Model save
Browse files- adapter_config.json +3 -3
- adapter_model.safetensors +1 -1
- all_results.json +4 -4
- runs/Feb06_23-24-31_GCRAZGDL1601/events.out.tfevents.1738884276.GCRAZGDL1601.3098201.0 +3 -0
- train_results.json +4 -4
- trainer_state.json +339 -339
- training_args.bin +1 -1
adapter_config.json
CHANGED
|
@@ -21,12 +21,12 @@
|
|
| 21 |
"revision": null,
|
| 22 |
"target_modules": [
|
| 23 |
"up_proj",
|
| 24 |
-
"v_proj",
|
| 25 |
"q_proj",
|
|
|
|
| 26 |
"gate_proj",
|
| 27 |
"k_proj",
|
| 28 |
-
"
|
| 29 |
-
"
|
| 30 |
],
|
| 31 |
"task_type": "CAUSAL_LM",
|
| 32 |
"use_dora": false,
|
|
|
|
| 21 |
"revision": null,
|
| 22 |
"target_modules": [
|
| 23 |
"up_proj",
|
|
|
|
| 24 |
"q_proj",
|
| 25 |
+
"v_proj",
|
| 26 |
"gate_proj",
|
| 27 |
"k_proj",
|
| 28 |
+
"o_proj",
|
| 29 |
+
"down_proj"
|
| 30 |
],
|
| 31 |
"task_type": "CAUSAL_LM",
|
| 32 |
"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 73911112
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9439f84441ba4a34585d5554e5f06048fe4bc93effd918b82410f94c5bf6edc7
|
| 3 |
size 73911112
|
all_results.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 0.9991079393398751,
|
| 3 |
"total_flos": 8.398274691072e+17,
|
| 4 |
-
"train_loss": 0.
|
| 5 |
-
"train_runtime":
|
| 6 |
"train_samples": 16710,
|
| 7 |
-
"train_samples_per_second":
|
| 8 |
-
"train_steps_per_second":
|
| 9 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 0.9991079393398751,
|
| 3 |
"total_flos": 8.398274691072e+17,
|
| 4 |
+
"train_loss": 0.5889353160347257,
|
| 5 |
+
"train_runtime": 8886.9999,
|
| 6 |
"train_samples": 16710,
|
| 7 |
+
"train_samples_per_second": 1.009,
|
| 8 |
+
"train_steps_per_second": 0.063
|
| 9 |
}
|
runs/Feb06_23-24-31_GCRAZGDL1601/events.out.tfevents.1738884276.GCRAZGDL1601.3098201.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:63fbc7d88f143ec334dee35764121bf41e0a33f92c44c7407b43f6de224f6a2c
|
| 3 |
+
size 30021
|
train_results.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 0.9991079393398751,
|
| 3 |
"total_flos": 8.398274691072e+17,
|
| 4 |
-
"train_loss": 0.
|
| 5 |
-
"train_runtime":
|
| 6 |
"train_samples": 16710,
|
| 7 |
-
"train_samples_per_second":
|
| 8 |
-
"train_steps_per_second":
|
| 9 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 0.9991079393398751,
|
| 3 |
"total_flos": 8.398274691072e+17,
|
| 4 |
+
"train_loss": 0.5889353160347257,
|
| 5 |
+
"train_runtime": 8886.9999,
|
| 6 |
"train_samples": 16710,
|
| 7 |
+
"train_samples_per_second": 1.009,
|
| 8 |
+
"train_steps_per_second": 0.063
|
| 9 |
}
|
trainer_state.json
CHANGED
|
@@ -9,797 +9,797 @@
|
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
-
"epoch": 0.
|
| 13 |
-
"grad_norm": 0.
|
| 14 |
"learning_rate": 0.0002,
|
| 15 |
-
"loss": 0.
|
| 16 |
"step": 5
|
| 17 |
},
|
| 18 |
{
|
| 19 |
-
"epoch": 0.
|
| 20 |
-
"grad_norm": 0.
|
| 21 |
"learning_rate": 0.0002,
|
| 22 |
-
"loss": 0.
|
| 23 |
"step": 10
|
| 24 |
},
|
| 25 |
{
|
| 26 |
-
"epoch": 0.
|
| 27 |
-
"grad_norm": 0.
|
| 28 |
"learning_rate": 0.0002,
|
| 29 |
-
"loss": 0.
|
| 30 |
"step": 15
|
| 31 |
},
|
| 32 |
{
|
| 33 |
-
"epoch": 0.
|
| 34 |
-
"grad_norm": 0.
|
| 35 |
"learning_rate": 0.0002,
|
| 36 |
-
"loss": 0.
|
| 37 |
"step": 20
|
| 38 |
},
|
| 39 |
{
|
| 40 |
-
"epoch": 0.
|
| 41 |
-
"grad_norm": 0.
|
| 42 |
"learning_rate": 0.0002,
|
| 43 |
-
"loss": 0.
|
| 44 |
"step": 25
|
| 45 |
},
|
| 46 |
{
|
| 47 |
-
"epoch": 0.
|
| 48 |
-
"grad_norm": 0.
|
| 49 |
"learning_rate": 0.0002,
|
| 50 |
-
"loss": 0.
|
| 51 |
"step": 30
|
| 52 |
},
|
| 53 |
{
|
| 54 |
-
"epoch": 0.
|
| 55 |
-
"grad_norm": 0.
|
| 56 |
"learning_rate": 0.0002,
|
| 57 |
-
"loss": 0.
|
| 58 |
"step": 35
|
| 59 |
},
|
| 60 |
{
|
| 61 |
-
"epoch": 0.
|
| 62 |
-
"grad_norm": 0.
|
| 63 |
"learning_rate": 0.0002,
|
| 64 |
-
"loss": 0.
|
| 65 |
"step": 40
|
| 66 |
},
|
| 67 |
{
|
| 68 |
-
"epoch": 0.
|
| 69 |
-
"grad_norm": 0.
|
| 70 |
"learning_rate": 0.0002,
|
| 71 |
-
"loss": 0.
|
| 72 |
"step": 45
|
| 73 |
},
|
| 74 |
{
|
| 75 |
-
"epoch": 0.
|
| 76 |
-
"grad_norm": 0.
|
| 77 |
"learning_rate": 0.0002,
|
| 78 |
-
"loss": 0.
|
| 79 |
"step": 50
|
| 80 |
},
|
| 81 |
{
|
| 82 |
-
"epoch": 0.
|
| 83 |
-
"grad_norm": 0.
|
| 84 |
"learning_rate": 0.0002,
|
| 85 |
-
"loss": 0.
|
| 86 |
"step": 55
|
| 87 |
},
|
| 88 |
{
|
| 89 |
-
"epoch": 0.
|
| 90 |
-
"grad_norm": 0.
|
| 91 |
"learning_rate": 0.0002,
|
| 92 |
-
"loss": 0.
|
| 93 |
"step": 60
|
| 94 |
},
|
| 95 |
{
|
| 96 |
-
"epoch": 0.
|
| 97 |
-
"grad_norm": 0.
|
| 98 |
"learning_rate": 0.0002,
|
| 99 |
-
"loss": 0.
|
| 100 |
"step": 65
|
| 101 |
},
|
| 102 |
{
|
| 103 |
-
"epoch": 0.
|
| 104 |
-
"grad_norm": 0.
|
| 105 |
"learning_rate": 0.0002,
|
| 106 |
-
"loss": 0.
|
| 107 |
"step": 70
|
| 108 |
},
|
| 109 |
{
|
| 110 |
-
"epoch": 0.
|
| 111 |
-
"grad_norm": 0.
|
| 112 |
"learning_rate": 0.0002,
|
| 113 |
-
"loss": 0.
|
| 114 |
"step": 75
|
| 115 |
},
|
| 116 |
{
|
| 117 |
-
"epoch": 0.
|
| 118 |
-
"grad_norm": 0.
|
| 119 |
"learning_rate": 0.0002,
|
| 120 |
-
"loss": 0.
|
| 121 |
"step": 80
|
| 122 |
},
|
| 123 |
{
|
| 124 |
-
"epoch": 0.
|
| 125 |
-
"grad_norm": 0.
|
| 126 |
"learning_rate": 0.0002,
|
| 127 |
-
"loss": 0.
|
| 128 |
"step": 85
|
| 129 |
},
|
| 130 |
{
|
| 131 |
-
"epoch": 0.
|
| 132 |
-
"grad_norm": 0.
|
| 133 |
"learning_rate": 0.0002,
|
| 134 |
-
"loss": 0.
|
| 135 |
"step": 90
|
| 136 |
},
|
| 137 |
{
|
| 138 |
-
"epoch": 0.
|
| 139 |
-
"grad_norm": 0.
|
| 140 |
"learning_rate": 0.0002,
|
| 141 |
-
"loss": 0.
|
| 142 |
"step": 95
|
| 143 |
},
|
| 144 |
{
|
| 145 |
-
"epoch": 0.
|
| 146 |
-
"grad_norm": 0.
|
| 147 |
"learning_rate": 0.0002,
|
| 148 |
-
"loss": 0.
