Upload folder using huggingface_hub
Browse files- adapter_config.json +2 -2
- adapter_model.safetensors +1 -1
- checkpoint-1050/adapter_config.json +2 -2
- checkpoint-1050/adapter_model.safetensors +1 -1
- checkpoint-1050/optimizer.pt +1 -1
- checkpoint-1050/rng_state.pth +1 -1
- checkpoint-1050/scheduler.pt +1 -1
- checkpoint-1050/trainer_state.json +327 -327
- checkpoint-1050/training_args.bin +1 -1
- checkpoint-350/adapter_config.json +2 -2
- checkpoint-350/adapter_model.safetensors +1 -1
- checkpoint-350/optimizer.pt +1 -1
- checkpoint-350/rng_state.pth +1 -1
- checkpoint-350/scheduler.pt +1 -1
- checkpoint-350/trainer_state.json +110 -110
- checkpoint-350/training_args.bin +1 -1
- checkpoint-700/adapter_config.json +2 -2
- checkpoint-700/adapter_model.safetensors +1 -1
- checkpoint-700/optimizer.pt +1 -1
- checkpoint-700/rng_state.pth +1 -1
- checkpoint-700/scheduler.pt +1 -1
- checkpoint-700/trainer_state.json +219 -219
- checkpoint-700/training_args.bin +1 -1
- training_args.bin +1 -1
adapter_config.json
CHANGED
|
@@ -20,8 +20,8 @@
|
|
| 20 |
"rank_pattern": {},
|
| 21 |
"revision": null,
|
| 22 |
"target_modules": [
|
| 23 |
-
"
|
| 24 |
-
"
|
| 25 |
],
|
| 26 |
"task_type": "CAUSAL_LM",
|
| 27 |
"use_dora": false,
|
|
|
|
| 20 |
"rank_pattern": {},
|
| 21 |
"revision": null,
|
| 22 |
"target_modules": [
|
| 23 |
+
"v_proj",
|
| 24 |
+
"q_proj"
|
| 25 |
],
|
| 26 |
"task_type": "CAUSAL_LM",
|
| 27 |
"use_dora": false,
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3416264
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0346bf3d1823e89b4797054ab8629cb0ecb7942156d4832bce2f4d073b71f201
|
| 3 |
size 3416264
|
checkpoint-1050/adapter_config.json
CHANGED
|
@@ -20,8 +20,8 @@
|
|
| 20 |
"rank_pattern": {},
|
| 21 |
"revision": null,
|
| 22 |
"target_modules": [
|
| 23 |
-
"
|
| 24 |
-
"
|
| 25 |
],
|
| 26 |
"task_type": "CAUSAL_LM",
|
| 27 |
"use_dora": false,
|
|
|
|
| 20 |
"rank_pattern": {},
|
| 21 |
"revision": null,
|
| 22 |
"target_modules": [
|
| 23 |
+
"v_proj",
|
| 24 |
+
"q_proj"
|
| 25 |
],
|
| 26 |
"task_type": "CAUSAL_LM",
|
| 27 |
"use_dora": false,
|
checkpoint-1050/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3416264
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0346bf3d1823e89b4797054ab8629cb0ecb7942156d4832bce2f4d073b71f201
|
| 3 |
size 3416264
|
checkpoint-1050/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 6869818
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:65c69ad74e25d4540bbfeb36ef99adc29f6a5f11187f375b6dcf335632f9bf77
|
| 3 |
size 6869818
|
checkpoint-1050/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:c7358d9c30f2639fd60afd346acbf92ecea749dafe0ff584e147ba759751f266
|
| 3 |
size 14244
|
checkpoint-1050/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 sha256:3dd067d46d8bf3a73453265c0d5998bca08a0fa082902b0c1a537936aedcddc6
|
| 3 |
size 1064
|
checkpoint-1050/trainer_state.json
CHANGED
|
@@ -10,761 +10,761 @@
|
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 0.02857142857142857,
|
| 13 |
-
"grad_norm":
|
| 14 |
-
"learning_rate":
|
| 15 |
-
"loss":
|
| 16 |
"step": 10
|
| 17 |
},
|
| 18 |
{
|
| 19 |
"epoch": 0.05714285714285714,
|
| 20 |
-
"grad_norm":
|
| 21 |
-
"learning_rate":
|
| 22 |
-
"loss":
|
| 23 |
"step": 20
|
| 24 |
},
|
| 25 |
{
|
| 26 |
"epoch": 0.08571428571428572,
|
| 27 |
-
"grad_norm":
|
| 28 |
-
"learning_rate":
|
| 29 |
-
"loss":
|
| 30 |
"step": 30
|
| 31 |
},
|
| 32 |
{
|
| 33 |
"epoch": 0.11428571428571428,
|
| 34 |
-
"grad_norm":
|
| 35 |
-
"learning_rate":
|
| 36 |
-
"loss":
|
| 37 |
"step": 40
|
| 38 |
},
|
| 39 |
{
|
| 40 |
"epoch": 0.14285714285714285,
|
| 41 |
-
"grad_norm":
|
| 42 |
-
"learning_rate":
|
| 43 |
-
"loss":
|
| 44 |
"step": 50
|
| 45 |
},
|
| 46 |
{
|
| 47 |
"epoch": 0.17142857142857143,
|
| 48 |
-
"grad_norm": 5.
|
| 49 |
-
"learning_rate":
|
| 50 |
-
"loss": 1.
|
| 51 |
"step": 60
|
| 52 |
},
|
| 53 |
{
|
| 54 |
"epoch": 0.2,
|
| 55 |
-
"grad_norm":
|
| 56 |
-
"learning_rate":
|
| 57 |
-
"loss": 1.
|
| 58 |
"step": 70
|
| 59 |
},
|
| 60 |
{
|
| 61 |
"epoch": 0.22857142857142856,
|
| 62 |
-
"grad_norm":
|
| 63 |
-
"learning_rate":
|
| 64 |
-
"loss": 1.
|
| 65 |
"step": 80
|
| 66 |
},
|
| 67 |
{
|
| 68 |
"epoch": 0.2571428571428571,
|
| 69 |
-
"grad_norm":
|
| 70 |
-
"learning_rate":
|
| 71 |
-
"loss": 1.
|
| 72 |
"step": 90
|
| 73 |
},
|
| 74 |
{
|
| 75 |
"epoch": 0.2857142857142857,
|
| 76 |
-
"grad_norm": 7.
|
| 77 |
-
"learning_rate":
|
| 78 |
-
"loss": 1.
|
| 79 |
"step": 100
|
| 80 |
},
|
| 81 |
{
|
| 82 |
"epoch": 0.3142857142857143,
|
| 83 |
-
"grad_norm":
|
| 84 |
-
"learning_rate":
|
| 85 |
-
"loss": 1.
|
| 86 |
"step": 110
|
| 87 |
},
|
| 88 |
{
|
| 89 |
"epoch": 0.34285714285714286,
|
| 90 |
-
"grad_norm":
|
| 91 |
-
"learning_rate":
|
| 92 |
-
"loss": 1.
|
| 93 |
"step": 120
|
| 94 |
},
|
| 95 |
{
|
| 96 |
"epoch": 0.37142857142857144,
|
| 97 |
-
"grad_norm":
|
| 98 |
-
"learning_rate":
|
| 99 |
-
"loss": 1.
|
| 100 |
"step": 130
|
| 101 |
},
|
| 102 |
{
|
| 103 |
"epoch": 0.4,
|
| 104 |
-
"grad_norm":
|
| 105 |
-
"learning_rate":
|
| 106 |
-
"loss": 1.
|
| 107 |
"step": 140
|
| 108 |
},
|
| 109 |
{
|
| 110 |
"epoch": 0.42857142857142855,
|
| 111 |
-
"grad_norm":
|
| 112 |
-
"learning_rate":
|
| 113 |
-
"loss": 1.
|
| 114 |
"step": 150
|
| 115 |
},
|
| 116 |
{
|
| 117 |
"epoch": 0.45714285714285713,
|
| 118 |
-
"grad_norm":
|
| 119 |
-
"learning_rate":
|
| 120 |
-
"loss": 1.
|
| 121 |
"step": 160
|
| 122 |
},
|
| 123 |
{
|
| 124 |
"epoch": 0.4857142857142857,
|
| 125 |
-
"grad_norm":
|
| 126 |
-
"learning_rate":
|
| 127 |
-
"loss": 1.
|
| 128 |
"step": 170
|
| 129 |
},
|
| 130 |
{
|
| 131 |
"epoch": 0.5142857142857142,
|
| 132 |
-
"grad_norm":
|
| 133 |
-
"learning_rate":
|
| 134 |
-
"loss": 1.
|
| 135 |
"step": 180
|
| 136 |
},
|
| 137 |
{
|
| 138 |
"epoch": 0.5428571428571428,
|
| 139 |
-
"grad_norm":
|
| 140 |
-
"learning_rate":
|
| 141 |
-
"loss": 1.
|
| 142 |
"step": 190
|
| 143 |
},
|
| 144 |
{
|
| 145 |
"epoch": 0.5714285714285714,
|
| 146 |
-
"grad_norm":
|
| 147 |
-
"learning_rate":
|
| 148 |
-
"loss": 1.
|
| 149 |
"step": 200
|
| 150 |
},
|
| 151 |
{
|
| 152 |
"epoch": 0.6,
|
| 153 |
-
"grad_norm":
|
| 154 |
-
"learning_rate":
|
| 155 |
-
"loss": 1.
|
| 156 |
"step": 210
|
| 157 |
},
|
| 158 |
{
|
| 159 |
"epoch": 0.6285714285714286,
|
| 160 |
-
"grad_norm":
|
| 161 |
-
"learning_rate":
|
| 162 |
-
"loss": 1.
|
| 163 |
"step": 220
|
| 164 |
},
|
| 165 |
{
|
| 166 |
"epoch": 0.6571428571428571,
|
| 167 |
-
"grad_norm":
|
| 168 |
-
"learning_rate":
|
| 169 |
-
"loss": 1.
|
| 170 |
"step": 230
|
| 171 |
},
|
| 172 |
{
|
| 173 |
"epoch": 0.6857142857142857,
|
| 174 |
-
"grad_norm":
|
| 175 |
-
"learning_rate":
|
| 176 |
-
"loss": 1.
|
| 177 |
"step": 240
|
| 178 |
},
|
| 179 |
{
|
| 180 |
"epoch": 0.7142857142857143,
|
| 181 |
-
"grad_norm":
|
| 182 |
-
"learning_rate":
|
| 183 |
-
"loss": 1.
|
| 184 |
"step": 250
|
| 185 |
},
|
| 186 |
{
|
| 187 |
"epoch": 0.7428571428571429,
|
| 188 |
-
"grad_norm":
|
| 189 |
-
"learning_rate":
|
| 190 |
-
"loss": 1.
|
| 191 |
"step": 260
|
| 192 |
},
|
| 193 |
{
|
| 194 |
"epoch": 0.7714285714285715,
|
| 195 |
-
"grad_norm":
|
| 196 |
-
"learning_rate":
|
| 197 |
-
"loss": 1.
|
| 198 |
"step": 270
|
| 199 |
},
|
| 200 |
{
|
| 201 |
"epoch": 0.8,
|
| 202 |
-
"grad_norm":
|
| 203 |
-
"learning_rate":
|
| 204 |
-
"loss": 1.
|
| 205 |
"step": 280
|
| 206 |
},
|
| 207 |
{
|
| 208 |
"epoch": 0.8285714285714286,
|
| 209 |
-
"grad_norm":
|
| 210 |
-
"learning_rate":
|
| 211 |
-
"loss": 1.
|
| 212 |
"step": 290
|
| 213 |
},
|
| 214 |
{
|
| 215 |
"epoch": 0.8571428571428571,
|
| 216 |
-
"grad_norm":
|
| 217 |
-
"learning_rate":
|
| 218 |
-
"loss": 1.
|
| 219 |
"step": 300
|
| 220 |
},
|
| 221 |
{
|
| 222 |
"epoch": 0.8857142857142857,
|
| 223 |
-
"grad_norm":
|
| 224 |
-
"learning_rate":
|
| 225 |
-
"loss": 1.
|
| 226 |
"step": 310
|
| 227 |
},
|
| 228 |
{
|
| 229 |
"epoch": 0.9142857142857143,
|
| 230 |
-
"grad_norm":
|
| 231 |
-
"learning_rate":
|
| 232 |
-
"loss": 1.
|
| 233 |
"step": 320
|
| 234 |
},
|
| 235 |
{
|
| 236 |
"epoch": 0.9428571428571428,
|
| 237 |
-
"grad_norm":
|
| 238 |
-
"learning_rate":
|
| 239 |
-
"loss": 1.
|
| 240 |
"step": 330
|
| 241 |
},
|
| 242 |
{
|
| 243 |
"epoch": 0.9714285714285714,
|
| 244 |
-
"grad_norm":
|
| 245 |
-
"learning_rate":
|
| 246 |
-
"loss": 1.
|
| 247 |
"step": 340
|
| 248 |
},
|
| 249 |
{
|
| 250 |
"epoch": 1.0,
|
| 251 |
-
"grad_norm":
|
| 252 |
-
"learning_rate":
|
| 253 |
-
"loss": 1.
|
| 254 |
"step": 350
|
| 255 |
},
|
| 256 |
{
|
| 257 |
"epoch": 1.0,
|
| 258 |
-
"eval_loss": 1.
|
| 259 |
-
"eval_runtime": 16.
|
| 260 |
-
"eval_samples_per_second": 12.
|
| 261 |
-
"eval_steps_per_second": 1.
|
| 262 |
"step": 350
|
| 263 |
},
|
| 264 |
{
|
| 265 |
"epoch": 1.0285714285714285,
|
| 266 |
-
"grad_norm":
|
| 267 |
-
"learning_rate":
|
| 268 |
-
"loss": 1.
|
| 269 |
"step": 360
|
| 270 |
},
|
| 271 |
{
|
| 272 |
"epoch": 1.0571428571428572,
|
| 273 |
-
"grad_norm":
|
| 274 |
-
"learning_rate":
|
| 275 |
-
"loss": 1.
|
| 276 |
"step": 370
|
| 277 |
},
|
| 278 |
{
|
| 279 |
"epoch": 1.0857142857142856,
|
| 280 |
-
"grad_norm":
|
| 281 |
-
"learning_rate":
|
| 282 |
-
"loss": 1.
|
| 283 |
"step": 380
|
| 284 |
},
|
| 285 |
{
|
| 286 |
"epoch": 1.1142857142857143,
|
| 287 |
-
"grad_norm":
|
| 288 |
-
"learning_rate":
|
| 289 |
-
"loss": 1.
|
| 290 |
"step": 390
|
| 291 |
},
|
| 292 |
{
|
| 293 |
"epoch": 1.1428571428571428,
|
| 294 |
-
"grad_norm":
|
| 295 |
-
"learning_rate":
|
| 296 |
-
"loss": 1.
|
| 297 |
"step": 400
|
| 298 |
},
|
| 299 |
{
|
| 300 |
"epoch": 1.1714285714285715,
|
| 301 |
-
"grad_norm":
|
| 302 |
-
"learning_rate":
|
| 303 |
-
"loss": 1.
|
| 304 |
"step": 410
|
| 305 |
},
|
| 306 |
{
|
| 307 |
"epoch": 1.2,
|
| 308 |
-
"grad_norm":
|
| 309 |
-
"learning_rate":
|
| 310 |
-
"loss": 1.
|
| 311 |
"step": 420
|
| 312 |
},
|
| 313 |
{
|
| 314 |
"epoch": 1.2285714285714286,
|
| 315 |
-
"grad_norm":
|
| 316 |
-
"learning_rate":
|
| 317 |
-
"loss": 1.
|
| 318 |
"step": 430
|
| 319 |
},
|
| 320 |
{
|
| 321 |
"epoch": 1.2571428571428571,
|
| 322 |
-
"grad_norm":
|
| 323 |
-
"learning_rate":
|
| 324 |
-
"loss":
|
| 325 |
"step": 440
|
| 326 |
},
|
| 327 |
{
|
| 328 |
"epoch": 1.2857142857142856,
|
| 329 |
-
"grad_norm":
|
| 330 |
-
"learning_rate":
|
| 331 |
-
"loss": 1.
|
| 332 |
"step": 450
|
| 333 |
},
|
| 334 |
{
|
| 335 |
"epoch": 1.3142857142857143,
|
| 336 |
-
"grad_norm":
|
| 337 |
-
"learning_rate":
|
| 338 |
-
"loss": 1.
|
| 339 |
"step": 460
|
| 340 |
},
|
| 341 |
{
|
| 342 |
"epoch": 1.342857142857143,
|
| 343 |
-
"grad_norm":
|
| 344 |
-
"learning_rate":
|
| 345 |
-
"loss": 1.
|
| 346 |
"step": 470
|
| 347 |
},
|
| 348 |
{
|
| 349 |
"epoch": 1.3714285714285714,
|
| 350 |
-
"grad_norm":
|
| 351 |
-
"learning_rate":
|
| 352 |
-
"loss": 1.
|
| 353 |
"step": 480
|
| 354 |
},
|
| 355 |
{
|
| 356 |
"epoch": 1.4,
|
| 357 |
-
"grad_norm":
|
| 358 |
-
"learning_rate":
|
| 359 |
-
"loss": 1.
