Training in progress, step 500, checkpoint
Browse files- last-checkpoint/config.json +34 -0
- last-checkpoint/generation_config.json +9 -0
- last-checkpoint/model.safetensors +3 -0
- last-checkpoint/optimizer.pt +3 -0
- last-checkpoint/rng_state.pth +3 -0
- last-checkpoint/scheduler.pt +3 -0
- last-checkpoint/tokenizer.json +0 -0
- last-checkpoint/tokenizer_config.json +17 -0
- last-checkpoint/trainer_state.json +424 -0
- last-checkpoint/training_args.bin +3 -0
last-checkpoint/config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"HybridTimeScaleLM"
|
| 4 |
+
],
|
| 5 |
+
"bos_token_id": 1,
|
| 6 |
+
"chunk_size": 128,
|
| 7 |
+
"dropout": 0.05,
|
| 8 |
+
"dtype": "bfloat16",
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"latent_dim": 768,
|
| 11 |
+
"layer_types": [
|
| 12 |
+
"linear",
|
| 13 |
+
"linear",
|
| 14 |
+
"linear",
|
| 15 |
+
"softmax",
|
| 16 |
+
"linear",
|
| 17 |
+
"linear",
|
| 18 |
+
"linear",
|
| 19 |
+
"softmax",
|
| 20 |
+
"linear",
|
| 21 |
+
"linear",
|
| 22 |
+
"linear",
|
| 23 |
+
"softmax"
|
| 24 |
+
],
|
| 25 |
+
"model_type": "hybrid_fourier_lm",
|
| 26 |
+
"num_layers": 12,
|
| 27 |
+
"num_modes": 64,
|
| 28 |
+
"pad_token_id": 2,
|
| 29 |
+
"tie_word_embeddings": true,
|
| 30 |
+
"time_scale": 128.0,
|
| 31 |
+
"transformers_version": "5.14.1",
|
| 32 |
+
"use_cache": false,
|
| 33 |
+
"vocab_size": 32768
|
| 34 |
+
}
|
last-checkpoint/generation_config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 1,
|
| 4 |
+
"eos_token_id": 2,
|
| 5 |
+
"output_attentions": false,
|
| 6 |
+
"output_hidden_states": false,
|
| 7 |
+
"pad_token_id": 2,
|
| 8 |
+
"transformers_version": "5.14.1"
|
| 9 |
+
}
|
last-checkpoint/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4a67d81e97596f2768511e4959660a99c3dabff68129710f50333a180c97ccf4
|
| 3 |
+
size 234681136
|
last-checkpoint/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:153578390500094706b5b2f9069514e099e3fa4d0f8671ad39f7456830573721
|
| 3 |
+
size 469516363
|
last-checkpoint/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:76cd281a3ce995fc434ac757f1094066d955dd6b7188cf148f0dd1523cb9cd80
|
| 3 |
+
size 14645
|
last-checkpoint/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:350811cf0b8d7ebb0375f99d7c5be37c2b3fc48fc087f648711ef9871266ac16
|
| 3 |
+
size 1465
|
last-checkpoint/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
last-checkpoint/tokenizer_config.json
ADDED
|
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"backend": "tokenizers",
|
| 4 |
+
"bos_token": "<s>",
|
| 5 |
+
"clean_up_tokenization_spaces": false,
|
| 6 |
+
"eos_token": "</s>",
|
| 7 |
+
"is_local": false,
|
| 8 |
+
"legacy": false,
|
| 9 |
+
"local_files_only": false,
|
| 10 |
+
"model_max_length": 1000000000,
|
| 11 |
+
"pad_token": "</s>",
|
| 12 |
+
"sp_model_kwargs": {},
|
| 13 |
+
"spaces_between_special_tokens": false,
|
| 14 |
+
"tokenizer_class": "TokenizersBackend",
|
| 15 |
+
"unk_token": "<unk>",
|
| 16 |
+
"use_default_system_prompt": false
|
| 17 |
+
}
|