|
| 149 |
"step": 100
|
| 150 |
},
|
| 151 |
{
|
| 152 |
-
"epoch": 0.
|
| 153 |
-
"grad_norm": 0.
|
| 154 |
"learning_rate": 0.0002,
|
| 155 |
-
"loss": 0.
|
| 156 |
"step": 105
|
| 157 |
},
|
| 158 |
{
|
| 159 |
-
"epoch": 0.
|
| 160 |
-
"grad_norm": 0.
|
| 161 |
"learning_rate": 0.0002,
|
| 162 |
-
"loss": 0.
|
| 163 |
"step": 110
|
| 164 |
},
|
| 165 |
{
|
| 166 |
-
"epoch": 0.
|
| 167 |
-
"grad_norm": 0.
|
| 168 |
"learning_rate": 0.0002,
|
| 169 |
-
"loss": 0.
|
| 170 |
"step": 115
|
| 171 |
},
|
| 172 |
{
|
| 173 |
-
"epoch": 0.
|
| 174 |
-
"grad_norm": 0.
|
| 175 |
"learning_rate": 0.0002,
|
| 176 |
-
"loss": 0.
|
| 177 |
"step": 120
|
| 178 |
},
|
| 179 |
{
|
| 180 |
-
"epoch": 0.
|
| 181 |
-
"grad_norm": 0.
|
| 182 |
"learning_rate": 0.0002,
|
| 183 |
-
"loss": 0.
|
| 184 |
"step": 125
|
| 185 |
},
|
| 186 |
{
|
| 187 |
-
"epoch": 0.
|
| 188 |
-
"grad_norm": 0.
|
| 189 |
"learning_rate": 0.0002,
|
| 190 |
-
"loss": 0.
|
| 191 |
"step": 130
|
| 192 |
},
|
| 193 |
{
|
| 194 |
-
"epoch": 0.
|
| 195 |
-
"grad_norm": 0.
|
| 196 |
"learning_rate": 0.0002,
|
| 197 |
-
"loss": 0.
|
| 198 |
"step": 135
|
| 199 |
},
|
| 200 |
{
|
| 201 |
-
"epoch": 0.
|
| 202 |
-
"grad_norm": 0.
|
| 203 |
"learning_rate": 0.0002,
|
| 204 |
-
"loss": 0.
|
| 205 |
"step": 140
|
| 206 |
},
|
| 207 |
{
|
| 208 |
-
"epoch": 0.
|
| 209 |
-
"grad_norm": 0.
|
| 210 |
"learning_rate": 0.0002,
|
| 211 |
-
"loss": 0.
|
| 212 |
"step": 145
|
| 213 |
},
|
| 214 |
{
|
| 215 |
-
"epoch": 0.
|
| 216 |
-
"grad_norm": 0.
|
| 217 |
"learning_rate": 0.0002,
|
| 218 |
-
"loss": 0.
|
| 219 |
"step": 150
|
| 220 |
},
|
| 221 |
{
|
| 222 |
-
"epoch": 0.
|
| 223 |
-
"grad_norm": 0.
|
| 224 |
"learning_rate": 0.0002,
|
| 225 |
-
"loss": 0.
|
| 226 |
"step": 155
|
| 227 |
},
|
| 228 |
{
|
| 229 |
-
"epoch": 0.
|
| 230 |
-
"grad_norm": 0.
|
| 231 |
"learning_rate": 0.0002,
|
| 232 |
-
"loss": 0.
|
| 233 |
"step": 160
|
| 234 |
},
|
| 235 |
{
|
| 236 |
-
"epoch": 0.
|
| 237 |
-
"grad_norm": 0.
|
| 238 |
"learning_rate": 0.0002,
|
| 239 |
-
"loss": 0.
|
| 240 |
"step": 165
|
| 241 |
},
|
| 242 |
{
|
| 243 |
-
"epoch": 0.
|
| 244 |
-
"grad_norm": 0.
|
| 245 |
"learning_rate": 0.0002,
|
| 246 |
-
"loss": 0.
|
| 247 |
"step": 170
|
| 248 |
},
|
| 249 |
{
|
| 250 |
-
"epoch": 0.
|
| 251 |
-
"grad_norm": 0.
|
| 252 |
"learning_rate": 0.0002,
|
| 253 |
-
"loss": 0.
|
| 254 |
"step": 175
|
| 255 |
},
|
| 256 |
{
|
| 257 |
-
"epoch": 0.
|
| 258 |
-
"grad_norm": 0.
|
| 259 |
"learning_rate": 0.0002,
|
| 260 |
-
"loss": 0.
|
| 261 |
"step": 180
|
| 262 |
},
|
| 263 |
{
|
| 264 |
-
"epoch": 0.
|
| 265 |
-
"grad_norm": 0.
|
| 266 |
"learning_rate": 0.0002,
|
| 267 |
-
"loss": 0.
|
| 268 |
"step": 185
|
| 269 |
},
|
| 270 |
{
|
| 271 |
-
"epoch": 0.
|
| 272 |
-
"grad_norm": 0.
|
| 273 |
"learning_rate": 0.0002,
|
| 274 |
-
"loss": 0.
|
| 275 |
"step": 190
|
| 276 |
},
|
| 277 |
{
|
| 278 |
-
"epoch": 0.
|
| 279 |
-
"grad_norm": 0.
|
| 280 |
"learning_rate": 0.0002,
|
| 281 |
-
"loss": 0.
|
| 282 |
"step": 195
|
| 283 |
},
|
| 284 |
{
|
| 285 |
-
"epoch": 0.
|
| 286 |
-
"grad_norm": 0.
|
| 287 |
"learning_rate": 0.0002,
|
| 288 |
-
"loss": 0.
|
| 289 |
"step": 200
|
| 290 |
},
|
| 291 |
{
|
| 292 |
-
"epoch": 0.
|
| 293 |
-
"grad_norm": 0.
|
| 294 |
"learning_rate": 0.0002,
|
| 295 |
-
"loss": 0.
|
| 296 |
"step": 205
|
| 297 |
},
|
| 298 |
{
|
| 299 |
-
"epoch": 0.
|
| 300 |
-
"grad_norm": 0.
|
| 301 |
"learning_rate": 0.0002,
|
| 302 |
-
"loss": 0.
|
| 303 |
"step": 210
|
| 304 |
},
|
| 305 |
{
|
| 306 |
-
"epoch": 0.
|
| 307 |
-
"grad_norm": 0.
|
| 308 |
"learning_rate": 0.0002,
|
| 309 |
-
"loss": 0.
|
| 310 |
"step": 215
|
| 311 |
},
|
| 312 |
{
|
| 313 |
-
"epoch": 0.
|
| 314 |
-
"grad_norm": 0.
|
| 315 |
"learning_rate": 0.0002,
|
| 316 |
-
"loss": 0.
|
| 317 |
"step": 220
|
| 318 |
},
|
| 319 |
{
|
| 320 |
-
"epoch": 0.
|
| 321 |
-
"grad_norm": 0.
|
| 322 |
"learning_rate": 0.0002,
|
| 323 |
-
"loss": 0.
|
| 324 |
"step": 225
|
| 325 |
},
|
| 326 |
{
|
| 327 |
-
"epoch": 0.
|
| 328 |
-
"grad_norm": 0.
|
| 329 |
"learning_rate": 0.0002,
|
| 330 |
-
"loss": 0.
|
| 331 |
"step": 230
|
| 332 |
},
|
| 333 |
{
|
| 334 |
-
"epoch": 0.
|
| 335 |
-
"grad_norm": 0.
|
| 336 |
"learning_rate": 0.0002,
|
| 337 |
-
"loss": 0.
|
| 338 |
"step": 235
|
| 339 |
},
|
| 340 |
{
|
| 341 |
-
"epoch": 0.
|
| 342 |
-
"grad_norm": 0.
|
| 343 |
"learning_rate": 0.0002,
|
| 344 |
-
"loss": 0.
|
| 345 |
"step": 240
|
| 346 |
},
|
| 347 |
{
|
| 348 |
-
"epoch": 0.
|
| 349 |
-
"grad_norm": 0.
|
| 350 |
"learning_rate": 0.0002,
|
| 351 |
-
"loss": 0.
|
| 352 |
"step": 245
|
| 353 |
},
|
| 354 |
{
|
| 355 |
-
"epoch": 0.
|
| 356 |
-
"grad_norm": 0.
|
| 357 |
"learning_rate": 0.0002,
|
| 358 |
-
"loss": 0.
|
| 359 |
"step": 250
|
| 360 |
},
|
| 361 |
{
|
| 362 |
-
"epoch": 0.
|
| 363 |
-
"grad_norm": 0.
|
| 364 |
"learning_rate": 0.0002,
|
| 365 |
-
"loss": 0.
|
| 366 |
"step": 255
|
| 367 |
},
|
| 368 |
{
|
| 369 |
-
"epoch": 0.
|
| 370 |
-
"grad_norm": 0.
|
| 371 |
"learning_rate": 0.0002,
|
| 372 |
-
"loss": 0.