|
| 360 |
"step": 490
|
| 361 |
},
|
| 362 |
{
|
| 363 |
"epoch": 1.4285714285714286,
|
| 364 |
-
"grad_norm":
|
| 365 |
-
"learning_rate":
|
| 366 |
-
"loss":
|
| 367 |
"step": 500
|
| 368 |
},
|
| 369 |
{
|
| 370 |
"epoch": 1.457142857142857,
|
| 371 |
-
"grad_norm":
|
| 372 |
-
"learning_rate":
|
| 373 |
-
"loss":
|
| 374 |
"step": 510
|
| 375 |
},
|
| 376 |
{
|
| 377 |
"epoch": 1.4857142857142858,
|
| 378 |
-
"grad_norm":
|
| 379 |
-
"learning_rate":
|
| 380 |
-
"loss":
|
| 381 |
"step": 520
|
| 382 |
},
|
| 383 |
{
|
| 384 |
"epoch": 1.5142857142857142,
|
| 385 |
-
"grad_norm":
|
| 386 |
-
"learning_rate":
|
| 387 |
-
"loss":
|
| 388 |
"step": 530
|
| 389 |
},
|
| 390 |
{
|
| 391 |
"epoch": 1.5428571428571427,
|
| 392 |
-
"grad_norm":
|
| 393 |
-
"learning_rate":
|
| 394 |
-
"loss": 1.
|
| 395 |
"step": 540
|
| 396 |
},
|
| 397 |
{
|
| 398 |
"epoch": 1.5714285714285714,
|
| 399 |
-
"grad_norm":
|
| 400 |
-
"learning_rate":
|
| 401 |
-
"loss":
|
| 402 |
"step": 550
|
| 403 |
},
|
| 404 |
{
|
| 405 |
"epoch": 1.6,
|
| 406 |
-
"grad_norm":
|
| 407 |
-
"learning_rate":
|
| 408 |
-
"loss": 1.
|
| 409 |
"step": 560
|
| 410 |
},
|
| 411 |
{
|
| 412 |
"epoch": 1.6285714285714286,
|
| 413 |
-
"grad_norm":
|
| 414 |
-
"learning_rate":
|
| 415 |
-
"loss": 1.
|
| 416 |
"step": 570
|
| 417 |
},
|
| 418 |
{
|
| 419 |
"epoch": 1.657142857142857,
|
| 420 |
-
"grad_norm":
|
| 421 |
-
"learning_rate":
|
| 422 |
-
"loss":
|
| 423 |
"step": 580
|
| 424 |
},
|
| 425 |
{
|
| 426 |
"epoch": 1.6857142857142857,
|
| 427 |
-
"grad_norm":
|
| 428 |
-
"learning_rate":
|
| 429 |
-
"loss": 1.
|
| 430 |
"step": 590
|
| 431 |
},
|
| 432 |
{
|
| 433 |
"epoch": 1.7142857142857144,
|
| 434 |
-
"grad_norm":
|
| 435 |
-
"learning_rate":
|
| 436 |
-
"loss":
|
| 437 |
"step": 600
|
| 438 |
},
|
| 439 |
{
|
| 440 |
"epoch": 1.7428571428571429,
|
| 441 |
-
"grad_norm":
|
| 442 |
-
"learning_rate":
|
| 443 |
-
"loss":
|
| 444 |
"step": 610
|
| 445 |
},
|
| 446 |
{
|
| 447 |
"epoch": 1.7714285714285714,
|
| 448 |
-
"grad_norm":
|
| 449 |
-
"learning_rate":
|
| 450 |
-
"loss":
|
| 451 |
"step": 620
|
| 452 |
},
|
| 453 |
{
|
| 454 |
"epoch": 1.8,
|
| 455 |
-
"grad_norm":
|
| 456 |
-
"learning_rate":
|
| 457 |
-
"loss": 1.
|
| 458 |
"step": 630
|
| 459 |
},
|
| 460 |
{
|
| 461 |
"epoch": 1.8285714285714287,
|
| 462 |
-
"grad_norm":
|
| 463 |
-
"learning_rate":
|
| 464 |
-
"loss": 1.
|
| 465 |
"step": 640
|
| 466 |
},
|
| 467 |
{
|
| 468 |
"epoch": 1.8571428571428572,
|
| 469 |
-
"grad_norm":
|
| 470 |
-
"learning_rate":
|
| 471 |
-
"loss":
|
| 472 |
"step": 650
|
| 473 |
},
|
| 474 |
{
|
| 475 |
"epoch": 1.8857142857142857,
|
| 476 |
-
"grad_norm":
|
| 477 |
-
"learning_rate":
|
| 478 |
-
"loss":
|
| 479 |
"step": 660
|
| 480 |
},
|
| 481 |
{
|
| 482 |
"epoch": 1.9142857142857141,
|
| 483 |
-
"grad_norm":
|
| 484 |
-
"learning_rate":
|
| 485 |
-
"loss":
|
| 486 |
"step": 670
|
| 487 |
},
|
| 488 |
{
|
| 489 |
"epoch": 1.9428571428571428,
|
| 490 |
-
"grad_norm":
|
| 491 |
-
"learning_rate":
|
| 492 |
-
"loss":
|
| 493 |
"step": 680
|
| 494 |
},
|
| 495 |
{
|
| 496 |
"epoch": 1.9714285714285715,
|
| 497 |
-
"grad_norm":
|
| 498 |
-
"learning_rate":
|
| 499 |
-
"loss":
|
| 500 |
"step": 690
|
| 501 |
},
|
| 502 |
{
|
| 503 |
"epoch": 2.0,
|
| 504 |
-
"grad_norm":
|
| 505 |
-
"learning_rate":
|
| 506 |
-
"loss":
|
| 507 |
"step": 700
|
| 508 |
},
|
| 509 |
{
|
| 510 |
"epoch": 2.0,
|
| 511 |
-
"eval_loss":
|
| 512 |
-
"eval_runtime": 16.
|
| 513 |
-
"eval_samples_per_second": 12.
|
| 514 |
-
"eval_steps_per_second": 1.
|
| 515 |
"step": 700
|
| 516 |
},
|
| 517 |
{
|
| 518 |
"epoch": 2.0285714285714285,
|
| 519 |
-
"grad_norm":
|
| 520 |
-
"learning_rate":
|
| 521 |
-
"loss":
|
| 522 |
"step": 710
|
| 523 |
},
|
| 524 |
{
|
| 525 |
"epoch": 2.057142857142857,
|
| 526 |
-
"grad_norm":
|
| 527 |
-
"learning_rate":
|
| 528 |
-
"loss":
|
| 529 |
"step": 720
|
| 530 |
},
|
| 531 |
{
|
| 532 |
"epoch": 2.085714285714286,
|
| 533 |
-
"grad_norm":
|
| 534 |
-
"learning_rate":
|
| 535 |
-
"loss":
|
| 536 |
"step": 730
|
| 537 |
},
|
| 538 |
{
|
| 539 |
"epoch": 2.1142857142857143,
|
| 540 |
-
"grad_norm":
|
| 541 |
-
"learning_rate":
|
| 542 |
-
"loss":
|
| 543 |
"step": 740
|
| 544 |
},
|
| 545 |
{
|
| 546 |
"epoch": 2.142857142857143,
|
| 547 |
-
"grad_norm":
|
| 548 |
-
"learning_rate":
|
| 549 |
-
"loss": 1.
|
| 550 |
"step": 750
|
| 551 |
},
|
| 552 |
{
|
| 553 |
"epoch": 2.1714285714285713,
|
| 554 |
-
"grad_norm":
|
| 555 |
-
"learning_rate":
|
| 556 |
-
"loss":
|
| 557 |
"step": 760
|
| 558 |
},
|
| 559 |
{
|
| 560 |
"epoch": 2.2,
|
| 561 |
-
"grad_norm":
|
| 562 |
-
"learning_rate":
|
| 563 |
-
"loss":
|
| 564 |
"step": 770
|
| 565 |
},
|
| 566 |
{
|
| 567 |
"epoch": 2.2285714285714286,
|
| 568 |
-
"grad_norm":
|
| 569 |
-
"learning_rate":
|
| 570 |
-
"loss":
|
| 571 |
"step": 780
|
| 572 |
},
|
| 573 |
{
|
| 574 |
"epoch": 2.257142857142857,
|
| 575 |
-
"grad_norm":
|
| 576 |
-
"learning_rate":
|
| 577 |
-
"loss":
|
| 578 |
"step": 790
|
| 579 |
},
|
| 580 |
{
|
| 581 |
"epoch": 2.2857142857142856,
|
| 582 |
-
"grad_norm":
|
| 583 |
-
"learning_rate":
|
| 584 |
-
"loss":
|
| 585 |
"step": 800
|
| 586 |
},
|
| 587 |
{
|
| 588 |
"epoch": 2.314285714285714,
|
| 589 |
-
"grad_norm":
|
| 590 |
-
"learning_rate":
|
| 591 |
-
"loss":
|
| 592 |
"step": 810
|
| 593 |
},
|
| 594 |
{
|
| 595 |
"epoch": 2.342857142857143,
|
| 596 |
-
"grad_norm":
|
| 597 |
-
"learning_rate":
|
| 598 |
-
"loss":
|
| 599 |
"step": 820
|
| 600 |
},
|
| 601 |
{
|
| 602 |
"epoch": 2.3714285714285714,
|
| 603 |
-
"grad_norm":
|
| 604 |
-
"learning_rate":
|
| 605 |
-
"loss":
|
| 606 |
"step": 830
|
| 607 |
},
|
| 608 |
{
|
| 609 |
"epoch": 2.4,
|
| 610 |
-
"grad_norm":
|
| 611 |
-
"learning_rate":
|
| 612 |
-
"loss":
|
| 613 |
"step": 840
|
| 614 |
},
|
| 615 |
{
|
| 616 |
"epoch": 2.4285714285714284,
|
| 617 |
-
"grad_norm":
|
| 618 |
-
"learning_rate":
|
| 619 |
-
"loss":
|
| 620 |
"step": 850
|
| 621 |
},
|
| 622 |
{
|
| 623 |
"epoch": 2.4571428571428573,
|
| 624 |
-
"grad_norm":
|
| 625 |
-
"learning_rate":
|
| 626 |
-
"loss":
|
| 627 |
"step": 860
|
| 628 |
},
|
| 629 |
{
|
| 630 |
"epoch": 2.4857142857142858,
|
| 631 |
-
"grad_norm":
|
| 632 |
-
"learning_rate":
|
| 633 |
-
"loss":
|
| 634 |
"step": 870
|
| 635 |
},
|
| 636 |
{
|
| 637 |
"epoch": 2.5142857142857142,
|
| 638 |
-
"grad_norm":
|
| 639 |
-
"learning_rate":
|
| 640 |
-
"loss":
|
| 641 |
"step": 880
|
| 642 |
},
|
| 643 |
{
|
| 644 |
"epoch": 2.5428571428571427,
|
| 645 |
-
"grad_norm":
|
| 646 |
-
"learning_rate":
|
| 647 |
-
"loss":
|
| 648 |
"step": 890
|
| 649 |
},
|
| 650 |
{
|
| 651 |
"epoch": 2.571428571428571,
|
| 652 |
-
"grad_norm":
|
| 653 |
-
"learning_rate":
|
| 654 |
-
"loss":
|
| 655 |
"step": 900
|
| 656 |
},
|
| 657 |
{
|
| 658 |
"epoch": 2.6,
|
| 659 |
-
"grad_norm":
|
| 660 |
-
"learning_rate":
|
| 661 |
-
"loss":
|
| 662 |
"step": 910
|
| 663 |
},
|
| 664 |
{
|
| 665 |
"epoch": 2.6285714285714286,
|
| 666 |
-
"grad_norm":
|
| 667 |
-
"learning_rate":
|
| 668 |
-
"loss":
|
| 669 |
"step": 920
|
| 670 |
},
|
| 671 |
{
|
| 672 |
"epoch": 2.657142857142857,
|
| 673 |
-
"grad_norm":
|
| 674 |
-
"learning_rate":
|
| 675 |
-
"loss":
|
| 676 |
"step": 930
|
| 677 |
},
|
| 678 |
{
|
| 679 |
"epoch": 2.685714285714286,
|
| 680 |
-
"grad_norm":
|
| 681 |
-
"learning_rate":
|
| 682 |
-
"loss":
|
| 683 |
"step": 940
|
| 684 |
},
|
| 685 |
{
|
| 686 |
"epoch": 2.7142857142857144,
|
| 687 |
-
"grad_norm":
|
| 688 |
-
"learning_rate":
|
| 689 |
-
"loss":
|
| 690 |
"step": 950
|
| 691 |
},
|
| 692 |
{
|
| 693 |
"epoch": 2.742857142857143,
|
| 694 |
-
"grad_norm":
|
| 695 |
-
"learning_rate":
|
| 696 |
-
"loss":
|
| 697 |
"step": 960
|
| 698 |
},
|
| 699 |
{
|
| 700 |
"epoch": 2.7714285714285714,
|
| 701 |
-
"grad_norm":
|
| 702 |
-
"learning_rate":
|
| 703 |
-
"loss":
|
| 704 |
"step": 970
|
| 705 |
},
|
| 706 |
{
|
| 707 |
"epoch": 2.8,
|
| 708 |
-
"grad_norm":
|
| 709 |
-
"learning_rate":
|
| 710 |
-
"loss":
|
| 711 |
"step": 980
|
| 712 |
},
|
| 713 |
{
|
| 714 |
"epoch": 2.8285714285714287,
|
| 715 |
-
"grad_norm":
|
| 716 |
-
"learning_rate":
|
| 717 |
-
"loss":
|
| 718 |
"step": 990
|
| 719 |
},
|
| 720 |
{
|
| 721 |
"epoch": 2.857142857142857,
|
| 722 |
-
"grad_norm":
|
| 723 |
-
"learning_rate":
|
| 724 |
-
"loss":
|
| 725 |
"step": 1000
|
| 726 |
},
|
| 727 |
{
|
| 728 |
"epoch": 2.8857142857142857,
|
| 729 |
-
"grad_norm":
|
| 730 |
-
"learning_rate":
|
| 731 |
-
"loss":
|
| 732 |
"step": 1010
|
| 733 |
},
|
| 734 |
{
|
| 735 |
"epoch": 2.914285714285714,
|
| 736 |
-
"grad_norm":
|
| 737 |
-
"learning_rate":
|
| 738 |
-
"loss":
|
| 739 |
"step": 1020
|
| 740 |
},
|
| 741 |
{
|
| 742 |
"epoch": 2.942857142857143,
|
| 743 |
-
"grad_norm":
|
| 744 |
-
"learning_rate":
|
| 745 |
-
"loss":
|
| 746 |
"step": 1030
|
| 747 |
},
|
| 748 |
{
|
| 749 |
"epoch": 2.9714285714285715,
|
| 750 |
-
"grad_norm":
|
| 751 |
-
"learning_rate":
|
| 752 |
-
"loss":
|
| 753 |
"step": 1040
|
| 754 |
},
|
| 755 |
{
|
| 756 |
"epoch": 3.0,
|
| 757 |
-
"grad_norm":
|
| 758 |
"learning_rate": 0.0,
|
| 759 |
-
"loss":
|
| 760 |
"step": 1050
|
| 761 |
},
|
| 762 |
{
|
| 763 |
"epoch": 3.0,
|
| 764 |
-
"eval_loss":
|
| 765 |
-
"eval_runtime": 16.
|
| 766 |
-
"eval_samples_per_second": 12.
|
| 767 |
-
"eval_steps_per_second": 1.
