Model save
Browse files
README.md
CHANGED
|
@@ -4,7 +4,6 @@ library_name: peft
|
|
| 4 |
tags:
|
| 5 |
- trl
|
| 6 |
- sft
|
| 7 |
-
- alignment-handbook
|
| 8 |
- generated_from_trainer
|
| 9 |
base_model: google/gemma-2b
|
| 10 |
datasets:
|
|
@@ -21,7 +20,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 21 |
|
| 22 |
This model is a fine-tuned version of [google/gemma-2b](https://huggingface.co/google/gemma-2b) on the generator dataset.
|
| 23 |
It achieves the following results on the evaluation set:
|
| 24 |
-
- Loss: 2.
|
| 25 |
|
| 26 |
## Model description
|
| 27 |
|
|
@@ -41,14 +40,14 @@ More information needed
|
|
| 41 |
|
| 42 |
The following hyperparameters were used during training:
|
| 43 |
- learning_rate: 0.0002
|
| 44 |
-
- train_batch_size:
|
| 45 |
-
- eval_batch_size:
|
| 46 |
- seed: 42
|
| 47 |
- distributed_type: multi-GPU
|
| 48 |
- num_devices: 3
|
| 49 |
- gradient_accumulation_steps: 2
|
| 50 |
-
- total_train_batch_size:
|
| 51 |
-
- total_eval_batch_size:
|
| 52 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 53 |
- lr_scheduler_type: cosine
|
| 54 |
- lr_scheduler_warmup_ratio: 0.1
|
|
@@ -58,16 +57,16 @@ The following hyperparameters were used during training:
|
|
| 58 |
|
| 59 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 60 |
|:-------------:|:-----:|:----:|:---------------:|
|
| 61 |
-
| 1.
|
| 62 |
-
| 1.
|
| 63 |
-
| 1.
|
| 64 |
-
|
|
| 65 |
-
|
|
| 66 |
-
| 0.
|
| 67 |
-
| 0.
|
| 68 |
-
| 0.
|
| 69 |
-
| 0.
|
| 70 |
-
| 0.
|
| 71 |
|
| 72 |
|
| 73 |
### Framework versions
|
|
|
|
| 4 |
tags:
|
| 5 |
- trl
|
| 6 |
- sft
|
|
|
|
| 7 |
- generated_from_trainer
|
| 8 |
base_model: google/gemma-2b
|
| 9 |
datasets:
|
|
|
|
| 20 |
|
| 21 |
This model is a fine-tuned version of [google/gemma-2b](https://huggingface.co/google/gemma-2b) on the generator dataset.
|
| 22 |
It achieves the following results on the evaluation set:
|
| 23 |
+
- Loss: 2.7931
|
| 24 |
|
| 25 |
## Model description
|
| 26 |
|
|
|
|
| 40 |
|
| 41 |
The following hyperparameters were used during training:
|
| 42 |
- learning_rate: 0.0002
|
| 43 |
+
- train_batch_size: 8
|
| 44 |
+
- eval_batch_size: 8
|
| 45 |
- seed: 42
|
| 46 |
- distributed_type: multi-GPU
|
| 47 |
- num_devices: 3
|
| 48 |
- gradient_accumulation_steps: 2
|
| 49 |
+
- total_train_batch_size: 48
|
| 50 |
+
- total_eval_batch_size: 24
|
| 51 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 52 |
- lr_scheduler_type: cosine
|
| 53 |
- lr_scheduler_warmup_ratio: 0.1
|
|
|
|
| 57 |
|
| 58 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 59 |
|:-------------:|:-----:|:----:|:---------------:|
|
| 60 |
+
| 1.1808 | 1.0 | 146 | 2.4876 |
|
| 61 |
+
| 1.0819 | 2.0 | 292 | 2.4820 |
|
| 62 |
+
| 1.035 | 3.0 | 438 | 2.4995 |
|
| 63 |
+
| 0.9796 | 4.0 | 584 | 2.5387 |
|
| 64 |
+
| 0.9366 | 5.0 | 730 | 2.6038 |
|
| 65 |
+
| 0.9051 | 6.0 | 876 | 2.6521 |
|
| 66 |
+
| 0.8676 | 7.0 | 1022 | 2.7249 |
|
| 67 |
+
| 0.8291 | 8.0 | 1168 | 2.7667 |
|
| 68 |
+
| 0.8286 | 9.0 | 1314 | 2.7899 |
|
| 69 |
+
| 0.8185 | 10.0 | 1460 | 2.7931 |
|
| 70 |
|
| 71 |
|
| 72 |
### Framework versions
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 78480320
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d0adbe9f8822dd528c487486d169b1cdc0db793f6c22d58013d09a1a98fa248f
|
| 3 |
size 78480320
|
all_results.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch": 10.
|
| 3 |
-
"total_flos": 8.
|
| 4 |
-
"train_loss": 0.
|
| 5 |
-
"train_runtime":
|
| 6 |
"train_samples": 64610,
|
| 7 |
-
"train_samples_per_second":
|
| 8 |
-
"train_steps_per_second":
|
| 9 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"total_flos": 8.702314001108828e+17,
|
| 4 |
+
"train_loss": 0.9981180969982931,
|
| 5 |
+
"train_runtime": 8741.0304,
|
| 6 |
"train_samples": 64610,
|
| 7 |
+
"train_samples_per_second": 8.01,
|
| 8 |
+
"train_steps_per_second": 0.167
|
| 9 |
}
|
runs/Jun10_15-40-50_user-HP-Z8-Fury-G5-Workstation-Desktop-PC/events.out.tfevents.1718001669.user-HP-Z8-Fury-G5-Workstation-Desktop-PC.6920.0
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f8da717ead12a274f7d00aab0a96423a7266dcdb7b22fc03364f0e6a82add57b
|
| 3 |
+
size 70380
|
train_results.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch": 10.
|
| 3 |
-
"total_flos": 8.
|
| 4 |
-
"train_loss": 0.
|
| 5 |
-
"train_runtime":
|
| 6 |
"train_samples": 64610,
|
| 7 |
-
"train_samples_per_second":
|
| 8 |
-
"train_steps_per_second":
|
| 9 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"total_flos": 8.702314001108828e+17,
|
| 4 |
+
"train_loss": 0.9981180969982931,
|
| 5 |
+
"train_runtime": 8741.0304,
|
| 6 |
"train_samples": 64610,
|
| 7 |
+
"train_samples_per_second": 8.01,
|
| 8 |
+
"train_steps_per_second": 0.167
|
| 9 |
}
|
trainer_state.json
CHANGED
|
@@ -1,2208 +1,2152 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch": 10.
|
| 5 |
"eval_steps": 500,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 0.00684931506849315,
|
| 13 |
-
"grad_norm":
|
| 14 |
-
"learning_rate":
|
| 15 |
"loss": 3.0017,
|
| 16 |
"step": 1
|
| 17 |
},
|
| 18 |
{
|
| 19 |
"epoch": 0.03424657534246575,
|
| 20 |
-
"grad_norm":
|
| 21 |
-
"learning_rate":
|
| 22 |
-
"loss": 3.
|
| 23 |
"step": 5
|
| 24 |
},
|
| 25 |
{
|
| 26 |
"epoch": 0.0684931506849315,
|
| 27 |
-
"grad_norm":
|
| 28 |
-
"learning_rate":
|
| 29 |
-
"loss": 3.
|
| 30 |
"step": 10
|
| 31 |
},
|
| 32 |
{
|
| 33 |
"epoch": 0.10273972602739725,
|
| 34 |
-
"grad_norm": 2.
|
| 35 |
-
"learning_rate":
|
| 36 |
-
"loss":
|
| 37 |
"step": 15
|
| 38 |
},
|
| 39 |
{
|
| 40 |
"epoch": 0.136986301369863,
|
| 41 |
-
"grad_norm":
|
| 42 |
-
"learning_rate":
|
| 43 |
-
"loss": 2.
|
| 44 |
"step": 20
|
| 45 |
},
|
| 46 |
{
|
| 47 |
"epoch": 0.17123287671232876,
|
| 48 |
-
"grad_norm":
|
| 49 |
-
"learning_rate":
|
| 50 |
-
"loss": 2.
|
| 51 |
"step": 25
|
| 52 |
},
|
| 53 |
{
|
| 54 |
"epoch": 0.2054794520547945,
|
| 55 |
-
"grad_norm":
|
| 56 |
-
"learning_rate":
|
| 57 |
-
"loss": 2.
|
| 58 |
"step": 30
|
| 59 |
},
|
| 60 |
{
|
| 61 |
"epoch": 0.23972602739726026,
|
| 62 |
-
"grad_norm": 1.
|
| 63 |
-
"learning_rate":
|
| 64 |
-
"loss": 2.
|
| 65 |
"step": 35
|
| 66 |
},
|
| 67 |
{
|
| 68 |
"epoch": 0.273972602739726,
|
| 69 |
-
"grad_norm":
|
| 70 |
-
"learning_rate":
|
| 71 |
-
"loss":
|
| 72 |
"step": 40
|
| 73 |
},
|
| 74 |
{
|
| 75 |
"epoch": 0.3082191780821918,
|
| 76 |
-
"grad_norm":
|
| 77 |
-
"learning_rate":
|
| 78 |
-
"loss":
|
| 79 |
"step": 45
|
| 80 |
},
|
| 81 |
{
|
| 82 |
"epoch": 0.3424657534246575,
|
| 83 |
-
"grad_norm":
|
| 84 |
-
"learning_rate":
|
| 85 |
-
"loss":
|
| 86 |
"step": 50
|
| 87 |
},
|
| 88 |
{
|
| 89 |
"epoch": 0.3767123287671233,
|
| 90 |
-
"grad_norm":
|
| 91 |
-
"learning_rate":
|
| 92 |
-
"loss": 1.
|
| 93 |
"step": 55
|
| 94 |
},
|
| 95 |
{
|
| 96 |
"epoch": 0.410958904109589,
|
| 97 |
-
"grad_norm":
|
| 98 |
-
"learning_rate":
|
| 99 |
-
"loss": 1.
|
| 100 |
"step": 60
|
| 101 |
},
|
| 102 |
{
|
| 103 |
"epoch": 0.4452054794520548,
|
| 104 |
-
"grad_norm": 0.
|
| 105 |
-
"learning_rate":
|
| 106 |
-
"loss": 1.
|
| 107 |
"step": 65
|
| 108 |
},
|
| 109 |
{
|
| 110 |
"epoch": 0.4794520547945205,
|
| 111 |
-
"grad_norm": 0.
|
| 112 |
-
"learning_rate":
|
| 113 |
-
"loss": 1.
|
| 114 |
"step": 70
|
| 115 |
},
|
| 116 |
{
|
| 117 |
"epoch": 0.5136986301369864,
|
| 118 |
-
"grad_norm":
|
| 119 |
-
"learning_rate":
|
| 120 |
-
"loss": 1.
|
| 121 |
"step": 75
|
| 122 |
},
|
| 123 |
{
|
| 124 |
"epoch": 0.547945205479452,
|
| 125 |
-
"grad_norm": 0.
|
| 126 |
-
"learning_rate":
|
| 127 |
-
"loss": 1.
|
| 128 |
"step": 80
|
| 129 |
},
|
| 130 |
{
|
| 131 |
"epoch": 0.5821917808219178,
|
| 132 |
-
"grad_norm": 0.
|
| 133 |
-
"learning_rate":
|
| 134 |
-
"loss": 1.
|
| 135 |
"step": 85
|
| 136 |
},
|
| 137 |
{
|
| 138 |
"epoch": 0.6164383561643836,
|
| 139 |
-
"grad_norm": 0.
|
| 140 |
-
"learning_rate":
|
| 141 |
-
"loss": 1.
|
| 142 |
"step": 90
|
| 143 |
},
|
| 144 |
{
|
| 145 |
"epoch": 0.6506849315068494,
|
| 146 |
-
"grad_norm": 0.
|
| 147 |
-
"learning_rate":
|
| 148 |
-
"loss": 1.
|
| 149 |
"step": 95
|
| 150 |
},
|
| 151 |
{
|
| 152 |
"epoch": 0.684931506849315,
|
| 153 |
-
"grad_norm": 0.
|
| 154 |
-
"learning_rate":
|
| 155 |
-
"loss": 1.
|
| 156 |
"step": 100
|
| 157 |
},
|
| 158 |
{
|
| 159 |
"epoch": 0.7191780821917808,
|
| 160 |
-
"grad_norm": 0
|
| 161 |
-
"learning_rate":
|
| 162 |
-
"loss": 1.
|
| 163 |
"step": 105
|
| 164 |
},
|
| 165 |
{
|
| 166 |
"epoch": 0.7534246575342466,
|
| 167 |
-
"grad_norm": 0.
|
| 168 |
-
"learning_rate": 0.
|
| 169 |
-
"loss": 1.
|
| 170 |
"step": 110
|
| 171 |
},
|
| 172 |
{
|
| 173 |
"epoch": 0.7876712328767124,
|
| 174 |
-
"grad_norm": 0.
|
| 175 |
-
"learning_rate": 0.
|
| 176 |
-
"loss": 1.
|
| 177 |
"step": 115
|
| 178 |
},
|
| 179 |
{
|
| 180 |
"epoch": 0.821917808219178,
|
| 181 |
-
"grad_norm": 0.
|
| 182 |
-
"learning_rate": 0.
|
| 183 |
-
"loss": 1.
|
| 184 |
"step": 120
|
| 185 |
},
|
| 186 |
{
|
| 187 |
"epoch": 0.8561643835616438,
|
| 188 |
-
"grad_norm": 0.
|
| 189 |
-
"learning_rate": 0.
|
| 190 |
-
"loss": 1.
|
| 191 |
"step": 125
|
| 192 |
},
|
| 193 |
{
|
| 194 |
"epoch": 0.8904109589041096,
|
| 195 |
-
"grad_norm": 0.
|
| 196 |
-
"learning_rate": 0.
|
| 197 |
-
"loss": 1.
|
| 198 |
"step": 130
|
| 199 |
},
|
| 200 |
{
|
| 201 |
"epoch": 0.9246575342465754,
|
| 202 |
-
"grad_norm": 0.
|
| 203 |
-
"learning_rate": 0.
|
| 204 |
-
"loss": 1.
|
| 205 |
"step": 135
|
| 206 |
},
|
| 207 |
{
|
| 208 |
"epoch": 0.958904109589041,
|
| 209 |
-
"grad_norm":
|
| 210 |
-
"learning_rate": 0.
|
| 211 |
-
"loss": 1.
|
| 212 |
"step": 140
|
| 213 |
},
|
| 214 |
{
|
| 215 |
"epoch": 0.9931506849315068,
|
| 216 |
-
"grad_norm": 0.
|
| 217 |
-
"learning_rate": 0.
|
| 218 |
-
"loss": 1.
|
| 219 |
"step": 145
|
| 220 |
},
|
| 221 |
{
|
| 222 |
"epoch": 1.0,
|
| 223 |
-
"eval_loss": 2.
|
| 224 |
-
"eval_runtime": 0.
|
| 225 |
-
"eval_samples_per_second":
|
| 226 |
-
"eval_steps_per_second": 1.
|
| 227 |
"step": 146
|
| 228 |
},
|
| 229 |
{
|
| 230 |
"epoch": 1.0273972602739727,
|
| 231 |
-
"grad_norm": 0.
|
| 232 |
-
"learning_rate": 0.
|
| 233 |
-
"loss": 1.
|
| 234 |
"step": 150
|
| 235 |
},
|
| 236 |
{
|
| 237 |
"epoch": 1.0616438356164384,
|
| 238 |
-
"grad_norm": 0.
|
| 239 |
-
"learning_rate": 0.
|
| 240 |
-
"loss": 1.
|
| 241 |
"step": 155
|
| 242 |
},
|
| 243 |
{
|
| 244 |
"epoch": 1.095890410958904,
|
| 245 |
-
"grad_norm": 0.
|
| 246 |
-
"learning_rate": 0.
|
| 247 |
-
"loss": 1.
|
| 248 |
"step": 160
|
| 249 |
},
|
| 250 |
{
|
| 251 |
"epoch": 1.13013698630137,
|
| 252 |
-
"grad_norm": 0.
|
| 253 |
-
"learning_rate": 0.
|
| 254 |
-
"loss": 1.
|
| 255 |
"step": 165
|
| 256 |
},
|
| 257 |
{
|
| 258 |
"epoch": 1.1643835616438356,
|
| 259 |
-
"grad_norm": 0.
|
| 260 |
-
"learning_rate": 0.
|
| 261 |
-
"loss": 1.
|
| 262 |
"step": 170
|
| 263 |
},
|
| 264 |
{
|
| 265 |
"epoch": 1.1986301369863013,
|
| 266 |
-
"grad_norm": 0.
|
| 267 |
-
"learning_rate": 0.
|
| 268 |
-
"loss": 1.
|
| 269 |
"step": 175
|
| 270 |
},
|
| 271 |
{
|
| 272 |
"epoch": 1.2328767123287672,
|
| 273 |
-
"grad_norm": 0.
|
| 274 |
-
"learning_rate": 0.
|
| 275 |
-
"loss": 1.
|
| 276 |
"step": 180
|
| 277 |
},
|
| 278 |
{
|
| 279 |
"epoch": 1.2671232876712328,
|
| 280 |
-
"grad_norm": 0.
|
| 281 |
-
"learning_rate": 0.
|
| 282 |
-
"loss": 1.
|
| 283 |
"step": 185
|
| 284 |
},
|
| 285 |
{
|
| 286 |
"epoch": 1.3013698630136985,
|
| 287 |
-
"grad_norm":
|
| 288 |
-
"learning_rate": 0.
|
| 289 |
-
"loss": 1.
|
| 290 |
"step": 190
|
| 291 |
},
|
| 292 |
{
|
| 293 |
"epoch": 1.3356164383561644,
|
| 294 |
-
"grad_norm": 0.
|
| 295 |
-
"learning_rate": 0.
|
| 296 |
-
"loss": 1.
|
| 297 |
"step": 195
|
| 298 |
},
|
| 299 |
{
|
| 300 |
"epoch": 1.36986301369863,
|
| 301 |
-
"grad_norm":
|
| 302 |
-
"learning_rate": 0.
|
| 303 |
-
"loss": 1.
|
| 304 |
"step": 200
|
| 305 |
},
|
| 306 |
{
|
| 307 |
"epoch": 1.404109589041096,
|
| 308 |
-
"grad_norm":
|
| 309 |
-
"learning_rate": 0.
|
| 310 |
-
"loss": 1.
|
| 311 |
"step": 205
|
| 312 |
},
|
| 313 |
{
|
| 314 |
"epoch": 1.4383561643835616,
|
| 315 |
-
"grad_norm": 0.
|
| 316 |
-
"learning_rate": 0.
|
| 317 |
-
"loss": 1.
|
| 318 |
"step": 210
|
| 319 |
},
|
| 320 |
{
|
| 321 |
"epoch": 1.4726027397260273,
|
| 322 |
-
"grad_norm": 0.
|
| 323 |
-
"learning_rate": 0.
|
| 324 |
-
"loss": 1.
|
| 325 |
"step": 215
|
| 326 |
},
|
| 327 |
{
|
| 328 |
"epoch": 1.5068493150684932,
|
| 329 |
-
"grad_norm": 0.
|
| 330 |
-
"learning_rate": 0.
|
| 331 |
-
"loss": 1.
|
| 332 |
"step": 220
|
| 333 |
},
|
| 334 |
{
|
| 335 |
"epoch": 1.541095890410959,
|
| 336 |
-
"grad_norm": 0.
|
| 337 |
-
"learning_rate": 0.
|
| 338 |
-
"loss": 1.
|
| 339 |
"step": 225
|
| 340 |
},
|
| 341 |
{
|
| 342 |
"epoch": 1.5753424657534247,
|
| 343 |
-
"grad_norm": 0.
|
| 344 |
-
"learning_rate": 0.
|
| 345 |
-
"loss": 1.
|
| 346 |
"step": 230
|
| 347 |
},
|
| 348 |
{
|
| 349 |
"epoch": 1.6095890410958904,
|
| 350 |
-
"grad_norm": 0.
|
| 351 |
-
"learning_rate": 0.
|
| 352 |
-
"loss": 1.
|
| 353 |
"step": 235
|
| 354 |
},
|
| 355 |
{
|
| 356 |
"epoch": 1.643835616438356,
|
| 357 |
-
"grad_norm": 0.
|
| 358 |
-
"learning_rate": 0.
|
| 359 |
-
"loss": 1.
|
| 360 |
"step": 240
|
| 361 |
},
|
| 362 |
{
|
| 363 |
"epoch": 1.678082191780822,
|
| 364 |
-
"grad_norm": 0.
|
| 365 |
-
"learning_rate": 0.
|
| 366 |
-
"loss": 1.
|
| 367 |
"step": 245
|
| 368 |
},
|
| 369 |
{
|
| 370 |
"epoch": 1.7123287671232876,
|
| 371 |
-
"grad_norm": 0.
|
| 372 |
-
"learning_rate": 0.
|
| 373 |
-
"loss": 1.
|
| 374 |
"step": 250
|
| 375 |
},
|
| 376 |
{
|
| 377 |
"epoch": 1.7465753424657535,
|
| 378 |
-
"grad_norm": 0.
|
| 379 |
-
"learning_rate": 0.
|
| 380 |
-
"loss": 1.
|
| 381 |
"step": 255
|
| 382 |
},
|
| 383 |
{
|
| 384 |
"epoch": 1.7808219178082192,
|
| 385 |
-
"grad_norm": 0.
|
| 386 |
-
"learning_rate": 0.
|
| 387 |
-
"loss": 1.
|
| 388 |
"step": 260
|
| 389 |
},
|
| 390 |
{
|
| 391 |
"epoch": 1.8150684931506849,
|
| 392 |
-
"grad_norm": 0.
|
| 393 |
-
"learning_rate": 0.
|
| 394 |
-
"loss": 1.
|
| 395 |
"step": 265
|
| 396 |
},
|
| 397 |
{
|
| 398 |
"epoch": 1.8493150684931505,
|
| 399 |
-
"grad_norm": 0.
|
| 400 |
-
"learning_rate": 0.
|
| 401 |
-
"loss": 1.
|
| 402 |
"step": 270
|
| 403 |
},
|
| 404 |
{
|
| 405 |
"epoch": 1.8835616438356164,
|
| 406 |
-
"grad_norm": 0.
|
| 407 |
-
"learning_rate": 0.
|
| 408 |
-
"loss": 1.
|
| 409 |
"step": 275
|
| 410 |
},
|
| 411 |
{
|
| 412 |
"epoch": 1.9178082191780823,
|
| 413 |
-
"grad_norm": 0.
|
| 414 |
-
"learning_rate": 0.
|
| 415 |
-
"loss": 1.
|
| 416 |
"step": 280
|
| 417 |
},
|
| 418 |
{
|
| 419 |
"epoch": 1.952054794520548,
|
| 420 |
-
"grad_norm": 0.
|
| 421 |
-
"learning_rate": 0.
|
| 422 |
-
"loss": 1.
|
| 423 |
"step": 285
|
| 424 |
},
|
| 425 |
{
|
| 426 |
"epoch": 1.9863013698630136,
|
| 427 |
-
"grad_norm": 0.
|
| 428 |
-
"learning_rate": 0.
|
| 429 |
-
"loss": 1.
|
| 430 |
"step": 290
|
| 431 |
},
|
| 432 |
{
|
| 433 |
"epoch": 2.0,
|
| 434 |
-
"eval_loss": 2.
|
| 435 |
-
"eval_runtime": 0.
|
| 436 |
-
"eval_samples_per_second":
|
| 437 |
-
"eval_steps_per_second": 1.
|
| 438 |
"step": 292
|
| 439 |
},
|
| 440 |
{
|
| 441 |
"epoch": 2.0205479452054793,
|
| 442 |
-
"grad_norm": 0.
|
| 443 |
-
"learning_rate": 0.
|
| 444 |
-
"loss": 1.
|
| 445 |
"step": 295
|
| 446 |
},
|
| 447 |
{
|
| 448 |
"epoch": 2.0547945205479454,
|
| 449 |
-
"grad_norm": 0.
|
| 450 |
-
"learning_rate": 0.
|
| 451 |
-
"loss": 1.
|
| 452 |
"step": 300
|
| 453 |
},
|
| 454 |
{
|
| 455 |
"epoch": 2.089041095890411,
|
| 456 |
-
"grad_norm": 0.
|
| 457 |
-
"learning_rate": 0.
|
| 458 |
-
"loss": 1.
|
| 459 |
"step": 305
|
| 460 |
},
|
| 461 |
{
|
| 462 |
"epoch": 2.1232876712328768,
|
| 463 |
-
"grad_norm": 0.
|
| 464 |
-
"learning_rate": 0.
|
| 465 |
-
"loss": 1.
|
| 466 |
"step": 310
|
| 467 |
},
|
| 468 |
{
|
| 469 |
"epoch": 2.1575342465753424,
|
| 470 |
-
"grad_norm": 0.
|
| 471 |
-
"learning_rate": 0.
