Commit
•
1351c5e
1
Parent(s):
20ccb4e
Model save
Browse files- README.md +3 -9
- all_results.json +4 -9
- model.safetensors +1 -1
- runs/May23_11-12-30_nova.cs.ucla.edu/events.out.tfevents.1716488476.nova.cs.ucla.edu.3155979.0 +2 -2
- train_results.json +4 -4
- trainer_state.json +602 -560
README.md
CHANGED
|
@@ -2,15 +2,9 @@
|
|
| 2 |
license: apache-2.0
|
| 3 |
base_model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
|
| 4 |
tags:
|
| 5 |
-
- alignment-handbook
|
| 6 |
- trl
|
| 7 |
- sft
|
| 8 |
- generated_from_trainer
|
| 9 |
-
- trl
|
| 10 |
-
- sft
|
| 11 |
-
- generated_from_trainer
|
| 12 |
-
datasets:
|
| 13 |
-
- yihanwang617/vicuna_sub_random_90k
|
| 14 |
model-index:
|
| 15 |
- name: tinyllama-sft-vicuna-random-100k
|
| 16 |
results: []
|
|
@@ -21,9 +15,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 21 |
|
| 22 |
# tinyllama-sft-vicuna-random-100k
|
| 23 |
|
| 24 |
-
This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T](https://huggingface.co/TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T) on the
|
| 25 |
It achieves the following results on the evaluation set:
|
| 26 |
-
- Loss: 0.
|
| 27 |
|
| 28 |
## Model description
|
| 29 |
|
|
@@ -60,7 +54,7 @@ The following hyperparameters were used during training:
|
|
| 60 |
|
| 61 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 62 |
|:-------------:|:-----:|:----:|:---------------:|
|
| 63 |
-
| 0.
|
| 64 |
|
| 65 |
|
| 66 |
### Framework versions
|
|
|
|
| 2 |
license: apache-2.0
|
| 3 |
base_model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
|
| 4 |
tags:
|
|
|
|
| 5 |
- trl
|
| 6 |
- sft
|
| 7 |
- generated_from_trainer
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8 |
model-index:
|
| 9 |
- name: tinyllama-sft-vicuna-random-100k
|
| 10 |
results: []
|
|
|
|
| 15 |
|
| 16 |
# tinyllama-sft-vicuna-random-100k
|
| 17 |
|
| 18 |
+
This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T](https://huggingface.co/TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T) on the None dataset.
|
| 19 |
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 0.7457
|
| 21 |
|
| 22 |
## Model description
|
| 23 |
|
|
|
|
| 54 |
|
| 55 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 56 |
|:-------------:|:-----:|:----:|:---------------:|
|
| 57 |
+
| 0.7119 | 1.0 | 732 | 0.7457 |
|
| 58 |
|
| 59 |
|
| 60 |
### Framework versions
|
all_results.json
CHANGED
|
@@ -1,13 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 1.0,
|
| 3 |
-
"
|
| 4 |
-
"
|
| 5 |
-
"
|
| 6 |
-
"
|
| 7 |
-
"eval_steps_per_second": 1.706,
|
| 8 |
-
"train_loss": 0.7627222812701425,
|
| 9 |
-
"train_runtime": 5862.0034,
|
| 10 |
-
"train_samples": 90000,
|
| 11 |
-
"train_samples_per_second": 15.353,
|
| 12 |
"train_steps_per_second": 0.12
|
| 13 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 1.0,
|
| 3 |
+
"train_loss": 0.7605658245216953,
|
| 4 |
+
"train_runtime": 6107.4706,
|
| 5 |
+
"train_samples": 93645,
|
| 6 |
+
"train_samples_per_second": 15.333,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7 |
"train_steps_per_second": 0.12
|
| 8 |
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2200128056
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5d0197f1a149140d509ffbf302f0286558ce76bdb854a11da9fa7dbd7c272e00
|
| 3 |
size 2200128056
|
runs/May23_11-12-30_nova.cs.ucla.edu/events.out.tfevents.1716488476.nova.cs.ucla.edu.3155979.0
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:f976b8f25f6b4f39d3eedd1db9255eb3b558ddfe8016fa26e48fbe454ae8bf8c
|
| 3 |
+
size 36405
|
train_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 1.0,
|
| 3 |
-
"train_loss": 0.
|
| 4 |
-
"train_runtime":
|
| 5 |
-
"train_samples":
|
| 6 |
-
"train_samples_per_second": 15.
|
| 7 |
"train_steps_per_second": 0.12
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 1.0,
|
| 3 |
+
"train_loss": 0.7605658245216953,
|
| 4 |
+
"train_runtime": 6107.4706,
|
| 5 |
+
"train_samples": 93645,
|
| 6 |
+
"train_samples_per_second": 15.333,
|
| 7 |
"train_steps_per_second": 0.12
|
| 8 |
}
|
trainer_state.json
CHANGED
|
@@ -1,1024 +1,1066 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch": 0
|
| 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": 0.0,
|
| 13 |
-
"grad_norm":
|
| 14 |
-
"learning_rate": 2.
|
| 15 |
-
"loss": 1.
|
| 16 |
"step": 1
|
| 17 |
},
|
| 18 |
{
|
| 19 |
"epoch": 0.01,
|
| 20 |
-
"grad_norm": 9.
|
| 21 |
-
"learning_rate": 1.
|
| 22 |
-
"loss": 1.
|
| 23 |
"step": 5
|
| 24 |
},
|
| 25 |
{
|
| 26 |
"epoch": 0.01,
|
| 27 |
-
"grad_norm":
|
| 28 |
-
"learning_rate": 2.
|
| 29 |
-
"loss": 1.
|
| 30 |
"step": 10
|
| 31 |
},
|
| 32 |
{
|
| 33 |
"epoch": 0.02,
|
| 34 |
-
"grad_norm":
|
| 35 |
-
"learning_rate": 4.
|
| 36 |
-
"loss": 1.
|
| 37 |
"step": 15
|
| 38 |
},
|
| 39 |
{
|
| 40 |
"epoch": 0.03,
|
| 41 |
-
"grad_norm": 1.
|
| 42 |
-
"learning_rate": 5.
|
| 43 |
-
"loss": 0.
|
| 44 |
"step": 20
|
| 45 |
},
|
| 46 |
{
|
| 47 |
-
"epoch": 0.
|
| 48 |
-
"grad_norm":
|
| 49 |
-
"learning_rate":
|
| 50 |
-
"loss": 0.
|
| 51 |
"step": 25
|
| 52 |
},
|
| 53 |
{
|
| 54 |
"epoch": 0.04,
|
| 55 |
-
"grad_norm": 1.
|
| 56 |
-
"learning_rate": 8.
|
| 57 |
-
"loss": 0.
|
| 58 |
"step": 30
|
| 59 |
},
|
| 60 |
{
|
| 61 |
"epoch": 0.05,
|
| 62 |
-
"grad_norm": 0.
|
| 63 |
-
"learning_rate": 9.
|
| 64 |
-
"loss": 0.
|
| 65 |
"step": 35
|
| 66 |
},
|
| 67 |
{
|
| 68 |
-
"epoch": 0.
|
| 69 |
-
"grad_norm": 0.
|
| 70 |
-
"learning_rate": 1.
|
| 71 |
-
"loss": 0.
|
| 72 |
"step": 40
|
| 73 |
},
|
| 74 |
{
|
| 75 |
"epoch": 0.06,
|
| 76 |
-
"grad_norm": 0.
|
| 77 |
-
"learning_rate": 1.
|
| 78 |
-
"loss": 0.
|
| 79 |
"step": 45
|
| 80 |
},
|
| 81 |
{
|
| 82 |
"epoch": 0.07,
|
| 83 |
-
"grad_norm": 0.
|
| 84 |
-
"learning_rate": 1.
|
| 85 |
-
"loss": 0.
|
| 86 |
"step": 50
|
| 87 |
},
|
| 88 |
{
|
| 89 |
"epoch": 0.08,
|
| 90 |
-
"grad_norm": 0.
|
| 91 |
-
"learning_rate": 1.
|
| 92 |
-
"loss": 0.
|
| 93 |
"step": 55
|
| 94 |
},
|
| 95 |
{
|
| 96 |
-
"epoch": 0.
|
| 97 |
-
"grad_norm": 0.
|
| 98 |
-
"learning_rate": 1.
|
| 99 |
-
"loss": 0.
|
| 100 |
"step": 60
|
| 101 |
},
|
| 102 |
{
|
| 103 |
"epoch": 0.09,
|
| 104 |
-
"grad_norm": 0.
|
| 105 |
-
"learning_rate": 1.
|
| 106 |
-
"loss": 0.
|
| 107 |
"step": 65
|
| 108 |
},
|
| 109 |
{
|
| 110 |
"epoch": 0.1,
|
| 111 |
-
"grad_norm": 0.
|
| 112 |
-
"learning_rate": 1.
|
| 113 |
-
"loss": 0.
|
| 114 |
"step": 70
|
| 115 |
},
|
| 116 |
{
|
| 117 |
-
"epoch": 0.
|
| 118 |
-
"grad_norm": 0.
|
| 119 |
-
"learning_rate": 1.
|
| 120 |
-
"loss": 0.
|
| 121 |
"step": 75
|
| 122 |
},
|
| 123 |
{
|
| 124 |
"epoch": 0.11,
|
| 125 |
-
"grad_norm": 0.
|
| 126 |
-
"learning_rate": 1.
|
| 127 |
-
"loss": 0.
|
| 128 |
"step": 80
|
| 129 |
},
|
| 130 |
{
|
| 131 |
"epoch": 0.12,
|
| 132 |
-
"grad_norm": 0.
|
| 133 |
-
"learning_rate": 1.
|
| 134 |
-
"loss": 0.
|
| 135 |
"step": 85
|
| 136 |
},
|
| 137 |
{
|
| 138 |
-
"epoch": 0.
|
| 139 |
-
"grad_norm": 0.
|
| 140 |
-
"learning_rate": 1.
|
| 141 |
-
"loss": 0.
|
| 142 |
"step": 90
|
| 143 |
},
|
| 144 |
{
|
| 145 |
-
"epoch": 0.
|
| 146 |
-
"grad_norm": 0.
|
| 147 |
-
"learning_rate": 1.
|
| 148 |
-
"loss": 0.
|
| 149 |
"step": 95
|
| 150 |
},
|
| 151 |
{
|
| 152 |
"epoch": 0.14,
|
| 153 |
-
"grad_norm": 0.
|
| 154 |
-
"learning_rate": 1.
|
| 155 |
-
"loss": 0.
|
| 156 |
"step": 100
|
| 157 |
},
|
| 158 |
{
|
| 159 |
-
"epoch": 0.
|
| 160 |
-
"grad_norm": 0.
|
| 161 |
-
"learning_rate": 1.
|
| 162 |
-
"loss": 0.
|
| 163 |
"step": 105
|
| 164 |
},
|
| 165 |
{
|
| 166 |
-
"epoch": 0.
|
| 167 |
-
"grad_norm": 0.
|
| 168 |
-
"learning_rate": 1.
|
| 169 |
-
"loss": 0.
|
| 170 |
"step": 110
|
| 171 |
},
|
| 172 |
{
|
| 173 |
"epoch": 0.16,
|
| 174 |
-
"grad_norm": 0.
|
| 175 |
-
"learning_rate": 1.
|
| 176 |
-
"loss": 0.
|
| 177 |
"step": 115
|
| 178 |
},
|
| 179 |
{
|
| 180 |
-
"epoch": 0.
|
| 181 |
-
"grad_norm": 0.
|
| 182 |
-
"learning_rate": 1.
|
| 183 |
-
"loss": 0.
|
| 184 |
"step": 120
|
| 185 |
},
|
| 186 |
{
|
| 187 |
-
"epoch": 0.