|
| 768 |
"step": 1050
|
| 769 |
}
|
| 770 |
],
|
|
@@ -785,7 +785,7 @@
|
|
| 785 |
"attributes": {}
|
| 786 |
}
|
| 787 |
},
|
| 788 |
-
"total_flos":
|
| 789 |
"train_batch_size": 8,
|
| 790 |
"trial_name": null,
|
| 791 |
"trial_params": null
|
|
|
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 0.02857142857142857,
|
| 13 |
+
"grad_norm": 5.210493087768555,
|
| 14 |
+
"learning_rate": 0.0004952380952380952,
|
| 15 |
+
"loss": 4.4131,
|
| 16 |
"step": 10
|
| 17 |
},
|
| 18 |
{
|
| 19 |
"epoch": 0.05714285714285714,
|
| 20 |
+
"grad_norm": 3.571948528289795,
|
| 21 |
+
"learning_rate": 0.0004904761904761905,
|
| 22 |
+
"loss": 2.5476,
|
| 23 |
"step": 20
|
| 24 |
},
|
| 25 |
{
|
| 26 |
"epoch": 0.08571428571428572,
|
| 27 |
+
"grad_norm": 2.640848398208618,
|
| 28 |
+
"learning_rate": 0.0004857142857142857,
|
| 29 |
+
"loss": 2.2491,
|
| 30 |
"step": 30
|
| 31 |
},
|
| 32 |
{
|
| 33 |
"epoch": 0.11428571428571428,
|
| 34 |
+
"grad_norm": 2.6611335277557373,
|
| 35 |
+
"learning_rate": 0.00048095238095238095,
|
| 36 |
+
"loss": 2.0477,
|
| 37 |
"step": 40
|
| 38 |
},
|
| 39 |
{
|
| 40 |
"epoch": 0.14285714285714285,
|
| 41 |
+
"grad_norm": 2.608750581741333,
|
| 42 |
+
"learning_rate": 0.0004761904761904762,
|
| 43 |
+
"loss": 2.028,
|
| 44 |
"step": 50
|
| 45 |
},
|
| 46 |
{
|
| 47 |
"epoch": 0.17142857142857143,
|
| 48 |
+
"grad_norm": 5.034807205200195,
|
| 49 |
+
"learning_rate": 0.0004714285714285714,
|
| 50 |
+
"loss": 1.7871,
|
| 51 |
"step": 60
|
| 52 |
},
|
| 53 |
{
|
| 54 |
"epoch": 0.2,
|
| 55 |
+
"grad_norm": 3.5893642902374268,
|
| 56 |
+
"learning_rate": 0.00046666666666666666,
|
| 57 |
+
"loss": 1.7879,
|
| 58 |
"step": 70
|
| 59 |
},
|
| 60 |
{
|
| 61 |
"epoch": 0.22857142857142856,
|
| 62 |
+
"grad_norm": 5.368953227996826,
|
| 63 |
+
"learning_rate": 0.00046190476190476195,
|
| 64 |
+
"loss": 1.8194,
|
| 65 |
"step": 80
|
| 66 |
},
|
| 67 |
{
|
| 68 |
"epoch": 0.2571428571428571,
|
| 69 |
+
"grad_norm": 3.7377731800079346,
|
| 70 |
+
"learning_rate": 0.00045714285714285713,
|
| 71 |
+
"loss": 1.6159,
|
| 72 |
"step": 90
|
| 73 |
},
|
| 74 |
{
|
| 75 |
"epoch": 0.2857142857142857,
|
| 76 |
+
"grad_norm": 7.883308410644531,
|
| 77 |
+
"learning_rate": 0.00045238095238095237,
|
| 78 |
+
"loss": 1.6244,
|
| 79 |
"step": 100
|
| 80 |
},
|
| 81 |
{
|
| 82 |
"epoch": 0.3142857142857143,
|
| 83 |
+
"grad_norm": 4.968689918518066,
|
| 84 |
+
"learning_rate": 0.00044761904761904766,
|
| 85 |
+
"loss": 1.6614,
|
| 86 |
"step": 110
|
| 87 |
},
|
| 88 |
{
|
| 89 |
"epoch": 0.34285714285714286,
|
| 90 |
+
"grad_norm": 2.592766046524048,
|
| 91 |
+
"learning_rate": 0.00044285714285714284,
|
| 92 |
+
"loss": 1.349,
|
| 93 |
"step": 120
|
| 94 |
},
|
| 95 |
{
|
| 96 |
"epoch": 0.37142857142857144,
|
| 97 |
+
"grad_norm": 2.783951997756958,
|
| 98 |
+
"learning_rate": 0.0004380952380952381,
|
| 99 |
+
"loss": 1.5065,
|
| 100 |
"step": 130
|
| 101 |
},
|
| 102 |
{
|
| 103 |
"epoch": 0.4,
|
| 104 |
+
"grad_norm": 5.2810378074646,
|
| 105 |
+
"learning_rate": 0.00043333333333333337,
|
| 106 |
+
"loss": 1.3934,
|
| 107 |
"step": 140
|
| 108 |
},
|
| 109 |
{
|
| 110 |
"epoch": 0.42857142857142855,
|
| 111 |
+
"grad_norm": 4.448086261749268,
|
| 112 |
+
"learning_rate": 0.00042857142857142855,
|
| 113 |
+
"loss": 1.5198,
|
| 114 |
"step": 150
|
| 115 |
},
|
| 116 |
{
|
| 117 |
"epoch": 0.45714285714285713,
|
| 118 |
+
"grad_norm": 3.211707353591919,
|
| 119 |
+
"learning_rate": 0.0004238095238095238,
|
| 120 |
+
"loss": 1.6207,
|
| 121 |
"step": 160
|
| 122 |
},
|
| 123 |
{
|
| 124 |
"epoch": 0.4857142857142857,
|
| 125 |
+
"grad_norm": 3.586463212966919,
|
| 126 |
+
"learning_rate": 0.0004190476190476191,
|
| 127 |
+
"loss": 1.2687,
|
| 128 |
"step": 170
|
| 129 |
},
|
| 130 |
{
|
| 131 |
"epoch": 0.5142857142857142,
|
| 132 |
+
"grad_norm": 2.6598610877990723,
|
| 133 |
+
"learning_rate": 0.0004142857142857143,
|
| 134 |
+
"loss": 1.3957,
|
| 135 |
"step": 180
|
| 136 |
},
|
| 137 |
{
|
| 138 |
"epoch": 0.5428571428571428,
|
| 139 |
+
"grad_norm": 3.480663776397705,
|
| 140 |
+
"learning_rate": 0.00040952380952380955,
|
| 141 |
+
"loss": 1.3543,
|
| 142 |
"step": 190
|
| 143 |
},
|
| 144 |
{
|
| 145 |
"epoch": 0.5714285714285714,
|
| 146 |
+
"grad_norm": 3.168818712234497,
|
| 147 |
+
"learning_rate": 0.0004047619047619048,
|
| 148 |
+
"loss": 1.2619,
|
| 149 |
"step": 200
|
| 150 |
},
|
| 151 |
{
|
| 152 |
"epoch": 0.6,
|
| 153 |
+
"grad_norm": 2.7529921531677246,
|
| 154 |
+
"learning_rate": 0.0004,
|
| 155 |
+
"loss": 1.1871,
|
| 156 |
"step": 210
|
| 157 |
},
|
| 158 |
{
|
| 159 |
"epoch": 0.6285714285714286,
|
| 160 |
+
"grad_norm": 6.538937568664551,
|
| 161 |
+
"learning_rate": 0.00039523809523809526,
|
| 162 |
+
"loss": 1.268,
|
| 163 |
"step": 220
|
| 164 |
},
|
| 165 |
{
|
| 166 |
"epoch": 0.6571428571428571,
|
| 167 |
+
"grad_norm": 3.3910727500915527,
|
| 168 |
+
"learning_rate": 0.0003904761904761905,
|
| 169 |
+
"loss": 1.4192,
|
| 170 |
"step": 230
|
| 171 |
},
|
| 172 |
{
|
| 173 |
"epoch": 0.6857142857142857,
|
| 174 |
+
"grad_norm": 2.31817889213562,
|
| 175 |
+
"learning_rate": 0.0003857142857142857,
|
| 176 |
+
"loss": 1.2339,
|
| 177 |
"step": 240
|
| 178 |
},
|
| 179 |
{
|
| 180 |
"epoch": 0.7142857142857143,
|
| 181 |
+
"grad_norm": 2.8181235790252686,
|
| 182 |
+
"learning_rate": 0.00038095238095238096,
|
| 183 |
+
"loss": 1.3153,
|
| 184 |
"step": 250
|
| 185 |
},
|
| 186 |
{
|
| 187 |
"epoch": 0.7428571428571429,
|
| 188 |
+
"grad_norm": 2.5716922283172607,
|
| 189 |
+
"learning_rate": 0.0003761904761904762,
|
| 190 |
+
"loss": 1.2066,
|
| 191 |
"step": 260
|
| 192 |
},
|
| 193 |
{
|
| 194 |
"epoch": 0.7714285714285715,
|
| 195 |
+
"grad_norm": 5.403870105743408,
|
| 196 |
+
"learning_rate": 0.00037142857142857143,
|
| 197 |
+
"loss": 1.2784,
|
| 198 |
"step": 270
|
| 199 |
},
|
| 200 |
{
|
| 201 |
"epoch": 0.8,
|
| 202 |
+
"grad_norm": 3.347729206085205,
|
| 203 |
+
"learning_rate": 0.00036666666666666667,
|
| 204 |
+
"loss": 1.2273,
|
| 205 |
"step": 280
|
| 206 |
},
|
| 207 |
{
|
| 208 |
"epoch": 0.8285714285714286,
|
| 209 |
+
"grad_norm": 2.7995996475219727,
|
| 210 |
+
"learning_rate": 0.0003619047619047619,
|
| 211 |
+
"loss": 1.159,
|
| 212 |
"step": 290
|
| 213 |
},
|
| 214 |
{
|
| 215 |
"epoch": 0.8571428571428571,
|
| 216 |
+
"grad_norm": 3.817213535308838,
|
| 217 |
+
"learning_rate": 0.00035714285714285714,
|
| 218 |
+
"loss": 1.1146,
|
| 219 |
"step": 300
|
| 220 |
},
|
| 221 |
{
|
| 222 |
"epoch": 0.8857142857142857,
|
| 223 |
+
"grad_norm": 3.3239715099334717,
|
| 224 |
+
"learning_rate": 0.00035238095238095243,
|
| 225 |
+
"loss": 1.1513,
|
| 226 |
"step": 310
|
| 227 |
},
|
| 228 |
{
|
| 229 |
"epoch": 0.9142857142857143,
|
| 230 |
+
"grad_norm": 3.042973518371582,
|
| 231 |
+
"learning_rate": 0.0003476190476190476,
|
| 232 |
+
"loss": 1.3906,
|
| 233 |
"step": 320
|
| 234 |
},
|
| 235 |
{
|
| 236 |
"epoch": 0.9428571428571428,
|
| 237 |
+
"grad_norm": 2.8079681396484375,
|
| 238 |
+
"learning_rate": 0.00034285714285714285,
|
| 239 |
+
"loss": 1.1547,
|
| 240 |
"step": 330
|
| 241 |
},
|
| 242 |
{
|
| 243 |
"epoch": 0.9714285714285714,
|
| 244 |
+
"grad_norm": 6.39453649520874,
|
| 245 |
+
"learning_rate": 0.00033809523809523814,
|
| 246 |
+
"loss": 1.0989,
|
| 247 |
"step": 340
|
| 248 |
},
|
| 249 |
{
|
| 250 |
"epoch": 1.0,
|
| 251 |
+
"grad_norm": 5.739945411682129,
|
| 252 |
+
"learning_rate": 0.0003333333333333333,
|
| 253 |
+
"loss": 1.1563,
|
| 254 |
"step": 350
|
| 255 |
},
|
| 256 |
{
|
| 257 |
"epoch": 1.0,
|
| 258 |
+
"eval_loss": 1.064656376838684,
|
| 259 |
+
"eval_runtime": 16.5324,
|
| 260 |
+
"eval_samples_per_second": 12.097,
|
| 261 |
+
"eval_steps_per_second": 1.512,
|
| 262 |
"step": 350
|
| 263 |
},
|
| 264 |
{
|
| 265 |
"epoch": 1.0285714285714285,
|
| 266 |
+
"grad_norm": 5.899299144744873,
|
| 267 |
+
"learning_rate": 0.00032857142857142856,
|
| 268 |
+
"loss": 1.0649,
|
| 269 |
"step": 360
|
| 270 |
},
|
| 271 |
{
|
| 272 |
"epoch": 1.0571428571428572,
|
| 273 |
+
"grad_norm": 3.3639721870422363,
|
| 274 |
+
"learning_rate": 0.00032380952380952385,
|
| 275 |
+
"loss": 1.1595,
|
| 276 |
"step": 370
|
| 277 |
},
|
| 278 |
{
|
| 279 |
"epoch": 1.0857142857142856,
|
| 280 |
+
"grad_norm": 2.811561346054077,
|
| 281 |
+
"learning_rate": 0.00031904761904761903,
|
| 282 |
+
"loss": 1.0871,
|
| 283 |
"step": 380
|
| 284 |
},
|
| 285 |
{
|
| 286 |
"epoch": 1.1142857142857143,
|
| 287 |
+
"grad_norm": 2.6730055809020996,
|
| 288 |
+
"learning_rate": 0.00031428571428571427,
|
| 289 |
+
"loss": 1.0294,
|
| 290 |
"step": 390
|
| 291 |
},
|
| 292 |
{
|
| 293 |
"epoch": 1.1428571428571428,
|
| 294 |
+
"grad_norm": 5.02337646484375,
|
| 295 |
+
"learning_rate": 0.00030952380952380956,
|
| 296 |
+
"loss": 1.0844,
|
| 297 |
"step": 400
|
| 298 |
},
|
| 299 |
{
|
| 300 |
"epoch": 1.1714285714285715,
|
| 301 |
+
"grad_norm": 4.188799858093262,
|
| 302 |
+
"learning_rate": 0.0003047619047619048,
|
| 303 |
+
"loss": 1.0464,
|
| 304 |
"step": 410
|
| 305 |
},
|
| 306 |
{
|
| 307 |
"epoch": 1.2,
|
| 308 |
+
"grad_norm": 5.055841445922852,
|
| 309 |
+
"learning_rate": 0.0003,
|
| 310 |
+
"loss": 1.1078,
|
| 311 |
"step": 420
|
| 312 |
},
|
| 313 |
{
|
| 314 |
"epoch": 1.2285714285714286,
|
| 315 |
+
"grad_norm": 8.09494400024414,
|
| 316 |
+
"learning_rate": 0.00029523809523809526,
|
| 317 |
+
"loss": 1.0539,
|
| 318 |
"step": 430
|
| 319 |
},
|
| 320 |
{
|
| 321 |
"epoch": 1.2571428571428571,
|
| 322 |
+
"grad_norm": 3.012653112411499,
|
| 323 |
+
"learning_rate": 0.0002904761904761905,
|
| 324 |
+
"loss": 0.927,
|
| 325 |
"step": 440
|
| 326 |
},
|
| 327 |
{
|
| 328 |
"epoch": 1.2857142857142856,
|
| 329 |
+
"grad_norm": 8.38936710357666,
|
| 330 |
+
"learning_rate": 0.0002857142857142857,
|
| 331 |
+
"loss": 1.2209,
|
| 332 |
"step": 450
|
| 333 |
},
|
| 334 |
{
|
| 335 |
"epoch": 1.3142857142857143,
|
| 336 |
+
"grad_norm": 4.191105365753174,
|
| 337 |
+
"learning_rate": 0.00028095238095238097,
|
| 338 |
+
"loss": 1.0086,
|
| 339 |
"step": 460
|
| 340 |
},
|
| 341 |
{
|
| 342 |
"epoch": 1.342857142857143,
|
| 343 |
+
"grad_norm": 2.9886045455932617,
|
| 344 |
+
"learning_rate": 0.0002761904761904762,
|
| 345 |
+
"loss": 1.0788,
|
| 346 |
"step": 470
|
| 347 |
},
|
| 348 |
{
|
| 349 |
"epoch": 1.3714285714285714,
|
| 350 |
+
"grad_norm": 3.5892975330352783,
|
| 351 |
+
"learning_rate": 0.0002714285714285714,
|
| 352 |
+
"loss": 1.0877,
|
| 353 |
"step": 480
|
| 354 |
},
|
| 355 |
{
|
| 356 |
"epoch": 1.4,
|
| 357 |
+
"grad_norm": 4.504238128662109,
|
| 358 |
+
"learning_rate": 0.0002666666666666667,
|
| 359 |
+
"loss": 1.0066,
|
| 360 |
"step": 490
|
| 361 |
},
|
| 362 |
{
|
| 363 |
"epoch": 1.4285714285714286,
|
| 364 |
+
"grad_norm": 3.601853132247925,
|
| 365 |
+
"learning_rate": 0.0002619047619047619,
|
| 366 |
+
"loss": 0.9915,
|
| 367 |
"step": 500
|
| 368 |
},
|
| 369 |
{
|
| 370 |
"epoch": 1.457142857142857,
|
| 371 |
+
"grad_norm": 4.008484840393066,
|
| 372 |
+
"learning_rate": 0.0002571428571428571,
|
| 373 |
+
"loss": 0.9651,
|
| 374 |
"step": 510
|
| 375 |
},
|
| 376 |
{
|
| 377 |
"epoch": 1.4857142857142858,
|
| 378 |
+
"grad_norm": 5.5403900146484375,
|
| 379 |
+
"learning_rate": 0.0002523809523809524,
|
| 380 |
+
"loss": 0.9018,
|
| 381 |
"step": 520
|
| 382 |
},
|
| 383 |
{
|
| 384 |
"epoch": 1.5142857142857142,
|
| 385 |
+
"grad_norm": 3.526982069015503,
|
| 386 |
+
"learning_rate": 0.0002476190476190476,
|
| 387 |
+
"loss": 0.9588,
|
| 388 |
"step": 530
|
| 389 |
},
|
| 390 |
{
|
| 391 |
"epoch": 1.5428571428571427,
|
| 392 |
+
"grad_norm": 3.666804075241089,
|
| 393 |
+
"learning_rate": 0.00024285714285714286,
|
| 394 |
+
"loss": 1.0092,
|
| 395 |
"step": 540
|
| 396 |
},
|
| 397 |
{
|
| 398 |
"epoch": 1.5714285714285714,
|
| 399 |
+
"grad_norm": 3.4340310096740723,
|
| 400 |
+
"learning_rate": 0.0002380952380952381,
|
| 401 |
+
"loss": 0.9342,
|
| 402 |
"step": 550
|
| 403 |
},
|
| 404 |
{
|
| 405 |
"epoch": 1.6,
|
| 406 |
+
"grad_norm": 5.815408229827881,
|
| 407 |
+
"learning_rate": 0.00023333333333333333,
|
| 408 |
+
"loss": 1.0666,
|
| 409 |
"step": 560
|
| 410 |
},
|
| 411 |
{
|
| 412 |
"epoch": 1.6285714285714286,
|
| 413 |
+
"grad_norm": 2.7780840396881104,
|
| 414 |
+
"learning_rate": 0.00022857142857142857,
|
| 415 |
+
"loss": 1.1026,
|
| 416 |
"step": 570
|
| 417 |
},
|
| 418 |
{
|
| 419 |
"epoch": 1.657142857142857,
|
| 420 |
+
"grad_norm": 3.8484044075012207,
|
| 421 |
+
"learning_rate": 0.00022380952380952383,
|
| 422 |
+
"loss": 0.937,
|
| 423 |
"step": 580
|
| 424 |
},
|
| 425 |
{
|
| 426 |
"epoch": 1.6857142857142857,
|
| 427 |
+
"grad_norm": 3.819007635116577,
|
| 428 |
+
"learning_rate": 0.00021904761904761904,
|