|
| 373 |
"step": 260
|
| 374 |
},
|
| 375 |
{
|
| 376 |
-
"epoch": 0.
|
| 377 |
-
"grad_norm": 0.
|
| 378 |
"learning_rate": 0.0002,
|
| 379 |
-
"loss": 0.
|
| 380 |
"step": 265
|
| 381 |
},
|
| 382 |
{
|
| 383 |
-
"epoch": 0.
|
| 384 |
-
"grad_norm": 0.
|
| 385 |
"learning_rate": 0.0002,
|
| 386 |
-
"loss": 0.
|
| 387 |
"step": 270
|
| 388 |
},
|
| 389 |
{
|
| 390 |
-
"epoch": 0.
|
| 391 |
-
"grad_norm": 0.
|
| 392 |
"learning_rate": 0.0002,
|
| 393 |
-
"loss": 0.
|
| 394 |
"step": 275
|
| 395 |
},
|
| 396 |
{
|
| 397 |
-
"epoch": 0.
|
| 398 |
-
"grad_norm": 0.
|
| 399 |
"learning_rate": 0.0002,
|
| 400 |
-
"loss": 0.
|
| 401 |
"step": 280
|
| 402 |
},
|
| 403 |
{
|
| 404 |
-
"epoch": 0.
|
| 405 |
-
"grad_norm": 0.
|
| 406 |
"learning_rate": 0.0002,
|
| 407 |
-
"loss": 0.
|
| 408 |
"step": 285
|
| 409 |
},
|
| 410 |
{
|
| 411 |
-
"epoch": 0.
|
| 412 |
-
"grad_norm": 0.
|
| 413 |
"learning_rate": 0.0002,
|
| 414 |
-
"loss": 0.
|
| 415 |
"step": 290
|
| 416 |
},
|
| 417 |
{
|
| 418 |
-
"epoch": 0.
|
| 419 |
-
"grad_norm": 0.
|
| 420 |
"learning_rate": 0.0002,
|
| 421 |
-
"loss": 0.
|
| 422 |
"step": 295
|
| 423 |
},
|
| 424 |
{
|
| 425 |
-
"epoch": 0.
|
| 426 |
-
"grad_norm": 0.
|
| 427 |
"learning_rate": 0.0002,
|
| 428 |
-
"loss": 0.
|
| 429 |
"step": 300
|
| 430 |
},
|
| 431 |
{
|
| 432 |
-
"epoch": 0.
|
| 433 |
-
"grad_norm": 0.
|
| 434 |
"learning_rate": 0.0002,
|
| 435 |
-
"loss": 0.
|
| 436 |
"step": 305
|
| 437 |
},
|
| 438 |
{
|
| 439 |
-
"epoch": 0.
|
| 440 |
-
"grad_norm": 0.
|
| 441 |
"learning_rate": 0.0002,
|
| 442 |
-
"loss": 0.
|
| 443 |
"step": 310
|
| 444 |
},
|
| 445 |
{
|
| 446 |
-
"epoch": 0.
|
| 447 |
-
"grad_norm": 0.
|
| 448 |
"learning_rate": 0.0002,
|
| 449 |
-
"loss": 0.
|
| 450 |
"step": 315
|
| 451 |
},
|
| 452 |
{
|
| 453 |
-
"epoch": 0.
|
| 454 |
-
"grad_norm": 0.
|
| 455 |
"learning_rate": 0.0002,
|
| 456 |
-
"loss": 0.
|
| 457 |
"step": 320
|
| 458 |
},
|
| 459 |
{
|
| 460 |
-
"epoch": 0.
|
| 461 |
-
"grad_norm": 0.
|
| 462 |
"learning_rate": 0.0002,
|
| 463 |
-
"loss": 0.
|
| 464 |
"step": 325
|
| 465 |
},
|
| 466 |
{
|
| 467 |
-
"epoch": 0.
|
| 468 |
-
"grad_norm": 0.
|
| 469 |
"learning_rate": 0.0002,
|
| 470 |
-
"loss": 0.
|
| 471 |
"step": 330
|
| 472 |
},
|
| 473 |
{
|
| 474 |
-
"epoch": 0.
|
| 475 |
-
"grad_norm": 0.
|
| 476 |
"learning_rate": 0.0002,
|
| 477 |
-
"loss": 0.
|
| 478 |
"step": 335
|
| 479 |
},
|
| 480 |
{
|
| 481 |
-
"epoch": 0.
|
| 482 |
-
"grad_norm": 0.
|
| 483 |
"learning_rate": 0.0002,
|
| 484 |
-
"loss": 0.
|
| 485 |
"step": 340
|
| 486 |
},
|
| 487 |
{
|
| 488 |
-
"epoch": 0.
|
| 489 |
-
"grad_norm": 0.
|
| 490 |
"learning_rate": 0.0002,
|
| 491 |
-
"loss": 0.
|
| 492 |
"step": 345
|
| 493 |
},
|
| 494 |
{
|
| 495 |
-
"epoch": 0.
|
| 496 |
-
"grad_norm": 0.
|
| 497 |
"learning_rate": 0.0002,
|
| 498 |
-
"loss": 0.
|
| 499 |
"step": 350
|
| 500 |
},
|
| 501 |
{
|
| 502 |
-
"epoch": 0.
|
| 503 |
-
"grad_norm": 0.
|
| 504 |
"learning_rate": 0.0002,
|
| 505 |
-
"loss": 0.
|
| 506 |
"step": 355
|
| 507 |
},
|
| 508 |
{
|
| 509 |
-
"epoch": 0.
|
| 510 |
-
"grad_norm": 0.
|
| 511 |
"learning_rate": 0.0002,
|
| 512 |
-
"loss": 0.
|
| 513 |
"step": 360
|
| 514 |
},
|
| 515 |
{
|
| 516 |
-
"epoch": 0.
|
| 517 |
-
"grad_norm": 0.
|
| 518 |
"learning_rate": 0.0002,
|
| 519 |
-
"loss": 0.
|
| 520 |
"step": 365
|
| 521 |
},
|
| 522 |
{
|
| 523 |
-
"epoch": 0.
|
| 524 |
-
"grad_norm": 0.
|
| 525 |
"learning_rate": 0.0002,
|
| 526 |
-
"loss": 0.
|
| 527 |
"step": 370
|
| 528 |
},
|
| 529 |
{
|
| 530 |
-
"epoch": 0.
|
| 531 |
-
"grad_norm": 0.
|
| 532 |
"learning_rate": 0.0002,
|
| 533 |
-
"loss": 0.
|
| 534 |
"step": 375
|
| 535 |
},
|
| 536 |
{
|
| 537 |
-
"epoch": 0.
|
| 538 |
-
"grad_norm": 0.
|
| 539 |
"learning_rate": 0.0002,
|
| 540 |
-
"loss": 0.
|
| 541 |
"step": 380
|
| 542 |
},
|
| 543 |
{
|
| 544 |
-
"epoch": 0.
|
| 545 |
-
"grad_norm": 0.
|
| 546 |
"learning_rate": 0.0002,
|
| 547 |
-
"loss": 0.
|
| 548 |
"step": 385
|
| 549 |
},
|
| 550 |
{
|
| 551 |
-
"epoch": 0.
|
| 552 |
-
"grad_norm": 0.
|
| 553 |
"learning_rate": 0.0002,
|
| 554 |
-
"loss": 0.
|
| 555 |
"step": 390
|
| 556 |
},
|
| 557 |
{
|
| 558 |
-
"epoch": 0.
|
| 559 |
-
"grad_norm": 0.
|
| 560 |
"learning_rate": 0.0002,
|
| 561 |
-
"loss": 0.
|
| 562 |
"step": 395
|
| 563 |
},
|
| 564 |
{
|
| 565 |
-
"epoch": 0.
|
| 566 |
-
"grad_norm": 0.
|
| 567 |
"learning_rate": 0.0002,
|
| 568 |
-
"loss": 0.
|
| 569 |
"step": 400
|
| 570 |
},
|
| 571 |
{
|
| 572 |
-
"epoch": 0.
|
| 573 |
-
"grad_norm": 0.
|
| 574 |
"learning_rate": 0.0002,
|
| 575 |
-
"loss": 0.
|
| 576 |
"step": 405
|
| 577 |
},
|
| 578 |
{
|
| 579 |
-
"epoch": 0.
|
| 580 |
-
"grad_norm": 0.
|
| 581 |
"learning_rate": 0.0002,
|
| 582 |
-
"loss": 0.
|
| 583 |
"step": 410
|
| 584 |
},
|
| 585 |
{
|
| 586 |
-
"epoch": 0.
|
| 587 |
-
"grad_norm": 0.
|
| 588 |
"learning_rate": 0.0002,
|
| 589 |
-
"loss": 0.
|
| 590 |
"step": 415
|
| 591 |
},
|
| 592 |
{
|
| 593 |
-
"epoch": 0.
|
| 594 |
-
"grad_norm": 0.
|
| 595 |
"learning_rate": 0.0002,
|
| 596 |
-
"loss": 0.
