Training in progress, step 2400, checkpoint
Browse files
checkpoint-2400/adapter_config.json
CHANGED
|
@@ -23,13 +23,13 @@
|
|
| 23 |
"rank_pattern": {},
|
| 24 |
"revision": null,
|
| 25 |
"target_modules": [
|
| 26 |
-
"v_proj",
|
| 27 |
-
"q_proj",
|
| 28 |
-
"gate_proj",
|
| 29 |
"up_proj",
|
| 30 |
"o_proj",
|
|
|
|
|
|
|
|
|
|
| 31 |
"k_proj",
|
| 32 |
-
"
|
| 33 |
],
|
| 34 |
"task_type": "CAUSAL_LM",
|
| 35 |
"use_dora": false,
|
|
|
|
| 23 |
"rank_pattern": {},
|
| 24 |
"revision": null,
|
| 25 |
"target_modules": [
|
|
|
|
|
|
|
|
|
|
| 26 |
"up_proj",
|
| 27 |
"o_proj",
|
| 28 |
+
"v_proj",
|
| 29 |
+
"q_proj",
|
| 30 |
+
"down_proj",
|
| 31 |
"k_proj",
|
| 32 |
+
"gate_proj"
|
| 33 |
],
|
| 34 |
"task_type": "CAUSAL_LM",
|
| 35 |
"use_dora": false,
|
checkpoint-2400/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 167832240
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ddd7acd85e35f4c1f0dbdb913c37fa37173314f7a7c5c9670ca2b52774a150be
|
| 3 |
size 167832240
|
checkpoint-2400/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 335922386
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c4e52cd757d3ba3fbe3c034cce5c94faa4b74692dabc2b4fb5f80fd4de5013a7
|
| 3 |
size 335922386
|
checkpoint-2400/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 sha256:406fc13076456f35e58ebcf21a7bf3c127428ba57be352bd7cb7e8808f6ce700
|
| 3 |
size 14244
|
checkpoint-2400/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 sha256:9f861323257965447b4aa628b03e7bb2c5b261e1de8ea9c8ff39417f10bf7901
|
| 3 |
size 1064
|
checkpoint-2400/trainer_state.json
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch": 2.
|
| 5 |
"eval_steps": 50,
|
| 6 |
"global_step": 2400,
|
| 7 |
"is_hyper_param_search": false,
|
|
@@ -9,2072 +9,2072 @@
|
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
-
"epoch": 0.
|
| 13 |
-
"grad_norm":
|
| 14 |
-
"learning_rate": 4.
|
| 15 |
-
"loss": 1.
|
| 16 |
"step": 10
|
| 17 |
},
|
| 18 |
{
|
| 19 |
-
"epoch": 0.
|
| 20 |
-
"grad_norm":
|
| 21 |
-
"learning_rate": 4.
|
| 22 |
-
"loss": 0.
|
| 23 |
"step": 20
|
| 24 |
},
|
| 25 |
{
|
| 26 |
-
"epoch": 0.
|
| 27 |
-
"grad_norm": 1.
|
| 28 |
-
"learning_rate": 4.
|
| 29 |
-
"loss": 0.
|
| 30 |
"step": 30
|
| 31 |
},
|
| 32 |
{
|
| 33 |
-
"epoch": 0.
|
| 34 |
-
"grad_norm": 0.
|
| 35 |
-
"learning_rate": 4.
|
| 36 |
-
"loss": 0.
|
| 37 |
"step": 40
|
| 38 |
},
|
| 39 |
{
|
| 40 |
-
"epoch": 0.
|
| 41 |
-
"grad_norm": 0.
|
| 42 |
-
"learning_rate": 4.
|
| 43 |
-
"loss": 0.
|
| 44 |
"step": 50
|
| 45 |
},
|
| 46 |
{
|
| 47 |
-
"epoch": 0.
|
| 48 |
-
"eval_loss": 0.
|
| 49 |
-
"eval_runtime": 13.
|
| 50 |
-
"eval_samples_per_second": 35.
|
| 51 |
-
"eval_steps_per_second": 2.
|
| 52 |
"step": 50
|
| 53 |
},
|
| 54 |
{
|
| 55 |
-
"epoch": 0.
|
| 56 |
-
"grad_norm": 0.
|
| 57 |
-
"learning_rate": 4.
|
| 58 |
-
"loss": 0.
|
| 59 |
"step": 60
|
| 60 |
},
|
| 61 |
{
|
| 62 |
-
"epoch": 0.
|
| 63 |
-
"grad_norm": 0.
|
| 64 |
-
"learning_rate": 4.
|
| 65 |
-
"loss": 0.
|
| 66 |
"step": 70
|
| 67 |
},
|
| 68 |
{
|
| 69 |
-
"epoch": 0.
|
| 70 |
-
"grad_norm": 0.
|
| 71 |
-
"learning_rate": 4.
|
| 72 |
-
"loss": 0.
|
| 73 |
"step": 80
|
| 74 |
},
|
| 75 |
{
|
| 76 |
-
"epoch": 0.
|
| 77 |
-
"grad_norm": 0.
|
| 78 |
-
"learning_rate": 4.
|
| 79 |
-
"loss": 0.
|
| 80 |
"step": 90
|
| 81 |
},
|
| 82 |
{
|
| 83 |
-
"epoch": 0.
|
| 84 |
-
"grad_norm": 0.
|
| 85 |
-
"learning_rate": 4.
|
| 86 |
-
"loss": 0.
|
| 87 |
"step": 100
|
| 88 |
},
|
| 89 |
{
|
| 90 |
-
"epoch": 0.
|
| 91 |
-
"eval_loss": 0.
|
| 92 |
-
"eval_runtime": 13.
|
| 93 |
-
"eval_samples_per_second": 35.
|
| 94 |
-
"eval_steps_per_second": 2.
|
| 95 |
"step": 100
|
| 96 |
},
|
| 97 |
{
|
| 98 |
-
"epoch": 0.
|
| 99 |
-
"grad_norm": 0.
|
| 100 |
-
"learning_rate": 4.
|
| 101 |
-
"loss": 0.
|
| 102 |
"step": 110
|
| 103 |
},
|
| 104 |
{
|
| 105 |
-
"epoch": 0.
|
| 106 |
-
"grad_norm": 0.
|
| 107 |
-
"learning_rate": 4.
|
| 108 |
-
"loss": 0.
|
| 109 |
"step": 120
|
| 110 |
},
|
| 111 |
{
|
| 112 |
-
"epoch": 0.
|
| 113 |
-
"grad_norm": 0.
|
| 114 |
-
"learning_rate": 4.
|
| 115 |
-
"loss": 0.
|
| 116 |
"step": 130
|
| 117 |
},
|
| 118 |
{
|
| 119 |
-
"epoch": 0.
|
| 120 |
-
"grad_norm": 0.
|
| 121 |
-
"learning_rate": 4.
|
| 122 |
-
"loss": 0.
|
| 123 |
"step": 140
|
| 124 |
},
|
| 125 |
{
|
| 126 |
-
"epoch": 0.
|
| 127 |
-
"grad_norm": 0.
|
| 128 |
-
"learning_rate": 4.
|
| 129 |
-
"loss": 0.
|
| 130 |
"step": 150
|
| 131 |
},
|
| 132 |
{
|
| 133 |
-
"epoch": 0.
|
| 134 |
-
"eval_loss": 0.
|
| 135 |
-
"eval_runtime": 13.
|
| 136 |
-
"eval_samples_per_second": 35.
|
| 137 |
-
"eval_steps_per_second": 2.
|
| 138 |
"step": 150
|
| 139 |
},
|
| 140 |
{
|
| 141 |
-
"epoch": 0.
|
| 142 |
-
"grad_norm": 0.
|
| 143 |
-
"learning_rate": 4.
|
| 144 |
-
"loss": 0.
|
| 145 |
"step": 160
|
| 146 |
},
|
| 147 |
{
|
| 148 |
-
"epoch": 0.
|
| 149 |
-
"grad_norm": 0.
|
| 150 |
-
"learning_rate": 4.
|
| 151 |
-
"loss": 0.
|
| 152 |
"step": 170
|
| 153 |
},
|
| 154 |
{
|
| 155 |
-
"epoch": 0.
|
| 156 |
-
"grad_norm": 0.
|
| 157 |
-
"learning_rate": 4.
|
| 158 |
-
"loss": 0.
|
| 159 |
"step": 180
|
| 160 |
},
|
| 161 |
{
|
| 162 |
-
"epoch": 0.
|
| 163 |
-
"grad_norm": 0.
|
| 164 |
-
"learning_rate": 4.
|
| 165 |
-
"loss": 0.
|
| 166 |
"step": 190
|
| 167 |
},
|
| 168 |
{
|
| 169 |
-
"epoch": 0.
|
| 170 |
-
"grad_norm": 0.
|
| 171 |
-
"learning_rate": 4.
|
| 172 |
-
"loss": 0.
|
| 173 |
"step": 200
|
| 174 |
},
|
| 175 |
{
|
| 176 |
-
"epoch": 0.
|
| 177 |
-
"eval_loss": 0.
|
| 178 |
-
"eval_runtime": 13.
|
| 179 |
-
"eval_samples_per_second": 35.
|
| 180 |
-
"eval_steps_per_second": 2.
|
| 181 |
"step": 200
|
| 182 |
},
|
| 183 |
{
|
| 184 |
-
"epoch": 0.
|
| 185 |
-
"grad_norm": 0.
|
| 186 |
-
"learning_rate": 4.
|
| 187 |
-
"loss": 0.
|
| 188 |
"step": 210
|
| 189 |
},
|
| 190 |
{
|
| 191 |
-
"epoch": 0.
|
| 192 |
-
"grad_norm": 0.
|
| 193 |
-
"learning_rate": 4.
|
| 194 |
-
"loss": 0.
|
| 195 |
"step": 220
|
| 196 |
},
|
| 197 |
{
|
| 198 |
-
"epoch": 0.
|
| 199 |
-
"grad_norm": 0.
|
| 200 |
-
"learning_rate": 4.
|
| 201 |
-
"loss": 0.
|
| 202 |
"step": 230
|
| 203 |
},
|
| 204 |
{
|
| 205 |
-
"epoch": 0.
|
| 206 |
-
"grad_norm": 0.
|
| 207 |
-
"learning_rate": 4.
|
| 208 |
-
"loss": 0.
|
| 209 |
"step": 240
|
| 210 |
},
|
| 211 |
{
|
| 212 |
-
"epoch": 0.
|
| 213 |
-
"grad_norm": 0.
|
| 214 |
-
"learning_rate": 4.
|
| 215 |
-
"loss": 0.
|
| 216 |
"step": 250
|
| 217 |
},
|
| 218 |
{
|
| 219 |
-
"epoch": 0.
|
| 220 |
-
"eval_loss": 0.
|
| 221 |
-
"eval_runtime": 13.
|
| 222 |
-
"eval_samples_per_second": 35.
|
| 223 |
-
"eval_steps_per_second": 2.
|
| 224 |
"step": 250
|
| 225 |
},
|
| 226 |
{
|
| 227 |
-
"epoch": 0.
|
| 228 |
-
"grad_norm": 0.
|
| 229 |
-
"learning_rate": 4.
|
| 230 |
-
"loss": 0.
|
| 231 |
"step": 260
|
| 232 |
},
|
| 233 |
{
|
| 234 |
-
"epoch": 0.
|
| 235 |
-
"grad_norm": 0.
|
| 236 |
-
"learning_rate": 4.
|
| 237 |
-
"loss": 0.
|
| 238 |
"step": 270
|
| 239 |
},
|
| 240 |
{
|
| 241 |
-
"epoch": 0.
|
| 242 |
-
"grad_norm": 0.
|
| 243 |
-
"learning_rate": 4.
|
| 244 |
-
"loss": 0.
|
| 245 |
"step": 280
|
| 246 |
},
|
| 247 |
{
|
| 248 |
-
"epoch": 0.
|
| 249 |
-
"grad_norm": 0.
|
| 250 |
-
"learning_rate": 4.
|
| 251 |
-
"loss": 0.
|
| 252 |
"step": 290
|
| 253 |
},
|
| 254 |
{
|
| 255 |
-
"epoch": 0.
|
| 256 |
-
"grad_norm": 0.
|
| 257 |
-
"learning_rate": 4.
|
| 258 |
-
"loss": 0.
|
| 259 |
"step": 300
|
| 260 |
},
|
| 261 |
{
|
| 262 |
-
"epoch": 0.
|
| 263 |
-
"eval_loss": 0.
|
| 264 |
-
"eval_runtime": 13.
|
| 265 |
-
"eval_samples_per_second": 35.
|
| 266 |
-
"eval_steps_per_second": 2.
|
| 267 |
"step": 300
|
| 268 |
},
|
| 269 |
{
|
| 270 |
-
"epoch": 0.
|
| 271 |
-
"grad_norm": 0.
|
| 272 |
-
"learning_rate": 4.
|
| 273 |
-
"loss": 0.
|
| 274 |
"step": 310
|
| 275 |
},
|
| 276 |
{
|
| 277 |
-
"epoch": 0.
|
| 278 |
-
"grad_norm": 0.
|
| 279 |
-
"learning_rate": 4.
|
| 280 |
-
"loss": 0.
|
| 281 |
"step": 320
|
| 282 |
},
|
| 283 |
{
|
| 284 |
-
"epoch": 0.
|
| 285 |
-
"grad_norm": 0.
|
| 286 |
-
"learning_rate": 4.
|
| 287 |
-
"loss": 0.
|
| 288 |
"step": 330
|
| 289 |
},
|
| 290 |
{
|
| 291 |
-
"epoch": 0.
|
| 292 |
-
"grad_norm": 0.
|
| 293 |
-
"learning_rate": 4.
|
| 294 |
-
"loss": 0.
|
| 295 |
"step": 340
|
| 296 |
},
|
| 297 |
{
|
| 298 |
-
"epoch": 0.
|
| 299 |
-
"grad_norm": 0.
|
| 300 |
-
"learning_rate": 4.
|
| 301 |
-
"loss": 0.
|
| 302 |
"step": 350
|
| 303 |
},
|
| 304 |
{
|
| 305 |
-
"epoch": 0.
|
| 306 |
-
"eval_loss": 0.
|
| 307 |
-
"eval_runtime": 13.
|
| 308 |
-
"eval_samples_per_second": 35.
|
| 309 |
-
"eval_steps_per_second": 2.
|
| 310 |
"step": 350
|
| 311 |
},
|
| 312 |
{
|
| 313 |
-
"epoch": 0.
|
| 314 |
-
"grad_norm": 0.
|
| 315 |
-
"learning_rate": 4.
|
| 316 |
-
"loss": 0.
|
| 317 |
"step": 360
|
| 318 |
},
|
| 319 |
{
|
| 320 |
-
"epoch": 0.
|
| 321 |
-
"grad_norm": 0.
|
| 322 |
-
"learning_rate": 4.
|
| 323 |
-
"loss": 0.
|
| 324 |
"step": 370
|
| 325 |
},
|
| 326 |
{
|
| 327 |
-
"epoch": 0.
|
| 328 |
-
"grad_norm": 0.
|
| 329 |
-
"learning_rate": 4.
|
| 330 |
-
"loss": 0.
|
| 331 |
"step": 380
|
| 332 |
},
|
| 333 |
{
|
| 334 |
-
"epoch": 0.
|
| 335 |
-
"grad_norm": 0.
|
| 336 |
-
"learning_rate": 4.
|
| 337 |
-
"loss": 0.
|
| 338 |
"step": 390
|
| 339 |
},
|
| 340 |
{
|
| 341 |
-
"epoch": 0.
|
| 342 |
-
"grad_norm": 0.
|
| 343 |
-
"learning_rate": 4.
|
| 344 |
-
"loss": 0.
|
| 345 |
"step": 400
|
| 346 |
},
|
| 347 |
{
|
| 348 |
-
"epoch": 0.
|
| 349 |
-
"eval_loss": 0.
|
| 350 |
-
"eval_runtime": 13.
|
| 351 |
-
"eval_samples_per_second": 35.
|
| 352 |
-
"eval_steps_per_second": 2.
|
| 353 |
"step": 400
|
| 354 |
},
|
| 355 |
{
|
| 356 |
-
"epoch": 0.
|
| 357 |
-
"grad_norm": 0.
|
| 358 |
-
"learning_rate": 4.
|
| 359 |
-
"loss": 0.
|
| 360 |
"step": 410
|
| 361 |
},
|
| 362 |
{
|
| 363 |
-
"epoch": 0.
|
| 364 |
-
"grad_norm": 0.
|
| 365 |
-
"learning_rate": 4.
|
| 366 |
-
"loss": 0.
|
| 367 |
"step": 420
|
| 368 |
},
|
| 369 |
{
|
| 370 |
-
"epoch": 0.
|
| 371 |
-
"grad_norm": 0.
|
| 372 |
-
"learning_rate": 4.
|
| 373 |
-
"loss": 0.
|
| 374 |
"step": 430
|
| 375 |
},
|
| 376 |
{
|
| 377 |
-
"epoch": 0.
|
| 378 |
-
"grad_norm": 0.
|
| 379 |
-
"learning_rate": 4.
|
| 380 |
-
"loss": 0.
|
| 381 |
"step": 440
|
| 382 |
},
|
| 383 |
{
|
| 384 |
-
"epoch": 0.
|
| 385 |
-
"grad_norm": 0.
|
| 386 |
-
"learning_rate": 4.
|
| 387 |
-
"loss": 0.
|
| 388 |
"step": 450
|
| 389 |
},
|
| 390 |
{
|
| 391 |
-
"epoch": 0.
|
| 392 |
-
"eval_loss": 0.
|
| 393 |
-
"eval_runtime": 13.
|
| 394 |
-
"eval_samples_per_second": 35.
|
| 395 |
-
"eval_steps_per_second": 2.
|
| 396 |
"step": 450
|
| 397 |
},
|
| 398 |
{
|
| 399 |
-
"epoch": 0.
|
| 400 |
-
"grad_norm": 0.
|
| 401 |
-
"learning_rate": 4.
|
| 402 |
-
"loss": 0.
|
| 403 |
"step": 460
|
| 404 |
},
|
| 405 |
{
|
| 406 |
-
"epoch": 0.
|
| 407 |
-
"grad_norm": 0.
|
| 408 |
-
"learning_rate": 4.
|
| 409 |
-
"loss": 0.
|
| 410 |
"step": 470
|
| 411 |
},
|
| 412 |
{
|
| 413 |
-
"epoch": 0.
|
| 414 |
-
"grad_norm": 0.
|
| 415 |
-
"learning_rate": 4.
|
| 416 |
-
"loss": 0.
|
| 417 |
"step": 480
|
| 418 |
},
|
| 419 |
{
|
| 420 |
-
"epoch": 0.
|
| 421 |
-
"grad_norm": 0.
|
| 422 |
-
"learning_rate": 4.
|
| 423 |
-
"loss": 0.
|
| 424 |
"step": 490
|
| 425 |
},
|
| 426 |
{
|
| 427 |
-
"epoch": 0.
|
| 428 |
-
"grad_norm": 0.
|
| 429 |
-
"learning_rate": 4.
|
| 430 |
-
"loss": 0.
|
| 431 |
"step": 500
|
| 432 |
},
|
| 433 |
{
|
| 434 |
-
"epoch": 0.
|
| 435 |
-
"eval_loss": 0.
|
| 436 |
-
"eval_runtime": 13.
|
| 437 |
-
"eval_samples_per_second": 35.
|
| 438 |
-
"eval_steps_per_second": 2.
|
| 439 |
"step": 500
|
| 440 |
},
|
| 441 |
{
|
| 442 |
-
"epoch": 0.
|
| 443 |
-
"grad_norm": 0.
|
| 444 |
-
"learning_rate": 4.
|
| 445 |
-
"loss": 0.
|
| 446 |
"step": 510
|
| 447 |
},
|
| 448 |
{
|
| 449 |
-
"epoch": 0.
|
| 450 |
-
"grad_norm": 0.
|
| 451 |
-
"learning_rate": 4.
|
| 452 |
-
"loss": 0.
|
| 453 |
"step": 520
|
| 454 |
},
|
| 455 |
{
|
| 456 |
-
"epoch": 0.
|
| 457 |
-
"grad_norm": 0.
|
| 458 |
-
"learning_rate": 4.
|
| 459 |
-
"loss": 0.
|
| 460 |
"step": 530
|
| 461 |
},
|
| 462 |
{
|
| 463 |
-
"epoch": 0.
|
| 464 |
-
"grad_norm": 0.
|
| 465 |
-
"learning_rate": 4.
|
| 466 |
-
"loss": 0.
|
| 467 |
"step": 540
|
| 468 |
},
|
| 469 |
{
|
| 470 |
-
"epoch": 0.
|
| 471 |
-
"grad_norm": 0.
|
| 472 |
-
"learning_rate": 4.
|
| 473 |
-
"loss": 0.
|
| 474 |
"step": 550
|
| 475 |
},
|
| 476 |
{
|
| 477 |
-
"epoch": 0.
|
| 478 |
-
"eval_loss": 0.
|
| 479 |
-
"eval_runtime": 13.
|
| 480 |
-
"eval_samples_per_second": 35.
|
| 481 |
-
"eval_steps_per_second": 2.
|
| 482 |
"step": 550
|
| 483 |
},
|
| 484 |
{
|
| 485 |
-
"epoch": 0.
|
| 486 |
-
"grad_norm": 0.
|
| 487 |
-
"learning_rate": 4.
|
| 488 |
-
"loss": 0.
|
| 489 |
"step": 560
|
| 490 |
},
|
| 491 |
{
|
| 492 |
-
"epoch": 0.
|
| 493 |
-
"grad_norm": 0.
|
| 494 |
-
"learning_rate":
|
| 495 |
-
"loss": 0.
|
| 496 |
"step": 570
|
| 497 |
},
|
| 498 |
{
|
| 499 |
-
"epoch": 0.
|
| 500 |
-
"grad_norm": 0.
|
| 501 |
-
"learning_rate": 3.
|
| 502 |
-
"loss": 0.
|
| 503 |
"step": 580
|
| 504 |
},
|
| 505 |
{
|
| 506 |
-
"epoch": 0.
|
| 507 |
-
"grad_norm": 0.
|
| 508 |
-
"learning_rate": 3.
|
| 509 |
-
"loss": 0.
|
| 510 |
"step": 590
|
| 511 |
},
|
| 512 |
{
|
| 513 |
-
"epoch": 0.
|
| 514 |
-
"grad_norm": 0.
|
| 515 |
-
"learning_rate": 3.
|
| 516 |
-
"loss": 0.
|
| 517 |
"step": 600
|
| 518 |
},
|
| 519 |
{
|
| 520 |
-
"epoch": 0.
|
| 521 |
-
"eval_loss": 0.
|
| 522 |
-
"eval_runtime": 13.
|
| 523 |
-
"eval_samples_per_second": 35.
|
| 524 |
-
"eval_steps_per_second": 2.
|
| 525 |
"step": 600
|
| 526 |
},
|
| 527 |
{
|
| 528 |
-
"epoch": 0.
|
| 529 |
-
"grad_norm": 0.
|
| 530 |
-
"learning_rate": 3.
|
| 531 |
-
"loss": 0.
|
| 532 |
"step": 610
|
| 533 |
},
|
| 534 |
{
|
| 535 |
-
"epoch": 0.
|
| 536 |
-
"grad_norm": 0.
|
| 537 |
-
"learning_rate": 3.
|
| 538 |
-
"loss": 0.
|
| 539 |
"step": 620
|
| 540 |
},
|
| 541 |
{
|
| 542 |
-
"epoch": 0.
|
| 543 |
-
"grad_norm": 0.
|
| 544 |
-
"learning_rate": 3.
|
| 545 |
-
"loss": 0.
|
| 546 |
"step": 630
|
| 547 |
},
|
| 548 |
{
|
| 549 |
-
"epoch": 0.
|
| 550 |
-
"grad_norm": 0.
|
| 551 |
-
"learning_rate": 3.
|
| 552 |
-
"loss": 0.
|
| 553 |
"step": 640
|
| 554 |
},
|
| 555 |
{
|
| 556 |
-
"epoch": 0.