last-checkpoint/trainer_state.json
ADDED
|
@@ -0,0 +1,424 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.1,
|
| 6 |
+
"eval_steps": 100,
|
| 7 |
+
"global_step": 500,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.002,
|
| 14 |
+
"grad_norm": 366.0,
|
| 15 |
+
"learning_rate": 1.7999999999999997e-05,
|
| 16 |
+
"loss": 3.335772705078125,
|
| 17 |
+
"step": 10
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.004,
|
| 21 |
+
"grad_norm": 76.0,
|
| 22 |
+
"learning_rate": 3.8e-05,
|
| 23 |
+
"loss": 3.325016403198242,
|
| 24 |
+
"step": 20
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.006,
|
| 28 |
+
"grad_norm": 426.0,
|
| 29 |
+
"learning_rate": 5.7999999999999994e-05,
|
| 30 |
+
"loss": 3.355701446533203,
|
| 31 |
+
"step": 30
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.008,
|
| 35 |
+
"grad_norm": 194.0,
|
| 36 |
+
"learning_rate": 7.8e-05,
|
| 37 |
+
"loss": 3.3106155395507812,
|
| 38 |
+
"step": 40
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.01,
|
| 42 |
+
"grad_norm": 712.0,
|
| 43 |
+
"learning_rate": 9.799999999999998e-05,
|
| 44 |
+
"loss": 3.270039367675781,
|
| 45 |
+
"step": 50
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.012,
|
| 49 |
+
"grad_norm": 164.0,
|
| 50 |
+
"learning_rate": 0.00011799999999999998,
|
| 51 |
+
"loss": 3.2886486053466797,
|
| 52 |
+
"step": 60
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.014,
|
| 56 |
+
"grad_norm": 162.0,
|
| 57 |
+
"learning_rate": 0.000138,
|
| 58 |
+
"loss": 3.2564620971679688,
|
| 59 |
+
"step": 70
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.016,
|
| 63 |
+
"grad_norm": 234.0,
|
| 64 |
+
"learning_rate": 0.00015799999999999996,
|
| 65 |
+
"loss": 3.267023468017578,
|
| 66 |
+
"step": 80
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.018,
|
| 70 |
+
"grad_norm": 1536.0,
|
| 71 |
+
"learning_rate": 0.000178,
|
| 72 |
+
"loss": 3.231563949584961,
|
| 73 |
+
"step": 90
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.02,
|
| 77 |
+
"grad_norm": 39.5,
|
| 78 |
+
"learning_rate": 0.000198,
|
| 79 |
+
"loss": 3.2340599060058595,
|
| 80 |
+
"step": 100
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.02,
|
| 84 |
+
"eval_loss": 3.491870403289795,
|
| 85 |
+
"eval_runtime": 4.5004,
|
| 86 |
+
"eval_samples_per_second": 66.216,
|
| 87 |
+
"eval_steps_per_second": 3.777,
|
| 88 |
+
"step": 100
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 0.022,
|
| 92 |
+
"grad_norm": 23.0,
|
| 93 |
+
"learning_rate": 0.00021799999999999999,
|
| 94 |
+
"loss": 3.20191650390625,
|
| 95 |
+
"step": 110
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 0.024,
|
| 99 |
+
"grad_norm": 32.0,
|
| 100 |
+
"learning_rate": 0.00023799999999999998,
|
| 101 |
+
"loss": 3.2040287017822267,
|
| 102 |
+
"step": 120
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 0.026,
|
| 106 |
+
"grad_norm": 136.0,
|
| 107 |
+
"learning_rate": 0.000258,
|
| 108 |
+
"loss": 3.1589597702026366,
|
| 109 |
+
"step": 130
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 0.028,