|
| 597 |
"step": 420
|
| 598 |
},
|
| 599 |
{
|
| 600 |
-
"epoch": 0.
|
| 601 |
-
"grad_norm": 0.
|
| 602 |
"learning_rate": 0.0002,
|
| 603 |
-
"loss": 0.
|
| 604 |
"step": 425
|
| 605 |
},
|
| 606 |
{
|
| 607 |
-
"epoch": 0.
|
| 608 |
-
"grad_norm": 0.
|
| 609 |
"learning_rate": 0.0002,
|
| 610 |
-
"loss": 0.
|
| 611 |
"step": 430
|
| 612 |
},
|
| 613 |
{
|
| 614 |
-
"epoch": 0.
|
| 615 |
-
"grad_norm": 0.
|
| 616 |
"learning_rate": 0.0002,
|
| 617 |
-
"loss": 0.
|
| 618 |
"step": 435
|
| 619 |
},
|
| 620 |
{
|
| 621 |
-
"epoch": 0.
|
| 622 |
-
"grad_norm": 0.
|
| 623 |
"learning_rate": 0.0002,
|
| 624 |
-
"loss": 0.
|
| 625 |
"step": 440
|
| 626 |
},
|
| 627 |
{
|
| 628 |
-
"epoch": 0.
|
| 629 |
-
"grad_norm": 0.
|
| 630 |
"learning_rate": 0.0002,
|
| 631 |
-
"loss": 0.
|
| 632 |
"step": 445
|
| 633 |
},
|
| 634 |
{
|
| 635 |
-
"epoch": 0.
|
| 636 |
-
"grad_norm": 0.
|
| 637 |
"learning_rate": 0.0002,
|
| 638 |
-
"loss": 0.
|
| 639 |
"step": 450
|
| 640 |
},
|
| 641 |
{
|
| 642 |
-
"epoch": 0.
|
| 643 |
-
"grad_norm": 0.
|
| 644 |
"learning_rate": 0.0002,
|
| 645 |
-
"loss": 0.
|
| 646 |
"step": 455
|
| 647 |
},
|
| 648 |
{
|
| 649 |
-
"epoch": 0.
|
| 650 |
-
"grad_norm": 0.
|
| 651 |
"learning_rate": 0.0002,
|
| 652 |
-
"loss": 0.
|
| 653 |
"step": 460
|
| 654 |
},
|
| 655 |
{
|
| 656 |
-
"epoch": 0.
|
| 657 |
-
"grad_norm": 0.
|
| 658 |
"learning_rate": 0.0002,
|
| 659 |
-
"loss": 0.
|
| 660 |
"step": 465
|
| 661 |
},
|
| 662 |
{
|
| 663 |
-
"epoch": 0.
|
| 664 |
-
"grad_norm": 0.
|
| 665 |
"learning_rate": 0.0002,
|
| 666 |
-
"loss": 0.
|
| 667 |
"step": 470
|
| 668 |
},
|
| 669 |
{
|
| 670 |
-
"epoch": 0.
|
| 671 |
-
"grad_norm": 0.
|
| 672 |
"learning_rate": 0.0002,
|
| 673 |
-
"loss": 0.
|
| 674 |
"step": 475
|
| 675 |
},
|
| 676 |
{
|
| 677 |
-
"epoch": 0.
|
| 678 |
-
"grad_norm": 0.
|
| 679 |
"learning_rate": 0.0002,
|
| 680 |
-
"loss": 0.
|
| 681 |
"step": 480
|
| 682 |
},
|
| 683 |
{
|
| 684 |
-
"epoch": 0.
|
| 685 |
-
"grad_norm": 0.
|
| 686 |
"learning_rate": 0.0002,
|
| 687 |
-
"loss": 0.
|
| 688 |
"step": 485
|
| 689 |
},
|
| 690 |
{
|
| 691 |
-
"epoch": 0.
|
| 692 |
-
"grad_norm": 0.
|
| 693 |
"learning_rate": 0.0002,
|
| 694 |
-
"loss": 0.
|
| 695 |
"step": 490
|
| 696 |
},
|
| 697 |
{
|
| 698 |
-
"epoch": 0.
|
| 699 |
-
"grad_norm": 0.
|
| 700 |
"learning_rate": 0.0002,
|
| 701 |
-
"loss": 0.
|
| 702 |
"step": 495
|
| 703 |
},
|
| 704 |
{
|
| 705 |
-
"epoch": 0.
|
| 706 |
-
"grad_norm": 0.
|
| 707 |
"learning_rate": 0.0002,
|
| 708 |
-
"loss": 0.
|
| 709 |
"step": 500
|
| 710 |
},
|
| 711 |
{
|
| 712 |
-
"epoch": 0.
|
| 713 |
-
"grad_norm": 0.
|
| 714 |
"learning_rate": 0.0002,
|
| 715 |
-
"loss": 0.
|
| 716 |
"step": 505
|
| 717 |
},
|
| 718 |
{
|
| 719 |
-
"epoch": 0.
|
| 720 |
-
"grad_norm": 0.
|
| 721 |
"learning_rate": 0.0002,
|
| 722 |
-
"loss": 0.
|
| 723 |
"step": 510
|
| 724 |
},
|
| 725 |
{
|
| 726 |
-
"epoch": 0.
|
| 727 |
-
"grad_norm": 0.
|
| 728 |
"learning_rate": 0.0002,
|
| 729 |
-
"loss": 0.
|
| 730 |
"step": 515
|
| 731 |
},
|
| 732 |
{
|
| 733 |
-
"epoch": 0.
|
| 734 |
-
"grad_norm": 0.
|
| 735 |
"learning_rate": 0.0002,
|
| 736 |
-
"loss": 0.
|
| 737 |
"step": 520
|
| 738 |
},
|
| 739 |
{
|
| 740 |
-
"epoch": 0.
|
| 741 |
-
"grad_norm": 0.
|
| 742 |
"learning_rate": 0.0002,
|
| 743 |
-
"loss": 0.
|
| 744 |
"step": 525
|
| 745 |
},
|
| 746 |
{
|
| 747 |
-
"epoch": 0.
|
| 748 |
-
"grad_norm": 0.
|
| 749 |
"learning_rate": 0.0002,
|
| 750 |
-
"loss": 0.
|
| 751 |
"step": 530
|
| 752 |
},
|
| 753 |
{
|
| 754 |
-
"epoch": 0.
|
| 755 |
-
"grad_norm": 0.
|
| 756 |
"learning_rate": 0.0002,
|
| 757 |
-
"loss": 0.
|
| 758 |
"step": 535
|
| 759 |
},
|
| 760 |
{
|
| 761 |
-
"epoch": 0.
|
| 762 |
-
"grad_norm": 0.
|
| 763 |
"learning_rate": 0.0002,
|
| 764 |
-
"loss": 0.
|
| 765 |
"step": 540
|
| 766 |
},
|
| 767 |
{
|
| 768 |
-
"epoch": 0.
|
| 769 |
-
"grad_norm": 0.
|
| 770 |
"learning_rate": 0.0002,
|
| 771 |
-
"loss": 0.
|
| 772 |
"step": 545
|
| 773 |
},
|
| 774 |
{
|
| 775 |
-
"epoch": 0.
|
| 776 |
-
"grad_norm": 0.
|
| 777 |
"learning_rate": 0.0002,
|
| 778 |
-
"loss": 0.
|
| 779 |
"step": 550
|
| 780 |
},
|
| 781 |
{
|
| 782 |
-
"epoch": 0.
|
| 783 |
-
"grad_norm": 0.
|
| 784 |
"learning_rate": 0.0002,
|
| 785 |
-
"loss": 0.
|
| 786 |
"step": 555
|
| 787 |
},
|
| 788 |
{
|
| 789 |
"epoch": 0.9991079393398751,
|
| 790 |
-
"grad_norm": 0.
|
| 791 |
"learning_rate": 0.0002,
|
| 792 |
-
"loss": 0.
|
| 793 |
"step": 560
|
| 794 |
},
|
| 795 |
{
|
| 796 |
"epoch": 0.9991079393398751,
|
| 797 |
"step": 560,
|
| 798 |
"total_flos": 8.398274691072e+17,
|
| 799 |
-
"train_loss": 0.