|
| 557 |
-
"grad_norm": 0.
|
| 558 |
-
"learning_rate": 3.
|
| 559 |
-
"loss": 0.
|
| 560 |
"step": 650
|
| 561 |
},
|
| 562 |
{
|
| 563 |
-
"epoch": 0.
|
| 564 |
-
"eval_loss": 0.
|
| 565 |
-
"eval_runtime": 13.
|
| 566 |
-
"eval_samples_per_second": 35.
|
| 567 |
-
"eval_steps_per_second": 2.
|
| 568 |
"step": 650
|
| 569 |
},
|
| 570 |
{
|
| 571 |
-
"epoch": 0.
|
| 572 |
-
"grad_norm": 0.
|
| 573 |
-
"learning_rate": 3.
|
| 574 |
-
"loss": 0.
|
| 575 |
"step": 660
|
| 576 |
},
|
| 577 |
{
|
| 578 |
-
"epoch": 0.
|
| 579 |
-
"grad_norm": 0.
|
| 580 |
-
"learning_rate": 3.
|
| 581 |
-
"loss": 0.
|
| 582 |
"step": 670
|
| 583 |
},
|
| 584 |
{
|
| 585 |
-
"epoch": 0.
|
| 586 |
-
"grad_norm": 0.
|
| 587 |
-
"learning_rate": 3.
|
| 588 |
-
"loss": 0.
|
| 589 |
"step": 680
|
| 590 |
},
|
| 591 |
{
|
| 592 |
-
"epoch": 0.
|
| 593 |
-
"grad_norm": 0.
|
| 594 |
-
"learning_rate": 3.
|
| 595 |
-
"loss": 0.
|
| 596 |
"step": 690
|
| 597 |
},
|
| 598 |
{
|
| 599 |
-
"epoch": 0.
|
| 600 |
-
"grad_norm": 0.
|
| 601 |
-
"learning_rate": 3.
|
| 602 |
-
"loss": 0.
|
| 603 |
"step": 700
|
| 604 |
},
|
| 605 |
{
|
| 606 |
-
"epoch": 0.
|
| 607 |
-
"eval_loss": 0.
|
| 608 |
-
"eval_runtime": 13.
|
| 609 |
-
"eval_samples_per_second": 35.
|
| 610 |
-
"eval_steps_per_second": 2.
|
| 611 |
"step": 700
|
| 612 |
},
|
| 613 |
{
|
| 614 |
-
"epoch": 0.
|
| 615 |
-
"grad_norm": 0.
|
| 616 |
-
"learning_rate": 3.
|
| 617 |
-
"loss": 0.
|
| 618 |
"step": 710
|
| 619 |
},
|
| 620 |
{
|
| 621 |
-
"epoch": 0.
|
| 622 |
-
"grad_norm": 0.
|
| 623 |
-
"learning_rate": 3.
|
| 624 |
-
"loss": 0.
|
| 625 |
"step": 720
|
| 626 |
},
|
| 627 |
{
|
| 628 |
-
"epoch": 0.
|
| 629 |
-
"grad_norm": 0.
|
| 630 |
-
"learning_rate": 3.
|
| 631 |
-
"loss": 0.
|
| 632 |
"step": 730
|
| 633 |
},
|
| 634 |
{
|
| 635 |
-
"epoch": 0.
|
| 636 |
-
"grad_norm": 0.
|
| 637 |
-
"learning_rate": 3.
|
| 638 |
-
"loss": 0.
|
| 639 |
"step": 740
|
| 640 |
},
|
| 641 |
{
|
| 642 |
-
"epoch": 0.
|
| 643 |
-
"grad_norm": 0.
|
| 644 |
-
"learning_rate": 3.
|
| 645 |
-
"loss": 0.
|
| 646 |
"step": 750
|
| 647 |
},
|
| 648 |
{
|
| 649 |
-
"epoch": 0.
|
| 650 |
-
"eval_loss": 0.
|
| 651 |
-
"eval_runtime": 13.
|
| 652 |
-
"eval_samples_per_second": 35.
|
| 653 |
-
"eval_steps_per_second": 2.
|
| 654 |
"step": 750
|
| 655 |
},
|
| 656 |
{
|
| 657 |
-
"epoch": 0.
|
| 658 |
-
"grad_norm": 0.
|
| 659 |
-
"learning_rate": 3.
|
| 660 |
-
"loss": 0.
|
| 661 |
"step": 760
|
| 662 |
},
|
| 663 |
{
|
| 664 |
-
"epoch": 0.
|
| 665 |
-
"grad_norm": 0.
|
| 666 |
-
"learning_rate": 3.
|
| 667 |
-
"loss": 0.
|
| 668 |
"step": 770
|
| 669 |
},
|
| 670 |
{
|
| 671 |
-
"epoch": 0.
|
| 672 |
-
"grad_norm": 0.
|
| 673 |
-
"learning_rate": 3.
|
| 674 |
-
"loss": 0.
|
| 675 |
"step": 780
|
| 676 |
},
|
| 677 |
{
|
| 678 |
-
"epoch": 0.
|
| 679 |
-
"grad_norm": 0.
|
| 680 |
-
"learning_rate": 3.
|
| 681 |
-
"loss": 0.
|
| 682 |
"step": 790
|
| 683 |
},
|
| 684 |
{
|
| 685 |
-
"epoch": 0.
|
| 686 |
-
"grad_norm": 0.
|
| 687 |
-
"learning_rate": 3.
|
| 688 |
-
"loss": 0.
|
| 689 |
"step": 800
|
| 690 |
},
|
| 691 |
{
|
| 692 |
-
"epoch": 0.
|
| 693 |
-
"eval_loss": 0.
|
| 694 |
-
"eval_runtime": 13.
|
| 695 |
-
"eval_samples_per_second": 35.
|
| 696 |
-
"eval_steps_per_second": 2.
|
| 697 |
"step": 800
|
| 698 |
},
|
| 699 |
{
|
| 700 |
-
"epoch": 0.
|
| 701 |
-
"grad_norm": 0.
|
| 702 |
-
"learning_rate": 3.
|
| 703 |
-
"loss": 0.
|
| 704 |
"step": 810
|
| 705 |
},
|
| 706 |
{
|
| 707 |
-
"epoch": 0.
|
| 708 |
-
"grad_norm": 0.
|
| 709 |
-
"learning_rate": 3.
|
| 710 |
-
"loss": 0.
|
| 711 |
"step": 820
|
| 712 |
},
|
| 713 |
{
|
| 714 |
-
"epoch": 0.
|
| 715 |
-
"grad_norm": 0.
|
| 716 |
-
"learning_rate": 3.
|
| 717 |
-
"loss": 0.
|
| 718 |
"step": 830
|
| 719 |
},
|
| 720 |
{
|
| 721 |
-
"epoch": 0.
|
| 722 |
-
"grad_norm": 0.
|
| 723 |
-
"learning_rate": 3.
|
| 724 |
-
"loss": 0.
|
| 725 |
"step": 840
|
| 726 |
},
|
| 727 |
{
|
| 728 |
-
"epoch": 0.
|
| 729 |
-
"grad_norm": 0.
|
| 730 |
-
"learning_rate": 3.
|
| 731 |
-
"loss": 0.
|
| 732 |
"step": 850
|
| 733 |
},
|
| 734 |
{
|
| 735 |
-
"epoch": 0.
|
| 736 |
-
"eval_loss": 0.
|
| 737 |
-
"eval_runtime": 13.
|
| 738 |
-
"eval_samples_per_second": 35.
|
| 739 |
-
"eval_steps_per_second": 2.
|
| 740 |
"step": 850
|
| 741 |
},
|
| 742 |
{
|
| 743 |
-
"epoch": 0.
|
| 744 |
-
"grad_norm": 0.
|
| 745 |
-
"learning_rate": 3.
|
| 746 |
-
"loss": 0.
|
| 747 |
"step": 860
|
| 748 |
},
|
| 749 |
{
|
| 750 |
-
"epoch": 0.
|
| 751 |
-
"grad_norm": 0.
|
| 752 |
-
"learning_rate": 3.
|
| 753 |
-
"loss": 0.
|
| 754 |
"step": 870
|
| 755 |
},
|
| 756 |
{
|
| 757 |
-
"epoch": 0.
|
| 758 |
-
"grad_norm": 0.
|
| 759 |
-
"learning_rate": 3.
|
| 760 |
-
"loss": 0.
|
| 761 |
"step": 880
|
| 762 |
},
|
| 763 |
{
|
| 764 |
-
"epoch": 0.
|
| 765 |
-
"grad_norm": 0.
|
| 766 |
-
"learning_rate": 3.
|
| 767 |
-
"loss": 0.
|
| 768 |
"step": 890
|
| 769 |
},
|
| 770 |
{
|
| 771 |
-
"epoch": 0.
|
| 772 |
-
"grad_norm": 0.
|
| 773 |
-
"learning_rate": 3.
|
| 774 |
-
"loss": 0.
|
| 775 |
"step": 900
|
| 776 |
},
|
| 777 |
{
|
| 778 |
-
"epoch": 0.
|
| 779 |
-
"eval_loss": 0.
|
| 780 |
-
"eval_runtime": 13.
|
| 781 |
-
"eval_samples_per_second": 35.
|
| 782 |
-
"eval_steps_per_second": 2.
|
| 783 |
"step": 900
|
| 784 |
},
|
| 785 |
{
|
| 786 |
-
"epoch": 0.
|
| 787 |
-
"grad_norm": 0.
|
| 788 |
-
"learning_rate": 3.
|
| 789 |
-
"loss": 0.
|
| 790 |
"step": 910
|
| 791 |
},
|
| 792 |
{
|
| 793 |
-
"epoch": 0.
|
| 794 |
-
"grad_norm": 0.
|
| 795 |
-
"learning_rate": 3.
|
| 796 |
-
"loss": 0.
|
| 797 |
"step": 920
|
| 798 |
},
|
| 799 |
{
|
| 800 |
-
"epoch": 0.
|
| 801 |
-
"grad_norm": 0.
|
| 802 |
-
"learning_rate": 3.
|
| 803 |
-
"loss": 0.
|
| 804 |
"step": 930
|
| 805 |
},
|
| 806 |
{
|
| 807 |
-
"epoch": 0.
|
| 808 |
-
"grad_norm": 0.
|
| 809 |
-
"learning_rate": 3.
|
| 810 |
-
"loss": 0.
|
| 811 |
"step": 940
|
| 812 |
},
|
| 813 |
{
|
| 814 |
-
"epoch":
|
| 815 |
-
"grad_norm": 0.
|
| 816 |
-
"learning_rate": 3.
|
| 817 |
-
"loss": 0.
|
| 818 |
"step": 950
|
| 819 |
},
|
| 820 |
{
|
| 821 |
-
"epoch":
|
| 822 |
-
"eval_loss": 0.
|
| 823 |
-
"eval_runtime": 13.
|
| 824 |
-
"eval_samples_per_second": 35.
|
| 825 |
-
"eval_steps_per_second": 2.
|
| 826 |
"step": 950
|
| 827 |
},
|
| 828 |
{
|
| 829 |
-
"epoch": 1.
|
| 830 |
-
"grad_norm": 0.
|
| 831 |
-
"learning_rate": 3.
|
| 832 |
-
"loss": 0.
|
| 833 |
"step": 960
|
| 834 |
},
|
| 835 |
{
|
| 836 |
-
"epoch": 1.
|
| 837 |
-
"grad_norm": 0.
|
| 838 |
-
"learning_rate": 3.
|
| 839 |
-
"loss": 0.
|
| 840 |
"step": 970
|
| 841 |
},
|
| 842 |
{
|
| 843 |
-
"epoch": 1.
|
| 844 |
-
"grad_norm": 0.
|
| 845 |
-
"learning_rate": 3.
|
| 846 |
-
"loss": 0.
|
| 847 |
"step": 980
|
| 848 |
},
|
| 849 |
{
|
| 850 |
-
"epoch": 1.
|
| 851 |
-
"grad_norm": 0.
|
| 852 |
-
"learning_rate": 3.
|
| 853 |
-
"loss": 0.
|
| 854 |
"step": 990
|
| 855 |
},
|
| 856 |
{
|
| 857 |
-
"epoch": 1.
|
| 858 |
-
"grad_norm": 0.
|
| 859 |
-
"learning_rate": 3.
|
| 860 |
-
"loss": 0.
|
| 861 |
"step": 1000
|
| 862 |
},
|
| 863 |
{
|
| 864 |
-
"epoch": 1.
|
| 865 |
-
"eval_loss": 0.
|
| 866 |
-
"eval_runtime": 13.
|
| 867 |
-
"eval_samples_per_second": 35.
|
| 868 |
-
"eval_steps_per_second": 2.
|
| 869 |
"step": 1000
|
| 870 |
},
|
| 871 |
{
|
| 872 |
-
"epoch": 1.
|
| 873 |
-
"grad_norm": 0.
|
| 874 |
-
"learning_rate": 3.
|
| 875 |
-
"loss": 0.
|
| 876 |
"step": 1010
|
| 877 |
},
|
| 878 |
{
|
| 879 |
-
"epoch": 1.
|
| 880 |
-
"grad_norm": 0.
|
| 881 |
-
"learning_rate": 3.
|
| 882 |
-
"loss": 0.
|
| 883 |
"step": 1020
|
| 884 |
},
|
| 885 |
{
|
| 886 |
-
"epoch": 1.
|
| 887 |
-
"grad_norm": 0.
|
| 888 |
-
"learning_rate": 3.
|
| 889 |
-
"loss": 0.
|
| 890 |
"step": 1030
|
| 891 |
},
|
| 892 |
{
|
| 893 |
-
"epoch": 1.
|
| 894 |
-
"grad_norm": 0.
|
| 895 |
-
"learning_rate": 3.
|
| 896 |
-
"loss": 0.
|
| 897 |
"step": 1040
|
| 898 |
},
|
| 899 |
{
|
| 900 |
-
"epoch": 1.
|
| 901 |
-
"grad_norm": 0.
|
| 902 |
-
"learning_rate": 3.
|
| 903 |
-
"loss": 0.
|
| 904 |
"step": 1050
|
| 905 |
},
|
| 906 |
{
|
| 907 |
-
"epoch": 1.
|
| 908 |
-
"eval_loss": 0.
|
| 909 |
-
"eval_runtime": 13.
|
| 910 |
-
"eval_samples_per_second": 35.
|
| 911 |
-
"eval_steps_per_second": 2.
|
| 912 |
"step": 1050
|
| 913 |
},
|
| 914 |
{
|
| 915 |
-
"epoch": 1.
|
| 916 |
-
"grad_norm": 0.
|
| 917 |
-
"learning_rate": 3.
|
| 918 |
-
"loss": 0.
|
| 919 |
"step": 1060
|
| 920 |
},
|
| 921 |
{
|
| 922 |
-
"epoch": 1.
|
| 923 |
-
"grad_norm": 0.
|
| 924 |
-
"learning_rate": 3.
|
| 925 |
-
"loss": 0.
|
| 926 |
"step": 1070
|
| 927 |
},
|
| 928 |
{
|
| 929 |
-
"epoch": 1.
|
| 930 |
-
"grad_norm": 0.
|
| 931 |
-
"learning_rate": 3.
|
| 932 |
-
"loss": 0.
|
| 933 |
"step": 1080
|
| 934 |
},
|
| 935 |
{
|
| 936 |
-
"epoch": 1.
|
| 937 |
-
"grad_norm": 0.
|
| 938 |
-
"learning_rate": 3.
|
| 939 |
-
"loss": 0.
|
| 940 |
"step": 1090
|
| 941 |
},
|
| 942 |
{
|
| 943 |
-
"epoch": 1.
|
| 944 |
-
"grad_norm": 0.
|
| 945 |
-
"learning_rate": 3.
|
| 946 |
-
"loss": 0.
|
| 947 |
"step": 1100
|
| 948 |
},
|
| 949 |
{
|
| 950 |
-
"epoch": 1.
|
| 951 |
-
"eval_loss": 0.
|
| 952 |
-
"eval_runtime": 13.
|
| 953 |
-
"eval_samples_per_second": 35.
|
| 954 |
-
"eval_steps_per_second": 2.
|
| 955 |
"step": 1100
|
| 956 |
},
|
| 957 |
{
|
| 958 |
-
"epoch": 1.
|
| 959 |
-
"grad_norm": 0.
|
| 960 |
-
"learning_rate": 3.
|
| 961 |
-
"loss": 0.
|
| 962 |
"step": 1110
|
| 963 |
},
|
| 964 |
{
|
| 965 |
-
"epoch": 1.
|
| 966 |
-
"grad_norm": 0.
|
| 967 |
-
"learning_rate": 3.
|
| 968 |
-
"loss": 0.
|
| 969 |
"step": 1120
|
| 970 |
},
|
| 971 |
{
|
| 972 |
-
"epoch": 1.
|
| 973 |
-
"grad_norm": 0.
|
| 974 |
-
"learning_rate": 3.
|
| 975 |
-
"loss": 0.
|
| 976 |
"step": 1130
|
| 977 |
},
|
| 978 |
{
|
| 979 |
-
"epoch": 1.
|
| 980 |
-
"grad_norm": 0.
|
| 981 |
-
"learning_rate":
|
| 982 |
-
"loss": 0.
|
| 983 |
"step": 1140
|
| 984 |
},
|
| 985 |
{
|
| 986 |
-
"epoch": 1.
|
| 987 |
-
"grad_norm": 0.
|
| 988 |
-
"learning_rate": 2.
|
| 989 |
-
"loss": 0.
|
| 990 |
"step": 1150
|
| 991 |
},
|
| 992 |
{
|
| 993 |
-
"epoch": 1.
|
| 994 |
-
"eval_loss": 0.
|
| 995 |
-
"eval_runtime": 13.
|
| 996 |
-
"eval_samples_per_second": 35.
|
| 997 |
-
"eval_steps_per_second": 2.
|
| 998 |
"step": 1150
|
| 999 |
},
|
| 1000 |
{
|
| 1001 |
-
"epoch": 1.
|
| 1002 |
-
"grad_norm": 0.
|
| 1003 |
-
"learning_rate": 2.
|
| 1004 |
-
"loss": 0.
|
| 1005 |
"step": 1160
|
| 1006 |
},
|
| 1007 |
{
|
| 1008 |
-
"epoch": 1.
|
| 1009 |
-
"grad_norm": 0.
|
| 1010 |
-
"learning_rate": 2.
|
| 1011 |
-
"loss": 0.
|
| 1012 |
"step": 1170
|
| 1013 |
},
|
| 1014 |
{
|
| 1015 |
-
"epoch": 1.
|
| 1016 |
-
"grad_norm": 0.
|
| 1017 |
-
"learning_rate": 2.
|
| 1018 |
"loss": 0.1983,
|
| 1019 |
"step": 1180
|
| 1020 |
},
|
| 1021 |
{
|
| 1022 |
-
"epoch": 1.
|
| 1023 |
-
"grad_norm": 0.
|
| 1024 |
-
"learning_rate": 2.
|
| 1025 |
-
"loss": 0.
|
| 1026 |
"step": 1190
|
| 1027 |
},
|
| 1028 |
{
|
| 1029 |
-
"epoch": 1.
|
| 1030 |
-
"grad_norm": 0.
|
| 1031 |
-
"learning_rate": 2.
|
| 1032 |
-
"loss": 0.
|
| 1033 |
"step": 1200
|
| 1034 |
},
|
| 1035 |
{
|
| 1036 |
-
"epoch": 1.
|
| 1037 |
-
"eval_loss": 0.
|
| 1038 |
-
"eval_runtime": 13.
|
| 1039 |
-
"eval_samples_per_second":
|
| 1040 |
-
"eval_steps_per_second": 2.
|
| 1041 |
"step": 1200
|
| 1042 |
},
|
| 1043 |
{
|
| 1044 |
-
"epoch": 1.
|
| 1045 |
-
"grad_norm": 0.
|
| 1046 |
-
"learning_rate": 2.
|
| 1047 |
-
"loss": 0.
|
| 1048 |
"step": 1210
|
| 1049 |
},
|
| 1050 |
{
|
| 1051 |
-
"epoch": 1.
|
| 1052 |
-
"grad_norm": 0.
|
| 1053 |
-
"learning_rate": 2.
|
| 1054 |
-
"loss": 0.
|
| 1055 |
"step": 1220
|
| 1056 |
},
|
| 1057 |
{
|
| 1058 |
-
"epoch": 1.
|
| 1059 |
-
"grad_norm": 0.
|
| 1060 |
-
"learning_rate": 2.
|
| 1061 |
-
"loss": 0.
|
| 1062 |
"step": 1230
|
| 1063 |
},
|
| 1064 |
{
|
| 1065 |
-
"epoch": 1.
|
| 1066 |
-
"grad_norm": 0.
|
| 1067 |
-
"learning_rate": 2.
|
| 1068 |
-
"loss": 0.
|
| 1069 |
"step": 1240
|
| 1070 |
},
|
| 1071 |
{
|
| 1072 |
-
"epoch": 1.
|
| 1073 |
-
"grad_norm": 0.
|
| 1074 |
-
"learning_rate": 2.
|
| 1075 |
-
"loss": 0.
|
| 1076 |
"step": 1250
|
| 1077 |
},
|
| 1078 |
{
|
| 1079 |
-
"epoch": 1.
|
| 1080 |
-
"eval_loss": 0.
|
| 1081 |
-
"eval_runtime": 13.
|
| 1082 |
-
"eval_samples_per_second": 35.
|
| 1083 |
-
"eval_steps_per_second": 2.
|
| 1084 |
"step": 1250
|
| 1085 |
},
|
| 1086 |
{
|
| 1087 |
-
"epoch": 1.
|
| 1088 |
-
"grad_norm": 0.
|
| 1089 |
-
"learning_rate": 2.
|
| 1090 |
-
"loss": 0.
|
| 1091 |
"step": 1260
|
| 1092 |
},
|
| 1093 |
{
|
| 1094 |
-
"epoch": 1.
|
| 1095 |
-
"grad_norm": 0.
|
| 1096 |
-
"learning_rate": 2.
|
| 1097 |
-
"loss": 0.
|
| 1098 |
"step": 1270
|
| 1099 |
},
|
| 1100 |
{
|
| 1101 |
-
"epoch": 1.
|
| 1102 |
-
"grad_norm": 0.
|
| 1103 |
-
"learning_rate": 2.
|
| 1104 |
-
"loss": 0.
|
| 1105 |
"step": 1280
|
| 1106 |
},
|
| 1107 |
{
|
| 1108 |
-
"epoch": 1.
|
| 1109 |
-
"grad_norm": 0.
|
| 1110 |
-
"learning_rate": 2.
|
| 1111 |
-
"loss": 0.
|
| 1112 |
"step": 1290
|
| 1113 |
},
|
| 1114 |
{
|
| 1115 |
-
"epoch": 1.
|
| 1116 |
-
"grad_norm": 0.
|
| 1117 |
-
"learning_rate": 2.
|
| 1118 |
-
"loss": 0.
|
| 1119 |
"step": 1300
|
| 1120 |
},
|
| 1121 |
{
|
| 1122 |
-
"epoch": 1.
|
| 1123 |
-
"eval_loss": 0.
|
| 1124 |
-
"eval_runtime": 13.
|
| 1125 |
-
"eval_samples_per_second": 35.
|
| 1126 |
-
"eval_steps_per_second": 2.
|
| 1127 |
"step": 1300
|
| 1128 |
},
|
| 1129 |
{
|
| 1130 |
-
"epoch": 1.
|
| 1131 |
-
"grad_norm": 0.
|
| 1132 |
-
"learning_rate": 2.
|
| 1133 |
-
"loss": 0.
|
| 1134 |
"step": 1310
|
| 1135 |
},
|
| 1136 |
{
|
| 1137 |
-
"epoch": 1.
|
| 1138 |
-
"grad_norm": 0.
|
| 1139 |
-
"learning_rate": 2.
|
| 1140 |
-
"loss": 0.
|
| 1141 |
"step": 1320
|
| 1142 |
},
|
| 1143 |
{
|
| 1144 |
-
"epoch": 1.
|
| 1145 |
-
"grad_norm": 0.
|
| 1146 |
-
"learning_rate": 2.