|
| 188 |
-
"grad_norm": 0.
|
| 189 |
-
"learning_rate": 1.
|
| 190 |
-
"loss": 0.
|
| 191 |
"step": 125
|
| 192 |
},
|
| 193 |
{
|
| 194 |
"epoch": 0.18,
|
| 195 |
-
"grad_norm": 0.
|
| 196 |
-
"learning_rate": 1.
|
| 197 |
-
"loss": 0.
|
| 198 |
"step": 130
|
| 199 |
},
|
| 200 |
{
|
| 201 |
-
"epoch": 0.
|
| 202 |
-
"grad_norm": 0.
|
| 203 |
-
"learning_rate": 1.
|
| 204 |
-
"loss": 0.
|
| 205 |
"step": 135
|
| 206 |
},
|
| 207 |
{
|
| 208 |
-
"epoch": 0.
|
| 209 |
-
"grad_norm": 0.
|
| 210 |
-
"learning_rate": 1.
|
| 211 |
-
"loss": 0.
|
| 212 |
"step": 140
|
| 213 |
},
|
| 214 |
{
|
| 215 |
-
"epoch": 0.
|
| 216 |
-
"grad_norm": 0.
|
| 217 |
-
"learning_rate": 1.
|
| 218 |
-
"loss": 0.
|
| 219 |
"step": 145
|
| 220 |
},
|
| 221 |
{
|
| 222 |
-
"epoch": 0.
|
| 223 |
-
"grad_norm": 0.
|
| 224 |
-
"learning_rate": 1.
|
| 225 |
-
"loss": 0.
|
| 226 |
"step": 150
|
| 227 |
},
|
| 228 |
{
|
| 229 |
-
"epoch": 0.
|
| 230 |
-
"grad_norm": 0.
|
| 231 |
-
"learning_rate": 1.
|
| 232 |
-
"loss": 0.
|
| 233 |
"step": 155
|
| 234 |
},
|
| 235 |
{
|
| 236 |
-
"epoch": 0.
|
| 237 |
-
"grad_norm": 0.
|
| 238 |
-
"learning_rate": 1.
|
| 239 |
-
"loss": 0.
|
| 240 |
"step": 160
|
| 241 |
},
|
| 242 |
{
|
| 243 |
"epoch": 0.23,
|
| 244 |
-
"grad_norm": 0.
|
| 245 |
-
"learning_rate": 1.
|
| 246 |
-
"loss": 0.
|
| 247 |
"step": 165
|
| 248 |
},
|
| 249 |
{
|
| 250 |
-
"epoch": 0.
|
| 251 |
-
"grad_norm": 0.
|
| 252 |
-
"learning_rate": 1.
|
| 253 |
-
"loss": 0.
|
| 254 |
"step": 170
|
| 255 |
},
|
| 256 |
{
|
| 257 |
-
"epoch": 0.
|
| 258 |
-
"grad_norm": 0.
|
| 259 |
-
"learning_rate": 1.
|
| 260 |
-
"loss": 0.
|
| 261 |
"step": 175
|
| 262 |
},
|
| 263 |
{
|
| 264 |
-
"epoch": 0.
|
| 265 |
-
"grad_norm": 0.
|
| 266 |
-
"learning_rate": 1.
|
| 267 |
-
"loss": 0.
|
| 268 |
"step": 180
|
| 269 |
},
|
| 270 |
{
|
| 271 |
-
"epoch": 0.
|
| 272 |
-
"grad_norm": 0.
|
| 273 |
-
"learning_rate": 1.
|
| 274 |
-
"loss": 0.
|
| 275 |
"step": 185
|
| 276 |
},
|
| 277 |
{
|
| 278 |
-
"epoch": 0.
|
| 279 |
-
"grad_norm": 0.
|
| 280 |
-
"learning_rate": 1.
|
| 281 |
-
"loss": 0.
|
| 282 |
"step": 190
|
| 283 |
},
|
| 284 |
{
|
| 285 |
-
"epoch": 0.
|
| 286 |
-
"grad_norm": 0.
|
| 287 |
-
"learning_rate": 1.
|
| 288 |
-
"loss": 0.
|
| 289 |
"step": 195
|
| 290 |
},
|
| 291 |
{
|
| 292 |
-
"epoch": 0.
|
| 293 |
-
"grad_norm": 0.
|
| 294 |
-
"learning_rate": 1.
|
| 295 |
-
"loss": 0.
|
| 296 |
"step": 200
|
| 297 |
},
|
| 298 |
{
|
| 299 |
-
"epoch": 0.
|
| 300 |
-
"grad_norm": 0.
|
| 301 |
-
"learning_rate": 1.
|
| 302 |
-
"loss": 0.
|
| 303 |
"step": 205
|
| 304 |
},
|
| 305 |
{
|
| 306 |
-
"epoch": 0.
|
| 307 |
-
"grad_norm": 0.
|
| 308 |
-
"learning_rate": 1.
|
| 309 |
-
"loss": 0.
|
| 310 |
"step": 210
|
| 311 |
},
|
| 312 |
{
|
| 313 |
-
"epoch": 0.
|
| 314 |
-
"grad_norm": 0.
|
| 315 |
-
"learning_rate": 1.
|
| 316 |
-
"loss": 0.
|
| 317 |
"step": 215
|
| 318 |
},
|
| 319 |
{
|
| 320 |
-
"epoch": 0.
|
| 321 |
-
"grad_norm": 0.
|
| 322 |
-
"learning_rate": 1.
|
| 323 |
-
"loss": 0.
|
| 324 |
"step": 220
|
| 325 |
},
|
| 326 |
{
|
| 327 |
-
"epoch": 0.
|
| 328 |
-
"grad_norm": 0.
|
| 329 |
-
"learning_rate": 1.
|
| 330 |
-
"loss": 0.
|
| 331 |
"step": 225
|
| 332 |
},
|
| 333 |
{
|
| 334 |
-
"epoch": 0.
|
| 335 |
-
"grad_norm": 0.
|
| 336 |
-
"learning_rate": 1.
|
| 337 |
-
"loss": 0.
|
| 338 |
"step": 230
|
| 339 |
},
|
| 340 |
{
|
| 341 |
-
"epoch": 0.
|
| 342 |
-
"grad_norm": 0.
|
| 343 |
-
"learning_rate": 1.
|
| 344 |
-
"loss": 0.
|
| 345 |
"step": 235
|
| 346 |
},
|
| 347 |
{
|
| 348 |
-
"epoch": 0.
|
| 349 |
-
"grad_norm": 0.
|
| 350 |
-
"learning_rate": 1.
|
| 351 |
-
"loss": 0.
|
| 352 |
"step": 240
|
| 353 |
},
|
| 354 |
{
|
| 355 |
-
"epoch": 0.
|
| 356 |
-
"grad_norm": 0.
|
| 357 |
-
"learning_rate": 1.
|
| 358 |
-
"loss": 0.
|
| 359 |
"step": 245
|
| 360 |
},
|
| 361 |
{
|
| 362 |
-
"epoch": 0.
|
| 363 |
-
"grad_norm": 0.
|
| 364 |
-
"learning_rate": 1.
|
| 365 |
-
"loss": 0.
|
| 366 |
"step": 250
|
| 367 |
},
|
| 368 |
{
|
| 369 |
-
"epoch": 0.
|
| 370 |
-
"grad_norm": 0.
|
| 371 |
-
"learning_rate": 1.
|
| 372 |
-
"loss": 0.
|
| 373 |
"step": 255
|
| 374 |
},
|
| 375 |
{
|
| 376 |
-
"epoch": 0.
|
| 377 |
-
"grad_norm": 0.
|
| 378 |
-
"learning_rate": 1.
|
| 379 |
-
"loss": 0.
|
| 380 |
"step": 260
|
| 381 |
},
|
| 382 |
{
|
| 383 |
-
"epoch": 0.
|
| 384 |
-
"grad_norm": 0.
|
| 385 |
-
"learning_rate": 1.
|
| 386 |
-
"loss": 0.
|
| 387 |
"step": 265
|
| 388 |
},
|
| 389 |
{
|
| 390 |
-
"epoch": 0.
|
| 391 |
-
"grad_norm": 0.
|
| 392 |
-
"learning_rate": 1.
|
| 393 |
-
"loss": 0.
|
| 394 |
"step": 270
|
| 395 |
},
|
| 396 |
{
|
| 397 |
-
"epoch": 0.
|
| 398 |
-
"grad_norm": 0.
|
| 399 |
-
"learning_rate": 1.
|
| 400 |
-
"loss": 0.
|
| 401 |
"step": 275
|
| 402 |
},
|
| 403 |
{
|
| 404 |
-
"epoch": 0.
|
| 405 |
-
"grad_norm": 0.
|
| 406 |
-
"learning_rate": 1.
|
| 407 |
-
"loss": 0.
|
| 408 |
"step": 280
|
| 409 |
},
|
| 410 |
{
|
| 411 |
-
"epoch": 0.
|
| 412 |
-
"grad_norm": 0.
|
| 413 |
-
"learning_rate": 1.
|
| 414 |
-
"loss": 0.
|
| 415 |
"step": 285
|
| 416 |
},
|
| 417 |
{
|
| 418 |
-
"epoch": 0.
|
| 419 |
-
"grad_norm": 0.
|
| 420 |
-
"learning_rate": 1.
|
| 421 |
-
"loss": 0.
|
| 422 |
"step": 290
|
| 423 |
},
|
| 424 |
{
|
| 425 |
-
"epoch": 0.
|
| 426 |
-
"grad_norm": 0.
|
| 427 |
-
"learning_rate": 1.
|
| 428 |
-
"loss": 0.
|
| 429 |
"step": 295
|
| 430 |
},
|
| 431 |
{
|
| 432 |
-
"epoch": 0.
|
| 433 |
-
"grad_norm": 0.
|
| 434 |
-
"learning_rate": 1.
|
| 435 |
-
"loss": 0.
|
| 436 |
"step": 300
|
| 437 |
},
|
| 438 |
{
|
| 439 |
-
"epoch": 0.
|
| 440 |
-
"grad_norm": 0.
|
| 441 |
-
"learning_rate": 1.
|
| 442 |
-
"loss": 0.
|
| 443 |
"step": 305
|
| 444 |
},
|
| 445 |
{
|
| 446 |
-
"epoch": 0.
|
| 447 |
-
"grad_norm": 0.
|
| 448 |
-
"learning_rate": 1.
|
| 449 |
-
"loss": 0.
|
| 450 |
"step": 310
|
| 451 |
},
|
| 452 |
{
|
| 453 |
-
"epoch": 0.
|
| 454 |
-
"grad_norm": 0.
|
| 455 |
-
"learning_rate": 1.
|
| 456 |
-
"loss": 0.
|
| 457 |
"step": 315
|
| 458 |
},
|
| 459 |
{
|
| 460 |
-
"epoch": 0.
|
| 461 |
-
"grad_norm": 0.
|
| 462 |
-
"learning_rate": 1.
|
| 463 |
-
"loss": 0.
|
| 464 |
"step": 320
|
| 465 |
},
|
| 466 |
{
|
| 467 |
-
"epoch": 0.
|
| 468 |
-
"grad_norm": 0.
|
| 469 |
-
"learning_rate": 1.
|
| 470 |
-
"loss": 0.
|
| 471 |
"step": 325
|
| 472 |
},
|
| 473 |
{
|
| 474 |
-
"epoch": 0.
|
| 475 |
-
"grad_norm": 0.
|
| 476 |
-
"learning_rate": 1.
|
| 477 |
-
"loss": 0.
|
| 478 |
"step": 330
|
| 479 |
},
|
| 480 |
{
|
| 481 |
-
"epoch": 0.
|
| 482 |
-
"grad_norm": 0.
|
| 483 |
-
"learning_rate": 1.