| 429 |
+
"loss": 1.1247,
|
| 430 |
"step": 590
|
| 431 |
},
|
| 432 |
{
|
| 433 |
"epoch": 1.7142857142857144,
|
| 434 |
+
"grad_norm": 3.8324477672576904,
|
| 435 |
+
"learning_rate": 0.00021428571428571427,
|
| 436 |
+
"loss": 0.9961,
|
| 437 |
"step": 600
|
| 438 |
},
|
| 439 |
{
|
| 440 |
"epoch": 1.7428571428571429,
|
| 441 |
+
"grad_norm": 3.2769389152526855,
|
| 442 |
+
"learning_rate": 0.00020952380952380954,
|
| 443 |
+
"loss": 0.9987,
|
| 444 |
"step": 610
|
| 445 |
},
|
| 446 |
{
|
| 447 |
"epoch": 1.7714285714285714,
|
| 448 |
+
"grad_norm": 5.3248443603515625,
|
| 449 |
+
"learning_rate": 0.00020476190476190477,
|
| 450 |
+
"loss": 0.9219,
|
| 451 |
"step": 620
|
| 452 |
},
|
| 453 |
{
|
| 454 |
"epoch": 1.8,
|
| 455 |
+
"grad_norm": 2.6656081676483154,
|
| 456 |
+
"learning_rate": 0.0002,
|
| 457 |
+
"loss": 1.0293,
|
| 458 |
"step": 630
|
| 459 |
},
|
| 460 |
{
|
| 461 |
"epoch": 1.8285714285714287,
|
| 462 |
+
"grad_norm": 2.6429567337036133,
|
| 463 |
+
"learning_rate": 0.00019523809523809525,
|
| 464 |
+
"loss": 1.0106,
|
| 465 |
"step": 640
|
| 466 |
},
|
| 467 |
{
|
| 468 |
"epoch": 1.8571428571428572,
|
| 469 |
+
"grad_norm": 4.4341864585876465,
|
| 470 |
+
"learning_rate": 0.00019047619047619048,
|
| 471 |
+
"loss": 0.8426,
|
| 472 |
"step": 650
|
| 473 |
},
|
| 474 |
{
|
| 475 |
"epoch": 1.8857142857142857,
|
| 476 |
+
"grad_norm": 4.535873889923096,
|
| 477 |
+
"learning_rate": 0.00018571428571428572,
|
| 478 |
+
"loss": 0.9335,
|
| 479 |
"step": 660
|
| 480 |
},
|
| 481 |
{
|
| 482 |
"epoch": 1.9142857142857141,
|
| 483 |
+
"grad_norm": 4.100979328155518,
|
| 484 |
+
"learning_rate": 0.00018095238095238095,
|
| 485 |
+
"loss": 0.9936,
|
| 486 |
"step": 670
|
| 487 |
},
|
| 488 |
{
|
| 489 |
"epoch": 1.9428571428571428,
|
| 490 |
+
"grad_norm": 4.034025192260742,
|
| 491 |
+
"learning_rate": 0.00017619047619047622,
|
| 492 |
+
"loss": 0.9305,
|
| 493 |
"step": 680
|
| 494 |
},
|
| 495 |
{
|
| 496 |
"epoch": 1.9714285714285715,
|
| 497 |
+
"grad_norm": 3.618300676345825,
|
| 498 |
+
"learning_rate": 0.00017142857142857143,
|
| 499 |
+
"loss": 0.975,
|
| 500 |
"step": 690
|
| 501 |
},
|
| 502 |
{
|
| 503 |
"epoch": 2.0,
|
| 504 |
+
"grad_norm": 3.0254437923431396,
|
| 505 |
+
"learning_rate": 0.00016666666666666666,
|
| 506 |
+
"loss": 0.997,
|
| 507 |
"step": 700
|
| 508 |
},
|
| 509 |
{
|
| 510 |
"epoch": 2.0,
|
| 511 |
+
"eval_loss": 0.893572211265564,
|
| 512 |
+
"eval_runtime": 16.613,
|
| 513 |
+
"eval_samples_per_second": 12.039,
|
| 514 |
+
"eval_steps_per_second": 1.505,
|
| 515 |
"step": 700
|
| 516 |
},
|
| 517 |
{
|
| 518 |
"epoch": 2.0285714285714285,
|
| 519 |
+
"grad_norm": 2.8559610843658447,
|
| 520 |
+
"learning_rate": 0.00016190476190476192,
|
| 521 |
+
"loss": 0.8578,
|
| 522 |
"step": 710
|
| 523 |
},
|
| 524 |
{
|
| 525 |
"epoch": 2.057142857142857,
|
| 526 |
+
"grad_norm": 2.623955488204956,
|
| 527 |
+
"learning_rate": 0.00015714285714285713,
|
| 528 |
+
"loss": 0.8208,
|
| 529 |
"step": 720
|
| 530 |
},
|
| 531 |
{
|
| 532 |
"epoch": 2.085714285714286,
|
| 533 |
+
"grad_norm": 4.081460475921631,
|
| 534 |
+
"learning_rate": 0.0001523809523809524,
|
| 535 |
+
"loss": 0.8064,
|
| 536 |
"step": 730
|
| 537 |
},
|
| 538 |
{
|
| 539 |
"epoch": 2.1142857142857143,
|
| 540 |
+
"grad_norm": 4.917724609375,
|
| 541 |
+
"learning_rate": 0.00014761904761904763,
|
| 542 |
+
"loss": 0.8172,
|
| 543 |
"step": 740
|
| 544 |
},
|
| 545 |
{
|
| 546 |
"epoch": 2.142857142857143,
|
| 547 |
+
"grad_norm": 5.27565336227417,
|
| 548 |
+
"learning_rate": 0.00014285714285714284,
|
| 549 |
+
"loss": 1.0486,
|
| 550 |
"step": 750
|
| 551 |
},
|
| 552 |
{
|
| 553 |
"epoch": 2.1714285714285713,
|
| 554 |
+
"grad_norm": 4.373621463775635,
|
| 555 |
+
"learning_rate": 0.0001380952380952381,
|
| 556 |
+
"loss": 0.8948,
|
| 557 |
"step": 760
|
| 558 |
},
|
| 559 |
{
|
| 560 |
"epoch": 2.2,
|
| 561 |
+
"grad_norm": 3.5879688262939453,
|
| 562 |
+
"learning_rate": 0.00013333333333333334,
|
| 563 |
+
"loss": 0.8612,
|
| 564 |
"step": 770
|
| 565 |
},
|
| 566 |
{
|
| 567 |
"epoch": 2.2285714285714286,
|
| 568 |
+
"grad_norm": 3.1236374378204346,
|
| 569 |
+
"learning_rate": 0.00012857142857142855,
|
| 570 |
+
"loss": 0.906,
|
| 571 |
"step": 780
|
| 572 |
},
|
| 573 |
{
|
| 574 |
"epoch": 2.257142857142857,
|
| 575 |
+
"grad_norm": 3.8395140171051025,
|
| 576 |
+
"learning_rate": 0.0001238095238095238,
|
| 577 |
+
"loss": 0.7673,
|
| 578 |
"step": 790
|
| 579 |
},
|
| 580 |
{
|
| 581 |
"epoch": 2.2857142857142856,
|
| 582 |
+
"grad_norm": 3.8085057735443115,
|
| 583 |
+
"learning_rate": 0.00011904761904761905,
|
| 584 |
+
"loss": 0.8075,
|
| 585 |
"step": 800
|
| 586 |
},
|
| 587 |
{
|
| 588 |
"epoch": 2.314285714285714,
|
| 589 |
+
"grad_norm": 3.388486385345459,
|
| 590 |
+
"learning_rate": 0.00011428571428571428,
|
| 591 |
+
"loss": 0.8651,
|
| 592 |
"step": 810
|
| 593 |
},
|
| 594 |
{
|
| 595 |
"epoch": 2.342857142857143,
|
| 596 |
+
"grad_norm": 3.3502166271209717,
|
| 597 |
+
"learning_rate": 0.00010952380952380952,
|
| 598 |
+
"loss": 0.8036,
|
| 599 |
"step": 820
|
| 600 |
},
|
| 601 |
{
|
| 602 |
"epoch": 2.3714285714285714,
|
| 603 |
+
"grad_norm": 3.833613634109497,
|
| 604 |
+
"learning_rate": 0.00010476190476190477,
|
| 605 |
+
"loss": 0.9703,
|
| 606 |
"step": 830
|
| 607 |
},
|
| 608 |
{
|
| 609 |
"epoch": 2.4,
|
| 610 |
+
"grad_norm": 3.7099878787994385,
|
| 611 |
+
"learning_rate": 0.0001,
|
| 612 |
+
"loss": 0.8167,
|
| 613 |
"step": 840
|
| 614 |
},
|
| 615 |
{
|
| 616 |
"epoch": 2.4285714285714284,
|
| 617 |
+
"grad_norm": 6.892563343048096,
|
| 618 |
+
"learning_rate": 9.523809523809524e-05,
|
| 619 |
+
"loss": 0.7719,
|
| 620 |
"step": 850
|
| 621 |
},
|
| 622 |
{
|
| 623 |
"epoch": 2.4571428571428573,
|
| 624 |
+
"grad_norm": 4.409047603607178,
|
| 625 |
+
"learning_rate": 9.047619047619048e-05,
|
| 626 |
+
"loss": 0.9031,
|
| 627 |
"step": 860
|
| 628 |
},
|
| 629 |
{
|
| 630 |
"epoch": 2.4857142857142858,
|
| 631 |
+
"grad_norm": 1.9474296569824219,
|
| 632 |
+
"learning_rate": 8.571428571428571e-05,
|
| 633 |
+
"loss": 0.9334,
|
| 634 |
"step": 870
|
| 635 |
},
|
| 636 |
{
|
| 637 |
"epoch": 2.5142857142857142,
|
| 638 |
+
"grad_norm": 2.9493942260742188,
|
| 639 |
+
"learning_rate": 8.095238095238096e-05,
|
| 640 |
+
"loss": 0.8624,
|
| 641 |
"step": 880
|
| 642 |
},
|
| 643 |
{
|
| 644 |
"epoch": 2.5428571428571427,
|
| 645 |
+
"grad_norm": 4.493179798126221,
|
| 646 |
+
"learning_rate": 7.61904761904762e-05,
|
| 647 |
+
"loss": 0.9769,
|
| 648 |
"step": 890
|
| 649 |
},
|
| 650 |
{
|
| 651 |
"epoch": 2.571428571428571,
|
| 652 |
+
"grad_norm": 5.590090751647949,
|
| 653 |
+
"learning_rate": 7.142857142857142e-05,
|
| 654 |
+
"loss": 0.6596,
|
| 655 |
"step": 900
|
| 656 |
},
|
| 657 |
{
|
| 658 |
"epoch": 2.6,
|
| 659 |
+
"grad_norm": 2.4073421955108643,
|
| 660 |
+
"learning_rate": 6.666666666666667e-05,
|
| 661 |
+
"loss": 0.8155,
|
| 662 |
"step": 910
|
| 663 |
},
|
| 664 |
{
|
| 665 |
"epoch": 2.6285714285714286,
|
| 666 |
+
"grad_norm": 3.83565092086792,
|
| 667 |
+
"learning_rate": 6.19047619047619e-05,
|
| 668 |
+
"loss": 0.8871,
|
| 669 |
"step": 920
|
| 670 |
},
|
| 671 |
{
|
| 672 |
"epoch": 2.657142857142857,
|
| 673 |
+
"grad_norm": 5.591251850128174,
|
| 674 |
+
"learning_rate": 5.714285714285714e-05,
|
| 675 |
+
"loss": 0.7536,
|
| 676 |
"step": 930
|
| 677 |
},
|
| 678 |
{
|
| 679 |
"epoch": 2.685714285714286,
|
| 680 |
+
"grad_norm": 4.405236721038818,
|
| 681 |
+
"learning_rate": 5.2380952380952384e-05,
|
| 682 |
+
"loss": 0.9314,
|
| 683 |
"step": 940
|
| 684 |
},
|
| 685 |
{
|
| 686 |
"epoch": 2.7142857142857144,
|
| 687 |
+
"grad_norm": 4.951947212219238,
|
| 688 |
+
"learning_rate": 4.761904761904762e-05,
|
| 689 |
+
"loss": 0.796,
|
| 690 |
"step": 950
|
| 691 |
},
|
| 692 |
{
|
| 693 |
"epoch": 2.742857142857143,
|
| 694 |
+
"grad_norm": 5.001076698303223,
|
| 695 |
+
"learning_rate": 4.2857142857142856e-05,
|
| 696 |
+
"loss": 0.7446,
|
| 697 |
"step": 960
|
| 698 |
},
|
| 699 |
{
|
| 700 |
"epoch": 2.7714285714285714,
|
| 701 |
+
"grad_norm": 5.915081024169922,
|
| 702 |
+
"learning_rate": 3.80952380952381e-05,
|
| 703 |
+
"loss": 0.9323,
|
| 704 |
"step": 970
|
| 705 |
},
|
| 706 |
{
|
| 707 |
"epoch": 2.8,
|
| 708 |
+
"grad_norm": 2.5451648235321045,
|
| 709 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 710 |
+
"loss": 0.9232,
|
| 711 |
"step": 980
|
| 712 |
},
|
| 713 |
{
|
| 714 |
"epoch": 2.8285714285714287,
|
| 715 |
+
"grad_norm": 3.71482515335083,
|
| 716 |
+
"learning_rate": 2.857142857142857e-05,
|
| 717 |
+
"loss": 0.8619,
|
| 718 |
"step": 990
|
| 719 |
},
|
| 720 |
{
|
| 721 |
"epoch": 2.857142857142857,
|
| 722 |
+
"grad_norm": 3.601994037628174,
|
| 723 |
+
"learning_rate": 2.380952380952381e-05,
|
| 724 |
+
"loss": 0.8866,
|
| 725 |
"step": 1000
|
| 726 |
},
|
| 727 |
{
|
| 728 |
"epoch": 2.8857142857142857,
|
| 729 |
+
"grad_norm": 4.266910552978516,
|
| 730 |
+
"learning_rate": 1.904761904761905e-05,
|
| 731 |
+
"loss": 0.7992,
|
| 732 |
"step": 1010
|
| 733 |
},
|
| 734 |
{
|
| 735 |
"epoch": 2.914285714285714,
|
| 736 |
+
"grad_norm": 2.968625783920288,
|
| 737 |
+
"learning_rate": 1.4285714285714285e-05,
|
| 738 |
+
"loss": 0.7861,
|
| 739 |
"step": 1020
|
| 740 |
},
|
| 741 |
{
|
| 742 |
"epoch": 2.942857142857143,
|
| 743 |
+
"grad_norm": 3.180135488510132,
|
| 744 |
+
"learning_rate": 9.523809523809525e-06,
|
| 745 |
+
"loss": 0.6923,
|
| 746 |
"step": 1030
|
| 747 |
},
|
| 748 |
{
|
| 749 |
"epoch": 2.9714285714285715,
|
| 750 |
+
"grad_norm": 3.609273910522461,
|
| 751 |
+
"learning_rate": 4.761904761904762e-06,
|
| 752 |
+
"loss": 0.6872,
|
| 753 |
"step": 1040
|
| 754 |
},
|
| 755 |
{
|
| 756 |
"epoch": 3.0,
|
| 757 |
+
"grad_norm": 4.716108798980713,
|
| 758 |
"learning_rate": 0.0,
|
| 759 |
+
"loss": 0.8321,
|
| 760 |
"step": 1050
|
| 761 |
},
|
| 762 |
{
|
| 763 |
"epoch": 3.0,
|
| 764 |
+
"eval_loss": 0.7921221852302551,
|
| 765 |
+
"eval_runtime": 16.5336,
|
| 766 |
+
"eval_samples_per_second": 12.097,
|
| 767 |
+
"eval_steps_per_second": 1.512,
|
| 768 |
"step": 1050
|
| 769 |
}
|
| 770 |
],
|
|
|
|
| 785 |
"attributes": {}
|
| 786 |
}
|
| 787 |
},
|
| 788 |
+
"total_flos": 6283456413696000.0,
|
| 789 |
"train_batch_size": 8,
|
| 790 |
"trial_name": null,
|
| 791 |
"trial_params": null
|
checkpoint-1050/training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5240
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1982b07d8277b0bc7aaf4f34307bfaa24bd97b8994cd2c48e972769e68324f20
|
| 3 |
size 5240
|
checkpoint-350/adapter_config.json
CHANGED
|
@@ -20,8 +20,8 @@
|
|
| 20 |
"rank_pattern": {},
|
| 21 |
"revision": null,
|
| 22 |
"target_modules": [
|
| 23 |
-
"
|
| 24 |
-
"
|
| 25 |
],
|
| 26 |
"task_type": "CAUSAL_LM",
|
| 27 |
"use_dora": false,
|
|
|
|
| 20 |
"rank_pattern": {},
|
| 21 |
"revision": null,
|
| 22 |
"target_modules": [
|
| 23 |
+
"v_proj",
|
| 24 |
+
"q_proj"
|
| 25 |
],
|
| 26 |
"task_type": "CAUSAL_LM",
|
| 27 |
"use_dora": false,
|
checkpoint-350/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3416264
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7425737072ba8acbe6d2f9c94c69f458d16d0a7f53fa0676b6840781f5a4b2fc
|
| 3 |
size 3416264
|
checkpoint-350/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 6869818
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a5ce96627e6b7708b4c7f689eccadb34c4192d05616b766eab604b48141e5e66
|
| 3 |
size 6869818
|
checkpoint-350/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:a60eb44815728d1c05bb3472d8ee196dc9c4a01b9978bca3eb64637848fdb4c7
|
| 3 |
size 14244
|
checkpoint-350/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:def6878723ae6de031424f87c5cc1de1a9c00f84dc97979090ddbd977a6d40b3
|
| 3 |
size 1064
|
checkpoint-350/trainer_state.json
CHANGED
|
@@ -10,255 +10,255 @@
|
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 0.02857142857142857,
|
| 13 |
-
"grad_norm":
|
| 14 |
-
"learning_rate":
|
| 15 |
-
"loss":
|
| 16 |
"step": 10
|
| 17 |
},
|
| 18 |
{
|
| 19 |
"epoch": 0.05714285714285714,
|
| 20 |
-
"grad_norm":
|
| 21 |
-
"learning_rate":
|
| 22 |
-
"loss":
|
| 23 |
"step": 20
|
| 24 |
},
|
| 25 |
{
|
| 26 |
"epoch": 0.08571428571428572,
|
| 27 |
-
"grad_norm":
|
| 28 |
-
"learning_rate":
|
| 29 |
-
"loss":
|
| 30 |
"step": 30
|
| 31 |
},
|
| 32 |
{
|
| 33 |
"epoch": 0.11428571428571428,
|
| 34 |
-
"grad_norm":
|
| 35 |
-
"learning_rate":
|
| 36 |
-
"loss":
|
| 37 |
"step": 40
|
| 38 |
},
|
| 39 |
{
|
| 40 |
"epoch": 0.14285714285714285,
|
| 41 |
-
"grad_norm":
|
| 42 |
-
"learning_rate":
|
| 43 |
-
"loss":
|
| 44 |
"step": 50
|
| 45 |
},
|
| 46 |
{
|
| 47 |
"epoch": 0.17142857142857143,
|
| 48 |
-
"grad_norm": 5.