|
| 1147 |
-
"loss": 0.
|
| 1148 |
"step": 1330
|
| 1149 |
},
|
| 1150 |
{
|
| 1151 |
-
"epoch": 1.
|
| 1152 |
-
"grad_norm": 0.
|
| 1153 |
-
"learning_rate": 2.
|
| 1154 |
-
"loss": 0.
|
| 1155 |
"step": 1340
|
| 1156 |
},
|
| 1157 |
{
|
| 1158 |
-
"epoch": 1.
|
| 1159 |
-
"grad_norm": 0.
|
| 1160 |
-
"learning_rate": 2.
|
| 1161 |
-
"loss": 0.
|
| 1162 |
"step": 1350
|
| 1163 |
},
|
| 1164 |
{
|
| 1165 |
-
"epoch": 1.
|
| 1166 |
-
"eval_loss": 0.
|
| 1167 |
-
"eval_runtime": 13.
|
| 1168 |
-
"eval_samples_per_second": 35.
|
| 1169 |
-
"eval_steps_per_second": 2.
|
| 1170 |
"step": 1350
|
| 1171 |
},
|
| 1172 |
{
|
| 1173 |
-
"epoch": 1.
|
| 1174 |
-
"grad_norm": 0.
|
| 1175 |
-
"learning_rate": 2.
|
| 1176 |
-
"loss": 0.
|
| 1177 |
"step": 1360
|
| 1178 |
},
|
| 1179 |
{
|
| 1180 |
-
"epoch": 1.
|
| 1181 |
-
"grad_norm": 0.
|
| 1182 |
-
"learning_rate": 2.
|
| 1183 |
-
"loss": 0.
|
| 1184 |
"step": 1370
|
| 1185 |
},
|
| 1186 |
{
|
| 1187 |
-
"epoch": 1.
|
| 1188 |
-
"grad_norm": 0.
|
| 1189 |
-
"learning_rate": 2.
|
| 1190 |
-
"loss": 0.
|
| 1191 |
"step": 1380
|
| 1192 |
},
|
| 1193 |
{
|
| 1194 |
-
"epoch": 1.
|
| 1195 |
-
"grad_norm": 0.
|
| 1196 |
-
"learning_rate": 2.
|
| 1197 |
-
"loss": 0.
|
| 1198 |
"step": 1390
|
| 1199 |
},
|
| 1200 |
{
|
| 1201 |
-
"epoch": 1.
|
| 1202 |
-
"grad_norm": 0.
|
| 1203 |
-
"learning_rate": 2.
|
| 1204 |
-
"loss": 0.
|
| 1205 |
"step": 1400
|
| 1206 |
},
|
| 1207 |
{
|
| 1208 |
-
"epoch": 1.
|
| 1209 |
-
"eval_loss": 0.
|
| 1210 |
-
"eval_runtime": 13.
|
| 1211 |
-
"eval_samples_per_second": 35.
|
| 1212 |
-
"eval_steps_per_second": 2.
|
| 1213 |
"step": 1400
|
| 1214 |
},
|
| 1215 |
{
|
| 1216 |
-
"epoch": 1.
|
| 1217 |
-
"grad_norm": 0.
|
| 1218 |
-
"learning_rate": 2.
|
| 1219 |
-
"loss": 0.
|
| 1220 |
"step": 1410
|
| 1221 |
},
|
| 1222 |
{
|
| 1223 |
-
"epoch": 1.
|
| 1224 |
-
"grad_norm": 0.
|
| 1225 |
-
"learning_rate": 2.
|
| 1226 |
-
"loss": 0.
|
| 1227 |
"step": 1420
|
| 1228 |
},
|
| 1229 |
{
|
| 1230 |
-
"epoch": 1.
|
| 1231 |
-
"grad_norm": 0.
|
| 1232 |
-
"learning_rate": 2.
|
| 1233 |
-
"loss": 0.
|
| 1234 |
"step": 1430
|
| 1235 |
},
|
| 1236 |
{
|
| 1237 |
-
"epoch": 1.
|
| 1238 |
-
"grad_norm": 0.
|
| 1239 |
-
"learning_rate": 2.
|
| 1240 |
-
"loss": 0.
|
| 1241 |
"step": 1440
|
| 1242 |
},
|
| 1243 |
{
|
| 1244 |
-
"epoch": 1.
|
| 1245 |
-
"grad_norm": 0.
|
| 1246 |
-
"learning_rate": 2.
|
| 1247 |
-
"loss": 0.
|
| 1248 |
"step": 1450
|
| 1249 |
},
|
| 1250 |
{
|
| 1251 |
-
"epoch": 1.
|
| 1252 |
-
"eval_loss": 0.
|
| 1253 |
-
"eval_runtime": 13.
|
| 1254 |
-
"eval_samples_per_second": 35.
|
| 1255 |
-
"eval_steps_per_second": 2.
|
| 1256 |
"step": 1450
|
| 1257 |
},
|
| 1258 |
{
|
| 1259 |
-
"epoch": 1.
|
| 1260 |
-
"grad_norm": 0.
|
| 1261 |
-
"learning_rate": 2.
|
| 1262 |
-
"loss": 0.
|
| 1263 |
"step": 1460
|
| 1264 |
},
|
| 1265 |
{
|
| 1266 |
-
"epoch": 1.
|
| 1267 |
-
"grad_norm": 0.
|
| 1268 |
-
"learning_rate": 2.
|
| 1269 |
-
"loss": 0.
|
| 1270 |
"step": 1470
|
| 1271 |
},
|
| 1272 |
{
|
| 1273 |
-
"epoch": 1.
|
| 1274 |
-
"grad_norm": 0.
|
| 1275 |
-
"learning_rate": 2.
|
| 1276 |
-
"loss": 0.
|
| 1277 |
"step": 1480
|
| 1278 |
},
|
| 1279 |
{
|
| 1280 |
-
"epoch": 1.
|
| 1281 |
-
"grad_norm": 0.
|
| 1282 |
-
"learning_rate": 2.
|
| 1283 |
-
"loss": 0.
|
| 1284 |
"step": 1490
|
| 1285 |
},
|
| 1286 |
{
|
| 1287 |
-
"epoch": 1.
|
| 1288 |
-
"grad_norm": 0.
|
| 1289 |
-
"learning_rate": 2.
|
| 1290 |
-
"loss": 0.
|
| 1291 |
"step": 1500
|
| 1292 |
},
|
| 1293 |
{
|
| 1294 |
-
"epoch": 1.
|
| 1295 |
-
"eval_loss": 0.
|
| 1296 |
-
"eval_runtime": 13.
|
| 1297 |
-
"eval_samples_per_second": 35.
|
| 1298 |
-
"eval_steps_per_second": 2.
|
| 1299 |
"step": 1500
|
| 1300 |
},
|
| 1301 |
{
|
| 1302 |
-
"epoch": 1.
|
| 1303 |
-
"grad_norm": 0.
|
| 1304 |
-
"learning_rate": 2.
|
| 1305 |
-
"loss": 0.
|
| 1306 |
"step": 1510
|
| 1307 |
},
|
| 1308 |
{
|
| 1309 |
-
"epoch": 1.
|
| 1310 |
-
"grad_norm": 0.
|
| 1311 |
-
"learning_rate": 2.
|
| 1312 |
-
"loss": 0.
|
| 1313 |
"step": 1520
|
| 1314 |
},
|
| 1315 |
{
|
| 1316 |
-
"epoch": 1.
|
| 1317 |
-
"grad_norm": 0.
|
| 1318 |
-
"learning_rate": 2.
|
| 1319 |
-
"loss": 0.
|
| 1320 |
"step": 1530
|
| 1321 |
},
|
| 1322 |
{
|
| 1323 |
-
"epoch": 1.
|
| 1324 |
-
"grad_norm": 0.
|
| 1325 |
-
"learning_rate": 2.
|
| 1326 |
-
"loss": 0.
|
| 1327 |
"step": 1540
|
| 1328 |
},
|
| 1329 |
{
|
| 1330 |
-
"epoch": 1.
|
| 1331 |
-
"grad_norm": 0.
|
| 1332 |
-
"learning_rate": 2.
|
| 1333 |
-
"loss": 0.
|
| 1334 |
"step": 1550
|
| 1335 |
},
|
| 1336 |
{
|
| 1337 |
-
"epoch": 1.
|
| 1338 |
-
"eval_loss": 0.
|
| 1339 |
-
"eval_runtime": 13.
|
| 1340 |
-
"eval_samples_per_second": 35.
|
| 1341 |
-
"eval_steps_per_second": 2.
|
| 1342 |
"step": 1550
|
| 1343 |
},
|
| 1344 |
{
|
| 1345 |
-
"epoch": 1.
|
| 1346 |
-
"grad_norm": 0.
|
| 1347 |
-
"learning_rate": 2.
|
| 1348 |
-
"loss": 0.
|
| 1349 |
"step": 1560
|
| 1350 |
},
|
| 1351 |
{
|
| 1352 |
-
"epoch": 1.
|
| 1353 |
-
"grad_norm": 0.
|
| 1354 |
-
"learning_rate": 2.
|
| 1355 |
-
"loss": 0.
|
| 1356 |
"step": 1570
|
| 1357 |
},
|
| 1358 |
{
|
| 1359 |
-
"epoch": 1.
|
| 1360 |
-
"grad_norm": 0.
|
| 1361 |
-
"learning_rate": 2.
|
| 1362 |
-
"loss": 0.
|
| 1363 |
"step": 1580
|
| 1364 |
},
|
| 1365 |
{
|
| 1366 |
-
"epoch": 1.
|
| 1367 |
-
"grad_norm": 0.
|
| 1368 |
-
"learning_rate": 2.
|
| 1369 |
-
"loss": 0.
|
| 1370 |
"step": 1590
|
| 1371 |
},
|
| 1372 |
{
|
| 1373 |
-
"epoch": 1.
|
| 1374 |
-
"grad_norm": 0.
|
| 1375 |
-
"learning_rate": 2.
|
| 1376 |
-
"loss": 0.
|
| 1377 |
"step": 1600
|
| 1378 |
},
|
| 1379 |
{
|
| 1380 |
-
"epoch": 1.
|
| 1381 |
-
"eval_loss": 0.
|
| 1382 |
-
"eval_runtime": 13.
|
| 1383 |
-
"eval_samples_per_second": 35.
|
| 1384 |
-
"eval_steps_per_second": 2.
|
| 1385 |
"step": 1600
|
| 1386 |
},
|
| 1387 |
{
|
| 1388 |
-
"epoch": 1.
|
| 1389 |
-
"grad_norm": 0.
|
| 1390 |
-
"learning_rate": 2.
|
| 1391 |
-
"loss": 0.
|
| 1392 |
"step": 1610
|
| 1393 |
},
|
| 1394 |
{
|
| 1395 |
-
"epoch": 1.
|
| 1396 |
-
"grad_norm": 0.
|
| 1397 |
-
"learning_rate": 2.
|
| 1398 |
-
"loss": 0.
|
| 1399 |
"step": 1620
|
| 1400 |
},
|
| 1401 |
{
|
| 1402 |
-
"epoch": 1.
|
| 1403 |
-
"grad_norm": 0.
|
| 1404 |
-
"learning_rate": 2.
|
| 1405 |
-
"loss": 0.
|
| 1406 |
"step": 1630
|
| 1407 |
},
|
| 1408 |
{
|
| 1409 |
-
"epoch": 1.
|
| 1410 |
-
"grad_norm": 0.
|
| 1411 |
-
"learning_rate": 2.
|
| 1412 |
-
"loss": 0.
|
| 1413 |
"step": 1640
|
| 1414 |
},
|
| 1415 |
{
|
| 1416 |
-
"epoch": 1.
|
| 1417 |
-
"grad_norm": 0.
|
| 1418 |
-
"learning_rate": 2.
|
| 1419 |
-
"loss": 0.
|
| 1420 |
"step": 1650
|
| 1421 |
},
|
| 1422 |
{
|
| 1423 |
-
"epoch": 1.
|
| 1424 |
-
"eval_loss": 0.
|
| 1425 |
-
"eval_runtime": 13.
|
| 1426 |
-
"eval_samples_per_second": 35.
|
| 1427 |
-
"eval_steps_per_second": 2.
|
| 1428 |
"step": 1650
|
| 1429 |
},
|
| 1430 |
{
|
| 1431 |
-
"epoch": 1.
|
| 1432 |
-
"grad_norm": 0.
|
| 1433 |
-
"learning_rate": 2.
|
| 1434 |
-
"loss": 0.
|
| 1435 |
"step": 1660
|
| 1436 |
},
|
| 1437 |
{
|
| 1438 |
-
"epoch": 1.
|
| 1439 |
-
"grad_norm": 0.
|
| 1440 |
-
"learning_rate": 2.
|
| 1441 |
-
"loss": 0.
|
| 1442 |
"step": 1670
|
| 1443 |
},
|
| 1444 |
{
|
| 1445 |
-
"epoch": 1.
|
| 1446 |
-
"grad_norm": 0.
|
| 1447 |
-
"learning_rate": 2.
|
| 1448 |
-
"loss": 0.
|
| 1449 |
"step": 1680
|
| 1450 |
},
|
| 1451 |
{
|
| 1452 |
-
"epoch": 1.
|
| 1453 |
-
"grad_norm": 0.
|
| 1454 |
-
"learning_rate": 2.
|
| 1455 |
-
"loss": 0.
|
| 1456 |
"step": 1690
|
| 1457 |
},
|
| 1458 |
{
|
| 1459 |
-
"epoch": 1.
|
| 1460 |
-
"grad_norm": 0.
|
| 1461 |
-
"learning_rate": 2.
|
| 1462 |
-
"loss": 0.
|
| 1463 |
"step": 1700
|
| 1464 |
},
|
| 1465 |
{
|
| 1466 |
-
"epoch": 1.
|
| 1467 |
-
"eval_loss": 0.
|
| 1468 |
-
"eval_runtime": 13.
|
| 1469 |
-
"eval_samples_per_second": 35.
|
| 1470 |
-
"eval_steps_per_second": 2.
|
| 1471 |
"step": 1700
|
| 1472 |
},
|
| 1473 |
{
|
| 1474 |
-
"epoch": 1.
|
| 1475 |
-
"grad_norm": 0.
|
| 1476 |
-
"learning_rate":
|
| 1477 |
-
"loss": 0.
|
| 1478 |
"step": 1710
|
| 1479 |
},
|
| 1480 |
{
|
| 1481 |
-
"epoch": 1.
|
| 1482 |
-
"grad_norm": 0.
|
| 1483 |
-
"learning_rate": 1.
|
| 1484 |
-
"loss": 0.
|
| 1485 |
"step": 1720
|
| 1486 |
},
|
| 1487 |
{
|
| 1488 |
-
"epoch": 1.
|
| 1489 |
-
"grad_norm":
|
| 1490 |
-
"learning_rate": 1.
|
| 1491 |
-
"loss": 0.
|
| 1492 |
"step": 1730
|
| 1493 |
},
|
| 1494 |
{
|
| 1495 |
-
"epoch": 1.
|
| 1496 |
-
"grad_norm": 0.
|
| 1497 |
-
"learning_rate": 1.
|
| 1498 |
-
"loss": 0.
|
| 1499 |
"step": 1740
|
| 1500 |
},
|
| 1501 |
{
|
| 1502 |
-
"epoch": 1.
|
| 1503 |
-
"grad_norm": 0.
|
| 1504 |
-
"learning_rate": 1.
|
| 1505 |
-
"loss": 0.
|
| 1506 |
"step": 1750
|
| 1507 |
},
|
| 1508 |
{
|
| 1509 |
-
"epoch": 1.
|
| 1510 |
-
"eval_loss": 0.
|
| 1511 |
-
"eval_runtime": 13.
|
| 1512 |
-
"eval_samples_per_second": 35.
|
| 1513 |
-
"eval_steps_per_second": 2.
|
| 1514 |
"step": 1750
|
| 1515 |
},
|
| 1516 |
{
|
| 1517 |
-
"epoch": 1.
|
| 1518 |
-
"grad_norm":
|
| 1519 |
-
"learning_rate": 1.
|
| 1520 |
-
"loss": 0.
|
| 1521 |
"step": 1760
|
| 1522 |
},
|
| 1523 |
{
|
| 1524 |
-
"epoch": 1.
|
| 1525 |
-
"grad_norm": 0.
|
| 1526 |
-
"learning_rate": 1.
|
| 1527 |
-
"loss": 0.
|
| 1528 |
"step": 1770
|
| 1529 |
},
|
| 1530 |
{
|
| 1531 |
-
"epoch": 1.
|
| 1532 |
-
"grad_norm": 0.
|
| 1533 |
-
"learning_rate": 1.
|
| 1534 |
-
"loss": 0.
|
| 1535 |
"step": 1780
|
| 1536 |
},
|
| 1537 |
{
|
| 1538 |
-
"epoch": 1.
|
| 1539 |
-
"grad_norm": 0.
|
| 1540 |
-
"learning_rate": 1.
|
| 1541 |
-
"loss": 0.
|
| 1542 |
"step": 1790
|
| 1543 |
},
|
| 1544 |
{
|
| 1545 |
-
"epoch": 1.
|
| 1546 |
-
"grad_norm": 0.
|
| 1547 |
-
"learning_rate": 1.
|
| 1548 |
-
"loss": 0.
|
| 1549 |
"step": 1800
|
| 1550 |
},
|
| 1551 |
{
|
| 1552 |
-
"epoch": 1.
|
| 1553 |
-
"eval_loss": 0.
|
| 1554 |
-
"eval_runtime": 13.
|
| 1555 |
-
"eval_samples_per_second": 35.
|
| 1556 |
-
"eval_steps_per_second": 2.
|
| 1557 |
"step": 1800
|
| 1558 |
},
|
| 1559 |
{
|
| 1560 |
-
"epoch": 1.
|
| 1561 |
-
"grad_norm": 0.
|
| 1562 |
-
"learning_rate": 1.
|
| 1563 |
-
"loss": 0.
|
| 1564 |
"step": 1810
|
| 1565 |
},
|
| 1566 |
{
|
| 1567 |
-
"epoch": 1.
|
| 1568 |
-
"grad_norm": 0.
|
| 1569 |
-
"learning_rate": 1.
|
| 1570 |
-
"loss": 0.
|
| 1571 |
"step": 1820
|
| 1572 |
},
|
| 1573 |
{
|
| 1574 |
-
"epoch": 1.
|
| 1575 |
-
"grad_norm": 0.
|
| 1576 |
-
"learning_rate": 1.
|
| 1577 |
-
"loss": 0.
|
| 1578 |
"step": 1830
|
| 1579 |
},
|
| 1580 |
{
|
| 1581 |
-
"epoch": 1.
|
| 1582 |
-
"grad_norm": 0.
|
| 1583 |
-
"learning_rate": 1.
|
| 1584 |
-
"loss": 0.
|
| 1585 |
"step": 1840
|
| 1586 |
},
|
| 1587 |
{
|
| 1588 |
-
"epoch": 1.
|
| 1589 |
-
"grad_norm": 0.
|
| 1590 |
-
"learning_rate": 1.
|
| 1591 |
-
"loss": 0.
|
| 1592 |
"step": 1850
|
| 1593 |
},
|
| 1594 |
{
|
| 1595 |
-
"epoch": 1.
|
| 1596 |
-
"eval_loss": 0.
|
| 1597 |
-
"eval_runtime": 13.
|
| 1598 |
-
"eval_samples_per_second": 35.
|
| 1599 |
-
"eval_steps_per_second": 2.
|
| 1600 |
"step": 1850
|
| 1601 |
},
|
| 1602 |
{
|
| 1603 |
-
"epoch": 1.
|
| 1604 |
-
"grad_norm": 0.
|
| 1605 |
-
"learning_rate": 1.
|
| 1606 |
-
"loss": 0.
|
| 1607 |
"step": 1860
|
| 1608 |
},
|
| 1609 |
{
|
| 1610 |
-
"epoch": 1.
|
| 1611 |
-
"grad_norm": 0.
|
| 1612 |
-
"learning_rate": 1.
|
| 1613 |
-
"loss": 0.
|
| 1614 |
"step": 1870
|
| 1615 |
},
|
| 1616 |
{
|
| 1617 |
-
"epoch": 1.
|
| 1618 |
-
"grad_norm": 0.
|
| 1619 |
-
"learning_rate": 1.
|
| 1620 |
-
"loss": 0.
|
| 1621 |
"step": 1880
|
| 1622 |
},
|
| 1623 |
{
|
| 1624 |
-
"epoch": 1.
|
| 1625 |
-
"grad_norm": 0.
|
| 1626 |
-
"learning_rate": 1.
|
| 1627 |
-
"loss": 0.
|
| 1628 |
"step": 1890
|
| 1629 |
},
|
| 1630 |
{
|
| 1631 |
-
"epoch":
|
| 1632 |
-
"grad_norm": 0.
|
| 1633 |
-
"learning_rate": 1.
|
| 1634 |
-
"loss": 0.
|
| 1635 |
"step": 1900
|
| 1636 |
},
|
| 1637 |
{
|
| 1638 |
-
"epoch":
|
| 1639 |
-
"eval_loss": 0.
|
| 1640 |
-
"eval_runtime": 13.
|
| 1641 |
-
"eval_samples_per_second": 35.
|
| 1642 |
-
"eval_steps_per_second": 2.
|
| 1643 |
"step": 1900
|
| 1644 |
},
|
| 1645 |
{
|
| 1646 |
-
"epoch": 2.
|
| 1647 |
-
"grad_norm": 0.
|
| 1648 |
-
"learning_rate": 1.
|
| 1649 |
-
"loss": 0.
|
| 1650 |
"step": 1910
|
| 1651 |
},
|
| 1652 |
{
|
| 1653 |
-
"epoch": 2.
|
| 1654 |
-
"grad_norm": 0.
|
| 1655 |
-
"learning_rate": 1.
|
| 1656 |
-
"loss": 0.
|
| 1657 |
"step": 1920
|
| 1658 |
},
|
| 1659 |
{
|
| 1660 |
-
"epoch": 2.
|
| 1661 |
-
"grad_norm": 0.
|
| 1662 |
-
"learning_rate": 1.
|
| 1663 |
-
"loss": 0.
|
| 1664 |
"step": 1930
|
| 1665 |
},
|
| 1666 |
{
|
| 1667 |
-
"epoch": 2.
|
| 1668 |
-
"grad_norm": 0.
|
| 1669 |
-
"learning_rate": 1.
|
| 1670 |
-
"loss": 0.
|
| 1671 |
"step": 1940
|
| 1672 |
},
|
| 1673 |
{
|
| 1674 |
-
"epoch": 2.
|
| 1675 |
-
"grad_norm": 0.
|
| 1676 |
-
"learning_rate": 1.
|
| 1677 |
-
"loss": 0.
|
| 1678 |
"step": 1950
|
| 1679 |
},
|
| 1680 |
{
|
| 1681 |
-
"epoch": 2.
|
| 1682 |
-
"eval_loss": 0.
|
| 1683 |
-
"eval_runtime": 13.
|
| 1684 |
-
"eval_samples_per_second": 35.
|
| 1685 |
-
"eval_steps_per_second": 2.
|
| 1686 |
"step": 1950
|
| 1687 |
},
|
| 1688 |
{
|
| 1689 |
-
"epoch": 2.
|
| 1690 |
-
"grad_norm": 0.
|
| 1691 |
-
"learning_rate": 1.
|
| 1692 |
-
"loss": 0.
|
| 1693 |
"step": 1960
|
| 1694 |
},
|
| 1695 |
{
|
| 1696 |
-
"epoch": 2.
|
| 1697 |
-
"grad_norm": 0.
|
| 1698 |
-
"learning_rate": 1.
|
| 1699 |
-
"loss": 0.
|
| 1700 |
"step": 1970
|
| 1701 |
},
|
| 1702 |
{
|
| 1703 |
-
"epoch": 2.
|
| 1704 |
-
"grad_norm": 0.
|
| 1705 |
-
"learning_rate": 1.
|
| 1706 |
-
"loss": 0.
|
| 1707 |
"step": 1980
|
| 1708 |
},
|
| 1709 |
{
|
| 1710 |
-
"epoch": 2.