|
| 484 |
-
"loss": 0.
|
| 485 |
"step": 335
|
| 486 |
},
|
| 487 |
{
|
| 488 |
-
"epoch": 0.
|
| 489 |
-
"grad_norm": 0.
|
| 490 |
-
"learning_rate": 1.
|
| 491 |
-
"loss": 0.
|
| 492 |
"step": 340
|
| 493 |
},
|
| 494 |
{
|
| 495 |
-
"epoch": 0.
|
| 496 |
-
"grad_norm": 0.
|
| 497 |
-
"learning_rate": 1.
|
| 498 |
-
"loss": 0.
|
| 499 |
"step": 345
|
| 500 |
},
|
| 501 |
{
|
| 502 |
-
"epoch": 0.
|
| 503 |
-
"grad_norm": 0.
|
| 504 |
-
"learning_rate": 1.
|
| 505 |
-
"loss": 0.
|
| 506 |
"step": 350
|
| 507 |
},
|
| 508 |
{
|
| 509 |
-
"epoch": 0.
|
| 510 |
-
"grad_norm": 0.
|
| 511 |
-
"learning_rate": 1.
|
| 512 |
-
"loss": 0.
|
| 513 |
"step": 355
|
| 514 |
},
|
| 515 |
{
|
| 516 |
-
"epoch": 0.
|
| 517 |
-
"grad_norm": 0.
|
| 518 |
-
"learning_rate": 1.
|
| 519 |
-
"loss": 0.
|
| 520 |
"step": 360
|
| 521 |
},
|
| 522 |
{
|
| 523 |
-
"epoch": 0.
|
| 524 |
-
"grad_norm": 0.
|
| 525 |
-
"learning_rate": 1.
|
| 526 |
-
"loss": 0.
|
| 527 |
"step": 365
|
| 528 |
},
|
| 529 |
{
|
| 530 |
-
"epoch": 0.
|
| 531 |
-
"grad_norm": 0.
|
| 532 |
-
"learning_rate": 1.
|
| 533 |
-
"loss": 0.
|
| 534 |
"step": 370
|
| 535 |
},
|
| 536 |
{
|
| 537 |
-
"epoch": 0.
|
| 538 |
-
"grad_norm": 0.
|
| 539 |
-
"learning_rate": 1.
|
| 540 |
-
"loss": 0.
|
| 541 |
"step": 375
|
| 542 |
},
|
| 543 |
{
|
| 544 |
-
"epoch": 0.
|
| 545 |
-
"grad_norm": 0.
|
| 546 |
-
"learning_rate": 1.
|
| 547 |
-
"loss": 0.
|
| 548 |
"step": 380
|
| 549 |
},
|
| 550 |
{
|
| 551 |
-
"epoch": 0.
|
| 552 |
-
"grad_norm": 0.
|
| 553 |
-
"learning_rate": 1.
|
| 554 |
-
"loss": 0.
|
| 555 |
"step": 385
|
| 556 |
},
|
| 557 |
{
|
| 558 |
-
"epoch": 0.
|
| 559 |
-
"grad_norm": 0.
|
| 560 |
-
"learning_rate":
|
| 561 |
-
"loss": 0.
|
| 562 |
"step": 390
|
| 563 |
},
|
| 564 |
{
|
| 565 |
-
"epoch": 0.
|
| 566 |
-
"grad_norm": 0.
|
| 567 |
-
"learning_rate":
|
| 568 |
-
"loss": 0.
|
| 569 |
"step": 395
|
| 570 |
},
|
| 571 |
{
|
| 572 |
-
"epoch": 0.
|
| 573 |
-
"grad_norm": 0.
|
| 574 |
-
"learning_rate":
|
| 575 |
-
"loss": 0.
|
| 576 |
"step": 400
|
| 577 |
},
|
| 578 |
{
|
| 579 |
-
"epoch": 0.
|
| 580 |
-
"grad_norm": 0.
|
| 581 |
-
"learning_rate": 9.
|
| 582 |
-
"loss": 0.
|
| 583 |
"step": 405
|
| 584 |
},
|
| 585 |
{
|
| 586 |
-
"epoch": 0.
|
| 587 |
-
"grad_norm": 0.
|
| 588 |
-
"learning_rate":
|
| 589 |
-
"loss": 0.
|
| 590 |
"step": 410
|
| 591 |
},
|
| 592 |
{
|
| 593 |
-
"epoch": 0.
|
| 594 |
-
"grad_norm": 0.
|
| 595 |
-
"learning_rate":
|
| 596 |
-
"loss": 0.
|
| 597 |
"step": 415
|
| 598 |
},
|
| 599 |
{
|
| 600 |
-
"epoch": 0.
|
| 601 |
-
"grad_norm": 0.
|
| 602 |
-
"learning_rate":
|
| 603 |
-
"loss": 0.
|
| 604 |
"step": 420
|
| 605 |
},
|
| 606 |
{
|
| 607 |
-
"epoch": 0.
|
| 608 |
-
"grad_norm": 0.
|
| 609 |
-
"learning_rate": 8.
|
| 610 |
-
"loss": 0.
|
| 611 |
"step": 425
|
| 612 |
},
|
| 613 |
{
|
| 614 |
-
"epoch": 0.
|
| 615 |
-
"grad_norm": 0.
|
| 616 |
-
"learning_rate":
|
| 617 |
-
"loss": 0.
|
| 618 |
"step": 430
|
| 619 |
},
|
| 620 |
{
|
| 621 |
-
"epoch": 0.
|
| 622 |
-
"grad_norm": 0.
|
| 623 |
-
"learning_rate":
|
| 624 |
-
"loss": 0.
|
| 625 |
"step": 435
|
| 626 |
},
|
| 627 |
{
|
| 628 |
-
"epoch": 0.
|
| 629 |
-
"grad_norm": 0.
|
| 630 |
-
"learning_rate":
|
| 631 |
-
"loss": 0.
|
| 632 |
"step": 440
|
| 633 |
},
|
| 634 |
{
|
| 635 |
-
"epoch": 0.
|
| 636 |
-
"grad_norm": 0.
|
| 637 |
-
"learning_rate":
|
| 638 |
-
"loss": 0.
|
| 639 |
"step": 445
|
| 640 |
},
|
| 641 |
{
|
| 642 |
-
"epoch": 0.
|
| 643 |
-
"grad_norm": 0.
|
| 644 |
-
"learning_rate":
|
| 645 |
-
"loss": 0.
|
| 646 |
"step": 450
|
| 647 |
},
|
| 648 |
{
|
| 649 |
-
"epoch": 0.
|
| 650 |
-
"grad_norm": 0.
|
| 651 |
-
"learning_rate":
|
| 652 |
-
"loss": 0.
|
| 653 |
"step": 455
|
| 654 |
},
|
| 655 |
{
|
| 656 |
-
"epoch": 0.
|
| 657 |
-
"grad_norm": 0.
|
| 658 |
-
"learning_rate":
|
| 659 |
-
"loss": 0.
|
| 660 |
"step": 460
|
| 661 |
},
|
| 662 |
{
|
| 663 |
-
"epoch": 0.
|
| 664 |
-
"grad_norm": 0.
|
| 665 |
-
"learning_rate":
|
| 666 |
-
"loss": 0.
|
| 667 |
"step": 465
|
| 668 |
},
|
| 669 |
{
|
| 670 |
-
"epoch": 0.
|
| 671 |
-
"grad_norm": 0.
|
| 672 |
-
"learning_rate":
|
| 673 |
-
"loss": 0.
|
| 674 |
"step": 470
|
| 675 |
},
|
| 676 |
{
|
| 677 |
-
"epoch": 0.
|
| 678 |
-
"grad_norm": 0.
|
| 679 |
-
"learning_rate":
|
| 680 |
-
"loss": 0.
|
| 681 |
"step": 475
|
| 682 |
},
|
| 683 |
{
|
| 684 |
-
"epoch": 0.
|
| 685 |
-
"grad_norm": 0.
|
| 686 |
-
"learning_rate":
|
| 687 |
-
"loss": 0.
|
| 688 |
"step": 480
|
| 689 |
},
|
| 690 |
{
|
| 691 |
-
"epoch": 0.
|
| 692 |
-
"grad_norm": 0.
|
| 693 |
-
"learning_rate":
|
| 694 |
-
"loss": 0.
|
| 695 |
"step": 485
|
| 696 |
},
|
| 697 |
{
|
| 698 |
-
"epoch": 0.
|
| 699 |
-
"grad_norm": 0.
|
| 700 |
-
"learning_rate": 5.
|
| 701 |
-
"loss": 0.
|
| 702 |
"step": 490
|
| 703 |
},
|
| 704 |
{
|
| 705 |
-
"epoch": 0.
|
| 706 |
-
"grad_norm": 0.
|
| 707 |
-
"learning_rate":
|
| 708 |
-
"loss": 0.
|
| 709 |
"step": 495
|
| 710 |
},
|
| 711 |
{
|
| 712 |
-
"epoch": 0.
|
| 713 |
-
"grad_norm": 0.
|
| 714 |
-
"learning_rate":
|
| 715 |
-
"loss": 0.
|
| 716 |
"step": 500
|
| 717 |
},
|
| 718 |
{
|
| 719 |
-
"epoch": 0.
|
| 720 |
-
"grad_norm": 0.
|
| 721 |
-
"learning_rate":
|
| 722 |
-
"loss": 0.
|
| 723 |
"step": 505
|
| 724 |
},
|
| 725 |
{
|
| 726 |
-
"epoch": 0.
|
| 727 |
-
"grad_norm": 0.
|
| 728 |
-
"learning_rate":
|
| 729 |
-
"loss": 0.
|
| 730 |
"step": 510
|
| 731 |
},
|
| 732 |
{
|
| 733 |
-
"epoch": 0.
|
| 734 |
-
"grad_norm": 0.
|
| 735 |
-
"learning_rate": 4.
|
| 736 |
-
"loss": 0.
|
| 737 |
"step": 515
|
| 738 |
},
|
| 739 |
{
|
| 740 |
-
"epoch": 0.
|
| 741 |
-
"grad_norm": 0.
|
| 742 |
-
"learning_rate":
|
| 743 |
-
"loss": 0.
|
| 744 |
"step": 520
|
| 745 |
},
|
| 746 |
{
|
| 747 |
-
"epoch": 0.
|
| 748 |
-
"grad_norm": 0.
|
| 749 |
-
"learning_rate":
|
| 750 |
-
"loss": 0.
|
| 751 |
"step": 525
|
| 752 |
},
|
| 753 |
{
|
| 754 |
-
"epoch": 0.
|
| 755 |
-
"grad_norm": 0.
|
| 756 |
-
"learning_rate":
|
| 757 |
-
"loss": 0.
|
| 758 |
"step": 530
|
| 759 |
},
|
| 760 |
{
|
| 761 |
-
"epoch": 0.
|
| 762 |
-
"grad_norm": 0.
|
| 763 |
-
"learning_rate":
|
| 764 |
-
"loss": 0.
|
| 765 |
"step": 535
|
| 766 |
},
|
| 767 |
{
|
| 768 |
-
"epoch": 0.
|
| 769 |
-
"grad_norm": 0.
|
| 770 |
-
"learning_rate": 3.
|
| 771 |
-
"loss": 0.
|
| 772 |
"step": 540
|
| 773 |
},
|
| 774 |
{
|
| 775 |
-
"epoch": 0.
|
| 776 |
-
"grad_norm": 0.
|
| 777 |
-
"learning_rate":
|
| 778 |
-
"loss": 0.
|
| 779 |
"step": 545
|
| 780 |
},
|
| 781 |
{
|
| 782 |
-
"epoch": 0.
|
| 783 |
-
"grad_norm": 0.
|
| 784 |
-
"learning_rate":
|
| 785 |
-
"loss": 0.
