Training in progress, step 500, checkpoint
Browse files- last-checkpoint/config.json +1 -1
- last-checkpoint/model.safetensors +1 -1
- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/rng_state.pth +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +257 -1153
- last-checkpoint/training_args.bin +1 -1
last-checkpoint/config.json
CHANGED
|
@@ -25,7 +25,7 @@
|
|
| 25 |
"position_embedding_type": "absolute",
|
| 26 |
"problem_type": "single_label_classification",
|
| 27 |
"torch_dtype": "float32",
|
| 28 |
-
"transformers_version": "4.
|
| 29 |
"type_vocab_size": 2,
|
| 30 |
"use_cache": true,
|
| 31 |
"vocab_size": 21628
|
|
|
|
| 25 |
"position_embedding_type": "absolute",
|
| 26 |
"problem_type": "single_label_classification",
|
| 27 |
"torch_dtype": "float32",
|
| 28 |
+
"transformers_version": "4.48.3",
|
| 29 |
"type_vocab_size": 2,
|
| 30 |
"use_cache": true,
|
| 31 |
"vocab_size": 21628
|
last-checkpoint/model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 410636248
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:835625f2edbfc20a73fcfc870a038552e3bac65a5153e8c5049a6e5e75f4fff2
|
| 3 |
size 410636248
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 821393658
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e842648a8de5363ee9555cfd74812dc3ecef61d528f4dc5e7522b13b41d2cb63
|
| 3 |
size 821393658
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14244
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8818f39adb2991c71be42f9538820c8ad5ace26fa92a971005edcfaa206900e4
|
| 3 |
size 14244
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1064
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5f405c2c673cf6aab61295c4e74c472a2015440052e52b46872a0ad1407e3ef9
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,1312 +1,416 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 0.
|
| 3 |
-
"best_model_checkpoint": "./results/checkpoint-
|
| 4 |
-
"epoch":
|
| 5 |
"eval_steps": 20,
|
| 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.
|
| 13 |
-
"grad_norm":
|
| 14 |
-
"learning_rate": 1.
|
| 15 |
-
"loss": 0.
|
| 16 |
"step": 20
|
| 17 |
},
|
| 18 |
{
|
| 19 |
-
"epoch": 0.
|
| 20 |
-
"eval_accuracy": 0.
|
| 21 |
-
"eval_loss": 0.
|
| 22 |
-
"eval_runtime":
|
| 23 |
-
"eval_samples_per_second":
|
| 24 |
-
"eval_steps_per_second":
|
| 25 |
"step": 20
|
| 26 |
},
|
| 27 |
{
|
| 28 |
-
"epoch": 0.
|
| 29 |
-
"grad_norm":
|
| 30 |
-
"learning_rate": 1.
|
| 31 |
-
"loss": 0.
|
| 32 |
"step": 40
|
| 33 |
},
|
| 34 |
{
|
| 35 |
-
"epoch": 0.
|
| 36 |
-
"eval_accuracy": 0.
|
| 37 |
-
"eval_loss": 0.
|
| 38 |
-
"eval_runtime":
|
| 39 |
-
"eval_samples_per_second":
|
| 40 |
-
"eval_steps_per_second":
|
| 41 |
"step": 40
|
| 42 |
},
|
| 43 |
{
|
| 44 |
-
"epoch": 0.
|
| 45 |
-
"grad_norm":
|
| 46 |
-
"learning_rate": 1.
|
| 47 |
-
"loss": 0.
|
| 48 |
"step": 60
|
| 49 |
},
|
| 50 |
{
|
| 51 |
-
"epoch": 0.
|
| 52 |
-
"eval_accuracy": 0.
|
| 53 |
-
"eval_loss": 0.
|
| 54 |
-
"eval_runtime":
|
| 55 |
-
"eval_samples_per_second":
|
| 56 |
-
"eval_steps_per_second":
|
| 57 |
"step": 60
|
| 58 |
},
|
| 59 |
{
|
| 60 |
-
"epoch": 0.
|
| 61 |
-
"grad_norm":
|
| 62 |
-
"learning_rate": 1.
|
| 63 |
-
"loss": 0.
|
| 64 |
"step": 80
|
| 65 |
},
|
| 66 |
{
|
| 67 |
-
"epoch": 0.
|
| 68 |
-
"eval_accuracy": 0.
|
| 69 |
-
"eval_loss": 0.
|
| 70 |
-
"eval_runtime":
|
| 71 |
-
"eval_samples_per_second":
|
| 72 |
-
"eval_steps_per_second":
|
| 73 |
"step": 80
|
| 74 |
},
|
| 75 |
{
|
| 76 |
-
"epoch": 0.
|
| 77 |
-
"grad_norm":
|
| 78 |
-
"learning_rate": 1.
|
| 79 |
-
"loss": 0.
|
| 80 |
"step": 100
|
| 81 |
},
|
| 82 |
{
|
| 83 |
-
"epoch": 0.
|
| 84 |
-
"eval_accuracy": 0.
|
| 85 |
-
"eval_loss": 0.
|
| 86 |
-
"eval_runtime":
|
| 87 |
-
"eval_samples_per_second":
|
| 88 |
-
"eval_steps_per_second":
|
| 89 |
"step": 100
|
| 90 |
},
|
| 91 |
{
|
| 92 |
-
"epoch": 0.
|
| 93 |
-
"grad_norm":
|
| 94 |
-
"learning_rate": 1.
|
| 95 |
-
"loss": 0.
|
| 96 |
"step": 120
|
| 97 |
},
|
| 98 |
{
|
| 99 |
-
"epoch": 0.
|
| 100 |
-
"eval_accuracy": 0.
|
| 101 |
-
"eval_loss": 0.
|
| 102 |
-
"eval_runtime":
|
| 103 |
-
"eval_samples_per_second":
|
| 104 |
-
"eval_steps_per_second":
|
| 105 |
"step": 120
|
| 106 |
},
|
| 107 |
{
|
| 108 |
-
"epoch": 0.
|
| 109 |
-
"grad_norm":
|
| 110 |
-
"learning_rate": 1.
|
| 111 |
-
"loss": 0.
|
| 112 |
"step": 140
|
| 113 |
},
|
| 114 |
{
|
| 115 |
-
"epoch": 0.
|
| 116 |
-
"eval_accuracy": 0.
|
| 117 |
-
"eval_loss": 0.
|
| 118 |
-
"eval_runtime":
|
| 119 |
-
"eval_samples_per_second":
|
| 120 |
-
"eval_steps_per_second":
|
| 121 |
"step": 140
|
| 122 |
},
|
| 123 |
{
|
| 124 |
-
"epoch": 0.
|
| 125 |
-
"grad_norm": 0.
|
| 126 |
-
"learning_rate": 1.
|
| 127 |
-
"loss": 0.
|
| 128 |
"step": 160
|
| 129 |
},
|
| 130 |
{
|
| 131 |
-
"epoch": 0.
|
| 132 |
-
"eval_accuracy": 0.
|
| 133 |
-
"eval_loss": 0.
|
| 134 |
-
"eval_runtime": 4.
|
| 135 |
-
"eval_samples_per_second":
|
| 136 |
-
"eval_steps_per_second":
|
| 137 |
"step": 160
|
| 138 |
},
|
| 139 |
{
|
| 140 |
-
"epoch": 0.
|
| 141 |
-
"grad_norm": 0.
|
| 142 |
-
"learning_rate": 1.
|
| 143 |
-
"loss": 0.
|
| 144 |
"step": 180
|
| 145 |
},
|
| 146 |
{
|
| 147 |
-
"epoch": 0.
|
| 148 |
-
"eval_accuracy": 0.
|
| 149 |
-
"eval_loss": 0.
|
| 150 |
-
"eval_runtime": 4.
|
| 151 |
-
"eval_samples_per_second":
|
| 152 |
-
"eval_steps_per_second":
|
| 153 |
"step": 180
|
| 154 |
},
|
| 155 |
{
|
| 156 |
-
"epoch": 0.
|
| 157 |
-
"grad_norm":
|
| 158 |
-
"learning_rate": 1.
|
| 159 |
-
"loss": 0.
|
| 160 |
"step": 200
|
| 161 |
},
|
| 162 |
{
|
| 163 |
-
"epoch": 0.
|
| 164 |
-
"eval_accuracy": 0.
|
| 165 |
-
"eval_loss": 0.
|
| 166 |
-
"eval_runtime": 4.
|
| 167 |
-
"eval_samples_per_second":
|
| 168 |
-
"eval_steps_per_second":
|
| 169 |
"step": 200
|
| 170 |
},
|
| 171 |
{
|
| 172 |
-
"epoch": 0.
|
| 173 |
-
"grad_norm":
|
| 174 |
-
"learning_rate": 1.
|
| 175 |
-
"loss": 0.
|
| 176 |
"step": 220
|
| 177 |
},
|
| 178 |
{
|
| 179 |
-
"epoch": 0.
|
| 180 |
-
"eval_accuracy": 0.
|
| 181 |
-
"eval_loss": 0.
|
| 182 |
-
"eval_runtime": 4.
|
| 183 |
-
"eval_samples_per_second":
|
| 184 |
-
"eval_steps_per_second":
|
| 185 |
"step": 220
|
| 186 |
},
|
| 187 |
{
|
| 188 |
-
"epoch": 0.
|
| 189 |
-
"grad_norm":
|
| 190 |
-
"learning_rate": 1.
|
| 191 |
-
"loss": 0.
|
| 192 |
"step": 240
|
| 193 |
},
|
| 194 |
{
|
| 195 |
-
"epoch": 0.
|
| 196 |
-
"eval_accuracy": 0.
|
| 197 |
-
"eval_loss": 0.
|
| 198 |
-
"eval_runtime": 4.
|
| 199 |
-
"eval_samples_per_second":
|
| 200 |
-
"eval_steps_per_second":
|
| 201 |
"step": 240
|
| 202 |
},
|
| 203 |
{
|
| 204 |
-
"epoch": 0.
|
| 205 |
-
"grad_norm":
|
| 206 |
-
"learning_rate": 1.
|
| 207 |
-
"loss": 0.
|
| 208 |
"step": 260
|
| 209 |
},
|
| 210 |
{
|
| 211 |
-
"epoch": 0.
|
| 212 |
-
"eval_accuracy": 0.
|
| 213 |
-
"eval_loss": 0.
|
| 214 |
-
"eval_runtime": 4.
|
| 215 |
-
"eval_samples_per_second":
|
| 216 |
-
"eval_steps_per_second":
|
| 217 |
"step": 260
|
| 218 |
},
|
| 219 |
{
|
| 220 |
-
"epoch": 0.
|
| 221 |
-
"grad_norm":
|
| 222 |
-
"learning_rate": 1.
|
| 223 |
-
"loss": 0.
|
| 224 |
"step": 280
|
| 225 |
},
|
| 226 |
{
|
| 227 |
-
"epoch": 0.
|
| 228 |
-
"eval_accuracy": 0.
|
| 229 |
-
"eval_loss": 0.
|
| 230 |
-
"eval_runtime": 4.
|
| 231 |
-
"eval_samples_per_second":
|
| 232 |
-
"eval_steps_per_second":
|
| 233 |
"step": 280
|
| 234 |
},
|
| 235 |
{
|
| 236 |
-
"epoch": 0.