|
| 1711 |
-
"grad_norm": 0.
|
| 1712 |
-
"learning_rate": 1.
|
| 1713 |
-
"loss": 0.
|
| 1714 |
"step": 1990
|
| 1715 |
},
|
| 1716 |
{
|
| 1717 |
-
"epoch": 2.
|
| 1718 |
-
"grad_norm": 0.
|
| 1719 |
-
"learning_rate": 1.
|
| 1720 |
-
"loss": 0.
|
| 1721 |
"step": 2000
|
| 1722 |
},
|
| 1723 |
{
|
| 1724 |
-
"epoch": 2.
|
| 1725 |
-
"eval_loss": 0.
|
| 1726 |
-
"eval_runtime": 13.
|
| 1727 |
-
"eval_samples_per_second": 35.
|
| 1728 |
-
"eval_steps_per_second": 2.
|
| 1729 |
"step": 2000
|
| 1730 |
},
|
| 1731 |
{
|
| 1732 |
-
"epoch": 2.
|
| 1733 |
-
"grad_norm": 0.
|
| 1734 |
-
"learning_rate": 1.
|
| 1735 |
-
"loss": 0.
|
| 1736 |
"step": 2010
|
| 1737 |
},
|
| 1738 |
{
|
| 1739 |
-
"epoch": 2.
|
| 1740 |
-
"grad_norm": 0.
|
| 1741 |
-
"learning_rate": 1.
|
| 1742 |
-
"loss": 0.
|
| 1743 |
"step": 2020
|
| 1744 |
},
|
| 1745 |
{
|
| 1746 |
-
"epoch": 2.
|
| 1747 |
-
"grad_norm": 0.
|
| 1748 |
-
"learning_rate": 1.
|
| 1749 |
-
"loss": 0.
|
| 1750 |
"step": 2030
|
| 1751 |
},
|
| 1752 |
{
|
| 1753 |
-
"epoch": 2.
|
| 1754 |
-
"grad_norm": 0.
|
| 1755 |
-
"learning_rate": 1.
|
| 1756 |
-
"loss": 0.
|
| 1757 |
"step": 2040
|
| 1758 |
},
|
| 1759 |
{
|
| 1760 |
-
"epoch": 2.
|
| 1761 |
-
"grad_norm": 0.
|
| 1762 |
-
"learning_rate": 1.
|
| 1763 |
-
"loss": 0.
|
| 1764 |
"step": 2050
|
| 1765 |
},
|
| 1766 |
{
|
| 1767 |
-
"epoch": 2.
|
| 1768 |
-
"eval_loss": 0.
|
| 1769 |
-
"eval_runtime": 13.
|
| 1770 |
-
"eval_samples_per_second": 35.
|
| 1771 |
-
"eval_steps_per_second": 2.
|
| 1772 |
"step": 2050
|
| 1773 |
},
|
| 1774 |
{
|
| 1775 |
-
"epoch": 2.
|
| 1776 |
-
"grad_norm": 0.
|
| 1777 |
-
"learning_rate": 1.
|
| 1778 |
-
"loss": 0.
|
| 1779 |
"step": 2060
|
| 1780 |
},
|
| 1781 |
{
|
| 1782 |
-
"epoch": 2.
|
| 1783 |
-
"grad_norm": 0.
|
| 1784 |
-
"learning_rate": 1.
|
| 1785 |
-
"loss": 0.
|
| 1786 |
"step": 2070
|
| 1787 |
},
|
| 1788 |
{
|
| 1789 |
-
"epoch": 2.
|
| 1790 |
-
"grad_norm": 0.
|
| 1791 |
-
"learning_rate": 1.
|
| 1792 |
-
"loss": 0.
|
| 1793 |
"step": 2080
|
| 1794 |
},
|
| 1795 |
{
|
| 1796 |
-
"epoch": 2.
|
| 1797 |
-
"grad_norm": 0.
|
| 1798 |
-
"learning_rate": 1.
|
| 1799 |
-
"loss": 0.
|
| 1800 |
"step": 2090
|
| 1801 |
},
|
| 1802 |
{
|
| 1803 |
-
"epoch": 2.
|
| 1804 |
-
"grad_norm": 0.
|
| 1805 |
-
"learning_rate": 1.
|
| 1806 |
-
"loss": 0.
|
| 1807 |
"step": 2100
|
| 1808 |
},
|
| 1809 |
{
|
| 1810 |
-
"epoch": 2.
|
| 1811 |
-
"eval_loss": 0.
|
| 1812 |
-
"eval_runtime": 13.
|
| 1813 |
-
"eval_samples_per_second": 35.
|
| 1814 |
-
"eval_steps_per_second": 2.
|
| 1815 |
"step": 2100
|
| 1816 |
},
|
| 1817 |
{
|
| 1818 |
-
"epoch": 2.
|
| 1819 |
-
"grad_norm": 0.
|
| 1820 |
-
"learning_rate": 1.
|
| 1821 |
-
"loss": 0.
|
| 1822 |
"step": 2110
|
| 1823 |
},
|
| 1824 |
{
|
| 1825 |
-
"epoch": 2.
|
| 1826 |
-
"grad_norm": 0.
|
| 1827 |
-
"learning_rate": 1.
|
| 1828 |
-
"loss": 0.
|
| 1829 |
"step": 2120
|
| 1830 |
},
|
| 1831 |
{
|
| 1832 |
-
"epoch": 2.
|
| 1833 |
-
"grad_norm": 0.
|
| 1834 |
-
"learning_rate": 1.
|
| 1835 |
-
"loss": 0.
|
| 1836 |
"step": 2130
|
| 1837 |
},
|
| 1838 |
{
|
| 1839 |
-
"epoch": 2.
|
| 1840 |
-
"grad_norm":
|
| 1841 |
-
"learning_rate": 1.
|
| 1842 |
-
"loss": 0.
|
| 1843 |
"step": 2140
|
| 1844 |
},
|
| 1845 |
{
|
| 1846 |
-
"epoch": 2.
|
| 1847 |
-
"grad_norm": 0.
|
| 1848 |
-
"learning_rate": 1.
|
| 1849 |
-
"loss": 0.
|
| 1850 |
"step": 2150
|
| 1851 |
},
|
| 1852 |
{
|
| 1853 |
-
"epoch": 2.
|
| 1854 |
-
"eval_loss": 0.
|
| 1855 |
-
"eval_runtime": 13.
|
| 1856 |
-
"eval_samples_per_second": 35.
|
| 1857 |
-
"eval_steps_per_second": 2.
|
| 1858 |
"step": 2150
|
| 1859 |
},
|
| 1860 |
{
|
| 1861 |
-
"epoch": 2.
|
| 1862 |
-
"grad_norm": 0.
|
| 1863 |
-
"learning_rate": 1.
|
| 1864 |
-
"loss": 0.
|
| 1865 |
"step": 2160
|
| 1866 |
},
|
| 1867 |
{
|
| 1868 |
-
"epoch": 2.
|
| 1869 |
-
"grad_norm": 0.
|
| 1870 |
-
"learning_rate": 1.
|
| 1871 |
-
"loss": 0.
|
| 1872 |
"step": 2170
|
| 1873 |
},
|
| 1874 |
{
|
| 1875 |
-
"epoch": 2.
|
| 1876 |
-
"grad_norm": 0.
|
| 1877 |
-
"learning_rate": 1.
|
| 1878 |
-
"loss": 0.
|
| 1879 |
"step": 2180
|
| 1880 |
},
|
| 1881 |
{
|
| 1882 |
-
"epoch": 2.
|
| 1883 |
-
"grad_norm":
|
| 1884 |
-
"learning_rate": 1.
|
| 1885 |
-
"loss": 0.
|
| 1886 |
"step": 2190
|
| 1887 |
},
|
| 1888 |
{
|
| 1889 |
-
"epoch": 2.
|
| 1890 |
-
"grad_norm":
|
| 1891 |
-
"learning_rate": 1.
|
| 1892 |
-
"loss": 0.
|
| 1893 |
"step": 2200
|
| 1894 |
},
|
| 1895 |
{
|
| 1896 |
-
"epoch": 2.
|
| 1897 |
-
"eval_loss": 0.
|
| 1898 |
-
"eval_runtime": 13.
|
| 1899 |
-
"eval_samples_per_second": 35.
|
| 1900 |
-
"eval_steps_per_second": 2.
|
| 1901 |
"step": 2200
|
| 1902 |
},
|
| 1903 |
{
|
| 1904 |
-
"epoch": 2.
|
| 1905 |
-
"grad_norm": 0.
|
| 1906 |
-
"learning_rate": 1.
|
| 1907 |
-
"loss": 0.
|
| 1908 |
"step": 2210
|
| 1909 |
},
|
| 1910 |
{
|
| 1911 |
-
"epoch": 2.
|
| 1912 |
-
"grad_norm": 0.
|
| 1913 |
-
"learning_rate": 1.
|
| 1914 |
-
"loss": 0.
|
| 1915 |
"step": 2220
|
| 1916 |
},
|
| 1917 |
{
|
| 1918 |
-
"epoch": 2.
|
| 1919 |
-
"grad_norm": 0.
|
| 1920 |
-
"learning_rate": 1.
|
| 1921 |
-
"loss": 0.
|
| 1922 |
"step": 2230
|
| 1923 |
},
|
| 1924 |
{
|
| 1925 |
-
"epoch": 2.
|
| 1926 |
-
"grad_norm": 0.
|
| 1927 |
-
"learning_rate": 1.
|
| 1928 |
-
"loss": 0.
|
| 1929 |
"step": 2240
|
| 1930 |
},
|
| 1931 |
{
|
| 1932 |
-
"epoch": 2.
|
| 1933 |
-
"grad_norm":
|
| 1934 |
-
"learning_rate": 1.
|
| 1935 |
-
"loss": 0.
|
| 1936 |
"step": 2250
|
| 1937 |
},
|
| 1938 |
{
|
| 1939 |
-
"epoch": 2.
|
| 1940 |
-
"eval_loss": 0.
|
| 1941 |
-
"eval_runtime": 13.
|
| 1942 |
-
"eval_samples_per_second": 35.
|
| 1943 |
-
"eval_steps_per_second": 2.
|
| 1944 |
"step": 2250
|
| 1945 |
},
|
| 1946 |
{
|
| 1947 |
-
"epoch": 2.
|
| 1948 |
-
"grad_norm": 0.
|
| 1949 |
-
"learning_rate": 1.
|
| 1950 |
-
"loss": 0.
|
| 1951 |
"step": 2260
|
| 1952 |
},
|
| 1953 |
{
|
| 1954 |
-
"epoch": 2.
|
| 1955 |
-
"grad_norm": 0.
|
| 1956 |
-
"learning_rate": 1.
|
| 1957 |
-
"loss": 0.
|
| 1958 |
"step": 2270
|
| 1959 |
},
|
| 1960 |
{
|
| 1961 |
-
"epoch": 2.
|
| 1962 |
-
"grad_norm":
|
| 1963 |
-
"learning_rate":
|
| 1964 |
-
"loss": 0.
|
| 1965 |
"step": 2280
|
| 1966 |
},
|
| 1967 |
{
|
| 1968 |
-
"epoch": 2.
|
| 1969 |
-
"grad_norm": 0.
|
| 1970 |
-
"learning_rate": 9.
|
| 1971 |
-
"loss": 0.
|
| 1972 |
"step": 2290
|
| 1973 |
},
|
| 1974 |
{
|
| 1975 |
-
"epoch": 2.
|
| 1976 |
-
"grad_norm": 0.
|
| 1977 |
-
"learning_rate": 9.
|
| 1978 |
-
"loss": 0.
|
| 1979 |
"step": 2300
|
| 1980 |
},
|
| 1981 |
{
|
| 1982 |
-
"epoch": 2.
|
| 1983 |
-
"eval_loss": 0.
|
| 1984 |
-
"eval_runtime": 13.
|
| 1985 |
-
"eval_samples_per_second": 35.
|
| 1986 |
-
"eval_steps_per_second": 2.
|
| 1987 |
"step": 2300
|
| 1988 |
},
|
| 1989 |
{
|
| 1990 |
-
"epoch": 2.
|
| 1991 |
-
"grad_norm": 0.
|
| 1992 |
-
"learning_rate": 9.
|
| 1993 |
-
"loss": 0.
|
| 1994 |
"step": 2310
|
| 1995 |
},
|
| 1996 |
{
|
| 1997 |
-
"epoch": 2.
|
| 1998 |
-
"grad_norm": 0.
|
| 1999 |
-
"learning_rate": 9.
|
| 2000 |
-
"loss": 0.
|
| 2001 |
"step": 2320
|
| 2002 |
},
|
| 2003 |
{
|
| 2004 |
-
"epoch": 2.
|
| 2005 |
-
"grad_norm": 0.
|
| 2006 |
-
"learning_rate": 9.
|
| 2007 |
-
"loss": 0.
|
| 2008 |
"step": 2330
|
| 2009 |
},
|
| 2010 |
{
|
| 2011 |
-
"epoch": 2.
|
| 2012 |
-
"grad_norm": 0.
|
| 2013 |
-
"learning_rate":
|
| 2014 |
-
"loss": 0.
|
| 2015 |
"step": 2340
|
| 2016 |
},
|
| 2017 |
{
|
| 2018 |
-
"epoch": 2.
|
| 2019 |
-
"grad_norm": 0.
|
| 2020 |
-
"learning_rate": 8.
|
| 2021 |
-
"loss": 0.
|
| 2022 |
"step": 2350
|
| 2023 |
},
|
| 2024 |
{
|
| 2025 |
-
"epoch": 2.
|
| 2026 |
-
"eval_loss": 0.
|
| 2027 |
-
"eval_runtime": 13.
|
| 2028 |
-
"eval_samples_per_second": 35.
|
| 2029 |
-
"eval_steps_per_second": 2.
|
| 2030 |
"step": 2350
|
| 2031 |
},
|
| 2032 |
{
|
| 2033 |
-
"epoch": 2.
|
| 2034 |
-
"grad_norm": 0.
|
| 2035 |
-
"learning_rate": 8.
|
| 2036 |
-
"loss": 0.
|
| 2037 |
"step": 2360
|
| 2038 |
},
|
| 2039 |
{
|
| 2040 |
-
"epoch": 2.
|
| 2041 |
-
"grad_norm": 0.
|
| 2042 |
-
"learning_rate": 8.
|
| 2043 |
-
"loss": 0.
|
| 2044 |
"step": 2370
|
| 2045 |
},
|
| 2046 |
{
|
| 2047 |
-
"epoch": 2.
|
| 2048 |
-
"grad_norm": 0.
|
| 2049 |
-
"learning_rate": 8.
|
| 2050 |
-
"loss": 0.
|
| 2051 |
"step": 2380
|
| 2052 |
},
|
| 2053 |
{
|
| 2054 |
-
"epoch": 2.
|
| 2055 |
-
"grad_norm": 0.
|
| 2056 |
-
"learning_rate": 8.
|
| 2057 |
-
"loss": 0.
|
| 2058 |
"step": 2390
|
| 2059 |
},
|
| 2060 |
{
|
| 2061 |
-
"epoch": 2.
|
| 2062 |
-
"grad_norm": 0.
|
| 2063 |
-
"learning_rate": 7.
|
| 2064 |
-
"loss": 0.
|
| 2065 |
"step": 2400
|
| 2066 |
},
|
| 2067 |
{
|
| 2068 |
-
"epoch": 2.
|
| 2069 |
-
"eval_loss": 0.
|
| 2070 |
-
"eval_runtime": 13.
|
| 2071 |
-
"eval_samples_per_second": 35.
|
| 2072 |
-
"eval_steps_per_second": 2.
|
| 2073 |
"step": 2400
|
| 2074 |
}
|
| 2075 |
],
|
| 2076 |
"logging_steps": 10,
|
| 2077 |
-
"max_steps":
|
| 2078 |
"num_input_tokens_seen": 0,
|
| 2079 |
"num_train_epochs": 3,
|
| 2080 |
"save_steps": 100,
|
|
@@ -2090,7 +2090,7 @@
|
|
| 2090 |
"attributes": {}
|
| 2091 |
}
|
| 2092 |
},
|
| 2093 |
-
"total_flos": 2.
|
| 2094 |
"train_batch_size": 16,
|
| 2095 |
"trial_name": null,
|
| 2096 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.528977871443625,
|
| 5 |
"eval_steps": 50,
|
| 6 |
"global_step": 2400,
|
| 7 |
"is_hyper_param_search": false,
|
|
|
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
+
"epoch": 0.01053740779768177,
|
| 13 |
+
"grad_norm": 3.070249080657959,
|
| 14 |
+
"learning_rate": 4.982437653670531e-05,
|
| 15 |
+
"loss": 1.7879,
|
| 16 |
"step": 10
|
| 17 |
},
|
| 18 |
{
|
| 19 |
+
"epoch": 0.02107481559536354,
|
| 20 |
+
"grad_norm": 1.702326774597168,
|
| 21 |
+
"learning_rate": 4.964875307341061e-05,
|
| 22 |
+
"loss": 0.5567,
|
| 23 |
"step": 20
|
| 24 |
},
|
| 25 |
{
|
| 26 |
+
"epoch": 0.03161222339304531,
|
| 27 |
+
"grad_norm": 1.1947294473648071,
|
| 28 |
+
"learning_rate": 4.947312961011591e-05,
|
| 29 |
+
"loss": 0.4493,
|
| 30 |
"step": 30
|
| 31 |
},
|
| 32 |
{
|
| 33 |
+
"epoch": 0.04214963119072708,
|
| 34 |
+
"grad_norm": 0.9556658267974854,
|
| 35 |
+
"learning_rate": 4.929750614682122e-05,
|
| 36 |
+
"loss": 0.3728,
|
| 37 |
"step": 40
|
| 38 |
},
|
| 39 |
{
|
| 40 |
+
"epoch": 0.05268703898840885,
|
| 41 |
+
"grad_norm": 0.7952510714530945,
|
| 42 |
+
"learning_rate": 4.9121882683526524e-05,
|
| 43 |
+
"loss": 0.3535,
|
| 44 |
"step": 50
|
| 45 |
},
|
| 46 |
{
|
| 47 |
+
"epoch": 0.05268703898840885,
|
| 48 |
+
"eval_loss": 0.4311191439628601,
|
| 49 |
+
"eval_runtime": 13.6539,
|
| 50 |
+
"eval_samples_per_second": 35.155,
|
| 51 |
+
"eval_steps_per_second": 2.197,
|
| 52 |
"step": 50
|
| 53 |
},
|
| 54 |
{
|
| 55 |
+
"epoch": 0.06322444678609063,
|
| 56 |
+
"grad_norm": 0.6962826251983643,
|
| 57 |
+
"learning_rate": 4.894625922023183e-05,
|
| 58 |
+
"loss": 0.3507,
|
| 59 |
"step": 60
|
| 60 |
},
|
| 61 |
{
|
| 62 |
+
"epoch": 0.0737618545837724,
|
| 63 |
+
"grad_norm": 0.6941961646080017,
|
| 64 |
+
"learning_rate": 4.877063575693713e-05,
|
| 65 |
+
"loss": 0.3585,
|
| 66 |
"step": 70
|
| 67 |
},
|
| 68 |
{
|
| 69 |
+
"epoch": 0.08429926238145416,
|
| 70 |
+
"grad_norm": 0.6864392757415771,
|
| 71 |
+
"learning_rate": 4.8595012293642434e-05,
|
| 72 |
+
"loss": 0.3496,
|
| 73 |
"step": 80
|
| 74 |
},
|
| 75 |
{
|
| 76 |
+
"epoch": 0.09483667017913593,
|
| 77 |
+
"grad_norm": 0.7322937846183777,
|
| 78 |
+
"learning_rate": 4.841938883034774e-05,
|
| 79 |
+
"loss": 0.3295,
|
| 80 |
"step": 90
|
| 81 |
},
|
| 82 |
{
|
| 83 |
+
"epoch": 0.1053740779768177,
|
| 84 |
+
"grad_norm": 0.6921488046646118,
|
| 85 |
+
"learning_rate": 4.824376536705304e-05,
|
| 86 |
+
"loss": 0.3357,
|
| 87 |
"step": 100
|
| 88 |
},
|
| 89 |
{
|
| 90 |
+
"epoch": 0.1053740779768177,
|
| 91 |
+
"eval_loss": 0.39120009541511536,
|
| 92 |
+
"eval_runtime": 13.7031,
|
| 93 |
+
"eval_samples_per_second": 35.029,
|
| 94 |
+
"eval_steps_per_second": 2.189,
|
| 95 |
"step": 100
|
| 96 |
},
|
| 97 |
{
|
| 98 |
+
"epoch": 0.11591148577449947,
|
| 99 |
+
"grad_norm": 0.6553240418434143,
|
| 100 |
+
"learning_rate": 4.8068141903758344e-05,
|
| 101 |
+
"loss": 0.3105,
|
| 102 |
"step": 110
|
| 103 |
},
|
| 104 |
{
|
| 105 |
+
"epoch": 0.12644889357218125,
|
| 106 |
+
"grad_norm": 0.5637819170951843,
|
| 107 |
+
"learning_rate": 4.789251844046364e-05,
|
| 108 |
+
"loss": 0.3164,
|
| 109 |
"step": 120
|
| 110 |
},
|
| 111 |
{
|
| 112 |
+
"epoch": 0.136986301369863,
|
| 113 |
+
"grad_norm": 0.6341928839683533,
|
| 114 |
+
"learning_rate": 4.7716894977168955e-05,
|
| 115 |
+
"loss": 0.304,
|
| 116 |
"step": 130
|
| 117 |
},
|
| 118 |
{
|
| 119 |
+
"epoch": 0.1475237091675448,
|
| 120 |
+
"grad_norm": 0.5917785167694092,
|
| 121 |
+
"learning_rate": 4.754127151387426e-05,
|
| 122 |
+
"loss": 0.3234,
|
| 123 |
"step": 140
|
| 124 |
},
|
| 125 |
{
|
| 126 |
+
"epoch": 0.15806111696522657,
|
| 127 |
+
"grad_norm": 0.5884453654289246,
|
| 128 |
+
"learning_rate": 4.736564805057956e-05,
|
| 129 |
+
"loss": 0.317,
|
| 130 |
"step": 150
|
| 131 |
},
|
| 132 |
{
|
| 133 |
+
"epoch": 0.15806111696522657,
|
| 134 |
+
"eval_loss": 0.37688738107681274,
|
| 135 |
+
"eval_runtime": 13.6535,
|
| 136 |
+
"eval_samples_per_second": 35.156,
|
| 137 |
+
"eval_steps_per_second": 2.197,
|
| 138 |
"step": 150
|
| 139 |
},
|
| 140 |
{
|
| 141 |
+
"epoch": 0.16859852476290832,
|
| 142 |
+
"grad_norm": 0.5819964408874512,
|
| 143 |
+
"learning_rate": 4.7190024587284866e-05,
|
| 144 |
+
"loss": 0.2992,
|
| 145 |
"step": 160
|
| 146 |
},
|
| 147 |
{
|
| 148 |
+
"epoch": 0.1791359325605901,
|
| 149 |
+
"grad_norm": 0.689468264579773,
|
| 150 |
+
"learning_rate": 4.7014401123990165e-05,
|
| 151 |
+
"loss": 0.3168,
|
| 152 |
"step": 170
|
| 153 |
},
|
| 154 |
{
|
| 155 |
+
"epoch": 0.18967334035827185,
|
| 156 |
+
"grad_norm": 0.6950872540473938,
|
| 157 |
+
"learning_rate": 4.683877766069547e-05,
|
| 158 |
+
"loss": 0.3041,
|
| 159 |
"step": 180
|
| 160 |
},
|
| 161 |
{
|
| 162 |
+
"epoch": 0.20021074815595363,
|
| 163 |
+
"grad_norm": 0.8322122097015381,
|
| 164 |
+
"learning_rate": 4.6663154197400776e-05,
|
| 165 |
+
"loss": 0.3028,
|
| 166 |
"step": 190
|
| 167 |
},
|
| 168 |
{
|
| 169 |
+
"epoch": 0.2107481559536354,
|
| 170 |
+
"grad_norm": 0.5850774645805359,
|
| 171 |
+
"learning_rate": 4.6487530734106075e-05,
|
| 172 |
+
"loss": 0.2992,
|
| 173 |
"step": 200
|
| 174 |
},
|
| 175 |
{
|
| 176 |
+
"epoch": 0.2107481559536354,
|
| 177 |
+
"eval_loss": 0.36230018734931946,
|
| 178 |
+
"eval_runtime": 13.6165,
|
| 179 |
+
"eval_samples_per_second": 35.251,
|
| 180 |
+
"eval_steps_per_second": 2.203,
|
| 181 |
"step": 200
|
| 182 |
},
|
| 183 |
{
|
| 184 |
+
"epoch": 0.22128556375131717,
|
| 185 |
+
"grad_norm": 0.6668715476989746,
|
| 186 |
+
"learning_rate": 4.631190727081138e-05,
|
| 187 |
+
"loss": 0.2924,
|
| 188 |
"step": 210
|
| 189 |
},
|
| 190 |
{
|
| 191 |
+
"epoch": 0.23182297154899895,
|
| 192 |
+
"grad_norm": 0.4749641418457031,
|
| 193 |
+
"learning_rate": 4.6136283807516686e-05,
|
| 194 |
+
"loss": 0.3017,
|
| 195 |