|
| 472 |
-
"loss": 1.
|
| 473 |
"step": 315
|
| 474 |
},
|
| 475 |
{
|
| 476 |
"epoch": 2.191780821917808,
|
| 477 |
-
"grad_norm":
|
| 478 |
-
"learning_rate": 0.
|
| 479 |
-
"loss": 1.
|
| 480 |
"step": 320
|
| 481 |
},
|
| 482 |
{
|
| 483 |
"epoch": 2.2260273972602738,
|
| 484 |
-
"grad_norm":
|
| 485 |
-
"learning_rate": 0.
|
| 486 |
-
"loss": 1.
|
| 487 |
"step": 325
|
| 488 |
},
|
| 489 |
{
|
| 490 |
"epoch": 2.26027397260274,
|
| 491 |
-
"grad_norm": 0.
|
| 492 |
-
"learning_rate": 0.
|
| 493 |
-
"loss": 1.
|
| 494 |
"step": 330
|
| 495 |
},
|
| 496 |
{
|
| 497 |
"epoch": 2.2945205479452055,
|
| 498 |
-
"grad_norm": 0.
|
| 499 |
-
"learning_rate": 0.
|
| 500 |
-
"loss": 1.
|
| 501 |
"step": 335
|
| 502 |
},
|
| 503 |
{
|
| 504 |
"epoch": 2.328767123287671,
|
| 505 |
-
"grad_norm": 0.
|
| 506 |
-
"learning_rate": 0.
|
| 507 |
-
"loss": 1.
|
| 508 |
"step": 340
|
| 509 |
},
|
| 510 |
{
|
| 511 |
"epoch": 2.363013698630137,
|
| 512 |
-
"grad_norm": 0.
|
| 513 |
-
"learning_rate": 0.
|
| 514 |
-
"loss": 1.
|
| 515 |
"step": 345
|
| 516 |
},
|
| 517 |
{
|
| 518 |
"epoch": 2.3972602739726026,
|
| 519 |
-
"grad_norm": 0.
|
| 520 |
-
"learning_rate": 0.
|
| 521 |
-
"loss": 1.
|
| 522 |
"step": 350
|
| 523 |
},
|
| 524 |
{
|
| 525 |
"epoch": 2.4315068493150687,
|
| 526 |
-
"grad_norm": 0.
|
| 527 |
-
"learning_rate": 0.
|
| 528 |
-
"loss": 1.
|
| 529 |
"step": 355
|
| 530 |
},
|
| 531 |
{
|
| 532 |
"epoch": 2.4657534246575343,
|
| 533 |
-
"grad_norm": 0.
|
| 534 |
-
"learning_rate": 0.
|
| 535 |
-
"loss": 1.
|
| 536 |
"step": 360
|
| 537 |
},
|
| 538 |
{
|
| 539 |
"epoch": 2.5,
|
| 540 |
-
"grad_norm": 0.
|
| 541 |
-
"learning_rate": 0.
|
| 542 |
-
"loss": 1.
|
| 543 |
"step": 365
|
| 544 |
},
|
| 545 |
{
|
| 546 |
"epoch": 2.5342465753424657,
|
| 547 |
-
"grad_norm": 0.
|
| 548 |
-
"learning_rate": 0.
|
| 549 |
-
"loss": 1.
|
| 550 |
"step": 370
|
| 551 |
},
|
| 552 |
{
|
| 553 |
"epoch": 2.5684931506849313,
|
| 554 |
-
"grad_norm": 0.
|
| 555 |
-
"learning_rate": 0.
|
| 556 |
-
"loss": 1.
|
| 557 |
"step": 375
|
| 558 |
},
|
| 559 |
{
|
| 560 |
"epoch": 2.602739726027397,
|
| 561 |
-
"grad_norm": 0.
|
| 562 |
-
"learning_rate": 0.
|
| 563 |
-
"loss": 1.
|
| 564 |
"step": 380
|
| 565 |
},
|
| 566 |
{
|
| 567 |
"epoch": 2.636986301369863,
|
| 568 |
-
"grad_norm": 0.
|
| 569 |
-
"learning_rate": 0.
|
| 570 |
-
"loss": 1.
|
| 571 |
"step": 385
|
| 572 |
},
|
| 573 |
{
|
| 574 |
"epoch": 2.671232876712329,
|
| 575 |
-
"grad_norm": 0.
|
| 576 |
-
"learning_rate": 0.
|
| 577 |
-
"loss": 1.
|
| 578 |
"step": 390
|
| 579 |
},
|
| 580 |
{
|
| 581 |
"epoch": 2.7054794520547945,
|
| 582 |
-
"grad_norm": 0.
|
| 583 |
-
"learning_rate": 0.
|
| 584 |
-
"loss": 1.
|
| 585 |
"step": 395
|
| 586 |
},
|
| 587 |
{
|
| 588 |
"epoch": 2.73972602739726,
|
| 589 |
-
"grad_norm": 0.
|
| 590 |
-
"learning_rate": 0.
|
| 591 |
-
"loss": 1.
|
| 592 |
"step": 400
|
| 593 |
},
|
| 594 |
{
|
| 595 |
"epoch": 2.7739726027397262,
|
| 596 |
-
"grad_norm": 0.
|
| 597 |
-
"learning_rate": 0.
|
| 598 |
-
"loss": 1.
|
| 599 |
"step": 405
|
| 600 |
},
|
| 601 |
{
|
| 602 |
"epoch": 2.808219178082192,
|
| 603 |
-
"grad_norm": 0.
|
| 604 |
-
"learning_rate": 0.
|
| 605 |
-
"loss": 1.
|
| 606 |
"step": 410
|
| 607 |
},
|
| 608 |
{
|
| 609 |
"epoch": 2.8424657534246576,
|
| 610 |
-
"grad_norm": 0.
|
| 611 |
-
"learning_rate": 0.
|
| 612 |
-
"loss": 1.
|
| 613 |
"step": 415
|
| 614 |
},
|
| 615 |
{
|
| 616 |
"epoch": 2.8767123287671232,
|
| 617 |
-
"grad_norm": 0.
|
| 618 |
-
"learning_rate": 0.
|
| 619 |
-
"loss": 1.
|
| 620 |
"step": 420
|
| 621 |
},
|
| 622 |
{
|
| 623 |
"epoch": 2.910958904109589,
|
| 624 |
-
"grad_norm": 0.
|
| 625 |
-
"learning_rate": 0.
|
| 626 |
-
"loss": 1.
|
| 627 |
"step": 425
|
| 628 |
},
|
| 629 |
{
|
| 630 |
"epoch": 2.9452054794520546,
|
| 631 |
-
"grad_norm": 0.
|
| 632 |
-
"learning_rate": 0.
|
| 633 |
-
"loss": 1.
|
| 634 |
"step": 430
|
| 635 |
},
|
| 636 |
{
|
| 637 |
"epoch": 2.9794520547945207,
|
| 638 |
-
"grad_norm":
|
| 639 |
-
"learning_rate": 0.
|
| 640 |
-
"loss": 1.
|
| 641 |
"step": 435
|
| 642 |
},
|
| 643 |
{
|
| 644 |
"epoch": 3.0,
|
| 645 |
-
"eval_loss": 2.
|
| 646 |
-
"eval_runtime": 0.
|
| 647 |
-
"eval_samples_per_second": 18.
|
| 648 |
-
"eval_steps_per_second": 1.
|
| 649 |
"step": 438
|
| 650 |
},
|
| 651 |
{
|
| 652 |
"epoch": 3.0136986301369864,
|
| 653 |
-
"grad_norm":
|
| 654 |
-
"learning_rate": 0.
|
| 655 |
-
"loss": 1.
|
| 656 |
"step": 440
|
| 657 |
},
|
| 658 |
{
|
| 659 |
"epoch": 3.047945205479452,
|
| 660 |
-
"grad_norm": 0.
|
| 661 |
-
"learning_rate": 0.
|
| 662 |
-
"loss":
|
| 663 |
"step": 445
|
| 664 |
},
|
| 665 |
{
|
| 666 |
"epoch": 3.0821917808219177,
|
| 667 |
-
"grad_norm": 0.
|
| 668 |
-
"learning_rate": 0.
|
| 669 |
-
"loss":
|
| 670 |
"step": 450
|
| 671 |
},
|
| 672 |
{
|
| 673 |
"epoch": 3.1164383561643834,
|
| 674 |
-
"grad_norm": 0.
|
| 675 |
-
"learning_rate": 0.
|
| 676 |
-
"loss":
|
| 677 |
"step": 455
|
| 678 |
},
|
| 679 |
{
|
| 680 |
"epoch": 3.1506849315068495,
|
| 681 |
-
"grad_norm": 0.
|
| 682 |
-
"learning_rate": 0.
|
| 683 |
-
"loss":
|
| 684 |
"step": 460
|
| 685 |
},
|
| 686 |
{
|
| 687 |
"epoch": 3.184931506849315,
|
| 688 |
-
"grad_norm": 0.
|
| 689 |
-
"learning_rate": 0.
|
| 690 |
-
"loss":
|
| 691 |
"step": 465
|
| 692 |
},
|
| 693 |
{
|
| 694 |
"epoch": 3.219178082191781,
|
| 695 |
-
"grad_norm": 0.
|
| 696 |
-
"learning_rate": 0.
|
| 697 |
-
"loss":
|
| 698 |
"step": 470
|
| 699 |
},
|
| 700 |
{
|
| 701 |
"epoch": 3.2534246575342465,
|
| 702 |
-
"grad_norm": 0.
|
| 703 |
-
"learning_rate": 0.
|
| 704 |
-
"loss":
|
| 705 |
"step": 475
|
| 706 |
},
|
| 707 |
{
|
| 708 |
"epoch": 3.287671232876712,
|
| 709 |
-
"grad_norm":
|
| 710 |
-
"learning_rate": 0.
|
| 711 |
-
"loss":
|
| 712 |
"step": 480
|
| 713 |
},
|
| 714 |
{
|
| 715 |
"epoch": 3.3219178082191783,
|
| 716 |
-
"grad_norm": 0.
|
| 717 |
-
"learning_rate": 0.
|
| 718 |
-
"loss":
|
| 719 |
"step": 485
|
| 720 |
},
|
| 721 |
{
|
| 722 |
"epoch": 3.356164383561644,
|
| 723 |
-
"grad_norm": 0.
|
| 724 |
-
"learning_rate": 0.
|
| 725 |
-
"loss":
|
| 726 |
"step": 490
|
| 727 |
},
|
| 728 |
{
|
| 729 |
"epoch": 3.3904109589041096,
|
| 730 |
-
"grad_norm": 0.
|
| 731 |
-
"learning_rate": 0.
|
| 732 |
-
"loss":
|
| 733 |
"step": 495
|
| 734 |
},
|
| 735 |
{
|
| 736 |
"epoch": 3.4246575342465753,
|
| 737 |
-
"grad_norm": 0.
|
| 738 |
-
"learning_rate": 0.
|
| 739 |
-
"loss":
|
| 740 |
"step": 500
|
| 741 |
},
|
| 742 |
{
|
| 743 |
"epoch": 3.458904109589041,
|
| 744 |
-
"grad_norm": 0.
|
| 745 |
-
"learning_rate": 0.
|
| 746 |
-
"loss":
|
| 747 |
"step": 505
|
| 748 |
},
|
| 749 |
{
|
| 750 |
"epoch": 3.493150684931507,
|
| 751 |
-
"grad_norm": 0.
|
| 752 |
-
"learning_rate": 0.
|
| 753 |
-
"loss":
|
| 754 |
"step": 510
|
| 755 |
},
|
| 756 |
{
|
| 757 |
"epoch": 3.5273972602739727,
|
| 758 |
-
"grad_norm": 0.
|
| 759 |
-
"learning_rate": 0.
|
| 760 |
-
"loss":
|
| 761 |
"step": 515
|
| 762 |
},
|
| 763 |
{
|
| 764 |
"epoch": 3.5616438356164384,
|
| 765 |
-
"grad_norm": 0.
|
| 766 |
-
"learning_rate": 0.
|
| 767 |
-
"loss":
|
| 768 |
"step": 520
|
| 769 |
},
|
| 770 |
{
|
| 771 |
"epoch": 3.595890410958904,
|
| 772 |
-
"grad_norm": 0.
|
| 773 |
-
"learning_rate": 0.
|
| 774 |
-
"loss":
|
| 775 |
"step": 525
|
| 776 |
},
|
| 777 |
{
|
| 778 |
"epoch": 3.6301369863013697,
|
| 779 |
-
"grad_norm": 0.
|
| 780 |
-
"learning_rate": 0.
|
| 781 |
-
"loss":
|
| 782 |
"step": 530
|
| 783 |
},
|
| 784 |
{
|
| 785 |
"epoch": 3.6643835616438354,
|
| 786 |
-
"grad_norm": 0.
|
| 787 |
-
"learning_rate": 0.
|
| 788 |
-
"loss":
|
| 789 |
"step": 535
|
| 790 |
},
|
| 791 |
{
|
| 792 |
"epoch": 3.6986301369863015,
|
| 793 |
-
"grad_norm": 0.
|
| 794 |
-
"learning_rate": 0.
|
| 795 |
-
"loss":
|
| 796 |
"step": 540
|
| 797 |
},
|
| 798 |
{
|
| 799 |
"epoch": 3.732876712328767,
|
| 800 |
-
"grad_norm": 0.
|
| 801 |
-
"learning_rate": 0.
|
| 802 |
-
"loss":
|
| 803 |
"step": 545
|
| 804 |
},
|
| 805 |
{
|
| 806 |
"epoch": 3.767123287671233,
|
| 807 |
-
"grad_norm": 0.
|
| 808 |
-
"learning_rate": 0.
|
| 809 |
-
"loss":
|
| 810 |
"step": 550
|
| 811 |
},
|
| 812 |
{
|
| 813 |
"epoch": 3.8013698630136985,
|
| 814 |
-
"grad_norm": 0.
|
| 815 |
-
"learning_rate": 0.
|
| 816 |
-
"loss":
|
| 817 |
"step": 555
|
| 818 |
},
|
| 819 |
{
|
| 820 |
"epoch": 3.8356164383561646,
|
| 821 |
-
"grad_norm": 0.
|
| 822 |
-
"learning_rate": 0.
|
| 823 |
-
"loss":
|
| 824 |
"step": 560
|
| 825 |
},
|
| 826 |
{
|
| 827 |
"epoch": 3.8698630136986303,
|
| 828 |
-
"grad_norm": 0.
|
| 829 |
-
"learning_rate": 0.
|
| 830 |
-
"loss":
|
| 831 |
"step": 565
|
| 832 |
},
|
| 833 |
{
|
| 834 |
"epoch": 3.904109589041096,
|
| 835 |
-
"grad_norm": 0.
|
| 836 |
-
"learning_rate": 0.
|
| 837 |
-
"loss":
|
| 838 |
"step": 570
|
| 839 |
},
|
| 840 |
{
|
| 841 |
"epoch": 3.9383561643835616,
|
| 842 |
-
"grad_norm": 0.
|
| 843 |
-
"learning_rate": 0.
|
| 844 |
-
"loss":
|
| 845 |
"step": 575
|
| 846 |
},
|
| 847 |
{
|
| 848 |
"epoch": 3.9726027397260273,
|
| 849 |
-
"grad_norm": 0.
|
| 850 |
-
"learning_rate": 0.
|
| 851 |
-
"loss":
|
| 852 |
"step": 580
|
| 853 |
},
|
| 854 |
{
|
| 855 |
"epoch": 4.0,
|
| 856 |
-
"eval_loss": 2.
|
| 857 |
-
"eval_runtime": 0.
|
| 858 |
-
"eval_samples_per_second":
|
| 859 |
-
"eval_steps_per_second": 1.
|
| 860 |
"step": 584
|
| 861 |
},
|
| 862 |
{
|
| 863 |
"epoch": 4.006849315068493,
|
| 864 |
-
"grad_norm": 0.
|
| 865 |
-
"learning_rate": 0.
|
| 866 |
-
"loss":
|
| 867 |
"step": 585
|
| 868 |
},
|
| 869 |
{
|
| 870 |
"epoch": 4.041095890410959,
|
| 871 |
-
"grad_norm": 0.
|
| 872 |
-
"learning_rate": 0.
|
| 873 |
-
"loss": 0.
|
| 874 |
"step": 590
|
| 875 |
},
|
| 876 |
{
|
| 877 |
"epoch": 4.075342465753424,
|
| 878 |
-
"grad_norm": 0.
|
| 879 |
-
"learning_rate": 0.
|
| 880 |
-
"loss":
|
| 881 |
"step": 595
|
| 882 |
},
|
| 883 |
{
|
| 884 |
"epoch": 4.109589041095891,
|
| 885 |
-
"grad_norm": 0.
|
| 886 |
-
"learning_rate": 0.
|
| 887 |
-
"loss":
|
| 888 |
"step": 600
|
| 889 |
},
|
| 890 |
{
|
| 891 |
"epoch": 4.1438356164383565,
|
| 892 |
-
"grad_norm": 0.
|
| 893 |
-
"learning_rate": 0.
|
| 894 |
-
"loss":
|
| 895 |
"step": 605
|
| 896 |
},
|
| 897 |
{
|
| 898 |
"epoch": 4.178082191780822,
|
| 899 |
-
"grad_norm": 0.
|
| 900 |
-
"learning_rate": 0.
|
| 901 |
-
"loss": 0.
|
| 902 |
"step": 610
|
| 903 |
},
|
| 904 |
{
|
| 905 |
"epoch": 4.212328767123288,
|
| 906 |
-
"grad_norm": 0.
|
| 907 |
-
"learning_rate": 0.
|
| 908 |
-
"loss":
|
| 909 |
"step": 615
|
| 910 |
},
|
| 911 |
{
|
| 912 |
"epoch": 4.2465753424657535,
|
| 913 |
-
"grad_norm": 0.
|
| 914 |
-
"learning_rate": 0.
|
| 915 |
-
"loss": 0.
|
| 916 |
"step": 620
|
| 917 |
},
|
| 918 |
{
|
| 919 |
"epoch": 4.280821917808219,
|
| 920 |
-
"grad_norm": 0.
|
| 921 |
-
"learning_rate": 0.
|
| 922 |
-
"loss":
|
| 923 |
"step": 625
|
| 924 |
},
|
| 925 |
{
|
| 926 |
"epoch": 4.315068493150685,
|
| 927 |
-
"grad_norm": 0.
|
| 928 |
-
"learning_rate": 0.
|
| 929 |
-
"loss": 0.
|
| 930 |
"step": 630
|
| 931 |
},
|
| 932 |
{
|
| 933 |
"epoch": 4.3493150684931505,
|
| 934 |
-
"grad_norm": 0.
|
| 935 |
-
"learning_rate": 0.
|
| 936 |
-
"loss":
|
| 937 |
"step": 635
|
| 938 |
},
|
| 939 |
{
|
| 940 |
"epoch": 4.383561643835616,
|
| 941 |
-
"grad_norm": 0.
|
| 942 |
-
"learning_rate": 0.
|
| 943 |
-
"loss":
|
| 944 |
"step": 640
|
| 945 |
},
|
| 946 |
{
|
| 947 |
"epoch": 4.417808219178082,
|
| 948 |
-
"grad_norm": 0.
|
| 949 |
-
"learning_rate": 0.
|
| 950 |
-
"loss":
|
| 951 |
"step": 645
|
| 952 |
},
|
| 953 |
{
|
| 954 |
"epoch": 4.4520547945205475,
|
| 955 |
-
"grad_norm": 0.
|
| 956 |
-
"learning_rate": 0.
|
| 957 |
-
"loss":
|
| 958 |
"step": 650
|
| 959 |
},
|
| 960 |
{
|
| 961 |
"epoch": 4.486301369863014,
|
| 962 |
-
"grad_norm": 0.
|
| 963 |
-
"learning_rate": 0.
|
| 964 |
-
"loss":
|
| 965 |
"step": 655
|
| 966 |
},
|
| 967 |
{
|
| 968 |
"epoch": 4.52054794520548,
|
| 969 |
-
"grad_norm": 0.
|
| 970 |
-
"learning_rate": 0.
|
| 971 |
-
"loss":
|
| 972 |
"step": 660
|
| 973 |
},
|
| 974 |
{
|
| 975 |
"epoch": 4.554794520547945,
|
| 976 |
-
"grad_norm": 0.
|
| 977 |
-
"learning_rate": 0.
|
| 978 |
-
"loss":
|
| 979 |
"step": 665
|
| 980 |
},
|
| 981 |
{
|
| 982 |
"epoch": 4.589041095890411,
|
| 983 |
-
"grad_norm": 0.
|
| 984 |
-
"learning_rate": 0.
|
| 985 |
-
"loss":
|
| 986 |
"step": 670
|
| 987 |
},
|
| 988 |
{
|
| 989 |
"epoch": 4.623287671232877,
|
| 990 |
-
"grad_norm": 0.
|
| 991 |
-
"learning_rate": 0.
|
| 992 |
-
"loss":
|
| 993 |
"step": 675
|
| 994 |
},
|
| 995 |
{
|
| 996 |
"epoch": 4.657534246575342,
|
| 997 |
-
"grad_norm": 0.
|
| 998 |
-
"learning_rate": 0.
|
| 999 |
-
"loss":
|
| 1000 |
"step": 680
|
| 1001 |
},
|
| 1002 |
{
|
| 1003 |
"epoch": 4.691780821917808,
|
| 1004 |
-
"grad_norm": 0.
|
| 1005 |
-
"learning_rate": 0.
|
| 1006 |
-
"loss":
|
| 1007 |
"step": 685
|
| 1008 |
},
|
| 1009 |
{
|
| 1010 |
"epoch": 4.726027397260274,
|
| 1011 |
-
"grad_norm": 0.
|
| 1012 |
-
"learning_rate": 0.
|
| 1013 |
-
"loss":
|
| 1014 |
"step": 690
|
| 1015 |
},
|
| 1016 |
{
|
| 1017 |
"epoch": 4.760273972602739,
|
| 1018 |
-
"grad_norm": 0.
|
| 1019 |
-
"learning_rate": 0.
|
| 1020 |
-
"loss":
|
| 1021 |
"step": 695
|
| 1022 |
},
|
| 1023 |
{
|
| 1024 |
"epoch": 4.794520547945205,
|
| 1025 |
-
"grad_norm": 0.
|
| 1026 |
-
"learning_rate": 0.
|
| 1027 |
-
"loss":
|
| 1028 |
"step": 700
|
| 1029 |
},
|
| 1030 |
{
|
| 1031 |
"epoch": 4.828767123287671,
|
| 1032 |
-
"grad_norm": 0.
|
| 1033 |
-
"learning_rate": 0.
|
| 1034 |
-
"loss":
|
| 1035 |
"step": 705
|
| 1036 |
},
|
| 1037 |
{
|
| 1038 |
"epoch": 4.863013698630137,
|
| 1039 |
-
"grad_norm": 0.
|
| 1040 |
-
"learning_rate": 0.
|
| 1041 |
-
"loss":
|
| 1042 |
"step": 710
|
| 1043 |
},
|
| 1044 |
{
|
| 1045 |
"epoch": 4.897260273972603,
|
| 1046 |
"grad_norm": 0.359375,
|
| 1047 |
-
"learning_rate": 0.
|
| 1048 |
-
"loss":
|
| 1049 |
"step": 715
|
| 1050 |
},
|
| 1051 |
{
|
| 1052 |
"epoch": 4.931506849315069,
|
| 1053 |
-
"grad_norm": 0.
|
| 1054 |
-
"learning_rate": 0.
|
| 1055 |
-
"loss":
|
| 1056 |
"step": 720
|
| 1057 |
},
|
| 1058 |
{
|
| 1059 |
"epoch": 4.965753424657534,
|
| 1060 |
-
"grad_norm": 0.
|
| 1061 |
-
"learning_rate": 0.
|
| 1062 |
-
"loss":
|
| 1063 |
"step": 725
|
| 1064 |
},
|
| 1065 |
{
|
| 1066 |
"epoch": 5.0,
|
| 1067 |
-
"grad_norm": 0.
|
| 1068 |
-
"learning_rate": 0.
|
| 1069 |
-
"loss":
|
| 1070 |
"step": 730
|
| 1071 |
},
|
| 1072 |
{
|
| 1073 |
"epoch": 5.0,
|
| 1074 |
-
"eval_loss": 2.
|
| 1075 |
-
"eval_runtime": 0.
|
| 1076 |
-
"eval_samples_per_second": 18.
|
| 1077 |
-
"eval_steps_per_second": 1.
|
| 1078 |
"step": 730
|
| 1079 |
},
|
| 1080 |
{
|
| 1081 |
"epoch": 5.034246575342466,
|
| 1082 |
-
"grad_norm": 0.
|
| 1083 |
-
"learning_rate": 0.
|
| 1084 |
-
"loss": 0.
|
| 1085 |
"step": 735
|
| 1086 |
},
|
| 1087 |
{
|
| 1088 |
"epoch": 5.068493150684931,
|
| 1089 |
-
"grad_norm": 0.
|
| 1090 |
-
"learning_rate": 0.
