Uploaded from W&B
Browse files- model-00001-of-00006.safetensors +1 -1
- model-00002-of-00006.safetensors +1 -1
- model-00003-of-00006.safetensors +1 -1
- model-00004-of-00006.safetensors +1 -1
- model-00005-of-00006.safetensors +1 -1
- model-00006-of-00006.safetensors +1 -1
- trainer_state.json +168 -413
- training_args.bin +1 -1
model-00001-of-00006.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4984780784
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e8f8796540da0ab8fe8314e7244ca2896d704f6e0b6b2ee83100ee18713ce16d
|
| 3 |
size 4984780784
|
model-00002-of-00006.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4980892048
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:883b8cd8920bb5272ad4371225b5f0b780999bd0004b79af4c6d4a54d5c489f6
|
| 3 |
size 4980892048
|
model-00003-of-00006.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4928485104
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:80ffb3e1525cf5c24986910381ac99a4d9cb85af1cff775ffc0e9096470e375b
|
| 3 |
size 4928485104
|
model-00004-of-00006.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4980892112
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a3a1e7a51aa9e3bcc672244bd97e05648170b3e0f692ef5beab1179fa4689d9f
|
| 3 |
size 4980892112
|
model-00005-of-00006.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4928485104
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0bc50985995feedb7b126801a4b5c6e7dabaeb02766012b18aa5aa698cbd7d51
|
| 3 |
size 4928485104
|
model-00006-of-00006.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4733130504
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a7dce3ec5ad86726303028f879f98d3bd5588dda85f21fe2a6a462c74edac5de
|
| 3 |
size 4733130504
|
trainer_state.json
CHANGED
|
@@ -2,592 +2,347 @@
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
-
"epoch": 4.
|
| 6 |
-
"eval_steps":
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
| 11 |
"log_history": [
|
| 12 |
{
|
| 13 |
-
"epoch": 0.
|
| 14 |
-
"grad_norm":
|
| 15 |
"learning_rate": 0.0,
|
| 16 |
-
"loss": 0.
|
| 17 |
"step": 1
|
| 18 |
},
|
| 19 |
{
|
| 20 |
-
"epoch": 0.
|
| 21 |
-
"eval_loss": 0.
|
| 22 |
-
"eval_runtime":
|
| 23 |
-
"eval_samples_per_second":
|
| 24 |
-
"eval_steps_per_second": 0.
|
| 25 |
"step": 1
|
| 26 |
},
|
| 27 |
{
|
| 28 |
-
"epoch": 0.
|
| 29 |
-
"grad_norm":
|
| 30 |
"learning_rate": 1.6666666666666668e-07,
|
| 31 |
-
"loss": 0.
|
| 32 |
"step": 2
|
| 33 |
},
|
| 34 |
{
|
| 35 |
-
"epoch": 0.
|
| 36 |
-
"grad_norm":
|
| 37 |
"learning_rate": 3.3333333333333335e-07,
|
| 38 |
-
"loss": 0.
|
| 39 |
"step": 3
|
| 40 |
},
|
| 41 |
{
|
| 42 |
-
"epoch": 0.
|
| 43 |
-
"grad_norm":
|
| 44 |
"learning_rate": 5.000000000000001e-07,
|
| 45 |
-
"loss": 0.
|
| 46 |
"step": 4
|
| 47 |
},
|
| 48 |
{
|
| 49 |
-
"epoch": 0.
|
| 50 |
-
"grad_norm":
|
| 51 |
"learning_rate": 6.666666666666667e-07,
|
| 52 |
-
"loss": 0.
|
| 53 |
"step": 5
|
| 54 |
},
|
| 55 |
{
|
| 56 |
-
"epoch": 0.
|
| 57 |
-
"grad_norm":
|
| 58 |
"learning_rate": 8.333333333333333e-07,
|
| 59 |
-
"loss": 0.
|
| 60 |
"step": 6
|
| 61 |
},
|
| 62 |
{
|
| 63 |
-
"epoch": 0.
|
| 64 |
-
"grad_norm":
|
| 65 |
"learning_rate": 1.0000000000000002e-06,
|
| 66 |
-
"loss": 0.
|
| 67 |
"step": 7
|
| 68 |
},
|
| 69 |
{
|
| 70 |
-
"epoch": 0.
|
| 71 |
-
"grad_norm": 3.
|
| 72 |
"learning_rate": 1.1666666666666668e-06,
|
| 73 |
-
"loss": 0.
|
| 74 |
"step": 8
|
| 75 |
},
|
| 76 |
{
|
| 77 |
-
"epoch": 0.
|
| 78 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 79 |
"learning_rate": 1.3333333333333334e-06,
|
| 80 |
-
"loss": 0.
|
| 81 |
"step": 9
|
| 82 |
},
|
| 83 |
{
|
| 84 |
-
"epoch":
|
| 85 |
-
"grad_norm":
|
| 86 |
"learning_rate": 1.5e-06,
|
| 87 |
-
"loss": 0.
|
| 88 |
"step": 10
|
| 89 |
},
|
| 90 |
{
|
| 91 |
-
"epoch":
|
| 92 |
-
"grad_norm":
|
| 93 |
"learning_rate": 1.6666666666666667e-06,
|
| 94 |
-
"loss": 0.
|
| 95 |
"step": 11
|
| 96 |
},
|
| 97 |
{
|
| 98 |
-
"epoch":
|
| 99 |
-
"grad_norm": 1.
|
| 100 |
"learning_rate": 1.8333333333333333e-06,
|
| 101 |
-
"loss": 0.
|
| 102 |
"step": 12
|
| 103 |
},
|
| 104 |
{
|
| 105 |
-
"epoch":
|
| 106 |
-
"grad_norm":
|
| 107 |
"learning_rate": 2.0000000000000003e-06,
|
| 108 |
-
"loss": 0.
