Training in progress, epoch 1, checkpoint
Browse files
last-checkpoint/model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2708729576
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7a4c6f5313c5413e947c3b9ae8fbdcd3db5cfb17ae9d38f3845a0d90a0a99de4
|
| 3 |
size 2708729576
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 52499200
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fa9bcb9d383cd758daed3e9bdac436feaaa8ace4983afd451ce084e4618839ef
|
| 3 |
size 52499200
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15006
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b35b4cd4104958a3e34a87e84eee852763c80157fefbeae8abd4d6ed6ea94168
|
| 3 |
size 15006
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1064
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bca4dbe650e04bc8012dd3f1938dfb2a637329721abd75c3bd59d28a64007b54
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,911 +1,43 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch":
|
| 5 |
-
"eval_steps":
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
-
{
|
| 12 |
-
"epoch": 0.07808687164470474,
|
| 13 |
-
"grad_norm": 562671.25,
|
| 14 |
-
"learning_rate": 9.921875000000001e-05,
|
| 15 |
-
"loss": 41909.175,
|
| 16 |
-
"step": 10
|
| 17 |
-
},
|
| 18 |
-
{
|
| 19 |
-
"epoch": 0.07808687164470474,
|
| 20 |
-
"eval_runtime": 19.6603,
|
| 21 |
-
"eval_samples_per_second": 21.973,
|
| 22 |
-
"eval_steps_per_second": 5.493,
|
| 23 |
-
"step": 10
|
| 24 |
-
},
|
| 25 |
-
{
|
| 26 |
-
"epoch": 0.15617374328940947,
|
| 27 |
-
"grad_norm": 344896.03125,
|
| 28 |
-
"learning_rate": 9.84375e-05,
|
| 29 |
-
"loss": 13890.8641,
|
| 30 |
-
"step": 20
|
| 31 |
-
},
|
| 32 |
-
{
|
| 33 |
-
"epoch": 0.15617374328940947,
|
| 34 |
-
"eval_runtime": 19.7074,
|
| 35 |
-
"eval_samples_per_second": 21.921,
|
| 36 |
-
"eval_steps_per_second": 5.48,
|
| 37 |
-
"step": 20
|
| 38 |
-
},
|
| 39 |
-
{
|
| 40 |
-
"epoch": 0.2342606149341142,
|
| 41 |
-
"grad_norm": 515524.21875,
|
| 42 |
-
"learning_rate": 9.765625e-05,
|
| 43 |
-
"loss": 11401.4898,
|
| 44 |
-
"step": 30
|
| 45 |
-
},
|
| 46 |
-
{
|
| 47 |
-
"epoch": 0.2342606149341142,
|
| 48 |
-
"eval_runtime": 19.7344,
|
| 49 |
-
"eval_samples_per_second": 21.891,
|
| 50 |
-
"eval_steps_per_second": 5.473,
|
| 51 |
-
"step": 30
|
| 52 |
-
},
|
| 53 |
-
{
|
| 54 |
-
"epoch": 0.31234748657881894,
|
| 55 |
-
"grad_norm": 388208.53125,
|
| 56 |
-
"learning_rate": 9.687500000000001e-05,
|
| 57 |
-
"loss": 6596.7703,
|
| 58 |
-
"step": 40
|
| 59 |
-
},
|
| 60 |
-
{
|
| 61 |
-
"epoch": 0.31234748657881894,
|
| 62 |
-
"eval_runtime": 19.7515,
|
| 63 |
-
"eval_samples_per_second": 21.872,
|
| 64 |
-
"eval_steps_per_second": 5.468,
|
| 65 |
-
"step": 40
|
| 66 |
-
},
|
| 67 |
{
|
| 68 |
"epoch": 0.3904343582235237,
|
| 69 |
-
"grad_norm":
|
| 70 |
"learning_rate": 9.609375e-05,
|
| 71 |
-
"loss":
|
| 72 |
"step": 50
|
| 73 |
},
|
| 74 |
{
|
| 75 |
"epoch": 0.3904343582235237,
|
| 76 |
-
"eval_runtime": 19.
|
| 77 |
-
"eval_samples_per_second": 21.
|
| 78 |
-
"eval_steps_per_second": 5.