|
| 1091 |
-
"loss": 0.
|
| 1092 |
"step": 740
|
| 1093 |
},
|
| 1094 |
{
|
| 1095 |
"epoch": 5.102739726027397,
|
| 1096 |
-
"grad_norm": 0.
|
| 1097 |
-
"learning_rate": 0.
|
| 1098 |
-
"loss": 0.
|
| 1099 |
"step": 745
|
| 1100 |
},
|
| 1101 |
{
|
| 1102 |
"epoch": 5.136986301369863,
|
| 1103 |
-
"grad_norm": 0.
|
| 1104 |
-
"learning_rate": 0.
|
| 1105 |
-
"loss": 0.
|
| 1106 |
"step": 750
|
| 1107 |
},
|
| 1108 |
{
|
| 1109 |
"epoch": 5.171232876712328,
|
| 1110 |
-
"grad_norm": 0.
|
| 1111 |
-
"learning_rate": 0.
|
| 1112 |
-
"loss": 0.
|
| 1113 |
"step": 755
|
| 1114 |
},
|
| 1115 |
{
|
| 1116 |
"epoch": 5.205479452054795,
|
| 1117 |
-
"grad_norm": 0.
|
| 1118 |
-
"learning_rate": 0.
|
| 1119 |
-
"loss": 0.
|
| 1120 |
"step": 760
|
| 1121 |
},
|
| 1122 |
{
|
| 1123 |
"epoch": 5.239726027397261,
|
| 1124 |
-
"grad_norm": 0.
|
| 1125 |
-
"learning_rate": 0.
|
| 1126 |
-
"loss": 0.
|
| 1127 |
"step": 765
|
| 1128 |
},
|
| 1129 |
{
|
| 1130 |
"epoch": 5.273972602739726,
|
| 1131 |
-
"grad_norm": 0.
|
| 1132 |
-
"learning_rate": 0.
|
| 1133 |
-
"loss": 0.
|
| 1134 |
"step": 770
|
| 1135 |
},
|
| 1136 |
{
|
| 1137 |
"epoch": 5.308219178082192,
|
| 1138 |
-
"grad_norm": 0.
|
| 1139 |
-
"learning_rate": 0.
|
| 1140 |
-
"loss": 0.
|
| 1141 |
"step": 775
|
| 1142 |
},
|
| 1143 |
{
|
| 1144 |
"epoch": 5.342465753424658,
|
| 1145 |
-
"grad_norm": 0.
|
| 1146 |
-
"learning_rate": 0.
|
| 1147 |
-
"loss": 0.
|
| 1148 |
"step": 780
|
| 1149 |
},
|
| 1150 |
{
|
| 1151 |
"epoch": 5.376712328767123,
|
| 1152 |
-
"grad_norm": 0.
|
| 1153 |
-
"learning_rate": 0.
|
| 1154 |
-
"loss": 0.
|
| 1155 |
"step": 785
|
| 1156 |
},
|
| 1157 |
{
|
| 1158 |
"epoch": 5.410958904109589,
|
| 1159 |
-
"grad_norm": 0.
|
| 1160 |
-
"learning_rate": 0.
|
| 1161 |
-
"loss": 0.
|
| 1162 |
"step": 790
|
| 1163 |
},
|
| 1164 |
{
|
| 1165 |
"epoch": 5.445205479452055,
|
| 1166 |
-
"grad_norm": 0.
|
| 1167 |
-
"learning_rate": 0.
|
| 1168 |
-
"loss": 0.
|
| 1169 |
"step": 795
|
| 1170 |
},
|
| 1171 |
{
|
| 1172 |
"epoch": 5.47945205479452,
|
| 1173 |
-
"grad_norm": 0.
|
| 1174 |
-
"learning_rate": 0.
|
| 1175 |
-
"loss": 0.
|
| 1176 |
"step": 800
|
| 1177 |
},
|
| 1178 |
{
|
| 1179 |
"epoch": 5.513698630136986,
|
| 1180 |
-
"grad_norm": 0.
|
| 1181 |
-
"learning_rate":
|
| 1182 |
-
"loss": 0.
|
| 1183 |
"step": 805
|
| 1184 |
},
|
| 1185 |
{
|
| 1186 |
"epoch": 5.5479452054794525,
|
| 1187 |
-
"grad_norm": 0.
|
| 1188 |
-
"learning_rate":
|
| 1189 |
-
"loss": 0.
|
| 1190 |
"step": 810
|
| 1191 |
},
|
| 1192 |
{
|
| 1193 |
"epoch": 5.582191780821918,
|
| 1194 |
-
"grad_norm": 0.
|
| 1195 |
-
"learning_rate":
|
| 1196 |
-
"loss": 0.
|
| 1197 |
"step": 815
|
| 1198 |
},
|
| 1199 |
{
|
| 1200 |
"epoch": 5.616438356164384,
|
| 1201 |
-
"grad_norm": 0.
|
| 1202 |
-
"learning_rate":
|
| 1203 |
-
"loss": 0.
|
| 1204 |
"step": 820
|
| 1205 |
},
|
| 1206 |
{
|
| 1207 |
"epoch": 5.6506849315068495,
|
| 1208 |
-
"grad_norm": 0.
|
| 1209 |
-
"learning_rate":
|
| 1210 |
-
"loss": 0.
|
| 1211 |
"step": 825
|
| 1212 |
},
|
| 1213 |
{
|
| 1214 |
"epoch": 5.684931506849315,
|
| 1215 |
-
"grad_norm": 0.
|
| 1216 |
-
"learning_rate":
|
| 1217 |
-
"loss": 0.
|
| 1218 |
"step": 830
|
| 1219 |
},
|
| 1220 |
{
|
| 1221 |
"epoch": 5.719178082191781,
|
| 1222 |
-
"grad_norm": 0.
|
| 1223 |
-
"learning_rate":
|
| 1224 |
-
"loss": 0.
|
| 1225 |
"step": 835
|
| 1226 |
},
|
| 1227 |
{
|
| 1228 |
"epoch": 5.7534246575342465,
|
| 1229 |
-
"grad_norm": 0.
|
| 1230 |
-
"learning_rate":
|
| 1231 |
-
"loss": 0.
|
| 1232 |
"step": 840
|
| 1233 |
},
|
| 1234 |
{
|
| 1235 |
"epoch": 5.787671232876712,
|
| 1236 |
-
"grad_norm": 0.
|
| 1237 |
-
"learning_rate":
|
| 1238 |
-
"loss": 0.
|
| 1239 |
"step": 845
|
| 1240 |
},
|
| 1241 |
{
|
| 1242 |
"epoch": 5.821917808219178,
|
| 1243 |
-
"grad_norm": 0.
|
| 1244 |
-
"learning_rate":
|
| 1245 |
-
"loss": 0.
|
| 1246 |
"step": 850
|
| 1247 |
},
|
| 1248 |
{
|
| 1249 |
"epoch": 5.8561643835616435,
|
| 1250 |
-
"grad_norm": 0.
|
| 1251 |
-
"learning_rate":
|
| 1252 |
-
"loss": 0.
|
| 1253 |
"step": 855
|
| 1254 |
},
|
| 1255 |
{
|
| 1256 |
"epoch": 5.890410958904109,
|
| 1257 |
-
"grad_norm": 0.
|
| 1258 |
-
"learning_rate":
|
| 1259 |
-
"loss": 0.
|
| 1260 |
"step": 860
|
| 1261 |
},
|
| 1262 |
{
|
| 1263 |
"epoch": 5.924657534246576,
|
| 1264 |
-
"grad_norm": 0.
|
| 1265 |
-
"learning_rate":
|
| 1266 |
-
"loss": 0.
|
| 1267 |
"step": 865
|
| 1268 |
},
|
| 1269 |
{
|
| 1270 |
"epoch": 5.958904109589041,
|
| 1271 |
-
"grad_norm": 0.
|
| 1272 |
-
"learning_rate":
|
| 1273 |
-
"loss": 0.
|
| 1274 |
"step": 870
|
| 1275 |
},
|
| 1276 |
{
|
| 1277 |
"epoch": 5.993150684931507,
|
| 1278 |
-
"grad_norm": 0.
|
| 1279 |
-
"learning_rate":
|
| 1280 |
-
"loss": 0.
|
| 1281 |
"step": 875
|
| 1282 |
},
|
| 1283 |
{
|
| 1284 |
"epoch": 6.0,
|
| 1285 |
-
"eval_loss": 2.
|
| 1286 |
-
"eval_runtime": 0.
|
| 1287 |
-
"eval_samples_per_second": 18.
|
| 1288 |
-
"eval_steps_per_second": 1.
|
| 1289 |
"step": 876
|
| 1290 |
},
|
| 1291 |
{
|
| 1292 |
"epoch": 6.027397260273973,
|
| 1293 |
-
"grad_norm": 0.
|
| 1294 |
-
"learning_rate":
|
| 1295 |
-
"loss": 0.
|
| 1296 |
"step": 880
|
| 1297 |
},
|
| 1298 |
{
|
| 1299 |
"epoch": 6.061643835616438,
|
| 1300 |
-
"grad_norm": 0.
|
| 1301 |
-
"learning_rate":
|
| 1302 |
-
"loss": 0.
|
| 1303 |
"step": 885
|
| 1304 |
},
|
| 1305 |
{
|
| 1306 |
"epoch": 6.095890410958904,
|
| 1307 |
-
"grad_norm": 0.
|
| 1308 |
-
"learning_rate":
|
| 1309 |
-
"loss": 0.
|
| 1310 |
"step": 890
|
| 1311 |
},
|
| 1312 |
{
|
| 1313 |
"epoch": 6.13013698630137,
|
| 1314 |
-
"grad_norm": 0.
|
| 1315 |
-
"learning_rate":
|
| 1316 |
-
"loss": 0.
|
| 1317 |
"step": 895
|
| 1318 |
},
|
| 1319 |
{
|
| 1320 |
"epoch": 6.164383561643835,
|
| 1321 |
-
"grad_norm": 0.
|
| 1322 |
-
"learning_rate":
|
| 1323 |
-
"loss": 0.
|
| 1324 |
"step": 900
|
| 1325 |
},
|
| 1326 |
{
|
| 1327 |
"epoch": 6.198630136986301,
|
| 1328 |
-
"grad_norm": 0.
|
| 1329 |
-
"learning_rate":
|
| 1330 |
-
"loss": 0.
|
| 1331 |
"step": 905
|
| 1332 |
},
|
| 1333 |
{
|
| 1334 |
"epoch": 6.232876712328767,
|
| 1335 |
-
"grad_norm": 0.
|
| 1336 |
-
"learning_rate":
|
| 1337 |
-
"loss": 0.
|
| 1338 |
"step": 910
|
| 1339 |
},
|
| 1340 |
{
|
| 1341 |
"epoch": 6.267123287671233,
|
| 1342 |
-
"grad_norm": 0.
|
| 1343 |
-
"learning_rate":
|
| 1344 |
-
"loss": 0.
|
| 1345 |
"step": 915
|
| 1346 |
},
|
| 1347 |
{
|
| 1348 |
"epoch": 6.301369863013699,
|
| 1349 |
-
"grad_norm": 0.
|
| 1350 |
-
"learning_rate":
|
| 1351 |
-
"loss": 0.
|
| 1352 |
"step": 920
|
| 1353 |
},
|
| 1354 |
{
|
| 1355 |
"epoch": 6.335616438356165,
|
| 1356 |
-
"grad_norm": 0.
|
| 1357 |
-
"learning_rate":
|
| 1358 |
-
"loss": 0.
|
| 1359 |
"step": 925
|
| 1360 |
},
|
| 1361 |
{
|
| 1362 |
"epoch": 6.36986301369863,
|
| 1363 |
-
"grad_norm": 0.
|
| 1364 |
-
"learning_rate":
|
| 1365 |
-
"loss": 0.
|
| 1366 |
"step": 930
|
| 1367 |
},
|
| 1368 |
{
|
| 1369 |
"epoch": 6.404109589041096,
|
| 1370 |
-
"grad_norm": 0.
|
| 1371 |
-
"learning_rate":
|
| 1372 |
-
"loss": 0.
|
| 1373 |
"step": 935
|
| 1374 |
},
|
| 1375 |
{
|
| 1376 |
"epoch": 6.438356164383562,
|
| 1377 |
-
"grad_norm": 0.
|
| 1378 |
-
"learning_rate":
|
| 1379 |
-
"loss": 0.
|
| 1380 |
"step": 940
|
| 1381 |
},
|
| 1382 |
{
|
| 1383 |
"epoch": 6.472602739726027,
|
| 1384 |
-
"grad_norm": 0.
|
| 1385 |
-
"learning_rate":
|
| 1386 |
-
"loss": 0.
|
| 1387 |
"step": 945
|
| 1388 |
},
|
| 1389 |
{
|
| 1390 |
"epoch": 6.506849315068493,
|
| 1391 |
-
"grad_norm": 0.
|
| 1392 |
-
"learning_rate":
|
| 1393 |
-
"loss": 0.
|
| 1394 |
"step": 950
|
| 1395 |
},
|
| 1396 |
{
|
| 1397 |
"epoch": 6.541095890410959,
|
| 1398 |
-
"grad_norm": 0.
|
| 1399 |
-
"learning_rate":
|
| 1400 |
-
"loss": 0.
|
| 1401 |
"step": 955
|
| 1402 |
},
|
| 1403 |
{
|
| 1404 |
"epoch": 6.575342465753424,
|
| 1405 |
-
"grad_norm": 0.
|
| 1406 |
-
"learning_rate":
|
| 1407 |
-
"loss": 0.
|
| 1408 |
"step": 960
|
| 1409 |
},
|
| 1410 |
{
|
| 1411 |
"epoch": 6.609589041095891,
|
| 1412 |
-
"grad_norm": 0.
|
| 1413 |
-
"learning_rate":
|
| 1414 |
-
"loss": 0.
|
| 1415 |
"step": 965
|
| 1416 |
},
|
| 1417 |
{
|
| 1418 |
"epoch": 6.6438356164383565,
|
| 1419 |
-
"grad_norm": 0.
|
| 1420 |
-
"learning_rate":
|
| 1421 |
-
"loss": 0.
|
| 1422 |
"step": 970
|
| 1423 |
},
|
| 1424 |
{
|
| 1425 |
"epoch": 6.678082191780822,
|
| 1426 |
-
"grad_norm": 0.
|
| 1427 |
-
"learning_rate":
|
| 1428 |
-
"loss": 0.
|
| 1429 |
"step": 975
|
| 1430 |
},
|
| 1431 |
{
|
| 1432 |
"epoch": 6.712328767123288,
|
| 1433 |
-
"grad_norm": 0.
|
| 1434 |
-
"learning_rate":
|
| 1435 |
-
"loss": 0.
|
| 1436 |
"step": 980
|
| 1437 |
},
|
| 1438 |
{
|
| 1439 |
"epoch": 6.7465753424657535,
|
| 1440 |
-
"grad_norm": 0.
|
| 1441 |
-
"learning_rate":
|
| 1442 |
-
"loss": 0.
|
| 1443 |
"step": 985
|
| 1444 |
},
|
| 1445 |
{
|
| 1446 |
"epoch": 6.780821917808219,
|
| 1447 |
-
"grad_norm": 0.
|
| 1448 |
-
"learning_rate":
|
| 1449 |
-
"loss": 0.
|
| 1450 |
"step": 990
|
| 1451 |
},
|
| 1452 |
{
|
| 1453 |
"epoch": 6.815068493150685,
|
| 1454 |
-
"grad_norm": 0.
|
| 1455 |
-
"learning_rate":
|
| 1456 |
-
"loss": 0.
|
| 1457 |
"step": 995
|
| 1458 |
},
|
| 1459 |
{
|
| 1460 |
"epoch": 6.8493150684931505,
|
| 1461 |
-
"grad_norm": 0.
|
| 1462 |
-
"learning_rate":
|
| 1463 |
-
"loss": 0.
|
| 1464 |
"step": 1000
|
| 1465 |
},
|
| 1466 |
{
|
| 1467 |
"epoch": 6.883561643835616,
|
| 1468 |
-
"grad_norm": 0.
|
| 1469 |
-
"learning_rate":
|
| 1470 |
-
"loss": 0.
|
| 1471 |
"step": 1005
|
| 1472 |
},
|
| 1473 |
{
|
| 1474 |
"epoch": 6.917808219178082,
|
| 1475 |
-
"grad_norm": 0.
|
| 1476 |
-
"learning_rate":
|
| 1477 |
-
"loss": 0.
|
| 1478 |
"step": 1010
|
| 1479 |
},
|
| 1480 |
{
|
| 1481 |
"epoch": 6.9520547945205475,
|
| 1482 |
-
"grad_norm": 0.
|
| 1483 |
-
"learning_rate":
|
| 1484 |
-
"loss": 0.
|
| 1485 |
"step": 1015
|
| 1486 |
},
|
| 1487 |
{
|
| 1488 |
"epoch": 6.986301369863014,
|
| 1489 |
-
"grad_norm": 0.
|
| 1490 |
-
"learning_rate":
|
| 1491 |
-
"loss": 0.
|
| 1492 |
"step": 1020
|
| 1493 |
},
|
| 1494 |
{
|
| 1495 |
"epoch": 7.0,
|
| 1496 |
-
"eval_loss": 2.
|
| 1497 |
-
"eval_runtime": 0.
|
| 1498 |
-
"eval_samples_per_second":
|
| 1499 |
-
"eval_steps_per_second": 1.
|
| 1500 |
"step": 1022
|
| 1501 |
},
|
| 1502 |
{
|
| 1503 |
"epoch": 7.02054794520548,
|
| 1504 |
-
"grad_norm": 0.
|
| 1505 |
-
"learning_rate":
|
| 1506 |
-
"loss": 0.
|
| 1507 |
"step": 1025
|
| 1508 |
},
|
| 1509 |
{
|
| 1510 |
"epoch": 7.054794520547945,
|
| 1511 |
-
"grad_norm": 0.
|
| 1512 |
-
"learning_rate":
|
| 1513 |
-
"loss": 0.
|
| 1514 |
"step": 1030
|
| 1515 |
},
|
| 1516 |
{
|
| 1517 |
"epoch": 7.089041095890411,
|
| 1518 |
-
"grad_norm": 0.
|
| 1519 |
-
"learning_rate":
|
| 1520 |
-
"loss": 0.
|
| 1521 |
"step": 1035
|
| 1522 |
},
|
| 1523 |
{
|
| 1524 |
"epoch": 7.123287671232877,
|
| 1525 |
-
"grad_norm": 0.
|
| 1526 |
-
"learning_rate":
|
| 1527 |
-
"loss": 0.
|
| 1528 |
"step": 1040
|
| 1529 |
},
|
| 1530 |
{
|
| 1531 |
"epoch": 7.157534246575342,
|
| 1532 |
-
"grad_norm": 0.
|
| 1533 |
-
"learning_rate":
|
| 1534 |
-
"loss": 0.
|
| 1535 |
"step": 1045
|
| 1536 |
},
|
| 1537 |
{
|
| 1538 |
"epoch": 7.191780821917808,
|
| 1539 |
-
"grad_norm": 0.
|
| 1540 |
-
"learning_rate":
|
| 1541 |
-
"loss": 0.
|
| 1542 |
"step": 1050
|
| 1543 |
},
|
| 1544 |
{
|
| 1545 |
"epoch": 7.226027397260274,
|
| 1546 |
-
"grad_norm": 0.
|
| 1547 |
-
"learning_rate":
|
| 1548 |
-
"loss": 0.
|
| 1549 |
"step": 1055
|
| 1550 |
},
|
| 1551 |
{
|
| 1552 |
"epoch": 7.260273972602739,
|
| 1553 |
-
"grad_norm": 0.
|
| 1554 |
-
"learning_rate":
|
| 1555 |
-
"loss": 0.
|
| 1556 |
"step": 1060
|
| 1557 |
},
|
| 1558 |
{
|
| 1559 |
"epoch": 7.294520547945205,
|
| 1560 |
-
"grad_norm": 0.
|
| 1561 |
-
"learning_rate":
|
| 1562 |
-
"loss": 0.
|
| 1563 |
"step": 1065
|
| 1564 |
},
|
| 1565 |
{
|
| 1566 |
"epoch": 7.328767123287671,
|
| 1567 |
-
"grad_norm": 0.
|
| 1568 |
-
"learning_rate":
|
| 1569 |
-
"loss": 0.
|
| 1570 |
"step": 1070
|
| 1571 |
},
|
| 1572 |
{
|
| 1573 |
"epoch": 7.363013698630137,
|
| 1574 |
-
"grad_norm": 0.
|
| 1575 |
-
"learning_rate":
|
| 1576 |
-
"loss": 0.
|
| 1577 |
"step": 1075
|
| 1578 |
},
|
| 1579 |
{
|
| 1580 |
"epoch": 7.397260273972603,
|
| 1581 |
-
"grad_norm": 0.
|
| 1582 |
-
"learning_rate":
|
| 1583 |
-
"loss": 0.
|
| 1584 |
"step": 1080
|
| 1585 |
},
|
| 1586 |
{
|
| 1587 |
"epoch": 7.431506849315069,
|
| 1588 |
-
"grad_norm": 0.
|
| 1589 |
-
"learning_rate":
|
| 1590 |
-
"loss": 0.
|
| 1591 |
"step": 1085
|
| 1592 |
},
|
| 1593 |
{
|
| 1594 |
"epoch": 7.465753424657534,
|
| 1595 |
-
"grad_norm": 0.
|
| 1596 |
-
"learning_rate":
|
| 1597 |
-
"loss": 0.
|
| 1598 |
"step": 1090
|
| 1599 |
},
|
| 1600 |
{
|
| 1601 |
"epoch": 7.5,
|
| 1602 |
-
"grad_norm": 0.
|
| 1603 |
-
"learning_rate":
|
| 1604 |
-
"loss": 0.
|
| 1605 |
"step": 1095
|
| 1606 |
},
|
| 1607 |
{
|
| 1608 |
"epoch": 7.534246575342466,
|
| 1609 |
-
"grad_norm": 0.
|
| 1610 |
-
"learning_rate":
|
| 1611 |
-
"loss": 0.
|
| 1612 |
"step": 1100
|
| 1613 |
},
|
| 1614 |
{
|
| 1615 |
"epoch": 7.568493150684931,
|
| 1616 |
-
"grad_norm": 0.
|
| 1617 |
-
"learning_rate":
|
| 1618 |
-
"loss": 0.
|
| 1619 |
"step": 1105
|
| 1620 |
},
|
| 1621 |
{
|
| 1622 |
"epoch": 7.602739726027397,
|
| 1623 |
-
"grad_norm": 0.
|
| 1624 |
-
"learning_rate":
|
| 1625 |
-
"loss": 0.
|
| 1626 |
"step": 1110
|
| 1627 |
},
|
| 1628 |
{
|
| 1629 |
"epoch": 7.636986301369863,
|
| 1630 |
-
"grad_norm": 0.
|
| 1631 |
-
"learning_rate":
|
| 1632 |
-
"loss": 0.
|
| 1633 |
"step": 1115
|
| 1634 |
},
|
| 1635 |
{
|
| 1636 |
"epoch": 7.671232876712329,
|
| 1637 |
-
"grad_norm": 0.
|
| 1638 |
-
"learning_rate":
|
| 1639 |
-
"loss": 0.
|
| 1640 |
"step": 1120
|
| 1641 |
},
|
| 1642 |
{
|
| 1643 |
"epoch": 7.705479452054795,
|
| 1644 |
-
"grad_norm": 0.
|
| 1645 |
-
"learning_rate":
|
| 1646 |
-
"loss": 0.
|
| 1647 |
"step": 1125
|
| 1648 |
},
|
| 1649 |
{
|
| 1650 |
"epoch": 7.739726027397261,
|
| 1651 |
-
"grad_norm": 0.
|
| 1652 |
-
"learning_rate":
|
| 1653 |
-
"loss": 0.
|
| 1654 |
"step": 1130
|
| 1655 |
},
|
| 1656 |
{
|
| 1657 |
"epoch": 7.773972602739726,
|
| 1658 |
-
"grad_norm": 0.
|
| 1659 |
-
"learning_rate":
|
| 1660 |
-
"loss": 0.
|
| 1661 |
"step": 1135
|
| 1662 |
},
|
| 1663 |
{
|
| 1664 |
"epoch": 7.808219178082192,
|
| 1665 |
-
"grad_norm": 0.
|
| 1666 |
-
"learning_rate":
|
| 1667 |
-
"loss": 0.
|
| 1668 |
"step": 1140
|
| 1669 |
},
|
| 1670 |
{
|
| 1671 |
"epoch": 7.842465753424658,
|
| 1672 |
-
"grad_norm": 0.
|
| 1673 |
-
"learning_rate":
|
| 1674 |
-
"loss": 0.
|
| 1675 |
"step": 1145
|
| 1676 |
},
|
| 1677 |
{
|
| 1678 |
"epoch": 7.876712328767123,
|
| 1679 |
-
"grad_norm": 0.
|
| 1680 |
-
"learning_rate":
|
| 1681 |
-
"loss": 0.