|
| 109 |
"step": 13
|
| 110 |
},
|
| 111 |
{
|
| 112 |
-
"epoch":
|
| 113 |
-
"grad_norm":
|
| 114 |
"learning_rate": 2.166666666666667e-06,
|
| 115 |
-
"loss": 0.
|
| 116 |
"step": 14
|
| 117 |
},
|
| 118 |
{
|
| 119 |
-
"epoch":
|
| 120 |
-
"grad_norm": 0.
|
| 121 |
"learning_rate": 2.3333333333333336e-06,
|
| 122 |
-
"loss": 0.
|
| 123 |
"step": 15
|
| 124 |
},
|
| 125 |
{
|
| 126 |
-
"epoch":
|
| 127 |
-
"
|
| 128 |
-
"
|
| 129 |
-
"
|
| 130 |
-
"
|
| 131 |
-
"step": 15
|
| 132 |
},
|
| 133 |
{
|
| 134 |
-
"epoch": 1.
|
| 135 |
-
"
|
| 136 |
-
"
|
| 137 |
-
"
|
|
|
|
| 138 |
"step": 16
|
| 139 |
},
|
| 140 |
{
|
| 141 |
-
"epoch": 1.
|
| 142 |
-
"grad_norm": 0.
|
| 143 |
"learning_rate": 2.666666666666667e-06,
|
| 144 |
-
"loss": 0.
|
| 145 |
"step": 17
|
| 146 |
},
|
| 147 |
{
|
| 148 |
-
"epoch":
|
| 149 |
-
"grad_norm": 0.
|
| 150 |
"learning_rate": 2.8333333333333335e-06,
|
| 151 |
-
"loss": 0.
|
| 152 |
"step": 18
|
| 153 |
},
|
| 154 |
{
|
| 155 |
-
"epoch":
|
| 156 |
-
"grad_norm": 0.
|
| 157 |
"learning_rate": 3e-06,
|
| 158 |
-
"loss": 0.
|
| 159 |
"step": 19
|
| 160 |
},
|
| 161 |
{
|
| 162 |
-
"epoch":
|
| 163 |
-
"grad_norm": 0.
|
| 164 |
"learning_rate": 3.1666666666666667e-06,
|
| 165 |
-
"loss": 0.
|
| 166 |
"step": 20
|
| 167 |
},
|
| 168 |
{
|
| 169 |
-
"epoch":
|
| 170 |
-
"grad_norm": 0.
|
| 171 |
"learning_rate": 3.3333333333333333e-06,
|
| 172 |
-
"loss": 0.
|
| 173 |
"step": 21
|
| 174 |
},
|
| 175 |
{
|
| 176 |
-
"epoch":
|
| 177 |
-
"grad_norm": 0.
|
| 178 |
"learning_rate": 3.5e-06,
|
| 179 |
-
"loss": 0.
|
| 180 |
"step": 22
|
| 181 |
},
|
| 182 |
{
|
| 183 |
-
"epoch":
|
| 184 |
-
"grad_norm": 0.
|
| 185 |
"learning_rate": 3.6666666666666666e-06,
|
| 186 |
-
"loss": 0.
|
| 187 |
"step": 23
|
| 188 |
},
|
| 189 |
{
|
| 190 |
-
"epoch":
|
| 191 |
-
"grad_norm": 0.
|
| 192 |
"learning_rate": 3.833333333333334e-06,
|
| 193 |
-
"loss": 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 194 |
"step": 24
|
| 195 |
},
|
| 196 |
{
|
| 197 |
-
"epoch":
|
| 198 |
-
"grad_norm": 0.
|
| 199 |
"learning_rate": 4.000000000000001e-06,
|
| 200 |
-
"loss": 0.
|
| 201 |
"step": 25
|
| 202 |
},
|
| 203 |
{
|
| 204 |
-
"epoch":
|
| 205 |
-
"grad_norm": 0.
|
| 206 |
"learning_rate": 4.166666666666667e-06,
|
| 207 |
-
"loss": 0.
|
| 208 |
"step": 26
|
| 209 |
},
|
| 210 |
{
|
| 211 |
-
"epoch":
|
| 212 |
-
"grad_norm": 0.
|
| 213 |
"learning_rate": 4.333333333333334e-06,
|
| 214 |
-
"loss": 0.
|
| 215 |
"step": 27
|
| 216 |
},
|
| 217 |
{
|
| 218 |
-
"epoch":
|
| 219 |
-
"grad_norm": 0.
|
| 220 |
"learning_rate": 4.5e-06,
|
| 221 |
-
"loss": 0.
|
| 222 |
"step": 28
|
| 223 |
},
|
| 224 |
{
|
| 225 |
-
"epoch":
|
| 226 |
-
"grad_norm": 0.
|
| 227 |
"learning_rate": 4.666666666666667e-06,
|
| 228 |
-
"loss": 0.
|
| 229 |
"step": 29
|
| 230 |
},
|
| 231 |
{
|
| 232 |
-
"epoch":
|
| 233 |
-
"grad_norm": 0.
|
| 234 |
"learning_rate": 4.833333333333333e-06,
|
| 235 |
-
"loss": 0.
|
| 236 |
-
"step": 30
|
| 237 |
-
},
|
| 238 |
-
{
|
| 239 |
-
"epoch": 1.903225806451613,
|
| 240 |
-
"eval_loss": 0.2790633738040924,
|
| 241 |
-
"eval_runtime": 47.0271,
|
| 242 |
-
"eval_samples_per_second": 9.548,
|
| 243 |
-
"eval_steps_per_second": 0.17,
|
| 244 |
"step": 30
|
| 245 |
},
|
| 246 |
{
|
| 247 |
-
"epoch":
|
| 248 |
-
"grad_norm": 0.
