretrain/config.json
ADDED
|
@@ -0,0 +1,89 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_faster_video": false,
|
| 3 |
+
"add_time_instruction": false,
|
| 4 |
+
"architectures": [
|
| 5 |
+
"Qwen3ForCausalLM"
|
| 6 |
+
],
|
| 7 |
+
"attention_bias": false,
|
| 8 |
+
"attention_dropout": 0.0,
|
| 9 |
+
"dtype": "bfloat16",
|
| 10 |
+
"eos_token_id": 151645,
|
| 11 |
+
"faster_token_stride": 10,
|
| 12 |
+
"force_sample": false,
|
| 13 |
+
"head_dim": 128,
|
| 14 |
+
"hidden_act": "silu",
|
| 15 |
+
"hidden_size": 2048,
|
| 16 |
+
"image_aspect_ratio": "square",
|
| 17 |
+
"image_crop_resolution": null,
|
| 18 |
+
"image_grid_pinpoints": null,
|
| 19 |
+
"image_split_resolution": null,
|
| 20 |
+
"initializer_range": 0.02,
|
| 21 |
+
"intermediate_size": 6144,
|
| 22 |
+
"layer_types": [
|
| 23 |
+
"full_attention",
|
| 24 |
+
"full_attention",
|
| 25 |
+
"full_attention",
|
| 26 |
+
"full_attention",
|
| 27 |
+
"full_attention",
|
| 28 |
+
"full_attention",
|
| 29 |
+
"full_attention",
|
| 30 |
+
"full_attention",
|
| 31 |
+
"full_attention",
|
| 32 |
+
"full_attention",
|
| 33 |
+
"full_attention",
|
| 34 |
+
"full_attention",
|
| 35 |
+
"full_attention",
|
| 36 |
+
"full_attention",
|
| 37 |
+
"full_attention",
|
| 38 |
+
"full_attention",
|
| 39 |
+
"full_attention",
|
| 40 |
+
"full_attention",
|
| 41 |
+
"full_attention",
|
| 42 |
+
"full_attention",
|
| 43 |
+
"full_attention",
|
| 44 |
+
"full_attention",
|
| 45 |
+
"full_attention",
|
| 46 |
+
"full_attention",
|
| 47 |
+
"full_attention",
|
| 48 |
+
"full_attention",
|
| 49 |
+
"full_attention",
|
| 50 |
+
"full_attention"
|
| 51 |
+
],
|
| 52 |
+
"max_position_embeddings": 40960,
|
| 53 |
+
"max_window_layers": 28,
|
| 54 |
+
"mm_hidden_size": 1536,
|
| 55 |
+
"mm_newline_position": "grid",
|
| 56 |
+
"mm_patch_merge_type": "flat",
|
| 57 |
+
"mm_projector_lr": null,
|
| 58 |
+
"mm_projector_type": "mlp2x_gelu",
|
| 59 |
+
"mm_resampler_type": null,
|
| 60 |
+
"mm_spatial_pool_mode": "bilinear",
|
| 61 |
+
"mm_spatial_pool_stride": null,
|
| 62 |
+
"mm_tunable_parts": "mm_mlp_adapter",
|
| 63 |
+
"mm_use_im_patch_token": false,
|
| 64 |
+
"mm_use_im_start_end": false,
|
| 65 |
+
"mm_vision_select_feature": "patch",
|
| 66 |
+
"mm_vision_select_layer": -1,
|
| 67 |
+
"mm_vision_tower": "vtb_ssl:pe",
|
| 68 |
+
"mm_vision_tower_lr": null,
|
| 69 |
+
"model_type": "qwen3",
|
| 70 |
+
"num_attention_heads": 16,
|
| 71 |
+
"num_hidden_layers": 28,
|
| 72 |
+
"num_key_value_heads": 8,
|
| 73 |
+
"pad_token_id": 151643,
|
| 74 |
+
"pos_skipping_range": 4096,
|
| 75 |
+
"rms_norm_eps": 1e-06,
|
| 76 |
+
"rope_scaling": null,
|
| 77 |
+
"rope_theta": 1000000,
|
| 78 |
+
"sliding_window": null,
|
| 79 |
+
"tie_word_embeddings": true,
|
| 80 |
+
"tokenizer_model_max_length": 8192,
|
| 81 |
+
"tokenizer_padding_side": "right",
|
| 82 |
+
"transformers_version": "4.57.6",
|
| 83 |
+
"use_cache": true,
|
| 84 |
+
"use_mm_proj": true,
|
| 85 |
+
"use_pos_skipping": false,
|
| 86 |
+
"use_sliding_window": false,
|
| 87 |
+
"vision_tower_pretrained": "/cache/ckpt/download/tokenizer/continuous/pe/PE-Core-G14-448/PE-Core-G14-448.pt",
|
| 88 |
+
"vocab_size": 151936
|
| 89 |
+
}
|
continuous/qwen3/pe_core_g14_448/pretrain/mm_projector.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a0a3ca9deaf3aac55bceefc7f3f17ebd6c93c5b117e36e2e37c2014583700fc4
|
| 3 |
+
size 29378616
|