|
| 113 |
+
"grad_norm": 238.0,
|
| 114 |
+
"learning_rate": 0.000278,
|
| 115 |
+
"loss": 3.150320625305176,
|
| 116 |
+
"step": 140
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.03,
|
| 120 |
+
"grad_norm": 540.0,
|
| 121 |
+
"learning_rate": 0.000298,
|
| 122 |
+
"loss": 3.172740364074707,
|
| 123 |
+
"step": 150
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.032,
|
| 127 |
+
"grad_norm": 58.0,
|
| 128 |
+
"learning_rate": 0.0003,
|
| 129 |
+
"loss": 3.149807167053223,
|
| 130 |
+
"step": 160
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 0.034,
|
| 134 |
+
"grad_norm": 196.0,
|
| 135 |
+
"learning_rate": 0.0003,
|
| 136 |
+
"loss": 3.169495391845703,
|
| 137 |
+
"step": 170
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 0.036,
|
| 141 |
+
"grad_norm": 444.0,
|
| 142 |
+
"learning_rate": 0.0003,
|
| 143 |
+
"loss": 3.1639734268188477,
|
| 144 |
+
"step": 180
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 0.038,
|
| 148 |
+
"grad_norm": 378.0,
|
| 149 |
+
"learning_rate": 0.0003,
|
| 150 |
+
"loss": 3.221640777587891,
|
| 151 |
+
"step": 190
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 0.04,
|
| 155 |
+
"grad_norm": 2272.0,
|
| 156 |
+
"learning_rate": 0.0003,
|
| 157 |
+
"loss": 3.1916147232055665,
|
| 158 |
+
"step": 200
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.04,
|
| 162 |
+
"eval_loss": 3.4648807048797607,
|
| 163 |
+
"eval_runtime": 4.3534,
|
| 164 |
+
"eval_samples_per_second": 68.452,
|
| 165 |
+
"eval_steps_per_second": 3.905,
|
| 166 |
+
"step": 200
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 0.042,
|
| 170 |
+
"grad_norm": 520.0,
|
| 171 |
+
"learning_rate": 0.0003,
|
| 172 |
+
"loss": 3.1814949035644533,
|
| 173 |
+
"step": 210
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 0.044,
|
| 177 |
+
"grad_norm": 87.0,
|
| 178 |
+
"learning_rate": 0.0003,
|
| 179 |
+
"loss": 3.1746402740478517,
|
| 180 |
+
"step": 220
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 0.046,
|
| 184 |
+
"grad_norm": 39.0,
|
| 185 |
+
"learning_rate": 0.0003,
|
| 186 |
+
"loss": 3.172597885131836,
|
| 187 |
+
"step": 230
|
| 188 |
+
},
|
| 189 |
+
{
|
| 190 |
+
"epoch": 0.048,
|
| 191 |
+
"grad_norm": 50.5,
|
| 192 |
+
"learning_rate": 0.0003,
|
| 193 |
+
"loss": 3.1576799392700194,
|
| 194 |
+
"step": 240
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 0.05,
|
| 198 |
+
"grad_norm": 29.0,
|
| 199 |
+
"learning_rate": 0.0003,
|
| 200 |
+
"loss": 3.1418006896972654,
|
| 201 |
+
"step": 250
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 0.052,
|
| 205 |
+
"grad_norm": 50.5,
|
| 206 |
+
"learning_rate": 0.0003,
|
| 207 |
+
"loss": 3.1035797119140627,
|
| 208 |
+
"step": 260
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 0.054,
|
| 212 |
+
"grad_norm": 568.0,
|
| 213 |
+
"learning_rate": 0.0003,
|
| 214 |
+
"loss": 3.095198059082031,
|
| 215 |
+
"step": 270
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 0.056,
|
| 219 |
+
"grad_norm": 15.5625,
|
| 220 |