|
| 800 |
-
"train_runtime":
|
| 801 |
-
"train_samples_per_second":
|
| 802 |
-
"train_steps_per_second":
|
| 803 |
}
|
| 804 |
],
|
| 805 |
"logging_steps": 5,
|
|
|
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
+
"epoch": 0.008920606601248885,
|
| 13 |
+
"grad_norm": 0.04344707727432251,
|
| 14 |
"learning_rate": 0.0002,
|
| 15 |
+
"loss": 0.7458,
|
| 16 |
"step": 5
|
| 17 |
},
|
| 18 |
{
|
| 19 |
+
"epoch": 0.01784121320249777,
|
| 20 |
+
"grad_norm": 0.041871875524520874,
|
| 21 |
"learning_rate": 0.0002,
|
| 22 |
+
"loss": 0.71,
|
| 23 |
"step": 10
|
| 24 |
},
|
| 25 |
{
|
| 26 |
+
"epoch": 0.026761819803746655,
|
| 27 |
+
"grad_norm": 0.041962090879678726,
|
| 28 |
"learning_rate": 0.0002,
|
| 29 |
+
"loss": 0.672,
|
| 30 |
"step": 15
|
| 31 |
},
|
| 32 |
{
|
| 33 |
+
"epoch": 0.03568242640499554,
|
| 34 |
+
"grad_norm": 0.03574032336473465,
|
| 35 |
"learning_rate": 0.0002,
|
| 36 |
+
"loss": 0.686,
|
| 37 |
"step": 20
|
| 38 |
},
|
| 39 |
{
|
| 40 |
+
"epoch": 0.04460303300624442,
|
| 41 |
+
"grad_norm": 0.03700491040945053,
|
| 42 |
"learning_rate": 0.0002,
|
| 43 |
+
"loss": 0.6515,
|
| 44 |
"step": 25
|
| 45 |
},
|
| 46 |
{
|
| 47 |
+
"epoch": 0.05352363960749331,
|
| 48 |
+
"grad_norm": 0.029821349307894707,
|
| 49 |
"learning_rate": 0.0002,
|
| 50 |
+
"loss": 0.6247,
|
| 51 |
"step": 30
|
| 52 |
},
|
| 53 |
{
|
| 54 |
+
"epoch": 0.06244424620874219,
|
| 55 |
+
"grad_norm": 0.027489786967635155,
|
| 56 |
"learning_rate": 0.0002,
|
| 57 |
+
"loss": 0.6248,
|
| 58 |
"step": 35
|
| 59 |
},
|
| 60 |
{
|
| 61 |
+
"epoch": 0.07136485280999108,
|
| 62 |
+
"grad_norm": 0.026733923703432083,
|
| 63 |
"learning_rate": 0.0002,
|
| 64 |
+
"loss": 0.626,
|
| 65 |
"step": 40
|
| 66 |
},
|
| 67 |
{
|
| 68 |
+
"epoch": 0.08028545941123996,
|
| 69 |
+
"grad_norm": 0.024855654686689377,
|
| 70 |
"learning_rate": 0.0002,
|
| 71 |
+
"loss": 0.6141,
|
| 72 |
"step": 45
|
| 73 |
},
|
| 74 |
{
|
| 75 |
+
"epoch": 0.08920606601248884,
|
| 76 |
+
"grad_norm": 0.024668758735060692,
|
| 77 |
"learning_rate": 0.0002,
|
| 78 |
+
"loss": 0.5882,
|
| 79 |
"step": 50
|
| 80 |
},
|
| 81 |
{
|
| 82 |
+
"epoch": 0.09812667261373774,
|
| 83 |
+
"grad_norm": 0.024284500628709793,
|
| 84 |
"learning_rate": 0.0002,
|
| 85 |
+
"loss": 0.599,
|
| 86 |
"step": 55
|
| 87 |
},
|
| 88 |
{
|
| 89 |
+
"epoch": 0.10704727921498662,
|
| 90 |
+
"grad_norm": 0.026213666424155235,
|
| 91 |
"learning_rate": 0.0002,
|
| 92 |
+
"loss": 0.6458,
|
| 93 |
"step": 60
|
| 94 |
},
|
| 95 |
{
|
| 96 |
+
"epoch": 0.1159678858162355,
|
| 97 |
+
"grad_norm": 0.025072986260056496,
|
| 98 |
"learning_rate": 0.0002,
|
| 99 |
+
"loss": 0.5974,
|
| 100 |
"step": 65
|
| 101 |
},
|
| 102 |
{
|
| 103 |
+
"epoch": 0.12488849241748438,
|
| 104 |
+
"grad_norm": 0.023400137200951576,
|
| 105 |
"learning_rate": 0.0002,
|
| 106 |
+
"loss": 0.5535,
|
| 107 |
"step": 70
|
| 108 |
},
|
| 109 |
{
|
| 110 |
+
"epoch": 0.13380909901873328,
|
| 111 |
+
"grad_norm": 0.025392651557922363,
|
| 112 |
"learning_rate": 0.0002,
|
| 113 |
+
"loss": 0.5756,
|
| 114 |
"step": 75
|
| 115 |
},
|
| 116 |
{
|
| 117 |
+
"epoch": 0.14272970561998216,
|
| 118 |
+
"grad_norm": 0.023731403052806854,
|
| 119 |
"learning_rate": 0.0002,
|
| 120 |
+
"loss": 0.5895,
|
| 121 |
"step": 80
|
| 122 |
},
|
| 123 |
{
|
| 124 |
+
"epoch": 0.15165031222123104,
|
| 125 |
+
"grad_norm": 0.02360088750720024,
|
| 126 |
"learning_rate": 0.0002,
|
| 127 |
+
"loss": 0.5869,
|
| 128 |
"step": 85
|
| 129 |
},
|
| 130 |
{
|
| 131 |
+
"epoch": 0.16057091882247992,
|
| 132 |
+
"grad_norm": 0.02655966207385063,
|
| 133 |
"learning_rate": 0.0002,
|
| 134 |
+
"loss": 0.5851,
|
| 135 |
"step": 90
|
| 136 |
},
|
| 137 |
{
|
| 138 |
+
"epoch": 0.1694915254237288,
|
| 139 |
+
"grad_norm": 0.02600923739373684,
|
| 140 |
"learning_rate": 0.0002,
|
| 141 |
+
"loss": 0.609,
|
| 142 |
"step": 95
|
| 143 |
},
|
| 144 |
{
|
| 145 |
+
"epoch": 0.1784121320249777,
|
| 146 |
+
"grad_norm": 0.025682499632239342,
|
| 147 |
"learning_rate": 0.0002,
|
| 148 |
+
"loss": 0.5885,
|
| 149 |
"step": 100
|
| 150 |
},
|
| 151 |
{
|
| 152 |
+
"epoch": 0.1873327386262266,
|
| 153 |
+
"grad_norm": 0.025844326242804527,
|
| 154 |
"learning_rate": 0.0002,
|
| 155 |
+
"loss": 0.5997,
|
| 156 |
"step": 105
|
| 157 |
},
|
| 158 |
{
|
| 159 |
+
"epoch": 0.19625334522747548,
|
| 160 |
+
"grad_norm": 0.027400100603699684,
|
| 161 |
"learning_rate": 0.0002,
|
| 162 |
+
"loss": 0.609,
|
| 163 |
"step": 110
|
| 164 |
},
|
| 165 |
{
|
| 166 |
+
"epoch": 0.20517395182872436,
|
| 167 |
+
"grad_norm": 0.025671344250440598,
|
| 168 |
"learning_rate": 0.0002,
|
| 169 |
+
"loss": 0.5678,
|
| 170 |
"step": 115
|
| 171 |
},
|
| 172 |
{
|
| 173 |
+
"epoch": 0.21409455842997324,
|
| 174 |
+
"grad_norm": 0.02872069925069809,
|
| 175 |
"learning_rate": 0.0002,
|
| 176 |
+
"loss": 0.6052,
|
| 177 |
"step": 120
|
| 178 |
},
|
| 179 |
{
|
| 180 |
+
"epoch": 0.22301516503122212,
|
| 181 |
+
"grad_norm": 0.026377148926258087,
|
| 182 |
"learning_rate": 0.0002,
|
| 183 |
+
"loss": 0.5961,
|
| 184 |
"step": 125
|
| 185 |
},
|
| 186 |
{
|
| 187 |
+
"epoch": 0.231935771632471,
|
| 188 |
+
"grad_norm": 0.027191588655114174,
|
| 189 |
"learning_rate": 0.0002,
|
| 190 |
+
"loss": 0.5903,
|
| 191 |
"step": 130
|
| 192 |
},
|
| 193 |
{
|
| 194 |
+
"epoch": 0.2408563782337199,
|
| 195 |
+
"grad_norm": 0.030450984835624695,
|
| 196 |
"learning_rate": 0.0002,
|
| 197 |
+
"loss": 0.5703,
|
| 198 |
"step": 135
|
| 199 |
},
|
| 200 |
{
|
| 201 |
+
"epoch": 0.24977698483496877,
|
| 202 |
+
"grad_norm": 0.02679985947906971,
|
| 203 |
"learning_rate": 0.0002,
|
| 204 |
+
"loss": 0.5805,
|
| 205 |
"step": 140
|
| 206 |
},
|
| 207 |
{
|
| 208 |
+
"epoch": 0.2586975914362177,