"step": 220
|
| 196 |
},
|
| 197 |
{
|
| 198 |
+
"epoch": 0.24236037934668073,
|
| 199 |
+
"grad_norm": 0.6381515860557556,
|
| 200 |
+
"learning_rate": 4.596066034422199e-05,
|
| 201 |
+
"loss": 0.2887,
|
| 202 |
"step": 230
|
| 203 |
},
|
| 204 |
{
|
| 205 |
+
"epoch": 0.2528977871443625,
|
| 206 |
+
"grad_norm": 0.49952977895736694,
|
| 207 |
+
"learning_rate": 4.57850368809273e-05,
|
| 208 |
+
"loss": 0.2833,
|
| 209 |
"step": 240
|
| 210 |
},
|
| 211 |
{
|
| 212 |
+
"epoch": 0.26343519494204426,
|
| 213 |
+
"grad_norm": 0.699518084526062,
|
| 214 |
+
"learning_rate": 4.5609413417632596e-05,
|
| 215 |
+
"loss": 0.2859,
|
| 216 |
"step": 250
|
| 217 |
},
|
| 218 |
{
|
| 219 |
+
"epoch": 0.26343519494204426,
|
| 220 |
+
"eval_loss": 0.3563433885574341,
|
| 221 |
+
"eval_runtime": 13.6275,
|
| 222 |
+
"eval_samples_per_second": 35.223,
|
| 223 |
+
"eval_steps_per_second": 2.201,
|
| 224 |
"step": 250
|
| 225 |
},
|
| 226 |
{
|
| 227 |
+
"epoch": 0.273972602739726,
|
| 228 |
+
"grad_norm": 0.5912085175514221,
|
| 229 |
+
"learning_rate": 4.54337899543379e-05,
|
| 230 |
+
"loss": 0.302,
|
| 231 |
"step": 260
|
| 232 |
},
|
| 233 |
{
|
| 234 |
+
"epoch": 0.2845100105374078,
|
| 235 |
+
"grad_norm": 0.6353363990783691,
|
| 236 |
+
"learning_rate": 4.525816649104321e-05,
|
| 237 |
+
"loss": 0.3112,
|
| 238 |
"step": 270
|
| 239 |
},
|
| 240 |
{
|
| 241 |
+
"epoch": 0.2950474183350896,
|
| 242 |
+
"grad_norm": 0.5483567118644714,
|
| 243 |
+
"learning_rate": 4.5082543027748506e-05,
|
| 244 |
+
"loss": 0.2808,
|
| 245 |
"step": 280
|
| 246 |
},
|
| 247 |
{
|
| 248 |
+
"epoch": 0.3055848261327713,
|
| 249 |
+
"grad_norm": 0.5003193616867065,
|
| 250 |
+
"learning_rate": 4.490691956445381e-05,
|
| 251 |
+
"loss": 0.3185,
|
| 252 |
"step": 290
|
| 253 |
},
|
| 254 |
{
|
| 255 |
+
"epoch": 0.31612223393045313,
|
| 256 |
+
"grad_norm": 0.4919240176677704,
|
| 257 |
+
"learning_rate": 4.473129610115912e-05,
|
| 258 |
+
"loss": 0.2883,
|
| 259 |
"step": 300
|
| 260 |
},
|
| 261 |
{
|
| 262 |
+
"epoch": 0.31612223393045313,
|
| 263 |
+
"eval_loss": 0.35315924882888794,
|
| 264 |
+
"eval_runtime": 13.6133,
|
| 265 |
+
"eval_samples_per_second": 35.26,
|
| 266 |
+
"eval_steps_per_second": 2.204,
|
| 267 |
"step": 300
|
| 268 |
},
|
| 269 |
{
|
| 270 |
+
"epoch": 0.3266596417281349,
|
| 271 |
+
"grad_norm": 0.5145038366317749,
|
| 272 |
+
"learning_rate": 4.455567263786442e-05,
|
| 273 |
+
"loss": 0.3084,
|
| 274 |
"step": 310
|
| 275 |
},
|
| 276 |
{
|
| 277 |
+
"epoch": 0.33719704952581664,
|
| 278 |
+
"grad_norm": 0.6343855261802673,
|
| 279 |
+
"learning_rate": 4.438004917456973e-05,
|
| 280 |
+
"loss": 0.295,
|
| 281 |
"step": 320
|
| 282 |
},
|
| 283 |
{
|
| 284 |
+
"epoch": 0.34773445732349845,
|
| 285 |
+
"grad_norm": 0.5336400270462036,
|
| 286 |
+
"learning_rate": 4.420442571127503e-05,
|
| 287 |
+
"loss": 0.2882,
|
| 288 |
"step": 330
|
| 289 |
},
|
| 290 |
{
|
| 291 |
+
"epoch": 0.3582718651211802,
|
| 292 |
+
"grad_norm": 0.49547308683395386,
|
| 293 |
+
"learning_rate": 4.4028802247980333e-05,
|
| 294 |
+
"loss": 0.3084,
|
| 295 |
"step": 340
|
| 296 |
},
|
| 297 |
{
|
| 298 |
+
"epoch": 0.36880927291886195,
|
| 299 |
+
"grad_norm": 0.5037292242050171,
|
| 300 |
+
"learning_rate": 4.385317878468563e-05,
|
| 301 |
+
"loss": 0.3084,
|
| 302 |
"step": 350
|
| 303 |
},
|
| 304 |
{
|
| 305 |
+
"epoch": 0.36880927291886195,
|
| 306 |
+
"eval_loss": 0.34608179330825806,
|
| 307 |
+
"eval_runtime": 13.6537,
|
| 308 |
+
"eval_samples_per_second": 35.155,
|
| 309 |
+
"eval_steps_per_second": 2.197,
|
| 310 |
"step": 350
|
| 311 |
},
|
| 312 |
{
|
| 313 |
+
"epoch": 0.3793466807165437,
|
| 314 |
+
"grad_norm": 0.5956543684005737,
|
| 315 |
+
"learning_rate": 4.367755532139094e-05,
|
| 316 |
+
"loss": 0.2763,
|
| 317 |
"step": 360
|
| 318 |
},
|
| 319 |
{
|
| 320 |
+
"epoch": 0.3898840885142255,
|
| 321 |
+
"grad_norm": 0.6263634562492371,
|
| 322 |
+
"learning_rate": 4.3501931858096244e-05,
|
| 323 |
+
"loss": 0.3025,
|
| 324 |
"step": 370
|
| 325 |
},
|
| 326 |
{
|
| 327 |
+
"epoch": 0.40042149631190727,
|
| 328 |
+
"grad_norm": 0.4832920730113983,
|
| 329 |
+
"learning_rate": 4.332630839480154e-05,
|
| 330 |
+
"loss": 0.2792,
|
| 331 |
"step": 380
|
| 332 |
},
|
| 333 |
{
|
| 334 |
+
"epoch": 0.410958904109589,
|
| 335 |
+
"grad_norm": 0.4969714879989624,
|
| 336 |
+
"learning_rate": 4.3150684931506855e-05,
|
| 337 |
+
"loss": 0.2704,
|
| 338 |
"step": 390
|
| 339 |
},
|
| 340 |
{
|
| 341 |
+
"epoch": 0.4214963119072708,
|
| 342 |
+
"grad_norm": 0.568900465965271,
|
| 343 |
+
"learning_rate": 4.297506146821216e-05,
|
| 344 |
+
"loss": 0.2734,
|
| 345 |
"step": 400
|
| 346 |
},
|
| 347 |
{
|
| 348 |
+
"epoch": 0.4214963119072708,
|
| 349 |
+
"eval_loss": 0.34151414036750793,
|
| 350 |
+
"eval_runtime": 13.664,
|
| 351 |
+
"eval_samples_per_second": 35.129,
|
| 352 |
+
"eval_steps_per_second": 2.196,
|
| 353 |
"step": 400
|
| 354 |
},
|
| 355 |
{
|
| 356 |
+
"epoch": 0.4320337197049526,
|
| 357 |
+
"grad_norm": 0.5023282170295715,
|
| 358 |
+
"learning_rate": 4.279943800491746e-05,
|
| 359 |
+
"loss": 0.2845,
|
| 360 |
"step": 410
|
| 361 |
},
|
| 362 |
{
|
| 363 |
+
"epoch": 0.44257112750263433,
|
| 364 |
+
"grad_norm": 0.531538188457489,
|
| 365 |
+
"learning_rate": 4.2623814541622765e-05,
|
| 366 |
+
"loss": 0.276,
|
| 367 |
"step": 420
|
| 368 |
},
|
| 369 |
{
|
| 370 |
+
"epoch": 0.45310853530031614,
|
| 371 |
+
"grad_norm": 0.6686979532241821,
|
| 372 |
+
"learning_rate": 4.2448191078328064e-05,
|
| 373 |
+
"loss": 0.283,
|
| 374 |
"step": 430
|
| 375 |
},
|
| 376 |
{
|
| 377 |
+
"epoch": 0.4636459430979979,
|
| 378 |
+
"grad_norm": 0.5194190144538879,
|
| 379 |
+
"learning_rate": 4.227256761503337e-05,
|
| 380 |
+
"loss": 0.2636,
|
| 381 |
"step": 440
|
| 382 |
},
|
| 383 |
{
|
| 384 |
+
"epoch": 0.47418335089567965,
|
| 385 |
+
"grad_norm": 0.6105541586875916,
|
| 386 |
+
"learning_rate": 4.2096944151738675e-05,
|
| 387 |
+
"loss": 0.2713,
|
| 388 |
"step": 450
|
| 389 |
},
|
| 390 |
{
|
| 391 |
+
"epoch": 0.47418335089567965,
|
| 392 |
+
"eval_loss": 0.33879777789115906,
|
| 393 |
+
"eval_runtime": 13.6666,
|
| 394 |
+
"eval_samples_per_second": 35.122,
|
| 395 |
+
"eval_steps_per_second": 2.195,
|
| 396 |
"step": 450
|
| 397 |
},
|
| 398 |
{
|
| 399 |
+
"epoch": 0.48472075869336145,
|
| 400 |
+
"grad_norm": 0.4929138123989105,
|
| 401 |
+
"learning_rate": 4.1921320688443974e-05,
|
| 402 |
+
"loss": 0.261,
|
| 403 |
"step": 460
|
| 404 |
},
|
| 405 |
{
|
| 406 |
+
"epoch": 0.4952581664910432,
|
| 407 |
+
"grad_norm": 0.584095299243927,
|
| 408 |
+
"learning_rate": 4.174569722514928e-05,
|
| 409 |
+
"loss": 0.2714,
|
| 410 |
"step": 470
|
| 411 |
},
|
| 412 |
{
|
| 413 |
+
"epoch": 0.505795574288725,
|
| 414 |
+
"grad_norm": 0.5386167764663696,
|
| 415 |
+
"learning_rate": 4.1570073761854585e-05,
|
| 416 |
+
"loss": 0.2855,
|
| 417 |
"step": 480
|
| 418 |
},
|
| 419 |
{
|
| 420 |
+
"epoch": 0.5163329820864068,
|
| 421 |
+
"grad_norm": 0.5819774270057678,
|
| 422 |
+
"learning_rate": 4.139445029855989e-05,
|
| 423 |
+
"loss": 0.2911,
|
| 424 |
"step": 490
|
| 425 |
},
|
| 426 |
{
|
| 427 |
+
"epoch": 0.5268703898840885,
|
| 428 |
+
"grad_norm": 0.5875944495201111,
|
| 429 |
+
"learning_rate": 4.12188268352652e-05,
|
| 430 |
+
"loss": 0.2619,
|
| 431 |
"step": 500
|
| 432 |
},
|
| 433 |
{
|
| 434 |
+
"epoch": 0.5268703898840885,
|
| 435 |
+
"eval_loss": 0.3364439010620117,
|
| 436 |
+
"eval_runtime": 13.6731,
|
| 437 |
+
"eval_samples_per_second": 35.105,
|
| 438 |
+
"eval_steps_per_second": 2.194,
|
| 439 |
"step": 500
|
| 440 |
},
|
| 441 |
{
|
| 442 |
+
"epoch": 0.5374077976817703,
|
| 443 |
+
"grad_norm": 0.6705812811851501,
|
| 444 |
+
"learning_rate": 4.1043203371970496e-05,
|
| 445 |
+
"loss": 0.2792,
|
| 446 |
"step": 510
|
| 447 |
},
|
| 448 |
{
|
| 449 |
+
"epoch": 0.547945205479452,
|
| 450 |
+
"grad_norm": 0.5975854396820068,
|
| 451 |
+
"learning_rate": 4.08675799086758e-05,
|
| 452 |
+
"loss": 0.2611,
|
| 453 |
"step": 520
|
| 454 |
},
|
| 455 |
{
|
| 456 |
+
"epoch": 0.5584826132771338,
|
| 457 |
+
"grad_norm": 0.5905255675315857,
|
| 458 |
+
"learning_rate": 4.069195644538111e-05,
|
| 459 |
+
"loss": 0.2688,
|
| 460 |
"step": 530
|
| 461 |
},
|
| 462 |
{
|
| 463 |
+
"epoch": 0.5690200210748156,
|
| 464 |
+
"grad_norm": 0.6222755312919617,
|
| 465 |
+
"learning_rate": 4.0516332982086406e-05,
|
| 466 |
+
"loss": 0.2968,
|
| 467 |
"step": 540
|
| 468 |
},
|
| 469 |
{
|
| 470 |
+
"epoch": 0.5795574288724974,
|
| 471 |
+
"grad_norm": 0.5604814291000366,
|
| 472 |
+
"learning_rate": 4.034070951879171e-05,
|
| 473 |
+
"loss": 0.2623,
|
| 474 |
"step": 550
|
| 475 |
},
|
| 476 |
{
|
| 477 |
+
"epoch": 0.5795574288724974,
|
| 478 |
+
"eval_loss": 0.3329848647117615,
|
| 479 |
+
"eval_runtime": 13.6573,
|
| 480 |
+
"eval_samples_per_second": 35.146,
|
| 481 |
+
"eval_steps_per_second": 2.197,
|
| 482 |
"step": 550
|
| 483 |
},
|
| 484 |
{
|
| 485 |
+
"epoch": 0.5900948366701791,
|
| 486 |
+
"grad_norm": 0.552557647228241,
|
| 487 |
+
"learning_rate": 4.016508605549702e-05,
|
| 488 |
+
"loss": 0.2579,
|
| 489 |
"step": 560
|
| 490 |
},
|
| 491 |
{
|
| 492 |
+
"epoch": 0.6006322444678609,
|
| 493 |
+
"grad_norm": 0.7151882648468018,
|
| 494 |
+
"learning_rate": 3.998946259220232e-05,
|
| 495 |
+
"loss": 0.263,
|
| 496 |
"step": 570
|
| 497 |
},
|
| 498 |
{
|
| 499 |
+
"epoch": 0.6111696522655427,
|
| 500 |
+
"grad_norm": 0.7065399289131165,
|
| 501 |
+
"learning_rate": 3.981383912890763e-05,
|
| 502 |
+
"loss": 0.2626,
|
| 503 |
"step": 580
|
| 504 |
},
|
| 505 |
{
|
| 506 |
+
"epoch": 0.6217070600632244,
|
| 507 |
+
"grad_norm": 0.5590985417366028,
|
| 508 |
+
"learning_rate": 3.963821566561293e-05,
|
| 509 |
+
"loss": 0.2614,
|
| 510 |
"step": 590
|
| 511 |
},
|
| 512 |
{
|
| 513 |
+
"epoch": 0.6322444678609063,
|
| 514 |
+
"grad_norm": 0.6018164157867432,
|
| 515 |
+
"learning_rate": 3.946259220231823e-05,
|
| 516 |
+
"loss": 0.2547,
|
| 517 |
"step": 600
|
| 518 |
},
|
| 519 |
{
|
| 520 |
+
"epoch": 0.6322444678609063,
|
| 521 |
+
"eval_loss": 0.3322373926639557,
|
| 522 |
+
"eval_runtime": 13.6386,
|
| 523 |
+
"eval_samples_per_second": 35.194,
|
| 524 |
+
"eval_steps_per_second": 2.2,
|
| 525 |
"step": 600
|
| 526 |
},
|
| 527 |
{
|
| 528 |
+
"epoch": 0.642781875658588,
|
| 529 |
+
"grad_norm": 0.6659051179885864,
|
| 530 |
+
"learning_rate": 3.928696873902353e-05,
|
| 531 |
+
"loss": 0.2768,
|
| 532 |
"step": 610
|
| 533 |
},
|
| 534 |
{
|
| 535 |
+
"epoch": 0.6533192834562698,
|
| 536 |
+
"grad_norm": 0.6509780883789062,
|
| 537 |
+
"learning_rate": 3.911134527572884e-05,
|
| 538 |
+
"loss": 0.272,
|
| 539 |
"step": 620
|
| 540 |
},
|
| 541 |
{
|
| 542 |
+
"epoch": 0.6638566912539515,
|
| 543 |
+
"grad_norm": 0.5752527713775635,
|
| 544 |
+
"learning_rate": 3.893572181243414e-05,
|
| 545 |
+
"loss": 0.2625,
|
| 546 |
"step": 630
|
| 547 |
},
|
| 548 |
{
|
| 549 |
+
"epoch": 0.6743940990516333,
|
| 550 |
+
"grad_norm": 0.4737485349178314,
|
| 551 |
+
"learning_rate": 3.876009834913945e-05,
|
| 552 |
+
"loss": 0.2668,
|
| 553 |
"step": 640
|
| 554 |
},
|
| 555 |
{
|
| 556 |
+
"epoch": 0.684931506849315,
|
| 557 |
+
"grad_norm": 0.548322319984436,
|
| 558 |
+
"learning_rate": 3.8584474885844754e-05,
|
| 559 |
+
"loss": 0.2597,
|
| 560 |
"step": 650
|
| 561 |
},
|
| 562 |
{
|
| 563 |
+
"epoch": 0.684931506849315,
|
| 564 |
+
"eval_loss": 0.3307412266731262,
|
| 565 |
+
"eval_runtime": 13.6407,
|
| 566 |
+
"eval_samples_per_second": 35.189,
|
| 567 |
+
"eval_steps_per_second": 2.199,
|
| 568 |
"step": 650
|
| 569 |
},
|
| 570 |
{
|
| 571 |
+
"epoch": 0.6954689146469969,
|
| 572 |
+
"grad_norm": 0.5635099411010742,
|
| 573 |
+
"learning_rate": 3.840885142255005e-05,
|
| 574 |
+
"loss": 0.2453,
|
| 575 |
"step": 660
|
| 576 |
},
|
| 577 |
{
|
| 578 |
+
"epoch": 0.7060063224446786,
|
| 579 |
+
"grad_norm": 0.6012313365936279,
|
| 580 |
+
"learning_rate": 3.823322795925536e-05,
|
| 581 |
+
"loss": 0.2695,
|
| 582 |
"step": 670
|
| 583 |
},
|
| 584 |
{
|
| 585 |
+
"epoch": 0.7165437302423604,
|
| 586 |
+
"grad_norm": 0.6025511026382446,
|
| 587 |
+
"learning_rate": 3.8057604495960664e-05,
|
| 588 |
+
"loss": 0.2599,
|
| 589 |
"step": 680
|
| 590 |
},
|
| 591 |
{
|
| 592 |
+
"epoch": 0.7270811380400422,
|
| 593 |
+
"grad_norm": 0.5996225476264954,
|
| 594 |
+
"learning_rate": 3.788198103266596e-05,
|
| 595 |
+
"loss": 0.2624,
|
| 596 |
"step": 690
|
| 597 |
},
|
| 598 |
{
|
| 599 |
+
"epoch": 0.7376185458377239,
|
| 600 |
+
"grad_norm": 0.5269689559936523,
|
| 601 |
+
"learning_rate": 3.770635756937127e-05,
|
| 602 |
+
"loss": 0.2498,
|
| 603 |
"step": 700
|
| 604 |
},
|
| 605 |
{
|
| 606 |
+
"epoch": 0.7376185458377239,
|
| 607 |
+
"eval_loss": 0.3312172591686249,
|
| 608 |
+
"eval_runtime": 13.6169,
|
| 609 |
+
"eval_samples_per_second": 35.25,
|
| 610 |
+
"eval_steps_per_second": 2.203,
|
| 611 |
"step": 700
|
| 612 |
},
|
| 613 |
{
|
| 614 |
+
"epoch": 0.7481559536354057,
|
| 615 |
+
"grad_norm": 0.6115732192993164,
|
| 616 |
+
"learning_rate": 3.7530734106076575e-05,
|
| 617 |
+
"loss": 0.2566,
|
| 618 |
"step": 710
|
| 619 |
},
|
| 620 |
{
|
| 621 |
+
"epoch": 0.7586933614330874,
|
| 622 |
+
"grad_norm": 0.4686366319656372,
|
| 623 |
+
"learning_rate": 3.7355110642781874e-05,
|
| 624 |
+
"loss": 0.2325,
|
| 625 |
"step": 720
|
| 626 |
},
|
| 627 |
{
|
| 628 |
+
"epoch": 0.7692307692307693,
|
| 629 |
+
"grad_norm": 0.5317673087120056,
|
| 630 |
+
"learning_rate": 3.717948717948718e-05,
|
| 631 |
+
"loss": 0.2429,
|
| 632 |
"step": 730
|
| 633 |
},
|
| 634 |
{
|
| 635 |
+
"epoch": 0.779768177028451,
|
| 636 |
+
"grad_norm": 0.5183236598968506,
|
| 637 |
+
"learning_rate": 3.7003863716192485e-05,
|
| 638 |
+
"loss": 0.2562,
|
| 639 |
"step": 740
|
| 640 |
},
|
| 641 |
{
|
| 642 |
+
"epoch": 0.7903055848261328,
|
| 643 |
+
"grad_norm": 0.5319241881370544,
|
| 644 |
+
"learning_rate": 3.682824025289779e-05,
|
| 645 |
+
"loss": 0.2356,
|
| 646 |
"step": 750
|
| 647 |
},
|
| 648 |
{
|
| 649 |
+
"epoch": 0.7903055848261328,
|
| 650 |
+
"eval_loss": 0.3285733163356781,
|
| 651 |
+
"eval_runtime": 13.6213,
|
| 652 |
+
"eval_samples_per_second": 35.239,
|
| 653 |
+
"eval_steps_per_second": 2.202,
|
| 654 |
"step": 750
|
| 655 |
},
|
| 656 |
{
|
| 657 |
+
"epoch": 0.8008429926238145,
|
| 658 |
+
"grad_norm": 0.5814469456672668,
|
| 659 |
+
"learning_rate": 3.6652616789603096e-05,
|
| 660 |
+
"loss": 0.2428,
|
| 661 |
"step": 760
|
| 662 |
},
|
| 663 |
{
|
| 664 |
+
"epoch": 0.8113804004214963,
|
| 665 |
+
"grad_norm": 0.5138055086135864,
|
| 666 |
+
"learning_rate": 3.6476993326308395e-05,
|
| 667 |
+
"loss": 0.2639,
|
| 668 |
"step": 770
|
| 669 |
},
|
| 670 |
{
|
| 671 |
+
"epoch": 0.821917808219178,
|
| 672 |
+
"grad_norm": 0.5066888332366943,
|
| 673 |
+
"learning_rate": 3.63013698630137e-05,
|
| 674 |
+
"loss": 0.2373,
|
| 675 |
"step": 780
|
| 676 |
},
|
| 677 |
{
|
| 678 |
+
"epoch": 0.8324552160168599,
|
| 679 |
+
"grad_norm": 0.513317883014679,
|
| 680 |
+