|
| 79 |
"step": 50
|
| 80 |
},
|
| 81 |
-
{
|
| 82 |
-
"epoch": 0.4685212298682284,
|
| 83 |
-
"grad_norm": 694649.5625,
|
| 84 |
-
"learning_rate": 9.53125e-05,
|
| 85 |
-
"loss": 4275.273,
|
| 86 |
-
"step": 60
|
| 87 |
-
},
|
| 88 |
-
{
|
| 89 |
-
"epoch": 0.4685212298682284,
|
| 90 |
-
"eval_runtime": 19.7487,
|
| 91 |
-
"eval_samples_per_second": 21.875,
|
| 92 |
-
"eval_steps_per_second": 5.469,
|
| 93 |
-
"step": 60
|
| 94 |
-
},
|
| 95 |
-
{
|
| 96 |
-
"epoch": 0.5466081015129332,
|
| 97 |
-
"grad_norm": 375526.53125,
|
| 98 |
-
"learning_rate": 9.453125000000001e-05,
|
| 99 |
-
"loss": 5022.9281,
|
| 100 |
-
"step": 70
|
| 101 |
-
},
|
| 102 |
-
{
|
| 103 |
-
"epoch": 0.5466081015129332,
|
| 104 |
-
"eval_runtime": 19.7307,
|
| 105 |
-
"eval_samples_per_second": 21.895,
|
| 106 |
-
"eval_steps_per_second": 5.474,
|
| 107 |
-
"step": 70
|
| 108 |
-
},
|
| 109 |
-
{
|
| 110 |
-
"epoch": 0.6246949731576379,
|
| 111 |
-
"grad_norm": 603116.25,
|
| 112 |
-
"learning_rate": 9.375e-05,
|
| 113 |
-
"loss": 3630.4668,
|
| 114 |
-
"step": 80
|
| 115 |
-
},
|
| 116 |
-
{
|
| 117 |
-
"epoch": 0.6246949731576379,
|
| 118 |
-
"eval_runtime": 19.7405,
|
| 119 |
-
"eval_samples_per_second": 21.884,
|
| 120 |
-
"eval_steps_per_second": 5.471,
|
| 121 |
-
"step": 80
|
| 122 |
-
},
|
| 123 |
-
{
|
| 124 |
-
"epoch": 0.7027818448023426,
|
| 125 |
-
"grad_norm": 440137.71875,
|
| 126 |
-
"learning_rate": 9.296875e-05,
|
| 127 |
-
"loss": 3183.9186,
|
| 128 |
-
"step": 90
|
| 129 |
-
},
|
| 130 |
-
{
|
| 131 |
-
"epoch": 0.7027818448023426,
|
| 132 |
-
"eval_runtime": 19.7964,
|
| 133 |
-
"eval_samples_per_second": 21.822,
|
| 134 |
-
"eval_steps_per_second": 5.456,
|
| 135 |
-
"step": 90
|
| 136 |
-
},
|
| 137 |
{
|
| 138 |
"epoch": 0.7808687164470474,
|
| 139 |
-
"grad_norm":
|
| 140 |
"learning_rate": 9.21875e-05,
|
| 141 |
-
"loss":
|
| 142 |
"step": 100
|
| 143 |
},
|
| 144 |
{
|
| 145 |
"epoch": 0.7808687164470474,
|
| 146 |
-
"eval_runtime": 19.
|
| 147 |
-
"eval_samples_per_second": 21.
|
| 148 |
-
"eval_steps_per_second": 5.461,
|
| 149 |
-
"step": 100
|
| 150 |
-
},
|
| 151 |
-
{
|
| 152 |
-
"epoch": 0.8589555880917521,
|
| 153 |
-
"grad_norm": 639365.375,
|
| 154 |
-
"learning_rate": 9.140625e-05,
|
| 155 |
-
"loss": 4252.8562,
|
| 156 |
-
"step": 110
|
| 157 |
-
},
|
| 158 |
-
{
|
| 159 |
-
"epoch": 0.8589555880917521,
|
| 160 |
-
"eval_runtime": 19.7724,
|
| 161 |
-
"eval_samples_per_second": 21.849,
|
| 162 |
"eval_steps_per_second": 5.462,
|
| 163 |
-
"step":
|
| 164 |
-
},
|
| 165 |
-
{
|
| 166 |
-
"epoch": 0.9370424597364568,
|
| 167 |
-
"grad_norm": 398296.34375,
|
| 168 |
-
"learning_rate": 9.062500000000001e-05,
|
| 169 |
-
"loss": 3483.168,
|
| 170 |
-
"step": 120
|
| 171 |
-
},
|
| 172 |
-
{
|
| 173 |
-
"epoch": 0.9370424597364568,
|
| 174 |
-
"eval_runtime": 19.7473,
|
| 175 |
-
"eval_samples_per_second": 21.876,
|
| 176 |
-
"eval_steps_per_second": 5.469,
|
| 177 |
-
"step": 120
|
| 178 |
-
},
|
| 179 |
-
{
|
| 180 |
-
"epoch": 1.0078086871644705,
|
| 181 |
-
"grad_norm": 307601.53125,
|
| 182 |
-
"learning_rate": 8.984375e-05,
|
| 183 |
-
"loss": 3748.8004,
|
| 184 |
-
"step": 130
|
| 185 |
-
},
|
| 186 |
-
{
|
| 187 |
-
"epoch": 1.0078086871644705,
|
| 188 |
-
"eval_runtime": 19.6206,
|
| 189 |
-
"eval_samples_per_second": 22.018,
|
| 190 |
-
"eval_steps_per_second": 5.504,
|
| 191 |
-
"step": 130
|
| 192 |
-
},
|
| 193 |
-
{
|
| 194 |
-
"epoch": 1.0858955588091752,
|
| 195 |
-
"grad_norm": 535453.9375,
|
| 196 |
-
"learning_rate": 8.90625e-05,
|
| 197 |
-
"loss": 3701.0125,