|
| 209 |
+
"grad_norm": 0.02805212326347828,
|
| 210 |
"learning_rate": 0.0002,
|
| 211 |
+
"loss": 0.5867,
|
| 212 |
"step": 145
|
| 213 |
},
|
| 214 |
{
|
| 215 |
+
"epoch": 0.26761819803746656,
|
| 216 |
+
"grad_norm": 0.027465296909213066,
|
| 217 |
"learning_rate": 0.0002,
|
| 218 |
+
"loss": 0.599,
|
| 219 |
"step": 150
|
| 220 |
},
|
| 221 |
{
|
| 222 |
+
"epoch": 0.27653880463871544,
|
| 223 |
+
"grad_norm": 0.027630291879177094,
|
| 224 |
"learning_rate": 0.0002,
|
| 225 |
+
"loss": 0.5894,
|
| 226 |
"step": 155
|
| 227 |
},
|
| 228 |
{
|
| 229 |
+
"epoch": 0.2854594112399643,
|
| 230 |
+
"grad_norm": 0.027628762647509575,
|
| 231 |
"learning_rate": 0.0002,
|
| 232 |
+
"loss": 0.5984,
|
| 233 |
"step": 160
|
| 234 |
},
|
| 235 |
{
|
| 236 |
+
"epoch": 0.2943800178412132,
|
| 237 |
+
"grad_norm": 0.02642473392188549,
|
| 238 |
"learning_rate": 0.0002,
|
| 239 |
+
"loss": 0.5966,
|
| 240 |
"step": 165
|
| 241 |
},
|
| 242 |
{
|
| 243 |
+
"epoch": 0.3033006244424621,
|
| 244 |
+
"grad_norm": 0.027726992964744568,
|
| 245 |
"learning_rate": 0.0002,
|
| 246 |
+
"loss": 0.5954,
|
| 247 |
"step": 170
|
| 248 |
},
|
| 249 |
{
|
| 250 |
+
"epoch": 0.31222123104371097,
|
| 251 |
+
"grad_norm": 0.027844909578561783,
|
| 252 |
"learning_rate": 0.0002,
|
| 253 |
+
"loss": 0.5932,
|
| 254 |
"step": 175
|
| 255 |
},
|
| 256 |
{
|
| 257 |
+
"epoch": 0.32114183764495985,
|
| 258 |
+
"grad_norm": 0.024765541777014732,
|
| 259 |
"learning_rate": 0.0002,
|
| 260 |
+
"loss": 0.5608,
|
| 261 |
"step": 180
|
| 262 |
},
|
| 263 |
{
|
| 264 |
+
"epoch": 0.33006244424620873,
|
| 265 |
+
"grad_norm": 0.02770071104168892,
|
| 266 |
"learning_rate": 0.0002,
|
| 267 |
+
"loss": 0.6121,
|
| 268 |
"step": 185
|
| 269 |
},
|
| 270 |
{
|
| 271 |
+
"epoch": 0.3389830508474576,
|
| 272 |
+
"grad_norm": 0.02800634689629078,
|
| 273 |
"learning_rate": 0.0002,
|
| 274 |
+
"loss": 0.5964,
|
| 275 |
"step": 190
|
| 276 |
},
|
| 277 |
{
|
| 278 |
+
"epoch": 0.3479036574487065,
|
| 279 |
+
"grad_norm": 0.028501659631729126,
|
| 280 |
"learning_rate": 0.0002,
|
| 281 |
+
"loss": 0.5757,
|
| 282 |
"step": 195
|
| 283 |
},
|
| 284 |
{
|
| 285 |
+
"epoch": 0.3568242640499554,
|
| 286 |
+
"grad_norm": 0.026436127722263336,
|
| 287 |
"learning_rate": 0.0002,
|
| 288 |
+
"loss": 0.5689,
|
| 289 |
"step": 200
|
| 290 |
},
|
| 291 |
{
|
| 292 |
+
"epoch": 0.36574487065120426,
|
| 293 |
+
"grad_norm": 0.027517864480614662,
|
| 294 |
"learning_rate": 0.0002,
|
| 295 |
+
"loss": 0.5999,
|
| 296 |
"step": 205
|
| 297 |
},
|
| 298 |
{
|
| 299 |
+
"epoch": 0.3746654772524532,
|
| 300 |
+
"grad_norm": 0.026851925998926163,
|
| 301 |
"learning_rate": 0.0002,
|
| 302 |
+
"loss": 0.5771,
|
| 303 |
"step": 210
|
| 304 |
},
|
| 305 |
{
|
| 306 |
+
"epoch": 0.3835860838537021,
|
| 307 |
+
"grad_norm": 0.027687210589647293,
|
| 308 |
"learning_rate": 0.0002,
|
| 309 |
+
"loss": 0.5627,
|
| 310 |
"step": 215
|
| 311 |
},
|
| 312 |
{
|
| 313 |
+
"epoch": 0.39250669045495096,
|
| 314 |
+
"grad_norm": 0.030687233433127403,
|
| 315 |
"learning_rate": 0.0002,
|
| 316 |
+
"loss": 0.6206,
|
| 317 |
"step": 220
|
| 318 |
},
|
| 319 |
{
|
| 320 |
+
"epoch": 0.40142729705619984,
|
| 321 |
+
"grad_norm": 0.028457796201109886,
|
| 322 |
"learning_rate": 0.0002,
|
| 323 |
+
"loss": 0.5753,
|
| 324 |
"step": 225
|
| 325 |
},
|
| 326 |
{
|
| 327 |
+
"epoch": 0.4103479036574487,
|
| 328 |
+
"grad_norm": 0.028889574110507965,
|
| 329 |
"learning_rate": 0.0002,
|
| 330 |
+
"loss": 0.5739,
|
| 331 |
"step": 230
|
| 332 |
},
|
| 333 |
{
|
| 334 |
+
"epoch": 0.4192685102586976,
|
| 335 |
+
"grad_norm": 0.028494860976934433,
|
| 336 |
"learning_rate": 0.0002,
|
| 337 |
+
"loss": 0.5895,
|
| 338 |
"step": 235
|
| 339 |
},
|
| 340 |
{
|
| 341 |
+
"epoch": 0.4281891168599465,
|
| 342 |
+
"grad_norm": 0.028224695473909378,
|
| 343 |
"learning_rate": 0.0002,
|
| 344 |
+
"loss": 0.6016,
|
| 345 |
"step": 240
|
| 346 |
},
|
| 347 |
{
|
| 348 |
+
"epoch": 0.43710972346119537,
|
| 349 |
+
"grad_norm": 0.027433231472969055,
|
| 350 |
"learning_rate": 0.0002,
|
| 351 |
+
"loss": 0.5759,
|
| 352 |
"step": 245
|
| 353 |
},
|
| 354 |
{
|
| 355 |
+
"epoch": 0.44603033006244425,
|
| 356 |
+
"grad_norm": 0.02770438976585865,
|
| 357 |
"learning_rate": 0.0002,
|
| 358 |
+
"loss": 0.5963,
|
| 359 |
"step": 250
|
| 360 |
},
|
| 361 |
{
|
| 362 |
+
"epoch": 0.45495093666369313,
|
| 363 |
+
"grad_norm": 0.030380843207240105,
|
| 364 |
"learning_rate": 0.0002,
|
| 365 |
+
"loss": 0.6346,
|
| 366 |
"step": 255
|
| 367 |
},
|
| 368 |
{
|
| 369 |
+
"epoch": 0.463871543264942,
|
| 370 |
+
"grad_norm": 0.028422418981790543,
|
| 371 |
"learning_rate": 0.0002,
|
| 372 |
+
"loss": 0.6088,
|
| 373 |
"step": 260
|
| 374 |
},
|
| 375 |
{
|
| 376 |
+
"epoch": 0.4727921498661909,
|
| 377 |
+
"grad_norm": 0.02833402529358864,
|
| 378 |
"learning_rate": 0.0002,
|
| 379 |
+
"loss": 0.5672,
|
| 380 |
"step": 265
|
| 381 |
},
|
| 382 |
{
|
| 383 |
+
"epoch": 0.4817127564674398,
|
| 384 |
+
"grad_norm": 0.0281459279358387,
|
| 385 |
"learning_rate": 0.0002,
|
| 386 |
+
"loss": 0.5875,
|
| 387 |
"step": 270
|
| 388 |
},
|
| 389 |
{
|
| 390 |
+
"epoch": 0.49063336306868865,
|
| 391 |
+
"grad_norm": 0.02902720309793949,
|
| 392 |
"learning_rate": 0.0002,
|
| 393 |
+
"loss": 0.578,
|
| 394 |
"step": 275
|
| 395 |
},
|
| 396 |
{
|
| 397 |
+
"epoch": 0.49955396966993754,
|
| 398 |
+
"grad_norm": 0.02845628187060356,
|
| 399 |
"learning_rate": 0.0002,
|
| 400 |
+
"loss": 0.5852,
|
| 401 |
"step": 280
|
| 402 |
},
|
| 403 |
{
|
| 404 |
+
"epoch": 0.5084745762711864,
|
| 405 |
+
"grad_norm": 0.02827693149447441,
|
| 406 |
"learning_rate": 0.0002,
|
| 407 |
+
"loss": 0.5651,
|
| 408 |
"step": 285
|
| 409 |
},
|
| 410 |