|
| 1682 |
"step": 1150
|
| 1683 |
},
|
| 1684 |
{
|
| 1685 |
"epoch": 7.910958904109589,
|
| 1686 |
-
"grad_norm": 0.
|
| 1687 |
-
"learning_rate":
|
| 1688 |
-
"loss": 0.
|
| 1689 |
"step": 1155
|
| 1690 |
},
|
| 1691 |
{
|
| 1692 |
"epoch": 7.945205479452055,
|
| 1693 |
-
"grad_norm": 0.
|
| 1694 |
-
"learning_rate":
|
| 1695 |
-
"loss": 0.
|
| 1696 |
"step": 1160
|
| 1697 |
},
|
| 1698 |
{
|
| 1699 |
"epoch": 7.97945205479452,
|
| 1700 |
-
"grad_norm": 0.
|
| 1701 |
-
"learning_rate":
|
| 1702 |
-
"loss": 0.
|
| 1703 |
"step": 1165
|
| 1704 |
},
|
| 1705 |
{
|
| 1706 |
"epoch": 8.0,
|
| 1707 |
-
"eval_loss": 2.
|
| 1708 |
-
"eval_runtime": 0.
|
| 1709 |
-
"eval_samples_per_second":
|
| 1710 |
-
"eval_steps_per_second": 1.
|
| 1711 |
"step": 1168
|
| 1712 |
},
|
| 1713 |
{
|
| 1714 |
"epoch": 8.013698630136986,
|
| 1715 |
-
"grad_norm": 0.
|
| 1716 |
-
"learning_rate":
|
| 1717 |
-
"loss": 0.
|
| 1718 |
"step": 1170
|
| 1719 |
},
|
| 1720 |
{
|
| 1721 |
"epoch": 8.047945205479452,
|
| 1722 |
-
"grad_norm": 0.
|
| 1723 |
-
"learning_rate":
|
| 1724 |
-
"loss": 0.
|
| 1725 |
"step": 1175
|
| 1726 |
},
|
| 1727 |
{
|
| 1728 |
"epoch": 8.082191780821917,
|
| 1729 |
-
"grad_norm": 0.
|
| 1730 |
-
"learning_rate":
|
| 1731 |
-
"loss": 0.
|
| 1732 |
"step": 1180
|
| 1733 |
},
|
| 1734 |
{
|
| 1735 |
"epoch": 8.116438356164384,
|
| 1736 |
-
"grad_norm": 0.
|
| 1737 |
-
"learning_rate":
|
| 1738 |
-
"loss": 0.
|
| 1739 |
"step": 1185
|
| 1740 |
},
|
| 1741 |
{
|
| 1742 |
"epoch": 8.150684931506849,
|
| 1743 |
-
"grad_norm": 0.
|
| 1744 |
-
"learning_rate":
|
| 1745 |
-
"loss": 0.
|
| 1746 |
"step": 1190
|
| 1747 |
},
|
| 1748 |
{
|
| 1749 |
"epoch": 8.184931506849315,
|
| 1750 |
-
"grad_norm": 0.
|
| 1751 |
-
"learning_rate":
|
| 1752 |
-
"loss": 0.
|
| 1753 |
"step": 1195
|
| 1754 |
},
|
| 1755 |
{
|
| 1756 |
"epoch": 8.219178082191782,
|
| 1757 |
-
"grad_norm": 0.
|
| 1758 |
-
"learning_rate":
|
| 1759 |
-
"loss": 0.
|
| 1760 |
"step": 1200
|
| 1761 |
},
|
| 1762 |
{
|
| 1763 |
"epoch": 8.253424657534246,
|
| 1764 |
-
"grad_norm": 0.
|
| 1765 |
-
"learning_rate":
|
| 1766 |
-
"loss": 0.
|
| 1767 |
"step": 1205
|
| 1768 |
},
|
| 1769 |
{
|
| 1770 |
"epoch": 8.287671232876713,
|
| 1771 |
-
"grad_norm": 0.
|
| 1772 |
-
"learning_rate":
|
| 1773 |
-
"loss": 0.
|
| 1774 |
"step": 1210
|
| 1775 |
},
|
| 1776 |
{
|
| 1777 |
"epoch": 8.321917808219178,
|
| 1778 |
-
"grad_norm": 0.
|
| 1779 |
-
"learning_rate":
|
| 1780 |
-
"loss": 0.
|
| 1781 |
"step": 1215
|
| 1782 |
},
|
| 1783 |
{
|
| 1784 |
"epoch": 8.356164383561644,
|
| 1785 |
-
"grad_norm": 0.
|
| 1786 |
-
"learning_rate":
|
| 1787 |
-
"loss": 0.
|
| 1788 |
"step": 1220
|
| 1789 |
},
|
| 1790 |
{
|
| 1791 |
"epoch": 8.39041095890411,
|
| 1792 |
-
"grad_norm": 0.
|
| 1793 |
-
"learning_rate":
|
| 1794 |
-
"loss": 0.
|
| 1795 |
"step": 1225
|
| 1796 |
},
|
| 1797 |
{
|
| 1798 |
"epoch": 8.424657534246576,
|
| 1799 |
-
"grad_norm": 0.
|
| 1800 |
-
"learning_rate":
|
| 1801 |
-
"loss": 0.
|
| 1802 |
"step": 1230
|
| 1803 |
},
|
| 1804 |
{
|
| 1805 |
"epoch": 8.45890410958904,
|
| 1806 |
-
"grad_norm": 0.
|
| 1807 |
-
"learning_rate":
|
| 1808 |
-
"loss": 0.
|
| 1809 |
"step": 1235
|
| 1810 |
},
|
| 1811 |
{
|
| 1812 |
"epoch": 8.493150684931507,
|
| 1813 |
-
"grad_norm": 0.
|
| 1814 |
-
"learning_rate":
|
| 1815 |
-
"loss": 0.
|
| 1816 |
"step": 1240
|
| 1817 |
},
|
| 1818 |
{
|
| 1819 |
"epoch": 8.527397260273972,
|
| 1820 |
-
"grad_norm": 0.
|
| 1821 |
-
"learning_rate":
|
| 1822 |
-
"loss": 0.
|
| 1823 |
"step": 1245
|
| 1824 |
},
|
| 1825 |
{
|
| 1826 |
"epoch": 8.561643835616438,
|
| 1827 |
-
"grad_norm": 0.
|
| 1828 |
-
"learning_rate":
|
| 1829 |
-
"loss": 0.
|
| 1830 |
"step": 1250
|
| 1831 |
},
|
| 1832 |
{
|
| 1833 |
"epoch": 8.595890410958905,
|
| 1834 |
-
"grad_norm": 0.
|
| 1835 |
-
"learning_rate":
|
| 1836 |
-
"loss": 0.
|
| 1837 |
"step": 1255
|
| 1838 |
},
|
| 1839 |
{
|
| 1840 |
"epoch": 8.63013698630137,
|
| 1841 |
-
"grad_norm": 0.
|
| 1842 |
-
"learning_rate":
|
| 1843 |
-
"loss": 0.
|
| 1844 |
"step": 1260
|
| 1845 |
},
|
| 1846 |
{
|
| 1847 |
"epoch": 8.664383561643836,
|
| 1848 |
-
"grad_norm": 0.
|
| 1849 |
-
"learning_rate":
|
| 1850 |
-
"loss": 0.
|
| 1851 |
"step": 1265
|
| 1852 |
},
|
| 1853 |
{
|
| 1854 |
"epoch": 8.698630136986301,
|
| 1855 |
-
"grad_norm": 0.
|
| 1856 |
-
"learning_rate":
|
| 1857 |
-
"loss": 0.
|
| 1858 |
"step": 1270
|
| 1859 |
},
|
| 1860 |
{
|
| 1861 |
"epoch": 8.732876712328768,
|
| 1862 |
-
"grad_norm": 0.
|
| 1863 |
-
"learning_rate":
|
| 1864 |
-
"loss": 0.
|
| 1865 |
"step": 1275
|
| 1866 |
},
|
| 1867 |
{
|
| 1868 |
"epoch": 8.767123287671232,
|
| 1869 |
-
"grad_norm": 0.
|
| 1870 |
-
"learning_rate":
|
| 1871 |
-
"loss": 0.
|
| 1872 |
"step": 1280
|
| 1873 |
},
|
| 1874 |
{
|
| 1875 |
"epoch": 8.801369863013699,
|
| 1876 |
-
"grad_norm": 0.
|
| 1877 |
-
"learning_rate": 8.
|
| 1878 |
-
"loss": 0.
|
| 1879 |
"step": 1285
|
| 1880 |
},
|
| 1881 |
{
|
| 1882 |
"epoch": 8.835616438356164,
|
| 1883 |
-
"grad_norm": 0.
|
| 1884 |
-
"learning_rate": 8.
|
| 1885 |
-
"loss": 0.
|
| 1886 |
"step": 1290
|
| 1887 |
},
|
| 1888 |
{
|
| 1889 |
"epoch": 8.86986301369863,
|
| 1890 |
-
"grad_norm": 0.
|
| 1891 |
-
"learning_rate":
|
| 1892 |
-
"loss": 0.
|
| 1893 |
"step": 1295
|
| 1894 |
},
|
| 1895 |
{
|
| 1896 |
"epoch": 8.904109589041095,
|
| 1897 |
-
"grad_norm": 0.
|
| 1898 |
-
"learning_rate":
|
| 1899 |
-
"loss": 0.
|
| 1900 |
"step": 1300
|
| 1901 |
},
|
| 1902 |
{
|
| 1903 |
"epoch": 8.938356164383562,
|
| 1904 |
-
"grad_norm": 0.
|
| 1905 |
-
"learning_rate":
|
| 1906 |
-
"loss": 0.
|
| 1907 |
"step": 1305
|
| 1908 |
},
|
| 1909 |
{
|
| 1910 |
"epoch": 8.972602739726028,
|
| 1911 |
-
"grad_norm": 0.
|
| 1912 |
-
"learning_rate":
|
| 1913 |
-
"loss": 0.
|
| 1914 |
"step": 1310
|
| 1915 |
},
|
| 1916 |
{
|
| 1917 |
"epoch": 9.0,
|
| 1918 |
-
"eval_loss": 2.
|
| 1919 |
-
"eval_runtime": 0.
|
| 1920 |
-
"eval_samples_per_second": 18.
|
| 1921 |
-
"eval_steps_per_second": 1.
|
| 1922 |
"step": 1314
|
| 1923 |
},
|
| 1924 |
{
|
| 1925 |
"epoch": 9.006849315068493,
|
| 1926 |
-
"grad_norm": 0.
|
| 1927 |
-
"learning_rate":
|
| 1928 |
-
"loss": 0.
|
| 1929 |
"step": 1315
|
| 1930 |
},
|
| 1931 |
{
|
| 1932 |
"epoch": 9.04109589041096,
|
| 1933 |
-
"grad_norm": 0.
|
| 1934 |
-
"learning_rate":
|
| 1935 |
-
"loss": 0.
|
| 1936 |
"step": 1320
|
| 1937 |
},
|
| 1938 |
{
|
| 1939 |
"epoch": 9.075342465753424,
|
| 1940 |
-
"grad_norm": 0.
|
| 1941 |
-
"learning_rate":
|
| 1942 |
-
"loss": 0.
|
| 1943 |
"step": 1325
|
| 1944 |
},
|
| 1945 |
{
|
| 1946 |
"epoch": 9.10958904109589,
|
| 1947 |
-
"grad_norm": 0.
|
| 1948 |
-
"learning_rate":
|
| 1949 |
-
"loss": 0.
|
| 1950 |
"step": 1330
|
| 1951 |
},
|
| 1952 |
{
|
| 1953 |
"epoch": 9.143835616438356,
|
| 1954 |
-
"grad_norm": 0.
|
| 1955 |
-
"learning_rate":
|
| 1956 |
-
"loss": 0.
|
| 1957 |
"step": 1335
|
| 1958 |
},
|
| 1959 |
{
|
| 1960 |
"epoch": 9.178082191780822,
|
| 1961 |
-
"grad_norm": 0.
|
| 1962 |
-
"learning_rate":
|
| 1963 |
-
"loss": 0.
|
| 1964 |
"step": 1340
|
| 1965 |
},
|
| 1966 |
{
|
| 1967 |
"epoch": 9.212328767123287,
|
| 1968 |
-
"grad_norm": 0.
|
| 1969 |
-
"learning_rate":
|
| 1970 |
-
"loss": 0.
|
| 1971 |
"step": 1345
|
| 1972 |
},
|
| 1973 |
{
|
| 1974 |
"epoch": 9.246575342465754,
|
| 1975 |
-
"grad_norm": 0.
|
| 1976 |
-
"learning_rate":
|
| 1977 |
-
"loss": 0.
|
| 1978 |
"step": 1350
|
| 1979 |
},
|
| 1980 |
{
|
| 1981 |
"epoch": 9.280821917808218,
|
| 1982 |
-
"grad_norm": 0.
|
| 1983 |
-
"learning_rate":
|
| 1984 |
-
"loss": 0.
|
| 1985 |
"step": 1355
|
| 1986 |
},
|
| 1987 |
{
|
| 1988 |
"epoch": 9.315068493150685,
|
| 1989 |
-
"grad_norm": 0.
|
| 1990 |
-
"learning_rate":
|
| 1991 |
-
"loss": 0.
|
| 1992 |
"step": 1360
|
| 1993 |
},
|
| 1994 |
{
|
| 1995 |
"epoch": 9.349315068493151,
|
| 1996 |
-
"grad_norm": 0.
|
| 1997 |
-
"learning_rate":
|
| 1998 |
-
"loss": 0.
|
| 1999 |
"step": 1365
|
| 2000 |
},
|
| 2001 |
{
|
| 2002 |
"epoch": 9.383561643835616,
|
| 2003 |
-
"grad_norm": 0.
|
| 2004 |
-
"learning_rate":
|
| 2005 |
-
"loss": 0.
|
| 2006 |
"step": 1370
|
| 2007 |
},
|
| 2008 |
{
|
| 2009 |
"epoch": 9.417808219178083,
|
| 2010 |
-
"grad_norm": 0.
|
| 2011 |
-
"learning_rate":
|
| 2012 |
-
"loss": 0.
|
| 2013 |
"step": 1375
|
| 2014 |
},
|
| 2015 |
{
|
| 2016 |
"epoch": 9.452054794520548,
|
| 2017 |
-
"grad_norm": 0.
|
| 2018 |
-
"learning_rate":
|
| 2019 |
-
"loss": 0.
|
| 2020 |
"step": 1380
|
| 2021 |
},
|
| 2022 |
{
|
| 2023 |
"epoch": 9.486301369863014,
|
| 2024 |
-
"grad_norm": 0.
|
| 2025 |
-
"learning_rate":
|
| 2026 |
-
"loss": 0.
|
| 2027 |
"step": 1385
|
| 2028 |
},
|
| 2029 |
{
|
| 2030 |
"epoch": 9.520547945205479,
|
| 2031 |
-
"grad_norm": 0.
|
| 2032 |
-
"learning_rate":
|
| 2033 |
-
"loss": 0.
|
| 2034 |
"step": 1390
|
| 2035 |
},
|
| 2036 |
{
|
| 2037 |
"epoch": 9.554794520547945,
|
| 2038 |
-
"grad_norm": 0.
|
| 2039 |
-
"learning_rate":
|
| 2040 |
-
"loss": 0.
|
| 2041 |
"step": 1395
|
| 2042 |
},
|
| 2043 |
{
|
| 2044 |
"epoch": 9.58904109589041,
|
| 2045 |
-
"grad_norm": 0.
|
| 2046 |
-
"learning_rate":
|
| 2047 |
-
"loss": 0.
|
| 2048 |
"step": 1400
|
| 2049 |
},
|
| 2050 |
{
|
| 2051 |
"epoch": 9.623287671232877,
|
| 2052 |
-
"grad_norm": 0.
|
| 2053 |
-
"learning_rate":
|
| 2054 |
-
"loss": 0.
|
| 2055 |
"step": 1405
|
| 2056 |
},
|
| 2057 |
{
|
| 2058 |
"epoch": 9.657534246575342,
|
| 2059 |
-
"grad_norm": 0.
|
| 2060 |
-
"learning_rate":
|
| 2061 |
-
"loss": 0.
|
| 2062 |
"step": 1410
|
| 2063 |
},
|
| 2064 |
{
|
| 2065 |
"epoch": 9.691780821917808,
|
| 2066 |
-
"grad_norm": 0.
|
| 2067 |
-
"learning_rate":
|
| 2068 |
-
"loss": 0.
|
| 2069 |
"step": 1415
|
| 2070 |
},
|
| 2071 |
{
|
| 2072 |
"epoch": 9.726027397260275,
|
| 2073 |
-
"grad_norm": 0.
|
| 2074 |
-
"learning_rate":
|
| 2075 |
-
"loss": 0.
|
| 2076 |
"step": 1420
|
| 2077 |
},
|
| 2078 |
{
|
| 2079 |
"epoch": 9.76027397260274,
|
| 2080 |
-
"grad_norm": 0.
|
| 2081 |
-
"learning_rate":
|
| 2082 |
-
"loss": 0.
|
| 2083 |
"step": 1425
|
| 2084 |
},
|
| 2085 |
{
|
| 2086 |
"epoch": 9.794520547945206,
|
| 2087 |
-
"grad_norm": 0.
|
| 2088 |
-
"learning_rate":
|
| 2089 |
-
"loss": 0.
|
| 2090 |
"step": 1430
|
| 2091 |
},
|
| 2092 |
{
|
| 2093 |
"epoch": 9.82876712328767,
|
| 2094 |
-
"grad_norm": 0.
|
| 2095 |
-
"learning_rate":
|
| 2096 |
-
"loss": 0.
|
| 2097 |
"step": 1435
|
| 2098 |
},
|
| 2099 |
{
|
| 2100 |
"epoch": 9.863013698630137,
|
| 2101 |
-
"grad_norm": 0.
|
| 2102 |
-
"learning_rate":
|
| 2103 |
-
"loss": 0.
|
| 2104 |
"step": 1440
|
| 2105 |
},
|
| 2106 |
{
|
| 2107 |
"epoch": 9.897260273972602,
|
| 2108 |
-
"grad_norm": 0.
|
| 2109 |
-
"learning_rate": 6.
|
| 2110 |
-
"loss": 0.
|
| 2111 |
"step": 1445
|
| 2112 |
},
|
| 2113 |
{
|
| 2114 |
"epoch": 9.931506849315069,
|
| 2115 |
-
"grad_norm": 0.
|
| 2116 |
-
"learning_rate":
|
| 2117 |
-
"loss": 0.
|
| 2118 |
"step": 1450
|
| 2119 |
},
|
| 2120 |
{
|
| 2121 |
"epoch": 9.965753424657533,
|
| 2122 |
-
"grad_norm": 0.
|
| 2123 |
-
"learning_rate":
|
| 2124 |
-
"loss": 0.
|
| 2125 |
"step": 1455
|
| 2126 |
},
|
| 2127 |
{
|
| 2128 |
"epoch": 10.0,
|
| 2129 |
-
"grad_norm": 0.
|
| 2130 |
-
"learning_rate":
|
| 2131 |
-
"loss": 0.
|
| 2132 |
"step": 1460
|
| 2133 |
},
|
| 2134 |
{
|
| 2135 |
"epoch": 10.0,
|
| 2136 |
-
"eval_loss": 2.
|
| 2137 |
-
"eval_runtime": 0.
|
| 2138 |
-
"eval_samples_per_second": 18.
|
| 2139 |
-
"eval_steps_per_second": 1.
|
| 2140 |
"step": 1460
|
| 2141 |
},
|
| 2142 |
{
|
| 2143 |
-
"epoch": 10.
|
| 2144 |
-
"
|
| 2145 |
-
"
|
| 2146 |
-
"
|
| 2147 |
-
"
|
| 2148 |
-
|
| 2149 |
-
|
| 2150 |
-
"epoch": 10.068493150684931,
|
| 2151 |
-
"grad_norm": 0.431640625,
|
| 2152 |
-
"learning_rate": 5.8933564555049105e-05,
|
| 2153 |
-
"loss": 0.8677,
|
| 2154 |
-
"step": 1470
|
| 2155 |
-
},
|
| 2156 |
-
{
|
| 2157 |
-
"epoch": 10.102739726027398,
|
| 2158 |
-
"grad_norm": 0.41796875,
|
| 2159 |
-
"learning_rate": 5.820822441035899e-05,
|
| 2160 |
-
"loss": 0.866,
|
| 2161 |
-
"step": 1475
|
| 2162 |
-
},
|
| 2163 |
-
{
|
| 2164 |
-
"epoch": 10.136986301369863,
|
| 2165 |
-
"grad_norm": 0.40625,
|
| 2166 |
-
"learning_rate": 5.7485538596368496e-05,
|
| 2167 |
-
"loss": 0.8664,
|
| 2168 |
-
"step": 1480
|
| 2169 |
-
},
|
| 2170 |
-
{
|
| 2171 |
-
"epoch": 10.17123287671233,
|
| 2172 |
-
"grad_norm": 0.41015625,
|
| 2173 |
-
"learning_rate": 5.6765553013188766e-05,
|
| 2174 |
-
"loss": 0.8645,
|
| 2175 |
-
"step": 1485
|
| 2176 |
-
},
|
| 2177 |
-
{
|
| 2178 |
-
"epoch": 10.205479452054794,
|
| 2179 |
-
"grad_norm": 0.400390625,
|
| 2180 |
-
"learning_rate": 5.6048313389430484e-05,
|
| 2181 |
-
"loss": 0.8624,
|
| 2182 |
-
"step": 1490
|
| 2183 |
-
},
|
| 2184 |
-
{
|
| 2185 |
-
"epoch": 10.23972602739726,
|
| 2186 |
-
"grad_norm": 0.408203125,
|
| 2187 |
-
"learning_rate": 5.533386527929962e-05,
|
| 2188 |
-
"loss": 0.874,
|
| 2189 |
-
"step": 1495
|
| 2190 |
-
},
|
| 2191 |
-
{
|
| 2192 |
-
"epoch": 10.273972602739725,
|
| 2193 |
-
"grad_norm": 0.40625,
|
| 2194 |
-
"learning_rate": 5.462225405970401e-05,
|
| 2195 |
-
"loss": 0.8708,
|
| 2196 |
-
"step": 1500
|
| 2197 |
-
},
|
| 2198 |
-
{
|
| 2199 |
-
"epoch": 10.273972602739725,
|
| 2200 |
-
"step": 1500,
|
| 2201 |
-
"total_flos": 8.853977907740017e+17,
|
| 2202 |
-
"train_loss": 0.0,
|
| 2203 |
-
"train_runtime": 3.0171,
|
| 2204 |
-
"train_samples_per_second": 23207.393,
|
| 2205 |
-
"train_steps_per_second": 483.902
|
| 2206 |
}
|
| 2207 |
],
|
| 2208 |
"logging_steps": 5,
|
|
@@ -2222,7 +2166,7 @@
|
|
| 2222 |
"attributes": {}
|
| 2223 |
}
|
| 2224 |
},
|
| 2225 |
-
"total_flos": 8.