|
| 249 |
"learning_rate": 5e-06,
|
| 250 |
-
"loss": 0.
|
| 251 |
"step": 31
|
| 252 |
},
|
| 253 |
{
|
| 254 |
-
"epoch":
|
| 255 |
-
"grad_norm": 0.
|
| 256 |
"learning_rate": 5.1666666666666675e-06,
|
| 257 |
-
"loss": 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 258 |
"step": 32
|
| 259 |
},
|
| 260 |
{
|
| 261 |
-
"epoch":
|
| 262 |
-
"grad_norm": 0.
|
| 263 |
"learning_rate": 5.333333333333334e-06,
|
| 264 |
-
"loss": 0.
|
| 265 |
"step": 33
|
| 266 |
},
|
| 267 |
{
|
| 268 |
-
"epoch":
|
| 269 |
-
"grad_norm": 0.
|
| 270 |
"learning_rate": 5.500000000000001e-06,
|
| 271 |
-
"loss": 0.
|
| 272 |
"step": 34
|
| 273 |
},
|
| 274 |
{
|
| 275 |
-
"epoch":
|
| 276 |
-
"grad_norm": 0.
|
| 277 |
"learning_rate": 5.666666666666667e-06,
|
| 278 |
-
"loss": 0.
|
| 279 |
"step": 35
|
| 280 |
},
|
| 281 |
{
|
| 282 |
-
"epoch":
|
| 283 |
-
"grad_norm": 0.
|
| 284 |
"learning_rate": 5.833333333333334e-06,
|
| 285 |
-
"loss": 0.
|
| 286 |
"step": 36
|
| 287 |
},
|
| 288 |
{
|
| 289 |
-
"epoch":
|
| 290 |
-
"grad_norm": 0.
|
| 291 |
"learning_rate": 6e-06,
|
| 292 |
-
"loss": 0.
|
| 293 |
"step": 37
|
| 294 |
},
|
| 295 |
{
|
| 296 |
-
"epoch":
|
| 297 |
-
"grad_norm": 0.
|
| 298 |
"learning_rate": 6.166666666666667e-06,
|
| 299 |
-
"loss": 0.
|
| 300 |
"step": 38
|
| 301 |
},
|
| 302 |
{
|
| 303 |
-
"epoch":
|
| 304 |
-
"grad_norm": 0.
|
| 305 |
"learning_rate": 6.333333333333333e-06,
|
| 306 |
-
"loss": 0.
|
| 307 |
"step": 39
|
| 308 |
},
|
| 309 |
{
|
| 310 |
-
"epoch":
|
| 311 |
-
"grad_norm": 0.
|
| 312 |
"learning_rate": 6.5000000000000004e-06,
|
| 313 |
-
"loss": 0.
|
| 314 |
"step": 40
|
| 315 |
},
|
| 316 |
{
|
| 317 |
-
"epoch":
|
| 318 |
-
"
|
| 319 |
-
"
|
| 320 |
-
"
|
| 321 |
-
"
|
| 322 |
-
|
| 323 |
-
{
|
| 324 |
-
"epoch": 2.6451612903225805,
|
| 325 |
-
"grad_norm": 0.14072832465171814,
|
| 326 |
-
"learning_rate": 6.833333333333334e-06,
|
| 327 |
-
"loss": 0.2288,
|
| 328 |
-
"step": 42
|
| 329 |
-
},
|
| 330 |
-
{
|
| 331 |
-
"epoch": 2.709677419354839,
|
| 332 |
-
"grad_norm": 0.13627326488494873,
|
| 333 |
-
"learning_rate": 7e-06,
|
| 334 |
-
"loss": 0.2275,
|
| 335 |
-
"step": 43
|
| 336 |
-
},
|
| 337 |
-
{
|
| 338 |
-
"epoch": 2.774193548387097,
|
| 339 |
-
"grad_norm": 0.1376984417438507,
|
| 340 |
-
"learning_rate": 7.166666666666667e-06,
|
| 341 |
-
"loss": 0.2219,
|
| 342 |
-
"step": 44
|
| 343 |
-
},
|
| 344 |
-
{
|
| 345 |
-
"epoch": 2.838709677419355,
|
| 346 |
-
"grad_norm": 0.15370023250579834,
|
| 347 |
-
"learning_rate": 7.333333333333333e-06,
|
| 348 |
-
"loss": 0.2169,
|
| 349 |
-
"step": 45
|
| 350 |
-
},
|
| 351 |
-
{
|
| 352 |
-
"epoch": 2.838709677419355,
|
| 353 |
-
"eval_loss": 0.2274538278579712,
|
| 354 |
-
"eval_runtime": 47.3085,
|
| 355 |
-
"eval_samples_per_second": 9.491,
|
| 356 |
-
"eval_steps_per_second": 0.169,
|
| 357 |
-
"step": 45
|
| 358 |
-
},
|
| 359 |
-
{
|
| 360 |
-
"epoch": 2.903225806451613,
|
| 361 |
-
"grad_norm": 0.26084059476852417,
|
| 362 |
-
"learning_rate": 7.500000000000001e-06,
|
| 363 |
-
"loss": 0.2202,
|
| 364 |
-
"step": 46
|
| 365 |
-
},
|
| 366 |
-
{
|
| 367 |
-
"epoch": 2.967741935483871,
|
| 368 |
-
"grad_norm": 0.2038145810365677,
|
| 369 |
-
"learning_rate": 7.666666666666667e-06,
|
| 370 |
-
"loss": 0.2208,
|
| 371 |
-
"step": 47
|
| 372 |
-
},
|
| 373 |
-
{
|
| 374 |
-
"epoch": 3.0,
|
| 375 |
-
"grad_norm": 0.2038145810365677,
|
| 376 |
-
"learning_rate": 7.833333333333333e-06,
|
| 377 |
-
"loss": 0.2054,
|
| 378 |
-
"step": 48
|
| 379 |