|
| 198 |
-
"step": 140
|
| 199 |
-
},
|
| 200 |
-
{
|
| 201 |
-
"epoch": 1.0858955588091752,
|
| 202 |
-
"eval_runtime": 19.714,
|
| 203 |
-
"eval_samples_per_second": 21.913,
|
| 204 |
-
"eval_steps_per_second": 5.478,
|
| 205 |
-
"step": 140
|
| 206 |
-
},
|
| 207 |
-
{
|
| 208 |
-
"epoch": 1.16398243045388,
|
| 209 |
-
"grad_norm": 578524.75,
|
| 210 |
-
"learning_rate": 8.828125000000001e-05,
|
| 211 |
-
"loss": 3222.8713,
|
| 212 |
-
"step": 150
|
| 213 |
-
},
|
| 214 |
-
{
|
| 215 |
-
"epoch": 1.16398243045388,
|
| 216 |
-
"eval_runtime": 19.7417,
|
| 217 |
-
"eval_samples_per_second": 21.883,
|
| 218 |
-
"eval_steps_per_second": 5.471,
|
| 219 |
-
"step": 150
|
| 220 |
-
},
|
| 221 |
-
{
|
| 222 |
-
"epoch": 1.2420693020985847,
|
| 223 |
-
"grad_norm": 413461.9375,
|
| 224 |
-
"learning_rate": 8.75e-05,
|
| 225 |
-
"loss": 3225.8557,
|
| 226 |
-
"step": 160
|
| 227 |
-
},
|
| 228 |
-
{
|
| 229 |
-
"epoch": 1.2420693020985847,
|
| 230 |
-
"eval_runtime": 19.7549,
|
| 231 |
-
"eval_samples_per_second": 21.868,
|
| 232 |
-
"eval_steps_per_second": 5.467,
|
| 233 |
-
"step": 160
|
| 234 |
-
},
|
| 235 |
-
{
|
| 236 |
-
"epoch": 1.3201561737432894,
|
| 237 |
-
"grad_norm": 473611.9375,
|
| 238 |
-
"learning_rate": 8.671875e-05,
|
| 239 |
-
"loss": 2951.6514,
|
| 240 |
-
"step": 170
|
| 241 |
-
},
|
| 242 |
-
{
|
| 243 |
-
"epoch": 1.3201561737432894,
|
| 244 |
-
"eval_runtime": 19.7505,
|
| 245 |
-
"eval_samples_per_second": 21.873,
|
| 246 |
-
"eval_steps_per_second": 5.468,
|
| 247 |
-
"step": 170
|
| 248 |
-
},
|
| 249 |
-
{
|
| 250 |
-
"epoch": 1.3982430453879942,
|
| 251 |
-
"grad_norm": 477603.59375,
|
| 252 |
-
"learning_rate": 8.593750000000001e-05,
|
| 253 |
-
"loss": 3479.666,
|
| 254 |
-
"step": 180
|
| 255 |
-
},
|
| 256 |
-
{
|
| 257 |
-
"epoch": 1.3982430453879942,
|
| 258 |
-
"eval_runtime": 19.7691,
|
| 259 |
-
"eval_samples_per_second": 21.852,
|
| 260 |
-
"eval_steps_per_second": 5.463,
|
| 261 |
-
"step": 180
|
| 262 |
-
},
|
| 263 |
-
{
|
| 264 |
-
"epoch": 1.476329917032699,
|
| 265 |
-
"grad_norm": 284746.375,
|
| 266 |
-
"learning_rate": 8.515625e-05,
|
| 267 |
-
"loss": 2754.5521,
|
| 268 |
-
"step": 190
|
| 269 |
-
},
|
| 270 |
-
{
|
| 271 |
-
"epoch": 1.476329917032699,
|
| 272 |
-
"eval_runtime": 19.7613,
|
| 273 |
-
"eval_samples_per_second": 21.861,
|
| 274 |
-
"eval_steps_per_second": 5.465,
|
| 275 |
-
"step": 190
|
| 276 |
-
},
|
| 277 |
-
{
|
| 278 |
-
"epoch": 1.5544167886774036,
|
| 279 |
-
"grad_norm": 583813.5625,
|
| 280 |
-
"learning_rate": 8.4375e-05,
|
| 281 |
-
"loss": 1812.6566,
|
| 282 |
-
"step": 200
|
| 283 |
-
},
|
| 284 |
-
{
|
| 285 |
-
"epoch": 1.5544167886774036,
|
| 286 |
-
"eval_runtime": 19.7512,
|
| 287 |
-
"eval_samples_per_second": 21.872,
|
| 288 |
-
"eval_steps_per_second": 5.468,
|
| 289 |
-
"step": 200
|
| 290 |
-
},
|
| 291 |
-
{
|
| 292 |
-
"epoch": 1.6325036603221084,
|
| 293 |
-
"grad_norm": 277886.28125,
|
| 294 |
-
"learning_rate": 8.359375000000001e-05,
|
| 295 |
-
"loss": 2136.5822,
|
| 296 |
-
"step": 210
|
| 297 |
-
},
|
| 298 |
-
{
|
| 299 |
-
"epoch": 1.6325036603221084,
|
| 300 |
-
"eval_runtime": 19.746,
|
| 301 |
-
"eval_samples_per_second": 21.878,
|
| 302 |
-
"eval_steps_per_second": 5.469,
|
| 303 |
-
"step": 210
|
| 304 |
-
},
|
| 305 |
-
{
|
| 306 |
-
"epoch": 1.710590531966813,
|
| 307 |
-
"grad_norm": 322902.34375,
|
| 308 |
-
"learning_rate": 8.28125e-05,
|
| 309 |
-
"loss": 2078.6055,
|
| 310 |
-
"step": 220
|
| 311 |
-
},
|
| 312 |
-
{
|
| 313 |
-
"epoch": 1.710590531966813,
|
| 314 |
-