|
| 786 |
"step": 550
|
| 787 |
},
|
| 788 |
{
|
| 789 |
-
"epoch": 0.
|
| 790 |
-
"grad_norm": 0.
|
| 791 |
-
"learning_rate":
|
| 792 |
-
"loss": 0.
|
| 793 |
"step": 555
|
| 794 |
},
|
| 795 |
{
|
| 796 |
-
"epoch": 0.
|
| 797 |
-
"grad_norm": 0.
|
| 798 |
-
"learning_rate":
|
| 799 |
-
"loss": 0.
|
| 800 |
"step": 560
|
| 801 |
},
|
| 802 |
{
|
| 803 |
-
"epoch": 0.
|
| 804 |
-
"grad_norm": 0.
|
| 805 |
-
"learning_rate":
|
| 806 |
-
"loss": 0.
|
| 807 |
"step": 565
|
| 808 |
},
|
| 809 |
{
|
| 810 |
-
"epoch": 0.
|
| 811 |
-
"grad_norm": 0.
|
| 812 |
-
"learning_rate": 2.
|
| 813 |
-
"loss": 0.
|
| 814 |
"step": 570
|
| 815 |
},
|
| 816 |
{
|
| 817 |
-
"epoch": 0.
|
| 818 |
-
"grad_norm": 0.
|
| 819 |
-
"learning_rate":
|
| 820 |
-
"loss": 0.
|
| 821 |
"step": 575
|
| 822 |
},
|
| 823 |
{
|
| 824 |
-
"epoch": 0.
|
| 825 |
-
"grad_norm": 0.
|
| 826 |
-
"learning_rate":
|
| 827 |
-
"loss": 0.
|
| 828 |
"step": 580
|
| 829 |
},
|
| 830 |
{
|
| 831 |
-
"epoch": 0.
|
| 832 |
-
"grad_norm": 0.
|
| 833 |
-
"learning_rate":
|
| 834 |
-
"loss": 0.
|
| 835 |
"step": 585
|
| 836 |
},
|
| 837 |
{
|
| 838 |
-
"epoch": 0.
|
| 839 |
-
"grad_norm": 0.
|
| 840 |
-
"learning_rate":
|
| 841 |
-
"loss": 0.
|
| 842 |
"step": 590
|
| 843 |
},
|
| 844 |
{
|
| 845 |
-
"epoch": 0.
|
| 846 |
-
"grad_norm": 0.
|
| 847 |
-
"learning_rate":
|
| 848 |
-
"loss": 0.
|
| 849 |
"step": 595
|
| 850 |
},
|
| 851 |
{
|
| 852 |
-
"epoch": 0.
|
| 853 |
-
"grad_norm": 0.
|
| 854 |
-
"learning_rate": 1.
|
| 855 |
-
"loss": 0.
|
| 856 |
"step": 600
|
| 857 |
},
|
| 858 |
{
|
| 859 |
-
"epoch": 0.
|
| 860 |
-
"grad_norm": 0.
|
| 861 |
-
"learning_rate": 1.
|
| 862 |
-
"loss": 0.
|
| 863 |
"step": 605
|
| 864 |
},
|
| 865 |
{
|
| 866 |
-
"epoch": 0.
|
| 867 |
-
"grad_norm": 0.
|
| 868 |
-
"learning_rate": 1.
|
| 869 |
-
"loss": 0.
|
| 870 |
"step": 610
|
| 871 |
},
|
| 872 |
{
|
| 873 |
-
"epoch": 0.
|
| 874 |
-
"grad_norm": 0.
|
| 875 |
-
"learning_rate":
|
| 876 |
-
"loss": 0.
|
| 877 |
"step": 615
|
| 878 |
},
|
| 879 |
{
|
| 880 |
-
"epoch": 0.
|
| 881 |
-
"grad_norm": 0.
|
| 882 |
-
"learning_rate":
|
| 883 |
-
"loss": 0.
|
| 884 |
"step": 620
|
| 885 |
},
|
| 886 |
{
|
| 887 |
-
"epoch": 0.
|
| 888 |
-
"grad_norm": 0.
|
| 889 |
-
"learning_rate":
|
| 890 |
-
"loss": 0.
|
| 891 |
"step": 625
|
| 892 |
},
|
| 893 |
{
|
| 894 |
-
"epoch": 0.
|
| 895 |
-
"grad_norm": 0.
|
| 896 |
-
"learning_rate":
|
| 897 |
-
"loss": 0.
|
| 898 |
"step": 630
|
| 899 |
},
|
| 900 |
{
|
| 901 |
-
"epoch": 0.
|
| 902 |
-
"grad_norm": 0.
|
| 903 |
-
"learning_rate":
|
| 904 |
-
"loss": 0.
|
| 905 |
"step": 635
|
| 906 |
},
|
| 907 |
{
|
| 908 |
-
"epoch": 0.
|
| 909 |
-
"grad_norm": 0.
|
| 910 |
-
"learning_rate":
|
| 911 |
-
"loss": 0.
|
| 912 |
"step": 640
|
| 913 |
},
|
| 914 |
{
|
| 915 |
-
"epoch": 0.
|
| 916 |
-
"grad_norm": 0.
|
| 917 |
-
"learning_rate":
|
| 918 |
-
"loss": 0.
|
| 919 |
"step": 645
|
| 920 |
},
|
| 921 |
{
|
| 922 |
-
"epoch": 0.
|
| 923 |
-
"grad_norm": 0.
|
| 924 |
-
"learning_rate":
|
| 925 |
-
"loss": 0.
|
| 926 |
"step": 650
|
| 927 |
},
|
| 928 |
{
|
| 929 |
-
"epoch": 0.
|
| 930 |
-
"grad_norm": 0.
|
| 931 |
-
"learning_rate":
|
| 932 |
-
"loss": 0.
|
| 933 |
"step": 655
|
| 934 |
},
|
| 935 |
{
|
| 936 |
-
"epoch": 0.
|
| 937 |
-
"grad_norm": 0.
|
| 938 |
-
"learning_rate":
|
| 939 |
-
"loss": 0.
|
| 940 |
"step": 660
|
| 941 |
},
|
| 942 |
{
|
| 943 |
-
"epoch": 0.
|
| 944 |
-
"grad_norm": 0.
|
| 945 |
-
"learning_rate":
|
| 946 |
-
"loss": 0.
|
| 947 |
"step": 665
|
| 948 |
},
|
| 949 |
{
|
| 950 |
-
"epoch": 0.
|
| 951 |
-
"grad_norm": 0.
|
| 952 |
-
"learning_rate":
|
| 953 |
-
"loss": 0.
|
| 954 |
"step": 670
|
| 955 |
},
|
| 956 |
{
|
| 957 |
-
"epoch": 0.
|
| 958 |
-
"grad_norm": 0.
|
| 959 |
-
"learning_rate":
|
| 960 |
-
"loss": 0.
|
| 961 |
"step": 675
|
| 962 |
},
|
| 963 |
{
|
| 964 |
-
"epoch": 0.
|
| 965 |
-
"grad_norm": 0.
|
| 966 |
-
"learning_rate":
|
| 967 |
-
"loss": 0.
|
| 968 |
"step": 680
|
| 969 |
},
|
| 970 |
{
|
| 971 |
-
"epoch": 0.
|
| 972 |
-
"grad_norm": 0.
|
| 973 |
-
"learning_rate":
|
| 974 |
-
"loss": 0.
|
| 975 |
"step": 685
|
| 976 |
},
|
| 977 |
{
|
| 978 |
-
"epoch": 0.
|
| 979 |
-
"grad_norm": 0.
|
| 980 |
-
"learning_rate": 2.
|
| 981 |
-
"loss": 0.
|
| 982 |
"step": 690
|
| 983 |
},
|
| 984 |
{
|
| 985 |
-
"epoch": 0.
|
| 986 |
-
"grad_norm": 0.
|
| 987 |
-
"learning_rate":
|
| 988 |
-
"loss": 0.
|
| 989 |
"step": 695
|
| 990 |
},
|
| 991 |
{
|
| 992 |
-
"epoch":
|
| 993 |
-
"grad_norm": 0.
|
| 994 |
-
"learning_rate": 1.
|
| 995 |
-
"loss": 0.
|
| 996 |
"step": 700
|
| 997 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 998 |
{
|
| 999 |
"epoch": 1.0,
|
| 1000 |
-
"eval_loss": 0.
|
| 1001 |
-
"eval_runtime": 9.
|
| 1002 |
-
"eval_samples_per_second": 52.
|
| 1003 |
-
"eval_steps_per_second": 1.
|
| 1004 |
-
"step":
|
| 1005 |
},
|
| 1006 |
{
|
| 1007 |
"epoch": 1.0,
|
| 1008 |
-
"step":
|
| 1009 |
-
"total_flos":
|
| 1010 |
-
"train_loss": 0.
|
| 1011 |
-
"train_runtime":
|
| 1012 |
-
"train_samples_per_second": 15.