-
},
|
| 380 |
-
{
|
| 381 |
-
"epoch": 3.064516129032258,
|
| 382 |
-
"grad_norm": 0.0778738260269165,
|
| 383 |
-
"learning_rate": 8.000000000000001e-06,
|
| 384 |
-
"loss": 0.2088,
|
| 385 |
-
"step": 49
|
| 386 |
-
},
|
| 387 |
-
{
|
| 388 |
-
"epoch": 3.129032258064516,
|
| 389 |
-
"grad_norm": 0.0922369435429573,
|
| 390 |
-
"learning_rate": 8.166666666666668e-06,
|
| 391 |
-
"loss": 0.2093,
|
| 392 |
-
"step": 50
|
| 393 |
-
},
|
| 394 |
-
{
|
| 395 |
-
"epoch": 3.193548387096774,
|
| 396 |
-
"grad_norm": 0.10241512209177017,
|
| 397 |
-
"learning_rate": 8.333333333333334e-06,
|
| 398 |
-
"loss": 0.2046,
|
| 399 |
-
"step": 51
|
| 400 |
-
},
|
| 401 |
-
{
|
| 402 |
-
"epoch": 3.258064516129032,
|
| 403 |
-
"grad_norm": 0.12188396602869034,
|
| 404 |
-
"learning_rate": 8.5e-06,
|
| 405 |
-
"loss": 0.2221,
|
| 406 |
-
"step": 52
|
| 407 |
-
},
|
| 408 |
-
{
|
| 409 |
-
"epoch": 3.3225806451612905,
|
| 410 |
-
"grad_norm": 0.08659562468528748,
|
| 411 |
-
"learning_rate": 8.666666666666668e-06,
|
| 412 |
-
"loss": 0.2101,
|
| 413 |
-
"step": 53
|
| 414 |
-
},
|
| 415 |
-
{
|
| 416 |
-
"epoch": 3.3870967741935485,
|
| 417 |
-
"grad_norm": 0.07995045930147171,
|
| 418 |
-
"learning_rate": 8.833333333333334e-06,
|
| 419 |
-
"loss": 0.2053,
|
| 420 |
-
"step": 54
|
| 421 |
-
},
|
| 422 |
-
{
|
| 423 |
-
"epoch": 3.4516129032258065,
|
| 424 |
-
"grad_norm": 0.08335064351558685,
|
| 425 |
-
"learning_rate": 9e-06,
|
| 426 |
-
"loss": 0.2128,
|
| 427 |
-
"step": 55
|
| 428 |
-
},
|
| 429 |
-
{
|
| 430 |
-
"epoch": 3.5161290322580645,
|
| 431 |
-
"grad_norm": 0.10316692292690277,
|
| 432 |
-
"learning_rate": 9.166666666666666e-06,
|
| 433 |
-
"loss": 0.191,
|
| 434 |
-
"step": 56
|
| 435 |
-
},
|
| 436 |
-
{
|
| 437 |
-
"epoch": 3.5806451612903225,
|
| 438 |
-
"grad_norm": 0.17479529976844788,
|
| 439 |
-
"learning_rate": 9.333333333333334e-06,
|
| 440 |
-
"loss": 0.1968,
|
| 441 |
-
"step": 57
|
| 442 |
-
},
|
| 443 |
-
{
|
| 444 |
-
"epoch": 3.6451612903225805,
|
| 445 |
-
"grad_norm": 0.12246640026569366,
|
| 446 |
-
"learning_rate": 9.5e-06,
|
| 447 |
-
"loss": 0.1997,
|
| 448 |
-
"step": 58
|
| 449 |
-
},
|
| 450 |
-
{
|
| 451 |
-
"epoch": 3.709677419354839,
|
| 452 |
-
"grad_norm": 0.0899316594004631,
|
| 453 |
-
"learning_rate": 9.666666666666667e-06,
|
| 454 |
-
"loss": 0.1987,
|
| 455 |
-
"step": 59
|
| 456 |
-
},
|
| 457 |
-
{
|
| 458 |
-
"epoch": 3.774193548387097,
|
| 459 |
-
"grad_norm": 0.08333521336317062,
|
| 460 |
-
"learning_rate": 9.833333333333333e-06,
|
| 461 |
-
"loss": 0.1955,
|
| 462 |
-
"step": 60
|
| 463 |
-
},
|
| 464 |
-
{
|
| 465 |
-
"epoch": 3.774193548387097,
|
| 466 |
-
"eval_loss": 0.2103077620267868,
|
| 467 |
-
"eval_runtime": 47.3577,
|
| 468 |
-
"eval_samples_per_second": 9.481,
|
| 469 |
-
"eval_steps_per_second": 0.169,
|
| 470 |
-
"step": 60
|
| 471 |
-
},
|
| 472 |
-
{
|
| 473 |
-
"epoch": 3.838709677419355,
|
| 474 |
-
"grad_norm": 0.07842453569173813,
|
| 475 |
-
"learning_rate": 1e-05,
|
| 476 |
-
"loss": 0.1921,
|
| 477 |
-
"step": 61
|
| 478 |
-
},
|
| 479 |
-
{
|
| 480 |
-
"epoch": 3.903225806451613,
|
| 481 |
-
"grad_norm": 0.08157943189144135,
|
| 482 |
-
"learning_rate": 9.890738003669029e-06,
|
| 483 |
-
"loss": 0.1981,
|
| 484 |
-
"step": 62
|
| 485 |
-
},
|
| 486 |
-
{
|
| 487 |
-
"epoch": 3.967741935483871,
|
| 488 |
-
"grad_norm": 0.08138000965118408,
|
| 489 |
-
"learning_rate": 9.567727288213005e-06,
|
| 490 |
-
"loss": 0.1986,
|
| 491 |
-
"step": 63
|
| 492 |
-
},
|