"eval_runtime": 19.7299,
|
| 315 |
-
"eval_samples_per_second": 21.896,
|
| 316 |
-
"eval_steps_per_second": 5.474,
|
| 317 |
-
"step": 220
|
| 318 |
-
},
|
| 319 |
-
{
|
| 320 |
-
"epoch": 1.7886774036115178,
|
| 321 |
-
"grad_norm": 453730.34375,
|
| 322 |
-
"learning_rate": 8.203125e-05,
|
| 323 |
-
"loss": 2769.8313,
|
| 324 |
-
"step": 230
|
| 325 |
-
},
|
| 326 |
-
{
|
| 327 |
-
"epoch": 1.7886774036115178,
|
| 328 |
-
"eval_runtime": 19.7557,
|
| 329 |
-
"eval_samples_per_second": 21.867,
|
| 330 |
-
"eval_steps_per_second": 5.467,
|
| 331 |
-
"step": 230
|
| 332 |
-
},
|
| 333 |
-
{
|
| 334 |
-
"epoch": 1.8667642752562226,
|
| 335 |
-
"grad_norm": 267086.625,
|
| 336 |
-
"learning_rate": 8.125000000000001e-05,
|
| 337 |
-
"loss": 1964.433,
|
| 338 |
-
"step": 240
|
| 339 |
-
},
|
| 340 |
-
{
|
| 341 |
-
"epoch": 1.8667642752562226,
|
| 342 |
-
"eval_runtime": 19.7438,
|
| 343 |
-
"eval_samples_per_second": 21.88,
|
| 344 |
-
"eval_steps_per_second": 5.47,
|
| 345 |
-
"step": 240
|
| 346 |
-
},
|
| 347 |
-
{
|
| 348 |
-
"epoch": 1.9448511469009273,
|
| 349 |
-
"grad_norm": 587362.4375,
|
| 350 |
-
"learning_rate": 8.046875e-05,
|
| 351 |
-
"loss": 1856.9432,
|
| 352 |
-
"step": 250
|
| 353 |
-
},
|
| 354 |
-
{
|
| 355 |
-
"epoch": 1.9448511469009273,
|
| 356 |
-
"eval_runtime": 19.8026,
|
| 357 |
-
"eval_samples_per_second": 21.815,
|
| 358 |
-
"eval_steps_per_second": 5.454,
|
| 359 |
-
"step": 250
|
| 360 |
-
},
|
| 361 |
-
{
|
| 362 |
-
"epoch": 2.015617374328941,
|
| 363 |
-
"grad_norm": 502681.75,
|
| 364 |
-
"learning_rate": 7.96875e-05,
|
| 365 |
-
"loss": 3382.1129,
|
| 366 |
-
"step": 260
|
| 367 |
-
},
|
| 368 |
-
{
|
| 369 |
-
"epoch": 2.015617374328941,
|
| 370 |
-
"eval_runtime": 19.6846,
|
| 371 |
-
"eval_samples_per_second": 21.946,
|
| 372 |
-
"eval_steps_per_second": 5.487,
|
| 373 |
-
"step": 260
|
| 374 |
-
},
|
| 375 |
-
{
|
| 376 |
-
"epoch": 2.0937042459736457,
|
| 377 |
-
"grad_norm": 191029.828125,
|
| 378 |
-
"learning_rate": 7.890625000000001e-05,
|
| 379 |
-
"loss": 2202.6236,
|
| 380 |
-
"step": 270
|
| 381 |
-
},
|
| 382 |
-
{
|
| 383 |
-
"epoch": 2.0937042459736457,
|
| 384 |
-
"eval_runtime": 19.7242,
|
| 385 |
-
"eval_samples_per_second": 21.902,
|
| 386 |
-
"eval_steps_per_second": 5.476,
|
| 387 |
-
"step": 270
|
| 388 |
-
},
|
| 389 |
-
{
|
| 390 |
-
"epoch": 2.1717911176183504,
|
| 391 |
-
"grad_norm": 262116.109375,
|
| 392 |
-
"learning_rate": 7.8125e-05,
|
| 393 |
-
"loss": 1782.3984,
|
| 394 |
-
"step": 280
|
| 395 |
-
},
|
| 396 |
-
{
|
| 397 |
-
"epoch": 2.1717911176183504,
|
| 398 |
-
"eval_runtime": 19.7531,
|
| 399 |
-
"eval_samples_per_second": 21.87,
|
| 400 |
-
"eval_steps_per_second": 5.467,
|
| 401 |
-
"step": 280
|
| 402 |
-
},
|
| 403 |
-
{
|
| 404 |
-
"epoch": 2.249877989263055,
|
| 405 |
-
"grad_norm": 389979.4375,
|
| 406 |
-
"learning_rate": 7.734375e-05,
|
| 407 |
-
"loss": 1784.0506,
|
| 408 |
-
"step": 290
|
| 409 |
-
},
|
| 410 |
-
{
|
| 411 |
-
"epoch": 2.249877989263055,
|
| 412 |
-
"eval_runtime": 19.7431,
|
| 413 |
-
"eval_samples_per_second": 21.881,
|
| 414 |
-
"eval_steps_per_second": 5.47,
|
| 415 |
-
"step": 290
|
| 416 |
-
},
|
| 417 |
-
{
|
| 418 |
-
"epoch": 2.32796486090776,
|
| 419 |
-
"grad_norm": 392025.96875,
|
| 420 |
-
"learning_rate": 7.65625e-05,
|
| 421 |
-
"loss": 1743.6416,
|
| 422 |
-
"step": 300
|
| 423 |
-
},
|
| 424 |
-
{
|
| 425 |
-
"epoch": 2.32796486090776,
|
| 426 |
-
"eval_runtime": 19.7493,
|
| 427 |
-
"eval_samples_per_second": 21.874,
|
| 428 |
-
"eval_steps_per_second": 5.469,
|