{
|
| 411 |
+
"epoch": 0.5173951828724354,
|
| 412 |
+
"grad_norm": 0.026872893795371056,
|
| 413 |
"learning_rate": 0.0002,
|
| 414 |
+
"loss": 0.5847,
|
| 415 |
"step": 290
|
| 416 |
},
|
| 417 |
{
|
| 418 |
+
"epoch": 0.5263157894736842,
|
| 419 |
+
"grad_norm": 0.02863125689327717,
|
| 420 |
"learning_rate": 0.0002,
|
| 421 |
+
"loss": 0.569,
|
| 422 |
"step": 295
|
| 423 |
},
|
| 424 |
{
|
| 425 |
+
"epoch": 0.5352363960749331,
|
| 426 |
+
"grad_norm": 0.02849287912249565,
|
| 427 |
"learning_rate": 0.0002,
|
| 428 |
+
"loss": 0.5904,
|
| 429 |
"step": 300
|
| 430 |
},
|
| 431 |
{
|
| 432 |
+
"epoch": 0.544157002676182,
|
| 433 |
+
"grad_norm": 0.029510285705327988,
|
| 434 |
"learning_rate": 0.0002,
|
| 435 |
+
"loss": 0.5743,
|
| 436 |
"step": 305
|
| 437 |
},
|
| 438 |
{
|
| 439 |
+
"epoch": 0.5530776092774309,
|
| 440 |
+
"grad_norm": 0.029404086992144585,
|
| 441 |
"learning_rate": 0.0002,
|
| 442 |
+
"loss": 0.5897,
|
| 443 |
"step": 310
|
| 444 |
},
|
| 445 |
{
|
| 446 |
+
"epoch": 0.5619982158786797,
|
| 447 |
+
"grad_norm": 0.028384504839777946,
|
| 448 |
"learning_rate": 0.0002,
|
| 449 |
+
"loss": 0.5928,
|
| 450 |
"step": 315
|
| 451 |
},
|
| 452 |
{
|
| 453 |
+
"epoch": 0.5709188224799286,
|
| 454 |
+
"grad_norm": 0.029003608971834183,
|
| 455 |
"learning_rate": 0.0002,
|
| 456 |
+
"loss": 0.5758,
|
| 457 |
"step": 320
|
| 458 |
},
|
| 459 |
{
|
| 460 |
+
"epoch": 0.5798394290811775,
|
| 461 |
+
"grad_norm": 0.026150822639465332,
|
| 462 |
"learning_rate": 0.0002,
|
| 463 |
+
"loss": 0.5688,
|
| 464 |
"step": 325
|
| 465 |
},
|
| 466 |
{
|
| 467 |
+
"epoch": 0.5887600356824264,
|
| 468 |
+
"grad_norm": 0.027160905301570892,
|
| 469 |
"learning_rate": 0.0002,
|
| 470 |
+
"loss": 0.5783,
|
| 471 |
"step": 330
|
| 472 |
},
|
| 473 |
{
|
| 474 |
+
"epoch": 0.5976806422836753,
|
| 475 |
+
"grad_norm": 0.026426801458001137,
|
| 476 |
"learning_rate": 0.0002,
|
| 477 |
+
"loss": 0.5605,
|
| 478 |
"step": 335
|
| 479 |
},
|
| 480 |
{
|
| 481 |
+
"epoch": 0.6066012488849242,
|
| 482 |
+
"grad_norm": 0.029923705384135246,
|
| 483 |
"learning_rate": 0.0002,
|
| 484 |
+
"loss": 0.5901,
|
| 485 |
"step": 340
|
| 486 |
},
|
| 487 |
{
|
| 488 |
+
"epoch": 0.6155218554861731,
|
| 489 |
+
"grad_norm": 0.02743326872587204,
|
| 490 |
"learning_rate": 0.0002,
|
| 491 |
+
"loss": 0.5964,
|
| 492 |
"step": 345
|
| 493 |
},
|
| 494 |
{
|
| 495 |
+
"epoch": 0.6244424620874219,
|
| 496 |
+
"grad_norm": 0.0284026637673378,
|
| 497 |
"learning_rate": 0.0002,
|
| 498 |
+
"loss": 0.5874,
|
| 499 |
"step": 350
|
| 500 |
},
|
| 501 |
{
|
| 502 |
+
"epoch": 0.6333630686886709,
|
| 503 |
+
"grad_norm": 0.030260000377893448,
|
| 504 |
"learning_rate": 0.0002,
|
| 505 |
+
"loss": 0.5831,
|
| 506 |
"step": 355
|
| 507 |
},
|
| 508 |
{
|
| 509 |
+
"epoch": 0.6422836752899197,
|
| 510 |
+
"grad_norm": 0.02586439996957779,
|
| 511 |
"learning_rate": 0.0002,
|
| 512 |
+
"loss": 0.5541,
|
| 513 |
"step": 360
|
| 514 |
},
|
| 515 |
{
|
| 516 |
+
"epoch": 0.6512042818911686,
|
| 517 |
+
"grad_norm": 0.026640642434358597,
|
| 518 |
"learning_rate": 0.0002,
|
| 519 |
+
"loss": 0.5669,
|
| 520 |
"step": 365
|
| 521 |
},
|
| 522 |
{
|
| 523 |
+
"epoch": 0.6601248884924175,
|
| 524 |
+
"grad_norm": 0.028971482068300247,
|
| 525 |
"learning_rate": 0.0002,
|
| 526 |
+
"loss": 0.5952,
|
| 527 |
"step": 370
|
| 528 |
},
|
| 529 |
{
|
| 530 |
+
"epoch": 0.6690454950936664,
|
| 531 |
+
"grad_norm": 0.027096880599856377,
|
| 532 |
"learning_rate": 0.0002,
|
| 533 |
+
"loss": 0.5606,
|
| 534 |
"step": 375
|
| 535 |
},
|
| 536 |
{
|
| 537 |
+
"epoch": 0.6779661016949152,
|
| 538 |
+
"grad_norm": 0.11753229796886444,
|
| 539 |
"learning_rate": 0.0002,
|
| 540 |
+
"loss": 0.5667,
|
| 541 |
"step": 380
|
| 542 |
},
|
| 543 |
{
|
| 544 |
+
"epoch": 0.6868867082961642,
|
| 545 |
+
"grad_norm": 0.029016384854912758,
|
| 546 |
"learning_rate": 0.0002,
|
| 547 |
+
"loss": 0.5819,
|
| 548 |
"step": 385
|
| 549 |
},
|
| 550 |
{
|
| 551 |
+
"epoch": 0.695807314897413,
|
| 552 |
+
"grad_norm": 0.03013915754854679,
|
| 553 |
"learning_rate": 0.0002,
|
| 554 |
+
"loss": 0.5756,
|
| 555 |
"step": 390
|
| 556 |
},
|
| 557 |
{
|
| 558 |
+
"epoch": 0.7047279214986619,
|
| 559 |
+
"grad_norm": 0.030191004276275635,
|
| 560 |
"learning_rate": 0.0002,
|
| 561 |
+
"loss": 0.5714,
|
| 562 |
"step": 395
|
| 563 |
},
|
| 564 |
{
|
| 565 |
+
"epoch": 0.7136485280999108,
|
| 566 |
+
"grad_norm": 0.02674183063209057,
|
| 567 |
"learning_rate": 0.0002,
|
| 568 |
+
"loss": 0.5867,
|
| 569 |
"step": 400
|
| 570 |
},
|
| 571 |
{
|
| 572 |
+
"epoch": 0.7225691347011597,
|
| 573 |
+
"grad_norm": 0.02824782207608223,
|
| 574 |
"learning_rate": 0.0002,
|
| 575 |
+
"loss": 0.587,
|
| 576 |
"step": 405
|
| 577 |
},
|
| 578 |
{
|
| 579 |
+
"epoch": 0.7314897413024085,
|
| 580 |
+
"grad_norm": 0.027175093069672585,
|
| 581 |
"learning_rate": 0.0002,
|
| 582 |
+
"loss": 0.5883,
|
| 583 |
"step": 410
|
| 584 |
},
|
| 585 |
{
|
| 586 |
+
"epoch": 0.7404103479036575,
|
| 587 |
+
"grad_norm": 0.028087187558412552,
|
| 588 |
"learning_rate": 0.0002,
|
| 589 |
+
"loss": 0.5734,
|
| 590 |
"step": 415
|
| 591 |
},
|
| 592 |
{
|
| 593 |
+
"epoch": 0.7493309545049064,
|
| 594 |
+
"grad_norm": 0.028495660051703453,
|
| 595 |
"learning_rate": 0.0002,
|
| 596 |
+
"loss": 0.5499,
|
| 597 |
"step": 420
|
| 598 |
},
|
| 599 |
{
|
| 600 |
+
"epoch": 0.7582515611061552,
|
| 601 |
+
"grad_norm": 0.029332948848605156,
|
| 602 |
"learning_rate": 0.0002,
|
| 603 |
+
"loss": 0.6101,
|
| 604 |
"step": 425
|
| 605 |
},
|
| 606 |
{
|
| 607 |
+
"epoch": 0.7671721677074042,
|
| 608 |
+
"grad_norm": 0.02667965553700924,
|
| 609 |
"learning_rate": 0.0002,
|
| 610 |
+
"loss": 0.5652,
|
| 611 |