| 493 |
-
{
|
| 494 |
-
"epoch": 4.0,
|
| 495 |
-
"grad_norm": 0.171842560172081,
|
| 496 |
-
"learning_rate": 9.045084971874738e-06,
|
| 497 |
-
"loss": 0.1897,
|
| 498 |
-
"step": 64
|
| 499 |
-
},
|
| 500 |
-
{
|
| 501 |
-
"epoch": 4.064516129032258,
|
| 502 |
-
"grad_norm": 0.20634017884731293,
|
| 503 |
-
"learning_rate": 8.345653031794292e-06,
|
| 504 |
-
"loss": 0.1877,
|
| 505 |
-
"step": 65
|
| 506 |
-
},
|
| 507 |
-
{
|
| 508 |
-
"epoch": 4.129032258064516,
|
| 509 |
-
"grad_norm": 0.35513147711753845,
|
| 510 |
-
"learning_rate": 7.500000000000001e-06,
|
| 511 |
-
"loss": 0.1897,
|
| 512 |
-
"step": 66
|
| 513 |
-
},
|
| 514 |
-
{
|
| 515 |
-
"epoch": 4.193548387096774,
|
| 516 |
-
"grad_norm": 0.1434732973575592,
|
| 517 |
-
"learning_rate": 6.545084971874738e-06,
|
| 518 |
-
"loss": 0.1856,
|
| 519 |
-
"step": 67
|
| 520 |
-
},
|
| 521 |
-
{
|
| 522 |
-
"epoch": 4.258064516129032,
|
| 523 |
-
"grad_norm": 0.27667921781539917,
|
| 524 |
-
"learning_rate": 5.522642316338268e-06,
|
| 525 |
-
"loss": 0.2036,
|
| 526 |
-
"step": 68
|
| 527 |
-
},
|
| 528 |
-
{
|
| 529 |
-
"epoch": 4.32258064516129,
|
| 530 |
-
"grad_norm": 0.12108495831489563,
|
| 531 |
-
"learning_rate": 4.477357683661734e-06,
|
| 532 |
-
"loss": 0.1917,
|
| 533 |
-
"step": 69
|
| 534 |
-
},
|
| 535 |
-
{
|
| 536 |
-
"epoch": 4.387096774193548,
|
| 537 |
-
"grad_norm": 0.21641023457050323,
|
| 538 |
-
"learning_rate": 3.4549150281252635e-06,
|
| 539 |
-
"loss": 0.1878,
|
| 540 |
-
"step": 70
|
| 541 |
-
},
|
| 542 |
-
{
|
| 543 |
-
"epoch": 4.451612903225806,
|
| 544 |
-
"grad_norm": 0.12491529434919357,
|
| 545 |
-
"learning_rate": 2.5000000000000015e-06,
|
| 546 |
-
"loss": 0.1952,
|
| 547 |
-
"step": 71
|
| 548 |
-
},
|
| 549 |
-
{
|
| 550 |
-
"epoch": 4.516129032258064,
|
| 551 |
-
"grad_norm": 0.14404062926769257,
|
| 552 |
-
"learning_rate": 1.6543469682057105e-06,
|
| 553 |
-
"loss": 0.1761,
|
| 554 |
-
"step": 72
|
| 555 |
-
},
|
| 556 |
-
{
|
| 557 |
-
"epoch": 4.580645161290323,
|
| 558 |
-
"grad_norm": 0.1197192370891571,
|
| 559 |
-
"learning_rate": 9.549150281252633e-07,
|
| 560 |
-
"loss": 0.1836,
|
| 561 |
-
"step": 73
|
| 562 |
-
},
|
| 563 |
-
{
|
| 564 |
-
"epoch": 4.645161290322581,
|
| 565 |
-
"grad_norm": 0.10862907022237778,
|
| 566 |
-
"learning_rate": 4.322727117869951e-07,
|
| 567 |
-
"loss": 0.1861,
|
| 568 |
-
"step": 74
|
| 569 |
-
},
|
| 570 |
-
{
|
| 571 |
-
"epoch": 4.709677419354839,
|
| 572 |
-
"grad_norm": 0.1004861518740654,
|
| 573 |
-
"learning_rate": 1.0926199633097156e-07,
|
| 574 |
-
"loss": 0.1852,
|
| 575 |
-
"step": 75
|
| 576 |
-
},
|
| 577 |
-
{
|
| 578 |
-
"epoch": 4.709677419354839,
|
| 579 |
-
"eval_loss": 0.20321273803710938,
|
| 580 |
-
"eval_runtime": 47.2462,
|
| 581 |
-
"eval_samples_per_second": 9.503,
|
| 582 |
-
"eval_steps_per_second": 0.169,
|
| 583 |
-
"step": 75
|
| 584 |
}
|
| 585 |
],
|
| 586 |
"logging_steps": 1,
|
| 587 |
-
"max_steps":
|
| 588 |
"num_input_tokens_seen": 0,
|
| 589 |
"num_train_epochs": 5,
|
| 590 |
-
"save_steps":
|
| 591 |
"stateful_callbacks": {
|
| 592 |
"TrainerControl": {
|
| 593 |
"args": {
|
|
@@ -600,7 +355,7 @@
|
|
| 600 |
"attributes": {}
|
| 601 |
}
|
| 602 |
},
|
| 603 |
-
"total_flos":
|
| 604 |
"train_batch_size": 8,
|
| 605 |
"trial_name": null,
|
| 606 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 4.470588235294118,
|
| 6 |
+
"eval_steps": 8,
|
| 7 |
+
"global_step": 40,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
| 11 |
"log_history": [