| 429 |
-
"step": 300
|
| 430 |
-
},
|
| 431 |
-
{
|
| 432 |
-
"epoch": 2.4060517325524646,
|
| 433 |
-
"grad_norm": 424892.03125,
|
| 434 |
-
"learning_rate": 7.578125e-05,
|
| 435 |
-
"loss": 1824.1576,
|
| 436 |
-
"step": 310
|
| 437 |
-
},
|
| 438 |
-
{
|
| 439 |
-
"epoch": 2.4060517325524646,
|
| 440 |
-
"eval_runtime": 19.7454,
|
| 441 |
-
"eval_samples_per_second": 21.879,
|
| 442 |
-
"eval_steps_per_second": 5.47,
|
| 443 |
-
"step": 310
|
| 444 |
-
},
|
| 445 |
-
{
|
| 446 |
-
"epoch": 2.4841386041971694,
|
| 447 |
-
"grad_norm": 319042.1875,
|
| 448 |
-
"learning_rate": 7.500000000000001e-05,
|
| 449 |
-
"loss": 1743.5293,
|
| 450 |
-
"step": 320
|
| 451 |
-
},
|
| 452 |
-
{
|
| 453 |
-
"epoch": 2.4841386041971694,
|
| 454 |
-
"eval_runtime": 19.756,
|
| 455 |
-
"eval_samples_per_second": 21.867,
|
| 456 |
-
"eval_steps_per_second": 5.467,
|
| 457 |
-
"step": 320
|
| 458 |
-
},
|
| 459 |
-
{
|
| 460 |
-
"epoch": 2.562225475841874,
|
| 461 |
-
"grad_norm": 519256.40625,
|
| 462 |
-
"learning_rate": 7.421875e-05,
|
| 463 |
-
"loss": 1764.0594,
|
| 464 |
-
"step": 330
|
| 465 |
-
},
|
| 466 |
-
{
|
| 467 |
-
"epoch": 2.562225475841874,
|
| 468 |
-
"eval_runtime": 19.7543,
|
| 469 |
-
"eval_samples_per_second": 21.869,
|
| 470 |
-
"eval_steps_per_second": 5.467,
|
| 471 |
-
"step": 330
|
| 472 |
-
},
|
| 473 |
-
{
|
| 474 |
-
"epoch": 2.640312347486579,
|
| 475 |
-
"grad_norm": 210543.75,
|
| 476 |
-
"learning_rate": 7.34375e-05,
|
| 477 |
-
"loss": 1172.6759,
|
| 478 |
-
"step": 340
|
| 479 |
-
},
|
| 480 |
-
{
|
| 481 |
-
"epoch": 2.640312347486579,
|
| 482 |
-
"eval_runtime": 19.7374,
|
| 483 |
-
"eval_samples_per_second": 21.887,
|
| 484 |
-
"eval_steps_per_second": 5.472,
|
| 485 |
-
"step": 340
|
| 486 |
-
},
|
| 487 |
-
{
|
| 488 |
-
"epoch": 2.7183992191312836,
|
| 489 |
-
"grad_norm": 259726.9375,
|
| 490 |
-
"learning_rate": 7.265625000000001e-05,
|
| 491 |
-
"loss": 1670.5373,
|
| 492 |
-
"step": 350
|
| 493 |
-
},
|
| 494 |
-
{
|
| 495 |
-
"epoch": 2.7183992191312836,
|
| 496 |
-
"eval_runtime": 19.7387,
|
| 497 |
-
"eval_samples_per_second": 21.886,
|
| 498 |
-
"eval_steps_per_second": 5.471,
|
| 499 |
-
"step": 350
|
| 500 |
-
},
|
| 501 |
-
{
|
| 502 |
-
"epoch": 2.7964860907759883,
|
| 503 |
-
"grad_norm": 575974.4375,
|
| 504 |
-
"learning_rate": 7.1875e-05,
|
| 505 |
-
"loss": 2305.6137,
|
| 506 |
-
"step": 360
|
| 507 |
-
},
|
| 508 |
-
{
|
| 509 |
-
"epoch": 2.7964860907759883,
|
| 510 |
-
"eval_runtime": 19.7355,
|
| 511 |
-
"eval_samples_per_second": 21.889,
|
| 512 |
-
"eval_steps_per_second": 5.472,
|
| 513 |
-
"step": 360
|
| 514 |
-
},
|
| 515 |
-
{
|
| 516 |
-
"epoch": 2.874572962420693,
|
| 517 |
-
"grad_norm": 529809.125,
|
| 518 |
-
"learning_rate": 7.109375e-05,
|
| 519 |
-
"loss": 2236.2371,
|
| 520 |
-
"step": 370
|
| 521 |
-
},
|
| 522 |
-
{
|
| 523 |
-
"epoch": 2.874572962420693,
|
| 524 |
-
"eval_runtime": 19.7607,
|
| 525 |
-
"eval_samples_per_second": 21.862,
|
| 526 |
-
"eval_steps_per_second": 5.465,
|
| 527 |
-
"step": 370
|
| 528 |
-
},
|
| 529 |
-
{
|
| 530 |
-
"epoch": 2.952659834065398,
|
| 531 |
-
"grad_norm": 649306.875,
|
| 532 |
-
"learning_rate": 7.031250000000001e-05,
|
| 533 |
-
"loss": 1477.9074,
|
| 534 |
-
"step": 380
|
| 535 |
-
},
|
| 536 |
-
{
|
| 537 |
-
"epoch": 2.952659834065398,
|
| 538 |
-
"eval_runtime": 19.7461,
|
| 539 |
-
"eval_samples_per_second": 21.878,
|
| 540 |
-
"eval_steps_per_second": 5.469,
|
| 541 |
-
"step": 380
|
| 542 |
-
},
|
| 543 |
-
{
|
| 544 |
-
"epoch": 3.0234260614934114,
|
| 545 |
-