|
| 2226 |
"train_batch_size": 8,
|
| 2227 |
"trial_name": null,
|
| 2228 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 10.0,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 1460,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 0.00684931506849315,
|
| 13 |
+
"grad_norm": 4.9375,
|
| 14 |
+
"learning_rate": 1.3698630136986302e-06,
|
| 15 |
"loss": 3.0017,
|
| 16 |
"step": 1
|
| 17 |
},
|
| 18 |
{
|
| 19 |
"epoch": 0.03424657534246575,
|
| 20 |
+
"grad_norm": 4.5625,
|
| 21 |
+
"learning_rate": 6.849315068493151e-06,
|
| 22 |
+
"loss": 3.0717,
|
| 23 |
"step": 5
|
| 24 |
},
|
| 25 |
{
|
| 26 |
"epoch": 0.0684931506849315,
|
| 27 |
+
"grad_norm": 5.40625,
|
| 28 |
+
"learning_rate": 1.3698630136986302e-05,
|
| 29 |
+
"loss": 3.002,
|
| 30 |
"step": 10
|
| 31 |
},
|
| 32 |
{
|
| 33 |
"epoch": 0.10273972602739725,
|
| 34 |
+
"grad_norm": 2.640625,
|
| 35 |
+
"learning_rate": 2.0547945205479453e-05,
|
| 36 |
+
"loss": 2.8518,
|
| 37 |
"step": 15
|
| 38 |
},
|
| 39 |
{
|
| 40 |
"epoch": 0.136986301369863,
|
| 41 |
+
"grad_norm": 1.734375,
|
| 42 |
+
"learning_rate": 2.7397260273972603e-05,
|
| 43 |
+
"loss": 2.6474,
|
| 44 |
"step": 20
|
| 45 |
},
|
| 46 |
{
|
| 47 |
"epoch": 0.17123287671232876,
|
| 48 |
+
"grad_norm": 1.59375,
|
| 49 |
+
"learning_rate": 3.424657534246575e-05,
|
| 50 |
+
"loss": 2.4285,
|
| 51 |
"step": 25
|
| 52 |
},
|
| 53 |
{
|
| 54 |
"epoch": 0.2054794520547945,
|
| 55 |
+
"grad_norm": 75.0,
|
| 56 |
+
"learning_rate": 4.1095890410958905e-05,
|
| 57 |
+
"loss": 2.2533,
|
| 58 |
"step": 30
|
| 59 |
},
|
| 60 |
{
|
| 61 |
"epoch": 0.23972602739726026,
|
| 62 |
+
"grad_norm": 1.84375,
|
| 63 |
+
"learning_rate": 4.794520547945205e-05,
|
| 64 |
+
"loss": 2.0584,
|
| 65 |
"step": 35
|
| 66 |
},
|
| 67 |
{
|
| 68 |
"epoch": 0.273972602739726,
|
| 69 |
+
"grad_norm": 0.80859375,
|
| 70 |
+
"learning_rate": 5.479452054794521e-05,
|
| 71 |
+
"loss": 1.9038,
|
| 72 |
"step": 40
|
| 73 |
},
|
| 74 |
{
|
| 75 |
"epoch": 0.3082191780821918,
|
| 76 |
+
"grad_norm": 0.65625,
|
| 77 |
+
"learning_rate": 6.164383561643835e-05,
|
| 78 |
+
"loss": 1.797,
|
| 79 |
"step": 45
|
| 80 |
},
|
| 81 |
{
|
| 82 |
"epoch": 0.3424657534246575,
|
| 83 |
+
"grad_norm": 0.5859375,
|
| 84 |
+
"learning_rate": 6.84931506849315e-05,
|
| 85 |
+
"loss": 1.6455,
|
| 86 |
"step": 50
|
| 87 |
},
|
| 88 |
{
|
| 89 |
"epoch": 0.3767123287671233,
|
| 90 |
+
"grad_norm": 0.40625,
|
| 91 |
+
"learning_rate": 7.534246575342466e-05,
|
| 92 |
+
"loss": 1.5458,
|
| 93 |
"step": 55
|
| 94 |
},
|
| 95 |
{
|
| 96 |
"epoch": 0.410958904109589,
|
| 97 |
+
"grad_norm": 0.345703125,
|
| 98 |
+
"learning_rate": 8.219178082191781e-05,
|
| 99 |
+
"loss": 1.4771,
|
| 100 |
"step": 60
|
| 101 |
},
|
| 102 |
{
|
| 103 |
"epoch": 0.4452054794520548,
|
| 104 |
+
"grad_norm": 0.38671875,
|
| 105 |
+
"learning_rate": 8.904109589041096e-05,
|
| 106 |
+
"loss": 1.4206,
|
| 107 |
"step": 65
|
| 108 |
},
|
| 109 |
{
|
| 110 |
"epoch": 0.4794520547945205,
|
| 111 |
+
"grad_norm": 0.546875,
|
| 112 |
+
"learning_rate": 9.58904109589041e-05,
|
| 113 |
+
"loss": 1.3804,
|
| 114 |
"step": 70
|
| 115 |
},
|
| 116 |
{
|
| 117 |
"epoch": 0.5136986301369864,
|
| 118 |
+
"grad_norm": 0.353515625,
|
| 119 |
+
"learning_rate": 0.00010273972602739728,
|
| 120 |
+
"loss": 1.3471,
|
| 121 |
"step": 75
|
| 122 |
},
|
| 123 |
{
|
| 124 |
"epoch": 0.547945205479452,
|
| 125 |
+
"grad_norm": 0.259765625,
|
| 126 |
+
"learning_rate": 0.00010958904109589041,
|
| 127 |
+
"loss": 1.3165,
|
| 128 |
"step": 80
|
| 129 |
},
|
| 130 |
{
|
| 131 |
"epoch": 0.5821917808219178,
|
| 132 |
+
"grad_norm": 0.53515625,
|
| 133 |
+
"learning_rate": 0.00011643835616438356,
|
| 134 |
+
"loss": 1.2853,
|
| 135 |
"step": 85
|
| 136 |
},
|
| 137 |
{
|
| 138 |
"epoch": 0.6164383561643836,
|
| 139 |
+
"grad_norm": 0.3828125,
|
| 140 |
+
"learning_rate": 0.0001232876712328767,
|
| 141 |
+
"loss": 1.2863,
|
| 142 |
"step": 90
|
| 143 |
},
|
| 144 |
{
|
| 145 |
"epoch": 0.6506849315068494,
|
| 146 |
+
"grad_norm": 0.8828125,
|
| 147 |
+
"learning_rate": 0.00013013698630136988,
|
| 148 |
+
"loss": 1.267,
|
| 149 |
"step": 95
|
| 150 |
},
|
| 151 |
{
|
| 152 |
"epoch": 0.684931506849315,
|
| 153 |
+
"grad_norm": 0.74609375,
|
| 154 |
+
"learning_rate": 0.000136986301369863,
|
| 155 |
+
"loss": 1.2466,
|
| 156 |
"step": 100
|
| 157 |
},
|
| 158 |
{
|
| 159 |
"epoch": 0.7191780821917808,
|
| 160 |
+
"grad_norm": 1.0,
|
| 161 |
+
"learning_rate": 0.00014383561643835618,
|
| 162 |
+
"loss": 1.2444,
|
| 163 |
"step": 105
|
| 164 |
},
|
| 165 |
{
|
| 166 |
"epoch": 0.7534246575342466,
|
| 167 |
+
"grad_norm": 0.3671875,
|
| 168 |
+
"learning_rate": 0.00015068493150684933,
|
| 169 |
+
"loss": 1.2283,
|
| 170 |
"step": 110
|
| 171 |
},
|
| 172 |
{
|
| 173 |
"epoch": 0.7876712328767124,
|
| 174 |
+
"grad_norm": 0.3125,
|
| 175 |
+
"learning_rate": 0.00015753424657534247,
|
| 176 |
+
"loss": 1.2153,
|
| 177 |
"step": 115
|
| 178 |
},
|
| 179 |
{
|
| 180 |
"epoch": 0.821917808219178,
|
| 181 |
+
"grad_norm": 0.3984375,
|
| 182 |
+
"learning_rate": 0.00016438356164383562,
|
| 183 |
+
"loss": 1.2106,
|
| 184 |
"step": 120
|
| 185 |
},
|
| 186 |
{
|
| 187 |
"epoch": 0.8561643835616438,
|
| 188 |
+
"grad_norm": 0.330078125,
|
| 189 |
+
"learning_rate": 0.00017123287671232877,
|
| 190 |
+
"loss": 1.1939,
|
| 191 |
"step": 125
|
| 192 |
},
|
| 193 |
{
|
| 194 |
"epoch": 0.8904109589041096,
|
| 195 |
+
"grad_norm": 0.57421875,
|
| 196 |
+
"learning_rate": 0.00017808219178082192,
|
| 197 |
+
"loss": 1.1965,
|
| 198 |
"step": 130
|
| 199 |
},
|
| 200 |
{
|
| 201 |
"epoch": 0.9246575342465754,
|
| 202 |
+
"grad_norm": 0.515625,
|
| 203 |
+
"learning_rate": 0.0001849315068493151,
|
| 204 |
+
"loss": 1.1839,
|
| 205 |
"step": 135
|
| 206 |
},
|
| 207 |
{
|
| 208 |
"epoch": 0.958904109589041,
|
| 209 |
+
"grad_norm": 1.4453125,
|
| 210 |
+
"learning_rate": 0.0001917808219178082,
|
| 211 |
+
"loss": 1.1983,
|
| 212 |
"step": 140
|
| 213 |
},
|
| 214 |
{
|
| 215 |
"epoch": 0.9931506849315068,
|
| 216 |
+
"grad_norm": 0.470703125,
|
| 217 |
+
"learning_rate": 0.00019863013698630139,
|
| 218 |
+
"loss": 1.1808,
|
| 219 |
"step": 145
|
| 220 |
},
|
| 221 |
{
|
| 222 |
"epoch": 1.0,
|
| 223 |
+
"eval_loss": 2.487597942352295,
|
| 224 |
+
"eval_runtime": 0.541,
|
| 225 |
+
"eval_samples_per_second": 18.483,
|
| 226 |
+
"eval_steps_per_second": 1.848,
|
| 227 |
"step": 146
|
| 228 |
},
|
| 229 |
{
|
| 230 |
"epoch": 1.0273972602739727,
|
| 231 |
+
"grad_norm": 0.396484375,
|
| 232 |
+
"learning_rate": 0.00019999542705801296,
|
| 233 |
+
"loss": 1.1618,
|
| 234 |
"step": 150
|
| 235 |
},
|
| 236 |
{
|
| 237 |
"epoch": 1.0616438356164384,
|
| 238 |
+
"grad_norm": 0.8125,
|
| 239 |
+
"learning_rate": 0.00019997685019798912,
|
| 240 |
+
"loss": 1.1531,
|
| 241 |
"step": 155
|
| 242 |
},
|
| 243 |
{
|
| 244 |
"epoch": 1.095890410958904,
|
| 245 |
+
"grad_norm": 0.390625,
|
| 246 |
+
"learning_rate": 0.00019994398626371643,
|
| 247 |
+
"loss": 1.1517,
|
| 248 |
"step": 160
|
| 249 |
},
|
| 250 |
{
|
| 251 |
"epoch": 1.13013698630137,
|
| 252 |
+
"grad_norm": 0.333984375,
|
| 253 |
+
"learning_rate": 0.00019989683995157677,
|
| 254 |
+
"loss": 1.1322,
|
| 255 |
"step": 165
|
| 256 |
},
|
| 257 |
{
|
| 258 |
"epoch": 1.1643835616438356,
|
| 259 |
+
"grad_norm": 0.318359375,
|
| 260 |
+
"learning_rate": 0.0001998354179989585,
|
| 261 |
+
"loss": 1.1413,
|
| 262 |
"step": 170
|
| 263 |
},
|
| 264 |
{
|
| 265 |
"epoch": 1.1986301369863013,
|
| 266 |
+
"grad_norm": 0.37109375,
|
| 267 |
+
"learning_rate": 0.00019975972918329356,
|
| 268 |
+
"loss": 1.1275,
|
| 269 |
"step": 175
|
| 270 |
},
|
| 271 |
{
|
| 272 |
"epoch": 1.2328767123287672,
|
| 273 |
+
"grad_norm": 0.54296875,
|
| 274 |
+
"learning_rate": 0.00019966978432080316,
|
| 275 |
+
"loss": 1.1261,
|
| 276 |
"step": 180
|
| 277 |
},
|
| 278 |
{
|
| 279 |
"epoch": 1.2671232876712328,
|
| 280 |
+
"grad_norm": 0.43359375,
|
| 281 |
+
"learning_rate": 0.00019956559626495212,
|
| 282 |
+
"loss": 1.1384,
|
| 283 |
"step": 185
|
| 284 |
},
|
| 285 |
{
|
| 286 |
"epoch": 1.3013698630136985,
|
| 287 |
+
"grad_norm": 2.4375,
|
| 288 |
+
"learning_rate": 0.00019944717990461207,
|
| 289 |
+
"loss": 1.1376,
|
| 290 |
"step": 190
|
| 291 |
},
|
| 292 |
{
|
| 293 |
"epoch": 1.3356164383561644,
|
| 294 |
+
"grad_norm": 0.423828125,
|
| 295 |
+
"learning_rate": 0.00019931455216193382,
|
| 296 |
+
"loss": 1.1376,
|
| 297 |
"step": 195
|
| 298 |
},
|
| 299 |
{
|
| 300 |
"epoch": 1.36986301369863,
|
| 301 |
+
"grad_norm": 0.55078125,
|
| 302 |
+
"learning_rate": 0.000199167731989929,
|
| 303 |
+
"loss": 1.14,
|
| 304 |
"step": 200
|
| 305 |
},
|
| 306 |
{
|
| 307 |
"epoch": 1.404109589041096,
|
| 308 |
+
"grad_norm": 0.44140625,
|
| 309 |
+
"learning_rate": 0.00019900674036976173,
|
| 310 |
+
"loss": 1.1281,
|
| 311 |
"step": 205
|
| 312 |
},
|
| 313 |
{
|
| 314 |
"epoch": 1.4383561643835616,
|
| 315 |
+
"grad_norm": 0.63671875,
|
| 316 |
+
"learning_rate": 0.00019883160030775016,
|
| 317 |
+
"loss": 1.1221,
|
| 318 |
"step": 210
|
| 319 |
},
|
| 320 |
{
|
| 321 |
"epoch": 1.4726027397260273,
|
| 322 |
+
"grad_norm": 0.36328125,
|
| 323 |
+
"learning_rate": 0.00019864233683207906,
|
| 324 |
+
"loss": 1.1217,
|
| 325 |
"step": 215
|
| 326 |
},
|
| 327 |
{
|
| 328 |
"epoch": 1.5068493150684932,
|
| 329 |
+
"grad_norm": 0.412109375,
|
| 330 |
+
"learning_rate": 0.00019843897698922284,
|
| 331 |
+
"loss": 1.1086,
|
| 332 |
"step": 220
|
| 333 |
},
|
| 334 |
{
|
| 335 |
"epoch": 1.541095890410959,
|
| 336 |
+
"grad_norm": 0.357421875,
|
| 337 |
+
"learning_rate": 0.00019822154984008088,
|
| 338 |
+
"loss": 1.1132,
|
| 339 |
"step": 225
|
| 340 |
},
|
| 341 |
{
|
| 342 |
"epoch": 1.5753424657534247,
|
| 343 |
+
"grad_norm": 0.314453125,
|
| 344 |
+
"learning_rate": 0.0001979900864558242,
|
| 345 |
+
"loss": 1.1094,
|
| 346 |
"step": 230
|
| 347 |
},
|
| 348 |
{
|
| 349 |
"epoch": 1.6095890410958904,
|
| 350 |
+
"grad_norm": 0.48046875,
|
| 351 |
+
"learning_rate": 0.00019774461991345577,
|
| 352 |
+
"loss": 1.1048,
|
| 353 |
"step": 235
|
| 354 |
},
|
| 355 |
{
|
| 356 |
"epoch": 1.643835616438356,
|
| 357 |
+
"grad_norm": 0.32421875,
|
| 358 |
+
"learning_rate": 0.00019748518529108316,
|
| 359 |
+
"loss": 1.0937,
|
| 360 |
"step": 240
|
| 361 |
},
|
| 362 |
{
|
| 363 |
"epoch": 1.678082191780822,
|
| 364 |
+
"grad_norm": 0.431640625,
|
| 365 |
+
"learning_rate": 0.00019721181966290613,
|
| 366 |
+
"loss": 1.1099,
|
| 367 |
"step": 245
|
| 368 |
},
|
| 369 |
{
|
| 370 |
"epoch": 1.7123287671232876,
|
| 371 |
+
"grad_norm": 0.35546875,
|
| 372 |
+
"learning_rate": 0.00019692456209391846,
|
| 373 |
+
"loss": 1.0998,
|
| 374 |
"step": 250
|
| 375 |
},
|
| 376 |
{
|
| 377 |
"epoch": 1.7465753424657535,
|
| 378 |
+
"grad_norm": 0.33984375,
|
| 379 |
+
"learning_rate": 0.0001966234536343253,
|
| 380 |
+
"loss": 1.0985,
|
| 381 |
"step": 255
|
| 382 |
},
|
| 383 |
{
|
| 384 |
"epoch": 1.7808219178082192,
|
| 385 |
+
"grad_norm": 0.455078125,
|
| 386 |
+
"learning_rate": 0.00019630853731367713,
|
| 387 |
+
"loss": 1.1036,
|
| 388 |
"step": 260
|
| 389 |
},
|
| 390 |
{
|
| 391 |
"epoch": 1.8150684931506849,
|
| 392 |
+
"grad_norm": 0.52734375,
|
| 393 |
+
"learning_rate": 0.00019597985813472052,
|
| 394 |
+
"loss": 1.0853,
|
| 395 |
"step": 265
|
| 396 |
},
|
| 397 |
{
|
| 398 |
"epoch": 1.8493150684931505,
|
| 399 |
+
"grad_norm": 0.30078125,
|
| 400 |
+
"learning_rate": 0.0001956374630669672,
|
| 401 |
+
"loss": 1.0958,
|
| 402 |
"step": 270
|
| 403 |
},
|
| 404 |
{
|
| 405 |
"epoch": 1.8835616438356164,
|
| 406 |
+
"grad_norm": 0.62890625,
|
| 407 |
+
"learning_rate": 0.00019528140103998177,
|
| 408 |
+
"loss": 1.0911,
|
| 409 |
"step": 275
|
| 410 |
},
|
| 411 |
{
|
| 412 |
"epoch": 1.9178082191780823,
|
| 413 |
+
"grad_norm": 0.5234375,
|
| 414 |
+
"learning_rate": 0.00019491172293638968,
|
| 415 |
+
"loss": 1.0812,
|
| 416 |
"step": 280
|
| 417 |
},
|
| 418 |
{
|
| 419 |
"epoch": 1.952054794520548,
|
| 420 |
+
"grad_norm": 0.44921875,
|
| 421 |
+
"learning_rate": 0.0001945284815846057,
|
| 422 |
+
"loss": 1.0777,
|
| 423 |
"step": 285
|
| 424 |
},
|
| 425 |
{
|
| 426 |
"epoch": 1.9863013698630136,
|
| 427 |
+
"grad_norm": 0.53515625,
|
| 428 |
+
"learning_rate": 0.00019413173175128473,
|
| 429 |
+
"loss": 1.0819,
|
| 430 |
"step": 290
|
| 431 |
},
|
| 432 |
{
|
| 433 |
"epoch": 2.0,
|
| 434 |
+
"eval_loss": 2.4820380210876465,
|
| 435 |
+
"eval_runtime": 0.5459,
|
| 436 |
+
"eval_samples_per_second": 18.32,
|
| 437 |
+
"eval_steps_per_second": 1.832,
|
| 438 |
"step": 292
|
| 439 |
},
|
| 440 |
{
|
| 441 |
"epoch": 2.0205479452054793,
|
| 442 |
+
"grad_norm": 0.412109375,
|
| 443 |
+
"learning_rate": 0.00019372153013349523,
|
| 444 |
+
"loss": 1.0712,
|
| 445 |
"step": 295
|
| 446 |
},
|
| 447 |
{
|
| 448 |
"epoch": 2.0547945205479454,
|
| 449 |
+
"grad_norm": 0.302734375,
|
| 450 |
+
"learning_rate": 0.00019329793535061723,
|
| 451 |
+
"loss": 1.0467,
|
| 452 |
"step": 300
|
| 453 |
},
|
| 454 |
{
|
| 455 |
"epoch": 2.089041095890411,
|
| 456 |
+
"grad_norm": 0.34765625,
|
| 457 |
+
"learning_rate": 0.0001928610079359652,
|
| 458 |
+
"loss": 1.0444,
|
| 459 |
"step": 305
|
| 460 |
},
|
| 461 |
{
|
| 462 |
"epoch": 2.1232876712328768,
|
| 463 |
+
"grad_norm": 0.376953125,
|
| 464 |
+
"learning_rate": 0.00019241081032813772,
|
| 465 |
+
"loss": 1.0393,
|
| 466 |
"step": 310
|
| 467 |
},
|
| 468 |
{
|
| 469 |
"epoch": 2.1575342465753424,
|
| 470 |
+
"grad_norm": 0.33984375,
|
| 471 |
+
"learning_rate": 0.00019194740686209464,
|
| 472 |
+
"loss": 1.0475,
|
| 473 |
"step": 315
|
| 474 |
},
|
| 475 |
{
|
| 476 |
"epoch": 2.191780821917808,
|
| 477 |
+
"grad_norm": 1.2578125,
|
| 478 |
+
"learning_rate": 0.0001914708637599636,
|
| 479 |
+
"loss": 1.0427,
|
| 480 |
"step": 320
|
| 481 |
},
|
| 482 |
{
|
| 483 |
"epoch": 2.2260273972602738,
|
| 484 |
+
"grad_norm": 1.5546875,
|
| 485 |
+
"learning_rate": 0.00019098124912157632,
|
| 486 |
+
"loss": 1.0486,
|
| 487 |
"step": 325
|
| 488 |
},
|
| 489 |
{
|
| 490 |
"epoch": 2.26027397260274,
|
| 491 |
+
"grad_norm": 0.458984375,
|
| 492 |
+
"learning_rate": 0.00019047863291473717,
|
| 493 |
+
"loss": 1.0412,
|
| 494 |
"step": 330
|
| 495 |
},
|
| 496 |
{
|
| 497 |
"epoch": 2.2945205479452055,
|
| 498 |
+
"grad_norm": 0.62109375,
|
| 499 |
+
"learning_rate": 0.00018996308696522433,
|
| 500 |
+
"loss": 1.0414,
|
| 501 |
"step": 335
|
| 502 |
},
|
| 503 |
{
|
| 504 |
"epoch": 2.328767123287671,
|
| 505 |
+
"grad_norm": 0.2890625,
|
| 506 |
+
"learning_rate": 0.0001894346849465257,
|
| 507 |
+
"loss": 1.033,
|
| 508 |
"step": 340
|
| 509 |
},
|
| 510 |
{
|
| 511 |
"epoch": 2.363013698630137,
|
| 512 |
+
"grad_norm": 0.328125,
|
| 513 |
+
"learning_rate": 0.00018889350236931055,
|
| 514 |
+
"loss": 1.0325,
|
| 515 |
"step": 345
|
| 516 |
},
|
| 517 |
{
|
| 518 |
"epoch": 2.3972602739726026,
|
| 519 |
+
"grad_norm": 0.333984375,
|
| 520 |
+
"learning_rate": 0.00018833961657063885,
|
| 521 |
+
"loss": 1.0499,
|
| 522 |
"step": 350
|
| 523 |
},
|
| 524 |
{
|
| 525 |
"epoch": 2.4315068493150687,
|
| 526 |
+
"grad_norm": 0.578125,
|
| 527 |
+
"learning_rate": 0.0001877731067029096,
|
| 528 |
+
"loss": 1.0361,
|
| 529 |
"step": 355
|
| 530 |
},
|
| 531 |
{
|
| 532 |
"epoch": 2.4657534246575343,
|
| 533 |
+
"grad_norm": 0.4921875,
|
| 534 |
+
"learning_rate": 0.00018719405372254948,
|
| 535 |
+
"loss": 1.0412,
|
| 536 |
"step": 360
|
| 537 |
},
|
| 538 |
{
|
| 539 |
"epoch": 2.5,
|
| 540 |
+
"grad_norm": 0.298828125,
|
| 541 |
+
"learning_rate": 0.00018660254037844388,
|
| 542 |
+
"loss": 1.0435,
|
| 543 |
"step": 365
|
| 544 |
},
|
| 545 |
{
|
| 546 |
"epoch": 2.5342465753424657,
|
| 547 |
+
"grad_norm": 0.4296875,
|
| 548 |
+
"learning_rate": 0.00018599865120011192,
|
| 549 |
+
"loss": 1.0369,
|
| 550 |
"step": 370
|
| 551 |
},
|
| 552 |
{
|
| 553 |
"epoch": 2.5684931506849313,
|
| 554 |
+
"grad_norm": 0.31640625,
|
| 555 |
+
"learning_rate": 0.00018538247248562674,