"learning_rate": 3.6125746399719e-05,
|
| 681 |
+
"loss": 0.2462,
|
| 682 |
"step": 790
|
| 683 |
},
|
| 684 |
{
|
| 685 |
+
"epoch": 0.8429926238145417,
|
| 686 |
+
"grad_norm": 0.5878031253814697,
|
| 687 |
+
"learning_rate": 3.5950122936424305e-05,
|
| 688 |
+
"loss": 0.2397,
|
| 689 |
"step": 800
|
| 690 |
},
|
| 691 |
{
|
| 692 |
+
"epoch": 0.8429926238145417,
|
| 693 |
+
"eval_loss": 0.3288480043411255,
|
| 694 |
+
"eval_runtime": 13.6316,
|
| 695 |
+
"eval_samples_per_second": 35.212,
|
| 696 |
+
"eval_steps_per_second": 2.201,
|
| 697 |
"step": 800
|
| 698 |
},
|
| 699 |
{
|
| 700 |
+
"epoch": 0.8535300316122234,
|
| 701 |
+
"grad_norm": 0.6269211769104004,
|
| 702 |
+
"learning_rate": 3.577449947312961e-05,
|
| 703 |
+
"loss": 0.2418,
|
| 704 |
"step": 810
|
| 705 |
},
|
| 706 |
{
|
| 707 |
+
"epoch": 0.8640674394099052,
|
| 708 |
+
"grad_norm": 0.5279048085212708,
|
| 709 |
+
"learning_rate": 3.5598876009834916e-05,
|
| 710 |
+
"loss": 0.246,
|
| 711 |
"step": 820
|
| 712 |
},
|
| 713 |
{
|
| 714 |
+
"epoch": 0.8746048472075869,
|
| 715 |
+
"grad_norm": 0.5837969183921814,
|
| 716 |
+
"learning_rate": 3.542325254654022e-05,
|
| 717 |
+
"loss": 0.256,
|
| 718 |
"step": 830
|
| 719 |
},
|
| 720 |
{
|
| 721 |
+
"epoch": 0.8851422550052687,
|
| 722 |
+
"grad_norm": 0.5384166240692139,
|
| 723 |
+
"learning_rate": 3.524762908324553e-05,
|
| 724 |
+
"loss": 0.2412,
|
| 725 |
"step": 840
|
| 726 |
},
|
| 727 |
{
|
| 728 |
+
"epoch": 0.8956796628029505,
|
| 729 |
+
"grad_norm": 0.5514136552810669,
|
| 730 |
+
"learning_rate": 3.507200561995083e-05,
|
| 731 |
+
"loss": 0.251,
|
| 732 |
"step": 850
|
| 733 |
},
|
| 734 |
{
|
| 735 |
+
"epoch": 0.8956796628029505,
|
| 736 |
+
"eval_loss": 0.3275190591812134,
|
| 737 |
+
"eval_runtime": 13.654,
|
| 738 |
+
"eval_samples_per_second": 35.155,
|
| 739 |
+
"eval_steps_per_second": 2.197,
|
| 740 |
"step": 850
|
| 741 |
},
|
| 742 |
{
|
| 743 |
+
"epoch": 0.9062170706006323,
|
| 744 |
+
"grad_norm": 0.5456790328025818,
|
| 745 |
+
"learning_rate": 3.489638215665613e-05,
|
| 746 |
+
"loss": 0.2337,
|
| 747 |
"step": 860
|
| 748 |
},
|
| 749 |
{
|
| 750 |
+
"epoch": 0.916754478398314,
|
| 751 |
+
"grad_norm": 0.5794851779937744,
|
| 752 |
+
"learning_rate": 3.472075869336143e-05,
|
| 753 |
+
"loss": 0.2462,
|
| 754 |
"step": 870
|
| 755 |
},
|
| 756 |
{
|
| 757 |
+
"epoch": 0.9272918861959958,
|
| 758 |
+
"grad_norm": 0.5296761393547058,
|
| 759 |
+
"learning_rate": 3.454513523006674e-05,
|
| 760 |
+
"loss": 0.2357,
|
| 761 |
"step": 880
|
| 762 |
},
|
| 763 |
{
|
| 764 |
+
"epoch": 0.9378292939936775,
|
| 765 |
+
"grad_norm": 0.5668390989303589,
|
| 766 |
+
"learning_rate": 3.436951176677204e-05,
|
| 767 |
+
"loss": 0.2439,
|
| 768 |
"step": 890
|
| 769 |
},
|
| 770 |
{
|
| 771 |
+
"epoch": 0.9483667017913593,
|
| 772 |
+
"grad_norm": 0.5026710629463196,
|
| 773 |
+
"learning_rate": 3.419388830347735e-05,
|
| 774 |
+
"loss": 0.2301,
|
| 775 |
"step": 900
|
| 776 |
},
|
| 777 |
{
|
| 778 |
+
"epoch": 0.9483667017913593,
|
| 779 |
+
"eval_loss": 0.32623717188835144,
|
| 780 |
+
"eval_runtime": 13.6644,
|
| 781 |
+
"eval_samples_per_second": 35.128,
|
| 782 |
+
"eval_steps_per_second": 2.195,
|
| 783 |
"step": 900
|
| 784 |
},
|
| 785 |
{
|
| 786 |
+
"epoch": 0.958904109589041,
|
| 787 |
+
"grad_norm": 0.5280706286430359,
|
| 788 |
+
"learning_rate": 3.4018264840182654e-05,
|
| 789 |
+
"loss": 0.238,
|
| 790 |
"step": 910
|
| 791 |
},
|
| 792 |
{
|
| 793 |
+
"epoch": 0.9694415173867229,
|
| 794 |
+
"grad_norm": 0.5578323006629944,
|
| 795 |
+
"learning_rate": 3.384264137688795e-05,
|
| 796 |
+
"loss": 0.2484,
|
| 797 |
"step": 920
|
| 798 |
},
|
| 799 |
{
|
| 800 |
+
"epoch": 0.9799789251844047,
|
| 801 |
+
"grad_norm": 0.5756859183311462,
|
| 802 |
+
"learning_rate": 3.366701791359326e-05,
|
| 803 |
+
"loss": 0.2539,
|
| 804 |
"step": 930
|
| 805 |
},
|
| 806 |
{
|
| 807 |
+
"epoch": 0.9905163329820864,
|
| 808 |
+
"grad_norm": 0.6118686199188232,
|
| 809 |
+
"learning_rate": 3.3491394450298564e-05,
|
| 810 |
+
"loss": 0.2401,
|
| 811 |
"step": 940
|
| 812 |
},
|
| 813 |
{
|
| 814 |
+
"epoch": 1.0010537407797682,
|
| 815 |
+
"grad_norm": 0.43512389063835144,
|
| 816 |
+
"learning_rate": 3.331577098700386e-05,
|
| 817 |
+
"loss": 0.2334,
|
| 818 |
"step": 950
|
| 819 |
},
|
| 820 |
{
|
| 821 |
+
"epoch": 1.0010537407797682,
|
| 822 |
+
"eval_loss": 0.32700982689857483,
|
| 823 |
+
"eval_runtime": 13.6561,
|
| 824 |
+
"eval_samples_per_second": 35.149,
|
| 825 |
+
"eval_steps_per_second": 2.197,
|
| 826 |
"step": 950
|
| 827 |
},
|
| 828 |
{
|
| 829 |
+
"epoch": 1.01159114857745,
|
| 830 |
+
"grad_norm": 0.5436535477638245,
|
| 831 |
+
"learning_rate": 3.314014752370917e-05,
|
| 832 |
+
"loss": 0.1933,
|
| 833 |
"step": 960
|
| 834 |
},
|
| 835 |
{
|
| 836 |
+
"epoch": 1.0221285563751317,
|
| 837 |
+
"grad_norm": 0.5048521161079407,
|
| 838 |
+
"learning_rate": 3.2964524060414474e-05,
|
| 839 |
+
"loss": 0.2088,
|
| 840 |
"step": 970
|
| 841 |
},
|
| 842 |
{
|
| 843 |
+
"epoch": 1.0326659641728135,
|
| 844 |
+
"grad_norm": 0.6231564283370972,
|
| 845 |
+
"learning_rate": 3.278890059711977e-05,
|
| 846 |
+
"loss": 0.2146,
|
| 847 |
"step": 980
|
| 848 |
},
|
| 849 |
{
|
| 850 |
+
"epoch": 1.0432033719704952,
|
| 851 |
+
"grad_norm": 0.6846581101417542,
|
| 852 |
+
"learning_rate": 3.261327713382508e-05,
|
| 853 |
+
"loss": 0.2149,
|
| 854 |
"step": 990
|
| 855 |
},
|
| 856 |
{
|
| 857 |
+
"epoch": 1.053740779768177,
|
| 858 |
+
"grad_norm": 0.5640810132026672,
|
| 859 |
+
"learning_rate": 3.2437653670530384e-05,
|
| 860 |
+
"loss": 0.2078,
|
| 861 |
"step": 1000
|
| 862 |
},
|
| 863 |
{
|
| 864 |
+
"epoch": 1.053740779768177,
|
| 865 |
+
"eval_loss": 0.3363134264945984,
|
| 866 |
+
"eval_runtime": 13.6484,
|
| 867 |
+
"eval_samples_per_second": 35.169,
|
| 868 |
+
"eval_steps_per_second": 2.198,
|
| 869 |
"step": 1000
|
| 870 |
},
|
| 871 |
{
|
| 872 |
+
"epoch": 1.064278187565859,
|
| 873 |
+
"grad_norm": 0.6279656887054443,
|
| 874 |
+
"learning_rate": 3.226203020723569e-05,
|
| 875 |
+
"loss": 0.2004,
|
| 876 |
"step": 1010
|
| 877 |
},
|
| 878 |
{
|
| 879 |
+
"epoch": 1.0748155953635405,
|
| 880 |
+
"grad_norm": 0.5957475304603577,
|
| 881 |
+
"learning_rate": 3.2086406743940996e-05,
|
| 882 |
+
"loss": 0.1952,
|
| 883 |
"step": 1020
|
| 884 |
},
|
| 885 |
{
|
| 886 |
+
"epoch": 1.0853530031612224,
|
| 887 |
+
"grad_norm": 0.6246820092201233,
|
| 888 |
+
"learning_rate": 3.1910783280646294e-05,
|
| 889 |
+
"loss": 0.2071,
|
| 890 |
"step": 1030
|
| 891 |
},
|
| 892 |
{
|
| 893 |
+
"epoch": 1.095890410958904,
|
| 894 |
+
"grad_norm": 0.5296807885169983,
|
| 895 |
+
"learning_rate": 3.17351598173516e-05,
|
| 896 |
+
"loss": 0.2077,
|
| 897 |
"step": 1040
|
| 898 |
},
|
| 899 |
{
|
| 900 |
+
"epoch": 1.106427818756586,
|
| 901 |
+
"grad_norm": 0.6367089152336121,
|
| 902 |
+
"learning_rate": 3.15595363540569e-05,
|
| 903 |
+
"loss": 0.2087,
|
| 904 |
"step": 1050
|
| 905 |
},
|
| 906 |
{
|
| 907 |
+
"epoch": 1.106427818756586,
|
| 908 |
+
"eval_loss": 0.3410273492336273,
|
| 909 |
+
"eval_runtime": 13.6191,
|
| 910 |
+
"eval_samples_per_second": 35.245,
|
| 911 |
+
"eval_steps_per_second": 2.203,
|
| 912 |
"step": 1050
|
| 913 |
},
|
| 914 |
{
|
| 915 |
+
"epoch": 1.1169652265542676,
|
| 916 |
+
"grad_norm": 0.5743587017059326,
|
| 917 |
+
"learning_rate": 3.1383912890762205e-05,
|
| 918 |
+
"loss": 0.2063,
|
| 919 |
"step": 1060
|
| 920 |
},
|
| 921 |
{
|
| 922 |
+
"epoch": 1.1275026343519494,
|
| 923 |
+
"grad_norm": 0.5830729603767395,
|
| 924 |
+
"learning_rate": 3.120828942746751e-05,
|
| 925 |
+
"loss": 0.2021,
|
| 926 |
"step": 1070
|
| 927 |
},
|
| 928 |
{
|
| 929 |
+
"epoch": 1.1380400421496313,
|
| 930 |
+
"grad_norm": 0.585697591304779,
|
| 931 |
+
"learning_rate": 3.1032665964172816e-05,
|
| 932 |
+
"loss": 0.2003,
|
| 933 |
"step": 1080
|
| 934 |
},
|
| 935 |
{
|
| 936 |
+
"epoch": 1.148577449947313,
|
| 937 |
+
"grad_norm": 0.6112616062164307,
|
| 938 |
+
"learning_rate": 3.085704250087812e-05,
|
| 939 |
+
"loss": 0.2035,
|
| 940 |
"step": 1090
|
| 941 |
},
|
| 942 |
{
|
| 943 |
+
"epoch": 1.1591148577449948,
|
| 944 |
+
"grad_norm": 0.6068351864814758,
|
| 945 |
+
"learning_rate": 3.068141903758342e-05,
|
| 946 |
+
"loss": 0.198,
|
| 947 |
"step": 1100
|
| 948 |
},
|
| 949 |
{
|
| 950 |
+
"epoch": 1.1591148577449948,
|
| 951 |
+
"eval_loss": 0.33999618887901306,
|
| 952 |
+
"eval_runtime": 13.5917,
|
| 953 |
+
"eval_samples_per_second": 35.316,
|
| 954 |
+
"eval_steps_per_second": 2.207,
|
| 955 |
"step": 1100
|
| 956 |
},
|
| 957 |
{
|
| 958 |
+
"epoch": 1.1696522655426764,
|
| 959 |
+
"grad_norm": 0.6323215961456299,
|
| 960 |
+
"learning_rate": 3.0505795574288726e-05,
|
| 961 |
+
"loss": 0.204,
|
| 962 |
"step": 1110
|
| 963 |
},
|
| 964 |
{
|
| 965 |
+
"epoch": 1.1801896733403583,
|
| 966 |
+
"grad_norm": 0.6767095923423767,
|
| 967 |
+
"learning_rate": 3.0330172110994032e-05,
|
| 968 |
+
"loss": 0.2,
|
| 969 |
"step": 1120
|
| 970 |
},
|
| 971 |
{
|
| 972 |
+
"epoch": 1.1907270811380402,
|
| 973 |
+
"grad_norm": 0.6808314919471741,
|
| 974 |
+
"learning_rate": 3.015454864769933e-05,
|
| 975 |
+
"loss": 0.2052,
|
| 976 |
"step": 1130
|
| 977 |
},
|
| 978 |
{
|
| 979 |
+
"epoch": 1.2012644889357218,
|
| 980 |
+
"grad_norm": 0.7271966934204102,
|
| 981 |
+
"learning_rate": 2.997892518440464e-05,
|
| 982 |
+
"loss": 0.2035,
|
| 983 |
"step": 1140
|
| 984 |
},
|
| 985 |
{
|
| 986 |
+
"epoch": 1.2118018967334037,
|
| 987 |
+
"grad_norm": 0.5914655327796936,
|
| 988 |
+
"learning_rate": 2.9803301721109945e-05,
|
| 989 |
+
"loss": 0.1999,
|
| 990 |
"step": 1150
|
| 991 |
},
|
| 992 |
{
|
| 993 |
+
"epoch": 1.2118018967334037,
|
| 994 |
+
"eval_loss": 0.3386387825012207,
|
| 995 |
+
"eval_runtime": 13.6001,
|
| 996 |
+
"eval_samples_per_second": 35.294,
|
| 997 |
+
"eval_steps_per_second": 2.206,
|
| 998 |
"step": 1150
|
| 999 |
},
|
| 1000 |
{
|
| 1001 |
+
"epoch": 1.2223393045310853,
|
| 1002 |
+
"grad_norm": 0.6497891545295715,
|
| 1003 |
+
"learning_rate": 2.9627678257815244e-05,
|
| 1004 |
+
"loss": 0.2059,
|
| 1005 |
"step": 1160
|
| 1006 |
},
|
| 1007 |
{
|
| 1008 |
+
"epoch": 1.2328767123287672,
|
| 1009 |
+
"grad_norm": 0.6975721120834351,
|
| 1010 |
+
"learning_rate": 2.945205479452055e-05,
|
| 1011 |
+
"loss": 0.1968,
|
| 1012 |
"step": 1170
|
| 1013 |
},
|
| 1014 |
{
|
| 1015 |
+
"epoch": 1.2434141201264488,
|
| 1016 |
+
"grad_norm": 0.6115730404853821,
|
| 1017 |
+
"learning_rate": 2.9276431331225852e-05,
|
| 1018 |
"loss": 0.1983,
|
| 1019 |
"step": 1180
|
| 1020 |
},
|
| 1021 |
{
|
| 1022 |
+
"epoch": 1.2539515279241307,
|
| 1023 |
+
"grad_norm": 0.6213293075561523,
|
| 1024 |
+
"learning_rate": 2.9100807867931158e-05,
|
| 1025 |
+
"loss": 0.2077,
|
| 1026 |
"step": 1190
|
| 1027 |
},
|
| 1028 |
{
|
| 1029 |
+
"epoch": 1.2644889357218125,
|
| 1030 |
+
"grad_norm": 0.6509750485420227,
|
| 1031 |
+
"learning_rate": 2.8925184404636463e-05,
|
| 1032 |
+
"loss": 0.194,
|
| 1033 |
"step": 1200
|
| 1034 |
},
|
| 1035 |
{
|
| 1036 |
+
"epoch": 1.2644889357218125,
|
| 1037 |
+
"eval_loss": 0.34055641293525696,
|
| 1038 |
+
"eval_runtime": 13.997,
|
| 1039 |
+
"eval_samples_per_second": 34.293,
|
| 1040 |
+
"eval_steps_per_second": 2.143,
|
| 1041 |
"step": 1200
|
| 1042 |
},
|
| 1043 |
{
|
| 1044 |
+
"epoch": 1.2750263435194942,
|
| 1045 |
+
"grad_norm": 0.4847603142261505,
|
| 1046 |
+
"learning_rate": 2.8749560941341762e-05,
|
| 1047 |
+
"loss": 0.1976,
|
| 1048 |
"step": 1210
|
| 1049 |
},
|
| 1050 |
{
|
| 1051 |
+
"epoch": 1.285563751317176,
|
| 1052 |
+
"grad_norm": 0.6689492464065552,
|
| 1053 |
+
"learning_rate": 2.8573937478047068e-05,
|
| 1054 |
+
"loss": 0.19,
|
| 1055 |
"step": 1220
|
| 1056 |
},
|
| 1057 |
{
|
| 1058 |
+
"epoch": 1.2961011591148577,
|
| 1059 |
+
"grad_norm": 0.6299355626106262,
|
| 1060 |
+
"learning_rate": 2.839831401475237e-05,
|
| 1061 |
+
"loss": 0.2025,
|
| 1062 |
"step": 1230
|
| 1063 |
},
|
| 1064 |
{
|
| 1065 |
+
"epoch": 1.3066385669125395,
|
| 1066 |
+
"grad_norm": 0.5940089821815491,
|
| 1067 |
+
"learning_rate": 2.8222690551457676e-05,
|
| 1068 |
+
"loss": 0.1917,
|
| 1069 |
"step": 1240
|
| 1070 |
},
|
| 1071 |
{
|
| 1072 |
+
"epoch": 1.3171759747102212,
|
| 1073 |
+
"grad_norm": 0.8054115772247314,
|
| 1074 |
+
"learning_rate": 2.804706708816298e-05,
|
| 1075 |
+
"loss": 0.1928,
|
| 1076 |
"step": 1250
|
| 1077 |
},
|
| 1078 |
{
|
| 1079 |
+
"epoch": 1.3171759747102212,
|
| 1080 |
+
"eval_loss": 0.34280383586883545,
|
| 1081 |
+
"eval_runtime": 13.6317,
|
| 1082 |
+
"eval_samples_per_second": 35.212,
|
| 1083 |
+
"eval_steps_per_second": 2.201,
|
| 1084 |
"step": 1250
|
| 1085 |
},
|
| 1086 |
{
|
| 1087 |
+
"epoch": 1.327713382507903,
|
| 1088 |
+
"grad_norm": 0.5501131415367126,
|
| 1089 |
+
"learning_rate": 2.7871443624868284e-05,
|
| 1090 |
+
"loss": 0.1933,
|
| 1091 |
"step": 1260
|
| 1092 |
},
|
| 1093 |
{
|
| 1094 |
+
"epoch": 1.338250790305585,
|
| 1095 |
+
"grad_norm": 0.6450643539428711,
|
| 1096 |
+
"learning_rate": 2.769582016157359e-05,
|
| 1097 |
+
"loss": 0.1994,
|
| 1098 |
"step": 1270
|
| 1099 |
},
|
| 1100 |
{
|
| 1101 |
+
"epoch": 1.3487881981032666,
|
| 1102 |
+
"grad_norm": 0.6347033381462097,
|
| 1103 |
+
"learning_rate": 2.7520196698278895e-05,
|
| 1104 |
+
"loss": 0.2004,
|
| 1105 |
"step": 1280
|
| 1106 |
},
|
| 1107 |
{
|
| 1108 |
+
"epoch": 1.3593256059009484,
|
| 1109 |
+
"grad_norm": 0.6968681216239929,
|
| 1110 |
+
"learning_rate": 2.7344573234984194e-05,
|
| 1111 |
+
"loss": 0.214,
|
| 1112 |
"step": 1290
|
| 1113 |
},
|
| 1114 |
{
|
| 1115 |
+
"epoch": 1.36986301369863,
|
| 1116 |
+
"grad_norm": 0.5916845202445984,
|
| 1117 |
+
"learning_rate": 2.71689497716895e-05,
|
| 1118 |
+
"loss": 0.1849,
|
| 1119 |
"step": 1300
|
| 1120 |
},
|
| 1121 |
{
|
| 1122 |
+
"epoch": 1.36986301369863,
|
| 1123 |
+
"eval_loss": 0.34068360924720764,
|
| 1124 |
+
"eval_runtime": 13.6631,
|
| 1125 |
+
"eval_samples_per_second": 35.131,
|
| 1126 |
+
"eval_steps_per_second": 2.196,
|
| 1127 |
"step": 1300
|
| 1128 |
},
|
| 1129 |
{
|
| 1130 |
+
"epoch": 1.380400421496312,
|
| 1131 |
+
"grad_norm": 0.7653020024299622,
|
| 1132 |
+
"learning_rate": 2.6993326308394802e-05,
|
| 1133 |
+
"loss": 0.1917,
|
| 1134 |
"step": 1310
|
| 1135 |
},
|
| 1136 |
{
|
| 1137 |
+
"epoch": 1.3909378292939936,
|
| 1138 |
+
"grad_norm": 0.6557948589324951,
|
| 1139 |
+
"learning_rate": 2.6817702845100107e-05,
|
| 1140 |
+
"loss": 0.2008,
|
| 1141 |
"step": 1320
|
| 1142 |
},
|
| 1143 |
{
|
| 1144 |
+
"epoch": 1.4014752370916754,
|
| 1145 |
+
"grad_norm": 0.57426518201828,
|
| 1146 |
+
"learning_rate": 2.6642079381805413e-05,
|
| 1147 |
+
"loss": 0.1889,
|
| 1148 |
"step": 1330
|
| 1149 |
},
|
| 1150 |
{
|
| 1151 |
+
"epoch": 1.4120126448893573,
|
| 1152 |
+
"grad_norm": 0.6126993298530579,
|
| 1153 |
+
"learning_rate": 2.6466455918510712e-05,
|
| 1154 |
+
"loss": 0.1995,
|
| 1155 |
"step": 1340
|
| 1156 |
},
|
| 1157 |
{
|
| 1158 |
+
"epoch": 1.422550052687039,
|
| 1159 |
+