|
| 49 |
-
"learning_rate":
|
| 50 |
-
"loss": 1.
|
| 51 |
"step": 60
|
| 52 |
},
|
| 53 |
{
|
| 54 |
"epoch": 0.2,
|
| 55 |
-
"grad_norm":
|
| 56 |
-
"learning_rate":
|
| 57 |
-
"loss": 1.
|
| 58 |
"step": 70
|
| 59 |
},
|
| 60 |
{
|
| 61 |
"epoch": 0.22857142857142856,
|
| 62 |
-
"grad_norm":
|
| 63 |
-
"learning_rate":
|
| 64 |
-
"loss": 1.
|
| 65 |
"step": 80
|
| 66 |
},
|
| 67 |
{
|
| 68 |
"epoch": 0.2571428571428571,
|
| 69 |
-
"grad_norm":
|
| 70 |
-
"learning_rate":
|
| 71 |
-
"loss": 1.
|
| 72 |
"step": 90
|
| 73 |
},
|
| 74 |
{
|
| 75 |
"epoch": 0.2857142857142857,
|
| 76 |
-
"grad_norm": 7.
|
| 77 |
-
"learning_rate":
|
| 78 |
-
"loss": 1.
|
| 79 |
"step": 100
|
| 80 |
},
|
| 81 |
{
|
| 82 |
"epoch": 0.3142857142857143,
|
| 83 |
-
"grad_norm":
|
| 84 |
-
"learning_rate":
|
| 85 |
-
"loss": 1.
|
| 86 |
"step": 110
|
| 87 |
},
|
| 88 |
{
|
| 89 |
"epoch": 0.34285714285714286,
|
| 90 |
-
"grad_norm":
|
| 91 |
-
"learning_rate":
|
| 92 |
-
"loss": 1.
|
| 93 |
"step": 120
|
| 94 |
},
|
| 95 |
{
|
| 96 |
"epoch": 0.37142857142857144,
|
| 97 |
-
"grad_norm":
|
| 98 |
-
"learning_rate":
|
| 99 |
-
"loss": 1.
|
| 100 |
"step": 130
|
| 101 |
},
|
| 102 |
{
|
| 103 |
"epoch": 0.4,
|
| 104 |
-
"grad_norm":
|
| 105 |
-
"learning_rate":
|
| 106 |
-
"loss": 1.
|
| 107 |
"step": 140
|
| 108 |
},
|
| 109 |
{
|
| 110 |
"epoch": 0.42857142857142855,
|
| 111 |
-
"grad_norm":
|
| 112 |
-
"learning_rate":
|
| 113 |
-
"loss": 1.
|
| 114 |
"step": 150
|
| 115 |
},
|
| 116 |
{
|
| 117 |
"epoch": 0.45714285714285713,
|
| 118 |
-
"grad_norm":
|
| 119 |
-
"learning_rate":
|
| 120 |
-
"loss": 1.
|
| 121 |
"step": 160
|
| 122 |
},
|
| 123 |
{
|
| 124 |
"epoch": 0.4857142857142857,
|
| 125 |
-
"grad_norm":
|
| 126 |
-
"learning_rate":
|
| 127 |
-
"loss": 1.
|
| 128 |
"step": 170
|
| 129 |
},
|
| 130 |
{
|
| 131 |
"epoch": 0.5142857142857142,
|
| 132 |
-
"grad_norm":
|
| 133 |
-
"learning_rate":
|
| 134 |
-
"loss": 1.
|
| 135 |
"step": 180
|
| 136 |
},
|
| 137 |
{
|
| 138 |
"epoch": 0.5428571428571428,
|
| 139 |
-
"grad_norm":
|
| 140 |
-
"learning_rate":
|
| 141 |
-
"loss": 1.
|
| 142 |
"step": 190
|
| 143 |
},
|
| 144 |
{
|
| 145 |
"epoch": 0.5714285714285714,
|
| 146 |
-
"grad_norm":
|
| 147 |
-
"learning_rate":
|
| 148 |
-
"loss": 1.
|
| 149 |
"step": 200
|
| 150 |
},
|
| 151 |
{
|
| 152 |
"epoch": 0.6,
|
| 153 |
-
"grad_norm":
|
| 154 |
-
"learning_rate":
|
| 155 |
-
"loss": 1.
|
| 156 |
"step": 210
|
| 157 |
},
|
| 158 |
{
|
| 159 |
"epoch": 0.6285714285714286,
|
| 160 |
-
"grad_norm":
|
| 161 |
-
"learning_rate":
|
| 162 |
-
"loss": 1.
|
| 163 |
"step": 220
|
| 164 |
},
|
| 165 |
{
|
| 166 |
"epoch": 0.6571428571428571,
|
| 167 |
-
"grad_norm":
|
| 168 |
-
"learning_rate":
|
| 169 |
-
"loss": 1.
|
| 170 |
"step": 230
|
| 171 |
},
|
| 172 |
{
|
| 173 |
"epoch": 0.6857142857142857,
|
| 174 |
-
"grad_norm":
|
| 175 |
-
"learning_rate":
|
| 176 |
-
"loss": 1.
|
| 177 |
"step": 240
|
| 178 |
},
|
| 179 |
{
|
| 180 |
"epoch": 0.7142857142857143,
|
| 181 |
-
"grad_norm":
|
| 182 |
-
"learning_rate":
|
| 183 |
-
"loss": 1.
|
| 184 |
"step": 250
|
| 185 |
},
|
| 186 |
{
|
| 187 |
"epoch": 0.7428571428571429,
|
| 188 |
-
"grad_norm":
|
| 189 |
-
"learning_rate":
|
| 190 |
-
"loss": 1.
|
| 191 |
"step": 260
|
| 192 |
},
|
| 193 |
{
|
| 194 |
"epoch": 0.7714285714285715,
|
| 195 |
-
"grad_norm":
|
| 196 |
-
"learning_rate":
|
| 197 |
-
"loss": 1.
|
| 198 |
"step": 270
|
| 199 |
},
|
| 200 |
{
|
| 201 |
"epoch": 0.8,
|
| 202 |
-
"grad_norm":
|
| 203 |
-
"learning_rate":
|
| 204 |
-
"loss": 1.
|
| 205 |
"step": 280
|
| 206 |
},
|
| 207 |
{
|
| 208 |
"epoch": 0.8285714285714286,
|
| 209 |
-
"grad_norm":
|
| 210 |
-
"learning_rate":
|
| 211 |
-
"loss": 1.
|
| 212 |
"step": 290
|
| 213 |
},
|
| 214 |
{
|
| 215 |
"epoch": 0.8571428571428571,
|
| 216 |
-
"grad_norm":
|
| 217 |
-
"learning_rate":
|
| 218 |
-
"loss": 1.
|
| 219 |
"step": 300
|
| 220 |
},
|
| 221 |
{
|
| 222 |
"epoch": 0.8857142857142857,
|
| 223 |
-
"grad_norm":
|
| 224 |
-
"learning_rate":
|
| 225 |
-
"loss": 1.
|
| 226 |
"step": 310
|
| 227 |
},
|
| 228 |
{
|
| 229 |
"epoch": 0.9142857142857143,
|
| 230 |
-
"grad_norm":
|
| 231 |
-
"learning_rate":
|
| 232 |
-
"loss": 1.
|
| 233 |
"step": 320
|
| 234 |
},
|
| 235 |
{
|
| 236 |
"epoch": 0.9428571428571428,
|
| 237 |
-
"grad_norm":
|
| 238 |
-
"learning_rate":
|
| 239 |
-
"loss": 1.
|
| 240 |
"step": 330
|
| 241 |
},
|
| 242 |
{
|
| 243 |
"epoch": 0.9714285714285714,
|
| 244 |
-
"grad_norm":
|
| 245 |
-
"learning_rate":
|
| 246 |
-
"loss": 1.
|
| 247 |
"step": 340
|
| 248 |
},
|
| 249 |
{
|
| 250 |
"epoch": 1.0,
|
| 251 |
-
"grad_norm":
|
| 252 |
-
"learning_rate":
|
| 253 |
-
"loss": 1.
|
| 254 |
"step": 350
|
| 255 |
},
|
| 256 |
{
|
| 257 |
"epoch": 1.0,
|
| 258 |
-
"eval_loss": 1.
|
| 259 |
-
"eval_runtime": 16.
|
| 260 |
-
"eval_samples_per_second": 12.
|
| 261 |
-
"eval_steps_per_second": 1.
|
| 262 |
"step": 350
|
| 263 |
}
|
| 264 |
],
|
|
@@ -279,7 +279,7 @@
|
|
| 279 |
"attributes": {}
|
| 280 |
}
|
| 281 |
},
|
| 282 |
-
"total_flos":
|
| 283 |
"train_batch_size": 8,
|
| 284 |
"trial_name": null,
|
| 285 |
"trial_params": null
|
|
|
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 0.02857142857142857,
|
| 13 |
+
"grad_norm": 5.210493087768555,
|
| 14 |
+
"learning_rate": 0.0004952380952380952,
|
| 15 |
+
"loss": 4.4131,
|
| 16 |
"step": 10
|
| 17 |
},
|
| 18 |
{
|
| 19 |
"epoch": 0.05714285714285714,
|
| 20 |
+
"grad_norm": 3.571948528289795,
|
| 21 |
+
"learning_rate": 0.0004904761904761905,
|
| 22 |
+
"loss": 2.5476,
|
| 23 |
"step": 20
|
| 24 |
},
|
| 25 |
{
|
| 26 |
"epoch": 0.08571428571428572,
|
| 27 |
+
"grad_norm": 2.640848398208618,
|
| 28 |
+
"learning_rate": 0.0004857142857142857,
|
| 29 |
+
"loss": 2.2491,
|
| 30 |
"step": 30
|
| 31 |
},
|
| 32 |
{
|
| 33 |
"epoch": 0.11428571428571428,
|
| 34 |
+
"grad_norm": 2.6611335277557373,
|
| 35 |
+
"learning_rate": 0.00048095238095238095,
|
| 36 |
+
"loss": 2.0477,
|
| 37 |
"step": 40
|
| 38 |
},
|
| 39 |
{
|
| 40 |
"epoch": 0.14285714285714285,
|
| 41 |
+
"grad_norm": 2.608750581741333,
|
| 42 |
+
"learning_rate": 0.0004761904761904762,
|
| 43 |
+
"loss": 2.028,
|
| 44 |
"step": 50
|
| 45 |
},
|
| 46 |
{
|
| 47 |
"epoch": 0.17142857142857143,
|
| 48 |
+
"grad_norm": 5.034807205200195,
|
| 49 |
+
"learning_rate": 0.0004714285714285714,
|
| 50 |
+
"loss": 1.7871,
|
| 51 |
"step": 60
|
| 52 |
},
|
| 53 |
{
|
| 54 |
"epoch": 0.2,
|
| 55 |
+
"grad_norm": 3.5893642902374268,
|
| 56 |
+
"learning_rate": 0.00046666666666666666,
|
| 57 |
+
"loss": 1.7879,
|
| 58 |
"step": 70
|
| 59 |
},
|
| 60 |
{
|
| 61 |
"epoch": 0.22857142857142856,
|
| 62 |
+
"grad_norm": 5.368953227996826,
|
| 63 |
+
"learning_rate": 0.00046190476190476195,
|
| 64 |
+
"loss": 1.8194,
|
| 65 |
"step": 80
|
| 66 |
},
|
| 67 |
{
|
| 68 |
"epoch": 0.2571428571428571,
|
| 69 |
+
"grad_norm": 3.7377731800079346,
|
| 70 |
+
"learning_rate": 0.00045714285714285713,
|
| 71 |
+
"loss": 1.6159,
|
| 72 |
"step": 90
|
| 73 |
},
|
| 74 |
{
|
| 75 |
"epoch": 0.2857142857142857,
|
| 76 |
+
"grad_norm": 7.883308410644531,
|
| 77 |
+
"learning_rate": 0.00045238095238095237,
|
| 78 |
+
"loss": 1.6244,
|
| 79 |
"step": 100
|
| 80 |
},
|
| 81 |
{
|
| 82 |
"epoch": 0.3142857142857143,
|
| 83 |
+
"grad_norm": 4.968689918518066,
|
| 84 |
+
"learning_rate": 0.00044761904761904766,
|
| 85 |
+
"loss": 1.6614,
|
| 86 |
"step": 110
|
| 87 |
},
|
| 88 |
{
|
| 89 |
"epoch": 0.34285714285714286,
|
| 90 |
+
"grad_norm": 2.592766046524048,
|
| 91 |
+
"learning_rate": 0.00044285714285714284,
|
| 92 |
+
"loss": 1.349,
|
| 93 |
"step": 120
|
| 94 |
},
|
| 95 |
{
|
| 96 |
"epoch": 0.37142857142857144,
|
| 97 |
+
"grad_norm": 2.783951997756958,
|
| 98 |
+
"learning_rate": 0.0004380952380952381,
|
| 99 |
+
"loss": 1.5065,
|
| 100 |
"step": 130
|
| 101 |
},
|
| 102 |
{
|
| 103 |
"epoch": 0.4,
|
| 104 |
+
"grad_norm": 5.2810378074646,
|
| 105 |
+
"learning_rate": 0.00043333333333333337,
|
| 106 |
+
"loss": 1.3934,
|
| 107 |
"step": 140
|
| 108 |
},
|
| 109 |
{
|
| 110 |
"epoch": 0.42857142857142855,
|
| 111 |
+
"grad_norm": 4.448086261749268,
|
| 112 |
+
"learning_rate": 0.00042857142857142855,
|
| 113 |
+
"loss": 1.5198,
|
| 114 |
"step": 150
|
| 115 |
},
|
| 116 |
{
|
| 117 |
"epoch": 0.45714285714285713,
|
| 118 |
+
"grad_norm": 3.211707353591919,
|
| 119 |
+
"learning_rate": 0.0004238095238095238,
|
| 120 |
+
"loss": 1.6207,
|
| 121 |
"step": 160
|
| 122 |
},
|
| 123 |
{
|
| 124 |
"epoch": 0.4857142857142857,
|
| 125 |
+
"grad_norm": 3.586463212966919,
|
| 126 |
+
"learning_rate": 0.0004190476190476191,
|
| 127 |
+
"loss": 1.2687,
|
| 128 |
"step": 170
|
| 129 |
},
|
| 130 |
{
|
| 131 |
"epoch": 0.5142857142857142,
|
| 132 |
+
"grad_norm": 2.6598610877990723,
|
| 133 |
+
"learning_rate": 0.0004142857142857143,
|
| 134 |
+
"loss": 1.3957,
|
| 135 |
"step": 180
|
| 136 |
},
|
| 137 |
{
|
| 138 |
"epoch": 0.5428571428571428,
|
| 139 |
+
"grad_norm": 3.480663776397705,
|
| 140 |
+
"learning_rate": 0.00040952380952380955,
|
| 141 |
+
"loss": 1.3543,
|
| 142 |
"step": 190
|
| 143 |
},
|
| 144 |
{
|
| 145 |
"epoch": 0.5714285714285714,
|
| 146 |
+
"grad_norm": 3.168818712234497,
|
| 147 |
+
"learning_rate": 0.0004047619047619048,
|
| 148 |
+
"loss": 1.2619,
|
| 149 |
"step": 200
|
| 150 |
},
|
| 151 |
{
|
| 152 |
"epoch": 0.6,
|
| 153 |
+
"grad_norm": 2.7529921531677246,
|
| 154 |
+
"learning_rate": 0.0004,
|
| 155 |
+
"loss": 1.1871,
|
| 156 |
"step": 210
|
| 157 |
},
|
| 158 |
{
|
| 159 |
"epoch": 0.6285714285714286,
|
| 160 |
+
"grad_norm": 6.538937568664551,
|
| 161 |
+
"learning_rate": 0.00039523809523809526,
|
| 162 |
+
"loss": 1.268,
|
| 163 |
"step": 220
|
| 164 |
},
|
| 165 |
{
|
| 166 |
"epoch": 0.6571428571428571,
|
| 167 |
+
"grad_norm": 3.3910727500915527,
|
| 168 |
+
"learning_rate": 0.0003904761904761905,
|
| 169 |
+
"loss": 1.4192,
|
| 170 |
"step": 230
|
| 171 |
},
|
| 172 |
{
|
| 173 |
"epoch": 0.6857142857142857,
|
| 174 |
+