|
| 1013 |
"train_steps_per_second": 0.12
|
| 1014 |
}
|
| 1015 |
],
|
| 1016 |
"logging_steps": 5,
|
| 1017 |
-
"max_steps":
|
| 1018 |
"num_input_tokens_seen": 0,
|
| 1019 |
"num_train_epochs": 1,
|
| 1020 |
"save_steps": 100,
|
| 1021 |
-
"total_flos":
|
| 1022 |
"train_batch_size": 16,
|
| 1023 |
"trial_name": null,
|
| 1024 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.0,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 732,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 0.0,
|
| 13 |
+
"grad_norm": 9.08570438897306,
|
| 14 |
+
"learning_rate": 2.702702702702703e-07,
|
| 15 |
+
"loss": 1.1396,
|
| 16 |
"step": 1
|
| 17 |
},
|
| 18 |
{
|
| 19 |
"epoch": 0.01,
|
| 20 |
+
"grad_norm": 9.679962246384667,
|
| 21 |
+
"learning_rate": 1.3513513513513515e-06,
|
| 22 |
+
"loss": 1.1779,
|
| 23 |
"step": 5
|
| 24 |
},
|
| 25 |
{
|
| 26 |
"epoch": 0.01,
|
| 27 |
+
"grad_norm": 10.102509592240429,
|
| 28 |
+
"learning_rate": 2.702702702702703e-06,
|
| 29 |
+
"loss": 1.1318,
|
| 30 |
"step": 10
|
| 31 |
},
|
| 32 |
{
|
| 33 |
"epoch": 0.02,
|
| 34 |
+
"grad_norm": 2.9319421528072973,
|
| 35 |
+
"learning_rate": 4.0540540540540545e-06,
|
| 36 |
+
"loss": 1.0028,
|
| 37 |
"step": 15
|
| 38 |
},
|
| 39 |
{
|
| 40 |
"epoch": 0.03,
|
| 41 |
+
"grad_norm": 1.3759757212785226,
|
| 42 |
+
"learning_rate": 5.405405405405406e-06,
|
| 43 |
+
"loss": 0.926,
|
| 44 |
"step": 20
|
| 45 |
},
|
| 46 |
{
|
| 47 |
+
"epoch": 0.03,
|
| 48 |
+
"grad_norm": 0.9504372792893874,
|
| 49 |
+
"learning_rate": 6.7567567567567575e-06,
|
| 50 |
+
"loss": 0.9044,
|
| 51 |
"step": 25
|
| 52 |
},
|
| 53 |
{
|
| 54 |
"epoch": 0.04,
|
| 55 |
+
"grad_norm": 1.2271132587175222,
|
| 56 |
+
"learning_rate": 8.108108108108109e-06,
|
| 57 |
+
"loss": 0.8775,
|
| 58 |
"step": 30
|
| 59 |
},
|
| 60 |
{
|
| 61 |
"epoch": 0.05,
|
| 62 |
+
"grad_norm": 0.8247319038566833,
|
| 63 |
+
"learning_rate": 9.45945945945946e-06,
|
| 64 |
+
"loss": 0.868,
|
| 65 |
"step": 35
|
| 66 |
},
|
| 67 |
{
|
| 68 |
+
"epoch": 0.05,
|
| 69 |
+
"grad_norm": 0.6839207898039522,
|
| 70 |
+
"learning_rate": 1.0810810810810812e-05,
|
| 71 |
+
"loss": 0.8626,
|
| 72 |
"step": 40
|
| 73 |
},
|
| 74 |
{
|
| 75 |
"epoch": 0.06,
|
| 76 |
+
"grad_norm": 0.6459463481231297,
|
| 77 |
+
"learning_rate": 1.2162162162162164e-05,
|
| 78 |
+
"loss": 0.8454,
|
| 79 |
"step": 45
|
| 80 |
},
|
| 81 |
{
|
| 82 |
"epoch": 0.07,
|
| 83 |
+
"grad_norm": 0.5903349665251353,
|
| 84 |
+
"learning_rate": 1.3513513513513515e-05,
|
| 85 |
+
"loss": 0.8437,
|
| 86 |
"step": 50
|
| 87 |
},
|
| 88 |
{
|
| 89 |
"epoch": 0.08,
|
| 90 |
+
"grad_norm": 0.5948338223404456,
|
| 91 |
+
"learning_rate": 1.4864864864864865e-05,
|
| 92 |
+
"loss": 0.8353,
|
| 93 |
"step": 55
|
| 94 |
},
|
| 95 |
{
|
| 96 |
+
"epoch": 0.08,
|
| 97 |
+
"grad_norm": 0.5895070475596026,
|
| 98 |
+
"learning_rate": 1.6216216216216218e-05,
|
| 99 |
+
"loss": 0.8222,
|
| 100 |
"step": 60
|
| 101 |
},
|
| 102 |
{
|
| 103 |
"epoch": 0.09,
|
| 104 |
+
"grad_norm": 0.6066852387492704,
|
| 105 |
+
"learning_rate": 1.756756756756757e-05,
|
| 106 |
+
"loss": 0.8144,
|
| 107 |
"step": 65
|
| 108 |
},
|
| 109 |
{
|
| 110 |
"epoch": 0.1,
|
| 111 |
+
"grad_norm": 0.602310053600098,
|
| 112 |
+
"learning_rate": 1.891891891891892e-05,
|
| 113 |
+
"loss": 0.821,
|
| 114 |
"step": 70
|
| 115 |
},
|
| 116 |
{
|
| 117 |
+
"epoch": 0.1,
|
| 118 |
+
"grad_norm": 0.5621279417664072,
|
| 119 |
+
"learning_rate": 1.999988602302209e-05,
|
| 120 |
+
"loss": 0.8133,
|
| 121 |
"step": 75
|
| 122 |
},
|
| 123 |
{
|
| 124 |
"epoch": 0.11,
|
| 125 |
+
"grad_norm": 0.6630630012402627,
|
| 126 |
+
"learning_rate": 1.9995897101594454e-05,
|
| 127 |
+
"loss": 0.8334,
|
| 128 |
"step": 80
|
| 129 |
},
|
| 130 |
{
|
| 131 |
"epoch": 0.12,
|
| 132 |
+
"grad_norm": 0.6077906778917731,
|
| 133 |
+
"learning_rate": 1.99862119291555e-05,
|
| 134 |
+
"loss": 0.804,
|
| 135 |
"step": 85
|
| 136 |
},
|
| 137 |
{
|
| 138 |
+
"epoch": 0.12,
|
| 139 |
+
"grad_norm": 0.5618472092387999,
|
| 140 |
+
"learning_rate": 1.997083602488702e-05,
|
| 141 |
+
"loss": 0.8193,
|
| 142 |
"step": 90
|
| 143 |
},
|
| 144 |
{
|
| 145 |
+
"epoch": 0.13,
|
| 146 |
+
"grad_norm": 0.6333601185724956,
|
| 147 |
+
"learning_rate": 1.994977815088504e-05,
|
| 148 |
+
"loss": 0.7945,
|
| 149 |
"step": 95
|
| 150 |
},
|
| 151 |
{
|
| 152 |
"epoch": 0.14,
|
| 153 |
+
"grad_norm": 0.6001887764474764,
|
| 154 |
+
"learning_rate": 1.9923050307166655e-05,
|
| 155 |
+
"loss": 0.8079,
|
| 156 |
"step": 100
|
| 157 |
},
|
| 158 |
{
|
| 159 |
+
"epoch": 0.14,
|
| 160 |
+
"grad_norm": 0.6114725172341102,
|
| 161 |
+
"learning_rate": 1.989066772483171e-05,
|
| 162 |
+
"loss": 0.8063,
|
| 163 |
"step": 105
|
| 164 |
},
|
| 165 |
{
|
| 166 |
+
"epoch": 0.15,
|
| 167 |
+
"grad_norm": 0.6410224419207078,
|
| 168 |
+
"learning_rate": 1.9852648857383224e-05,
|
| 169 |
+
"loss": 0.8079,
|
| 170 |
"step": 110
|
| 171 |
},
|
| 172 |
{
|
| 173 |
"epoch": 0.16,
|
| 174 |
+
"grad_norm": 0.6155008789371026,
|
| 175 |
+
"learning_rate": 1.9809015370211505e-05,
|
| 176 |
+
"loss": 0.8012,
|
| 177 |
"step": 115
|
| 178 |
},
|
| 179 |
{
|
| 180 |
+
"epoch": 0.16,
|
| 181 |
+
"grad_norm": 0.5701298765644415,
|
| 182 |
+
"learning_rate": 1.9759792128247922e-05,
|
| 183 |
+
"loss": 0.7858,
|
| 184 |
"step": 120
|
| 185 |
},
|
| 186 |
{
|
| 187 |
+
"epoch": 0.17,
|
| 188 |
+
"grad_norm": 0.5769994850814212,
|
| 189 |
+
"learning_rate": 1.9705007181795416e-05,
|
| 190 |
+
"loss": 0.7949,
|
| 191 |
"step": 125
|
| 192 |
},
|
| 193 |
{
|
| 194 |
"epoch": 0.18,
|
| 195 |
+
"grad_norm": 0.5989802045117304,
|
| 196 |
+
"learning_rate": 1.964469175054377e-05,
|
| 197 |
+
"loss": 0.7912,
|
| 198 |
"step": 130
|
| 199 |
},
|
| 200 |
{
|
| 201 |
+
"epoch": 0.18,
|
| 202 |
+
"grad_norm": 0.6158332171463875,
|
| 203 |
+
"learning_rate": 1.9578880205778793e-05,
|
| 204 |
+
"loss": 0.8,
|
| 205 |
"step": 135
|
| 206 |
},
|
| 207 |
{
|
| 208 |
+
"epoch": 0.19,
|
| 209 |
+
"grad_norm": 0.6045880045462032,
|
| 210 |
+
"learning_rate": 1.950761005079556e-05,
|
| 211 |
+
"loss": 0.7831,
|
| 212 |
"step": 140
|
| 213 |
},
|
| 214 |
{
|
| 215 |
+
"epoch": 0.2,
|
| 216 |
+
"grad_norm": 0.6022037882647541,
|
| 217 |
+
"learning_rate": 1.9430921899526786e-05,
|
| 218 |
+
"loss": 0.7967,
|
| 219 |
"step": 145
|
| 220 |
},
|
| 221 |
{
|
| 222 |
+
"epoch": 0.2,
|
| 223 |
+
"grad_norm": 0.5703057672919921,
|
| 224 |
+
"learning_rate": 1.934885945339865e-05,
|
| 225 |
+
"loss": 0.7851,
|
| 226 |
"step": 150
|
| 227 |
},
|
| 228 |
{
|
| 229 |
+
"epoch": 0.21,
|
| 230 |
+
"grad_norm": 0.5660007442989872,
|
| 231 |
+
"learning_rate": 1.9261469476427122e-05,
|
| 232 |
+
"loss": 0.7699,
|
| 233 |
"step": 155
|
| 234 |
},
|
| 235 |
{
|
| 236 |
+
"epoch": 0.22,
|
| 237 |
+
"grad_norm": 0.6052031318507304,
|
| 238 |
+
"learning_rate": 1.916880176856909e-05,
|
| 239 |
+
"loss": 0.787,
|
| 240 |
"step": 160
|
| 241 |
},
|
| 242 |
{
|
| 243 |
"epoch": 0.23,
|
| 244 |
+
"grad_norm": 0.5691776960805929,
|
| 245 |
+
"learning_rate": 1.907090913734341e-05,
|
| 246 |
+
"loss": 0.7851,
|
| 247 |
"step": 165
|
| 248 |
},
|
| 249 |
{
|
| 250 |
+
"epoch": 0.23,
|
| 251 |
+
"grad_norm": 0.6074889597948341,
|
| 252 |
+
"learning_rate": 1.896784736773805e-05,
|
| 253 |
+
"loss": 0.7753,
|
| 254 |
"step": 170
|
| 255 |
},
|
| 256 |
{
|
| 257 |
+
"epoch": 0.24,
|
| 258 |
+
"grad_norm": 0.5860864302531827,
|
| 259 |
+
"learning_rate": 1.885967519042054e-05,
|
| 260 |
+
"loss": 0.7871,
|
| 261 |
"step": 175
|
| 262 |
},
|
| 263 |
{
|
| 264 |
+
"epoch": 0.25,
|
| 265 |
+
"grad_norm": 0.569482390256513,
|
| 266 |
+
"learning_rate": 1.8746454248269777e-05,
|
| 267 |
+
"loss": 0.7601,