|
| 556 |
+
"loss": 1.0298,
|
| 557 |
"step": 375
|
| 558 |
},
|
| 559 |
{
|
| 560 |
"epoch": 2.602739726027397,
|
| 561 |
+
"grad_norm": 0.3125,
|
| 562 |
+
"learning_rate": 0.00018475409228928312,
|
| 563 |
+
"loss": 1.0325,
|
| 564 |
"step": 380
|
| 565 |
},
|
| 566 |
{
|
| 567 |
"epoch": 2.636986301369863,
|
| 568 |
+
"grad_norm": 0.41015625,
|
| 569 |
+
"learning_rate": 0.0001841136004090144,
|
| 570 |
+
"loss": 1.0411,
|
| 571 |
"step": 385
|
| 572 |
},
|
| 573 |
{
|
| 574 |
"epoch": 2.671232876712329,
|
| 575 |
+
"grad_norm": 0.310546875,
|
| 576 |
+
"learning_rate": 0.00018346108837355972,
|
| 577 |
+
"loss": 1.0372,
|
| 578 |
"step": 390
|
| 579 |
},
|
| 580 |
{
|
| 581 |
"epoch": 2.7054794520547945,
|
| 582 |
+
"grad_norm": 0.384765625,
|
| 583 |
+
"learning_rate": 0.00018279664942938447,
|
| 584 |
+
"loss": 1.0364,
|
| 585 |
"step": 395
|
| 586 |
},
|
| 587 |
{
|
| 588 |
"epoch": 2.73972602739726,
|
| 589 |
+
"grad_norm": 0.279296875,
|
| 590 |
+
"learning_rate": 0.00018212037852735486,
|
| 591 |
+
"loss": 1.0237,
|
| 592 |
"step": 400
|
| 593 |
},
|
| 594 |
{
|
| 595 |
"epoch": 2.7739726027397262,
|
| 596 |
+
"grad_norm": 0.375,
|
| 597 |
+
"learning_rate": 0.0001814323723091692,
|
| 598 |
+
"loss": 1.0341,
|
| 599 |
"step": 405
|
| 600 |
},
|
| 601 |
{
|
| 602 |
"epoch": 2.808219178082192,
|
| 603 |
+
"grad_norm": 0.486328125,
|
| 604 |
+
"learning_rate": 0.00018073272909354727,
|
| 605 |
+
"loss": 1.0256,
|
| 606 |
"step": 410
|
| 607 |
},
|
| 608 |
{
|
| 609 |
"epoch": 2.8424657534246576,
|
| 610 |
+
"grad_norm": 0.287109375,
|
| 611 |
+
"learning_rate": 0.00018002154886218033,
|
| 612 |
+
"loss": 1.0347,
|
| 613 |
"step": 415
|
| 614 |
},
|
| 615 |
{
|
| 616 |
"epoch": 2.8767123287671232,
|
| 617 |
+
"grad_norm": 0.427734375,
|
| 618 |
+
"learning_rate": 0.00017929893324544332,
|
| 619 |
+
"loss": 1.0357,
|
| 620 |
"step": 420
|
| 621 |
},
|
| 622 |
{
|
| 623 |
"epoch": 2.910958904109589,
|
| 624 |
+
"grad_norm": 0.408203125,
|
| 625 |
+
"learning_rate": 0.00017856498550787144,
|
| 626 |
+
"loss": 1.029,
|
| 627 |
"step": 425
|
| 628 |
},
|
| 629 |
{
|
| 630 |
"epoch": 2.9452054794520546,
|
| 631 |
+
"grad_norm": 0.375,
|
| 632 |
+
"learning_rate": 0.00017781981053340337,
|
| 633 |
+
"loss": 1.0263,
|
| 634 |
"step": 430
|
| 635 |
},
|
| 636 |
{
|
| 637 |
"epoch": 2.9794520547945207,
|
| 638 |
+
"grad_norm": 0.474609375,
|
| 639 |
+
"learning_rate": 0.00017706351481039284,
|
| 640 |
+
"loss": 1.035,
|
| 641 |
"step": 435
|
| 642 |
},
|
| 643 |
{
|
| 644 |
"epoch": 3.0,
|
| 645 |
+
"eval_loss": 2.4995357990264893,
|
| 646 |
+
"eval_runtime": 0.5513,
|
| 647 |
+
"eval_samples_per_second": 18.139,
|
| 648 |
+
"eval_steps_per_second": 1.814,
|
| 649 |
"step": 438
|
| 650 |
},
|
| 651 |
{
|
| 652 |
"epoch": 3.0136986301369864,
|
| 653 |
+
"grad_norm": 0.302734375,
|
| 654 |
+
"learning_rate": 0.00017629620641639103,
|
| 655 |
+
"loss": 1.006,
|
| 656 |
"step": 440
|
| 657 |
},
|
| 658 |
{
|
| 659 |
"epoch": 3.047945205479452,
|
| 660 |
+
"grad_norm": 0.349609375,
|
| 661 |
+
"learning_rate": 0.00017551799500270198,
|
| 662 |
+
"loss": 0.9868,
|
| 663 |
"step": 445
|
| 664 |
},
|
| 665 |
{
|
| 666 |
"epoch": 3.0821917808219177,
|
| 667 |
+
"grad_norm": 0.37109375,
|
| 668 |
+
"learning_rate": 0.00017472899177871297,
|
| 669 |
+
"loss": 0.9878,
|
| 670 |
"step": 450
|
| 671 |
},
|
| 672 |
{
|
| 673 |
"epoch": 3.1164383561643834,
|
| 674 |
+
"grad_norm": 0.35546875,
|
| 675 |
+
"learning_rate": 0.00017392930949600217,
|
| 676 |
+
"loss": 0.9897,
|
| 677 |
"step": 455
|
| 678 |
},
|
| 679 |
{
|
| 680 |
"epoch": 3.1506849315068495,
|
| 681 |
+
"grad_norm": 0.50390625,
|
| 682 |
+
"learning_rate": 0.00017311906243222614,
|
| 683 |
+
"loss": 0.9801,
|
| 684 |
"step": 460
|
| 685 |
},
|
| 686 |
{
|
| 687 |
"epoch": 3.184931506849315,
|
| 688 |
+
"grad_norm": 0.322265625,
|
| 689 |
+
"learning_rate": 0.00017229836637478902,
|
| 690 |
+
"loss": 0.9837,
|
| 691 |
"step": 465
|
| 692 |
},
|
| 693 |
{
|
| 694 |
"epoch": 3.219178082191781,
|
| 695 |
+
"grad_norm": 0.38671875,
|
| 696 |
+
"learning_rate": 0.00017146733860429612,
|
| 697 |
+
"loss": 0.9774,
|
| 698 |
"step": 470
|
| 699 |
},
|
| 700 |
{
|
| 701 |
"epoch": 3.2534246575342465,
|
| 702 |
+
"grad_norm": 0.59765625,
|
| 703 |
+
"learning_rate": 0.00017062609787779403,
|
| 704 |
+
"loss": 0.9918,
|
| 705 |
"step": 475
|
| 706 |
},
|
| 707 |
{
|
| 708 |
"epoch": 3.287671232876712,
|
| 709 |
+
"grad_norm": 0.310546875,
|
| 710 |
+
"learning_rate": 0.00016977476441179992,
|
| 711 |
+
"loss": 0.9844,
|
| 712 |
"step": 480
|
| 713 |
},
|
| 714 |
{
|
| 715 |
"epoch": 3.3219178082191783,
|
| 716 |
+
"grad_norm": 0.337890625,
|
| 717 |
+
"learning_rate": 0.0001689134598651219,
|
| 718 |
+
"loss": 0.9841,
|
| 719 |
"step": 485
|
| 720 |
},
|
| 721 |
{
|
| 722 |
"epoch": 3.356164383561644,
|
| 723 |
+
"grad_norm": 0.30078125,
|
| 724 |
+
"learning_rate": 0.0001680423073214737,
|
| 725 |
+
"loss": 0.993,
|
| 726 |
"step": 490
|
| 727 |
},
|
| 728 |
{
|
| 729 |
"epoch": 3.3904109589041096,
|
| 730 |
+
"grad_norm": 0.349609375,
|
| 731 |
+
"learning_rate": 0.00016716143127188548,
|
| 732 |
+
"loss": 0.9842,
|
| 733 |
"step": 495
|
| 734 |
},
|
| 735 |
{
|
| 736 |
"epoch": 3.4246575342465753,
|
| 737 |
+
"grad_norm": 0.37109375,
|
| 738 |
+
"learning_rate": 0.00016627095759691362,
|
| 739 |
+
"loss": 0.9925,
|
| 740 |
"step": 500
|
| 741 |
},
|
| 742 |
{
|
| 743 |
"epoch": 3.458904109589041,
|
| 744 |
+
"grad_norm": 0.474609375,
|
| 745 |
+
"learning_rate": 0.0001653710135486518,
|
| 746 |
+
"loss": 0.9822,
|
| 747 |
"step": 505
|
| 748 |
},
|
| 749 |
{
|
| 750 |
"epoch": 3.493150684931507,
|
| 751 |
+
"grad_norm": 0.3046875,
|
| 752 |
+
"learning_rate": 0.00016446172773254629,
|
| 753 |
+
"loss": 0.985,
|
| 754 |
"step": 510
|
| 755 |
},
|
| 756 |
{
|
| 757 |
"epoch": 3.5273972602739727,
|
| 758 |
+
"grad_norm": 0.37109375,
|
| 759 |
+
"learning_rate": 0.00016354323008901776,
|
| 760 |
+
"loss": 0.9937,
|
| 761 |
"step": 515
|
| 762 |
},
|
| 763 |
{
|
| 764 |
"epoch": 3.5616438356164384,
|
| 765 |
+
"grad_norm": 0.314453125,
|
| 766 |
+
"learning_rate": 0.0001626156518748922,
|
| 767 |
+
"loss": 0.9889,
|
| 768 |
"step": 520
|
| 769 |
},
|
| 770 |
{
|
| 771 |
"epoch": 3.595890410958904,
|
| 772 |
+
"grad_norm": 0.3046875,
|
| 773 |
+
"learning_rate": 0.00016167912564464383,
|
| 774 |
+
"loss": 0.9816,
|
| 775 |
"step": 525
|
| 776 |
},
|
| 777 |
{
|
| 778 |
"epoch": 3.6301369863013697,
|
| 779 |
+
"grad_norm": 0.314453125,
|
| 780 |
+
"learning_rate": 0.0001607337852314527,
|
| 781 |
+
"loss": 0.9873,
|
| 782 |
"step": 530
|
| 783 |
},
|
| 784 |
{
|
| 785 |
"epoch": 3.6643835616438354,
|
| 786 |
+
"grad_norm": 0.3046875,
|
| 787 |
+
"learning_rate": 0.0001597797657280792,
|
| 788 |
+
"loss": 0.9935,
|
| 789 |
"step": 535
|
| 790 |
},
|
| 791 |
{
|
| 792 |
"epoch": 3.6986301369863015,
|
| 793 |
+
"grad_norm": 0.287109375,
|
| 794 |
+
"learning_rate": 0.00015881720346755905,
|
| 795 |
+
"loss": 0.9863,
|
| 796 |
"step": 540
|
| 797 |
},
|
| 798 |
{
|
| 799 |
"epoch": 3.732876712328767,
|
| 800 |
+
"grad_norm": 0.34375,
|
| 801 |
+
"learning_rate": 0.00015784623600372042,
|
| 802 |
+
"loss": 0.9782,
|
| 803 |
"step": 545
|
| 804 |
},
|
| 805 |
{
|
| 806 |
"epoch": 3.767123287671233,
|
| 807 |
+
"grad_norm": 0.375,
|
| 808 |
+
"learning_rate": 0.00015686700209152738,
|
| 809 |
+
"loss": 0.9779,
|
| 810 |
"step": 550
|
| 811 |
},
|
| 812 |
{
|
| 813 |
"epoch": 3.8013698630136985,
|
| 814 |
+
"grad_norm": 0.3515625,
|
| 815 |
+
"learning_rate": 0.00015587964166725095,
|
| 816 |
+
"loss": 0.9883,
|
| 817 |
"step": 555
|
| 818 |
},
|
| 819 |
{
|
| 820 |
"epoch": 3.8356164383561646,
|
| 821 |
+
"grad_norm": 0.33203125,
|
| 822 |
+
"learning_rate": 0.00015488429582847192,
|
| 823 |
+
"loss": 0.968,
|
| 824 |
"step": 560
|
| 825 |
},
|
| 826 |
{
|
| 827 |
"epoch": 3.8698630136986303,
|
| 828 |
+
"grad_norm": 0.478515625,
|
| 829 |
+
"learning_rate": 0.00015388110681391725,
|
| 830 |
+
"loss": 0.9858,
|
| 831 |
"step": 565
|
| 832 |
},
|
| 833 |
{
|
| 834 |
"epoch": 3.904109589041096,
|
| 835 |
+
"grad_norm": 0.294921875,
|
| 836 |
+
"learning_rate": 0.0001528702179831338,
|
| 837 |
+
"loss": 0.9668,
|
| 838 |
"step": 570
|
| 839 |
},
|
| 840 |
{
|
| 841 |
"epoch": 3.9383561643835616,
|
| 842 |
+
"grad_norm": 0.3203125,
|
| 843 |
+
"learning_rate": 0.00015185177379600152,
|
| 844 |
+
"loss": 0.9853,
|
| 845 |
"step": 575
|
| 846 |
},
|
| 847 |
{
|
| 848 |
"epoch": 3.9726027397260273,
|
| 849 |
+
"grad_norm": 0.302734375,
|
| 850 |
+
"learning_rate": 0.00015082591979208976,
|
| 851 |
+
"loss": 0.9796,
|
| 852 |
"step": 580
|
| 853 |
},
|
| 854 |
{
|
| 855 |
"epoch": 4.0,
|
| 856 |
+
"eval_loss": 2.5387372970581055,
|
| 857 |
+
"eval_runtime": 0.5485,
|
| 858 |
+
"eval_samples_per_second": 18.233,
|
| 859 |
+
"eval_steps_per_second": 1.823,
|
| 860 |
"step": 584
|
| 861 |
},
|
| 862 |
{
|
| 863 |
"epoch": 4.006849315068493,
|
| 864 |
+
"grad_norm": 0.369140625,
|
| 865 |
+
"learning_rate": 0.000149792802569859,
|
| 866 |
+
"loss": 0.981,
|
| 867 |
"step": 585
|
| 868 |
},
|
| 869 |
{
|
| 870 |
"epoch": 4.041095890410959,
|
| 871 |
+
"grad_norm": 0.31640625,
|
| 872 |
+
"learning_rate": 0.00014875256976571135,
|
| 873 |
+
"loss": 0.9259,
|
| 874 |
"step": 590
|
| 875 |
},
|
| 876 |
{
|
| 877 |
"epoch": 4.075342465753424,
|
| 878 |
+
"grad_norm": 0.302734375,
|
| 879 |
+
"learning_rate": 0.0001477053700328929,
|
| 880 |
+
"loss": 0.9421,
|
| 881 |
"step": 595
|
| 882 |
},
|
| 883 |
{
|
| 884 |
"epoch": 4.109589041095891,
|
| 885 |
+
"grad_norm": 0.310546875,
|
| 886 |
+
"learning_rate": 0.00014665135302025035,
|
| 887 |
+
"loss": 0.9348,
|
| 888 |
"step": 600
|
| 889 |
},
|
| 890 |
{
|
| 891 |
"epoch": 4.1438356164383565,
|
| 892 |
+
"grad_norm": 0.322265625,
|
| 893 |
+
"learning_rate": 0.00014559066935084588,
|
| 894 |
+
"loss": 0.9353,
|
| 895 |
"step": 605
|
| 896 |
},
|
| 897 |
{
|
| 898 |
"epoch": 4.178082191780822,
|
| 899 |
+
"grad_norm": 0.314453125,
|
| 900 |
+
"learning_rate": 0.00014452347060043237,
|
| 901 |
+
"loss": 0.9267,
|
| 902 |
"step": 610
|
| 903 |
},
|
| 904 |
{
|
| 905 |
"epoch": 4.212328767123288,
|
| 906 |
+
"grad_norm": 0.359375,
|
| 907 |
+
"learning_rate": 0.00014344990927579268,
|
| 908 |
+
"loss": 0.9451,
|
| 909 |
"step": 615
|
| 910 |
},
|
| 911 |
{
|
| 912 |
"epoch": 4.2465753424657535,
|
| 913 |
+
"grad_norm": 0.486328125,
|
| 914 |
+
"learning_rate": 0.0001423701387929459,
|
| 915 |
+
"loss": 0.9245,
|
| 916 |
"step": 620
|
| 917 |
},
|
| 918 |
{
|
| 919 |
"epoch": 4.280821917808219,
|
| 920 |
+
"grad_norm": 0.4765625,
|
| 921 |
+
"learning_rate": 0.0001412843134552235,
|
| 922 |
+
"loss": 0.9371,
|
| 923 |
"step": 625
|
| 924 |
},
|
| 925 |
{
|
| 926 |
"epoch": 4.315068493150685,
|
| 927 |
+
"grad_norm": 0.38671875,
|
| 928 |
+
"learning_rate": 0.00014019258843121893,
|
| 929 |
+
"loss": 0.9309,
|
| 930 |
"step": 630
|
| 931 |
},
|
| 932 |
{
|
| 933 |
"epoch": 4.3493150684931505,
|
| 934 |
+
"grad_norm": 0.4453125,
|
| 935 |
+
"learning_rate": 0.0001390951197326134,
|
| 936 |
+
"loss": 0.9426,
|
| 937 |
"step": 635
|
| 938 |
},
|
| 939 |
{
|
| 940 |
"epoch": 4.383561643835616,
|
| 941 |
+
"grad_norm": 0.474609375,
|
| 942 |
+
"learning_rate": 0.00013799206419188103,
|
| 943 |
+
"loss": 0.9359,
|
| 944 |
"step": 640
|
| 945 |
},
|
| 946 |
{
|
| 947 |
"epoch": 4.417808219178082,
|
| 948 |
+
"grad_norm": 0.396484375,
|
| 949 |
+
"learning_rate": 0.00013688357943987732,
|
| 950 |
+
"loss": 0.945,
|
| 951 |
"step": 645
|
| 952 |
},
|
| 953 |
{
|
| 954 |
"epoch": 4.4520547945205475,
|
| 955 |
+
"grad_norm": 0.36328125,
|
| 956 |
+
"learning_rate": 0.0001357698238833126,
|
| 957 |
+
"loss": 0.9341,
|
| 958 |
"step": 650
|
| 959 |
},
|
| 960 |
{
|
| 961 |
"epoch": 4.486301369863014,
|
| 962 |
+
"grad_norm": 0.361328125,
|
| 963 |
+
"learning_rate": 0.0001346509566821153,
|
| 964 |
+
"loss": 0.9454,
|
| 965 |
"step": 655
|
| 966 |
},
|
| 967 |
{
|
| 968 |
"epoch": 4.52054794520548,
|
| 969 |
+
"grad_norm": 0.341796875,
|
| 970 |
+
"learning_rate": 0.00013352713772668765,
|
| 971 |
+
"loss": 0.9414,
|
| 972 |
"step": 660
|
| 973 |
},
|
| 974 |
{
|
| 975 |
"epoch": 4.554794520547945,
|
| 976 |
+
"grad_norm": 0.431640625,
|
| 977 |
+
"learning_rate": 0.00013239852761505626,
|
| 978 |
+
"loss": 0.9429,
|
| 979 |
"step": 665
|
| 980 |
},
|
| 981 |
{
|
| 982 |
"epoch": 4.589041095890411,
|
| 983 |
+
"grad_norm": 0.40625,
|
| 984 |
+
"learning_rate": 0.00013126528762992247,
|
| 985 |
+
"loss": 0.947,
|
| 986 |
"step": 670
|
| 987 |
},
|
| 988 |
{
|
| 989 |
"epoch": 4.623287671232877,
|
| 990 |
+
"grad_norm": 0.3125,
|
| 991 |
+
"learning_rate": 0.00013012757971561415,
|
| 992 |
+
"loss": 0.9387,
|
| 993 |
"step": 675
|
| 994 |
},
|
| 995 |
{
|
| 996 |
"epoch": 4.657534246575342,
|
| 997 |
+
"grad_norm": 0.33984375,
|
| 998 |
+
"learning_rate": 0.00012898556645494325,
|
| 999 |
+
"loss": 0.9485,
|
| 1000 |
"step": 680
|
| 1001 |
},
|
| 1002 |
{
|
| 1003 |
"epoch": 4.691780821917808,
|
| 1004 |
+
"grad_norm": 0.326171875,
|
| 1005 |
+
"learning_rate": 0.0001278394110459724,
|
| 1006 |
+
"loss": 0.9457,
|
| 1007 |
"step": 685
|
| 1008 |
},
|
| 1009 |
{
|
| 1010 |
"epoch": 4.726027397260274,
|
| 1011 |
+
"grad_norm": 0.341796875,
|
| 1012 |
+
"learning_rate": 0.0001266892772786929,
|
| 1013 |
+
"loss": 0.9463,
|
| 1014 |
"step": 690
|
| 1015 |
},
|
| 1016 |
{
|
| 1017 |
"epoch": 4.760273972602739,
|
| 1018 |
+
"grad_norm": 0.31640625,
|
| 1019 |
+
"learning_rate": 0.0001255353295116187,
|
| 1020 |
+
"loss": 0.9518,
|
| 1021 |
"step": 695
|
| 1022 |
},
|
| 1023 |
{
|
| 1024 |
"epoch": 4.794520547945205,
|
| 1025 |
+
"grad_norm": 0.349609375,
|
| 1026 |
+
"learning_rate": 0.00012437773264829897,
|
| 1027 |
+
"loss": 0.9382,
|
| 1028 |
"step": 700
|
| 1029 |
},
|
| 1030 |
{
|
| 1031 |
"epoch": 4.828767123287671,
|
| 1032 |
+
"grad_norm": 0.34765625,
|
| 1033 |
+
"learning_rate": 0.00012321665211375256,
|
| 1034 |
+
"loss": 0.9485,
|
| 1035 |
"step": 705
|
| 1036 |
},
|
| 1037 |
{
|
| 1038 |
"epoch": 4.863013698630137,
|
| 1039 |
+
"grad_norm": 0.3203125,
|
| 1040 |
+
"learning_rate": 0.00012205225383082843,
|
| 1041 |
+
"loss": 0.9393,
|
| 1042 |
"step": 710
|
| 1043 |
},
|
| 1044 |
{
|
| 1045 |
"epoch": 4.897260273972603,
|
| 1046 |
"grad_norm": 0.359375,
|
| 1047 |
+
"learning_rate": 0.00012088470419649432,
|
| 1048 |
+
"loss": 0.9568,
|
| 1049 |
"step": 715
|
| 1050 |
},
|
| 1051 |
{
|
| 1052 |
"epoch": 4.931506849315069,
|
| 1053 |
+
"grad_norm": 0.337890625,
|
| 1054 |
+
"learning_rate": 0.00011971417005805818,
|
| 1055 |
+
"loss": 0.9352,
|
| 1056 |
"step": 720
|
| 1057 |
},
|
| 1058 |
{
|
| 1059 |
"epoch": 4.965753424657534,
|
| 1060 |
+
"grad_norm": 0.353515625,
|
| 1061 |
+
"learning_rate": 0.0001185408186893251,
|
| 1062 |
+
"loss": 0.9383,
|
| 1063 |
"step": 725
|
| 1064 |
},
|
| 1065 |
{
|
| 1066 |
"epoch": 5.0,
|
| 1067 |
+
"grad_norm": 0.322265625,
|
| 1068 |
+
"learning_rate": 0.00011736481776669306,
|
| 1069 |
+
"loss": 0.9366,
|
| 1070 |
"step": 730
|
| 1071 |
},
|
| 1072 |
{
|
| 1073 |
"epoch": 5.0,
|
| 1074 |
+
"eval_loss": 2.6037707328796387,
|
| 1075 |
+
"eval_runtime": 0.5451,
|
| 1076 |
+
"eval_samples_per_second": 18.346,
|
| 1077 |
+
"eval_steps_per_second": 1.835,
|
| 1078 |
"step": 730
|
| 1079 |
},
|
| 1080 |
{
|
| 1081 |
"epoch": 5.034246575342466,
|
| 1082 |
+
"grad_norm": 0.349609375,
|
| 1083 |
+
"learning_rate": 0.00011618633534519141,
|
| 1084 |
+
"loss": 0.9013,
|
| 1085 |
"step": 735
|
| 1086 |
},
|
| 1087 |
{
|
| 1088 |
"epoch": 5.068493150684931,
|
| 1089 |
+
"grad_norm": 0.31640625,
|
| 1090 |
+
"learning_rate": 0.00011500553983446527,
|
| 1091 |
+
"loss": 0.9034,
|
| 1092 |
"step": 740
|
| 1093 |
},
|
| 1094 |
{
|
| 1095 |
"epoch": 5.102739726027397,
|
| 1096 |
+
"grad_norm": 0.34765625,
|
| 1097 |
+
"learning_rate": 0.00011382259997470899,
|
| 1098 |
+
"loss": 0.8925,
|
| 1099 |
"step": 745
|
| 1100 |
},
|
| 1101 |
{
|