"grad_norm": 2.31817889213562,
|
| 175 |
+
"learning_rate": 0.0003857142857142857,
|
| 176 |
+
"loss": 1.2339,
|
| 177 |
"step": 240
|
| 178 |
},
|
| 179 |
{
|
| 180 |
"epoch": 0.7142857142857143,
|
| 181 |
+
"grad_norm": 2.8181235790252686,
|
| 182 |
+
"learning_rate": 0.00038095238095238096,
|
| 183 |
+
"loss": 1.3153,
|
| 184 |
"step": 250
|
| 185 |
},
|
| 186 |
{
|
| 187 |
"epoch": 0.7428571428571429,
|
| 188 |
+
"grad_norm": 2.5716922283172607,
|
| 189 |
+
"learning_rate": 0.0003761904761904762,
|
| 190 |
+
"loss": 1.2066,
|
| 191 |
"step": 260
|
| 192 |
},
|
| 193 |
{
|
| 194 |
"epoch": 0.7714285714285715,
|
| 195 |
+
"grad_norm": 5.403870105743408,
|
| 196 |
+
"learning_rate": 0.00037142857142857143,
|
| 197 |
+
"loss": 1.2784,
|
| 198 |
"step": 270
|
| 199 |
},
|
| 200 |
{
|
| 201 |
"epoch": 0.8,
|
| 202 |
+
"grad_norm": 3.347729206085205,
|
| 203 |
+
"learning_rate": 0.00036666666666666667,
|
| 204 |
+
"loss": 1.2273,
|
| 205 |
"step": 280
|
| 206 |
},
|
| 207 |
{
|
| 208 |
"epoch": 0.8285714285714286,
|
| 209 |
+
"grad_norm": 2.7995996475219727,
|
| 210 |
+
"learning_rate": 0.0003619047619047619,
|
| 211 |
+
"loss": 1.159,
|
| 212 |
"step": 290
|
| 213 |
},
|
| 214 |
{
|
| 215 |
"epoch": 0.8571428571428571,
|
| 216 |
+
"grad_norm": 3.817213535308838,
|
| 217 |
+
"learning_rate": 0.00035714285714285714,
|
| 218 |
+
"loss": 1.1146,
|
| 219 |
"step": 300
|
| 220 |
},
|
| 221 |
{
|
| 222 |
"epoch": 0.8857142857142857,
|
| 223 |
+
"grad_norm": 3.3239715099334717,
|
| 224 |
+
"learning_rate": 0.00035238095238095243,
|
| 225 |
+
"loss": 1.1513,
|
| 226 |
"step": 310
|
| 227 |
},
|
| 228 |
{
|
| 229 |
"epoch": 0.9142857142857143,
|
| 230 |
+
"grad_norm": 3.042973518371582,
|
| 231 |
+
"learning_rate": 0.0003476190476190476,
|
| 232 |
+
"loss": 1.3906,
|
| 233 |
"step": 320
|
| 234 |
},
|
| 235 |
{
|
| 236 |
"epoch": 0.9428571428571428,
|
| 237 |
+
"grad_norm": 2.8079681396484375,
|
| 238 |
+
"learning_rate": 0.00034285714285714285,
|
| 239 |
+
"loss": 1.1547,
|
| 240 |
"step": 330
|
| 241 |
},
|
| 242 |
{
|
| 243 |
"epoch": 0.9714285714285714,
|
| 244 |
+
"grad_norm": 6.39453649520874,
|
| 245 |
+
"learning_rate": 0.00033809523809523814,
|
| 246 |
+
"loss": 1.0989,
|
| 247 |
"step": 340
|
| 248 |
},
|
| 249 |
{
|
| 250 |
"epoch": 1.0,
|
| 251 |
+
"grad_norm": 5.739945411682129,
|
| 252 |
+
"learning_rate": 0.0003333333333333333,
|
| 253 |
+
"loss": 1.1563,
|
| 254 |
"step": 350
|
| 255 |
},
|
| 256 |
{
|
| 257 |
"epoch": 1.0,
|
| 258 |
+
"eval_loss": 1.064656376838684,
|
| 259 |
+
"eval_runtime": 16.5324,
|
| 260 |
+
"eval_samples_per_second": 12.097,
|
| 261 |
+
"eval_steps_per_second": 1.512,
|
| 262 |
"step": 350
|
| 263 |
}
|
| 264 |
],
|
|
|
|
| 279 |
"attributes": {}
|
| 280 |
}
|
| 281 |
},
|
| 282 |
+
"total_flos": 2094485471232000.0,
|
| 283 |
"train_batch_size": 8,
|
| 284 |
"trial_name": null,
|
| 285 |
"trial_params": null
|
checkpoint-350/training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5240
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1982b07d8277b0bc7aaf4f34307bfaa24bd97b8994cd2c48e972769e68324f20
|
| 3 |
size 5240
|
checkpoint-700/adapter_config.json
CHANGED
|
@@ -20,8 +20,8 @@
|
|
| 20 |
"rank_pattern": {},
|
| 21 |
"revision": null,
|
| 22 |
"target_modules": [
|
| 23 |
-
"
|
| 24 |
-
"
|
| 25 |
],
|
| 26 |
"task_type": "CAUSAL_LM",
|
| 27 |
"use_dora": false,
|
|
|
|
| 20 |
"rank_pattern": {},
|
| 21 |
"revision": null,
|
| 22 |
"target_modules": [
|
| 23 |
+
"v_proj",
|
| 24 |
+
"q_proj"
|
| 25 |
],
|
| 26 |
"task_type": "CAUSAL_LM",
|
| 27 |
"use_dora": false,
|
checkpoint-700/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3416264
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:272d892f181091df9c53c56b733b46487117c9ff3f709e43844e4925d4302ea6
|
| 3 |
size 3416264
|
checkpoint-700/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 6869818
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2fdad2f22ddadb3c8130f49e48198958bf03d74f744708327044990e56b3d21a
|
| 3 |
size 6869818
|
checkpoint-700/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:b50e1d829b6f58094a5a1390d8e3ee0aa39e25fa2ec141d6471b70ffb58c1ac3
|
| 3 |
size 14244
|
checkpoint-700/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 sha256:28b00ddbc3d3a3abe006434542557db9d921f0260b12618e776b614466247588
|
| 3 |
size 1064
|
checkpoint-700/trainer_state.json
CHANGED
|
@@ -10,508 +10,508 @@
|
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 0.02857142857142857,
|
| 13 |
-
"grad_norm":
|
| 14 |
-
"learning_rate":
|
| 15 |
-
"loss":
|
| 16 |
"step": 10
|
| 17 |
},
|
| 18 |
{
|
| 19 |
"epoch": 0.05714285714285714,
|
| 20 |
-
"grad_norm":
|
| 21 |
-
"learning_rate":
|
| 22 |
-
"loss":
|
| 23 |
"step": 20
|
| 24 |
},
|
| 25 |
{
|
| 26 |
"epoch": 0.08571428571428572,
|
| 27 |
-
"grad_norm":
|
| 28 |
-
"learning_rate":
|
| 29 |
-
"loss":
|
| 30 |
"step": 30
|
| 31 |
},
|
| 32 |
{
|
| 33 |
"epoch": 0.11428571428571428,
|
| 34 |
-
"grad_norm":
|
| 35 |
-
"learning_rate":
|
| 36 |
-
"loss":
|
| 37 |
"step": 40
|
| 38 |
},
|
| 39 |
{
|
| 40 |
"epoch": 0.14285714285714285,
|
| 41 |
-
"grad_norm":
|
| 42 |
-
"learning_rate":
|
| 43 |
-
"loss":
|
| 44 |
"step": 50
|
| 45 |
},
|
| 46 |
{
|
| 47 |
"epoch": 0.17142857142857143,
|
| 48 |
-
"grad_norm": 5.
|
| 49 |
-
"learning_rate":
|
| 50 |
-
"loss": 1.
|
| 51 |
"step": 60
|
| 52 |
},
|
| 53 |
{
|
| 54 |
"epoch": 0.2,
|
| 55 |
-
"grad_norm":
|
| 56 |
-
"learning_rate":
|
| 57 |
-
"loss": 1.
|
| 58 |
"step": 70
|
| 59 |
},
|
| 60 |
{
|
| 61 |
"epoch": 0.22857142857142856,
|
| 62 |
-
"grad_norm":
|
| 63 |
-
"learning_rate":
|
| 64 |
-
"loss": 1.
|
| 65 |
"step": 80
|
| 66 |
},
|
| 67 |
{
|
| 68 |
"epoch": 0.2571428571428571,
|
| 69 |
-
"grad_norm":
|
| 70 |
-
"learning_rate":
|
| 71 |
-
"loss": 1.
|
| 72 |
"step": 90
|
| 73 |
},
|
| 74 |
{
|
| 75 |
"epoch": 0.2857142857142857,
|
| 76 |
-
"grad_norm": 7.
|
| 77 |
-
"learning_rate":
|
| 78 |
-
"loss": 1.
|
| 79 |
"step": 100
|
| 80 |
},
|
| 81 |
{
|
| 82 |
"epoch": 0.3142857142857143,
|
| 83 |
-
"grad_norm":
|
| 84 |
-
"learning_rate":
|
| 85 |
-
"loss": 1.
|
| 86 |
"step": 110
|
| 87 |
},
|
| 88 |
{
|
| 89 |
"epoch": 0.34285714285714286,
|
| 90 |
-
"grad_norm":
|
| 91 |
-
"learning_rate":
|
| 92 |
-
"loss": 1.
|
| 93 |
"step": 120
|
| 94 |
},
|
| 95 |
{
|
| 96 |
"epoch": 0.37142857142857144,
|
| 97 |
-
"grad_norm":
|
| 98 |
-
"learning_rate":
|
| 99 |
-
"loss": 1.
|
| 100 |
"step": 130
|
| 101 |
},
|
| 102 |
{
|
| 103 |
"epoch": 0.4,
|
| 104 |
-
"grad_norm":
|
| 105 |
-
"learning_rate":
|
| 106 |
-
"loss": 1.
|
| 107 |
"step": 140
|
| 108 |
},
|
| 109 |
{
|
| 110 |
"epoch": 0.42857142857142855,
|
| 111 |
-
"grad_norm":
|
| 112 |
-
"learning_rate":
|
| 113 |
-
"loss": 1.
|
| 114 |
"step": 150
|
| 115 |
},
|
| 116 |
{
|
| 117 |
"epoch": 0.45714285714285713,
|
| 118 |
-
"grad_norm":
|
| 119 |
-
"learning_rate":
|
| 120 |
-
"loss": 1.
|
| 121 |
"step": 160
|
| 122 |
},
|
| 123 |
{
|
| 124 |
"epoch": 0.4857142857142857,
|
| 125 |
-
"grad_norm":
|
| 126 |
-
"learning_rate":
|
| 127 |
-
"loss": 1.
|
| 128 |
"step": 170
|
| 129 |
},
|
| 130 |
{
|
| 131 |
"epoch": 0.5142857142857142,
|
| 132 |
-
"grad_norm":
|
| 133 |
-
"learning_rate":
|
| 134 |
-
"loss": 1.
|
| 135 |
"step": 180
|
| 136 |
},
|
| 137 |
{
|
| 138 |
"epoch": 0.5428571428571428,
|
| 139 |
-
"grad_norm":
|
| 140 |
-
"learning_rate":
|
| 141 |
-
"loss": 1.
|
| 142 |
"step": 190
|
| 143 |
},
|
| 144 |
{
|
| 145 |
"epoch": 0.5714285714285714,
|
| 146 |
-
"grad_norm":
|
| 147 |
-
"learning_rate":
|
| 148 |
-
"loss": 1.
|
| 149 |
"step": 200
|
| 150 |
},
|
| 151 |
{
|
| 152 |
"epoch": 0.6,
|
| 153 |
-
"grad_norm":
|
| 154 |
-
"learning_rate":
|
| 155 |
-
"loss": 1.
|
| 156 |
"step": 210
|
| 157 |
},
|
| 158 |
{
|
| 159 |
"epoch": 0.6285714285714286,
|
| 160 |
-
"grad_norm":
|
| 161 |
-
"learning_rate":
|
| 162 |
-
"loss": 1.
|
| 163 |
"step": 220
|
| 164 |
},
|
| 165 |
{
|
| 166 |
"epoch": 0.6571428571428571,
|
| 167 |
-
"grad_norm":
|
| 168 |
-
"learning_rate":
|
| 169 |
-
"loss": 1.
|
| 170 |
"step": 230
|
| 171 |
},
|
| 172 |
{
|
| 173 |
"epoch": 0.6857142857142857,
|
| 174 |
-
"grad_norm":
|
| 175 |
-
"learning_rate":
|
| 176 |
-
"loss": 1.
|
| 177 |
"step": 240
|
| 178 |
},
|
| 179 |
{
|
| 180 |
"epoch": 0.7142857142857143,
|
| 181 |
-
"grad_norm":
|
| 182 |
-
"learning_rate":
|
| 183 |
-
"loss": 1.
|
| 184 |
"step": 250
|
| 185 |
},
|
| 186 |
{
|
| 187 |
"epoch": 0.7428571428571429,
|
| 188 |
-
"grad_norm":
|
| 189 |
-
"learning_rate":
|
| 190 |
-
"loss": 1.
|
| 191 |
"step": 260
|
| 192 |
},
|
| 193 |
{
|
| 194 |
"epoch": 0.7714285714285715,
|
| 195 |
-
"grad_norm":
|
| 196 |
-
"learning_rate":
|
| 197 |
-
"loss": 1.
|
| 198 |
"step": 270
|
| 199 |
},
|
| 200 |
{
|
| 201 |
"epoch": 0.8,
|
| 202 |
-
"grad_norm":
|
| 203 |
-
"learning_rate":
|
| 204 |
-
"loss": 1.
|
| 205 |
"step": 280
|
| 206 |
},
|
| 207 |
{
|
| 208 |
"epoch": 0.8285714285714286,
|
| 209 |
-
"grad_norm":
|
| 210 |
-
"learning_rate":
|
| 211 |
-
"loss": 1.
|
| 212 |
"step": 290
|
| 213 |
},
|
| 214 |
{
|
| 215 |
"epoch": 0.8571428571428571,
|
| 216 |
-
"grad_norm":
|
| 217 |
-
"learning_rate":
|
| 218 |
-
"loss": 1.
|
| 219 |
"step": 300
|
| 220 |
},
|
| 221 |
{
|
| 222 |
"epoch": 0.8857142857142857,
|
| 223 |
-
"grad_norm":
|
| 224 |
-
"learning_rate":
|
| 225 |
-
"loss": 1.
|
| 226 |
"step": 310
|
| 227 |
},
|
| 228 |
{
|
| 229 |
"epoch": 0.9142857142857143,
|
| 230 |
-
"grad_norm":
|
| 231 |
-
"learning_rate":
|
| 232 |
-
"loss": 1.
|
| 233 |
"step": 320
|
| 234 |
},
|
| 235 |
{
|
| 236 |
"epoch": 0.9428571428571428,
|
| 237 |
-
"grad_norm":
|
| 238 |
-
"learning_rate":
|
| 239 |
-
"loss": 1.
|
| 240 |
"step": 330
|
| 241 |
},
|
| 242 |
{
|
| 243 |
"epoch": 0.9714285714285714,
|
| 244 |
-
"grad_norm":
|
| 245 |
-
"learning_rate":
|
| 246 |
-
"loss": 1.
|
| 247 |
"step": 340
|
| 248 |
},
|
| 249 |
{
|
| 250 |
"epoch": 1.0,
|
| 251 |
-
"grad_norm":
|
| 252 |
-
"learning_rate":
|
| 253 |
-
"loss": 1.