|
| 268 |
"step": 180
|
| 269 |
},
|
| 270 |
{
|
| 271 |
+
"epoch": 0.25,
|
| 272 |
+
"grad_norm": 0.5854282191729411,
|
| 273 |
+
"learning_rate": 1.862824906124826e-05,
|
| 274 |
+
"loss": 0.7819,
|
| 275 |
"step": 185
|
| 276 |
},
|
| 277 |
{
|
| 278 |
+
"epoch": 0.26,
|
| 279 |
+
"grad_norm": 0.6428086559905823,
|
| 280 |
+
"learning_rate": 1.850512698963485e-05,
|
| 281 |
+
"loss": 0.7831,
|
| 282 |
"step": 190
|
| 283 |
},
|
| 284 |
{
|
| 285 |
+
"epoch": 0.27,
|
| 286 |
+
"grad_norm": 0.5698221365710079,
|
| 287 |
+
"learning_rate": 1.8377158195638877e-05,
|
| 288 |
+
"loss": 0.7604,
|
| 289 |
"step": 195
|
| 290 |
},
|
| 291 |
{
|
| 292 |
+
"epoch": 0.27,
|
| 293 |
+
"grad_norm": 0.7373917549594062,
|
| 294 |
+
"learning_rate": 1.8244415603417603e-05,
|
| 295 |
+
"loss": 0.7587,
|
| 296 |
"step": 200
|
| 297 |
},
|
| 298 |
{
|
| 299 |
+
"epoch": 0.28,
|
| 300 |
+
"grad_norm": 0.585209211283403,
|
| 301 |
+
"learning_rate": 1.8106974857519737e-05,
|
| 302 |
+
"loss": 0.7804,
|
| 303 |
"step": 205
|
| 304 |
},
|
| 305 |
{
|
| 306 |
+
"epoch": 0.29,
|
| 307 |
+
"grad_norm": 0.6168183287266534,
|
| 308 |
+
"learning_rate": 1.7964914279778716e-05,
|
| 309 |
+
"loss": 0.7797,
|
| 310 |
"step": 210
|
| 311 |
},
|
| 312 |
{
|
| 313 |
+
"epoch": 0.29,
|
| 314 |
+
"grad_norm": 0.625316831394029,
|
| 315 |
+
"learning_rate": 1.78183148246803e-05,
|
| 316 |
+
"loss": 0.7583,
|
| 317 |
"step": 215
|
| 318 |
},
|
| 319 |
{
|
| 320 |
+
"epoch": 0.3,
|
| 321 |
+
"grad_norm": 0.5564471122778261,
|
| 322 |
+
"learning_rate": 1.7667260033229953e-05,
|
| 323 |
+
"loss": 0.7512,
|
| 324 |
"step": 220
|
| 325 |
},
|
| 326 |
{
|
| 327 |
+
"epoch": 0.31,
|
| 328 |
+
"grad_norm": 0.5890010216830359,
|
| 329 |
+
"learning_rate": 1.751183598534625e-05,
|
| 330 |
+
"loss": 0.7528,
|
| 331 |
"step": 225
|
| 332 |
},
|
| 333 |
{
|
| 334 |
+
"epoch": 0.31,
|
| 335 |
+
"grad_norm": 0.6009170802635413,
|
| 336 |
+
"learning_rate": 1.7352131250807466e-05,
|
| 337 |
+
"loss": 0.7626,
|
| 338 |
"step": 230
|
| 339 |
},
|
| 340 |
{
|
| 341 |
+
"epoch": 0.32,
|
| 342 |
+
"grad_norm": 0.5792443910657085,
|
| 343 |
+
"learning_rate": 1.7188236838779297e-05,
|
| 344 |
+
"loss": 0.7632,
|
| 345 |
"step": 235
|
| 346 |
},
|
| 347 |
{
|
| 348 |
+
"epoch": 0.33,
|
| 349 |
+
"grad_norm": 0.5716562571066842,
|
| 350 |
+
"learning_rate": 1.702024614595248e-05,
|
| 351 |
+
"loss": 0.7551,
|
| 352 |
"step": 240
|
| 353 |
},
|
| 354 |
{
|
| 355 |
+
"epoch": 0.33,
|
| 356 |
+
"grad_norm": 0.5703410316230326,
|
| 357 |
+
"learning_rate": 1.6848254903319866e-05,
|
| 358 |
+
"loss": 0.7427,
|
| 359 |
"step": 245
|
| 360 |
},
|
| 361 |
{
|
| 362 |
+
"epoch": 0.34,
|
| 363 |
+
"grad_norm": 0.6094207116793442,
|
| 364 |
+
"learning_rate": 1.6672361121623238e-05,
|
| 365 |
+
"loss": 0.7943,
|
| 366 |
"step": 250
|
| 367 |
},
|
| 368 |
{
|
| 369 |
+
"epoch": 0.35,
|
| 370 |
+
"grad_norm": 0.5915494337632395,
|
| 371 |
+
"learning_rate": 1.6492665035501048e-05,
|
| 372 |
+
"loss": 0.7373,
|
| 373 |
"step": 255
|
| 374 |
},
|
| 375 |
{
|
| 376 |
+
"epoch": 0.36,
|
| 377 |
+
"grad_norm": 0.5958263340568929,
|
| 378 |
+
"learning_rate": 1.6309269046368777e-05,
|
| 379 |
+
"loss": 0.7523,
|
| 380 |
"step": 260
|
| 381 |
},
|
| 382 |
{
|
| 383 |
+
"epoch": 0.36,
|
| 384 |
+
"grad_norm": 0.6569542499394689,
|
| 385 |
+
"learning_rate": 1.612227766406461e-05,
|
| 386 |
+
"loss": 0.755,
|
| 387 |
"step": 265
|
| 388 |
},
|
| 389 |
{
|
| 390 |
+
"epoch": 0.37,
|
| 391 |
+
"grad_norm": 0.5775231523651057,
|
| 392 |
+
"learning_rate": 1.5931797447293553e-05,
|
| 393 |
+
"loss": 0.7292,
|
| 394 |
"step": 270
|
| 395 |
},
|
| 396 |
{
|
| 397 |
+
"epoch": 0.38,
|
| 398 |
+
"grad_norm": 0.6322564996445303,
|
| 399 |
+
"learning_rate": 1.5737936942904025e-05,
|
| 400 |
+
"loss": 0.7476,
|
| 401 |
"step": 275
|
| 402 |
},
|
| 403 |
{
|
| 404 |
+
"epoch": 0.38,
|
| 405 |
+
"grad_norm": 0.5522985173213607,
|
| 406 |
+
"learning_rate": 1.554080662403144e-05,
|
| 407 |
+
"loss": 0.7427,
|
| 408 |
"step": 280
|
| 409 |
},
|
| 410 |
{
|
| 411 |
+
"epoch": 0.39,
|
| 412 |
+
"grad_norm": 0.6314561016931608,
|
| 413 |
+
"learning_rate": 1.5340518827144145e-05,
|
| 414 |
+
"loss": 0.7602,
|
| 415 |
"step": 285
|
| 416 |
},
|
| 417 |
{
|
| 418 |
+
"epoch": 0.4,
|
| 419 |
+
"grad_norm": 0.5865596324052452,
|
| 420 |
+
"learning_rate": 1.5137187688027437e-05,
|
| 421 |
+
"loss": 0.7496,
|
| 422 |
"step": 290
|
| 423 |
},
|
| 424 |
{
|
| 425 |
+
"epoch": 0.4,
|
| 426 |
+
"grad_norm": 0.5697597752265093,
|
| 427 |
+
"learning_rate": 1.4930929076742317e-05,
|
| 428 |
+
"loss": 0.7392,
|
| 429 |
"step": 295
|
| 430 |
},
|
| 431 |
{
|
| 432 |
+
"epoch": 0.41,
|
| 433 |
+
"grad_norm": 0.6129791987688828,
|
| 434 |
+
"learning_rate": 1.4721860531595868e-05,
|
| 435 |
+
"loss": 0.7537,
|
| 436 |
"step": 300
|
| 437 |
},
|
| 438 |
{
|
| 439 |
+
"epoch": 0.42,
|
| 440 |
+
"grad_norm": 0.5897396431474848,
|
| 441 |
+
"learning_rate": 1.451010119216102e-05,
|
| 442 |
+
"loss": 0.7583,
|
| 443 |
"step": 305
|
| 444 |
},
|
| 445 |
{
|
| 446 |
+
"epoch": 0.42,
|
| 447 |
+
"grad_norm": 0.5710567280058013,
|
| 448 |
+
"learning_rate": 1.4295771731383799e-05,
|
| 449 |
+
"loss": 0.7275,
|
| 450 |
"step": 310
|
| 451 |
},
|
| 452 |
{
|
| 453 |
+
"epoch": 0.43,
|
| 454 |
+
"grad_norm": 0.5953176828826594,
|
| 455 |
+
"learning_rate": 1.4078994286816768e-05,
|
| 456 |
+
"loss": 0.7453,
|
| 457 |
"step": 315
|
| 458 |
},
|
| 459 |
{
|
| 460 |
+
"epoch": 0.44,
|
| 461 |
+
"grad_norm": 0.6242032112691839,
|
| 462 |
+
"learning_rate": 1.3859892391017867e-05,
|
| 463 |
+
"loss": 0.7644,
|
| 464 |
"step": 320
|
| 465 |
},
|
| 466 |
{
|
| 467 |
+
"epoch": 0.44,
|
| 468 |
+
"grad_norm": 0.6014365104233058,
|
| 469 |
+
"learning_rate": 1.3638590901154276e-05,
|
| 470 |
+
"loss": 0.7532,
|
| 471 |
"step": 325
|
| 472 |
},
|
| 473 |
{
|
| 474 |
+
"epoch": 0.45,
|
| 475 |
+
"grad_norm": 0.5726135101483418,
|
| 476 |
+
"learning_rate": 1.341521592785145e-05,
|
| 477 |
+
"loss": 0.7663,
|
| 478 |
"step": 330
|
| 479 |
},
|
| 480 |
{
|
| 481 |
+
"epoch": 0.46,
|
| 482 |
+
"grad_norm": 0.6061053656685103,
|
| 483 |
+
"learning_rate": 1.3189894763327851e-05,
|
| 484 |
+
"loss": 0.7476,
|
| 485 |
"step": 335
|
| 486 |
},
|
| 487 |
{
|
| 488 |
+
"epoch": 0.46,
|
| 489 |
+
"grad_norm": 0.5910382927751472,
|
| 490 |
+
"learning_rate": 1.2962755808856341e-05,
|
| 491 |
+
"loss": 0.7418,
|
| 492 |
"step": 340
|
| 493 |
},
|
| 494 |
{
|
| 495 |
+
"epoch": 0.47,
|
| 496 |
+
"grad_norm": 0.6192359895872668,
|
| 497 |
+
"learning_rate": 1.2733928501593587e-05,
|
| 498 |
+
"loss": 0.7322,
|
| 499 |
"step": 345
|
| 500 |
},
|
| 501 |
{
|
| 502 |
+
"epoch": 0.48,
|
| 503 |
+
"grad_norm": 0.5754476677307057,
|
| 504 |
+
"learning_rate": 1.2503543240819127e-05,
|
| 505 |
+
"loss": 0.7505,
|
| 506 |
"step": 350
|
| 507 |
},
|
| 508 |
{
|
| 509 |
+
"epoch": 0.48,
|
| 510 |
+
"grad_norm": 0.5954914603467452,
|
| 511 |
+
"learning_rate": 1.227173131362619e-05,
|
| 512 |
+
"loss": 0.7316,
|
| 513 |
"step": 355
|
| 514 |
},
|
| 515 |
{
|
| 516 |
+
"epoch": 0.49,
|
| 517 |
+
"grad_norm": 0.636714901981685,
|
| 518 |
+
"learning_rate": 1.2038624820106572e-05,
|
| 519 |
+
"loss": 0.7483,
|
| 520 |
"step": 360
|
| 521 |
},
|
| 522 |
{
|
| 523 |
+
"epoch": 0.5,
|
| 524 |
+
"grad_norm": 0.5956828212931418,
|
| 525 |
+
"learning_rate": 1.1804356598072223e-05,
|
| 526 |
+
"loss": 0.7141,
|
| 527 |
"step": 365
|
| 528 |
},
|
| 529 |
{
|
| 530 |
+
"epoch": 0.51,
|
| 531 |
+
"grad_norm": 0.6438375663233106,
|
| 532 |
+
"learning_rate": 1.1569060147356441e-05,
|
| 533 |
+
"loss": 0.7589,
|
| 534 |
"step": 370
|
| 535 |
},
|
| 536 |
{
|
| 537 |