"grad_norm": 468387.1875,
|
| 546 |
-
"learning_rate": 6.953125e-05,
|
| 547 |
-
"loss": 1111.9008,
|
| 548 |
-
"step": 390
|
| 549 |
-
},
|
| 550 |
-
{
|
| 551 |
-
"epoch": 3.0234260614934114,
|
| 552 |
-
"eval_runtime": 19.6555,
|
| 553 |
-
"eval_samples_per_second": 21.979,
|
| 554 |
-
"eval_steps_per_second": 5.495,
|
| 555 |
-
"step": 390
|
| 556 |
-
},
|
| 557 |
-
{
|
| 558 |
-
"epoch": 3.101512933138116,
|
| 559 |
-
"grad_norm": 396892.71875,
|
| 560 |
-
"learning_rate": 6.875e-05,
|
| 561 |
-
"loss": 1161.8062,
|
| 562 |
-
"step": 400
|
| 563 |
-
},
|
| 564 |
-
{
|
| 565 |
-
"epoch": 3.101512933138116,
|
| 566 |
-
"eval_runtime": 19.6988,
|
| 567 |
-
"eval_samples_per_second": 21.93,
|
| 568 |
-
"eval_steps_per_second": 5.483,
|
| 569 |
-
"step": 400
|
| 570 |
-
},
|
| 571 |
-
{
|
| 572 |
-
"epoch": 3.179599804782821,
|
| 573 |
-
"grad_norm": 267550.6875,
|
| 574 |
-
"learning_rate": 6.796875000000001e-05,
|
| 575 |
-
"loss": 1332.8658,
|
| 576 |
-
"step": 410
|
| 577 |
-
},
|
| 578 |
-
{
|
| 579 |
-
"epoch": 3.179599804782821,
|
| 580 |
-
"eval_runtime": 19.7594,
|
| 581 |
-
"eval_samples_per_second": 21.863,
|
| 582 |
-
"eval_steps_per_second": 5.466,
|
| 583 |
-
"step": 410
|
| 584 |
-
},
|
| 585 |
-
{
|
| 586 |
-
"epoch": 3.2576866764275256,
|
| 587 |
-
"grad_norm": 383417.75,
|
| 588 |
-
"learning_rate": 6.71875e-05,
|
| 589 |
-
"loss": 1149.9299,
|
| 590 |
-
"step": 420
|
| 591 |
-
},
|
| 592 |
-
{
|
| 593 |
-
"epoch": 3.2576866764275256,
|
| 594 |
-
"eval_runtime": 19.7802,
|
| 595 |
-
"eval_samples_per_second": 21.84,
|
| 596 |
-
"eval_steps_per_second": 5.46,
|
| 597 |
-
"step": 420
|
| 598 |
-
},
|
| 599 |
-
{
|
| 600 |
-
"epoch": 3.3357735480722304,
|
| 601 |
-
"grad_norm": 197298.359375,
|
| 602 |
-
"learning_rate": 6.640625e-05,
|
| 603 |
-
"loss": 1427.1258,
|
| 604 |
-
"step": 430
|
| 605 |
-
},
|
| 606 |
-
{
|
| 607 |
-
"epoch": 3.3357735480722304,
|
| 608 |
-
"eval_runtime": 19.7807,
|
| 609 |
-
"eval_samples_per_second": 21.84,
|
| 610 |
-
"eval_steps_per_second": 5.46,
|
| 611 |
-
"step": 430
|
| 612 |
-
},
|
| 613 |
-
{
|
| 614 |
-
"epoch": 3.413860419716935,
|
| 615 |
-
"grad_norm": 196738.484375,
|
| 616 |
-
"learning_rate": 6.562500000000001e-05,
|
| 617 |
-
"loss": 1029.203,
|
| 618 |
-
"step": 440
|
| 619 |
-
},
|
| 620 |
-
{
|
| 621 |
-
"epoch": 3.413860419716935,
|
| 622 |
-
"eval_runtime": 19.7502,
|
| 623 |
-
"eval_samples_per_second": 21.873,
|
| 624 |
-
"eval_steps_per_second": 5.468,
|
| 625 |
-
"step": 440
|
| 626 |
-
},
|
| 627 |
-
{
|
| 628 |
-
"epoch": 3.49194729136164,
|
| 629 |
-
"grad_norm": 415209.96875,
|
| 630 |
-
"learning_rate": 6.484375e-05,
|
| 631 |
-
"loss": 1040.8042,
|
| 632 |
-
"step": 450
|
| 633 |
-
},
|
| 634 |
-
{
|
| 635 |
-
"epoch": 3.49194729136164,
|
| 636 |
-
"eval_runtime": 19.7611,
|
| 637 |
-
"eval_samples_per_second": 21.861,
|
| 638 |
-
"eval_steps_per_second": 5.465,
|
| 639 |
-
"step": 450
|
| 640 |
-
},
|
| 641 |
-
{
|
| 642 |
-
"epoch": 3.5700341630063446,
|
| 643 |
-
"grad_norm": 328070.78125,
|
| 644 |
-
"learning_rate": 6.40625e-05,
|
| 645 |
-
"loss": 977.6191,
|
| 646 |
-
"step": 460
|
| 647 |
-
},
|
| 648 |
-
{
|
| 649 |
-
"epoch": 3.5700341630063446,
|
| 650 |
-
"eval_runtime": 19.7543,
|
| 651 |
-
"eval_samples_per_second": 21.869,
|
| 652 |
-
"eval_steps_per_second": 5.467,
|
| 653 |
-
"step": 460
|
| 654 |
-
},
|
| 655 |
-
{
|
| 656 |
-
"epoch": 3.6481210346510493,
|
| 657 |
-
"grad_norm": 327954.34375,
|
| 658 |
-
"learning_rate": 6.328125e-05,
|
| 659 |
-
"loss": 893.5069,
|
| 660 |
-
"step": 470
|