|
| 237 |
-
"grad_norm":
|
| 238 |
-
"learning_rate": 1.
|
| 239 |
-
"loss": 0.
|
| 240 |
"step": 300
|
| 241 |
},
|
| 242 |
{
|
| 243 |
-
"epoch": 0.
|
| 244 |
-
"eval_accuracy": 0.
|
| 245 |
-
"eval_loss": 0.
|
| 246 |
-
"eval_runtime": 4.
|
| 247 |
-
"eval_samples_per_second":
|
| 248 |
-
"eval_steps_per_second":
|
| 249 |
"step": 300
|
| 250 |
},
|
| 251 |
{
|
| 252 |
-
"epoch": 0.
|
| 253 |
-
"grad_norm":
|
| 254 |
-
"learning_rate": 1.
|
| 255 |
-
"loss": 0.
|
| 256 |
"step": 320
|
| 257 |
},
|
| 258 |
{
|
| 259 |
-
"epoch": 0.
|
| 260 |
-
"eval_accuracy": 0.
|
| 261 |
-
"eval_loss": 0.
|
| 262 |
-
"eval_runtime": 4.
|
| 263 |
-
"eval_samples_per_second":
|
| 264 |
-
"eval_steps_per_second":
|
| 265 |
"step": 320
|
| 266 |
},
|
| 267 |
{
|
| 268 |
-
"epoch":
|
| 269 |
-
"grad_norm":
|
| 270 |
-
"learning_rate": 1.
|
| 271 |
-
"loss": 0.
|
| 272 |
"step": 340
|
| 273 |
},
|
| 274 |
{
|
| 275 |
-
"epoch":
|
| 276 |
-
"eval_accuracy": 0.
|
| 277 |
-
"eval_loss": 0.
|
| 278 |
-
"eval_runtime": 4.
|
| 279 |
-
"eval_samples_per_second":
|
| 280 |
-
"eval_steps_per_second":
|
| 281 |
"step": 340
|
| 282 |
},
|
| 283 |
{
|
| 284 |
-
"epoch": 1.
|
| 285 |
-
"grad_norm":
|
| 286 |
-
"learning_rate": 1.
|
| 287 |
-
"loss": 0.
|
| 288 |
"step": 360
|
| 289 |
},
|
| 290 |
{
|
| 291 |
-
"epoch": 1.
|
| 292 |
-
"eval_accuracy": 0.
|
| 293 |
-
"eval_loss": 0.
|
| 294 |
-
"eval_runtime": 4.
|
| 295 |
-
"eval_samples_per_second":
|
| 296 |
-
"eval_steps_per_second":
|
| 297 |
"step": 360
|
| 298 |
},
|
| 299 |
{
|
| 300 |
-
"epoch": 1.
|
| 301 |
-
"grad_norm": 0.
|
| 302 |
-
"learning_rate": 1.
|
| 303 |
-
"loss": 0.
|
| 304 |
"step": 380
|
| 305 |
},
|
| 306 |
{
|
| 307 |
-
"epoch": 1.
|
| 308 |
-
"eval_accuracy": 0.
|
| 309 |
-
"eval_loss": 0.
|
| 310 |
-
"eval_runtime": 4.
|
| 311 |
-
"eval_samples_per_second":
|
| 312 |
-
"eval_steps_per_second":
|
| 313 |
"step": 380
|
| 314 |
},
|
| 315 |
{
|
| 316 |
-
"epoch": 1.
|
| 317 |
-
"grad_norm": 0.
|
| 318 |
-
"learning_rate": 1.
|
| 319 |
-
"loss": 0.
|
| 320 |
"step": 400
|
| 321 |
},
|
| 322 |
{
|
| 323 |
-
"epoch": 1.
|
| 324 |
-
"eval_accuracy": 0.
|
| 325 |
-
"eval_loss": 0.
|
| 326 |
-
"eval_runtime": 4.
|
| 327 |
-
"eval_samples_per_second":
|
| 328 |
-
"eval_steps_per_second":
|
| 329 |
"step": 400
|
| 330 |
},
|
| 331 |
{
|
| 332 |
-
"epoch": 1.
|
| 333 |
-
"grad_norm": 0.
|
| 334 |
-
"learning_rate": 1.
|
| 335 |
-
"loss": 0.
|
| 336 |
"step": 420
|
| 337 |
},
|
| 338 |
{
|
| 339 |
-
"epoch": 1.
|
| 340 |
-
"eval_accuracy": 0.
|
| 341 |
-
"eval_loss": 0.
|
| 342 |
-
"eval_runtime": 4.
|
| 343 |
-
"eval_samples_per_second":
|
| 344 |
-
"eval_steps_per_second":
|
| 345 |
"step": 420
|
| 346 |
},
|
| 347 |
{
|
| 348 |
-
"epoch": 1.
|
| 349 |
-
"grad_norm": 0.
|
| 350 |
-
"learning_rate": 1.
|
| 351 |
-
"loss": 0.
|
| 352 |
"step": 440
|
| 353 |
},
|
| 354 |
{
|
| 355 |
-
"epoch": 1.
|
| 356 |
-
"eval_accuracy": 0.
|
| 357 |
-
"eval_loss": 0.
|
| 358 |
-
"eval_runtime": 4.
|
| 359 |
-
"eval_samples_per_second":
|
| 360 |
-
"eval_steps_per_second":
|
| 361 |
"step": 440
|
| 362 |
},
|
| 363 |
{
|
| 364 |
-
"epoch": 1.
|
| 365 |
-
"grad_norm":
|
| 366 |
-
"learning_rate": 1.
|
| 367 |
-
"loss": 0.
|
| 368 |
"step": 460
|
| 369 |
},
|
| 370 |
{
|
| 371 |
-
"epoch": 1.
|
| 372 |
-
"eval_accuracy": 0.
|
| 373 |
-
"eval_loss": 0.
|
| 374 |
-
"eval_runtime": 4.
|
| 375 |
-
"eval_samples_per_second":
|
| 376 |
-
"eval_steps_per_second":
|
| 377 |
"step": 460
|
| 378 |
},
|
| 379 |
{
|
| 380 |
-
"epoch": 1.
|
| 381 |
-
"grad_norm": 0.
|
| 382 |
-
"learning_rate": 1.
|
| 383 |
-
"loss": 0.
|
| 384 |
"step": 480
|
| 385 |
},
|
| 386 |
{
|
| 387 |
-
"epoch": 1.
|
| 388 |
-
"eval_accuracy": 0.
|
| 389 |
-
"eval_loss": 0.
|
| 390 |
-
"eval_runtime": 4.
|
| 391 |
-
"eval_samples_per_second":
|
| 392 |
-
"eval_steps_per_second":
|
| 393 |
"step": 480
|
| 394 |
},
|
| 395 |
{
|
| 396 |
-
"epoch": 1.
|
| 397 |
-
"grad_norm": 0.
|
| 398 |
-
"learning_rate": 1.
|
| 399 |
-
"loss": 0.
|
| 400 |
"step": 500
|
| 401 |
},
|
| 402 |
{
|
| 403 |
-
"epoch": 1.
|
| 404 |
-
"eval_accuracy": 0.
|
| 405 |
-
"eval_loss": 0.
|
| 406 |
-
"eval_runtime": 4.
|
| 407 |
-
"eval_samples_per_second":
|
| 408 |
-
"eval_steps_per_second":
|
| 409 |
"step": 500
|
| 410 |
-
},
|
| 411 |
-
{
|
| 412 |
-
"epoch": 1.6,
|
| 413 |
-
"grad_norm": 7.504834175109863,
|
| 414 |
-
"learning_rate": 1.3600000000000002e-05,
|
| 415 |
-
"loss": 0.2027,
|
| 416 |
-
"step": 520
|
| 417 |
-
},
|
| 418 |
-
{
|
| 419 |
-
"epoch": 1.6,
|
| 420 |
-
"eval_accuracy": 0.94,
|
| 421 |
-
"eval_loss": 0.2419724315404892,
|
| 422 |
-
"eval_runtime": 4.392,
|
| 423 |
-
"eval_samples_per_second": 34.153,
|
| 424 |
-
"eval_steps_per_second": 8.652,
|
| 425 |
-
"step": 520
|
| 426 |
-
},
|
| 427 |
-
{
|
| 428 |
-
"epoch": 1.6615384615384614,
|
| 429 |
-
"grad_norm": 0.03419135510921478,
|
| 430 |
-
"learning_rate": 1.3353846153846155e-05,
|
| 431 |
-
"loss": 0.1009,
|
| 432 |
-
"step": 540
|
| 433 |
-
},
|
| 434 |
-
{
|
| 435 |
-
"epoch": 1.6615384615384614,
|
| 436 |
-
"eval_accuracy": 0.86,
|
| 437 |
-
"eval_loss": 0.5571817755699158,
|
| 438 |
-
"eval_runtime": 4.5429,
|
| 439 |
-
"eval_samples_per_second": 33.019,
|
| 440 |
-
"eval_steps_per_second": 8.365,
|
| 441 |
-
"step": 540
|
| 442 |
-
},
|
| 443 |
-
{
|
| 444 |
-
"epoch": 1.7230769230769232,
|
| 445 |
-
"grad_norm": 7.043415546417236,
|
| 446 |
-
"learning_rate": 1.3107692307692307e-05,
|
| 447 |
-
"loss": 0.1411,
|
| 448 |
-
"step": 560
|
| 449 |
-
},
|
| 450 |
-
{
|
| 451 |
-
"epoch": 1.7230769230769232,
|
| 452 |
-
"eval_accuracy": 0.8866666666666667,
|
| 453 |
-
"eval_loss": 0.548427402973175,
|
| 454 |
-
"eval_runtime": 4.6315,
|
| 455 |
-
"eval_samples_per_second": 32.387,
|
| 456 |
-
"eval_steps_per_second": 8.205,
|
| 457 |
-
"step": 560
|
| 458 |
-
},
|
| 459 |
-
{
|
| 460 |
-
"epoch": 1.7846153846153845,
|
| 461 |
-
"grad_norm": 0.009195130318403244,
|
| 462 |
-
"learning_rate": 1.2861538461538462e-05,
|
| 463 |
-
"loss": 0.078,
|
| 464 |
-
"step": 580
|
| 465 |
-
},
|
| 466 |
-
{
|
| 467 |
-
"epoch": 1.7846153846153845,
|
| 468 |
-
"eval_accuracy": 0.9333333333333333,
|
| 469 |
-
"eval_loss": 0.28637686371803284,
|
| 470 |
-
"eval_runtime": 4.5867,
|
| 471 |
-
"eval_samples_per_second": 32.703,
|
| 472 |
-
"eval_steps_per_second": 8.285,
|
| 473 |
-
"step": 580
|
| 474 |
-
},
|
| 475 |
-
{
|
| 476 |
-
"epoch": 1.8461538461538463,
|
| 477 |
-
"grad_norm": 0.026943389326334,
|
| 478 |
-
"learning_rate": 1.2615384615384616e-05,
|
| 479 |
-
"loss": 0.2094,
|
| 480 |
-
"step": 600
|
| 481 |
-
},
|
| 482 |
-
{
|
| 483 |
-
"epoch": 1.8461538461538463,
|
| 484 |
-
"eval_accuracy": 0.9066666666666666,
|
| 485 |
-
"eval_loss": 0.47838306427001953,
|
| 486 |
-
"eval_runtime": 4.3919,
|
| 487 |
-
"eval_samples_per_second": 34.154,
|
| 488 |
-
"eval_steps_per_second": 8.652,
|
| 489 |
-
"step": 600
|
| 490 |
-
},
|
| 491 |
-
{
|
| 492 |
-
"epoch": 1.9076923076923076,
|
| 493 |
-
"grad_norm": 0.07408376038074493,