continuous/qwen3/pe_core_g14_448/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": 0.5879537463188171,
|
| 15 |
+
"learning_rate": 0.00032142857142857147,
|
| 16 |
+
"loss": 8.9536,
|
| 17 |
+
"step": 10
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.03669724770642202,
|
| 21 |
+
"grad_norm": 0.11044657975435257,
|
| 22 |
+
"learning_rate": 0.0006785714285714287,
|
| 23 |
+
"loss": 6.0939,
|
| 24 |
+
"step": 20
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.05504587155963303,
|
| 28 |
+
"grad_norm": 0.07740133255720139,
|
| 29 |
+
"learning_rate": 0.0009999907688176173,
|
| 30 |
+
"loss": 5.1385,
|
| 31 |
+
"step": 30
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.07339449541284404,
|
| 35 |
+
"grad_norm": 0.02474163845181465,
|
| 36 |
+
"learning_rate": 0.0009988834393115766,
|
| 37 |
+
"loss": 4.8822,
|
| 38 |
+
"step": 40
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.09174311926605505,
|
| 42 |
+
"grad_norm": 0.01555261854082346,
|
| 43 |
+
"learning_rate": 0.0009959345572940772,
|
| 44 |
+
"loss": 4.7897,
|
| 45 |
+
"step": 50
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.11009174311926606,
|
| 49 |
+
"grad_norm": 0.014950305223464966,
|
| 50 |
+
"learning_rate": 0.0009911550081155983,
|
| 51 |
+
"loss": 4.7452,
|
| 52 |
+
"step": 60
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.12844036697247707,
|
| 56 |
+
"grad_norm": 0.019125716760754585,
|
| 57 |
+
"learning_rate": 0.0009845624347566433,
|
| 58 |
+
"loss": 4.7023,
|
| 59 |
+
"step": 70
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.14678899082568808,
|
| 63 |
+
"grad_norm": 0.010757917538285255,
|
| 64 |
+
"learning_rate": 0.0009761811727013547,
|
| 65 |
+
"loss": 4.6814,
|
| 66 |
+
"step": 80
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.1651376146788991,
|
| 70 |
+
"grad_norm": 0.010514724999666214,
|
| 71 |
+
"learning_rate": 0.0009660421601067666,
|
| 72 |
+
"loss": 4.6517,
|
| 73 |
+
"step": 90
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.1834862385321101,
|
| 77 |
+
"grad_norm": 0.014230862259864807,
|
| 78 |
+
"learning_rate": 0.0009541828235992926,
|
| 79 |
+
"loss": 4.641,
|
| 80 |
+
"step": 100
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.2018348623853211,
|
| 84 |
+
"grad_norm": 0.011217114515602589,
|
| 85 |
+
"learning_rate": 0.0009406469401200151,
|
| 86 |
+
"loss": 4.6176,
|
| 87 |
+
"step": 110
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.22018348623853212,
|
| 91 |
+
"grad_norm": 0.01928178034722805,
|
| 92 |
+
"learning_rate": 0.0009254844753287492,
|
| 93 |
+
"loss": 4.6094,
|
| 94 |
+
"step": 120
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.23853211009174313,
|
| 98 |
+
"grad_norm": 0.01254762802273035,
|
| 99 |
+
"learning_rate": 0.0009087513991633924,
|
| 100 |
+
"loss": 4.587,
|
| 101 |
+
"step": 130
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.25688073394495414,
|
| 105 |
+
"grad_norm": 0.013727293349802494,
|
| 106 |
+
"learning_rate": 0.0008905094792353917,
|
| 107 |
+
"loss": 4.568,
|
| 108 |
+
"step": 140
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.27522935779816515,
|
| 112 |
+
"grad_norm": 0.015303186140954494,
|
| 113 |
+
"learning_rate": 0.0008708260528239789,
|
| 114 |
+
"loss": 4.5638,
|
| 115 |
+
"step": 150
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.29357798165137616,
|
| 119 |
+
"grad_norm": 0.02061416581273079,
|
| 120 |
+
"learning_rate": 0.0008497737783108237,