"step": 430
|
| 612 |
},
|
| 613 |
{
|
| 614 |
+
"epoch": 0.776092774308653,
|
| 615 |
+
"grad_norm": 0.0268410611897707,
|
| 616 |
"learning_rate": 0.0002,
|
| 617 |
+
"loss": 0.5584,
|
| 618 |
"step": 435
|
| 619 |
},
|
| 620 |
{
|
| 621 |
+
"epoch": 0.7850133809099019,
|
| 622 |
+
"grad_norm": 0.027814755216240883,
|
| 623 |
"learning_rate": 0.0002,
|
| 624 |
+
"loss": 0.5724,
|
| 625 |
"step": 440
|
| 626 |
},
|
| 627 |
{
|
| 628 |
+
"epoch": 0.7939339875111507,
|
| 629 |
+
"grad_norm": 0.02988579496741295,
|
| 630 |
"learning_rate": 0.0002,
|
| 631 |
+
"loss": 0.57,
|
| 632 |
"step": 445
|
| 633 |
},
|
| 634 |
{
|
| 635 |
+
"epoch": 0.8028545941123997,
|
| 636 |
+
"grad_norm": 0.028960440307855606,
|
| 637 |
"learning_rate": 0.0002,
|
| 638 |
+
"loss": 0.5484,
|
| 639 |
"step": 450
|
| 640 |
},
|
| 641 |
{
|
| 642 |
+
"epoch": 0.8117752007136485,
|
| 643 |
+
"grad_norm": 0.028208531439304352,
|
| 644 |
"learning_rate": 0.0002,
|
| 645 |
+
"loss": 0.5875,
|
| 646 |
"step": 455
|
| 647 |
},
|
| 648 |
{
|
| 649 |
+
"epoch": 0.8206958073148974,
|
| 650 |
+
"grad_norm": 0.025945566594600677,
|
| 651 |
"learning_rate": 0.0002,
|
| 652 |
+
"loss": 0.5696,
|
| 653 |
"step": 460
|
| 654 |
},
|
| 655 |
{
|
| 656 |
+
"epoch": 0.8296164139161463,
|
| 657 |
+
"grad_norm": 0.028697073459625244,
|
| 658 |
"learning_rate": 0.0002,
|
| 659 |
+
"loss": 0.5703,
|
| 660 |
"step": 465
|
| 661 |
},
|
| 662 |
{
|
| 663 |
+
"epoch": 0.8385370205173952,
|
| 664 |
+
"grad_norm": 0.028819743543863297,
|
| 665 |
"learning_rate": 0.0002,
|
| 666 |
+
"loss": 0.5814,
|
| 667 |
"step": 470
|
| 668 |
},
|
| 669 |
{
|
| 670 |
+
"epoch": 0.847457627118644,
|
| 671 |
+
"grad_norm": 0.02928623929619789,
|
| 672 |
"learning_rate": 0.0002,
|
| 673 |
+
"loss": 0.5738,
|
| 674 |
"step": 475
|
| 675 |
},
|
| 676 |
{
|
| 677 |
+
"epoch": 0.856378233719893,
|
| 678 |
+
"grad_norm": 0.027526717633008957,
|
| 679 |
"learning_rate": 0.0002,
|
| 680 |
+
"loss": 0.5678,
|
| 681 |
"step": 480
|
| 682 |
},
|
| 683 |
{
|
| 684 |
+
"epoch": 0.8652988403211418,
|
| 685 |
+
"grad_norm": 0.02858017198741436,
|
| 686 |
"learning_rate": 0.0002,
|
| 687 |
+
"loss": 0.5815,
|
| 688 |
"step": 485
|
| 689 |
},
|
| 690 |
{
|
| 691 |
+
"epoch": 0.8742194469223907,
|
| 692 |
+
"grad_norm": 0.028315911069512367,
|
| 693 |
"learning_rate": 0.0002,
|
| 694 |
+
"loss": 0.5928,
|
| 695 |
"step": 490
|
| 696 |
},
|
| 697 |
{
|
| 698 |
+
"epoch": 0.8831400535236396,
|
| 699 |
+
"grad_norm": 0.029983386397361755,
|
| 700 |
"learning_rate": 0.0002,
|
| 701 |
+
"loss": 0.6047,
|
| 702 |
"step": 495
|
| 703 |
},
|
| 704 |
{
|
| 705 |
+
"epoch": 0.8920606601248885,
|
| 706 |
+
"grad_norm": 0.028466004878282547,
|
| 707 |
"learning_rate": 0.0002,
|
| 708 |
+
"loss": 0.5918,
|
| 709 |
"step": 500
|
| 710 |
},
|
| 711 |
{
|
| 712 |
+
"epoch": 0.9009812667261374,
|
| 713 |
+
"grad_norm": 0.02696722000837326,
|
| 714 |
"learning_rate": 0.0002,
|
| 715 |
+
"loss": 0.5856,
|
| 716 |
"step": 505
|
| 717 |
},
|
| 718 |
{
|
| 719 |
+
"epoch": 0.9099018733273863,
|
| 720 |
+
"grad_norm": 0.029618097469210625,
|
| 721 |
"learning_rate": 0.0002,
|
| 722 |
+
"loss": 0.5617,
|
| 723 |
"step": 510
|
| 724 |
},
|
| 725 |
{
|
| 726 |
+
"epoch": 0.9188224799286352,
|
| 727 |
+
"grad_norm": 0.02784411609172821,
|
| 728 |
"learning_rate": 0.0002,
|
| 729 |
+
"loss": 0.553,
|
| 730 |
"step": 515
|
| 731 |
},
|
| 732 |
{
|
| 733 |
+
"epoch": 0.927743086529884,
|
| 734 |
+
"grad_norm": 0.02615758404135704,
|
| 735 |
"learning_rate": 0.0002,
|
| 736 |
+
"loss": 0.5555,
|
| 737 |
"step": 520
|
| 738 |
},
|
| 739 |
{
|
| 740 |
+
"epoch": 0.936663693131133,
|
| 741 |
+
"grad_norm": 0.028149690479040146,
|
| 742 |
"learning_rate": 0.0002,
|
| 743 |
+
"loss": 0.5723,
|
| 744 |
"step": 525
|
| 745 |
},
|
| 746 |
{
|
| 747 |
+
"epoch": 0.9455842997323818,
|
| 748 |
+
"grad_norm": 0.026176296174526215,
|
| 749 |
"learning_rate": 0.0002,
|
| 750 |
+
"loss": 0.5785,
|
| 751 |
"step": 530
|
| 752 |
},
|
| 753 |
{
|
| 754 |
+
"epoch": 0.9545049063336307,
|
| 755 |
+
"grad_norm": 0.02792450040578842,
|
| 756 |
"learning_rate": 0.0002,
|
| 757 |
+
"loss": 0.5871,
|
| 758 |
"step": 535
|
| 759 |
},
|
| 760 |
{
|
| 761 |
+
"epoch": 0.9634255129348795,
|
| 762 |
+
"grad_norm": 0.027666164562106133,
|
| 763 |
"learning_rate": 0.0002,
|
| 764 |
+
"loss": 0.5544,
|
| 765 |
"step": 540
|
| 766 |
},
|
| 767 |
{
|
| 768 |
+
"epoch": 0.9723461195361285,
|
| 769 |
+
"grad_norm": 0.027818914502859116,
|
| 770 |
"learning_rate": 0.0002,
|
| 771 |
+
"loss": 0.5716,
|
| 772 |
"step": 545
|
| 773 |
},
|
| 774 |
{
|
| 775 |
+
"epoch": 0.9812667261373773,
|
| 776 |
+
"grad_norm": 0.028460504487156868,
|
| 777 |
"learning_rate": 0.0002,
|
| 778 |
+
"loss": 0.5825,
|
| 779 |
"step": 550
|
| 780 |
},
|
| 781 |
{
|
| 782 |
+
"epoch": 0.9901873327386262,
|
| 783 |
+
"grad_norm": 0.028340350836515427,
|
| 784 |
"learning_rate": 0.0002,
|
| 785 |
+
"loss": 0.5593,
|
| 786 |
"step": 555
|
| 787 |
},
|
| 788 |
{
|
| 789 |
"epoch": 0.9991079393398751,
|
| 790 |
+
"grad_norm": 0.028169002383947372,
|
| 791 |
"learning_rate": 0.0002,
|
| 792 |
+
"loss": 0.5903,
|
| 793 |
"step": 560
|
| 794 |
},
|
| 795 |
{
|
| 796 |
"epoch": 0.9991079393398751,
|
| 797 |
"step": 560,
|
| 798 |
"total_flos": 8.398274691072e+17,
|
| 799 |
+
"train_loss": 0.5889353160347257,
|
| 800 |
+
"train_runtime": 8886.9999,
|
| 801 |
+
"train_samples_per_second": 1.009,
|
| 802 |
+
"train_steps_per_second": 0.063
|
| 803 |
}
|
| 804 |
],
|
| 805 |
"logging_steps": 5,
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5688
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5416cc212d3f82d6c34f13b8d64adc3e4eba46d885d3a698ff2292fc017985f6
|
| 3 |
size 5688
|