|
| 12 |
{
|
| 13 |
+
"epoch": 0.11764705882352941,
|
| 14 |
+
"grad_norm": 4.44871711730957,
|
| 15 |
"learning_rate": 0.0,
|
| 16 |
+
"loss": 0.8246,
|
| 17 |
"step": 1
|
| 18 |
},
|
| 19 |
{
|
| 20 |
+
"epoch": 0.11764705882352941,
|
| 21 |
+
"eval_loss": 0.805208146572113,
|
| 22 |
+
"eval_runtime": 6.2252,
|
| 23 |
+
"eval_samples_per_second": 8.674,
|
| 24 |
+
"eval_steps_per_second": 0.161,
|
| 25 |
"step": 1
|
| 26 |
},
|
| 27 |
{
|
| 28 |
+
"epoch": 0.23529411764705882,
|
| 29 |
+
"grad_norm": 4.301537036895752,
|
| 30 |
"learning_rate": 1.6666666666666668e-07,
|
| 31 |
+
"loss": 0.7921,
|
| 32 |
"step": 2
|
| 33 |
},
|
| 34 |
{
|
| 35 |
+
"epoch": 0.35294117647058826,
|
| 36 |
+
"grad_norm": 4.532798767089844,
|
| 37 |
"learning_rate": 3.3333333333333335e-07,
|
| 38 |
+
"loss": 0.8146,
|
| 39 |
"step": 3
|
| 40 |
},
|
| 41 |
{
|
| 42 |
+
"epoch": 0.47058823529411764,
|
| 43 |
+
"grad_norm": 4.427340984344482,
|
| 44 |
"learning_rate": 5.000000000000001e-07,
|
| 45 |
+
"loss": 0.8033,
|
| 46 |
"step": 4
|
| 47 |
},
|
| 48 |
{
|
| 49 |
+
"epoch": 0.5882352941176471,
|
| 50 |
+
"grad_norm": 4.337186813354492,
|
| 51 |
"learning_rate": 6.666666666666667e-07,
|
| 52 |
+
"loss": 0.794,
|
| 53 |
"step": 5
|
| 54 |
},
|
| 55 |
{
|
| 56 |
+
"epoch": 0.7058823529411765,
|
| 57 |
+
"grad_norm": 4.229191303253174,
|
| 58 |
"learning_rate": 8.333333333333333e-07,
|
| 59 |
+
"loss": 0.7852,
|
| 60 |
"step": 6
|
| 61 |
},
|
| 62 |
{
|
| 63 |
+
"epoch": 0.8235294117647058,
|
| 64 |
+
"grad_norm": 4.042285442352295,
|
| 65 |
"learning_rate": 1.0000000000000002e-06,
|
| 66 |
+
"loss": 0.8128,
|
| 67 |
"step": 7
|
| 68 |
},
|
| 69 |
{
|
| 70 |
+
"epoch": 0.9411764705882353,
|
| 71 |
+
"grad_norm": 3.8515684604644775,
|
| 72 |
"learning_rate": 1.1666666666666668e-06,
|
| 73 |
+
"loss": 0.7934,
|
| 74 |
"step": 8
|
| 75 |
},
|
| 76 |
{
|
| 77 |
+
"epoch": 0.9411764705882353,
|
| 78 |
+
"eval_loss": 0.7717350721359253,
|
| 79 |
+
"eval_runtime": 6.2111,
|
| 80 |
+
"eval_samples_per_second": 8.694,
|
| 81 |
+
"eval_steps_per_second": 0.161,
|
| 82 |
+
"step": 8
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 1.0,
|
| 86 |
+
"grad_norm": 3.8515684604644775,
|
| 87 |
"learning_rate": 1.3333333333333334e-06,
|
| 88 |
+
"loss": 0.7954,
|
| 89 |
"step": 9
|
| 90 |
},
|
| 91 |
{
|
| 92 |
+
"epoch": 1.1176470588235294,
|
| 93 |
+
"grad_norm": 1.560177206993103,
|
| 94 |
"learning_rate": 1.5e-06,
|
| 95 |
+
"loss": 0.7693,
|
| 96 |
"step": 10
|
| 97 |
},
|
| 98 |
{
|
| 99 |
+
"epoch": 1.2352941176470589,
|
| 100 |
+
"grad_norm": 1.4581290483474731,
|
| 101 |
"learning_rate": 1.6666666666666667e-06,
|
| 102 |
+
"loss": 0.7423,
|
| 103 |
"step": 11
|
| 104 |
},
|
| 105 |
{
|
| 106 |
+
"epoch": 1.3529411764705883,
|
| 107 |
+
"grad_norm": 1.034300446510315,
|
| 108 |
"learning_rate": 1.8333333333333333e-06,
|
| 109 |
+
"loss": 0.7327,
|
| 110 |
"step": 12
|
| 111 |
},
|
| 112 |
{
|
| 113 |
+
"epoch": 1.4705882352941178,
|
| 114 |
+
"grad_norm": 0.8479865193367004,
|
| 115 |
"learning_rate": 2.0000000000000003e-06,
|
| 116 |
+
"loss": 0.7191,
|
| 117 |
"step": 13
|
| 118 |
},
|
| 119 |
{
|
| 120 |
+
"epoch": 1.5882352941176472,
|
| 121 |
+
"grad_norm": 0.7605553269386292,
|
| 122 |
"learning_rate": 2.166666666666667e-06,
|
| 123 |
+
"loss": 0.7157,
|
| 124 |
"step": 14
|
| 125 |
},
|
| 126 |
{
|
| 127 |
+
"epoch": 1.7058823529411766,
|
| 128 |
+
"grad_norm": 0.7409340739250183,
|
| 129 |
"learning_rate": 2.3333333333333336e-06,
|
| 130 |
+