|
| 494 |
-
"learning_rate": 1.2369230769230771e-05,
|
| 495 |
-
"loss": 0.2487,
|
| 496 |
-
"step": 620
|
| 497 |
-
},
|
| 498 |
-
{
|
| 499 |
-
"epoch": 1.9076923076923076,
|
| 500 |
-
"eval_accuracy": 0.9266666666666666,
|
| 501 |
-
"eval_loss": 0.28538334369659424,
|
| 502 |
-
"eval_runtime": 4.3426,
|
| 503 |
-
"eval_samples_per_second": 34.542,
|
| 504 |
-
"eval_steps_per_second": 8.751,
|
| 505 |
-
"step": 620
|
| 506 |
-
},
|
| 507 |
-
{
|
| 508 |
-
"epoch": 1.9692307692307693,
|
| 509 |
-
"grad_norm": 0.019653869792819023,
|
| 510 |
-
"learning_rate": 1.2123076923076924e-05,
|
| 511 |
-
"loss": 0.1476,
|
| 512 |
-
"step": 640
|
| 513 |
-
},
|
| 514 |
-
{
|
| 515 |
-
"epoch": 1.9692307692307693,
|
| 516 |
-
"eval_accuracy": 0.9466666666666667,
|
| 517 |
-
"eval_loss": 0.20959021151065826,
|
| 518 |
-
"eval_runtime": 4.3786,
|
| 519 |
-
"eval_samples_per_second": 34.258,
|
| 520 |
-
"eval_steps_per_second": 8.679,
|
| 521 |
-
"step": 640
|
| 522 |
-
},
|
| 523 |
-
{
|
| 524 |
-
"epoch": 2.0307692307692307,
|
| 525 |
-
"grad_norm": 3.520812511444092,
|
| 526 |
-
"learning_rate": 1.1876923076923076e-05,
|
| 527 |
-
"loss": 0.0111,
|
| 528 |
-
"step": 660
|
| 529 |
-
},
|
| 530 |
-
{
|
| 531 |
-
"epoch": 2.0307692307692307,
|
| 532 |
-
"eval_accuracy": 0.9333333333333333,
|
| 533 |
-
"eval_loss": 0.32781320810317993,
|
| 534 |
-
"eval_runtime": 4.4324,
|
| 535 |
-
"eval_samples_per_second": 33.842,
|
| 536 |
-
"eval_steps_per_second": 8.573,
|
| 537 |
-
"step": 660
|
| 538 |
-
},
|
| 539 |
-
{
|
| 540 |
-
"epoch": 2.0923076923076924,
|
| 541 |
-
"grad_norm": 0.21061906218528748,
|
| 542 |
-
"learning_rate": 1.1630769230769231e-05,
|
| 543 |
-
"loss": 0.056,
|
| 544 |
-
"step": 680
|
| 545 |
-
},
|
| 546 |
-
{
|
| 547 |
-
"epoch": 2.0923076923076924,
|
| 548 |
-
"eval_accuracy": 0.94,
|
| 549 |
-
"eval_loss": 0.30281564593315125,
|
| 550 |
-
"eval_runtime": 4.4548,
|
| 551 |
-
"eval_samples_per_second": 33.671,
|
| 552 |
-
"eval_steps_per_second": 8.53,
|
| 553 |
-
"step": 680
|
| 554 |
-
},
|
| 555 |
-
{
|
| 556 |
-
"epoch": 2.1538461538461537,
|
| 557 |
-
"grad_norm": 0.018383851274847984,
|
| 558 |
-
"learning_rate": 1.1384615384615385e-05,
|
| 559 |
-
"loss": 0.0025,
|
| 560 |
-
"step": 700
|
| 561 |
-
},
|
| 562 |
-
{
|
| 563 |
-
"epoch": 2.1538461538461537,
|
| 564 |
-
"eval_accuracy": 0.9,
|
| 565 |
-
"eval_loss": 0.43134716153144836,
|
| 566 |
-
"eval_runtime": 4.461,
|
| 567 |
-
"eval_samples_per_second": 33.625,
|
| 568 |
-
"eval_steps_per_second": 8.518,
|
| 569 |
-
"step": 700
|
| 570 |
-
},
|
| 571 |
-
{
|
| 572 |
-
"epoch": 2.2153846153846155,
|
| 573 |
-
"grad_norm": 0.011862259358167648,
|
| 574 |
-
"learning_rate": 1.113846153846154e-05,
|
| 575 |
-
"loss": 0.0171,
|
| 576 |
-
"step": 720
|
| 577 |
-
},
|
| 578 |
-
{
|
| 579 |
-
"epoch": 2.2153846153846155,
|
| 580 |
-
"eval_accuracy": 0.9333333333333333,
|
| 581 |
-
"eval_loss": 0.34005066752433777,
|
| 582 |
-
"eval_runtime": 4.4583,
|
| 583 |
-
"eval_samples_per_second": 33.645,
|
| 584 |
-
"eval_steps_per_second": 8.523,
|
| 585 |
-
"step": 720
|
| 586 |
-
},
|
| 587 |
-
{
|
| 588 |
-
"epoch": 2.276923076923077,
|
| 589 |
-
"grad_norm": 0.0058084093034267426,
|
| 590 |
-
"learning_rate": 1.0892307692307693e-05,
|
| 591 |
-
"loss": 0.2359,
|
| 592 |
-
"step": 740
|
| 593 |
-
},
|
| 594 |
-
{
|
| 595 |
-
"epoch": 2.276923076923077,
|
| 596 |
-
"eval_accuracy": 0.9466666666666667,
|
| 597 |
-
"eval_loss": 0.307921439409256,
|
| 598 |
-
"eval_runtime": 4.4204,
|
| 599 |
-
"eval_samples_per_second": 33.934,
|
| 600 |
-
"eval_steps_per_second": 8.597,
|
| 601 |
-
"step": 740
|
| 602 |
-
},
|
| 603 |
-
{
|
| 604 |
-
"epoch": 2.3384615384615386,
|
| 605 |
-
"grad_norm": 0.016815124079585075,
|
| 606 |
-
"learning_rate": 1.0646153846153845e-05,
|
| 607 |
-
"loss": 0.0966,
|
| 608 |
-
"step": 760
|
| 609 |
-
},
|
| 610 |
-
{
|
| 611 |
-
"epoch": 2.3384615384615386,
|
| 612 |
-
"eval_accuracy": 0.9,
|
| 613 |
-
"eval_loss": 0.4836403429508209,
|
| 614 |
-
"eval_runtime": 4.3792,
|
| 615 |
-
"eval_samples_per_second": 34.253,
|
| 616 |
-
"eval_steps_per_second": 8.677,
|
| 617 |
-
"step": 760
|
| 618 |
-
},
|
| 619 |
-
{
|
| 620 |
-
"epoch": 2.4,
|
| 621 |
-
"grad_norm": 0.015141594223678112,
|
| 622 |
-
"learning_rate": 1.04e-05,
|
| 623 |
-
"loss": 0.0375,
|
| 624 |
-
"step": 780
|
| 625 |
-
},
|
| 626 |
-
{
|
| 627 |
-
"epoch": 2.4,
|
| 628 |
-
"eval_accuracy": 0.88,
|
| 629 |
-
"eval_loss": 0.5408951640129089,
|
| 630 |
-
"eval_runtime": 4.4073,
|
| 631 |
-
"eval_samples_per_second": 34.035,
|
| 632 |
-
"eval_steps_per_second": 8.622,
|
| 633 |
-
"step": 780
|
| 634 |
-
},
|
| 635 |
-
{
|
| 636 |
-
"epoch": 2.4615384615384617,
|
| 637 |
-
"grad_norm": 165.95953369140625,
|
| 638 |
-
"learning_rate": 1.0153846153846154e-05,
|
| 639 |
-
"loss": 0.1249,
|
| 640 |
-
"step": 800
|
| 641 |
-
},
|
| 642 |
-
{
|
| 643 |
-
"epoch": 2.4615384615384617,
|
| 644 |
-
"eval_accuracy": 0.9466666666666667,
|
| 645 |
-
"eval_loss": 0.28574925661087036,
|
| 646 |
-
"eval_runtime": 4.4126,
|
| 647 |
-
"eval_samples_per_second": 33.993,
|
| 648 |
-
"eval_steps_per_second": 8.612,
|
| 649 |
-
"step": 800
|
| 650 |
-
},
|
| 651 |
-
{
|
| 652 |
-
"epoch": 2.523076923076923,
|
| 653 |
-
"grad_norm": 0.012361918576061726,
|
| 654 |
-
"learning_rate": 9.907692307692309e-06,
|
| 655 |
-
"loss": 0.0408,
|
| 656 |
-
"step": 820
|
| 657 |
-
},
|
| 658 |
-
{
|
| 659 |
-
"epoch": 2.523076923076923,
|
| 660 |
-
"eval_accuracy": 0.94,
|
| 661 |
-
"eval_loss": 0.2854212820529938,
|
| 662 |
-
"eval_runtime": 4.4397,
|
| 663 |
-
"eval_samples_per_second": 33.786,
|
| 664 |
-
"eval_steps_per_second": 8.559,
|
| 665 |
-
"step": 820
|
| 666 |
-
},
|
| 667 |
-
{
|
| 668 |
-
"epoch": 2.5846153846153848,
|
| 669 |
-
"grad_norm": 5.374172687530518,
|
| 670 |
-
"learning_rate": 9.661538461538462e-06,
|
| 671 |
-
"loss": 0.0685,
|
| 672 |
-
"step": 840
|
| 673 |
-
},
|
| 674 |
-
{
|
| 675 |
-
"epoch": 2.5846153846153848,
|
| 676 |
-
"eval_accuracy": 0.94,
|
| 677 |
-
"eval_loss": 0.3301023840904236,
|
| 678 |
-
"eval_runtime": 4.4529,
|
| 679 |
-
"eval_samples_per_second": 33.686,
|
| 680 |
-
"eval_steps_per_second": 8.534,
|
| 681 |
-
"step": 840
|
| 682 |
-
},
|
| 683 |
-
{
|
| 684 |
-
"epoch": 2.646153846153846,
|
| 685 |
-
"grad_norm": 0.008875902742147446,
|
| 686 |
-
"learning_rate": 9.415384615384616e-06,
|
| 687 |
-
"loss": 0.0676,
|
| 688 |
-
"step": 860
|
| 689 |
-
},
|
| 690 |
-
{
|
| 691 |
-
"epoch": 2.646153846153846,
|
| 692 |
-
"eval_accuracy": 0.9066666666666666,
|
| 693 |
-
"eval_loss": 0.4170176386833191,
|
| 694 |
-
"eval_runtime": 4.4549,
|
| 695 |
-
"eval_samples_per_second": 33.671,
|
| 696 |
-
"eval_steps_per_second": 8.53,
|
| 697 |
-
"step": 860
|
| 698 |
-
},
|
| 699 |
-
{
|
| 700 |
-
"epoch": 2.707692307692308,
|
| 701 |
-
"grad_norm": 0.04137089475989342,
|
| 702 |
-
"learning_rate": 9.169230769230771e-06,
|
| 703 |
-
"loss": 0.09,
|
| 704 |
-
"step": 880
|
| 705 |
-
},
|
| 706 |
-
{