| 1102 |
"epoch": 5.136986301369863,
|
| 1103 |
+
"grad_norm": 0.345703125,
|
| 1104 |
+
"learning_rate": 0.00011263768481255264,
|
| 1105 |
+
"loss": 0.8901,
|
| 1106 |
"step": 750
|
| 1107 |
},
|
| 1108 |
{
|
| 1109 |
"epoch": 5.171232876712328,
|
| 1110 |
+
"grad_norm": 0.333984375,
|
| 1111 |
+
"learning_rate": 0.00011145096367690444,
|
| 1112 |
+
"loss": 0.8945,
|
| 1113 |
"step": 755
|
| 1114 |
},
|
| 1115 |
{
|
| 1116 |
"epoch": 5.205479452054795,
|
| 1117 |
+
"grad_norm": 0.42578125,
|
| 1118 |
+
"learning_rate": 0.00011026260615475333,
|
| 1119 |
+
"loss": 0.8961,
|
| 1120 |
"step": 760
|
| 1121 |
},
|
| 1122 |
{
|
| 1123 |
"epoch": 5.239726027397261,
|
| 1124 |
+
"grad_norm": 0.4765625,
|
| 1125 |
+
"learning_rate": 0.00010907278206693395,
|
| 1126 |
+
"loss": 0.8911,
|
| 1127 |
"step": 765
|
| 1128 |
},
|
| 1129 |
{
|
| 1130 |
"epoch": 5.273972602739726,
|
| 1131 |
+
"grad_norm": 0.3828125,
|
| 1132 |
+
"learning_rate": 0.00010788166144385888,
|
| 1133 |
+
"loss": 0.9018,
|
| 1134 |
"step": 770
|
| 1135 |
},
|
| 1136 |
{
|
| 1137 |
"epoch": 5.308219178082192,
|
| 1138 |
+
"grad_norm": 0.51953125,
|
| 1139 |
+
"learning_rate": 0.00010668941450122055,
|
| 1140 |
+
"loss": 0.9046,
|
| 1141 |
"step": 775
|
| 1142 |
},
|
| 1143 |
{
|
| 1144 |
"epoch": 5.342465753424658,
|
| 1145 |
+
"grad_norm": 0.54296875,
|
| 1146 |
+
"learning_rate": 0.0001054962116156667,
|
| 1147 |
+
"loss": 0.8964,
|
| 1148 |
"step": 780
|
| 1149 |
},
|
| 1150 |
{
|
| 1151 |
"epoch": 5.376712328767123,
|
| 1152 |
+
"grad_norm": 0.50390625,
|
| 1153 |
+
"learning_rate": 0.00010430222330045304,
|
| 1154 |
+
"loss": 0.9071,
|
| 1155 |
"step": 785
|
| 1156 |
},
|
| 1157 |
{
|
| 1158 |
"epoch": 5.410958904109589,
|
| 1159 |
+
"grad_norm": 0.4921875,
|
| 1160 |
+
"learning_rate": 0.0001031076201810762,
|
| 1161 |
+
"loss": 0.8981,
|
| 1162 |
"step": 790
|
| 1163 |
},
|
| 1164 |
{
|
| 1165 |
"epoch": 5.445205479452055,
|
| 1166 |
+
"grad_norm": 0.3359375,
|
| 1167 |
+
"learning_rate": 0.00010191257297089052,
|
| 1168 |
+
"loss": 0.9054,
|
| 1169 |
"step": 795
|
| 1170 |
},
|
| 1171 |
{
|
| 1172 |
"epoch": 5.47945205479452,
|
| 1173 |
+
"grad_norm": 0.337890625,
|
| 1174 |
+
"learning_rate": 0.00010071725244671282,
|
| 1175 |
+
"loss": 0.9061,
|
| 1176 |
"step": 800
|
| 1177 |
},
|
| 1178 |
{
|
| 1179 |
"epoch": 5.513698630136986,
|
| 1180 |
+
"grad_norm": 0.4140625,
|
| 1181 |
+
"learning_rate": 9.952182942441733e-05,
|
| 1182 |
+
"loss": 0.905,
|
| 1183 |
"step": 805
|
| 1184 |
},
|
| 1185 |
{
|
| 1186 |
"epoch": 5.5479452054794525,
|
| 1187 |
+
"grad_norm": 0.33203125,
|
| 1188 |
+
"learning_rate": 9.83264747345259e-05,
|
| 1189 |
+
"loss": 0.8981,
|
| 1190 |
"step": 810
|
| 1191 |
},
|
| 1192 |
{
|
| 1193 |
"epoch": 5.582191780821918,
|
| 1194 |
+
"grad_norm": 0.416015625,
|
| 1195 |
+
"learning_rate": 9.713135919779515e-05,
|
| 1196 |
+
"loss": 0.8956,
|
| 1197 |
"step": 815
|
| 1198 |
},
|
| 1199 |
{
|
| 1200 |
"epoch": 5.616438356164384,
|
| 1201 |
+
"grad_norm": 0.41015625,
|
| 1202 |
+
"learning_rate": 9.593665360080599e-05,
|
| 1203 |
+
"loss": 0.9116,
|
| 1204 |
"step": 820
|
| 1205 |
},
|
| 1206 |
{
|
| 1207 |
"epoch": 5.6506849315068495,
|
| 1208 |
+
"grad_norm": 0.357421875,
|
| 1209 |
+
"learning_rate": 9.474252867155732e-05,
|
| 1210 |
+
"loss": 0.9002,
|
| 1211 |
"step": 825
|
| 1212 |
},
|
| 1213 |
{
|
| 1214 |
"epoch": 5.684931506849315,
|
| 1215 |
+
"grad_norm": 0.322265625,
|
| 1216 |
+
"learning_rate": 9.354915505506839e-05,
|
| 1217 |
+
"loss": 0.8971,
|
| 1218 |
"step": 830
|
| 1219 |
},
|
| 1220 |
{
|
| 1221 |
"epoch": 5.719178082191781,
|
| 1222 |
+
"grad_norm": 0.3359375,
|
| 1223 |
+
"learning_rate": 9.235670328899293e-05,
|
| 1224 |
+
"loss": 0.8988,
|
| 1225 |
"step": 835
|
| 1226 |
},
|
| 1227 |
{
|
| 1228 |
"epoch": 5.7534246575342465,
|
| 1229 |
+
"grad_norm": 0.3359375,
|
| 1230 |
+
"learning_rate": 9.116534377924883e-05,
|
| 1231 |
+
"loss": 0.8922,
|
| 1232 |
"step": 840
|
| 1233 |
},
|
| 1234 |
{
|
| 1235 |
"epoch": 5.787671232876712,
|
| 1236 |
+
"grad_norm": 0.32421875,
|
| 1237 |
+
"learning_rate": 8.997524677566627e-05,
|
| 1238 |
+
"loss": 0.8953,
|
| 1239 |
"step": 845
|
| 1240 |
},
|
| 1241 |
{
|
| 1242 |
"epoch": 5.821917808219178,
|
| 1243 |
+
"grad_norm": 0.326171875,
|
| 1244 |
+
"learning_rate": 8.878658234765858e-05,
|
| 1245 |
+
"loss": 0.8986,
|
| 1246 |
"step": 850
|
| 1247 |
},
|
| 1248 |
{
|
| 1249 |
"epoch": 5.8561643835616435,
|
| 1250 |
+
"grad_norm": 0.322265625,
|
| 1251 |
+
"learning_rate": 8.759952035991844e-05,
|
| 1252 |
+
"loss": 0.8949,
|
| 1253 |
"step": 855
|
| 1254 |
},
|
| 1255 |
{
|
| 1256 |
"epoch": 5.890410958904109,
|
| 1257 |
+
"grad_norm": 0.33203125,
|
| 1258 |
+
"learning_rate": 8.641423044814374e-05,
|
| 1259 |
+
"loss": 0.9013,
|
| 1260 |
"step": 860
|
| 1261 |
},
|
| 1262 |
{
|
| 1263 |
"epoch": 5.924657534246576,
|
| 1264 |
+
"grad_norm": 0.33203125,
|
| 1265 |
+
"learning_rate": 8.5230881994796e-05,
|
| 1266 |
+
"loss": 0.9133,
|
| 1267 |
"step": 865
|
| 1268 |
},
|
| 1269 |
{
|
| 1270 |
"epoch": 5.958904109589041,
|
| 1271 |
+
"grad_norm": 0.33984375,
|
| 1272 |
+
"learning_rate": 8.404964410489485e-05,
|
| 1273 |
+
"loss": 0.9042,
|
| 1274 |
"step": 870
|
| 1275 |
},
|
| 1276 |
{
|
| 1277 |
"epoch": 5.993150684931507,
|
| 1278 |
+
"grad_norm": 0.33203125,
|
| 1279 |
+
"learning_rate": 8.287068558185225e-05,
|
| 1280 |
+
"loss": 0.9051,
|
| 1281 |
"step": 875
|
| 1282 |
},
|
| 1283 |
{
|
| 1284 |
"epoch": 6.0,
|
| 1285 |
+
"eval_loss": 2.6520962715148926,
|
| 1286 |
+
"eval_runtime": 0.5512,
|
| 1287 |
+
"eval_samples_per_second": 18.142,
|
| 1288 |
+
"eval_steps_per_second": 1.814,
|
| 1289 |
"step": 876
|
| 1290 |
},
|
| 1291 |
{
|
| 1292 |
"epoch": 6.027397260273973,
|
| 1293 |
+
"grad_norm": 0.33203125,
|
| 1294 |
+
"learning_rate": 8.169417490335007e-05,
|
| 1295 |
+
"loss": 0.8764,
|
| 1296 |
"step": 880
|
| 1297 |
},
|
| 1298 |
{
|
| 1299 |
"epoch": 6.061643835616438,
|
| 1300 |
+
"grad_norm": 0.34765625,
|
| 1301 |
+
"learning_rate": 8.052028019726371e-05,
|
| 1302 |
+
"loss": 0.8608,
|
| 1303 |
"step": 885
|
| 1304 |
},
|
| 1305 |
{
|
| 1306 |
"epoch": 6.095890410958904,
|
| 1307 |
+
"grad_norm": 0.349609375,
|
| 1308 |
+
"learning_rate": 7.934916921763628e-05,
|
| 1309 |
+
"loss": 0.8474,
|
| 1310 |
"step": 890
|
| 1311 |
},
|
| 1312 |
{
|
| 1313 |
"epoch": 6.13013698630137,
|
| 1314 |
+
"grad_norm": 0.361328125,
|
| 1315 |
+
"learning_rate": 7.818100932070546e-05,
|
| 1316 |
+
"loss": 0.8558,
|
| 1317 |
"step": 895
|
| 1318 |
},
|
| 1319 |
{
|
| 1320 |
"epoch": 6.164383561643835,
|
| 1321 |
+
"grad_norm": 0.34375,
|
| 1322 |
+
"learning_rate": 7.701596744098818e-05,
|
| 1323 |
+
"loss": 0.858,
|
| 1324 |
"step": 900
|
| 1325 |
},
|
| 1326 |
{
|
| 1327 |
"epoch": 6.198630136986301,
|
| 1328 |
+
"grad_norm": 0.34375,
|
| 1329 |
+
"learning_rate": 7.585421006742463e-05,
|
| 1330 |
+
"loss": 0.8568,
|
| 1331 |
"step": 905
|
| 1332 |
},
|
| 1333 |
{
|
| 1334 |
"epoch": 6.232876712328767,
|
| 1335 |
+
"grad_norm": 0.333984375,
|
| 1336 |
+
"learning_rate": 7.469590321958662e-05,
|
| 1337 |
+
"loss": 0.8626,
|
| 1338 |
"step": 910
|
| 1339 |
},
|
| 1340 |
{
|
| 1341 |
"epoch": 6.267123287671233,
|
| 1342 |
+
"grad_norm": 0.353515625,
|
| 1343 |
+
"learning_rate": 7.354121242395254e-05,
|
| 1344 |
+
"loss": 0.8685,
|
| 1345 |
"step": 915
|
| 1346 |
},
|
| 1347 |
{
|
| 1348 |
"epoch": 6.301369863013699,
|
| 1349 |
+
"grad_norm": 0.3828125,
|
| 1350 |
+
"learning_rate": 7.239030269025311e-05,
|
| 1351 |
+
"loss": 0.8621,
|
| 1352 |
"step": 920
|
| 1353 |
},
|
| 1354 |
{
|
| 1355 |
"epoch": 6.335616438356165,
|
| 1356 |
+
"grad_norm": 0.404296875,
|
| 1357 |
+
"learning_rate": 7.124333848789091e-05,
|
| 1358 |
+
"loss": 0.8687,
|
| 1359 |
"step": 925
|
| 1360 |
},
|
| 1361 |
{
|
| 1362 |
"epoch": 6.36986301369863,
|
| 1363 |
+
"grad_norm": 0.35546875,
|
| 1364 |
+
"learning_rate": 7.010048372243698e-05,
|
| 1365 |
+
"loss": 0.8691,
|
| 1366 |
"step": 930
|
| 1367 |
},
|
| 1368 |
{
|
| 1369 |
"epoch": 6.404109589041096,
|
| 1370 |
+
"grad_norm": 0.44140625,
|
| 1371 |
+
"learning_rate": 6.8961901712208e-05,
|
| 1372 |
+
"loss": 0.8651,
|
| 1373 |
"step": 935
|
| 1374 |
},
|
| 1375 |
{
|
| 1376 |
"epoch": 6.438356164383562,
|
| 1377 |
+
"grad_norm": 0.353515625,
|
| 1378 |
+
"learning_rate": 6.782775516492771e-05,
|
| 1379 |
+
"loss": 0.8656,
|
| 1380 |
"step": 940
|
| 1381 |
},
|
| 1382 |
{
|
| 1383 |
"epoch": 6.472602739726027,
|
| 1384 |
+
"grad_norm": 0.384765625,
|
| 1385 |
+
"learning_rate": 6.669820615447522e-05,
|
| 1386 |
+
"loss": 0.8683,
|
| 1387 |
"step": 945
|
| 1388 |
},
|
| 1389 |
{
|
| 1390 |
"epoch": 6.506849315068493,
|
| 1391 |
+
"grad_norm": 0.361328125,
|
| 1392 |
+
"learning_rate": 6.5573416097724e-05,
|
| 1393 |
+
"loss": 0.8632,
|
| 1394 |
"step": 950
|
| 1395 |
},
|
| 1396 |
{
|
| 1397 |
"epoch": 6.541095890410959,
|
| 1398 |
+
"grad_norm": 0.353515625,
|
| 1399 |
+
"learning_rate": 6.445354573147484e-05,
|
| 1400 |
+
"loss": 0.8693,
|
| 1401 |
"step": 955
|
| 1402 |
},
|
| 1403 |
{
|
| 1404 |
"epoch": 6.575342465753424,
|
| 1405 |
+
"grad_norm": 0.341796875,
|
| 1406 |
+
"learning_rate": 6.333875508948593e-05,
|
| 1407 |
+
"loss": 0.8724,
|
| 1408 |
"step": 960
|
| 1409 |
},
|
| 1410 |
{
|
| 1411 |
"epoch": 6.609589041095891,
|
| 1412 |
+
"grad_norm": 0.35546875,
|
| 1413 |
+
"learning_rate": 6.22292034796035e-05,
|
| 1414 |
+
"loss": 0.8659,
|
| 1415 |
"step": 965
|
| 1416 |
},
|
| 1417 |
{
|
| 1418 |
"epoch": 6.6438356164383565,
|
| 1419 |
+
"grad_norm": 0.357421875,
|
| 1420 |
+
"learning_rate": 6.112504946099604e-05,
|
| 1421 |
+
"loss": 0.8674,
|
| 1422 |
"step": 970
|
| 1423 |
},
|
| 1424 |
{
|
| 1425 |
"epoch": 6.678082191780822,
|
| 1426 |
+
"grad_norm": 0.390625,
|
| 1427 |
+
"learning_rate": 6.0026450821495536e-05,
|
| 1428 |
+
"loss": 0.8762,
|
| 1429 |
"step": 975
|
| 1430 |
},
|
| 1431 |
{
|
| 1432 |
"epoch": 6.712328767123288,
|
| 1433 |
+
"grad_norm": 0.33984375,
|
| 1434 |
+
"learning_rate": 5.8933564555049105e-05,
|
| 1435 |
+
"loss": 0.8581,
|
| 1436 |
"step": 980
|
| 1437 |
},
|
| 1438 |
{
|
| 1439 |
"epoch": 6.7465753424657535,
|
| 1440 |
+
"grad_norm": 0.34765625,
|
| 1441 |
+
"learning_rate": 5.784654683928391e-05,
|
| 1442 |
+
"loss": 0.8718,
|
| 1443 |
"step": 985
|
| 1444 |
},
|
| 1445 |
{
|
| 1446 |
"epoch": 6.780821917808219,
|
| 1447 |
+
"grad_norm": 0.36328125,
|
| 1448 |
+
"learning_rate": 5.6765553013188766e-05,
|
| 1449 |
+
"loss": 0.8637,
|
| 1450 |
"step": 990
|
| 1451 |
},
|
| 1452 |
{
|
| 1453 |
"epoch": 6.815068493150685,
|
| 1454 |
+
"grad_norm": 0.361328125,
|
| 1455 |
+
"learning_rate": 5.5690737554915604e-05,
|
| 1456 |
+
"loss": 0.8684,
|
| 1457 |
"step": 995
|
| 1458 |
},
|
| 1459 |
{
|
| 1460 |
"epoch": 6.8493150684931505,
|
| 1461 |
+
"grad_norm": 0.353515625,
|
| 1462 |
+
"learning_rate": 5.462225405970401e-05,
|
| 1463 |
+
"loss": 0.8693,
|
| 1464 |
"step": 1000
|
| 1465 |
},
|
| 1466 |
{
|
| 1467 |
"epoch": 6.883561643835616,
|
| 1468 |
+
"grad_norm": 0.34765625,
|
| 1469 |
+
"learning_rate": 5.3560255217931785e-05,
|
| 1470 |
+
"loss": 0.871,
|
| 1471 |
"step": 1005
|
| 1472 |
},
|
| 1473 |
{
|
| 1474 |
"epoch": 6.917808219178082,
|
| 1475 |
+
"grad_norm": 0.369140625,
|
| 1476 |
+
"learning_rate": 5.2504892793295e-05,
|
| 1477 |
+
"loss": 0.8644,
|
| 1478 |
"step": 1010
|
| 1479 |
},
|
| 1480 |
{
|
| 1481 |
"epoch": 6.9520547945205475,
|
| 1482 |
+
"grad_norm": 0.34375,
|
| 1483 |
+
"learning_rate": 5.145631760112022e-05,
|
| 1484 |
+
"loss": 0.8688,
|
| 1485 |
"step": 1015
|
| 1486 |
},
|
| 1487 |
{
|
| 1488 |
"epoch": 6.986301369863014,
|
| 1489 |
+
"grad_norm": 0.34765625,
|
| 1490 |
+
"learning_rate": 5.041467948681269e-05,
|
| 1491 |
+
"loss": 0.8676,
|
| 1492 |
"step": 1020
|
| 1493 |
},
|
| 1494 |
{
|
| 1495 |
"epoch": 7.0,
|
| 1496 |
+
"eval_loss": 2.7248690128326416,
|
| 1497 |
+
"eval_runtime": 0.5502,
|
| 1498 |
+
"eval_samples_per_second": 18.174,
|
| 1499 |
+
"eval_steps_per_second": 1.817,
|
| 1500 |
"step": 1022
|
| 1501 |
},
|
| 1502 |
{
|
| 1503 |
"epoch": 7.02054794520548,
|
| 1504 |
+
"grad_norm": 0.328125,
|
| 1505 |
+
"learning_rate": 4.9380127304442634e-05,
|
| 1506 |
+
"loss": 0.8501,
|
| 1507 |
"step": 1025
|
| 1508 |
},
|
| 1509 |
{
|
| 1510 |
"epoch": 7.054794520547945,
|
| 1511 |
+
"grad_norm": 0.357421875,
|
| 1512 |
+
"learning_rate": 4.835280889547351e-05,
|
| 1513 |
+
"loss": 0.8375,
|
| 1514 |
"step": 1030
|
| 1515 |
},
|
| 1516 |
{
|
| 1517 |
"epoch": 7.089041095890411,
|
| 1518 |
+
"grad_norm": 0.3515625,
|
| 1519 |
+
"learning_rate": 4.733287106763481e-05,
|
| 1520 |
+
"loss": 0.8297,
|
| 1521 |
"step": 1035
|
| 1522 |
},
|
| 1523 |
{
|
| 1524 |
"epoch": 7.123287671232877,
|
| 1525 |
+
"grad_norm": 0.375,
|
| 1526 |
+
"learning_rate": 4.6320459573942856e-05,
|
| 1527 |
+
"loss": 0.8336,
|
| 1528 |
"step": 1040
|
| 1529 |
},
|
| 1530 |
{
|
| 1531 |
"epoch": 7.157534246575342,
|
| 1532 |
+
"grad_norm": 0.365234375,
|
| 1533 |
+
"learning_rate": 4.531571909187197e-05,
|
| 1534 |
+
"loss": 0.832,
|
| 1535 |
"step": 1045
|
| 1536 |
},
|
| 1537 |
{
|
| 1538 |
"epoch": 7.191780821917808,
|
| 1539 |
+
"grad_norm": 0.376953125,
|
| 1540 |
+
"learning_rate": 4.431879320267972e-05,
|
| 1541 |
+
"loss": 0.8393,
|
| 1542 |
"step": 1050
|
| 1543 |
},
|
| 1544 |
{
|
| 1545 |
"epoch": 7.226027397260274,
|
| 1546 |
+
"grad_norm": 0.361328125,
|
| 1547 |
+
"learning_rate": 4.332982437088825e-05,
|
| 1548 |
+
"loss": 0.8425,
|
| 1549 |
"step": 1055
|
| 1550 |
},
|
| 1551 |
{
|
| 1552 |
"epoch": 7.260273972602739,
|
| 1553 |
+
"grad_norm": 0.34765625,
|
| 1554 |
+
"learning_rate": 4.2348953923925916e-05,
|
| 1555 |
+
"loss": 0.846,
|
| 1556 |
"step": 1060
|
| 1557 |
},
|
| 1558 |
{
|
| 1559 |
"epoch": 7.294520547945205,
|
| 1560 |
+
"grad_norm": 0.349609375,
|
| 1561 |
+
"learning_rate": 4.137632203193086e-05,
|
| 1562 |
+
"loss": 0.8396,
|
| 1563 |
"step": 1065
|
| 1564 |
},
|
| 1565 |
{
|
| 1566 |
"epoch": 7.328767123287671,
|
| 1567 |
+
"grad_norm": 0.3515625,
|
| 1568 |
+
"learning_rate": 4.041206768772022e-05,
|
| 1569 |
+
"loss": 0.836,
|
| 1570 |
"step": 1070
|
| 1571 |
},
|
| 1572 |
{
|
| 1573 |
"epoch": 7.363013698630137,
|
| 1574 |
+
"grad_norm": 0.365234375,
|
| 1575 |
+
"learning_rate": 3.9456328686927525e-05,
|
| 1576 |
+
"loss": 0.8442,
|
| 1577 |
"step": 1075
|
| 1578 |
},
|
| 1579 |
{
|
| 1580 |
"epoch": 7.397260273972603,
|
| 1581 |
+
"grad_norm": 0.34765625,
|
| 1582 |
+
"learning_rate": 3.850924160831115e-05,
|
| 1583 |
+
"loss": 0.8358,
|
| 1584 |
"step": 1080
|
| 1585 |
},
|
| 1586 |
{
|
| 1587 |
"epoch": 7.431506849315069,
|
| 1588 |
+
"grad_norm": 0.3515625,
|
| 1589 |
+
"learning_rate": 3.757094179423672e-05,
|
| 1590 |
+
"loss": 0.8381,
|
| 1591 |
"step": 1085
|
| 1592 |
},
|
| 1593 |
{
|
| 1594 |
"epoch": 7.465753424657534,
|
| 1595 |
+
"grad_norm": 0.349609375,
|
| 1596 |
+
"learning_rate": 3.6641563331336125e-05,
|
| 1597 |
+
"loss": 0.837,
|
| 1598 |
"step": 1090
|
| 1599 |
},
|
| 1600 |
{
|
| 1601 |
"epoch": 7.5,
|
| 1602 |
+
"grad_norm": 0.359375,
|
| 1603 |
+
"learning_rate": 3.5721239031346066e-05,
|
| 1604 |
+
"loss": 0.8435,
|
| 1605 |
"step": 1095
|
| 1606 |
},
|
| 1607 |
{
|
| 1608 |
"epoch": 7.534246575342466,
|
| 1609 |
+
"grad_norm": 0.376953125,
|
| 1610 |
+
"learning_rate": 3.4810100412128747e-05,
|
| 1611 |
+
"loss": 0.8412,
|
| 1612 |
"step": 1100
|
| 1613 |
},
|
| 1614 |
{
|
| 1615 |
"epoch": 7.568493150684931,
|
| 1616 |
+
"grad_norm": 0.34765625,
|
| 1617 |
+
"learning_rate": 3.3908277678877445e-05,
|
| 1618 |
+
"loss": 0.8361,
|
| 1619 |
"step": 1105
|
| 1620 |
},
|
| 1621 |
{
|
| 1622 |
"epoch": 7.602739726027397,
|
| 1623 |
+
"grad_norm": 0.359375,
|
| 1624 |
+
"learning_rate": 3.3015899705509734e-05,
|
| 1625 |
+
"loss": 0.84,
|
| 1626 |
"step": 1110
|
| 1627 |
},
|
| 1628 |
{
|
| 1629 |
"epoch": 7.636986301369863,
|
| 1630 |
+
"grad_norm": 0.369140625,
|
| 1631 |
+
"learning_rate": 3.21330940162508e-05,
|