|
| 121 |
+
"loss": 4.543,
|
| 122 |
+
"step": 160
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.3119266055045872,
|
| 126 |
+
"grad_norm": 0.023816712200641632,
|
| 127 |
+
"learning_rate": 0.0008274303669726426,
|
| 128 |
+
"loss": 4.527,
|
| 129 |
+
"step": 170
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.3302752293577982,
|
| 133 |
+
"grad_norm": 0.018957873806357384,
|
| 134 |
+
"learning_rate": 0.0008038782961218137,
|
| 135 |
+
"loss": 4.504,
|
| 136 |
+
"step": 180
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.3486238532110092,
|
| 140 |
+
"grad_norm": 0.017127271741628647,
|
| 141 |
+
"learning_rate": 0.000779204504653894,
|
| 142 |
+
"loss": 4.4933,
|
| 143 |
+
"step": 190
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.3669724770642202,
|
| 147 |
+
"grad_norm": 0.018205173313617706,
|
| 148 |
+
"learning_rate": 0.0007535000721258791,
|
| 149 |
+
"loss": 4.4628,
|
| 150 |
+
"step": 200
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.3853211009174312,
|
| 154 |
+
"grad_norm": 0.018623432144522667,
|
| 155 |
+
"learning_rate": 0.00072685988254984,
|
| 156 |
+
"loss": 4.4477,
|
| 157 |
+
"step": 210
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.4036697247706422,
|
| 161 |
+
"grad_norm": 0.01694387011229992,
|
| 162 |
+
"learning_rate": 0.0006993822741429906,
|
| 163 |
+
"loss": 4.4533,
|
| 164 |
+
"step": 220
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.42201834862385323,
|
| 168 |
+
"grad_norm": 0.021918291226029396,
|
| 169 |
+
"learning_rate": 0.0006711686763270818,
|
| 170 |
+
"loss": 4.4445,
|
| 171 |
+
"step": 230
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.44036697247706424,
|
| 175 |
+
"grad_norm": 0.024065854027867317,
|
| 176 |
+
"learning_rate": 0.0006423232353170831,
|
| 177 |
+
"loss": 4.4234,
|
| 178 |
+
"step": 240
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.45871559633027525,
|
| 182 |
+
"grad_norm": 0.027499450370669365,
|
| 183 |
+
"learning_rate": 0.0006129524296812335,
|
| 184 |
+
"loss": 4.4011,
|
| 185 |
+
"step": 250
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.47706422018348627,
|
| 189 |
+
"grad_norm": 0.025129957124590874,
|
| 190 |
+
"learning_rate": 0.0005831646772915651,
|
| 191 |
+
"loss": 4.4099,
|
| 192 |
+
"step": 260
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.4954128440366973,
|
| 196 |
+
"grad_norm": 0.021545307710766792,
|
| 197 |
+
"learning_rate": 0.0005530699351157809,
|
| 198 |
+
"loss": 4.3818,
|
| 199 |
+
"step": 270
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.5137614678899083,
|
| 203 |
+
"grad_norm": 0.024142540991306305,
|
| 204 |
+
"learning_rate": 0.0005227792933277943,
|
| 205 |
+
"loss": 4.3744,
|
| 206 |
+
"step": 280
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.5321100917431193,
|
| 210 |
+
"grad_norm": 0.030607372522354126,
|
| 211 |
+
"learning_rate": 0.0004924045652352092,
|
| 212 |
+
"loss": 4.3557,
|
| 213 |
+
"step": 290
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.5504587155963303,
|
| 217 |
+
"grad_norm": 0.023899829015135765,
|
| 218 |
+
"learning_rate": 0.0004620578745374633,
|
| 219 |
+
"loss": 4.3509,
|
| 220 |
+
"step": 300
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.5688073394495413,
|
| 224 |
+
"grad_norm": 0.030498959124088287,
|
| 225 |
+
"learning_rate": 0.0004318512414382059,
|
| 226 |
+
"loss": 4.3602,
|
| 227 |
+
"step": 310