|
| 707 |
-
"epoch": 2.707692307692308,
|
| 708 |
-
"eval_accuracy": 0.9066666666666666,
|
| 709 |
-
"eval_loss": 0.4454558193683624,
|
| 710 |
-
"eval_runtime": 4.4394,
|
| 711 |
-
"eval_samples_per_second": 33.789,
|
| 712 |
-
"eval_steps_per_second": 8.56,
|
| 713 |
-
"step": 880
|
| 714 |
-
},
|
| 715 |
-
{
|
| 716 |
-
"epoch": 2.769230769230769,
|
| 717 |
-
"grad_norm": 0.015553557313978672,
|
| 718 |
-
"learning_rate": 8.923076923076925e-06,
|
| 719 |
-
"loss": 0.0011,
|
| 720 |
-
"step": 900
|
| 721 |
-
},
|
| 722 |
-
{
|
| 723 |
-
"epoch": 2.769230769230769,
|
| 724 |
-
"eval_accuracy": 0.9266666666666666,
|
| 725 |
-
"eval_loss": 0.39541763067245483,
|
| 726 |
-
"eval_runtime": 4.4614,
|
| 727 |
-
"eval_samples_per_second": 33.622,
|
| 728 |
-
"eval_steps_per_second": 8.518,
|
| 729 |
-
"step": 900
|
| 730 |
-
},
|
| 731 |
-
{
|
| 732 |
-
"epoch": 2.830769230769231,
|
| 733 |
-
"grad_norm": 0.017664454877376556,
|
| 734 |
-
"learning_rate": 8.676923076923078e-06,
|
| 735 |
-
"loss": 0.0198,
|
| 736 |
-
"step": 920
|
| 737 |
-
},
|
| 738 |
-
{
|
| 739 |
-
"epoch": 2.830769230769231,
|
| 740 |
-
"eval_accuracy": 0.9133333333333333,
|
| 741 |
-
"eval_loss": 0.42129218578338623,
|
| 742 |
-
"eval_runtime": 4.4526,
|
| 743 |
-
"eval_samples_per_second": 33.688,
|
| 744 |
-
"eval_steps_per_second": 8.534,
|
| 745 |
-
"step": 920
|
| 746 |
-
},
|
| 747 |
-
{
|
| 748 |
-
"epoch": 2.8923076923076922,
|
| 749 |
-
"grad_norm": 175.416748046875,
|
| 750 |
-
"learning_rate": 8.430769230769231e-06,
|
| 751 |
-
"loss": 0.1061,
|
| 752 |
-
"step": 940
|
| 753 |
-
},
|
| 754 |
-
{
|
| 755 |
-
"epoch": 2.8923076923076922,
|
| 756 |
-
"eval_accuracy": 0.94,
|
| 757 |
-
"eval_loss": 0.3032118082046509,
|
| 758 |
-
"eval_runtime": 4.4334,
|
| 759 |
-
"eval_samples_per_second": 33.834,
|
| 760 |
-
"eval_steps_per_second": 8.571,
|
| 761 |
-
"step": 940
|
| 762 |
-
},
|
| 763 |
-
{
|
| 764 |
-
"epoch": 2.953846153846154,
|
| 765 |
-
"grad_norm": 0.005338897928595543,
|
| 766 |
-
"learning_rate": 8.184615384615385e-06,
|
| 767 |
-
"loss": 0.0003,
|
| 768 |
-
"step": 960
|
| 769 |
-
},
|
| 770 |
-
{
|
| 771 |
-
"epoch": 2.953846153846154,
|
| 772 |
-
"eval_accuracy": 0.92,
|
| 773 |
-
"eval_loss": 0.37594375014305115,
|
| 774 |
-
"eval_runtime": 4.428,
|
| 775 |
-
"eval_samples_per_second": 33.876,
|
| 776 |
-
"eval_steps_per_second": 8.582,
|
| 777 |
-
"step": 960
|
| 778 |
-
},
|
| 779 |
-
{
|
| 780 |
-
"epoch": 3.0153846153846153,
|
| 781 |
-
"grad_norm": 0.007272149436175823,
|
| 782 |
-
"learning_rate": 7.93846153846154e-06,
|
| 783 |
-
"loss": 0.0003,
|
| 784 |
-
"step": 980
|
| 785 |
-
},
|
| 786 |
-
{
|
| 787 |
-
"epoch": 3.0153846153846153,
|
| 788 |
-
"eval_accuracy": 0.92,
|
| 789 |
-
"eval_loss": 0.3951640725135803,
|
| 790 |
-
"eval_runtime": 4.4131,
|
| 791 |
-
"eval_samples_per_second": 33.99,
|
| 792 |
-
"eval_steps_per_second": 8.611,
|
| 793 |
-
"step": 980
|
| 794 |
-
},
|
| 795 |
-
{
|
| 796 |
-
"epoch": 3.076923076923077,
|
| 797 |
-
"grad_norm": 0.0032081459648907185,
|
| 798 |
-
"learning_rate": 7.692307692307694e-06,
|
| 799 |
-
"loss": 0.0037,
|
| 800 |
-
"step": 1000
|
| 801 |
-
},
|
| 802 |
-
{
|
| 803 |
-
"epoch": 3.076923076923077,
|
| 804 |
-
"eval_accuracy": 0.9133333333333333,
|
| 805 |
-
"eval_loss": 0.429452121257782,
|
| 806 |
-
"eval_runtime": 4.4088,
|
| 807 |
-
"eval_samples_per_second": 34.023,
|
| 808 |
-
"eval_steps_per_second": 8.619,
|
| 809 |
-
"step": 1000
|
| 810 |
-
},
|
| 811 |
-
{
|
| 812 |
-
"epoch": 3.1384615384615384,
|
| 813 |
-
"grad_norm": 0.00659064669162035,
|
| 814 |
-
"learning_rate": 7.446153846153846e-06,
|
| 815 |
-
"loss": 0.0003,
|
| 816 |
-
"step": 1020
|
| 817 |
-
},
|
| 818 |
-
{
|
| 819 |
-
"epoch": 3.1384615384615384,
|
| 820 |
-
"eval_accuracy": 0.9133333333333333,
|
| 821 |
-
"eval_loss": 0.49057698249816895,
|
| 822 |
-
"eval_runtime": 4.386,
|
| 823 |
-
"eval_samples_per_second": 34.2,
|
| 824 |
-
"eval_steps_per_second": 8.664,
|
| 825 |
-
"step": 1020
|
| 826 |
-
},
|
| 827 |
-
{
|
| 828 |
-
"epoch": 3.2,
|
| 829 |
-
"grad_norm": 0.043470922857522964,
|
| 830 |
-
"learning_rate": 7.2000000000000005e-06,
|
| 831 |
-
"loss": 0.0003,
|
| 832 |
-
"step": 1040
|
| 833 |
-
},
|
| 834 |
-
{
|
| 835 |
-
"epoch": 3.2,
|
| 836 |
-
"eval_accuracy": 0.9133333333333333,
|
| 837 |
-
"eval_loss": 0.48904499411582947,
|
| 838 |
-
"eval_runtime": 4.5644,
|
| 839 |
-
"eval_samples_per_second": 32.863,
|
| 840 |
-
"eval_steps_per_second": 8.325,
|
| 841 |
-
"step": 1040
|
| 842 |
-
},
|
| 843 |
-
{
|
| 844 |
-
"epoch": 3.2615384615384615,
|
| 845 |
-
"grad_norm": 0.005845973733812571,
|
| 846 |
-
"learning_rate": 6.953846153846154e-06,
|
| 847 |
-
"loss": 0.0642,
|
| 848 |
-
"step": 1060
|
| 849 |
-
},
|
| 850 |
-
{
|
| 851 |
-
"epoch": 3.2615384615384615,
|
| 852 |
-
"eval_accuracy": 0.9333333333333333,
|
| 853 |
-
"eval_loss": 0.34622737765312195,
|
| 854 |
-
"eval_runtime": 4.642,
|
| 855 |
-
"eval_samples_per_second": 32.313,
|
| 856 |
-
"eval_steps_per_second": 8.186,
|
| 857 |
-
"step": 1060
|
| 858 |
-
},
|
| 859 |
-
{
|
| 860 |
-
"epoch": 3.3230769230769233,
|
| 861 |
-
"grad_norm": 0.015024982392787933,
|
| 862 |
-
"learning_rate": 6.707692307692308e-06,
|
| 863 |
-
"loss": 0.0003,
|
| 864 |
-
"step": 1080
|
| 865 |
-
},
|
| 866 |
-
{
|
| 867 |
-
"epoch": 3.3230769230769233,
|
| 868 |
-
"eval_accuracy": 0.9466666666666667,
|
| 869 |
-
"eval_loss": 0.3094027638435364,
|
| 870 |
-
"eval_runtime": 4.5041,
|
| 871 |
-
"eval_samples_per_second": 33.303,
|
| 872 |
-
"eval_steps_per_second": 8.437,
|
| 873 |
-
"step": 1080
|
| 874 |
-
},
|
| 875 |
-
{
|
| 876 |
-
"epoch": 3.3846153846153846,
|
| 877 |
-
"grad_norm": 0.004358809906989336,
|
| 878 |
-
"learning_rate": 6.461538461538463e-06,
|
| 879 |
-
"loss": 0.0003,
|
| 880 |
-
"step": 1100
|
| 881 |
-
},
|
| 882 |
-
{
|
| 883 |
-
"epoch": 3.3846153846153846,
|
| 884 |
-
"eval_accuracy": 0.94,
|
| 885 |
-
"eval_loss": 0.32816219329833984,
|
| 886 |
-
"eval_runtime": 4.3854,
|
| 887 |
-
"eval_samples_per_second": 34.204,
|
| 888 |
-
"eval_steps_per_second": 8.665,
|
| 889 |
-
"step": 1100
|
| 890 |
-
},
|
| 891 |
-
{
|
| 892 |
-
"epoch": 3.4461538461538463,
|
| 893 |
-
"grad_norm": 0.003102461341768503,
|
| 894 |
-
"learning_rate": 6.215384615384615e-06,
|
| 895 |
-
"loss": 0.1037,
|
| 896 |
-
"step": 1120
|
| 897 |
-
},
|
| 898 |
-
{
|
| 899 |
-
"epoch": 3.4461538461538463,
|
| 900 |
-
"eval_accuracy": 0.9333333333333333,
|
| 901 |
-
"eval_loss": 0.38093501329421997,
|
| 902 |
-
"eval_runtime": 4.3086,
|
| 903 |
-
"eval_samples_per_second": 34.814,
|
| 904 |
-
"eval_steps_per_second": 8.82,
|
| 905 |
-
"step": 1120
|
| 906 |
-
},
|
| 907 |
-
{
|
| 908 |
-
"epoch": 3.5076923076923077,
|
| 909 |
-
"grad_norm": 1.403334379196167,
|
| 910 |
-
"learning_rate": 5.9692307692307695e-06,
|
| 911 |
-
"loss": 0.0006,
|
| 912 |
-
"step": 1140
|
| 913 |
-
},
|
| 914 |
-
{
|
| 915 |
-
"epoch": 3.5076923076923077,
|
| 916 |
-
"eval_accuracy": 0.9266666666666666,