+
"epoch": 0.51,
|
| 538 |
+
"grad_norm": 0.5911783265386276,
|
| 539 |
+
"learning_rate": 1.133286955373779e-05,
|
| 540 |
+
"loss": 0.7485,
|
| 541 |
"step": 375
|
| 542 |
},
|
| 543 |
{
|
| 544 |
+
"epoch": 0.52,
|
| 545 |
+
"grad_norm": 0.5615839698644924,
|
| 546 |
+
"learning_rate": 1.1095919412530136e-05,
|
| 547 |
+
"loss": 0.75,
|
| 548 |
"step": 380
|
| 549 |
},
|
| 550 |
{
|
| 551 |
+
"epoch": 0.53,
|
| 552 |
+
"grad_norm": 0.5906964619382736,
|
| 553 |
+
"learning_rate": 1.0858344751882304e-05,
|
| 554 |
+
"loss": 0.7089,
|
| 555 |
"step": 385
|
| 556 |
},
|
| 557 |
{
|
| 558 |
+
"epoch": 0.53,
|
| 559 |
+
"grad_norm": 0.622095376177676,
|
| 560 |
+
"learning_rate": 1.0620280955831088e-05,
|
| 561 |
+
"loss": 0.7418,
|
| 562 |
"step": 390
|
| 563 |
},
|
| 564 |
{
|
| 565 |
+
"epoch": 0.54,
|
| 566 |
+
"grad_norm": 0.5629629729406987,
|
| 567 |
+
"learning_rate": 1.038186368715145e-05,
|
| 568 |
+
"loss": 0.7148,
|
| 569 |
"step": 395
|
| 570 |
},
|
| 571 |
{
|
| 572 |
+
"epoch": 0.55,
|
| 573 |
+
"grad_norm": 0.5596961155705783,
|
| 574 |
+
"learning_rate": 1.0143228810047877e-05,
|
| 575 |
+
"loss": 0.7226,
|
| 576 |
"step": 400
|
| 577 |
},
|
| 578 |
{
|
| 579 |
+
"epoch": 0.55,
|
| 580 |
+
"grad_norm": 0.5949479844701526,
|
| 581 |
+
"learning_rate": 9.904512312730948e-06,
|
| 582 |
+
"loss": 0.7446,
|
| 583 |
"step": 405
|
| 584 |
},
|
| 585 |
{
|
| 586 |
+
"epoch": 0.56,
|
| 587 |
+
"grad_norm": 0.5503557697571823,
|
| 588 |
+
"learning_rate": 9.665850229923258e-06,
|
| 589 |
+
"loss": 0.7294,
|
| 590 |
"step": 410
|
| 591 |
},
|
| 592 |
{
|
| 593 |
+
"epoch": 0.57,
|
| 594 |
+
"grad_norm": 0.5646735246212238,
|
| 595 |
+
"learning_rate": 9.4273785653388e-06,
|
| 596 |
+
"loss": 0.7399,
|
| 597 |
"step": 415
|
| 598 |
},
|
| 599 |
{
|
| 600 |
+
"epoch": 0.57,
|
| 601 |
+
"grad_norm": 0.6166612666135994,
|
| 602 |
+
"learning_rate": 9.189233214180057e-06,
|
| 603 |
+
"loss": 0.7464,
|
| 604 |
"step": 420
|
| 605 |
},
|
| 606 |
{
|
| 607 |
+
"epoch": 0.58,
|
| 608 |
+
"grad_norm": 0.6607877653922463,
|
| 609 |
+
"learning_rate": 8.951549885696889e-06,
|
| 610 |
+
"loss": 0.7104,
|
| 611 |
"step": 425
|
| 612 |
},
|
| 613 |
{
|
| 614 |
+
"epoch": 0.59,
|
| 615 |
+
"grad_norm": 0.5828440632986862,
|
| 616 |
+
"learning_rate": 8.714464025851428e-06,
|
| 617 |
+
"loss": 0.748,
|
| 618 |
"step": 430
|
| 619 |
},
|
| 620 |
{
|
| 621 |
+
"epoch": 0.59,
|
| 622 |
+
"grad_norm": 0.6692052000569471,
|
| 623 |
+
"learning_rate": 8.478110740132971e-06,
|
| 624 |
+
"loss": 0.7194,
|
| 625 |
"step": 435
|
| 626 |
},
|
| 627 |
{
|
| 628 |
+
"epoch": 0.6,
|
| 629 |
+
"grad_norm": 0.5925544656331848,
|
| 630 |
+
"learning_rate": 8.242624716566928e-06,
|
| 631 |
+
"loss": 0.7414,
|
| 632 |
"step": 440
|
| 633 |
},
|
| 634 |
{
|
| 635 |
+
"epoch": 0.61,
|
| 636 |
+
"grad_norm": 0.5681970472775137,
|
| 637 |
+
"learning_rate": 8.008140148961642e-06,
|
| 638 |
+
"loss": 0.7266,
|
| 639 |
"step": 445
|
| 640 |
},
|
| 641 |
{
|
| 642 |
+
"epoch": 0.61,
|
| 643 |
+
"grad_norm": 0.6022566260644191,
|
| 644 |
+
"learning_rate": 7.774790660436857e-06,
|
| 645 |
+
"loss": 0.7458,
|
| 646 |
"step": 450
|
| 647 |
},
|
| 648 |
{
|
| 649 |
+
"epoch": 0.62,
|
| 650 |
+
"grad_norm": 0.6280077977218962,
|
| 651 |
+
"learning_rate": 7.542709227277396e-06,
|
| 652 |
+
"loss": 0.7265,
|
| 653 |
"step": 455
|
| 654 |
},
|
| 655 |
{
|
| 656 |
+
"epoch": 0.63,
|
| 657 |
+
"grad_norm": 0.5662044508467975,
|
| 658 |
+
"learning_rate": 7.312028103155426e-06,
|
| 659 |
+
"loss": 0.7296,
|
| 660 |
"step": 460
|
| 661 |
},
|
| 662 |
{
|
| 663 |
+
"epoch": 0.64,
|
| 664 |
+
"grad_norm": 0.5875195935745249,
|
| 665 |
+
"learning_rate": 7.0828787437645455e-06,
|
| 666 |
+
"loss": 0.7666,
|
| 667 |
"step": 465
|
| 668 |
},
|
| 669 |
{
|
| 670 |
+
"epoch": 0.64,
|
| 671 |
+
"grad_norm": 0.5878339828851088,
|
| 672 |
+
"learning_rate": 6.8553917319085676e-06,
|
| 673 |
+
"loss": 0.7478,
|
| 674 |
"step": 470
|
| 675 |
},
|
| 676 |
{
|
| 677 |
+
"epoch": 0.65,
|
| 678 |
+
"grad_norm": 0.552328272875581,
|
| 679 |
+
"learning_rate": 6.629696703087755e-06,
|
| 680 |
+
"loss": 0.7237,
|
| 681 |
"step": 475
|
| 682 |
},
|
| 683 |
{
|
| 684 |
+
"epoch": 0.66,
|
| 685 |
+
"grad_norm": 0.6071223669952857,
|
| 686 |
+
"learning_rate": 6.405922271624874e-06,
|
| 687 |
+
"loss": 0.7357,
|
| 688 |
"step": 480
|
| 689 |
},
|
| 690 |
{
|
| 691 |
+
"epoch": 0.66,
|
| 692 |
+
"grad_norm": 0.6060821252643572,
|
| 693 |
+
"learning_rate": 6.184195957373176e-06,
|
| 694 |
+
"loss": 0.7178,
|
| 695 |
"step": 485
|
| 696 |
},
|
| 697 |
{
|
| 698 |
+
"epoch": 0.67,
|
| 699 |
+
"grad_norm": 0.543636900637841,
|
| 700 |
+
"learning_rate": 5.964644113048079e-06,
|
| 701 |
+
"loss": 0.7264,
|
| 702 |
"step": 490
|
| 703 |
},
|
| 704 |
{
|
| 705 |
+
"epoch": 0.68,
|
| 706 |
+
"grad_norm": 0.603596293760061,
|
| 707 |
+
"learning_rate": 5.74739185222394e-06,
|
| 708 |
+
"loss": 0.7415,
|
| 709 |
"step": 495
|
| 710 |
},
|
| 711 |
{
|
| 712 |
+
"epoch": 0.68,
|
| 713 |
+
"grad_norm": 0.5558735174394915,
|
| 714 |
+
"learning_rate": 5.532562978036964e-06,
|
| 715 |
+
"loss": 0.7431,
|
| 716 |
"step": 500
|
| 717 |
},
|
| 718 |
{
|
| 719 |
+
"epoch": 0.69,
|
| 720 |
+
"grad_norm": 0.5937971276012349,
|
| 721 |
+
"learning_rate": 5.320279912634907e-06,
|
| 722 |
+
"loss": 0.7316,
|
| 723 |
"step": 505
|
| 724 |
},
|
| 725 |
{
|
| 726 |
+
"epoch": 0.7,
|
| 727 |
+
"grad_norm": 0.5786141927192617,
|
| 728 |
+
"learning_rate": 5.110663627413695e-06,
|
| 729 |
+
"loss": 0.713,
|
| 730 |
"step": 510
|
| 731 |
},
|
| 732 |
{
|
| 733 |
+
"epoch": 0.7,
|
| 734 |
+
"grad_norm": 0.5809275145865697,
|
| 735 |
+
"learning_rate": 4.903833574080825e-06,
|
| 736 |
+
"loss": 0.7273,
|
| 737 |
"step": 515
|
| 738 |
},
|
| 739 |
{
|
| 740 |
+
"epoch": 0.71,
|
| 741 |
+
"grad_norm": 0.571032903937194,
|
| 742 |
+
"learning_rate": 4.6999076165847214e-06,
|
| 743 |
+
"loss": 0.7128,
|
| 744 |
"step": 520
|
| 745 |
},
|
| 746 |
{
|
| 747 |
+
"epoch": 0.72,
|
| 748 |
+
"grad_norm": 0.6308749156115376,
|
| 749 |
+
"learning_rate": 4.499001963948929e-06,
|
| 750 |
+
"loss": 0.727,
|
| 751 |
"step": 525
|
| 752 |
},
|
| 753 |
{
|
| 754 |
+
"epoch": 0.72,
|
| 755 |
+
"grad_norm": 0.5475000263845851,
|
| 756 |
+
"learning_rate": 4.301231104049359e-06,
|
| 757 |
+
"loss": 0.7236,
|
| 758 |
"step": 530
|
| 759 |
},
|
| 760 |
{
|
| 761 |
+
"epoch": 0.73,
|
| 762 |
+
"grad_norm": 0.5451654896042127,
|
| 763 |
+
"learning_rate": 4.106707738372357e-06,
|
| 764 |
+
"loss": 0.717,
|
| 765 |
"step": 535
|
| 766 |
},
|
| 767 |
{
|
| 768 |
+
"epoch": 0.74,
|
| 769 |
+
"grad_norm": 0.5895012216093011,
|
| 770 |
+
"learning_rate": 3.915542717790759e-06,
|
| 771 |
+
"loss": 0.7253,
|
| 772 |
"step": 540
|
| 773 |
},
|
| 774 |
{
|
| 775 |
+
"epoch": 0.74,
|
| 776 |
+
"grad_norm": 0.5991508019426129,
|
| 777 |
+
"learning_rate": 3.727844979394526e-06,
|
| 778 |
+
"loss": 0.7108,
|
| 779 |
"step": 545
|
| 780 |
},
|
| 781 |
{
|
| 782 |
+
"epoch": 0.75,
|
| 783 |
+
"grad_norm": 0.6024026652126097,
|
| 784 |
+
"learning_rate": 3.543721484411976e-06,
|
| 785 |
+
"loss": 0.7148,
|
| 786 |
"step": 550
|
| 787 |
},
|
| 788 |
{
|
| 789 |
+
"epoch": 0.76,
|
| 790 |
+
"grad_norm": 0.5479626437376189,
|
| 791 |
+
"learning_rate": 3.3632771572569878e-06,
|
| 792 |
+
"loss": 0.7205,
|
| 793 |
"step": 555
|
| 794 |
},
|
| 795 |
{
|
| 796 |
+
"epoch": 0.77,
|
| 797 |
+
"grad_norm": 0.5637951714589972,
|
| 798 |
+
"learning_rate": 3.1866148257368666e-06,
|
| 799 |
+
"loss": 0.7291,
|
| 800 |
"step": 560
|
| 801 |
},
|
| 802 |
{
|
| 803 |
+
"epoch": 0.77,
|
| 804 |
+
"grad_norm": 0.5971328138449835,
|
| 805 |
+