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.5871559633027523,
|
| 231 |
+
"grad_norm": 0.022088056430220604,
|
| 232 |
+
"learning_rate": 0.0004018961691397148,
|
| 233 |
+
"loss": 4.3471,
|
| 234 |
+
"step": 320
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.6055045871559633,
|
| 238 |
+
"grad_norm": 0.022722410038113594,
|
| 239 |
+
"learning_rate": 0.0003723032322457458,
|
| 240 |
+
"loss": 4.324,
|
| 241 |
+
"step": 330
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.6238532110091743,
|
| 245 |
+
"grad_norm": 0.027692673727869987,
|
| 246 |
+
"learning_rate": 0.0003431816685921625,
|
| 247 |
+
"loss": 4.3186,
|
| 248 |
+
"step": 340
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.6422018348623854,
|
| 252 |
+
"grad_norm": 0.02197856828570366,
|
| 253 |
+
"learning_rate": 0.0003146389760120416,
|
| 254 |
+
"loss": 4.3202,
|
| 255 |
+
"step": 350
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.6605504587155964,
|
| 259 |
+
"grad_norm": 0.02591855823993683,
|
| 260 |
+
"learning_rate": 0.00028678051552373485,
|
| 261 |
+
"loss": 4.3234,
|
| 262 |
+
"step": 360
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.6788990825688074,
|
| 266 |
+
"grad_norm": 0.021228553727269173,
|
| 267 |
+
"learning_rate": 0.0002597091224066581,
|
| 268 |
+
"loss": 4.2992,
|
| 269 |
+
"step": 370
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.6972477064220184,
|
| 273 |
+
"grad_norm": 0.020466575399041176,
|
| 274 |
+
"learning_rate": 0.0002335247266004629,
|
| 275 |
+
"loss": 4.3119,
|
| 276 |
+
"step": 380
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.7155963302752294,
|
| 280 |
+
"grad_norm": 0.022122304886579514,
|
| 281 |
+
"learning_rate": 0.000208323983828828,
|
| 282 |
+
"loss": 4.2912,
|
| 283 |
+
"step": 390
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.7339449541284404,
|
| 287 |
+
"grad_norm": 0.021740855649113655,
|
| 288 |
+
"learning_rate": 0.0001841999188095224,
|
| 289 |
+
"loss": 4.2908,
|
| 290 |
+
"step": 400
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.7522935779816514,
|
| 294 |
+
"grad_norm": 0.021341314539313316,
|
| 295 |
+
"learning_rate": 0.00016124158186777676,
|
| 296 |
+
"loss": 4.2885,
|
| 297 |
+
"step": 410
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.7706422018348624,
|
| 301 |
+
"grad_norm": 0.022280272096395493,
|
| 302 |
+
"learning_rate": 0.0001395337202205211,
|
| 303 |
+
"loss": 4.2764,
|
| 304 |
+
"step": 420
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.7889908256880734,
|
| 308 |
+
"grad_norm": 0.01967952586710453,
|
| 309 |
+
"learning_rate": 0.00011915646514489292,
|
| 310 |
+
"loss": 4.2807,
|
| 311 |
+
"step": 430
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.8073394495412844,
|
| 315 |
+
"grad_norm": 0.024896159768104553,
|
| 316 |
+
"learning_rate": 0.00010018503618578818,
|
| 317 |
+
"loss": 4.2856,
|
| 318 |
+
"step": 440
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.8256880733944955,
|
| 322 |
+
"grad_norm": 0.01987198367714882,
|
| 323 |
+
"learning_rate": 8.268946349432583e-05,
|
| 324 |
+
"loss": 4.2754,
|
| 325 |
+
"step": 450
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.8440366972477065,
|
| 329 |
+
"grad_norm": 0.02097586914896965,
|
| 330 |
+
"learning_rate": 6.673432932217117e-05,
|
| 331 |
+
"loss": 4.2657,
|
| 332 |
+
"step": 460
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.8623853211009175,