+
"learning_rate": 0.0003,
|
| 221 |
+
"loss": 3.079079818725586,
|
| 222 |
+
"step": 280
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 0.058,
|
| 226 |
+
"grad_norm": 17.625,
|
| 227 |
+
"learning_rate": 0.0003,
|
| 228 |
+
"loss": 3.060195732116699,
|
| 229 |
+
"step": 290
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"epoch": 0.06,
|
| 233 |
+
"grad_norm": 56.25,
|
| 234 |
+
"learning_rate": 0.0003,
|
| 235 |
+
"loss": 3.0736625671386717,
|
| 236 |
+
"step": 300
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 0.06,
|
| 240 |
+
"eval_loss": 3.349555015563965,
|
| 241 |
+
"eval_runtime": 4.3918,
|
| 242 |
+
"eval_samples_per_second": 67.854,
|
| 243 |
+
"eval_steps_per_second": 3.871,
|
| 244 |
+
"step": 300
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"epoch": 0.062,
|
| 248 |
+
"grad_norm": 432.0,
|
| 249 |
+
"learning_rate": 0.0003,
|
| 250 |
+
"loss": 3.0508825302124025,
|
| 251 |
+
"step": 310
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 0.064,
|
| 255 |
+
"grad_norm": 6.28125,
|
| 256 |
+
"learning_rate": 0.0003,
|
| 257 |
+
"loss": 3.021405792236328,
|
| 258 |
+
"step": 320
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 0.066,
|
| 262 |
+
"grad_norm": 161.0,
|
| 263 |
+
"learning_rate": 0.0003,
|
| 264 |
+
"loss": 3.011042022705078,
|
| 265 |
+
"step": 330
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 0.068,
|
| 269 |
+
"grad_norm": 29.625,
|
| 270 |
+
"learning_rate": 0.0003,
|
| 271 |
+
"loss": 2.9988969802856444,
|
| 272 |
+
"step": 340
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 0.07,
|
| 276 |
+
"grad_norm": 24.625,
|
| 277 |
+
"learning_rate": 0.0003,
|
| 278 |
+
"loss": 2.9939882278442385,
|
| 279 |
+
"step": 350
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 0.072,
|
| 283 |
+
"grad_norm": 61.0,
|
| 284 |
+
"learning_rate": 0.0003,
|
| 285 |
+
"loss": 2.979990768432617,
|
| 286 |
+
"step": 360
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 0.074,
|
| 290 |
+
"grad_norm": 13.6875,
|
| 291 |
+
"learning_rate": 0.0003,
|
| 292 |
+
"loss": 2.9845876693725586,
|
| 293 |
+
"step": 370
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 0.076,
|
| 297 |
+
"grad_norm": 280.0,
|
| 298 |
+
"learning_rate": 0.0003,
|
| 299 |
+
"loss": 2.975000762939453,
|
| 300 |
+
"step": 380
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 0.078,
|
| 304 |
+
"grad_norm": 21.125,
|
| 305 |
+
"learning_rate": 0.0003,
|
| 306 |
+
"loss": 2.958791732788086,
|
| 307 |
+
"step": 390
|
| 308 |
+
},
|
| 309 |
+
{
|
| 310 |
+
"epoch": 0.08,
|
| 311 |
+
"grad_norm": 12.8125,
|
| 312 |
+
"learning_rate": 0.0003,
|
| 313 |
+
"loss": 2.956746482849121,
|
| 314 |
+
"step": 400
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 0.08,
|
| 318 |
+
"eval_loss": 3.2549893856048584,
|
| 319 |
+
"eval_runtime": 4.4045,
|
| 320 |
+
"eval_samples_per_second": 67.658,
|
| 321 |
+
"eval_steps_per_second": 3.86,
|
| 322 |
+
"step": 400
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 0.082,
|
| 326 |