| 661 |
-
},
|
| 662 |
-
{
|
| 663 |
-
"epoch": 3.6481210346510493,
|
| 664 |
-
"eval_runtime": 19.7609,
|
| 665 |
-
"eval_samples_per_second": 21.861,
|
| 666 |
-
"eval_steps_per_second": 5.465,
|
| 667 |
-
"step": 470
|
| 668 |
-
},
|
| 669 |
-
{
|
| 670 |
-
"epoch": 3.726207906295754,
|
| 671 |
-
"grad_norm": 429292.5625,
|
| 672 |
-
"learning_rate": 6.25e-05,
|
| 673 |
-
"loss": 982.0832,
|
| 674 |
-
"step": 480
|
| 675 |
-
},
|
| 676 |
-
{
|
| 677 |
-
"epoch": 3.726207906295754,
|
| 678 |
-
"eval_runtime": 19.7484,
|
| 679 |
-
"eval_samples_per_second": 21.875,
|
| 680 |
-
"eval_steps_per_second": 5.469,
|
| 681 |
-
"step": 480
|
| 682 |
-
},
|
| 683 |
-
{
|
| 684 |
-
"epoch": 3.804294777940459,
|
| 685 |
-
"grad_norm": 388092.28125,
|
| 686 |
-
"learning_rate": 6.171875e-05,
|
| 687 |
-
"loss": 849.4025,
|
| 688 |
-
"step": 490
|
| 689 |
-
},
|
| 690 |
-
{
|
| 691 |
-
"epoch": 3.804294777940459,
|
| 692 |
-
"eval_runtime": 19.7469,
|
| 693 |
-
"eval_samples_per_second": 21.877,
|
| 694 |
-
"eval_steps_per_second": 5.469,
|
| 695 |
-
"step": 490
|
| 696 |
-
},
|
| 697 |
-
{
|
| 698 |
-
"epoch": 3.8823816495851635,
|
| 699 |
-
"grad_norm": 240416.734375,
|
| 700 |
-
"learning_rate": 6.0937500000000004e-05,
|
| 701 |
-
"loss": 1007.4567,
|
| 702 |
-
"step": 500
|
| 703 |
-
},
|
| 704 |
-
{
|
| 705 |
-
"epoch": 3.8823816495851635,
|
| 706 |
-
"eval_runtime": 19.7422,
|
| 707 |
-
"eval_samples_per_second": 21.882,
|
| 708 |
-
"eval_steps_per_second": 5.471,
|
| 709 |
-
"step": 500
|
| 710 |
-
},
|
| 711 |
-
{
|
| 712 |
-
"epoch": 3.9604685212298683,
|
| 713 |
-
"grad_norm": 309579.21875,
|
| 714 |
-
"learning_rate": 6.015625e-05,
|
| 715 |
-
"loss": 960.0591,
|
| 716 |
-
"step": 510
|
| 717 |
-
},
|
| 718 |
-
{
|
| 719 |
-
"epoch": 3.9604685212298683,
|
| 720 |
-
"eval_runtime": 19.7662,
|
| 721 |
-
"eval_samples_per_second": 21.855,
|
| 722 |
-
"eval_steps_per_second": 5.464,
|
| 723 |
-
"step": 510
|
| 724 |
-
},
|
| 725 |
-
{
|
| 726 |
-
"epoch": 4.031234748657882,
|
| 727 |
-
"grad_norm": 484968.46875,
|
| 728 |
-
"learning_rate": 5.9375e-05,
|
| 729 |
-
"loss": 1164.3749,
|
| 730 |
-
"step": 520
|
| 731 |
-
},
|
| 732 |
-
{
|
| 733 |
-
"epoch": 4.031234748657882,
|
| 734 |
-
"eval_runtime": 19.6732,
|
| 735 |
-
"eval_samples_per_second": 21.959,
|
| 736 |
-
"eval_steps_per_second": 5.49,
|
| 737 |
-
"step": 520
|
| 738 |
-
},
|
| 739 |
-
{
|
| 740 |
-
"epoch": 4.109321620302587,
|
| 741 |
-
"grad_norm": 329296.75,
|
| 742 |
-
"learning_rate": 5.8593750000000005e-05,
|
| 743 |
-
"loss": 1631.9979,
|
| 744 |
-
"step": 530
|
| 745 |
-
},
|
| 746 |
-
{
|
| 747 |
-
"epoch": 4.109321620302587,
|
| 748 |
-
"eval_runtime": 19.7244,
|
| 749 |
-
"eval_samples_per_second": 21.902,
|
| 750 |
-
"eval_steps_per_second": 5.475,
|
| 751 |
-
"step": 530
|
| 752 |
-
},
|
| 753 |
-
{
|
| 754 |
-
"epoch": 4.187408491947291,
|
| 755 |
-
"grad_norm": 554537.125,
|
| 756 |
-
"learning_rate": 5.78125e-05,
|
| 757 |
-
"loss": 1570.2684,
|
| 758 |
-
"step": 540
|
| 759 |
-
},
|
| 760 |
-
{
|
| 761 |
-
"epoch": 4.187408491947291,
|
| 762 |
-
"eval_runtime": 19.7495,
|
| 763 |
-
"eval_samples_per_second": 21.874,
|
| 764 |
-
"eval_steps_per_second": 5.468,
|
| 765 |
-
"step": 540
|
| 766 |
-
},
|
| 767 |
-
{
|
| 768 |
-
"epoch": 4.265495363591996,
|
| 769 |
-
"grad_norm": 417775.03125,
|
| 770 |
-
"learning_rate": 5.703125e-05,
|
| 771 |
-
"loss": 1599.58,
|
| 772 |
-
"step": 550
|
| 773 |
-
},
|
| 774 |
-
{
|
| 775 |
-
"epoch": 4.265495363591996,
|
| 776 |
-
"eval_runtime": 19.7438,
|
| 777 |
-