|
| 917 |
-
"eval_loss": 0.44484424591064453,
|
| 918 |
-
"eval_runtime": 4.3328,
|
| 919 |
-
"eval_samples_per_second": 34.62,
|
| 920 |
-
"eval_steps_per_second": 8.77,
|
| 921 |
-
"step": 1140
|
| 922 |
-
},
|
| 923 |
-
{
|
| 924 |
-
"epoch": 3.569230769230769,
|
| 925 |
-
"grad_norm": 0.0068647353909909725,
|
| 926 |
-
"learning_rate": 5.723076923076923e-06,
|
| 927 |
-
"loss": 0.0942,
|
| 928 |
-
"step": 1160
|
| 929 |
-
},
|
| 930 |
-
{
|
| 931 |
-
"epoch": 3.569230769230769,
|
| 932 |
-
"eval_accuracy": 0.8866666666666667,
|
| 933 |
-
"eval_loss": 0.6030946969985962,
|
| 934 |
-
"eval_runtime": 4.4045,
|
| 935 |
-
"eval_samples_per_second": 34.056,
|
| 936 |
-
"eval_steps_per_second": 8.627,
|
| 937 |
-
"step": 1160
|
| 938 |
-
},
|
| 939 |
-
{
|
| 940 |
-
"epoch": 3.6307692307692307,
|
| 941 |
-
"grad_norm": 0.00668348977342248,
|
| 942 |
-
"learning_rate": 5.476923076923077e-06,
|
| 943 |
-
"loss": 0.0003,
|
| 944 |
-
"step": 1180
|
| 945 |
-
},
|
| 946 |
-
{
|
| 947 |
-
"epoch": 3.6307692307692307,
|
| 948 |
-
"eval_accuracy": 0.8866666666666667,
|
| 949 |
-
"eval_loss": 0.4964194595813751,
|
| 950 |
-
"eval_runtime": 4.4815,
|
| 951 |
-
"eval_samples_per_second": 33.471,
|
| 952 |
-
"eval_steps_per_second": 8.479,
|
| 953 |
-
"step": 1180
|
| 954 |
-
},
|
| 955 |
-
{
|
| 956 |
-
"epoch": 3.6923076923076925,
|
| 957 |
-
"grad_norm": 0.009669807739555836,
|
| 958 |
-
"learning_rate": 5.230769230769232e-06,
|
| 959 |
-
"loss": 0.0007,
|
| 960 |
-
"step": 1200
|
| 961 |
-
},
|
| 962 |
-
{
|
| 963 |
-
"epoch": 3.6923076923076925,
|
| 964 |
-
"eval_accuracy": 0.8866666666666667,
|
| 965 |
-
"eval_loss": 0.5268967151641846,
|
| 966 |
-
"eval_runtime": 4.5142,
|
| 967 |
-
"eval_samples_per_second": 33.228,
|
| 968 |
-
"eval_steps_per_second": 8.418,
|
| 969 |
-
"step": 1200
|
| 970 |
-
},
|
| 971 |
-
{
|
| 972 |
-
"epoch": 3.753846153846154,
|
| 973 |
-
"grad_norm": 0.00334552931599319,
|
| 974 |
-
"learning_rate": 4.984615384615385e-06,
|
| 975 |
-
"loss": 0.0887,
|
| 976 |
-
"step": 1220
|
| 977 |
-
},
|
| 978 |
-
{
|
| 979 |
-
"epoch": 3.753846153846154,
|
| 980 |
-
"eval_accuracy": 0.8866666666666667,
|
| 981 |
-
"eval_loss": 0.49135467410087585,
|
| 982 |
-
"eval_runtime": 4.4888,
|
| 983 |
-
"eval_samples_per_second": 33.417,
|
| 984 |
-
"eval_steps_per_second": 8.466,
|
| 985 |
-
"step": 1220
|
| 986 |
-
},
|
| 987 |
-
{
|
| 988 |
-
"epoch": 3.815384615384615,
|
| 989 |
-
"grad_norm": 0.005591992288827896,
|
| 990 |
-
"learning_rate": 4.738461538461539e-06,
|
| 991 |
-
"loss": 0.0003,
|
| 992 |
-
"step": 1240
|
| 993 |
-
},
|
| 994 |
-
{
|
| 995 |
-
"epoch": 3.815384615384615,
|
| 996 |
-
"eval_accuracy": 0.9266666666666666,
|
| 997 |
-
"eval_loss": 0.395882248878479,
|
| 998 |
-
"eval_runtime": 4.4355,
|
| 999 |
-
"eval_samples_per_second": 33.818,
|
| 1000 |
-
"eval_steps_per_second": 8.567,
|
| 1001 |
-
"step": 1240
|
| 1002 |
-
},
|
| 1003 |
-
{
|
| 1004 |
-
"epoch": 3.876923076923077,
|
| 1005 |
-
"grad_norm": 0.02592817321419716,
|
| 1006 |
-
"learning_rate": 4.492307692307693e-06,
|
| 1007 |
-
"loss": 0.0008,
|
| 1008 |
-
"step": 1260
|
| 1009 |
-
},
|
| 1010 |
-
{
|
| 1011 |
-
"epoch": 3.876923076923077,
|
| 1012 |
-
"eval_accuracy": 0.9266666666666666,
|
| 1013 |
-
"eval_loss": 0.42400792241096497,
|
| 1014 |
-
"eval_runtime": 4.4143,
|
| 1015 |
-
"eval_samples_per_second": 33.98,
|
| 1016 |
-
"eval_steps_per_second": 8.608,
|
| 1017 |
-
"step": 1260
|
| 1018 |
-
},
|
| 1019 |
-
{
|
| 1020 |
-
"epoch": 3.9384615384615387,
|
| 1021 |
-
"grad_norm": 0.0067848521284759045,
|
| 1022 |
-
"learning_rate": 4.246153846153846e-06,
|
| 1023 |
-
"loss": 0.0003,
|
| 1024 |
-
"step": 1280
|
| 1025 |
-
},
|
| 1026 |
-
{
|
| 1027 |
-
"epoch": 3.9384615384615387,
|
| 1028 |
-
"eval_accuracy": 0.92,
|
| 1029 |
-
"eval_loss": 0.43341755867004395,
|
| 1030 |
-
"eval_runtime": 4.3946,
|
| 1031 |
-
"eval_samples_per_second": 34.133,
|
| 1032 |
-
"eval_steps_per_second": 8.647,
|
| 1033 |
-
"step": 1280
|
| 1034 |
-
},
|
| 1035 |
-
{
|
| 1036 |
-
"epoch": 4.0,
|
| 1037 |
-
"grad_norm": 0.004882505163550377,
|
| 1038 |
-
"learning_rate": 4.000000000000001e-06,
|
| 1039 |
-
"loss": 0.0003,
|
| 1040 |
-
"step": 1300
|
| 1041 |
-
},
|
| 1042 |
-
{
|
| 1043 |
-
"epoch": 4.0,
|
| 1044 |
-
"eval_accuracy": 0.9266666666666666,
|
| 1045 |
-
"eval_loss": 0.42421114444732666,
|
| 1046 |
-
"eval_runtime": 4.4076,
|
| 1047 |
-
"eval_samples_per_second": 34.032,
|
| 1048 |
-
"eval_steps_per_second": 8.621,
|
| 1049 |
-
"step": 1300
|
| 1050 |
-
},
|
| 1051 |
-
{
|
| 1052 |
-
"epoch": 4.061538461538461,
|
| 1053 |
-
"grad_norm": 0.006306629162281752,
|
| 1054 |
-
"learning_rate": 3.753846153846154e-06,
|
| 1055 |
-
"loss": 0.0002,
|
| 1056 |
-
"step": 1320
|
| 1057 |
-
},
|
| 1058 |
-
{
|
| 1059 |
-
"epoch": 4.061538461538461,
|
| 1060 |
-
"eval_accuracy": 0.9266666666666666,
|
| 1061 |
-
"eval_loss": 0.42182713747024536,
|
| 1062 |
-
"eval_runtime": 4.4367,
|
| 1063 |
-
"eval_samples_per_second": 33.809,
|
| 1064 |
-
"eval_steps_per_second": 8.565,
|
| 1065 |
-
"step": 1320
|
| 1066 |
-
},
|
| 1067 |
-
{
|
| 1068 |
-
"epoch": 4.123076923076923,
|
| 1069 |
-
"grad_norm": 0.10213489085435867,
|
| 1070 |
-
"learning_rate": 3.507692307692308e-06,
|
| 1071 |
-
"loss": 0.0003,
|
| 1072 |
-
"step": 1340
|
| 1073 |
-
},
|
| 1074 |
-
{
|
| 1075 |
-
"epoch": 4.123076923076923,
|
| 1076 |
-
"eval_accuracy": 0.9266666666666666,
|
| 1077 |
-
"eval_loss": 0.41865241527557373,
|
| 1078 |
-
"eval_runtime": 4.4189,
|
| 1079 |
-
"eval_samples_per_second": 33.945,
|
| 1080 |
-
"eval_steps_per_second": 8.599,
|
| 1081 |
-
"step": 1340
|
| 1082 |
-
},
|
| 1083 |
-
{
|
| 1084 |
-
"epoch": 4.184615384615385,
|
| 1085 |
-
"grad_norm": 0.007508518174290657,
|
| 1086 |
-
"learning_rate": 3.2615384615384615e-06,
|
| 1087 |
-
"loss": 0.0002,
|
| 1088 |
-
"step": 1360
|
| 1089 |
-
},
|
| 1090 |
-
{
|
| 1091 |
-
"epoch": 4.184615384615385,
|
| 1092 |
-
"eval_accuracy": 0.9266666666666666,
|
| 1093 |
-
"eval_loss": 0.41028958559036255,
|
| 1094 |
-
"eval_runtime": 4.491,
|
| 1095 |
-
"eval_samples_per_second": 33.4,
|
| 1096 |
-
"eval_steps_per_second": 8.461,
|
| 1097 |
-
"step": 1360
|
| 1098 |
-
},
|
| 1099 |
-
{
|
| 1100 |
-
"epoch": 4.246153846153846,
|
| 1101 |
-
"grad_norm": 0.004084484186023474,
|
| 1102 |
-
"learning_rate": 3.0153846153846154e-06,
|
| 1103 |
-
"loss": 0.0002,
|
| 1104 |
-
"step": 1380
|
| 1105 |
-
},
|
| 1106 |
-
{
|
| 1107 |
-
"epoch": 4.246153846153846,
|
| 1108 |
-
"eval_accuracy": 0.9266666666666666,
|
| 1109 |
-
"eval_loss": 0.4090527892112732,
|
| 1110 |
-
"eval_runtime": 4.4734,
|
| 1111 |
-
"eval_samples_per_second": 33.532,
|
| 1112 |
-
"eval_steps_per_second": 8.495,
|
| 1113 |
-
"step": 1380
|
| 1114 |
-
},
|
| 1115 |
-
{
|
| 1116 |
-
"epoch": 4.3076923076923075,
|
| 1117 |
-
"grad_norm": 0.00797939207404852,
|
| 1118 |
-
"learning_rate": 2.7692307692307697e-06,
|
| 1119 |
-
"loss": 0.0002,
|
| 1120 |
-
"step": 1400
|
| 1121 |
-
},
|
| 1122 |
-
{