"loss": 0.7046,
|
| 131 |
"step": 15
|
| 132 |
},
|
| 133 |
{
|
| 134 |
+
"epoch": 1.8235294117647058,
|
| 135 |
+
"grad_norm": 0.494981974363327,
|
| 136 |
+
"learning_rate": 2.5e-06,
|
| 137 |
+
"loss": 0.655,
|
| 138 |
+
"step": 16
|
|
|
|
| 139 |
},
|
| 140 |
{
|
| 141 |
+
"epoch": 1.8235294117647058,
|
| 142 |
+
"eval_loss": 0.6643162369728088,
|
| 143 |
+
"eval_runtime": 6.2115,
|
| 144 |
+
"eval_samples_per_second": 8.694,
|
| 145 |
+
"eval_steps_per_second": 0.161,
|
| 146 |
"step": 16
|
| 147 |
},
|
| 148 |
{
|
| 149 |
+
"epoch": 1.9411764705882353,
|
| 150 |
+
"grad_norm": 0.49645841121673584,
|
| 151 |
"learning_rate": 2.666666666666667e-06,
|
| 152 |
+
"loss": 0.6661,
|
| 153 |
"step": 17
|
| 154 |
},
|
| 155 |
{
|
| 156 |
+
"epoch": 2.0,
|
| 157 |
+
"grad_norm": 0.9438714981079102,
|
| 158 |
"learning_rate": 2.8333333333333335e-06,
|
| 159 |
+
"loss": 0.6513,
|
| 160 |
"step": 18
|
| 161 |
},
|
| 162 |
{
|
| 163 |
+
"epoch": 2.1176470588235294,
|
| 164 |
+
"grad_norm": 0.8686451315879822,
|
| 165 |
"learning_rate": 3e-06,
|
| 166 |
+
"loss": 0.6513,
|
| 167 |
"step": 19
|
| 168 |
},
|
| 169 |
{
|
| 170 |
+
"epoch": 2.235294117647059,
|
| 171 |
+
"grad_norm": 0.8095314502716064,
|
| 172 |
"learning_rate": 3.1666666666666667e-06,
|
| 173 |
+
"loss": 0.6406,
|
| 174 |
"step": 20
|
| 175 |
},
|
| 176 |
{
|
| 177 |
+
"epoch": 2.3529411764705883,
|
| 178 |
+
"grad_norm": 0.6763771772384644,
|
| 179 |
"learning_rate": 3.3333333333333333e-06,
|
| 180 |
+
"loss": 0.616,
|
| 181 |
"step": 21
|
| 182 |
},
|
| 183 |
{
|
| 184 |
+
"epoch": 2.4705882352941178,
|
| 185 |
+
"grad_norm": 0.8396726846694946,
|
| 186 |
"learning_rate": 3.5e-06,
|
| 187 |
+
"loss": 0.6185,
|
| 188 |
"step": 22
|
| 189 |
},
|
| 190 |
{
|
| 191 |
+
"epoch": 2.588235294117647,
|
| 192 |
+
"grad_norm": 0.8915113806724548,
|
| 193 |
"learning_rate": 3.6666666666666666e-06,
|
| 194 |
+
"loss": 0.6013,
|
| 195 |
"step": 23
|
| 196 |
},
|
| 197 |
{
|
| 198 |
+
"epoch": 2.7058823529411766,
|
| 199 |
+
"grad_norm": 0.7986668348312378,
|
| 200 |
"learning_rate": 3.833333333333334e-06,
|
| 201 |
+
"loss": 0.5917,
|
| 202 |
+
"step": 24
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 2.7058823529411766,
|
| 206 |
+
"eval_loss": 0.5887576341629028,
|
| 207 |
+
"eval_runtime": 6.2271,
|
| 208 |
+
"eval_samples_per_second": 8.672,
|
| 209 |
+
"eval_steps_per_second": 0.161,
|
| 210 |
"step": 24
|
| 211 |
},
|
| 212 |
{
|
| 213 |
+
"epoch": 2.8235294117647056,
|
| 214 |
+
"grad_norm": 0.6417509317398071,
|
| 215 |
"learning_rate": 4.000000000000001e-06,
|
| 216 |
+
"loss": 0.5879,
|
| 217 |
"step": 25
|
| 218 |
},
|
| 219 |
{
|
| 220 |
+
"epoch": 2.9411764705882355,
|
| 221 |
+
"grad_norm": 0.5458969473838806,
|
| 222 |
"learning_rate": 4.166666666666667e-06,
|
| 223 |
+
"loss": 0.5844,
|
| 224 |
"step": 26
|
| 225 |
},
|
| 226 |
{
|
| 227 |
+
"epoch": 3.0,
|
| 228 |
+
"grad_norm": 0.5458969473838806,
|
| 229 |
"learning_rate": 4.333333333333334e-06,
|
| 230 |
+
"loss": 0.5812,
|
| 231 |
"step": 27
|
| 232 |
},
|
| 233 |
{
|
| 234 |
+
"epoch": 3.1176470588235294,
|
| 235 |
+
"grad_norm": 0.2729341983795166,
|
| 236 |
"learning_rate": 4.5e-06,
|
| 237 |
+
"loss": 0.5651,
|
| 238 |
"step": 28
|
| 239 |
},
|
| 240 |
{
|
| 241 |
+
"epoch": 3.235294117647059,
|
| 242 |
+
"grad_norm": 0.2618759572505951,
|
| 243 |
"learning_rate": 4.666666666666667e-06,
|
| 244 |
+
"loss": 0.537,
|
| 245 |
"step": 29
|
| 246 |
},
|
| 247 |
{
|
| 248 |
+
"epoch": 3.3529411764705883,