+
"grad_norm": 314.0,
|
| 327 |
+
"learning_rate": 0.0003,
|
| 328 |
+
"loss": 2.9515405654907227,
|
| 329 |
+
"step": 410
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 0.084,
|
| 333 |
+
"grad_norm": 2.125,
|
| 334 |
+
"learning_rate": 0.0003,
|
| 335 |
+
"loss": 2.910631561279297,
|
| 336 |
+
"step": 420
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 0.086,
|
| 340 |
+
"grad_norm": 24.75,
|
| 341 |
+
"learning_rate": 0.0003,
|
| 342 |
+
"loss": 2.8589399337768553,
|
| 343 |
+
"step": 430
|
| 344 |
+
},
|
| 345 |
+
{
|
| 346 |
+
"epoch": 0.088,
|
| 347 |
+
"grad_norm": 3.78125,
|
| 348 |
+
"learning_rate": 0.0003,
|
| 349 |
+
"loss": 2.844576835632324,
|
| 350 |
+
"step": 440
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 0.09,
|
| 354 |
+
"grad_norm": 1.6171875,
|
| 355 |
+
"learning_rate": 0.0003,
|
| 356 |
+
"loss": 2.7850717544555663,
|
| 357 |
+
"step": 450
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 0.092,
|
| 361 |
+
"grad_norm": 6.5625,
|
| 362 |
+
"learning_rate": 0.0003,
|
| 363 |
+
"loss": 2.7605606079101563,
|
| 364 |
+
"step": 460
|
| 365 |
+
},
|
| 366 |
+
{
|
| 367 |
+
"epoch": 0.094,
|
| 368 |
+
"grad_norm": 12.5625,
|
| 369 |
+
"learning_rate": 0.0003,
|
| 370 |
+
"loss": 2.747697639465332,
|
| 371 |
+
"step": 470
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 0.096,
|
| 375 |
+
"grad_norm": 0.7734375,
|
| 376 |
+
"learning_rate": 0.0003,
|
| 377 |
+
"loss": 2.7024419784545897,
|
| 378 |
+
"step": 480
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 0.098,
|
| 382 |
+
"grad_norm": 0.55078125,
|
| 383 |
+
"learning_rate": 0.0003,
|
| 384 |
+
"loss": 2.727059173583984,
|
| 385 |
+
"step": 490
|
| 386 |
+
},
|
| 387 |
+
{
|
| 388 |
+
"epoch": 0.1,
|
| 389 |
+
"grad_norm": 1.3046875,
|
| 390 |
+
"learning_rate": 0.0003,
|
| 391 |
+
"loss": 2.688610076904297,
|
| 392 |
+
"step": 500
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 0.1,
|
| 396 |
+
"eval_loss": 3.0536108016967773,
|
| 397 |
+
"eval_runtime": 4.4183,
|
| 398 |
+
"eval_samples_per_second": 67.447,
|
| 399 |
+
"eval_steps_per_second": 3.848,
|
| 400 |
+
"step": 500
|
| 401 |
+
}
|
| 402 |
+
],
|
| 403 |
+
"logging_steps": 10,
|
| 404 |
+
"max_steps": 5000,
|
| 405 |
+
"num_input_tokens_seen": 0,
|
| 406 |
+
"num_train_epochs": 9223372036854775807,
|
| 407 |
+
"save_steps": 500,
|
| 408 |
+
"stateful_callbacks": {
|
| 409 |
+
"TrainerControl": {
|
| 410 |
+
"args": {
|
| 411 |
+
"should_epoch_stop": false,
|
| 412 |
+
"should_evaluate": false,
|
| 413 |
+
"should_log": false,
|
| 414 |
+
"should_save": true,
|
| 415 |
+
"should_training_stop": false
|
| 416 |
+
},
|
| 417 |
+
"attributes": {}
|
| 418 |
+
}
|
| 419 |
+
},
|
| 420 |
+
"total_flos": 1.63077257428992e+17,
|
| 421 |
+
"train_batch_size": 18,
|
| 422 |
+
"trial_name": null,
|
| 423 |
+
"trial_params": null
|
| 424 |
+
}
|
last-checkpoint/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c9a625cbd88d4dad26e6b50e0305d7d4e34154cb8f6a48898a5b841114f667ac
|
| 3 |
+
size 5265
|