|
| 1123 |
-
"epoch": 4.3076923076923075,
|
| 1124 |
-
"eval_accuracy": 0.9266666666666666,
|
| 1125 |
-
"eval_loss": 0.4111497402191162,
|
| 1126 |
-
"eval_runtime": 4.4612,
|
| 1127 |
-
"eval_samples_per_second": 33.624,
|
| 1128 |
-
"eval_steps_per_second": 8.518,
|
| 1129 |
-
"step": 1400
|
| 1130 |
-
},
|
| 1131 |
-
{
|
| 1132 |
-
"epoch": 4.36923076923077,
|
| 1133 |
-
"grad_norm": 0.0033812555484473705,
|
| 1134 |
-
"learning_rate": 2.523076923076923e-06,
|
| 1135 |
-
"loss": 0.0003,
|
| 1136 |
-
"step": 1420
|
| 1137 |
-
},
|
| 1138 |
-
{
|
| 1139 |
-
"epoch": 4.36923076923077,
|
| 1140 |
-
"eval_accuracy": 0.9266666666666666,
|
| 1141 |
-
"eval_loss": 0.40916740894317627,
|
| 1142 |
-
"eval_runtime": 4.4676,
|
| 1143 |
-
"eval_samples_per_second": 33.575,
|
| 1144 |
-
"eval_steps_per_second": 8.506,
|
| 1145 |
-
"step": 1420
|
| 1146 |
-
},
|
| 1147 |
-
{
|
| 1148 |
-
"epoch": 4.430769230769231,
|
| 1149 |
-
"grad_norm": 0.005078181624412537,
|
| 1150 |
-
"learning_rate": 2.276923076923077e-06,
|
| 1151 |
-
"loss": 0.0003,
|
| 1152 |
-
"step": 1440
|
| 1153 |
-
},
|
| 1154 |
-
{
|
| 1155 |
-
"epoch": 4.430769230769231,
|
| 1156 |
-
"eval_accuracy": 0.9333333333333333,
|
| 1157 |
-
"eval_loss": 0.3990814685821533,
|
| 1158 |
-
"eval_runtime": 4.4277,
|
| 1159 |
-
"eval_samples_per_second": 33.877,
|
| 1160 |
-
"eval_steps_per_second": 8.582,
|
| 1161 |
-
"step": 1440
|
| 1162 |
-
},
|
| 1163 |
-
{
|
| 1164 |
-
"epoch": 4.492307692307692,
|
| 1165 |
-
"grad_norm": 0.003911417443305254,
|
| 1166 |
-
"learning_rate": 2.030769230769231e-06,
|
| 1167 |
-
"loss": 0.0002,
|
| 1168 |
-
"step": 1460
|
| 1169 |
-
},
|
| 1170 |
-
{
|
| 1171 |
-
"epoch": 4.492307692307692,
|
| 1172 |
-
"eval_accuracy": 0.9333333333333333,
|
| 1173 |
-
"eval_loss": 0.39907512068748474,
|
| 1174 |
-
"eval_runtime": 4.4194,
|
| 1175 |
-
"eval_samples_per_second": 33.941,
|
| 1176 |
-
"eval_steps_per_second": 8.598,
|
| 1177 |
-
"step": 1460
|
| 1178 |
-
},
|
| 1179 |
-
{
|
| 1180 |
-
"epoch": 4.553846153846154,
|
| 1181 |
-
"grad_norm": 0.005002380348742008,
|
| 1182 |
-
"learning_rate": 1.7846153846153846e-06,
|
| 1183 |
-
"loss": 0.0002,
|
| 1184 |
-
"step": 1480
|
| 1185 |
-
},
|
| 1186 |
-
{
|
| 1187 |
-
"epoch": 4.553846153846154,
|
| 1188 |
-
"eval_accuracy": 0.9333333333333333,
|
| 1189 |
-
"eval_loss": 0.39858585596084595,
|
| 1190 |
-
"eval_runtime": 4.4069,
|
| 1191 |
-
"eval_samples_per_second": 34.037,
|
| 1192 |
-
"eval_steps_per_second": 8.623,
|
| 1193 |
-
"step": 1480
|
| 1194 |
-
},
|
| 1195 |
-
{
|
| 1196 |
-
"epoch": 4.615384615384615,
|
| 1197 |
-
"grad_norm": 0.005623374599963427,
|
| 1198 |
-
"learning_rate": 1.5384615384615387e-06,
|
| 1199 |
-
"loss": 0.0004,
|
| 1200 |
-
"step": 1500
|
| 1201 |
-
},
|
| 1202 |
-
{
|
| 1203 |
-
"epoch": 4.615384615384615,
|
| 1204 |
-
"eval_accuracy": 0.9333333333333333,
|
| 1205 |
-
"eval_loss": 0.4055434763431549,
|
| 1206 |
-
"eval_runtime": 4.4211,
|
| 1207 |
-
"eval_samples_per_second": 33.928,
|
| 1208 |
-
"eval_steps_per_second": 8.595,
|
| 1209 |
-
"step": 1500
|
| 1210 |
-
},
|
| 1211 |
-
{
|
| 1212 |
-
"epoch": 4.676923076923077,
|
| 1213 |
-
"grad_norm": 0.007997775450348854,
|
| 1214 |
-
"learning_rate": 1.2923076923076924e-06,
|
| 1215 |
-
"loss": 0.1421,
|
| 1216 |
-
"step": 1520
|
| 1217 |
-
},
|
| 1218 |
-
{
|
| 1219 |
-
"epoch": 4.676923076923077,
|
| 1220 |
-
"eval_accuracy": 0.9333333333333333,
|
| 1221 |
-
"eval_loss": 0.400637149810791,
|
| 1222 |
-
"eval_runtime": 4.3593,
|
| 1223 |
-
"eval_samples_per_second": 34.41,
|
| 1224 |
-
"eval_steps_per_second": 8.717,
|
| 1225 |
-
"step": 1520
|
| 1226 |
-
},
|
| 1227 |
-
{
|
| 1228 |
-
"epoch": 4.7384615384615385,
|
| 1229 |
-
"grad_norm": 0.004181304015219212,
|
| 1230 |
-
"learning_rate": 1.0461538461538463e-06,
|
| 1231 |
-
"loss": 0.0002,
|
| 1232 |
-
"step": 1540
|
| 1233 |
-
},
|
| 1234 |
-
{
|
| 1235 |
-
"epoch": 4.7384615384615385,
|
| 1236 |
-
"eval_accuracy": 0.9266666666666666,
|
| 1237 |
-
"eval_loss": 0.40295225381851196,
|
| 1238 |
-
"eval_runtime": 4.5588,
|
| 1239 |
-
"eval_samples_per_second": 32.903,
|
| 1240 |
-
"eval_steps_per_second": 8.336,
|
| 1241 |
-
"step": 1540
|
| 1242 |
-
},
|
| 1243 |
-
{
|
| 1244 |
-
"epoch": 4.8,
|
| 1245 |
-
"grad_norm": 0.003899338422343135,
|
| 1246 |
-
"learning_rate": 8.000000000000001e-07,
|
| 1247 |
-
"loss": 0.0002,
|
| 1248 |
-
"step": 1560
|
| 1249 |
-
},
|
| 1250 |
-
{
|
| 1251 |
-
"epoch": 4.8,
|
| 1252 |
-
"eval_accuracy": 0.9266666666666666,
|
| 1253 |
-
"eval_loss": 0.4034216105937958,
|
| 1254 |
-
"eval_runtime": 4.6347,
|
| 1255 |
-
"eval_samples_per_second": 32.365,
|
| 1256 |
-
"eval_steps_per_second": 8.199,
|
| 1257 |
-
"step": 1560
|
| 1258 |
-
},
|
| 1259 |
-
{
|
| 1260 |
-
"epoch": 4.861538461538462,
|
| 1261 |
-
"grad_norm": 0.004380157217383385,
|
| 1262 |
-
"learning_rate": 5.53846153846154e-07,
|
| 1263 |
-
"loss": 0.0628,
|
| 1264 |
-
"step": 1580
|
| 1265 |
-
},
|
| 1266 |
-
{
|
| 1267 |
-
"epoch": 4.861538461538462,
|
| 1268 |
-
"eval_accuracy": 0.9333333333333333,
|
| 1269 |
-
"eval_loss": 0.38764962553977966,
|
| 1270 |
-
"eval_runtime": 4.5609,
|
| 1271 |
-
"eval_samples_per_second": 32.888,
|
| 1272 |
-
"eval_steps_per_second": 8.332,
|
| 1273 |
-
"step": 1580
|
| 1274 |
-
},
|
| 1275 |
-
{
|
| 1276 |
-
"epoch": 4.923076923076923,
|
| 1277 |
-
"grad_norm": 0.004398785065859556,
|
| 1278 |
-
"learning_rate": 3.0769230769230774e-07,
|
| 1279 |
-
"loss": 0.0003,
|
| 1280 |
-
"step": 1600
|
| 1281 |
-
},
|
| 1282 |
-
{
|
| 1283 |
-
"epoch": 4.923076923076923,
|
| 1284 |
-
"eval_accuracy": 0.9333333333333333,
|
| 1285 |
-
"eval_loss": 0.38795334100723267,
|
| 1286 |
-
"eval_runtime": 4.4706,
|
| 1287 |
-
"eval_samples_per_second": 33.553,
|
| 1288 |
-
"eval_steps_per_second": 8.5,
|
| 1289 |
-
"step": 1600
|
| 1290 |
-
},
|
| 1291 |
-
{
|
| 1292 |
-
"epoch": 4.984615384615385,
|
| 1293 |
-
"grad_norm": 0.0024876066017895937,
|
| 1294 |
-
"learning_rate": 6.153846153846154e-08,
|
| 1295 |
-
"loss": 0.0003,
|
| 1296 |
-
"step": 1620
|
| 1297 |
-
},
|
| 1298 |
-
{
|
| 1299 |
-
"epoch": 4.984615384615385,
|
| 1300 |
-
"eval_accuracy": 0.9333333333333333,
|
| 1301 |
-
"eval_loss": 0.39026668667793274,
|
| 1302 |
-
"eval_runtime": 4.3714,
|
| 1303 |
-
"eval_samples_per_second": 34.314,
|
| 1304 |
-
"eval_steps_per_second": 8.693,
|
| 1305 |
-
"step": 1620
|
| 1306 |
}
|
| 1307 |
],
|
| 1308 |
"logging_steps": 20,
|
| 1309 |
-
"max_steps":
|
| 1310 |
"num_input_tokens_seen": 0,
|
| 1311 |
"num_train_epochs": 5,
|
| 1312 |
"save_steps": 500,
|
|
@@ -1317,12 +421,12 @@
|
|
| 1317 |
"should_evaluate": false,
|
| 1318 |
"should_log": false,
|
| 1319 |
"should_save": true,
|
| 1320 |
-
"should_training_stop":
|
| 1321 |
},
|
| 1322 |
"attributes": {}
|
| 1323 |
}
|
| 1324 |
},
|
| 1325 |
-
"total_flos":
|
| 1326 |
"train_batch_size": 4,
|
| 1327 |
"trial_name": null,
|
| 1328 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.2427118569612503,
|
| 3 |
+