"grad_norm": 0.6700727343559265,
|
| 1160 |
+
"learning_rate": 2.6290832455216018e-05,
|
| 1161 |
+
"loss": 0.1898,
|
| 1162 |
"step": 1350
|
| 1163 |
},
|
| 1164 |
{
|
| 1165 |
+
"epoch": 1.422550052687039,
|
| 1166 |
+
"eval_loss": 0.3482060432434082,
|
| 1167 |
+
"eval_runtime": 13.6643,
|
| 1168 |
+
"eval_samples_per_second": 35.128,
|
| 1169 |
+
"eval_steps_per_second": 2.195,
|
| 1170 |
"step": 1350
|
| 1171 |
},
|
| 1172 |
{
|
| 1173 |
+
"epoch": 1.4330874604847208,
|
| 1174 |
+
"grad_norm": 0.6523577570915222,
|
| 1175 |
+
"learning_rate": 2.611520899192132e-05,
|
| 1176 |
+
"loss": 0.1977,
|
| 1177 |
"step": 1360
|
| 1178 |
},
|
| 1179 |
{
|
| 1180 |
+
"epoch": 1.4436248682824027,
|
| 1181 |
+
"grad_norm": 0.6040759682655334,
|
| 1182 |
+
"learning_rate": 2.5939585528626625e-05,
|
| 1183 |
+
"loss": 0.1833,
|
| 1184 |
"step": 1370
|
| 1185 |
},
|
| 1186 |
{
|
| 1187 |
+
"epoch": 1.4541622760800843,
|
| 1188 |
+
"grad_norm": 0.6998751163482666,
|
| 1189 |
+
"learning_rate": 2.576396206533193e-05,
|
| 1190 |
+
"loss": 0.1917,
|
| 1191 |
"step": 1380
|
| 1192 |
},
|
| 1193 |
{
|
| 1194 |
+
"epoch": 1.464699683877766,
|
| 1195 |
+
"grad_norm": 0.7758492231369019,
|
| 1196 |
+
"learning_rate": 2.5588338602037233e-05,
|
| 1197 |
+
"loss": 0.192,
|
| 1198 |
"step": 1390
|
| 1199 |
},
|
| 1200 |
{
|
| 1201 |
+
"epoch": 1.4752370916754478,
|
| 1202 |
+
"grad_norm": 0.708914577960968,
|
| 1203 |
+
"learning_rate": 2.541271513874254e-05,
|
| 1204 |
+
"loss": 0.1853,
|
| 1205 |
"step": 1400
|
| 1206 |
},
|
| 1207 |
{
|
| 1208 |
+
"epoch": 1.4752370916754478,
|
| 1209 |
+
"eval_loss": 0.3444618582725525,
|
| 1210 |
+
"eval_runtime": 13.653,
|
| 1211 |
+
"eval_samples_per_second": 35.157,
|
| 1212 |
+
"eval_steps_per_second": 2.197,
|
| 1213 |
"step": 1400
|
| 1214 |
},
|
| 1215 |
{
|
| 1216 |
+
"epoch": 1.4857744994731297,
|
| 1217 |
+
"grad_norm": 0.6209197640419006,
|
| 1218 |
+
"learning_rate": 2.5237091675447845e-05,
|
| 1219 |
+
"loss": 0.1826,
|
| 1220 |
"step": 1410
|
| 1221 |
},
|
| 1222 |
{
|
| 1223 |
+
"epoch": 1.4963119072708113,
|
| 1224 |
+
"grad_norm": 0.714142918586731,
|
| 1225 |
+
"learning_rate": 2.5061468212153144e-05,
|
| 1226 |
+
"loss": 0.1921,
|
| 1227 |
"step": 1420
|
| 1228 |
},
|
| 1229 |
{
|
| 1230 |
+
"epoch": 1.5068493150684932,
|
| 1231 |
+
"grad_norm": 0.6723175644874573,
|
| 1232 |
+
"learning_rate": 2.4885844748858446e-05,
|
| 1233 |
+
"loss": 0.2006,
|
| 1234 |
"step": 1430
|
| 1235 |
},
|
| 1236 |
{
|
| 1237 |
+
"epoch": 1.517386722866175,
|
| 1238 |
+
"grad_norm": 0.8485958576202393,
|
| 1239 |
+
"learning_rate": 2.4710221285563755e-05,
|
| 1240 |
+
"loss": 0.2032,
|
| 1241 |
"step": 1440
|
| 1242 |
},
|
| 1243 |
{
|
| 1244 |
+
"epoch": 1.5279241306638567,
|
| 1245 |
+
"grad_norm": 0.6563605666160583,
|
| 1246 |
+
"learning_rate": 2.4534597822269057e-05,
|
| 1247 |
+
"loss": 0.1951,
|
| 1248 |
"step": 1450
|
| 1249 |
},
|
| 1250 |
{
|
| 1251 |
+
"epoch": 1.5279241306638567,
|
| 1252 |
+
"eval_loss": 0.34677523374557495,
|
| 1253 |
+
"eval_runtime": 13.6421,
|
| 1254 |
+
"eval_samples_per_second": 35.185,
|
| 1255 |
+
"eval_steps_per_second": 2.199,
|
| 1256 |
"step": 1450
|
| 1257 |
},
|
| 1258 |
{
|
| 1259 |
+
"epoch": 1.5384615384615383,
|
| 1260 |
+
"grad_norm": 0.6512174010276794,
|
| 1261 |
+
"learning_rate": 2.435897435897436e-05,
|
| 1262 |
+
"loss": 0.1946,
|
| 1263 |
"step": 1460
|
| 1264 |
},
|
| 1265 |
{
|
| 1266 |
+
"epoch": 1.5489989462592202,
|
| 1267 |
+
"grad_norm": 0.8586357831954956,
|
| 1268 |
+
"learning_rate": 2.418335089567966e-05,
|
| 1269 |
+
"loss": 0.1818,
|
| 1270 |
"step": 1470
|
| 1271 |
},
|
| 1272 |
{
|
| 1273 |
+
"epoch": 1.559536354056902,
|
| 1274 |
+
"grad_norm": 0.6348748803138733,
|
| 1275 |
+
"learning_rate": 2.4007727432384967e-05,
|
| 1276 |
+
"loss": 0.19,
|
| 1277 |
"step": 1480
|
| 1278 |
},
|
| 1279 |
{
|
| 1280 |
+
"epoch": 1.5700737618545837,
|
| 1281 |
+
"grad_norm": 0.6497516632080078,
|
| 1282 |
+
"learning_rate": 2.3832103969090273e-05,
|
| 1283 |
+
"loss": 0.1901,
|
| 1284 |
"step": 1490
|
| 1285 |
},
|
| 1286 |
{
|
| 1287 |
+
"epoch": 1.5806111696522656,
|
| 1288 |
+
"grad_norm": 0.5382278561592102,
|
| 1289 |
+
"learning_rate": 2.3656480505795575e-05,
|
| 1290 |
+
"loss": 0.1877,
|
| 1291 |
"step": 1500
|
| 1292 |
},
|
| 1293 |
{
|
| 1294 |
+
"epoch": 1.5806111696522656,
|
| 1295 |
+
"eval_loss": 0.35011863708496094,
|
| 1296 |
+
"eval_runtime": 13.6377,
|
| 1297 |
+
"eval_samples_per_second": 35.196,
|
| 1298 |
+
"eval_steps_per_second": 2.2,
|
| 1299 |
"step": 1500
|
| 1300 |
},
|
| 1301 |
{
|
| 1302 |
+
"epoch": 1.5911485774499474,
|
| 1303 |
+
"grad_norm": 0.5429180860519409,
|
| 1304 |
+
"learning_rate": 2.3480857042500877e-05,
|
| 1305 |
+
"loss": 0.1961,
|
| 1306 |
"step": 1510
|
| 1307 |
},
|
| 1308 |
{
|
| 1309 |
+
"epoch": 1.601685985247629,
|
| 1310 |
+
"grad_norm": 0.6648889183998108,
|
| 1311 |
+
"learning_rate": 2.3305233579206183e-05,
|
| 1312 |
+
"loss": 0.1934,
|
| 1313 |
"step": 1520
|
| 1314 |
},
|
| 1315 |
{
|
| 1316 |
+
"epoch": 1.6122233930453107,
|
| 1317 |
+
"grad_norm": 0.6552326679229736,
|
| 1318 |
+
"learning_rate": 2.312961011591149e-05,
|
| 1319 |
+
"loss": 0.1928,
|
| 1320 |
"step": 1530
|
| 1321 |
},
|
| 1322 |
{
|
| 1323 |
+
"epoch": 1.6227608008429928,
|
| 1324 |
+
"grad_norm": 0.6863034963607788,
|
| 1325 |
+
"learning_rate": 2.295398665261679e-05,
|
| 1326 |
+
"loss": 0.1956,
|
| 1327 |
"step": 1540
|
| 1328 |
},
|
| 1329 |
{
|
| 1330 |
+
"epoch": 1.6332982086406744,
|
| 1331 |
+
"grad_norm": 0.8960068225860596,
|
| 1332 |
+
"learning_rate": 2.2778363189322093e-05,
|
| 1333 |
+
"loss": 0.203,
|
| 1334 |
"step": 1550
|
| 1335 |
},
|
| 1336 |
{
|
| 1337 |
+
"epoch": 1.6332982086406744,
|
| 1338 |
+
"eval_loss": 0.3496212661266327,
|
| 1339 |
+
"eval_runtime": 13.629,
|
| 1340 |
+
"eval_samples_per_second": 35.219,
|
| 1341 |
+
"eval_steps_per_second": 2.201,
|
| 1342 |
"step": 1550
|
| 1343 |
},
|
| 1344 |
{
|
| 1345 |
+
"epoch": 1.643835616438356,
|
| 1346 |
+
"grad_norm": 0.7601160407066345,
|
| 1347 |
+
"learning_rate": 2.2602739726027396e-05,
|
| 1348 |
+
"loss": 0.1934,
|
| 1349 |
"step": 1560
|
| 1350 |
},
|
| 1351 |
{
|
| 1352 |
+
"epoch": 1.654373024236038,
|
| 1353 |
+
"grad_norm": 0.9118824601173401,
|
| 1354 |
+
"learning_rate": 2.2427116262732705e-05,
|
| 1355 |
+
"loss": 0.1861,
|
| 1356 |
"step": 1570
|
| 1357 |
},
|
| 1358 |
{
|
| 1359 |
+
"epoch": 1.6649104320337198,
|
| 1360 |
+
"grad_norm": 0.8418806195259094,
|
| 1361 |
+
"learning_rate": 2.2251492799438007e-05,
|
| 1362 |
+
"loss": 0.1794,
|
| 1363 |
"step": 1580
|
| 1364 |
},
|
| 1365 |
{
|
| 1366 |
+
"epoch": 1.6754478398314014,
|
| 1367 |
+
"grad_norm": 0.7187584042549133,
|
| 1368 |
+
"learning_rate": 2.207586933614331e-05,
|
| 1369 |
+
"loss": 0.1878,
|
| 1370 |
"step": 1590
|
| 1371 |
},
|
| 1372 |
{
|
| 1373 |
+
"epoch": 1.685985247629083,
|
| 1374 |
+
"grad_norm": 0.7605792284011841,
|
| 1375 |
+
"learning_rate": 2.190024587284861e-05,
|
| 1376 |
+
"loss": 0.1868,
|
| 1377 |
"step": 1600
|
| 1378 |
},
|
| 1379 |
{
|
| 1380 |
+
"epoch": 1.685985247629083,
|
| 1381 |
+
"eval_loss": 0.3536493182182312,
|
| 1382 |
+
"eval_runtime": 13.6104,
|
| 1383 |
+
"eval_samples_per_second": 35.267,
|
| 1384 |
+
"eval_steps_per_second": 2.204,
|
| 1385 |
"step": 1600
|
| 1386 |
},
|
| 1387 |
{
|
| 1388 |
+
"epoch": 1.6965226554267652,
|
| 1389 |
+
"grad_norm": 0.6814613342285156,
|
| 1390 |
+
"learning_rate": 2.1724622409553917e-05,
|
| 1391 |
+
"loss": 0.1851,
|
| 1392 |
"step": 1610
|
| 1393 |
},
|
| 1394 |
{
|
| 1395 |
+
"epoch": 1.7070600632244468,
|
| 1396 |
+
"grad_norm": 0.6218210458755493,
|
| 1397 |
+
"learning_rate": 2.1548998946259223e-05,
|
| 1398 |
+
"loss": 0.1921,
|
| 1399 |
"step": 1620
|
| 1400 |
},
|
| 1401 |
{
|
| 1402 |
+
"epoch": 1.7175974710221285,
|
| 1403 |
+
"grad_norm": 0.9718311429023743,
|
| 1404 |
+
"learning_rate": 2.1373375482964525e-05,
|
| 1405 |
+
"loss": 0.1844,
|
| 1406 |
"step": 1630
|
| 1407 |
},
|
| 1408 |
{
|
| 1409 |
+
"epoch": 1.7281348788198103,
|
| 1410 |
+
"grad_norm": 0.6959328055381775,
|
| 1411 |
+
"learning_rate": 2.1197752019669827e-05,
|
| 1412 |
+
"loss": 0.1802,
|
| 1413 |
"step": 1640
|
| 1414 |
},
|
| 1415 |
{
|
| 1416 |
+
"epoch": 1.7386722866174922,
|
| 1417 |
+
"grad_norm": 0.6459183096885681,
|
| 1418 |
+
"learning_rate": 2.1022128556375133e-05,
|
| 1419 |
+
"loss": 0.1801,
|
| 1420 |
"step": 1650
|
| 1421 |
},
|
| 1422 |
{
|
| 1423 |
+
"epoch": 1.7386722866174922,
|
| 1424 |
+
"eval_loss": 0.3579024374485016,
|
| 1425 |
+
"eval_runtime": 13.6133,
|
| 1426 |
+
"eval_samples_per_second": 35.26,
|
| 1427 |
+
"eval_steps_per_second": 2.204,
|
| 1428 |
"step": 1650
|
| 1429 |
},
|
| 1430 |
{
|
| 1431 |
+
"epoch": 1.7492096944151738,
|
| 1432 |
+
"grad_norm": 0.8063459396362305,
|
| 1433 |
+
"learning_rate": 2.084650509308044e-05,
|
| 1434 |
+
"loss": 0.1793,
|
| 1435 |
"step": 1660
|
| 1436 |
},
|
| 1437 |
{
|
| 1438 |
+
"epoch": 1.7597471022128557,
|
| 1439 |
+
"grad_norm": 0.7973386645317078,
|
| 1440 |
+
"learning_rate": 2.067088162978574e-05,
|
| 1441 |
+
"loss": 0.1851,
|
| 1442 |
"step": 1670
|
| 1443 |
},
|
| 1444 |
{
|
| 1445 |
+
"epoch": 1.7702845100105375,
|
| 1446 |
+
"grad_norm": 0.6851320862770081,
|
| 1447 |
+
"learning_rate": 2.0495258166491043e-05,
|
| 1448 |
+
"loss": 0.1745,
|
| 1449 |
"step": 1680
|
| 1450 |
},
|
| 1451 |
{
|
| 1452 |
+
"epoch": 1.7808219178082192,
|
| 1453 |
+
"grad_norm": 0.6314299702644348,
|
| 1454 |
+
"learning_rate": 2.0319634703196345e-05,
|
| 1455 |
+
"loss": 0.1891,
|
| 1456 |
"step": 1690
|
| 1457 |
},
|
| 1458 |
{
|
| 1459 |
+
"epoch": 1.7913593256059008,
|
| 1460 |
+
"grad_norm": 0.7445196509361267,
|
| 1461 |
+
"learning_rate": 2.0144011239901654e-05,
|
| 1462 |
+
"loss": 0.173,
|
| 1463 |
"step": 1700
|
| 1464 |
},
|
| 1465 |
{
|
| 1466 |
+
"epoch": 1.7913593256059008,
|
| 1467 |
+
"eval_loss": 0.3595808744430542,
|
| 1468 |
+
"eval_runtime": 13.6356,
|
| 1469 |
+
"eval_samples_per_second": 35.202,
|
| 1470 |
+
"eval_steps_per_second": 2.2,
|
| 1471 |
"step": 1700
|
| 1472 |
},
|
| 1473 |
{
|
| 1474 |
+
"epoch": 1.8018967334035827,
|
| 1475 |
+
"grad_norm": 0.6725503206253052,
|
| 1476 |
+
"learning_rate": 1.9968387776606957e-05,
|
| 1477 |
+
"loss": 0.1729,
|
| 1478 |
"step": 1710
|
| 1479 |
},
|
| 1480 |
{
|
| 1481 |
+
"epoch": 1.8124341412012646,
|
| 1482 |
+
"grad_norm": 0.7874764204025269,
|
| 1483 |
+
"learning_rate": 1.979276431331226e-05,
|
| 1484 |
+
"loss": 0.1789,
|
| 1485 |
"step": 1720
|
| 1486 |
},
|
| 1487 |
{
|
| 1488 |
+
"epoch": 1.8229715489989462,
|
| 1489 |
+
"grad_norm": 1.164414882659912,
|
| 1490 |
+
"learning_rate": 1.961714085001756e-05,
|
| 1491 |
+
"loss": 0.1799,
|
| 1492 |
"step": 1730
|
| 1493 |
},
|
| 1494 |
{
|
| 1495 |
+
"epoch": 1.833508956796628,
|
| 1496 |
+
"grad_norm": 0.6965774297714233,
|
| 1497 |
+
"learning_rate": 1.9441517386722867e-05,
|
| 1498 |
+
"loss": 0.1806,
|
| 1499 |
"step": 1740
|
| 1500 |
},
|
| 1501 |
{
|
| 1502 |
+
"epoch": 1.84404636459431,
|
| 1503 |
+
"grad_norm": 0.7329718470573425,
|
| 1504 |
+
"learning_rate": 1.9265893923428172e-05,
|
| 1505 |
+
"loss": 0.1877,
|
| 1506 |
"step": 1750
|
| 1507 |
},
|
| 1508 |
{
|
| 1509 |
+
"epoch": 1.84404636459431,
|
| 1510 |
+
"eval_loss": 0.3642064929008484,
|
| 1511 |
+
"eval_runtime": 13.6522,
|
| 1512 |
+
"eval_samples_per_second": 35.159,
|
| 1513 |
+
"eval_steps_per_second": 2.197,
|
| 1514 |
"step": 1750
|
| 1515 |
},
|
| 1516 |
{
|
| 1517 |
+
"epoch": 1.8545837723919916,
|
| 1518 |
+
"grad_norm": 1.6226530075073242,
|
| 1519 |
+
"learning_rate": 1.9090270460133475e-05,
|
| 1520 |
+
"loss": 0.1843,
|
| 1521 |
"step": 1760
|
| 1522 |
},
|
| 1523 |
{
|
| 1524 |
+
"epoch": 1.8651211801896732,
|
| 1525 |
+
"grad_norm": 0.6283461451530457,
|
| 1526 |
+
"learning_rate": 1.8914646996838777e-05,
|
| 1527 |
+
"loss": 0.1733,
|
| 1528 |
"step": 1770
|
| 1529 |
},
|
| 1530 |
{
|
| 1531 |
+
"epoch": 1.875658587987355,
|
| 1532 |
+
"grad_norm": 0.5947582125663757,
|
| 1533 |
+
"learning_rate": 1.8739023533544083e-05,
|
| 1534 |
+
"loss": 0.1788,
|
| 1535 |
"step": 1780
|
| 1536 |
},
|
| 1537 |
{
|
| 1538 |
+
"epoch": 1.886195995785037,
|
| 1539 |
+
"grad_norm": 0.7731133699417114,
|
| 1540 |
+
"learning_rate": 1.8563400070249388e-05,
|
| 1541 |
+
"loss": 0.1749,
|
| 1542 |
"step": 1790
|
| 1543 |
},
|
| 1544 |
{
|
| 1545 |
+
"epoch": 1.8967334035827186,
|
| 1546 |
+
"grad_norm": 0.869389533996582,
|
| 1547 |
+
"learning_rate": 1.838777660695469e-05,
|
| 1548 |
+
"loss": 0.1787,
|
| 1549 |
"step": 1800
|
| 1550 |
},
|
| 1551 |
{
|
| 1552 |
+
"epoch": 1.8967334035827186,
|
| 1553 |
+
"eval_loss": 0.36554011702537537,
|
| 1554 |
+
"eval_runtime": 13.6633,
|
| 1555 |
+
"eval_samples_per_second": 35.131,
|
| 1556 |
+
"eval_steps_per_second": 2.196,
|
| 1557 |
"step": 1800
|
| 1558 |
},
|
| 1559 |
{
|
| 1560 |
+
"epoch": 1.9072708113804004,
|
| 1561 |
+
"grad_norm": 0.6407529711723328,
|
| 1562 |
+
"learning_rate": 1.8212153143659993e-05,
|
| 1563 |
+
"loss": 0.1693,
|
| 1564 |
"step": 1810
|
| 1565 |
},
|
| 1566 |
{
|
| 1567 |
+
"epoch": 1.9178082191780823,
|
| 1568 |
+
"grad_norm": 0.9166205525398254,
|
| 1569 |
+
"learning_rate": 1.80365296803653e-05,
|
| 1570 |
+
"loss": 0.1716,
|
| 1571 |
"step": 1820
|
| 1572 |
},
|
| 1573 |
{
|
| 1574 |
+
"epoch": 1.928345626975764,
|
| 1575 |
+
"grad_norm": 0.7278560400009155,
|
| 1576 |
+
"learning_rate": 1.7860906217070604e-05,
|
| 1577 |
+
"loss": 0.1782,
|
| 1578 |
"step": 1830
|
| 1579 |
},
|
| 1580 |
{
|
| 1581 |
+
"epoch": 1.9388830347734456,
|
| 1582 |
+
"grad_norm": 0.5721282362937927,
|
| 1583 |
+
"learning_rate": 1.7685282753775906e-05,
|
| 1584 |
+
"loss": 0.1735,
|
| 1585 |
"step": 1840
|
| 1586 |
},
|
| 1587 |
{
|
| 1588 |
+
"epoch": 1.9494204425711275,
|
| 1589 |
+
"grad_norm": 0.707082986831665,
|
| 1590 |
+
"learning_rate": 1.750965929048121e-05,
|
| 1591 |
+
"loss": 0.1767,
|
| 1592 |
"step": 1850
|
| 1593 |
},
|
| 1594 |
{
|
| 1595 |
+
"epoch": 1.9494204425711275,
|
| 1596 |
+
"eval_loss": 0.3640550374984741,
|
| 1597 |
+
"eval_runtime": 13.667,
|
| 1598 |
+
"eval_samples_per_second": 35.121,
|
| 1599 |
+
"eval_steps_per_second": 2.195,
|
| 1600 |
"step": 1850
|
| 1601 |
},
|
| 1602 |
{
|
| 1603 |
+
"epoch": 1.9599578503688093,
|
| 1604 |
+
"grad_norm": 0.6257717609405518,
|
| 1605 |
+
"learning_rate": 1.733403582718651e-05,
|
| 1606 |
+
"loss": 0.1706,
|
| 1607 |
"step": 1860
|
| 1608 |
},
|
| 1609 |
{
|
| 1610 |
+
"epoch": 1.970495258166491,
|
| 1611 |
+
"grad_norm": 0.8650119304656982,
|
| 1612 |
+
"learning_rate": 1.7158412363891816e-05,
|
| 1613 |
+
"loss": 0.171,
|
| 1614 |
"step": 1870
|
| 1615 |
},
|
| 1616 |
{
|
| 1617 |
+
"epoch": 1.9810326659641728,
|
| 1618 |
+
"grad_norm": 0.6042978167533875,
|
| 1619 |
+
"learning_rate": 1.6982788900597122e-05,
|
| 1620 |
+
"loss": 0.1687,
|
| 1621 |
"step": 1880
|
| 1622 |
},
|
| 1623 |
{
|
| 1624 |
+
"epoch": 1.9915700737618547,
|
| 1625 |
+
"grad_norm": 0.8354888558387756,
|
| 1626 |