|
| 254 |
"step": 350
|
| 255 |
},
|
| 256 |
{
|
| 257 |
"epoch": 1.0,
|
| 258 |
-
"eval_loss": 1.
|
| 259 |
-
"eval_runtime": 16.
|
| 260 |
-
"eval_samples_per_second": 12.
|
| 261 |
-
"eval_steps_per_second": 1.
|
| 262 |
"step": 350
|
| 263 |
},
|
| 264 |
{
|
| 265 |
"epoch": 1.0285714285714285,
|
| 266 |
-
"grad_norm":
|
| 267 |
-
"learning_rate":
|
| 268 |
-
"loss": 1.
|
| 269 |
"step": 360
|
| 270 |
},
|
| 271 |
{
|
| 272 |
"epoch": 1.0571428571428572,
|
| 273 |
-
"grad_norm":
|
| 274 |
-
"learning_rate":
|
| 275 |
-
"loss": 1.
|
| 276 |
"step": 370
|
| 277 |
},
|
| 278 |
{
|
| 279 |
"epoch": 1.0857142857142856,
|
| 280 |
-
"grad_norm":
|
| 281 |
-
"learning_rate":
|
| 282 |
-
"loss": 1.
|
| 283 |
"step": 380
|
| 284 |
},
|
| 285 |
{
|
| 286 |
"epoch": 1.1142857142857143,
|
| 287 |
-
"grad_norm":
|
| 288 |
-
"learning_rate":
|
| 289 |
-
"loss": 1.
|
| 290 |
"step": 390
|
| 291 |
},
|
| 292 |
{
|
| 293 |
"epoch": 1.1428571428571428,
|
| 294 |
-
"grad_norm":
|
| 295 |
-
"learning_rate":
|
| 296 |
-
"loss": 1.
|
| 297 |
"step": 400
|
| 298 |
},
|
| 299 |
{
|
| 300 |
"epoch": 1.1714285714285715,
|
| 301 |
-
"grad_norm":
|
| 302 |
-
"learning_rate":
|
| 303 |
-
"loss": 1.
|
| 304 |
"step": 410
|
| 305 |
},
|
| 306 |
{
|
| 307 |
"epoch": 1.2,
|
| 308 |
-
"grad_norm":
|
| 309 |
-
"learning_rate":
|
| 310 |
-
"loss": 1.
|
| 311 |
"step": 420
|
| 312 |
},
|
| 313 |
{
|
| 314 |
"epoch": 1.2285714285714286,
|
| 315 |
-
"grad_norm":
|
| 316 |
-
"learning_rate":
|
| 317 |
-
"loss": 1.
|
| 318 |
"step": 430
|
| 319 |
},
|
| 320 |
{
|
| 321 |
"epoch": 1.2571428571428571,
|
| 322 |
-
"grad_norm":
|
| 323 |
-
"learning_rate":
|
| 324 |
-
"loss":
|
| 325 |
"step": 440
|
| 326 |
},
|
| 327 |
{
|
| 328 |
"epoch": 1.2857142857142856,
|
| 329 |
-
"grad_norm":
|
| 330 |
-
"learning_rate":
|
| 331 |
-
"loss": 1.
|
| 332 |
"step": 450
|
| 333 |
},
|
| 334 |
{
|
| 335 |
"epoch": 1.3142857142857143,
|
| 336 |
-
"grad_norm":
|
| 337 |
-
"learning_rate":
|
| 338 |
-
"loss": 1.
|
| 339 |
"step": 460
|
| 340 |
},
|
| 341 |
{
|
| 342 |
"epoch": 1.342857142857143,
|
| 343 |
-
"grad_norm":
|
| 344 |
-
"learning_rate":
|
| 345 |
-
"loss": 1.
|
| 346 |
"step": 470
|
| 347 |
},
|
| 348 |
{
|
| 349 |
"epoch": 1.3714285714285714,
|
| 350 |
-
"grad_norm":
|
| 351 |
-
"learning_rate":
|
| 352 |
-
"loss": 1.
|
| 353 |
"step": 480
|
| 354 |
},
|
| 355 |
{
|
| 356 |
"epoch": 1.4,
|
| 357 |
-
"grad_norm":
|
| 358 |
-
"learning_rate":
|
| 359 |
-
"loss": 1.
|
| 360 |
"step": 490
|
| 361 |
},
|
| 362 |
{
|
| 363 |
"epoch": 1.4285714285714286,
|
| 364 |
-
"grad_norm":
|
| 365 |
-
"learning_rate":
|
| 366 |
-
"loss":
|
| 367 |
"step": 500
|
| 368 |
},
|
| 369 |
{
|
| 370 |
"epoch": 1.457142857142857,
|
| 371 |
-
"grad_norm":
|
| 372 |
-
"learning_rate":
|
| 373 |
-
"loss":
|
| 374 |
"step": 510
|
| 375 |
},
|
| 376 |
{
|
| 377 |
"epoch": 1.4857142857142858,
|
| 378 |
-
"grad_norm":
|
| 379 |
-
"learning_rate":
|
| 380 |
-
"loss":
|
| 381 |
"step": 520
|
| 382 |
},
|
| 383 |
{
|
| 384 |
"epoch": 1.5142857142857142,
|
| 385 |
-
"grad_norm":
|
| 386 |
-
"learning_rate":
|
| 387 |
-
"loss":
|
| 388 |
"step": 530
|
| 389 |
},
|
| 390 |
{
|
| 391 |
"epoch": 1.5428571428571427,
|
| 392 |
-
"grad_norm":
|
| 393 |
-
"learning_rate":
|
| 394 |
-
"loss": 1.
|
| 395 |
"step": 540
|
| 396 |
},
|
| 397 |
{
|
| 398 |
"epoch": 1.5714285714285714,
|
| 399 |
-
"grad_norm":
|
| 400 |
-
"learning_rate":
|
| 401 |
-
"loss":
|
| 402 |
"step": 550
|
| 403 |
},
|
| 404 |
{
|
| 405 |
"epoch": 1.6,
|
| 406 |
-
"grad_norm":
|
| 407 |
-
"learning_rate":
|
| 408 |
-
"loss": 1.
|
| 409 |
"step": 560
|
| 410 |
},
|
| 411 |
{
|
| 412 |
"epoch": 1.6285714285714286,
|
| 413 |
-
"grad_norm":
|
| 414 |
-
"learning_rate":
|
| 415 |
-
"loss": 1.
|
| 416 |
"step": 570
|
| 417 |
},
|
| 418 |
{
|
| 419 |
"epoch": 1.657142857142857,
|
| 420 |
-
"grad_norm":
|
| 421 |
-
"learning_rate":
|
| 422 |
-
"loss":
|
| 423 |
"step": 580
|
| 424 |
},
|
| 425 |
{
|
| 426 |
"epoch": 1.6857142857142857,
|
| 427 |
-
"grad_norm":
|
| 428 |
-
"learning_rate":
|
| 429 |
-
"loss": 1.
|
| 430 |
"step": 590
|
| 431 |
},
|
| 432 |
{
|
| 433 |
"epoch": 1.7142857142857144,
|
| 434 |
-
"grad_norm":
|
| 435 |
-
"learning_rate":
|
| 436 |
-
"loss":
|
| 437 |
"step": 600
|
| 438 |
},
|
| 439 |
{
|
| 440 |
"epoch": 1.7428571428571429,
|
| 441 |
-
"grad_norm":
|
| 442 |
-
"learning_rate":
|
| 443 |
-
"loss":
|
| 444 |
"step": 610
|
| 445 |
},
|
| 446 |
{
|
| 447 |
"epoch": 1.7714285714285714,
|
| 448 |
-
"grad_norm":
|
| 449 |
-
"learning_rate":
|
| 450 |
-
"loss":
|
| 451 |
"step": 620
|
| 452 |
},
|
| 453 |
{
|
| 454 |
"epoch": 1.8,
|
| 455 |
-
"grad_norm":
|
| 456 |
-
"learning_rate":
|
| 457 |
-
"loss": 1.
|
| 458 |
"step": 630
|
| 459 |
},
|
| 460 |
{
|
| 461 |
"epoch": 1.8285714285714287,
|
| 462 |
-
"grad_norm":
|
| 463 |
-
"learning_rate":
|
| 464 |
-
"loss": 1.
|
| 465 |
"step": 640
|
| 466 |
},
|
| 467 |
{
|
| 468 |
"epoch": 1.8571428571428572,
|
| 469 |
-
"grad_norm":
|
| 470 |
-
"learning_rate":
|
| 471 |
-
"loss":
|
| 472 |
"step": 650
|
| 473 |
},
|
| 474 |
{
|
| 475 |
"epoch": 1.8857142857142857,
|
| 476 |
-
"grad_norm":
|
| 477 |
-
"learning_rate":
|
| 478 |
-
"loss":
|
| 479 |
"step": 660
|
| 480 |
},
|
| 481 |
{
|
| 482 |
"epoch": 1.9142857142857141,
|
| 483 |
-
"grad_norm":
|
| 484 |
-
"learning_rate":
|
| 485 |
-
"loss":
|
| 486 |
"step": 670
|
| 487 |
},
|
| 488 |
{
|
| 489 |
"epoch": 1.9428571428571428,
|
| 490 |
-
"grad_norm":
|
| 491 |
-
"learning_rate":
|
| 492 |
-
"loss":
|
| 493 |
"step": 680
|
| 494 |
},
|
| 495 |
{
|
| 496 |
"epoch": 1.9714285714285715,
|
| 497 |
-
"grad_norm":
|
| 498 |
-
"learning_rate":
|
| 499 |
-
"loss":
|
| 500 |
"step": 690
|
| 501 |
},
|
| 502 |
{
|
| 503 |
"epoch": 2.0,
|
| 504 |
-
"grad_norm":
|
| 505 |
-
"learning_rate":
|
| 506 |
-
"loss":
|
| 507 |
"step": 700
|
| 508 |
},
|
| 509 |
{
|
| 510 |
"epoch": 2.0,
|
| 511 |
-
"eval_loss":
|
| 512 |
-
"eval_runtime": 16.
|
| 513 |
-
"eval_samples_per_second": 12.
|
| 514 |
-
"eval_steps_per_second": 1.
|
| 515 |
"step": 700
|
| 516 |
}
|
| 517 |
],
|
|
@@ -532,7 +532,7 @@
|
|
| 532 |
"attributes": {}
|
| 533 |
}
|
| 534 |
},
|
| 535 |
-
"total_flos":
|
| 536 |
"train_batch_size": 8,
|
| 537 |
"trial_name": null,
|
| 538 |
"trial_params": null
|
|
|
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 0.02857142857142857,
|
| 13 |
+
"grad_norm": 5.210493087768555,
|
| 14 |
+
"learning_rate": 0.0004952380952380952,
|
| 15 |
+
"loss": 4.4131,
|
| 16 |
"step": 10
|
| 17 |
},
|
| 18 |
{
|
| 19 |
"epoch": 0.05714285714285714,
|
| 20 |
+
"grad_norm": 3.571948528289795,
|
| 21 |
+
"learning_rate": 0.0004904761904761905,
|
| 22 |
+
"loss": 2.5476,
|
| 23 |
"step": 20
|
| 24 |
},
|
| 25 |
{
|
| 26 |
"epoch": 0.08571428571428572,
|
| 27 |
+
"grad_norm": 2.640848398208618,
|
| 28 |
+
"learning_rate": 0.0004857142857142857,
|
| 29 |
+
"loss": 2.2491,
|
| 30 |
"step": 30
|
| 31 |
},
|
| 32 |
{
|
| 33 |
"epoch": 0.11428571428571428,
|
| 34 |
+
"grad_norm": 2.6611335277557373,
|
| 35 |
+
"learning_rate": 0.00048095238095238095,
|
| 36 |
+
"loss": 2.0477,
|
| 37 |
"step": 40
|
| 38 |
},
|
| 39 |
{
|
| 40 |
"epoch": 0.14285714285714285,
|
| 41 |
+
"grad_norm": 2.608750581741333,
|
| 42 |
+
"learning_rate": 0.0004761904761904762,
|
| 43 |
+
"loss": 2.028,
|
| 44 |
"step": 50
|
| 45 |
},
|
| 46 |
{
|
| 47 |
"epoch": 0.17142857142857143,
|
| 48 |
+
"grad_norm": 5.034807205200195,
|
| 49 |
+
"learning_rate": 0.0004714285714285714,
|
| 50 |
+
"loss": 1.7871,
|
| 51 |
"step": 60
|
| 52 |
},
|
| 53 |
{
|
| 54 |
"epoch": 0.2,
|
| 55 |
+
"grad_norm": 3.5893642902374268,
|
| 56 |
+
"learning_rate": 0.00046666666666666666,
|
| 57 |
+
"loss": 1.7879,
|
| 58 |
"step": 70
|
| 59 |
},
|
| 60 |
{
|
| 61 |
"epoch": 0.22857142857142856,
|
| 62 |
+
"grad_norm": 5.368953227996826,
|
| 63 |
+
"learning_rate": 0.00046190476190476195,
|
| 64 |
+
"loss": 1.8194,
|
| 65 |
"step": 80
|
| 66 |
},
|
| 67 |
{
|
| 68 |
"epoch": 0.2571428571428571,
|
| 69 |
+
"grad_norm": 3.7377731800079346,
|
| 70 |
+
"learning_rate": 0.00045714285714285713,
|
| 71 |
+
"loss": 1.6159,
|
| 72 |
"step": 90
|
| 73 |
},
|
| 74 |
{
|
| 75 |
"epoch": 0.2857142857142857,
|
| 76 |
+
"grad_norm": 7.883308410644531,
|
| 77 |
+
"learning_rate": 0.00045238095238095237,
|
| 78 |
+
"loss": 1.6244,
|
| 79 |
"step": 100
|
| 80 |
},
|
| 81 |
{
|
| 82 |
"epoch": 0.3142857142857143,
|
| 83 |
+
"grad_norm": 4.968689918518066,
|
| 84 |
+
"learning_rate": 0.00044761904761904766,
|
| 85 |
+
"loss": 1.6614,
|
| 86 |
"step": 110
|
| 87 |
},
|
| 88 |
{
|
| 89 |
"epoch": 0.34285714285714286,
|
| 90 |
+
"grad_norm": 2.592766046524048,
|
| 91 |
+
"learning_rate": 0.00044285714285714284,
|
| 92 |
+
"loss": 1.349,
|
| 93 |
"step": 120
|
| 94 |
},
|
| 95 |
{
|
| 96 |
"epoch": 0.37142857142857144,
|
| 97 |
+
"grad_norm": 2.783951997756958,
|
| 98 |
+
"learning_rate": 0.0004380952380952381,
|
| 99 |
+
"loss": 1.5065,
|
| 100 |
"step": 130
|
| 101 |
},
|
| 102 |
{
|
| 103 |
"epoch": 0.4,
|
| 104 |
+
"grad_norm": 5.2810378074646,
|
| 105 |
+
"learning_rate": 0.00043333333333333337,
|
| 106 |
+
"loss": 1.3934,
|
| 107 |
"step": 140
|
| 108 |
},
|
| 109 |
{
|
| 110 |
"epoch": 0.42857142857142855,
|
| 111 |
+
"grad_norm": 4.448086261749268,
|
| 112 |
+
"learning_rate": 0.00042857142857142855,
|
| 113 |
+
"loss": 1.5198,
|
| 114 |
"step": 150
|
| 115 |
},
|
| 116 |
{
|
| 117 |
"epoch": 0.45714285714285713,
|
| 118 |
+
"grad_norm": 3.211707353591919,
|
| 119 |
+
"learning_rate": 0.0004238095238095238,
|
| 120 |
+
"loss": 1.6207,
|
| 121 |
"step": 160
|
| 122 |
},
|
| 123 |
{
|
| 124 |
"epoch": 0.4857142857142857,
|
| 125 |
+
"grad_norm": 3.586463212966919,
|
| 126 |
+
"learning_rate": 0.0004190476190476191,
|
| 127 |
+
"loss": 1.2687,
|
| 128 |
"step": 170
|
| 129 |
},
|
| 130 |
{
|
| 131 |
"epoch": 0.5142857142857142,
|
| 132 |
+
"grad_norm": 2.6598610877990723,
|
| 133 |
+
"learning_rate": 0.0004142857142857143,
|
| 134 |
+
"loss": 1.3957,
|
| 135 |
"step": 180
|
| 136 |
},
|
| 137 |
{
|
| 138 |
"epoch": 0.5428571428571428,
|
| 139 |
+
"grad_norm": 3.480663776397705,
|
| 140 |
+
"learning_rate": 0.00040952380952380955,
|
| 141 |
+
"loss": 1.3543,
|
| 142 |
"step": 190
|
| 143 |
},
|
| 144 |
{
|
| 145 |
"epoch": 0.5714285714285714,
|
| 146 |
+
"grad_norm": 3.168818712234497,
|
| 147 |
+
"learning_rate": 0.0004047619047619048,
|
| 148 |
+
"loss": 1.2619,
|
| 149 |
"step": 200
|
| 150 |
},
|
| 151 |
{
|
| 152 |
"epoch": 0.6,
|
| 153 |
+
"grad_norm": 2.7529921531677246,
|
| 154 |
+
"learning_rate": 0.0004,
|
| 155 |
+
"loss": 1.1871,
|
| 156 |
"step": 210
|
| 157 |
},
|
| 158 |
{
|
| 159 |
"epoch": 0.6285714285714286,
|
| 160 |
+
"grad_norm": 6.538937568664551,
|
| 161 |
+
"learning_rate": 0.00039523809523809526,
|
| 162 |
+
"loss": 1.268,
|
| 163 |
"step": 220
|
| 164 |
},
|
| 165 |
{
|
| 166 |
"epoch": 0.6571428571428571,
|
| 167 |
+
"grad_norm": 3.3910727500915527,
|
| 168 |
+
"learning_rate": 0.0003904761904761905,
|
| 169 |
+