"best_model_checkpoint": "./results/checkpoint-340",
|
| 4 |
+
"epoch": 1.4326647564469914,
|
| 5 |
"eval_steps": 20,
|
| 6 |
+
"global_step": 500,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
+
"epoch": 0.05730659025787966,
|
| 13 |
+
"grad_norm": 12.298672676086426,
|
| 14 |
+
"learning_rate": 1.9770773638968482e-05,
|
| 15 |
+
"loss": 0.5003,
|
| 16 |
"step": 20
|
| 17 |
},
|
| 18 |
{
|
| 19 |
+
"epoch": 0.05730659025787966,
|
| 20 |
+
"eval_accuracy": 0.8227848101265823,
|
| 21 |
+
"eval_loss": 0.35164713859558105,
|
| 22 |
+
"eval_runtime": 3.7107,
|
| 23 |
+
"eval_samples_per_second": 42.58,
|
| 24 |
+
"eval_steps_per_second": 10.78,
|
| 25 |
"step": 20
|
| 26 |
},
|
| 27 |
{
|
| 28 |
+
"epoch": 0.11461318051575932,
|
| 29 |
+
"grad_norm": 14.603419303894043,
|
| 30 |
+
"learning_rate": 1.9541547277936966e-05,
|
| 31 |
+
"loss": 0.3891,
|
| 32 |
"step": 40
|
| 33 |
},
|
| 34 |
{
|
| 35 |
+
"epoch": 0.11461318051575932,
|
| 36 |
+
"eval_accuracy": 0.8227848101265823,
|
| 37 |
+
"eval_loss": 0.3729996383190155,
|
| 38 |
+
"eval_runtime": 3.7683,
|
| 39 |
+
"eval_samples_per_second": 41.928,
|
| 40 |
+
"eval_steps_per_second": 10.615,
|
| 41 |
"step": 40
|
| 42 |
},
|
| 43 |
{
|
| 44 |
+
"epoch": 0.17191977077363896,
|
| 45 |
+
"grad_norm": 14.791304588317871,
|
| 46 |
+
"learning_rate": 1.9312320916905443e-05,
|
| 47 |
+
"loss": 0.4264,
|
| 48 |
"step": 60
|
| 49 |
},
|
| 50 |
{
|
| 51 |
+
"epoch": 0.17191977077363896,
|
| 52 |
+
"eval_accuracy": 0.8164556962025317,
|
| 53 |
+
"eval_loss": 0.3530322313308716,
|
| 54 |
+
"eval_runtime": 3.8072,
|
| 55 |
+
"eval_samples_per_second": 41.5,
|
| 56 |
+
"eval_steps_per_second": 10.506,
|
| 57 |
"step": 60
|
| 58 |
},
|
| 59 |
{
|
| 60 |
+
"epoch": 0.22922636103151864,
|
| 61 |
+
"grad_norm": 20.58723258972168,
|
| 62 |
+
"learning_rate": 1.9083094555873927e-05,
|
| 63 |
+
"loss": 0.421,
|
| 64 |
"step": 80
|
| 65 |
},
|
| 66 |
{
|
| 67 |
+
"epoch": 0.22922636103151864,
|
| 68 |
+
"eval_accuracy": 0.8987341772151899,
|
| 69 |
+
"eval_loss": 0.24272167682647705,
|
| 70 |
+
"eval_runtime": 3.831,
|
| 71 |
+
"eval_samples_per_second": 41.243,
|
| 72 |
+
"eval_steps_per_second": 10.441,
|
| 73 |
"step": 80
|
| 74 |
},
|
| 75 |
{
|
| 76 |
+
"epoch": 0.28653295128939826,
|
| 77 |
+
"grad_norm": 1.8356260061264038,
|
| 78 |
+
"learning_rate": 1.8853868194842408e-05,
|
| 79 |
+
"loss": 0.37,
|
| 80 |
"step": 100
|
| 81 |
},
|
| 82 |
{
|
| 83 |
+
"epoch": 0.28653295128939826,
|
| 84 |
+
"eval_accuracy": 0.8417721518987342,
|
| 85 |
+
"eval_loss": 0.4437476098537445,
|
| 86 |
+
"eval_runtime": 3.8974,
|
| 87 |
+
"eval_samples_per_second": 40.54,
|
| 88 |
+
"eval_steps_per_second": 10.263,
|
| 89 |
"step": 100
|
| 90 |
},
|
| 91 |
{
|
| 92 |
+
"epoch": 0.3438395415472779,
|
| 93 |
+
"grad_norm": 16.2299861907959,
|
| 94 |
+
"learning_rate": 1.8624641833810892e-05,
|
| 95 |
+
"loss": 0.447,
|
| 96 |
"step": 120
|
| 97 |
},
|
| 98 |
{
|
| 99 |
+
"epoch": 0.3438395415472779,
|
| 100 |
+
"eval_accuracy": 0.8481012658227848,
|
| 101 |
+
"eval_loss": 0.34341034293174744,
|
| 102 |
+
"eval_runtime": 3.8961,
|
| 103 |
+
"eval_samples_per_second": 40.553,
|
| 104 |
+
"eval_steps_per_second": 10.267,
|
| 105 |
"step": 120
|
| 106 |
},
|
| 107 |
{
|
| 108 |
+
"epoch": 0.40114613180515757,
|
| 109 |
+
"grad_norm": 3.1842381954193115,
|
| 110 |
+
"learning_rate": 1.8395415472779372e-05,
|
| 111 |
+
"loss": 0.2692,
|
| 112 |
"step": 140
|
| 113 |
},
|
| 114 |
{
|
| 115 |
+
"epoch": 0.40114613180515757,
|
| 116 |
+
"eval_accuracy": 0.8860759493670886,
|
| 117 |
+
"eval_loss": 0.354509174823761,
|
| 118 |
+
"eval_runtime": 3.9827,
|
| 119 |
+
"eval_samples_per_second": 39.671,
|
| 120 |
+
"eval_steps_per_second": 10.043,
|
| 121 |
"step": 140
|
| 122 |
},
|
| 123 |
{
|
| 124 |
+
"epoch": 0.4584527220630373,
|
| 125 |
+
"grad_norm": 0.07769237458705902,
|
| 126 |
+
"learning_rate": 1.8166189111747853e-05,
|
| 127 |
+
"loss": 0.2534,
|
| 128 |
"step": 160
|
| 129 |
},
|
| 130 |
{
|
| 131 |
+
"epoch": 0.4584527220630373,
|
| 132 |
+
"eval_accuracy": 0.9050632911392406,
|
| 133 |
+
"eval_loss": 0.36426371335983276,
|
| 134 |
+
"eval_runtime": 4.1167,
|
| 135 |
+
"eval_samples_per_second": 38.38,
|
| 136 |
+
"eval_steps_per_second": 9.717,
|
| 137 |
"step": 160
|
| 138 |
},
|
| 139 |
{
|
| 140 |
+
"epoch": 0.5157593123209169,
|
| 141 |
+
"grad_norm": 0.09249360114336014,
|
| 142 |
+
"learning_rate": 1.7936962750716333e-05,
|
| 143 |
+
"loss": 0.3963,
|
| 144 |
"step": 180
|
| 145 |
},
|
| 146 |
{
|
| 147 |
+
"epoch": 0.5157593123209169,
|
| 148 |
+
"eval_accuracy": 0.8734177215189873,
|
| 149 |
+
"eval_loss": 0.4266941249370575,
|
| 150 |
+
"eval_runtime": 4.1856,
|
| 151 |
+
"eval_samples_per_second": 37.748,
|
| 152 |
+
"eval_steps_per_second": 9.557,
|
| 153 |
"step": 180
|
| 154 |
},
|
| 155 |
{
|
| 156 |
+
"epoch": 0.5730659025787965,
|
| 157 |
+
"grad_norm": 28.059228897094727,
|
| 158 |
+
"learning_rate": 1.7707736389684814e-05,
|
| 159 |
+
"loss": 0.2337,
|
| 160 |
"step": 200
|
| 161 |
},
|
| 162 |
{
|
| 163 |
+
"epoch": 0.5730659025787965,
|
| 164 |
+
"eval_accuracy": 0.8670886075949367,
|
| 165 |
+
"eval_loss": 0.5053204894065857,
|
| 166 |
+
"eval_runtime": 4.2429,
|
| 167 |
+
"eval_samples_per_second": 37.239,
|
| 168 |
+
"eval_steps_per_second": 9.427,
|
| 169 |
"step": 200
|
| 170 |
},
|
| 171 |
{
|
| 172 |
+
"epoch": 0.6303724928366762,
|
| 173 |
+
"grad_norm": 8.809836387634277,
|
| 174 |
+
"learning_rate": 1.7478510028653298e-05,
|
| 175 |
+
"loss": 0.4065,
|
| 176 |
"step": 220
|
| 177 |
},
|
| 178 |
{
|
| 179 |
+
"epoch": 0.6303724928366762,
|
| 180 |
+
"eval_accuracy": 0.9050632911392406,
|
| 181 |
+
"eval_loss": 0.37862661480903625,
|
| 182 |
+
"eval_runtime": 4.1359,
|
| 183 |
+
"eval_samples_per_second": 38.202,
|
| 184 |
+
"eval_steps_per_second": 9.671,
|
| 185 |
"step": 220
|
| 186 |
},
|
| 187 |
{
|
| 188 |
+
"epoch": 0.6876790830945558,
|
| 189 |
+
"grad_norm": 31.02484703063965,
|
| 190 |
+
"learning_rate": 1.724928366762178e-05,
|
| 191 |
+
"loss": 0.4239,
|
| 192 |
"step": 240
|
| 193 |
},
|
| 194 |
{
|
| 195 |
+
"epoch": 0.6876790830945558,
|
| 196 |
+
"eval_accuracy": 0.9050632911392406,
|
| 197 |
+
"eval_loss": 0.27570071816444397,
|
| 198 |
+
"eval_runtime": 4.1471,
|
| 199 |
+
"eval_samples_per_second": 38.099,
|
| 200 |
+
"eval_steps_per_second": 9.645,
|
| 201 |
"step": 240
|
| 202 |
},
|
| 203 |
{
|
| 204 |
+
"epoch": 0.7449856733524355,
|
| 205 |
+
"grad_norm": 0.2250363677740097,
|
| 206 |
+
"learning_rate": 1.702005730659026e-05,
|
| 207 |
+
"loss": 0.2728,
|
| 208 |
"step": 260
|
| 209 |
},
|
| 210 |
{
|
| 211 |
+
"epoch": 0.7449856733524355,
|
| 212 |
+
"eval_accuracy": 0.9050632911392406,
|
| 213 |
+
"eval_loss": 0.30951112508773804,
|
| 214 |
+
"eval_runtime": 4.0996,
|
| 215 |
+
"eval_samples_per_second": 38.54,
|
| 216 |
+
"eval_steps_per_second": 9.757,
|
| 217 |
"step": 260
|
| 218 |
},
|
| 219 |
{
|
| 220 |
+
"epoch": 0.8022922636103151,
|
| 221 |
+
"grad_norm": 10.018088340759277,