| 1632 |
+
"loss": 0.8427,
|
| 1633 |
"step": 1115
|
| 1634 |
},
|
| 1635 |
{
|
| 1636 |
"epoch": 7.671232876712329,
|
| 1637 |
+
"grad_norm": 0.373046875,
|
| 1638 |
+
"learning_rate": 3.125998676740987e-05,
|
| 1639 |
+
"loss": 0.8443,
|
| 1640 |
"step": 1120
|
| 1641 |
},
|
| 1642 |
{
|
| 1643 |
"epoch": 7.705479452054795,
|
| 1644 |
+
"grad_norm": 0.36328125,
|
| 1645 |
+
"learning_rate": 3.0396702729352023e-05,
|
| 1646 |
+
"loss": 0.841,
|
| 1647 |
"step": 1125
|
| 1648 |
},
|
| 1649 |
{
|
| 1650 |
"epoch": 7.739726027397261,
|
| 1651 |
+
"grad_norm": 0.353515625,
|
| 1652 |
+
"learning_rate": 2.9543365268667867e-05,
|
| 1653 |
+
"loss": 0.8482,
|
| 1654 |
"step": 1130
|
| 1655 |
},
|
| 1656 |
{
|
| 1657 |
"epoch": 7.773972602739726,
|
| 1658 |
+
"grad_norm": 0.349609375,
|
| 1659 |
+
"learning_rate": 2.8700096330544012e-05,
|
| 1660 |
+
"loss": 0.8388,
|
| 1661 |
"step": 1135
|
| 1662 |
},
|
| 1663 |
{
|
| 1664 |
"epoch": 7.808219178082192,
|
| 1665 |
+
"grad_norm": 0.3515625,
|
| 1666 |
+
"learning_rate": 2.7867016421336776e-05,
|
| 1667 |
+
"loss": 0.8486,
|
| 1668 |
"step": 1140
|
| 1669 |
},
|
| 1670 |
{
|
| 1671 |
"epoch": 7.842465753424658,
|
| 1672 |
+
"grad_norm": 0.34765625,
|
| 1673 |
+
"learning_rate": 2.7044244591351232e-05,
|
| 1674 |
+
"loss": 0.8453,
|
| 1675 |
"step": 1145
|
| 1676 |
},
|
| 1677 |
{
|
| 1678 |
"epoch": 7.876712328767123,
|
| 1679 |
+
"grad_norm": 0.36328125,
|
| 1680 |
+
"learning_rate": 2.6231898417828603e-05,
|
| 1681 |
+
"loss": 0.8358,
|
| 1682 |
"step": 1150
|
| 1683 |
},
|
| 1684 |
{
|
| 1685 |
"epoch": 7.910958904109589,
|
| 1686 |
+
"grad_norm": 0.35546875,
|
| 1687 |
+
"learning_rate": 2.5430093988143778e-05,
|
| 1688 |
+
"loss": 0.8344,
|
| 1689 |
"step": 1155
|
| 1690 |
},
|
| 1691 |
{
|
| 1692 |
"epoch": 7.945205479452055,
|
| 1693 |
+
"grad_norm": 0.35546875,
|
| 1694 |
+
"learning_rate": 2.4638945883216235e-05,
|
| 1695 |
+
"loss": 0.8312,
|
| 1696 |
"step": 1160
|
| 1697 |
},
|
| 1698 |
{
|
| 1699 |
"epoch": 7.97945205479452,
|
| 1700 |
+
"grad_norm": 0.35546875,
|
| 1701 |
+
"learning_rate": 2.385856716113587e-05,
|
| 1702 |
+
"loss": 0.8291,
|
| 1703 |
"step": 1165
|
| 1704 |
},
|
| 1705 |
{
|
| 1706 |
"epoch": 8.0,
|
| 1707 |
+
"eval_loss": 2.766744613647461,
|
| 1708 |
+
"eval_runtime": 0.5415,
|
| 1709 |
+
"eval_samples_per_second": 18.469,
|
| 1710 |
+
"eval_steps_per_second": 1.847,
|
| 1711 |
"step": 1168
|
| 1712 |
},
|
| 1713 |
{
|
| 1714 |
"epoch": 8.013698630136986,
|
| 1715 |
+
"grad_norm": 0.369140625,
|
| 1716 |
+
"learning_rate": 2.3089069341006565e-05,
|
| 1717 |
+
"loss": 0.8283,
|
| 1718 |
"step": 1170
|
| 1719 |
},
|
| 1720 |
{
|
| 1721 |
"epoch": 8.047945205479452,
|
| 1722 |
+
"grad_norm": 0.349609375,
|
| 1723 |
+
"learning_rate": 2.2330562387009745e-05,
|
| 1724 |
+
"loss": 0.8203,
|
| 1725 |
"step": 1175
|
| 1726 |
},
|
| 1727 |
{
|
| 1728 |
"epoch": 8.082191780821917,
|
| 1729 |
+
"grad_norm": 0.353515625,
|
| 1730 |
+
"learning_rate": 2.1583154692689976e-05,
|
| 1731 |
+
"loss": 0.8221,
|
| 1732 |
"step": 1180
|
| 1733 |
},
|
| 1734 |
{
|
| 1735 |
"epoch": 8.116438356164384,
|
| 1736 |
+
"grad_norm": 0.36328125,
|
| 1737 |
+
"learning_rate": 2.08469530654652e-05,
|
| 1738 |
+
"loss": 0.8256,
|
| 1739 |
"step": 1185
|
| 1740 |
},
|
| 1741 |
{
|
| 1742 |
"epoch": 8.150684931506849,
|
| 1743 |
+
"grad_norm": 0.36328125,
|
| 1744 |
+
"learning_rate": 2.0122062711363532e-05,
|
| 1745 |
+
"loss": 0.8139,
|
| 1746 |
"step": 1190
|
| 1747 |
},
|
| 1748 |
{
|
| 1749 |
"epoch": 8.184931506849315,
|
| 1750 |
+
"grad_norm": 0.357421875,
|
| 1751 |
+
"learning_rate": 1.9408587219988805e-05,
|
| 1752 |
+
"loss": 0.8351,
|
| 1753 |
"step": 1195
|
| 1754 |
},
|
| 1755 |
{
|
| 1756 |
"epoch": 8.219178082191782,
|
| 1757 |
+
"grad_norm": 0.359375,
|
| 1758 |
+
"learning_rate": 1.8706628549717452e-05,
|
| 1759 |
+
"loss": 0.8258,
|
| 1760 |
"step": 1200
|
| 1761 |
},
|
| 1762 |
{
|
| 1763 |
"epoch": 8.253424657534246,
|
| 1764 |
+
"grad_norm": 0.357421875,
|
| 1765 |
+
"learning_rate": 1.8016287013128018e-05,
|
| 1766 |
+
"loss": 0.8139,
|
| 1767 |
"step": 1205
|
| 1768 |
},
|
| 1769 |
{
|
| 1770 |
"epoch": 8.287671232876713,
|
| 1771 |
+
"grad_norm": 0.357421875,
|
| 1772 |
+
"learning_rate": 1.7337661262666294e-05,
|
| 1773 |
+
"loss": 0.8305,
|
| 1774 |
"step": 1210
|
| 1775 |
},
|
| 1776 |
{
|
| 1777 |
"epoch": 8.321917808219178,
|
| 1778 |
+
"grad_norm": 0.353515625,
|
| 1779 |
+
"learning_rate": 1.6670848276547334e-05,
|
| 1780 |
+
"loss": 0.8239,
|
| 1781 |
"step": 1215
|
| 1782 |
},
|
| 1783 |
{
|
| 1784 |
"epoch": 8.356164383561644,
|
| 1785 |
+
"grad_norm": 0.36328125,
|
| 1786 |
+
"learning_rate": 1.601594334489702e-05,
|
| 1787 |
+
"loss": 0.8252,
|
| 1788 |
"step": 1220
|
| 1789 |
},
|
| 1790 |
{
|
| 1791 |
"epoch": 8.39041095890411,
|
| 1792 |
+
"grad_norm": 0.36328125,
|
| 1793 |
+
"learning_rate": 1.5373040056134814e-05,
|
| 1794 |
+
"loss": 0.8194,
|
| 1795 |
"step": 1225
|
| 1796 |
},
|
| 1797 |
{
|
| 1798 |
"epoch": 8.424657534246576,
|
| 1799 |
+
"grad_norm": 0.359375,
|
| 1800 |
+
"learning_rate": 1.474223028359939e-05,
|
| 1801 |
+
"loss": 0.8188,
|
| 1802 |
"step": 1230
|
| 1803 |
},
|
| 1804 |
{
|
| 1805 |
"epoch": 8.45890410958904,
|
| 1806 |
+
"grad_norm": 0.359375,
|
| 1807 |
+
"learning_rate": 1.4123604172419713e-05,
|
| 1808 |
+
"loss": 0.8206,
|
| 1809 |
"step": 1235
|
| 1810 |
},
|
| 1811 |
{
|
| 1812 |
"epoch": 8.493150684931507,
|
| 1813 |
+
"grad_norm": 0.35546875,
|
| 1814 |
+
"learning_rate": 1.3517250126632986e-05,
|
| 1815 |
+
"loss": 0.8223,
|
| 1816 |
"step": 1240
|
| 1817 |
},
|
| 1818 |
{
|
| 1819 |
"epoch": 8.527397260273972,
|
| 1820 |
+
"grad_norm": 0.357421875,
|
| 1821 |
+
"learning_rate": 1.292325479655131e-05,
|
| 1822 |
+
"loss": 0.8257,
|
| 1823 |
"step": 1245
|
| 1824 |
},
|
| 1825 |
{
|
| 1826 |
"epoch": 8.561643835616438,
|
| 1827 |
+
"grad_norm": 0.349609375,
|
| 1828 |
+
"learning_rate": 1.2341703066379074e-05,
|
| 1829 |
+
"loss": 0.8239,
|
| 1830 |
"step": 1250
|
| 1831 |
},
|
| 1832 |
{
|
| 1833 |
"epoch": 8.595890410958905,
|
| 1834 |
+
"grad_norm": 0.345703125,
|
| 1835 |
+
"learning_rate": 1.1772678042082607e-05,
|
| 1836 |
+
"loss": 0.8173,
|
| 1837 |
"step": 1255
|
| 1838 |
},
|
| 1839 |
{
|
| 1840 |
"epoch": 8.63013698630137,
|
| 1841 |
+
"grad_norm": 0.357421875,
|
| 1842 |
+
"learning_rate": 1.1216261039514087e-05,
|
| 1843 |
+
"loss": 0.8266,
|
| 1844 |
"step": 1260
|
| 1845 |
},
|
| 1846 |
{
|
| 1847 |
"epoch": 8.664383561643836,
|
| 1848 |
+
"grad_norm": 0.3515625,
|
| 1849 |
+
"learning_rate": 1.0672531572791178e-05,
|
| 1850 |
+
"loss": 0.8237,
|
| 1851 |
"step": 1265
|
| 1852 |
},
|
| 1853 |
{
|
| 1854 |
"epoch": 8.698630136986301,
|
| 1855 |
+
"grad_norm": 0.359375,
|
| 1856 |
+
"learning_rate": 1.0141567342934132e-05,
|
| 1857 |
+
"loss": 0.8335,
|
| 1858 |
"step": 1270
|
| 1859 |
},
|
| 1860 |
{
|
| 1861 |
"epoch": 8.732876712328768,
|
| 1862 |
+
"grad_norm": 0.353515625,
|
| 1863 |
+
"learning_rate": 9.623444226762035e-06,
|
| 1864 |
+
"loss": 0.8239,
|
| 1865 |
"step": 1275
|
| 1866 |
},
|
| 1867 |
{
|
| 1868 |
"epoch": 8.767123287671232,
|
| 1869 |
+
"grad_norm": 0.353515625,
|
| 1870 |
+
"learning_rate": 9.118236266049707e-06,
|
| 1871 |
+
"loss": 0.8308,
|
| 1872 |
"step": 1280
|
| 1873 |
},
|
| 1874 |
{
|
| 1875 |
"epoch": 8.801369863013699,
|
| 1876 |
+
"grad_norm": 0.34765625,
|
| 1877 |
+
"learning_rate": 8.626015656946895e-06,
|
| 1878 |
+
"loss": 0.8266,
|
| 1879 |
"step": 1285
|
| 1880 |
},
|
| 1881 |
{
|
| 1882 |
"epoch": 8.835616438356164,
|
| 1883 |
+
"grad_norm": 0.341796875,
|
| 1884 |
+
"learning_rate": 8.146852739661105e-06,
|
| 1885 |
+
"loss": 0.8248,
|
| 1886 |
"step": 1290
|
| 1887 |
},
|
| 1888 |
{
|
| 1889 |
"epoch": 8.86986301369863,
|
| 1890 |
+
"grad_norm": 0.353515625,
|
| 1891 |
+
"learning_rate": 7.6808159884057e-06,
|
| 1892 |
+
"loss": 0.8322,
|
| 1893 |
"step": 1295
|
| 1894 |
},
|
| 1895 |
{
|
| 1896 |
"epoch": 8.904109589041095,
|
| 1897 |
+
"grad_norm": 0.349609375,
|
| 1898 |
+
"learning_rate": 7.2279720016148244e-06,
|
| 1899 |
+
"loss": 0.823,
|
| 1900 |
"step": 1300
|
| 1901 |
},
|
| 1902 |
{
|
| 1903 |
"epoch": 8.938356164383562,
|
| 1904 |
+
"grad_norm": 0.3515625,
|
| 1905 |
+
"learning_rate": 6.788385492426053e-06,
|
| 1906 |
+
"loss": 0.825,
|
| 1907 |
"step": 1305
|
| 1908 |
},
|
| 1909 |
{
|
| 1910 |
"epoch": 8.972602739726028,
|
| 1911 |
+
"grad_norm": 0.357421875,
|
| 1912 |
+
"learning_rate": 6.36211927943271e-06,
|
| 1913 |
+
"loss": 0.8286,
|
| 1914 |
"step": 1310
|
| 1915 |
},
|
| 1916 |
{
|
| 1917 |
"epoch": 9.0,
|
| 1918 |
+
"eval_loss": 2.7898991107940674,
|
| 1919 |
+
"eval_runtime": 0.5501,
|
| 1920 |
+
"eval_samples_per_second": 18.177,
|
| 1921 |
+
"eval_steps_per_second": 1.818,
|
| 1922 |
"step": 1314
|
| 1923 |
},
|
| 1924 |
{
|
| 1925 |
"epoch": 9.006849315068493,
|
| 1926 |
+
"grad_norm": 0.34765625,
|
| 1927 |
+
"learning_rate": 5.949234277706861e-06,
|
| 1928 |
+
"loss": 0.8231,
|
| 1929 |
"step": 1315
|
| 1930 |
},
|
| 1931 |
{
|
| 1932 |
"epoch": 9.04109589041096,
|
| 1933 |
+
"grad_norm": 0.349609375,
|
| 1934 |
+
"learning_rate": 5.549789490094304e-06,
|
| 1935 |
+
"loss": 0.8237,
|
| 1936 |
"step": 1320
|
| 1937 |
},
|
| 1938 |
{
|
| 1939 |
"epoch": 9.075342465753424,
|
| 1940 |
+
"grad_norm": 0.349609375,
|
| 1941 |
+
"learning_rate": 5.163841998782837e-06,
|
| 1942 |
+
"loss": 0.8125,
|
| 1943 |
"step": 1325
|
| 1944 |
},
|
| 1945 |
{
|
| 1946 |
"epoch": 9.10958904109589,
|
| 1947 |
+
"grad_norm": 0.34375,
|
| 1948 |
+
"learning_rate": 4.79144695714504e-06,
|
| 1949 |
+
"loss": 0.8179,
|
| 1950 |
"step": 1330
|
| 1951 |
},
|
| 1952 |
{
|
| 1953 |
"epoch": 9.143835616438356,
|
| 1954 |
+
"grad_norm": 0.34375,
|
| 1955 |
+
"learning_rate": 4.432657581856525e-06,
|
| 1956 |
+
"loss": 0.8173,
|
| 1957 |
"step": 1335
|
| 1958 |
},
|
| 1959 |
{
|
| 1960 |
"epoch": 9.178082191780822,
|
| 1961 |
+
"grad_norm": 0.37109375,
|
| 1962 |
+
"learning_rate": 4.087525145291204e-06,
|
| 1963 |
+
"loss": 0.8186,
|
| 1964 |
"step": 1340
|
| 1965 |
},
|
| 1966 |
{
|
| 1967 |
"epoch": 9.212328767123287,
|
| 1968 |
+
"grad_norm": 0.3515625,
|
| 1969 |
+
"learning_rate": 3.7560989681941992e-06,
|
| 1970 |
+
"loss": 0.8233,
|
| 1971 |
"step": 1345
|
| 1972 |
},
|
| 1973 |
{
|
| 1974 |
"epoch": 9.246575342465754,
|
| 1975 |
+
"grad_norm": 0.345703125,
|
| 1976 |
+
"learning_rate": 3.4384264126337328e-06,
|
| 1977 |
+
"loss": 0.8147,
|
| 1978 |
"step": 1350
|
| 1979 |
},
|
| 1980 |
{
|
| 1981 |
"epoch": 9.280821917808218,
|
| 1982 |
+
"grad_norm": 0.3515625,
|
| 1983 |
+
"learning_rate": 3.1345528752329212e-06,
|
| 1984 |
+
"loss": 0.8076,
|
| 1985 |
"step": 1355
|
| 1986 |
},
|
| 1987 |
{
|
| 1988 |
"epoch": 9.315068493150685,
|
| 1989 |
+
"grad_norm": 0.3515625,
|
| 1990 |
+
"learning_rate": 2.8445217806824077e-06,
|
| 1991 |
+
"loss": 0.8259,
|
| 1992 |
"step": 1360
|
| 1993 |
},
|
| 1994 |
{
|
| 1995 |
"epoch": 9.349315068493151,
|
| 1996 |
+
"grad_norm": 0.3515625,
|
| 1997 |
+
"learning_rate": 2.5683745755348044e-06,
|
| 1998 |
+
"loss": 0.819,
|
| 1999 |
"step": 1365
|
| 2000 |
},
|
| 2001 |
{
|
| 2002 |
"epoch": 9.383561643835616,
|
| 2003 |
+
"grad_norm": 0.361328125,
|
| 2004 |
+
"learning_rate": 2.30615072228183e-06,
|
| 2005 |
+
"loss": 0.8218,
|
| 2006 |
"step": 1370
|
| 2007 |
},
|
| 2008 |
{
|
| 2009 |
"epoch": 9.417808219178083,
|
| 2010 |
+
"grad_norm": 0.359375,
|
| 2011 |
+
"learning_rate": 2.057887693714988e-06,
|
| 2012 |
+
"loss": 0.8166,
|
| 2013 |
"step": 1375
|
| 2014 |
},
|
| 2015 |
{
|
| 2016 |
"epoch": 9.452054794520548,
|
| 2017 |
+
"grad_norm": 0.3515625,
|
| 2018 |
+
"learning_rate": 1.8236209675705274e-06,
|
| 2019 |
+
"loss": 0.815,
|
| 2020 |
"step": 1380
|
| 2021 |
},
|
| 2022 |
{
|
| 2023 |
"epoch": 9.486301369863014,
|
| 2024 |
+
"grad_norm": 0.3515625,
|
| 2025 |
+
"learning_rate": 1.6033840214595308e-06,
|
| 2026 |
+
"loss": 0.8287,
|
| 2027 |
"step": 1385
|
| 2028 |
},
|
| 2029 |
{
|
| 2030 |
"epoch": 9.520547945205479,
|
| 2031 |
+
"grad_norm": 0.349609375,
|
| 2032 |
+
"learning_rate": 1.397208328083921e-06,
|
| 2033 |
+
"loss": 0.8239,
|
| 2034 |
"step": 1390
|
| 2035 |
},
|
| 2036 |
{
|
| 2037 |
"epoch": 9.554794520547945,
|
| 2038 |
+
"grad_norm": 0.3515625,
|
| 2039 |
+
"learning_rate": 1.205123350738746e-06,
|
| 2040 |
+
"loss": 0.8238,
|
| 2041 |
"step": 1395
|
| 2042 |
},
|
| 2043 |
{
|
| 2044 |
"epoch": 9.58904109589041,
|
| 2045 |
+
"grad_norm": 0.34765625,
|
| 2046 |
+
"learning_rate": 1.0271565391018922e-06,
|
| 2047 |
+
"loss": 0.8231,
|
| 2048 |
"step": 1400
|
| 2049 |
},
|
| 2050 |
{
|
| 2051 |
"epoch": 9.623287671232877,
|
| 2052 |
+
"grad_norm": 0.361328125,
|
| 2053 |
+
"learning_rate": 8.633333253113995e-07,
|
| 2054 |
+
"loss": 0.8246,
|
| 2055 |
"step": 1405
|
| 2056 |
},
|
| 2057 |
{
|
| 2058 |
"epoch": 9.657534246575342,
|
| 2059 |
+
"grad_norm": 0.361328125,
|
| 2060 |
+
"learning_rate": 7.136771203310245e-07,
|
| 2061 |
+
"loss": 0.8131,
|
| 2062 |
"step": 1410
|
| 2063 |
},
|
| 2064 |
{
|
| 2065 |
"epoch": 9.691780821917808,
|
| 2066 |
+
"grad_norm": 0.3515625,
|
| 2067 |
+
"learning_rate": 5.782093106048159e-07,
|
| 2068 |
+
"loss": 0.8196,
|
| 2069 |
"step": 1415
|
| 2070 |
},
|
| 2071 |
{
|
| 2072 |
"epoch": 9.726027397260275,
|
| 2073 |
+
"grad_norm": 0.345703125,
|
| 2074 |
+
"learning_rate": 4.569492550008603e-07,
|
| 2075 |
+
"loss": 0.8097,
|
| 2076 |
"step": 1420
|
| 2077 |
},
|
| 2078 |
{
|
| 2079 |
"epoch": 9.76027397260274,
|
| 2080 |
+
"grad_norm": 0.36328125,
|
| 2081 |
+
"learning_rate": 3.49914282044872e-07,
|
| 2082 |
+
"loss": 0.8272,
|
| 2083 |
"step": 1425
|
| 2084 |
},
|
| 2085 |
{
|
| 2086 |
"epoch": 9.794520547945206,
|
| 2087 |
+
"grad_norm": 0.365234375,
|
| 2088 |
+
"learning_rate": 2.5711968744382974e-07,
|
| 2089 |
+
"loss": 0.8285,
|
| 2090 |
"step": 1430
|
| 2091 |
},
|
| 2092 |
{
|
| 2093 |
"epoch": 9.82876712328767,
|
| 2094 |
+
"grad_norm": 0.353515625,
|
| 2095 |
+
"learning_rate": 1.7857873190019192e-07,
|
| 2096 |
+
"loss": 0.8323,
|
| 2097 |
"step": 1435
|
| 2098 |
},
|
| 2099 |
{
|
| 2100 |
"epoch": 9.863013698630137,
|
| 2101 |
+
"grad_norm": 0.359375,
|
| 2102 |
+
"learning_rate": 1.143026392168789e-07,
|
| 2103 |
+
"loss": 0.822,
|
| 2104 |
"step": 1440
|
| 2105 |
},
|
| 2106 |
{
|
| 2107 |
"epoch": 9.897260273972602,
|
| 2108 |
+
"grad_norm": 0.353515625,
|
| 2109 |
+
"learning_rate": 6.430059469334504e-08,
|
| 2110 |
+
"loss": 0.8329,
|
| 2111 |
"step": 1445
|
| 2112 |
},
|
| 2113 |
{
|
| 2114 |
"epoch": 9.931506849315069,
|
| 2115 |
+
"grad_norm": 0.349609375,
|
| 2116 |
+
"learning_rate": 2.8579743813006432e-08,
|
| 2117 |
+
"loss": 0.8213,
|
| 2118 |
"step": 1450
|
| 2119 |
},
|
| 2120 |
{
|
| 2121 |
"epoch": 9.965753424657533,
|
| 2122 |
+
"grad_norm": 0.35546875,
|
| 2123 |
+
"learning_rate": 7.145191222035497e-09,
|
| 2124 |
+
"loss": 0.8169,
|
| 2125 |
"step": 1455
|
| 2126 |
},
|
| 2127 |
{
|
| 2128 |
"epoch": 10.0,
|
| 2129 |
+
"grad_norm": 0.35546875,
|
| 2130 |
+
"learning_rate": 0.0,
|
| 2131 |
+
"loss": 0.8185,
|
| 2132 |
"step": 1460
|
| 2133 |
},
|
| 2134 |
{
|
| 2135 |
"epoch": 10.0,
|
| 2136 |
+
"eval_loss": 2.793144464492798,
|
| 2137 |
+
"eval_runtime": 0.5503,
|
| 2138 |
+
"eval_samples_per_second": 18.172,
|
| 2139 |
+
"eval_steps_per_second": 1.817,
|
| 2140 |
"step": 1460
|
| 2141 |
},
|
| 2142 |
{
|
| 2143 |
+
"epoch": 10.0,
|
| 2144 |
+
"step": 1460,
|
| 2145 |
+
"total_flos": 8.702314001108828e+17,
|
| 2146 |
+
"train_loss": 0.9981180969982931,
|
| 2147 |
+
"train_runtime": 8741.0304,
|
| 2148 |
+
"train_samples_per_second": 8.01,
|
| 2149 |
+
"train_steps_per_second": 0.167
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2150 |
}
|
| 2151 |
],
|
| 2152 |
"logging_steps": 5,
|
|
|
|
| 2166 |
"attributes": {}
|
| 2167 |
}
|
| 2168 |
},
|
| 2169 |
+
"total_flos": 8.702314001108828e+17,
|
| 2170 |
"train_batch_size": 8,
|
| 2171 |
"trial_name": null,
|
| 2172 |
"trial_params": null
|