|
| 249 |
+
"grad_norm": 0.2737997770309448,
|
| 250 |
"learning_rate": 4.833333333333333e-06,
|
| 251 |
+
"loss": 0.5463,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 252 |
"step": 30
|
| 253 |
},
|
| 254 |
{
|
| 255 |
+
"epoch": 3.4705882352941178,
|
| 256 |
+
"grad_norm": 0.2667374610900879,
|
| 257 |
"learning_rate": 5e-06,
|
| 258 |
+
"loss": 0.5399,
|
| 259 |
"step": 31
|
| 260 |
},
|
| 261 |
{
|
| 262 |
+
"epoch": 3.588235294117647,
|
| 263 |
+
"grad_norm": 0.26491186022758484,
|
| 264 |
"learning_rate": 5.1666666666666675e-06,
|
| 265 |
+
"loss": 0.5542,
|
| 266 |
+
"step": 32
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 3.588235294117647,
|
| 270 |
+
"eval_loss": 0.5400622487068176,
|
| 271 |
+
"eval_runtime": 6.2239,
|
| 272 |
+
"eval_samples_per_second": 8.676,
|
| 273 |
+
"eval_steps_per_second": 0.161,
|
| 274 |
"step": 32
|
| 275 |
},
|
| 276 |
{
|
| 277 |
+
"epoch": 3.7058823529411766,
|
| 278 |
+
"grad_norm": 0.2621231973171234,
|
| 279 |
"learning_rate": 5.333333333333334e-06,
|
| 280 |
+
"loss": 0.5184,
|
| 281 |
"step": 33
|
| 282 |
},
|
| 283 |
{
|
| 284 |
+
"epoch": 3.8235294117647056,
|
| 285 |
+
"grad_norm": 0.2459402233362198,
|
| 286 |
"learning_rate": 5.500000000000001e-06,
|
| 287 |
+
"loss": 0.5128,
|
| 288 |
"step": 34
|
| 289 |
},
|
| 290 |
{
|
| 291 |
+
"epoch": 3.9411764705882355,
|
| 292 |
+
"grad_norm": 0.2450851947069168,
|
| 293 |
"learning_rate": 5.666666666666667e-06,
|
| 294 |
+
"loss": 0.5173,
|
| 295 |
"step": 35
|
| 296 |
},
|
| 297 |
{
|
| 298 |
+
"epoch": 4.0,
|
| 299 |
+
"grad_norm": 0.5196430087089539,
|
| 300 |
"learning_rate": 5.833333333333334e-06,
|
| 301 |
+
"loss": 0.489,
|
| 302 |
"step": 36
|
| 303 |
},
|
| 304 |
{
|
| 305 |
+
"epoch": 4.117647058823529,
|
| 306 |
+
"grad_norm": 0.4224274158477783,
|
| 307 |
"learning_rate": 6e-06,
|
| 308 |
+
"loss": 0.5092,
|
| 309 |
"step": 37
|
| 310 |
},
|
| 311 |
{
|
| 312 |
+
"epoch": 4.235294117647059,
|
| 313 |
+
"grad_norm": 0.3706662952899933,
|
| 314 |
"learning_rate": 6.166666666666667e-06,
|
| 315 |
+
"loss": 0.4878,
|
| 316 |
"step": 38
|
| 317 |
},
|
| 318 |
{
|
| 319 |
+
"epoch": 4.352941176470588,
|
| 320 |
+
"grad_norm": 0.34465476870536804,
|
| 321 |
"learning_rate": 6.333333333333333e-06,
|
| 322 |
+
"loss": 0.4742,
|
| 323 |
"step": 39
|
| 324 |
},
|
| 325 |
{
|
| 326 |
+
"epoch": 4.470588235294118,
|
| 327 |
+
"grad_norm": 0.36074212193489075,
|
| 328 |
"learning_rate": 6.5000000000000004e-06,
|
| 329 |
+
"loss": 0.4819,
|
| 330 |
"step": 40
|
| 331 |
},
|
| 332 |
{
|
| 333 |
+
"epoch": 4.470588235294118,
|
| 334 |
+
"eval_loss": 0.5065333843231201,
|
| 335 |
+
"eval_runtime": 6.2211,
|
| 336 |
+
"eval_samples_per_second": 8.68,
|
| 337 |
+
"eval_steps_per_second": 0.161,
|
| 338 |
+
"step": 40
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 339 |
}
|
| 340 |
],
|
| 341 |
"logging_steps": 1,
|
| 342 |
+
"max_steps": 40,
|
| 343 |
"num_input_tokens_seen": 0,
|
| 344 |
"num_train_epochs": 5,
|
| 345 |
+
"save_steps": 8,
|
| 346 |
"stateful_callbacks": {
|
| 347 |
"TrainerControl": {
|
| 348 |
"args": {
|
|
|
|
| 355 |
"attributes": {}
|
| 356 |
}
|
| 357 |
},
|
| 358 |
+
"total_flos": 6.689516326362284e+18,
|
| 359 |
"train_batch_size": 8,
|
| 360 |
"trial_name": null,
|
| 361 |
"trial_params": null
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 11576
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:20edd61d5a9f82d4af66c83a4e33162991a25eb8afc528f4d4e41d56cc7399fd
|
| 3 |
size 11576
|