|
| 222 |
+
"learning_rate": 1.679083094555874e-05,
|
| 223 |
+
"loss": 0.3323,
|
| 224 |
"step": 280
|
| 225 |
},
|
| 226 |
{
|
| 227 |
+
"epoch": 0.8022922636103151,
|
| 228 |
+
"eval_accuracy": 0.9177215189873418,
|
| 229 |
+
"eval_loss": 0.3325574994087219,
|
| 230 |
+
"eval_runtime": 4.1341,
|
| 231 |
+
"eval_samples_per_second": 38.219,
|
| 232 |
+
"eval_steps_per_second": 9.676,
|
| 233 |
"step": 280
|
| 234 |
},
|
| 235 |
{
|
| 236 |
+
"epoch": 0.8595988538681948,
|
| 237 |
+
"grad_norm": 32.16545104980469,
|
| 238 |
+
"learning_rate": 1.6561604584527223e-05,
|
| 239 |
+
"loss": 0.2479,
|
| 240 |
"step": 300
|
| 241 |
},
|
| 242 |
{
|
| 243 |
+
"epoch": 0.8595988538681948,
|
| 244 |
+
"eval_accuracy": 0.9113924050632911,
|
| 245 |
+
"eval_loss": 0.301921546459198,
|
| 246 |
+
"eval_runtime": 4.296,
|
| 247 |
+
"eval_samples_per_second": 36.779,
|
| 248 |
+
"eval_steps_per_second": 9.311,
|
| 249 |
"step": 300
|
| 250 |
},
|
| 251 |
{
|
| 252 |
+
"epoch": 0.9169054441260746,
|
| 253 |
+
"grad_norm": 20.30685043334961,
|
| 254 |
+
"learning_rate": 1.6332378223495704e-05,
|
| 255 |
+
"loss": 0.4682,
|
| 256 |
"step": 320
|
| 257 |
},
|
| 258 |
{
|
| 259 |
+
"epoch": 0.9169054441260746,
|
| 260 |
+
"eval_accuracy": 0.9050632911392406,
|
| 261 |
+
"eval_loss": 0.31456297636032104,
|
| 262 |
+
"eval_runtime": 4.3777,
|
| 263 |
+
"eval_samples_per_second": 36.092,
|
| 264 |
+
"eval_steps_per_second": 9.137,
|
| 265 |
"step": 320
|
| 266 |
},
|
| 267 |
{
|
| 268 |
+
"epoch": 0.9742120343839542,
|
| 269 |
+
"grad_norm": 26.28807830810547,
|
| 270 |
+
"learning_rate": 1.6103151862464185e-05,
|
| 271 |
+
"loss": 0.5659,
|
| 272 |
"step": 340
|
| 273 |
},
|
| 274 |
{
|
| 275 |
+
"epoch": 0.9742120343839542,
|
| 276 |
+
"eval_accuracy": 0.930379746835443,
|
| 277 |
+
"eval_loss": 0.2427118569612503,
|
| 278 |
+
"eval_runtime": 4.3194,
|
| 279 |
+
"eval_samples_per_second": 36.579,
|
| 280 |
+
"eval_steps_per_second": 9.261,
|
| 281 |
"step": 340
|
| 282 |
},
|
| 283 |
{
|
| 284 |
+
"epoch": 1.0315186246418337,
|
| 285 |
+
"grad_norm": 18.92162322998047,
|
| 286 |
+
"learning_rate": 1.5873925501432665e-05,
|
| 287 |
+
"loss": 0.1859,
|
| 288 |
"step": 360
|
| 289 |
},
|
| 290 |
{
|
| 291 |
+
"epoch": 1.0315186246418337,
|
| 292 |
+
"eval_accuracy": 0.9240506329113924,
|
| 293 |
+
"eval_loss": 0.2563447058200836,
|
| 294 |
+
"eval_runtime": 4.2716,
|
| 295 |
+
"eval_samples_per_second": 36.989,
|
| 296 |
+
"eval_steps_per_second": 9.364,
|
| 297 |
"step": 360
|
| 298 |
},
|
| 299 |
{
|
| 300 |
+
"epoch": 1.0888252148997135,
|
| 301 |
+
"grad_norm": 0.12231427431106567,
|
| 302 |
+
"learning_rate": 1.5644699140401146e-05,
|
| 303 |
+
"loss": 0.0832,
|
| 304 |
"step": 380
|
| 305 |
},
|
| 306 |
{
|
| 307 |
+
"epoch": 1.0888252148997135,
|
| 308 |
+
"eval_accuracy": 0.9177215189873418,
|
| 309 |
+
"eval_loss": 0.29223397374153137,
|
| 310 |
+
"eval_runtime": 4.2485,
|
| 311 |
+
"eval_samples_per_second": 37.19,
|
| 312 |
+
"eval_steps_per_second": 9.415,
|
| 313 |
"step": 380
|
| 314 |
},
|
| 315 |
{
|
| 316 |
+
"epoch": 1.146131805157593,
|
| 317 |
+
"grad_norm": 0.025886153802275658,
|
| 318 |
+
"learning_rate": 1.541547277936963e-05,
|
| 319 |
+
"loss": 0.1351,
|
| 320 |
"step": 400
|
| 321 |
},
|
| 322 |
{
|
| 323 |
+
"epoch": 1.146131805157593,
|
| 324 |
+
"eval_accuracy": 0.9050632911392406,
|
| 325 |
+
"eval_loss": 0.33985620737075806,
|
| 326 |
+
"eval_runtime": 4.2345,
|
| 327 |
+
"eval_samples_per_second": 37.312,
|
| 328 |
+
"eval_steps_per_second": 9.446,
|
| 329 |
"step": 400
|
| 330 |
},
|
| 331 |
{
|
| 332 |
+
"epoch": 1.2034383954154728,
|
| 333 |
+
"grad_norm": 0.022903436794877052,
|
| 334 |
+
"learning_rate": 1.518624641833811e-05,
|
| 335 |
+
"loss": 0.1608,
|
| 336 |
"step": 420
|
| 337 |
},
|
| 338 |
{
|
| 339 |
+
"epoch": 1.2034383954154728,
|
| 340 |
+
"eval_accuracy": 0.9113924050632911,
|
| 341 |
+
"eval_loss": 0.45555388927459717,
|
| 342 |
+
"eval_runtime": 4.2515,
|
| 343 |
+
"eval_samples_per_second": 37.163,
|
| 344 |
+
"eval_steps_per_second": 9.408,
|
| 345 |
"step": 420
|
| 346 |
},
|
| 347 |
{
|
| 348 |
+
"epoch": 1.2607449856733524,
|
| 349 |
+
"grad_norm": 0.009185605682432652,
|
| 350 |
+
"learning_rate": 1.495702005730659e-05,
|
| 351 |
+
"loss": 0.3276,
|
| 352 |
"step": 440
|
| 353 |
},
|
| 354 |
{
|
| 355 |
+
"epoch": 1.2607449856733524,
|
| 356 |
+
"eval_accuracy": 0.9113924050632911,
|
| 357 |
+
"eval_loss": 0.3819015920162201,
|
| 358 |
+
"eval_runtime": 4.2461,
|
| 359 |
+
"eval_samples_per_second": 37.21,
|
| 360 |
+
"eval_steps_per_second": 9.42,
|
| 361 |
"step": 440
|
| 362 |
},
|
| 363 |
{
|
| 364 |
+
"epoch": 1.3180515759312321,
|
| 365 |
+
"grad_norm": 0.03250379115343094,
|
| 366 |
+
"learning_rate": 1.4727793696275073e-05,
|
| 367 |
+
"loss": 0.2105,
|
| 368 |
"step": 460
|
| 369 |
},
|
| 370 |
{
|
| 371 |
+
"epoch": 1.3180515759312321,
|
| 372 |
+
"eval_accuracy": 0.9050632911392406,
|
| 373 |
+
"eval_loss": 0.3724599778652191,
|
| 374 |
+
"eval_runtime": 4.2739,
|
| 375 |
+
"eval_samples_per_second": 36.968,
|
| 376 |
+
"eval_steps_per_second": 9.359,
|
| 377 |
"step": 460
|
| 378 |
},
|
| 379 |
{
|
| 380 |
+
"epoch": 1.3753581661891117,
|
| 381 |
+
"grad_norm": 0.075935497879982,
|
| 382 |
+
"learning_rate": 1.4498567335243553e-05,
|
| 383 |
+
"loss": 0.1077,
|
| 384 |
"step": 480
|
| 385 |
},
|
| 386 |
{
|
| 387 |
+
"epoch": 1.3753581661891117,
|
| 388 |
+
"eval_accuracy": 0.9240506329113924,
|
| 389 |
+
"eval_loss": 0.3591189980506897,
|
| 390 |
+
"eval_runtime": 4.29,
|
| 391 |
+
"eval_samples_per_second": 36.829,
|
| 392 |
+
"eval_steps_per_second": 9.324,
|
| 393 |
"step": 480
|
| 394 |
},
|
| 395 |
{
|
| 396 |
+
"epoch": 1.4326647564469914,
|
| 397 |
+
"grad_norm": 0.7707359194755554,
|
| 398 |
+
"learning_rate": 1.4269340974212036e-05,
|
| 399 |
+
"loss": 0.0568,
|
| 400 |
"step": 500
|
| 401 |
},
|
| 402 |
{
|
| 403 |
+
"epoch": 1.4326647564469914,
|
| 404 |
+
"eval_accuracy": 0.9177215189873418,
|
| 405 |
+
"eval_loss": 0.36658525466918945,
|
| 406 |
+
"eval_runtime": 4.2533,
|
| 407 |
+
"eval_samples_per_second": 37.148,
|
| 408 |
+
"eval_steps_per_second": 9.405,
|
| 409 |
"step": 500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 410 |
}
|
| 411 |
],
|
| 412 |
"logging_steps": 20,
|
| 413 |
+
"max_steps": 1745,
|
| 414 |
"num_input_tokens_seen": 0,
|
| 415 |
"num_train_epochs": 5,
|
| 416 |
"save_steps": 500,
|
|
|
|
| 421 |
"should_evaluate": false,
|
| 422 |
"should_log": false,
|
| 423 |
"should_save": true,
|
| 424 |
+
"should_training_stop": false
|
| 425 |
},
|
| 426 |
"attributes": {}
|
| 427 |
}
|
| 428 |
},
|
| 429 |
+
"total_flos": 453767903850240.0,
|
| 430 |
"train_batch_size": 4,
|
| 431 |
"trial_name": null,
|
| 432 |
"trial_params": null
|
last-checkpoint/training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5368
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d6554c2b55adc50f6a299c2a600dde3efe6668814434d86cbfc3e4225bb34fb0
|
| 3 |
size 5368
|