+
"learning_rate": 1.6807165437302424e-05,
|
| 1627 |
+
"loss": 0.1676,
|
| 1628 |
"step": 1890
|
| 1629 |
},
|
| 1630 |
{
|
| 1631 |
+
"epoch": 2.0021074815595363,
|
| 1632 |
+
"grad_norm": 0.5127582550048828,
|
| 1633 |
+
"learning_rate": 1.6631541974007727e-05,
|
| 1634 |
+
"loss": 0.1615,
|
| 1635 |
"step": 1900
|
| 1636 |
},
|
| 1637 |
{
|
| 1638 |
+
"epoch": 2.0021074815595363,
|
| 1639 |
+
"eval_loss": 0.3677693009376526,
|
| 1640 |
+
"eval_runtime": 13.6584,
|
| 1641 |
+
"eval_samples_per_second": 35.143,
|
| 1642 |
+
"eval_steps_per_second": 2.196,
|
| 1643 |
"step": 1900
|
| 1644 |
},
|
| 1645 |
{
|
| 1646 |
+
"epoch": 2.012644889357218,
|
| 1647 |
+
"grad_norm": 0.6080672740936279,
|
| 1648 |
+
"learning_rate": 1.6455918510713032e-05,
|
| 1649 |
+
"loss": 0.1499,
|
| 1650 |
"step": 1910
|
| 1651 |
},
|
| 1652 |
{
|
| 1653 |
+
"epoch": 2.0231822971549,
|
| 1654 |
+
"grad_norm": 0.6206851601600647,
|
| 1655 |
+
"learning_rate": 1.6280295047418338e-05,
|
| 1656 |
+
"loss": 0.1412,
|
| 1657 |
"step": 1920
|
| 1658 |
},
|
| 1659 |
{
|
| 1660 |
+
"epoch": 2.0337197049525817,
|
| 1661 |
+
"grad_norm": 0.8675506711006165,
|
| 1662 |
+
"learning_rate": 1.610467158412364e-05,
|
| 1663 |
+
"loss": 0.1468,
|
| 1664 |
"step": 1930
|
| 1665 |
},
|
| 1666 |
{
|
| 1667 |
+
"epoch": 2.0442571127502633,
|
| 1668 |
+
"grad_norm": 0.7144894003868103,
|
| 1669 |
+
"learning_rate": 1.5929048120828942e-05,
|
| 1670 |
+
"loss": 0.1505,
|
| 1671 |
"step": 1940
|
| 1672 |
},
|
| 1673 |
{
|
| 1674 |
+
"epoch": 2.0547945205479454,
|
| 1675 |
+
"grad_norm": 0.6287038326263428,
|
| 1676 |
+
"learning_rate": 1.5753424657534248e-05,
|
| 1677 |
+
"loss": 0.1481,
|
| 1678 |
"step": 1950
|
| 1679 |
},
|
| 1680 |
{
|
| 1681 |
+
"epoch": 2.0547945205479454,
|
| 1682 |
+
"eval_loss": 0.3874117434024811,
|
| 1683 |
+
"eval_runtime": 13.6221,
|
| 1684 |
+
"eval_samples_per_second": 35.237,
|
| 1685 |
+
"eval_steps_per_second": 2.202,
|
| 1686 |
"step": 1950
|
| 1687 |
},
|
| 1688 |
{
|
| 1689 |
+
"epoch": 2.065331928345627,
|
| 1690 |
+
"grad_norm": 0.8757415413856506,
|
| 1691 |
+
"learning_rate": 1.5577801194239554e-05,
|
| 1692 |
+
"loss": 0.1476,
|
| 1693 |
"step": 1960
|
| 1694 |
},
|
| 1695 |
{
|
| 1696 |
+
"epoch": 2.0758693361433087,
|
| 1697 |
+
"grad_norm": 0.9166101813316345,
|
| 1698 |
+
"learning_rate": 1.5402177730944856e-05,
|
| 1699 |
+
"loss": 0.15,
|
| 1700 |
"step": 1970
|
| 1701 |
},
|
| 1702 |
{
|
| 1703 |
+
"epoch": 2.0864067439409903,
|
| 1704 |
+
"grad_norm": 0.7331491112709045,
|
| 1705 |
+
"learning_rate": 1.5226554267650158e-05,
|
| 1706 |
+
"loss": 0.1581,
|
| 1707 |
"step": 1980
|
| 1708 |
},
|
| 1709 |
{
|
| 1710 |
+
"epoch": 2.0969441517386724,
|
| 1711 |
+
"grad_norm": 0.7679803967475891,
|
| 1712 |
+
"learning_rate": 1.5050930804355462e-05,
|
| 1713 |
+
"loss": 0.1435,
|
| 1714 |
"step": 1990
|
| 1715 |
},
|
| 1716 |
{
|
| 1717 |
+
"epoch": 2.107481559536354,
|
| 1718 |
+
"grad_norm": 0.6296097636222839,
|
| 1719 |
+
"learning_rate": 1.4875307341060764e-05,
|
| 1720 |
+
"loss": 0.1586,
|
| 1721 |
"step": 2000
|
| 1722 |
},
|
| 1723 |
{
|
| 1724 |
+
"epoch": 2.107481559536354,
|
| 1725 |
+
"eval_loss": 0.399673730134964,
|
| 1726 |
+
"eval_runtime": 13.5877,
|
| 1727 |
+
"eval_samples_per_second": 35.326,
|
| 1728 |
+
"eval_steps_per_second": 2.208,
|
| 1729 |
"step": 2000
|
| 1730 |
},
|
| 1731 |
{
|
| 1732 |
+
"epoch": 2.1180189673340357,
|
| 1733 |
+
"grad_norm": 0.7950565814971924,
|
| 1734 |
+
"learning_rate": 1.4699683877766072e-05,
|
| 1735 |
+
"loss": 0.147,
|
| 1736 |
"step": 2010
|
| 1737 |
},
|
| 1738 |
{
|
| 1739 |
+
"epoch": 2.128556375131718,
|
| 1740 |
+
"grad_norm": 0.7187503576278687,
|
| 1741 |
+
"learning_rate": 1.4524060414471374e-05,
|
| 1742 |
+
"loss": 0.1505,
|
| 1743 |
"step": 2020
|
| 1744 |
},
|
| 1745 |
{
|
| 1746 |
+
"epoch": 2.1390937829293994,
|
| 1747 |
+
"grad_norm": 0.6770270466804504,
|
| 1748 |
+
"learning_rate": 1.4348436951176678e-05,
|
| 1749 |
+
"loss": 0.1509,
|
| 1750 |
"step": 2030
|
| 1751 |
},
|
| 1752 |
{
|
| 1753 |
+
"epoch": 2.149631190727081,
|
| 1754 |
+
"grad_norm": 0.7002925276756287,
|
| 1755 |
+
"learning_rate": 1.417281348788198e-05,
|
| 1756 |
+
"loss": 0.149,
|
| 1757 |
"step": 2040
|
| 1758 |
},
|
| 1759 |
{
|
| 1760 |
+
"epoch": 2.1601685985247627,
|
| 1761 |
+
"grad_norm": 0.8196738362312317,
|
| 1762 |
+
"learning_rate": 1.3997190024587286e-05,
|
| 1763 |
+
"loss": 0.1496,
|
| 1764 |
"step": 2050
|
| 1765 |
},
|
| 1766 |
{
|
| 1767 |
+
"epoch": 2.1601685985247627,
|
| 1768 |
+
"eval_loss": 0.4035220742225647,
|
| 1769 |
+
"eval_runtime": 13.6079,
|
| 1770 |
+
"eval_samples_per_second": 35.274,
|
| 1771 |
+
"eval_steps_per_second": 2.205,
|
| 1772 |
"step": 2050
|
| 1773 |
},
|
| 1774 |
{
|
| 1775 |
+
"epoch": 2.170706006322445,
|
| 1776 |
+
"grad_norm": 0.972318708896637,
|
| 1777 |
+
"learning_rate": 1.382156656129259e-05,
|
| 1778 |
+
"loss": 0.1507,
|
| 1779 |
"step": 2060
|
| 1780 |
},
|
| 1781 |
{
|
| 1782 |
+
"epoch": 2.1812434141201265,
|
| 1783 |
+
"grad_norm": 0.8114174604415894,
|
| 1784 |
+
"learning_rate": 1.3645943097997894e-05,
|
| 1785 |
+
"loss": 0.1498,
|
| 1786 |
"step": 2070
|
| 1787 |
},
|
| 1788 |
{
|
| 1789 |
+
"epoch": 2.191780821917808,
|
| 1790 |
+
"grad_norm": 0.6477043032646179,
|
| 1791 |
+
"learning_rate": 1.3470319634703196e-05,
|
| 1792 |
+
"loss": 0.1523,
|
| 1793 |
"step": 2080
|
| 1794 |
},
|
| 1795 |
{
|
| 1796 |
+
"epoch": 2.20231822971549,
|
| 1797 |
+
"grad_norm": 0.8281266093254089,
|
| 1798 |
+
"learning_rate": 1.32946961714085e-05,
|
| 1799 |
+
"loss": 0.1498,
|
| 1800 |
"step": 2090
|
| 1801 |
},
|
| 1802 |
{
|
| 1803 |
+
"epoch": 2.212855637513172,
|
| 1804 |
+
"grad_norm": 0.7811893224716187,
|
| 1805 |
+
"learning_rate": 1.3119072708113806e-05,
|
| 1806 |
+
"loss": 0.1486,
|
| 1807 |
"step": 2100
|
| 1808 |
},
|
| 1809 |
{
|
| 1810 |
+
"epoch": 2.212855637513172,
|
| 1811 |
+
"eval_loss": 0.3995499908924103,
|
| 1812 |
+
"eval_runtime": 13.6182,
|
| 1813 |
+
"eval_samples_per_second": 35.247,
|
| 1814 |
+
"eval_steps_per_second": 2.203,
|
| 1815 |
"step": 2100
|
| 1816 |
},
|
| 1817 |
{
|
| 1818 |
+
"epoch": 2.2233930453108535,
|
| 1819 |
+
"grad_norm": 0.8453881144523621,
|
| 1820 |
+
"learning_rate": 1.2943449244819108e-05,
|
| 1821 |
+
"loss": 0.1473,
|
| 1822 |
"step": 2110
|
| 1823 |
},
|
| 1824 |
{
|
| 1825 |
+
"epoch": 2.233930453108535,
|
| 1826 |
+
"grad_norm": 0.8025777339935303,
|
| 1827 |
+
"learning_rate": 1.2767825781524412e-05,
|
| 1828 |
+
"loss": 0.1502,
|
| 1829 |
"step": 2120
|
| 1830 |
},
|
| 1831 |
{
|
| 1832 |
+
"epoch": 2.244467860906217,
|
| 1833 |
+
"grad_norm": 0.775323748588562,
|
| 1834 |
+
"learning_rate": 1.2592202318229716e-05,
|
| 1835 |
+
"loss": 0.1402,
|
| 1836 |
"step": 2130
|
| 1837 |
},
|
| 1838 |
{
|
| 1839 |
+
"epoch": 2.255005268703899,
|
| 1840 |
+
"grad_norm": 1.1507049798965454,
|
| 1841 |
+
"learning_rate": 1.241657885493502e-05,
|
| 1842 |
+
"loss": 0.1447,
|
| 1843 |
"step": 2140
|
| 1844 |
},
|
| 1845 |
{
|
| 1846 |
+
"epoch": 2.2655426765015805,
|
| 1847 |
+
"grad_norm": 0.7232986688613892,
|
| 1848 |
+
"learning_rate": 1.2240955391640324e-05,
|
| 1849 |
+
"loss": 0.1477,
|
| 1850 |
"step": 2150
|
| 1851 |
},
|
| 1852 |
{
|
| 1853 |
+
"epoch": 2.2655426765015805,
|
| 1854 |
+
"eval_loss": 0.409657746553421,
|
| 1855 |
+
"eval_runtime": 13.6393,
|
| 1856 |
+
"eval_samples_per_second": 35.192,
|
| 1857 |
+
"eval_steps_per_second": 2.2,
|
| 1858 |
"step": 2150
|
| 1859 |
},
|
| 1860 |
{
|
| 1861 |
+
"epoch": 2.2760800842992626,
|
| 1862 |
+
"grad_norm": 0.957969069480896,
|
| 1863 |
+
"learning_rate": 1.2065331928345628e-05,
|
| 1864 |
+
"loss": 0.1477,
|
| 1865 |
"step": 2160
|
| 1866 |
},
|
| 1867 |
{
|
| 1868 |
+
"epoch": 2.286617492096944,
|
| 1869 |
+
"grad_norm": 0.7197175621986389,
|
| 1870 |
+
"learning_rate": 1.1889708465050932e-05,
|
| 1871 |
+
"loss": 0.1399,
|
| 1872 |
"step": 2170
|
| 1873 |
},
|
| 1874 |
{
|
| 1875 |
+
"epoch": 2.297154899894626,
|
| 1876 |
+
"grad_norm": 0.7239243984222412,
|
| 1877 |
+
"learning_rate": 1.1714085001756236e-05,
|
| 1878 |
+
"loss": 0.1508,
|
| 1879 |
"step": 2180
|
| 1880 |
},
|
| 1881 |
{
|
| 1882 |
+
"epoch": 2.3076923076923075,
|
| 1883 |
+
"grad_norm": 0.9576734900474548,
|
| 1884 |
+
"learning_rate": 1.153846153846154e-05,
|
| 1885 |
+
"loss": 0.1424,
|
| 1886 |
"step": 2190
|
| 1887 |
},
|
| 1888 |
{
|
| 1889 |
+
"epoch": 2.3182297154899896,
|
| 1890 |
+
"grad_norm": 1.0368537902832031,
|
| 1891 |
+
"learning_rate": 1.1362838075166843e-05,
|
| 1892 |
+
"loss": 0.1499,
|
| 1893 |
"step": 2200
|
| 1894 |
},
|
| 1895 |
{
|
| 1896 |
+
"epoch": 2.3182297154899896,
|
| 1897 |
+
"eval_loss": 0.40890181064605713,
|
| 1898 |
+
"eval_runtime": 13.6591,
|
| 1899 |
+
"eval_samples_per_second": 35.141,
|
| 1900 |
+
"eval_steps_per_second": 2.196,
|
| 1901 |
"step": 2200
|
| 1902 |
},
|
| 1903 |
{
|
| 1904 |
+
"epoch": 2.328767123287671,
|
| 1905 |
+
"grad_norm": 0.6726427674293518,
|
| 1906 |
+
"learning_rate": 1.1187214611872146e-05,
|
| 1907 |
+
"loss": 0.15,
|
| 1908 |
"step": 2210
|
| 1909 |
},
|
| 1910 |
{
|
| 1911 |
+
"epoch": 2.339304531085353,
|
| 1912 |
+
"grad_norm": 0.6462188363075256,
|
| 1913 |
+
"learning_rate": 1.1011591148577451e-05,
|
| 1914 |
+
"loss": 0.1452,
|
| 1915 |
"step": 2220
|
| 1916 |
},
|
| 1917 |
{
|
| 1918 |
+
"epoch": 2.349841938883035,
|
| 1919 |
+
"grad_norm": 0.7393044829368591,
|
| 1920 |
+
"learning_rate": 1.0835967685282754e-05,
|
| 1921 |
+
"loss": 0.1477,
|
| 1922 |
"step": 2230
|
| 1923 |
},
|
| 1924 |
{
|
| 1925 |
+
"epoch": 2.3603793466807166,
|
| 1926 |
+
"grad_norm": 0.8233257532119751,
|
| 1927 |
+
"learning_rate": 1.0660344221988058e-05,
|
| 1928 |
+
"loss": 0.154,
|
| 1929 |
"step": 2240
|
| 1930 |
},
|
| 1931 |
{
|
| 1932 |
+
"epoch": 2.3709167544783982,
|
| 1933 |
+
"grad_norm": 0.8854420781135559,
|
| 1934 |
+
"learning_rate": 1.0484720758693362e-05,
|
| 1935 |
+
"loss": 0.1443,
|
| 1936 |
"step": 2250
|
| 1937 |
},
|
| 1938 |
{
|
| 1939 |
+
"epoch": 2.3709167544783982,
|
| 1940 |
+
"eval_loss": 0.40763771533966064,
|
| 1941 |
+
"eval_runtime": 13.6523,
|
| 1942 |
+
"eval_samples_per_second": 35.159,
|
| 1943 |
+
"eval_steps_per_second": 2.197,
|
| 1944 |
"step": 2250
|
| 1945 |
},
|
| 1946 |
{
|
| 1947 |
+
"epoch": 2.3814541622760803,
|
| 1948 |
+
"grad_norm": 0.7281904220581055,
|
| 1949 |
+
"learning_rate": 1.0309097295398666e-05,
|
| 1950 |
+
"loss": 0.1504,
|
| 1951 |
"step": 2260
|
| 1952 |
},
|
| 1953 |
{
|
| 1954 |
+
"epoch": 2.391991570073762,
|
| 1955 |
+
"grad_norm": 0.7077420353889465,
|
| 1956 |
+
"learning_rate": 1.013347383210397e-05,
|
| 1957 |
+
"loss": 0.1453,
|
| 1958 |
"step": 2270
|
| 1959 |
},
|
| 1960 |
{
|
| 1961 |
+
"epoch": 2.4025289778714436,
|
| 1962 |
+
"grad_norm": 0.6380478739738464,
|
| 1963 |
+
"learning_rate": 9.957850368809273e-06,
|
| 1964 |
+
"loss": 0.1468,
|
| 1965 |
"step": 2280
|
| 1966 |
},
|
| 1967 |
{
|
| 1968 |
+
"epoch": 2.4130663856691252,
|
| 1969 |
+
"grad_norm": 0.5880696773529053,
|
| 1970 |
+
"learning_rate": 9.782226905514577e-06,
|
| 1971 |
+
"loss": 0.1402,
|
| 1972 |
"step": 2290
|
| 1973 |
},
|
| 1974 |
{
|
| 1975 |
+
"epoch": 2.4236037934668073,
|
| 1976 |
+
"grad_norm": 0.7334967851638794,
|
| 1977 |
+
"learning_rate": 9.606603442219881e-06,
|
| 1978 |
+
"loss": 0.1449,
|
| 1979 |
"step": 2300
|
| 1980 |
},
|
| 1981 |
{
|
| 1982 |
+
"epoch": 2.4236037934668073,
|
| 1983 |
+
"eval_loss": 0.41403505206108093,
|
| 1984 |
+
"eval_runtime": 13.6561,
|
| 1985 |
+
"eval_samples_per_second": 35.149,
|
| 1986 |
+
"eval_steps_per_second": 2.197,
|
| 1987 |
"step": 2300
|
| 1988 |
},
|
| 1989 |
{
|
| 1990 |
+
"epoch": 2.434141201264489,
|
| 1991 |
+
"grad_norm": 0.7387108206748962,
|
| 1992 |
+
"learning_rate": 9.430979978925185e-06,
|
| 1993 |
+
"loss": 0.1392,
|
| 1994 |
"step": 2310
|
| 1995 |
},
|
| 1996 |
{
|
| 1997 |
+
"epoch": 2.4446786090621706,
|
| 1998 |
+
"grad_norm": 0.6824939846992493,
|
| 1999 |
+
"learning_rate": 9.255356515630488e-06,
|
| 2000 |
+
"loss": 0.1446,
|
| 2001 |
"step": 2320
|
| 2002 |
},
|
| 2003 |
{
|
| 2004 |
+
"epoch": 2.4552160168598522,
|
| 2005 |
+
"grad_norm": 0.7604888677597046,
|
| 2006 |
+
"learning_rate": 9.079733052335793e-06,
|
| 2007 |
+
"loss": 0.1403,
|
| 2008 |
"step": 2330
|
| 2009 |
},
|
| 2010 |
{
|
| 2011 |
+
"epoch": 2.4657534246575343,
|
| 2012 |
+
"grad_norm": 0.851366400718689,
|
| 2013 |
+
"learning_rate": 8.904109589041095e-06,
|
| 2014 |
+
"loss": 0.1463,
|
| 2015 |
"step": 2340
|
| 2016 |
},
|
| 2017 |
{
|
| 2018 |
+
"epoch": 2.476290832455216,
|
| 2019 |
+
"grad_norm": 0.6607230305671692,
|
| 2020 |
+
"learning_rate": 8.728486125746401e-06,
|
| 2021 |
+
"loss": 0.1433,
|
| 2022 |
"step": 2350
|
| 2023 |
},
|
| 2024 |
{
|
| 2025 |
+
"epoch": 2.476290832455216,
|
| 2026 |
+
"eval_loss": 0.40974321961402893,
|
| 2027 |
+
"eval_runtime": 13.648,
|
| 2028 |
+
"eval_samples_per_second": 35.17,
|
| 2029 |
+
"eval_steps_per_second": 2.198,
|
| 2030 |
"step": 2350
|
| 2031 |
},
|
| 2032 |
{
|
| 2033 |
+
"epoch": 2.4868282402528976,
|
| 2034 |
+
"grad_norm": 0.785926342010498,
|
| 2035 |
+
"learning_rate": 8.552862662451703e-06,
|
| 2036 |
+
"loss": 0.1403,
|
| 2037 |
"step": 2360
|
| 2038 |
},
|
| 2039 |
{
|
| 2040 |
+
"epoch": 2.4973656480505797,
|
| 2041 |
+
"grad_norm": 0.7373778223991394,
|
| 2042 |
+
"learning_rate": 8.377239199157007e-06,
|
| 2043 |
+
"loss": 0.1399,
|
| 2044 |
"step": 2370
|
| 2045 |
},
|
| 2046 |
{
|
| 2047 |
+
"epoch": 2.5079030558482613,
|
| 2048 |
+
"grad_norm": 0.9675643444061279,
|
| 2049 |
+
"learning_rate": 8.201615735862311e-06,
|
| 2050 |
+
"loss": 0.1481,
|
| 2051 |
"step": 2380
|
| 2052 |
},
|
| 2053 |
{
|
| 2054 |
+
"epoch": 2.518440463645943,
|
| 2055 |
+
"grad_norm": 0.7026488780975342,
|
| 2056 |
+
"learning_rate": 8.025992272567615e-06,
|
| 2057 |
+
"loss": 0.1385,
|
| 2058 |
"step": 2390
|
| 2059 |
},
|
| 2060 |
{
|
| 2061 |
+
"epoch": 2.528977871443625,
|
| 2062 |
+
"grad_norm": 0.6957457065582275,
|
| 2063 |
+
"learning_rate": 7.85036880927292e-06,
|
| 2064 |
+
"loss": 0.1444,
|
| 2065 |
"step": 2400
|
| 2066 |
},
|
| 2067 |
{
|
| 2068 |
+
"epoch": 2.528977871443625,
|
| 2069 |
+
"eval_loss": 0.4191787838935852,
|
| 2070 |
+
"eval_runtime": 13.6468,
|
| 2071 |
+
"eval_samples_per_second": 35.173,
|
| 2072 |
+
"eval_steps_per_second": 2.198,
|
| 2073 |
"step": 2400
|
| 2074 |
}
|
| 2075 |
],
|
| 2076 |
"logging_steps": 10,
|
| 2077 |
+
"max_steps": 2847,
|
| 2078 |
"num_input_tokens_seen": 0,
|
| 2079 |
"num_train_epochs": 3,
|
| 2080 |
"save_steps": 100,
|
|
|
|
| 2090 |
"attributes": {}
|
| 2091 |
}
|
| 2092 |
},
|
| 2093 |
+
"total_flos": 2.8791430127404646e+17,
|
| 2094 |
"train_batch_size": 16,
|
| 2095 |
"trial_name": null,
|
| 2096 |
"trial_params": null
|
checkpoint-2400/training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5880
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b5fa9d8b62d1ebe6967a504a7decdb5eeee2bb4aac96e7414f3930f9adcff095
|
| 3 |
size 5880
|