"loss": 1.4192,
|
| 170 |
"step": 230
|
| 171 |
},
|
| 172 |
{
|
| 173 |
"epoch": 0.6857142857142857,
|
| 174 |
+
"grad_norm": 2.31817889213562,
|
| 175 |
+
"learning_rate": 0.0003857142857142857,
|
| 176 |
+
"loss": 1.2339,
|
| 177 |
"step": 240
|
| 178 |
},
|
| 179 |
{
|
| 180 |
"epoch": 0.7142857142857143,
|
| 181 |
+
"grad_norm": 2.8181235790252686,
|
| 182 |
+
"learning_rate": 0.00038095238095238096,
|
| 183 |
+
"loss": 1.3153,
|
| 184 |
"step": 250
|
| 185 |
},
|
| 186 |
{
|
| 187 |
"epoch": 0.7428571428571429,
|
| 188 |
+
"grad_norm": 2.5716922283172607,
|
| 189 |
+
"learning_rate": 0.0003761904761904762,
|
| 190 |
+
"loss": 1.2066,
|
| 191 |
"step": 260
|
| 192 |
},
|
| 193 |
{
|
| 194 |
"epoch": 0.7714285714285715,
|
| 195 |
+
"grad_norm": 5.403870105743408,
|
| 196 |
+
"learning_rate": 0.00037142857142857143,
|
| 197 |
+
"loss": 1.2784,
|
| 198 |
"step": 270
|
| 199 |
},
|
| 200 |
{
|
| 201 |
"epoch": 0.8,
|
| 202 |
+
"grad_norm": 3.347729206085205,
|
| 203 |
+
"learning_rate": 0.00036666666666666667,
|
| 204 |
+
"loss": 1.2273,
|
| 205 |
"step": 280
|
| 206 |
},
|
| 207 |
{
|
| 208 |
"epoch": 0.8285714285714286,
|
| 209 |
+
"grad_norm": 2.7995996475219727,
|
| 210 |
+
"learning_rate": 0.0003619047619047619,
|
| 211 |
+
"loss": 1.159,
|
| 212 |
"step": 290
|
| 213 |
},
|
| 214 |
{
|
| 215 |
"epoch": 0.8571428571428571,
|
| 216 |
+
"grad_norm": 3.817213535308838,
|
| 217 |
+
"learning_rate": 0.00035714285714285714,
|
| 218 |
+
"loss": 1.1146,
|
| 219 |
"step": 300
|
| 220 |
},
|
| 221 |
{
|
| 222 |
"epoch": 0.8857142857142857,
|
| 223 |
+
"grad_norm": 3.3239715099334717,
|
| 224 |
+
"learning_rate": 0.00035238095238095243,
|
| 225 |
+
"loss": 1.1513,
|
| 226 |
"step": 310
|
| 227 |
},
|
| 228 |
{
|
| 229 |
"epoch": 0.9142857142857143,
|
| 230 |
+
"grad_norm": 3.042973518371582,
|
| 231 |
+
"learning_rate": 0.0003476190476190476,
|
| 232 |
+
"loss": 1.3906,
|
| 233 |
"step": 320
|
| 234 |
},
|
| 235 |
{
|
| 236 |
"epoch": 0.9428571428571428,
|
| 237 |
+
"grad_norm": 2.8079681396484375,
|
| 238 |
+
"learning_rate": 0.00034285714285714285,
|
| 239 |
+
"loss": 1.1547,
|
| 240 |
"step": 330
|
| 241 |
},
|
| 242 |
{
|
| 243 |
"epoch": 0.9714285714285714,
|
| 244 |
+
"grad_norm": 6.39453649520874,
|
| 245 |
+
"learning_rate": 0.00033809523809523814,
|
| 246 |
+
"loss": 1.0989,
|
| 247 |
"step": 340
|
| 248 |
},
|
| 249 |
{
|
| 250 |
"epoch": 1.0,
|
| 251 |
+
"grad_norm": 5.739945411682129,
|
| 252 |
+
"learning_rate": 0.0003333333333333333,
|
| 253 |
+
"loss": 1.1563,
|
| 254 |
"step": 350
|
| 255 |
},
|
| 256 |
{
|
| 257 |
"epoch": 1.0,
|
| 258 |
+
"eval_loss": 1.064656376838684,
|
| 259 |
+
"eval_runtime": 16.5324,
|
| 260 |
+
"eval_samples_per_second": 12.097,
|
| 261 |
+
"eval_steps_per_second": 1.512,
|
| 262 |
"step": 350
|
| 263 |
},
|
| 264 |
{
|
| 265 |
"epoch": 1.0285714285714285,
|
| 266 |
+
"grad_norm": 5.899299144744873,
|
| 267 |
+
"learning_rate": 0.00032857142857142856,
|
| 268 |
+
"loss": 1.0649,
|
| 269 |
"step": 360
|
| 270 |
},
|
| 271 |
{
|
| 272 |
"epoch": 1.0571428571428572,
|
| 273 |
+
"grad_norm": 3.3639721870422363,
|
| 274 |
+
"learning_rate": 0.00032380952380952385,
|
| 275 |
+
"loss": 1.1595,
|
| 276 |
"step": 370
|
| 277 |
},
|
| 278 |
{
|
| 279 |
"epoch": 1.0857142857142856,
|
| 280 |
+
"grad_norm": 2.811561346054077,
|
| 281 |
+
"learning_rate": 0.00031904761904761903,
|
| 282 |
+
"loss": 1.0871,
|
| 283 |
"step": 380
|
| 284 |
},
|
| 285 |
{
|
| 286 |
"epoch": 1.1142857142857143,
|
| 287 |
+
"grad_norm": 2.6730055809020996,
|
| 288 |
+
"learning_rate": 0.00031428571428571427,
|
| 289 |
+
"loss": 1.0294,
|
| 290 |
"step": 390
|
| 291 |
},
|
| 292 |
{
|
| 293 |
"epoch": 1.1428571428571428,
|
| 294 |
+
"grad_norm": 5.02337646484375,
|
| 295 |
+
"learning_rate": 0.00030952380952380956,
|
| 296 |
+
"loss": 1.0844,
|
| 297 |
"step": 400
|
| 298 |
},
|
| 299 |
{
|
| 300 |
"epoch": 1.1714285714285715,
|
| 301 |
+
"grad_norm": 4.188799858093262,
|
| 302 |
+
"learning_rate": 0.0003047619047619048,
|
| 303 |
+
"loss": 1.0464,
|
| 304 |
"step": 410
|
| 305 |
},
|
| 306 |
{
|
| 307 |
"epoch": 1.2,
|
| 308 |
+
"grad_norm": 5.055841445922852,
|
| 309 |
+
"learning_rate": 0.0003,
|
| 310 |
+
"loss": 1.1078,
|
| 311 |
"step": 420
|
| 312 |
},
|
| 313 |
{
|
| 314 |
"epoch": 1.2285714285714286,
|
| 315 |
+
"grad_norm": 8.09494400024414,
|
| 316 |
+
"learning_rate": 0.00029523809523809526,
|
| 317 |
+
"loss": 1.0539,
|
| 318 |
"step": 430
|
| 319 |
},
|
| 320 |
{
|
| 321 |
"epoch": 1.2571428571428571,
|
| 322 |
+
"grad_norm": 3.012653112411499,
|
| 323 |
+
"learning_rate": 0.0002904761904761905,
|
| 324 |
+
"loss": 0.927,
|
| 325 |
"step": 440
|
| 326 |
},
|
| 327 |
{
|
| 328 |
"epoch": 1.2857142857142856,
|
| 329 |
+
"grad_norm": 8.38936710357666,
|
| 330 |
+
"learning_rate": 0.0002857142857142857,
|
| 331 |
+
"loss": 1.2209,
|
| 332 |
"step": 450
|
| 333 |
},
|
| 334 |
{
|
| 335 |
"epoch": 1.3142857142857143,
|
| 336 |
+
"grad_norm": 4.191105365753174,
|
| 337 |
+
"learning_rate": 0.00028095238095238097,
|
| 338 |
+
"loss": 1.0086,
|
| 339 |
"step": 460
|
| 340 |
},
|
| 341 |
{
|
| 342 |
"epoch": 1.342857142857143,
|
| 343 |
+
"grad_norm": 2.9886045455932617,
|
| 344 |
+
"learning_rate": 0.0002761904761904762,
|
| 345 |
+
"loss": 1.0788,
|
| 346 |
"step": 470
|
| 347 |
},
|
| 348 |
{
|
| 349 |
"epoch": 1.3714285714285714,
|
| 350 |
+
"grad_norm": 3.5892975330352783,
|
| 351 |
+
"learning_rate": 0.0002714285714285714,
|
| 352 |
+
"loss": 1.0877,
|
| 353 |
"step": 480
|
| 354 |
},
|
| 355 |
{
|
| 356 |
"epoch": 1.4,
|
| 357 |
+
"grad_norm": 4.504238128662109,
|
| 358 |
+
"learning_rate": 0.0002666666666666667,
|
| 359 |
+
"loss": 1.0066,
|
| 360 |
"step": 490
|
| 361 |
},
|
| 362 |
{
|
| 363 |
"epoch": 1.4285714285714286,
|
| 364 |
+
"grad_norm": 3.601853132247925,
|
| 365 |
+
"learning_rate": 0.0002619047619047619,
|
| 366 |
+
"loss": 0.9915,
|
| 367 |
"step": 500
|
| 368 |
},
|
| 369 |
{
|
| 370 |
"epoch": 1.457142857142857,
|
| 371 |
+
"grad_norm": 4.008484840393066,
|
| 372 |
+
"learning_rate": 0.0002571428571428571,
|
| 373 |
+
"loss": 0.9651,
|
| 374 |
"step": 510
|
| 375 |
},
|
| 376 |
{
|
| 377 |
"epoch": 1.4857142857142858,
|
| 378 |
+
"grad_norm": 5.5403900146484375,
|
| 379 |
+
"learning_rate": 0.0002523809523809524,
|
| 380 |
+
"loss": 0.9018,
|
| 381 |
"step": 520
|
| 382 |
},
|
| 383 |
{
|
| 384 |
"epoch": 1.5142857142857142,
|
| 385 |
+
"grad_norm": 3.526982069015503,
|
| 386 |
+
"learning_rate": 0.0002476190476190476,
|
| 387 |
+
"loss": 0.9588,
|
| 388 |
"step": 530
|
| 389 |
},
|
| 390 |
{
|
| 391 |
"epoch": 1.5428571428571427,
|
| 392 |
+
"grad_norm": 3.666804075241089,
|
| 393 |
+
"learning_rate": 0.00024285714285714286,
|
| 394 |
+
"loss": 1.0092,
|
| 395 |
"step": 540
|
| 396 |
},
|
| 397 |
{
|
| 398 |
"epoch": 1.5714285714285714,
|
| 399 |
+
"grad_norm": 3.4340310096740723,
|
| 400 |
+
"learning_rate": 0.0002380952380952381,
|
| 401 |
+
"loss": 0.9342,
|
| 402 |
"step": 550
|
| 403 |
},
|
| 404 |
{
|
| 405 |
"epoch": 1.6,
|
| 406 |
+
"grad_norm": 5.815408229827881,
|
| 407 |
+
"learning_rate": 0.00023333333333333333,
|
| 408 |
+
"loss": 1.0666,
|
| 409 |
"step": 560
|
| 410 |
},
|
| 411 |
{
|
| 412 |
"epoch": 1.6285714285714286,
|
| 413 |
+
"grad_norm": 2.7780840396881104,
|
| 414 |
+
"learning_rate": 0.00022857142857142857,
|
| 415 |
+
"loss": 1.1026,
|
| 416 |
"step": 570
|
| 417 |
},
|
| 418 |
{
|
| 419 |
"epoch": 1.657142857142857,
|
| 420 |
+
"grad_norm": 3.8484044075012207,
|
| 421 |
+
"learning_rate": 0.00022380952380952383,
|
| 422 |
+
"loss": 0.937,
|
| 423 |
"step": 580
|
| 424 |
},
|
| 425 |
{
|
| 426 |
"epoch": 1.6857142857142857,
|
| 427 |
+
"grad_norm": 3.819007635116577,
|
| 428 |
+
"learning_rate": 0.00021904761904761904,
|
| 429 |
+
"loss": 1.1247,
|
| 430 |
"step": 590
|
| 431 |
},
|
| 432 |
{
|
| 433 |
"epoch": 1.7142857142857144,
|
| 434 |
+
"grad_norm": 3.8324477672576904,
|
| 435 |
+
"learning_rate": 0.00021428571428571427,
|
| 436 |
+
"loss": 0.9961,
|
| 437 |
"step": 600
|
| 438 |
},
|
| 439 |
{
|
| 440 |
"epoch": 1.7428571428571429,
|
| 441 |
+
"grad_norm": 3.2769389152526855,
|
| 442 |
+
"learning_rate": 0.00020952380952380954,
|
| 443 |
+
"loss": 0.9987,
|
| 444 |
"step": 610
|
| 445 |
},
|
| 446 |
{
|
| 447 |
"epoch": 1.7714285714285714,
|
| 448 |
+
"grad_norm": 5.3248443603515625,
|
| 449 |
+
"learning_rate": 0.00020476190476190477,
|
| 450 |
+
"loss": 0.9219,
|
| 451 |
"step": 620
|
| 452 |
},
|
| 453 |
{
|
| 454 |
"epoch": 1.8,
|
| 455 |
+
"grad_norm": 2.6656081676483154,
|
| 456 |
+
"learning_rate": 0.0002,
|
| 457 |
+
"loss": 1.0293,
|
| 458 |
"step": 630
|
| 459 |
},
|
| 460 |
{
|
| 461 |
"epoch": 1.8285714285714287,
|
| 462 |
+
"grad_norm": 2.6429567337036133,
|
| 463 |
+
"learning_rate": 0.00019523809523809525,
|
| 464 |
+
"loss": 1.0106,
|
| 465 |
"step": 640
|
| 466 |
},
|
| 467 |
{
|
| 468 |
"epoch": 1.8571428571428572,
|
| 469 |
+
"grad_norm": 4.4341864585876465,
|
| 470 |
+
"learning_rate": 0.00019047619047619048,
|
| 471 |
+
"loss": 0.8426,
|
| 472 |
"step": 650
|
| 473 |
},
|
| 474 |
{
|
| 475 |
"epoch": 1.8857142857142857,
|
| 476 |
+
"grad_norm": 4.535873889923096,
|
| 477 |
+
"learning_rate": 0.00018571428571428572,
|
| 478 |
+
"loss": 0.9335,
|
| 479 |
"step": 660
|
| 480 |
},
|
| 481 |
{
|
| 482 |
"epoch": 1.9142857142857141,
|
| 483 |
+
"grad_norm": 4.100979328155518,
|
| 484 |
+
"learning_rate": 0.00018095238095238095,
|
| 485 |
+
"loss": 0.9936,
|
| 486 |
"step": 670
|
| 487 |
},
|
| 488 |
{
|
| 489 |
"epoch": 1.9428571428571428,
|
| 490 |
+
"grad_norm": 4.034025192260742,
|
| 491 |
+
"learning_rate": 0.00017619047619047622,
|
| 492 |
+
"loss": 0.9305,
|
| 493 |
"step": 680
|
| 494 |
},
|
| 495 |
{
|
| 496 |
"epoch": 1.9714285714285715,
|
| 497 |
+
"grad_norm": 3.618300676345825,
|
| 498 |
+
"learning_rate": 0.00017142857142857143,
|
| 499 |
+
"loss": 0.975,
|
| 500 |
"step": 690
|
| 501 |
},
|
| 502 |
{
|
| 503 |
"epoch": 2.0,
|
| 504 |
+
"grad_norm": 3.0254437923431396,
|
| 505 |
+
"learning_rate": 0.00016666666666666666,
|
| 506 |
+
"loss": 0.997,
|
| 507 |
"step": 700
|
| 508 |
},
|
| 509 |
{
|
| 510 |
"epoch": 2.0,
|
| 511 |
+
"eval_loss": 0.893572211265564,
|
| 512 |
+
"eval_runtime": 16.613,
|
| 513 |
+
"eval_samples_per_second": 12.039,
|
| 514 |
+
"eval_steps_per_second": 1.505,
|
| 515 |
"step": 700
|
| 516 |
}
|
| 517 |
],
|
|
|
|
| 532 |
"attributes": {}
|
| 533 |
}
|
| 534 |
},
|
| 535 |
+
"total_flos": 4188970942464000.0,
|
| 536 |
"train_batch_size": 8,
|
| 537 |
"trial_name": null,
|
| 538 |
"trial_params": null
|
checkpoint-700/training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5240
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1982b07d8277b0bc7aaf4f34307bfaa24bd97b8994cd2c48e972769e68324f20
|
| 3 |
size 5240
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5240
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1982b07d8277b0bc7aaf4f34307bfaa24bd97b8994cd2c48e972769e68324f20
|
| 3 |
size 5240
|