|
| 336 |
+
"grad_norm": 0.02145460434257984,
|
| 337 |
+
"learning_rate": 5.2378529625954684e-05,
|
| 338 |
+
"loss": 4.2522,
|
| 339 |
+
"step": 470
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.8807339449541285,
|
| 343 |
+
"grad_norm": 0.019403358921408653,
|
| 344 |
+
"learning_rate": 3.9675056661785556e-05,
|
| 345 |
+
"loss": 4.2634,
|
| 346 |
+
"step": 480
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.8990825688073395,
|
| 350 |
+
"grad_norm": 0.017992153763771057,
|
| 351 |
+
"learning_rate": 2.8670803372379538e-05,
|
| 352 |
+
"loss": 4.2615,
|
| 353 |
+
"step": 490
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.9174311926605505,
|
| 357 |
+
"grad_norm": 0.01869320124387741,
|
| 358 |
+
"learning_rate": 1.9406390288876586e-05,
|
| 359 |
+
"loss": 4.2752,
|
| 360 |
+
"step": 500
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.9357798165137615,
|
| 364 |
+
"grad_norm": 0.019285522401332855,
|
| 365 |
+
"learning_rate": 1.191601558631461e-05,
|
| 366 |
+
"loss": 4.2623,
|
| 367 |
+
"step": 510
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.9541284403669725,
|
| 371 |
+
"grad_norm": 0.018383022397756577,
|
| 372 |
+
"learning_rate": 6.2273288462559305e-06,
|
| 373 |
+
"loss": 4.2555,
|
| 374 |
+
"step": 520
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.9724770642201835,
|
| 378 |
+
"grad_norm": 0.018844157457351685,
|
| 379 |
+
"learning_rate": 2.361328992552314e-06,
|
| 380 |
+
"loss": 4.2567,
|
| 381 |
+
"step": 530
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.9908256880733946,
|
| 385 |
+
"grad_norm": 0.018752411007881165,
|
| 386 |
+
"learning_rate": 3.322867770044202e-07,
|
| 387 |
+
"loss": 4.263,
|
| 388 |
+
"step": 540
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 1.0,
|
| 392 |
+
"step": 545,
|
| 393 |
+
"total_flos": 5.78038655642239e+17,
|
| 394 |
+
"train_loss": 4.548338104388036,
|
| 395 |
+
"train_runtime": 8331.1665,
|
| 396 |
+
"train_samples_per_second": 66.993,
|
| 397 |
+
"train_steps_per_second": 0.065
|
| 398 |
+
}
|
| 399 |
+
],
|
| 400 |
+
"logging_steps": 10,
|
| 401 |
+
"max_steps": 545,
|
| 402 |
+
"num_input_tokens_seen": 29204608,
|
| 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": 5.78038655642239e+17,
|
| 418 |
+
"train_batch_size": 8,
|
| 419 |
+
"trial_name": null,
|
| 420 |
+
"trial_params": null
|
| 421 |
+
}
|
continuous/qwen3/pe_lang_l14_448/finetune/added_tokens.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</think>": 151668,
|
| 3 |
+
"</tool_call>": 151658,
|
| 4 |
+
"</tool_response>": 151666,
|
| 5 |
+
"<think>": 151667,
|
| 6 |
+
"<tool_call>": 151657,
|
| 7 |
+
"<tool_response>": 151665,
|
| 8 |
+
"<|box_end|>": 151649,
|
| 9 |
+
"<|box_start|>": 151648,
|
| 10 |
+
"<|endoftext|>": 151643,
|
| 11 |
+
"<|file_sep|>": 151664,
|
| 12 |
+
"<|fim_middle|>": 151660,
|
| 13 |
+
"<|fim_pad|>": 151662,
|
| 14 |
+
"<|fim_prefix|>": 151659,
|
| 15 |
+
"<|fim_suffix|>": 151661,
|
| 16 |
+
"<|im_end|>": 151645,
|
| 17 |
+
"<|im_start|>": 151644,
|
| 18 |
+
"<|image_pad|>": 151655,
|
| 19 |
+
"<|object_ref_end|>": 151647,
|
| 20 |
+
"<|object_ref_start|>": 151646,
|
| 21 |
+
"<|quad_end|>": 151651,
|
| 22 |
+
"<|quad_start|>": 151650,
|
| 23 |
+
"<|repo_name|>": 151663,
|
| 24 |
+
"<|video_pad|>": 151656,
|
| 25 |
+
"<|vision_end|>": 151653,
|
| 26 |
+
"<|vision_pad|>": 151654,
|
| 27 |
+
"<|vision_start|>": 151652
|
| 28 |
+
}
|