"learning_rate": 3.0138351624550165e-06,
|
| 806 |
+
"loss": 0.7242,
|
| 807 |
"step": 565
|
| 808 |
},
|
| 809 |
{
|
| 810 |
+
"epoch": 0.78,
|
| 811 |
+
"grad_norm": 0.5566178272277884,
|
| 812 |
+
"learning_rate": 2.845036627441755e-06,
|
| 813 |
+
"loss": 0.725,
|
| 814 |
"step": 570
|
| 815 |
},
|
| 816 |
{
|
| 817 |
+
"epoch": 0.79,
|
| 818 |
+
"grad_norm": 0.5747018707425353,
|
| 819 |
+
"learning_rate": 2.6803154120460007e-06,
|
| 820 |
+
"loss": 0.7232,
|
| 821 |
"step": 575
|
| 822 |
},
|
| 823 |
{
|
| 824 |
+
"epoch": 0.79,
|
| 825 |
+
"grad_norm": 0.583278019846911,
|
| 826 |
+
"learning_rate": 2.5197653841197546e-06,
|
| 827 |
+
"loss": 0.7593,
|
| 828 |
"step": 580
|
| 829 |
},
|
| 830 |
{
|
| 831 |
+
"epoch": 0.8,
|
| 832 |
+
"grad_norm": 0.5792687056211038,
|
| 833 |
+
"learning_rate": 2.3634780345266805e-06,
|
| 834 |
+
"loss": 0.7263,
|
| 835 |
"step": 585
|
| 836 |
},
|
| 837 |
{
|
| 838 |
+
"epoch": 0.81,
|
| 839 |
+
"grad_norm": 0.5936774049714754,
|
| 840 |
+
"learning_rate": 2.211542425005223e-06,
|
| 841 |
+
"loss": 0.7105,
|
| 842 |
"step": 590
|
| 843 |
},
|
| 844 |
{
|
| 845 |
+
"epoch": 0.81,
|
| 846 |
+
"grad_norm": 0.5618344372585139,
|
| 847 |
+
"learning_rate": 2.064045137415982e-06,
|
| 848 |
+
"loss": 0.7148,
|
| 849 |
"step": 595
|
| 850 |
},
|
| 851 |
{
|
| 852 |
+
"epoch": 0.82,
|
| 853 |
+
"grad_norm": 0.5753081059010117,
|
| 854 |
+
"learning_rate": 1.9210702244022616e-06,
|
| 855 |
+
"loss": 0.7313,
|
| 856 |
"step": 600
|
| 857 |
},
|
| 858 |
{
|
| 859 |
+
"epoch": 0.83,
|
| 860 |
+
"grad_norm": 0.5418687310157559,
|
| 861 |
+
"learning_rate": 1.7826991614919264e-06,
|
| 862 |
+
"loss": 0.7245,
|
| 863 |
"step": 605
|
| 864 |
},
|
| 865 |
{
|
| 866 |
+
"epoch": 0.83,
|
| 867 |
+
"grad_norm": 0.5828322063852037,
|
| 868 |
+
"learning_rate": 1.6490108006678495e-06,
|
| 869 |
+
"loss": 0.7527,
|
| 870 |
"step": 610
|
| 871 |
},
|
| 872 |
{
|
| 873 |
+
"epoch": 0.84,
|
| 874 |
+
"grad_norm": 0.5878067843611324,
|
| 875 |
+
"learning_rate": 1.5200813254334013e-06,
|
| 876 |
+
"loss": 0.7213,
|
| 877 |
"step": 615
|
| 878 |
},
|
| 879 |
{
|
| 880 |
+
"epoch": 0.85,
|
| 881 |
+
"grad_norm": 0.5816156229837385,
|
| 882 |
+
"learning_rate": 1.3959842073986085e-06,
|
| 883 |
+
"loss": 0.7134,
|
| 884 |
"step": 620
|
| 885 |
},
|
| 886 |
{
|
| 887 |
+
"epoch": 0.85,
|
| 888 |
+
"grad_norm": 0.5962667792304962,
|
| 889 |
+
"learning_rate": 1.2767901644116943e-06,
|
| 890 |
+
"loss": 0.7233,
|
| 891 |
"step": 625
|
| 892 |
},
|
| 893 |
{
|
| 894 |
+
"epoch": 0.86,
|
| 895 |
+
"grad_norm": 0.5399112934132381,
|
| 896 |
+
"learning_rate": 1.1625671202598875e-06,
|
| 897 |
+
"loss": 0.7179,
|
| 898 |
"step": 630
|
| 899 |
},
|
| 900 |
{
|
| 901 |
+
"epoch": 0.87,
|
| 902 |
+
"grad_norm": 0.5397855641716054,
|
| 903 |
+
"learning_rate": 1.0533801659624531e-06,
|
| 904 |
+
"loss": 0.7114,
|
| 905 |
"step": 635
|
| 906 |
},
|
| 907 |
{
|
| 908 |
+
"epoch": 0.87,
|
| 909 |
+
"grad_norm": 0.5936653550047086,
|
| 910 |
+
"learning_rate": 9.492915226779809e-07,
|
| 911 |
+
"loss": 0.7175,
|
| 912 |
"step": 640
|
| 913 |
},
|
| 914 |
{
|
| 915 |
+
"epoch": 0.88,
|
| 916 |
+
"grad_norm": 0.6099602078388837,
|
| 917 |
+
"learning_rate": 8.503605062471187e-07,
|
| 918 |
+
"loss": 0.7119,
|
| 919 |
"step": 645
|
| 920 |
},
|
| 921 |
{
|
| 922 |
+
"epoch": 0.89,
|
| 923 |
+
"grad_norm": 0.6177660757674084,
|
| 924 |
+
"learning_rate": 7.566434933909006e-07,
|
| 925 |
+
"loss": 0.7132,
|
| 926 |
"step": 650
|
| 927 |
},
|
| 928 |
{
|
| 929 |
+
"epoch": 0.89,
|
| 930 |
+
"grad_norm": 0.5217732163513131,
|
| 931 |
+
"learning_rate": 6.681938895839746e-07,
|
| 932 |
+
"loss": 0.7128,
|
| 933 |
"step": 655
|
| 934 |
},
|
| 935 |
{
|
| 936 |
+
"epoch": 0.9,
|
| 937 |
+
"grad_norm": 0.5808565758298766,
|
| 938 |
+
"learning_rate": 5.850620986210198e-07,
|
| 939 |
+
"loss": 0.6972,
|
| 940 |
"step": 660
|
| 941 |
},
|
| 942 |
{
|
| 943 |
+
"epoch": 0.91,
|
| 944 |
+
"grad_norm": 0.5829050029411651,
|
| 945 |
+
"learning_rate": 5.072954938936925e-07,
|
| 946 |
+
"loss": 0.7253,
|
| 947 |
"step": 665
|
| 948 |
},
|
| 949 |
{
|
| 950 |
+
"epoch": 0.92,
|
| 951 |
+
"grad_norm": 0.5481607356326386,
|
| 952 |
+
"learning_rate": 4.3493839139447716e-07,
|
| 953 |
+
"loss": 0.7222,
|
| 954 |
"step": 670
|
| 955 |
},
|
| 956 |
{
|
| 957 |
+
"epoch": 0.92,
|
| 958 |
+
"grad_norm": 0.5652882598658524,
|
| 959 |
+
"learning_rate": 3.6803202446282217e-07,
|
| 960 |
+
"loss": 0.6845,
|
| 961 |
"step": 675
|
| 962 |
},
|
| 963 |
{
|
| 964 |
+
"epoch": 0.93,
|
| 965 |
+
"grad_norm": 0.5796535522251339,
|
| 966 |
+
"learning_rate": 3.0661452028795335e-07,
|
| 967 |
+
"loss": 0.7148,
|
| 968 |
"step": 680
|
| 969 |
},
|
| 970 |
{
|
| 971 |
+
"epoch": 0.94,
|
| 972 |
+
"grad_norm": 0.5887255027538941,
|
| 973 |
+
"learning_rate": 2.507208781817638e-07,
|
| 974 |
+
"loss": 0.7224,
|
| 975 |
"step": 685
|
| 976 |
},
|
| 977 |
{
|
| 978 |
+
"epoch": 0.94,
|
| 979 |
+
"grad_norm": 0.5592326454997533,
|
| 980 |
+
"learning_rate": 2.0038294963413251e-07,
|
| 981 |
+
"loss": 0.7113,
|
| 982 |
"step": 690
|
| 983 |
},
|
| 984 |
{
|
| 985 |
+
"epoch": 0.95,
|
| 986 |
+
"grad_norm": 0.5776817470975002,
|
| 987 |
+
"learning_rate": 1.556294201620734e-07,
|
| 988 |
+
"loss": 0.7033,
|
| 989 |
"step": 695
|
| 990 |
},
|
| 991 |
{
|
| 992 |
+
"epoch": 0.96,
|
| 993 |
+
"grad_norm": 0.5696597587226961,
|
| 994 |
+
"learning_rate": 1.1648579296304252e-07,
|
| 995 |
+
"loss": 0.7277,
|
| 996 |
"step": 700
|
| 997 |
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 0.96,
|
| 1000 |
+
"grad_norm": 0.5641386210392492,
|
| 1001 |
+
"learning_rate": 8.297437438170797e-08,
|
| 1002 |
+
"loss": 0.7256,
|
| 1003 |
+
"step": 705
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 0.97,
|
| 1007 |
+
"grad_norm": 0.5889080994491116,
|
| 1008 |
+
"learning_rate": 5.51142611984834e-08,
|
| 1009 |
+
"loss": 0.7279,
|
| 1010 |
+
"step": 710
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 0.98,
|
| 1014 |
+
"grad_norm": 0.5665974446341169,
|
| 1015 |
+
"learning_rate": 3.2921329747056527e-08,
|
| 1016 |
+
"loss": 0.7311,
|
| 1017 |
+
"step": 715
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 0.98,
|
| 1021 |
+
"grad_norm": 0.5822891522453822,
|
| 1022 |
+
"learning_rate": 1.6408226867118404e-08,
|
| 1023 |
+
"loss": 0.7131,
|
| 1024 |
+
"step": 720
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 0.99,
|
| 1028 |
+
"grad_norm": 0.5631956425423463,
|
| 1029 |
+
"learning_rate": 5.584362697453882e-09,
|
| 1030 |
+
"loss": 0.7071,
|
| 1031 |
+
"step": 725
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 1.0,
|
| 1035 |
+
"grad_norm": 0.563567530638776,
|
| 1036 |
+
"learning_rate": 4.5590531348227443e-10,
|
| 1037 |
+
"loss": 0.7119,
|
| 1038 |
+
"step": 730
|
| 1039 |
+
},
|
| 1040 |
{
|
| 1041 |
"epoch": 1.0,
|
| 1042 |
+
"eval_loss": 0.7456573247909546,
|
| 1043 |
+
"eval_runtime": 9.4968,
|
| 1044 |
+
"eval_samples_per_second": 52.649,
|
| 1045 |
+
"eval_steps_per_second": 1.685,
|
| 1046 |
+
"step": 732
|
| 1047 |
},
|
| 1048 |
{
|
| 1049 |
"epoch": 1.0,
|
| 1050 |
+
"step": 732,
|
| 1051 |
+
"total_flos": 106029000622080.0,
|
| 1052 |
+
"train_loss": 0.7605658245216953,
|
| 1053 |
+
"train_runtime": 6107.4706,
|
| 1054 |
+
"train_samples_per_second": 15.333,
|
| 1055 |
"train_steps_per_second": 0.12
|
| 1056 |
}
|
| 1057 |
],
|
| 1058 |
"logging_steps": 5,
|
| 1059 |
+
"max_steps": 732,
|
| 1060 |
"num_input_tokens_seen": 0,
|
| 1061 |
"num_train_epochs": 1,
|
| 1062 |
"save_steps": 100,
|
| 1063 |
+
"total_flos": 106029000622080.0,
|
| 1064 |
"train_batch_size": 16,
|
| 1065 |
"trial_name": null,
|
| 1066 |
"trial_params": null
|