"eval_samples_per_second": 21.88,
|
| 778 |
-
"eval_steps_per_second": 5.47,
|
| 779 |
-
"step": 550
|
| 780 |
-
},
|
| 781 |
-
{
|
| 782 |
-
"epoch": 4.343582235236701,
|
| 783 |
-
"grad_norm": 308738.78125,
|
| 784 |
-
"learning_rate": 5.6250000000000005e-05,
|
| 785 |
-
"loss": 1184.2381,
|
| 786 |
-
"step": 560
|
| 787 |
-
},
|
| 788 |
-
{
|
| 789 |
-
"epoch": 4.343582235236701,
|
| 790 |
-
"eval_runtime": 19.7443,
|
| 791 |
-
"eval_samples_per_second": 21.88,
|
| 792 |
-
"eval_steps_per_second": 5.47,
|
| 793 |
-
"step": 560
|
| 794 |
-
},
|
| 795 |
-
{
|
| 796 |
-
"epoch": 4.421669106881406,
|
| 797 |
-
"grad_norm": 281127.5625,
|
| 798 |
-
"learning_rate": 5.546875e-05,
|
| 799 |
-
"loss": 969.7674,
|
| 800 |
-
"step": 570
|
| 801 |
-
},
|
| 802 |
-
{
|
| 803 |
-
"epoch": 4.421669106881406,
|
| 804 |
-
"eval_runtime": 19.7635,
|
| 805 |
-
"eval_samples_per_second": 21.858,
|
| 806 |
-
"eval_steps_per_second": 5.465,
|
| 807 |
-
"step": 570
|
| 808 |
-
},
|
| 809 |
-
{
|
| 810 |
-
"epoch": 4.49975597852611,
|
| 811 |
-
"grad_norm": 343310.84375,
|
| 812 |
-
"learning_rate": 5.46875e-05,
|
| 813 |
-
"loss": 938.8365,
|
| 814 |
-
"step": 580
|
| 815 |
-
},
|
| 816 |
-
{
|
| 817 |
-
"epoch": 4.49975597852611,
|
| 818 |
-
"eval_runtime": 19.7819,
|
| 819 |
-
"eval_samples_per_second": 21.838,
|
| 820 |
-
"eval_steps_per_second": 5.46,
|
| 821 |
-
"step": 580
|
| 822 |
-
},
|
| 823 |
-
{
|
| 824 |
-
"epoch": 4.577842850170815,
|
| 825 |
-
"grad_norm": 274241.34375,
|
| 826 |
-
"learning_rate": 5.3906250000000006e-05,
|
| 827 |
-
"loss": 1338.7786,
|
| 828 |
-
"step": 590
|
| 829 |
-
},
|
| 830 |
-
{
|
| 831 |
-
"epoch": 4.577842850170815,
|
| 832 |
-
"eval_runtime": 19.7579,
|
| 833 |
-
"eval_samples_per_second": 21.865,
|
| 834 |
-
"eval_steps_per_second": 5.466,
|
| 835 |
-
"step": 590
|
| 836 |
-
},
|
| 837 |
-
{
|
| 838 |
-
"epoch": 4.65592972181552,
|
| 839 |
-
"grad_norm": 416818.875,
|
| 840 |
-
"learning_rate": 5.3125000000000004e-05,
|
| 841 |
-
"loss": 1180.1237,
|
| 842 |
-
"step": 600
|
| 843 |
-
},
|
| 844 |
-
{
|
| 845 |
-
"epoch": 4.65592972181552,
|
| 846 |
-
"eval_runtime": 19.7618,
|
| 847 |
-
"eval_samples_per_second": 21.86,
|
| 848 |
-
"eval_steps_per_second": 5.465,
|
| 849 |
-
"step": 600
|
| 850 |
-
},
|
| 851 |
-
{
|
| 852 |
-
"epoch": 4.7340165934602245,
|
| 853 |
-
"grad_norm": 292501.71875,
|
| 854 |
-
"learning_rate": 5.234375e-05,
|
| 855 |
-
"loss": 1117.2909,
|
| 856 |
-
"step": 610
|
| 857 |
-
},
|
| 858 |
-
{
|
| 859 |
-
"epoch": 4.7340165934602245,
|
| 860 |
-
"eval_runtime": 19.7565,
|
| 861 |
-
"eval_samples_per_second": 21.866,
|
| 862 |
-
"eval_steps_per_second": 5.467,
|
| 863 |
-
"step": 610
|
| 864 |
-
},
|
| 865 |
-
{
|
| 866 |
-
"epoch": 4.812103465104929,
|
| 867 |
-
"grad_norm": 415090.75,
|
| 868 |
-
"learning_rate": 5.15625e-05,
|
| 869 |
-
"loss": 1297.7303,
|
| 870 |
-
"step": 620
|
| 871 |
-
},
|
| 872 |
-
{
|
| 873 |
-
"epoch": 4.812103465104929,
|
| 874 |
-
"eval_runtime": 19.7543,
|
| 875 |
-
"eval_samples_per_second": 21.869,
|
| 876 |
-
"eval_steps_per_second": 5.467,
|
| 877 |
-
"step": 620
|
| 878 |
-
},
|
| 879 |
-
{
|
| 880 |
-
"epoch": 4.890190336749634,
|
| 881 |
-
"grad_norm": 481957.6875,
|
| 882 |
-
"learning_rate": 5.0781250000000004e-05,
|
| 883 |
-
"loss": 1024.6031,
|
| 884 |
-
"step": 630
|
| 885 |
-
},
|
| 886 |
-
{
|
| 887 |
-
"epoch": 4.890190336749634,
|
| 888 |
-
"eval_runtime": 19.7456,
|
| 889 |
-
"eval_samples_per_second": 21.878,
|
| 890 |
-
"eval_steps_per_second": 5.47,
|
| 891 |
-
"step": 630
|
| 892 |
-
},
|
| 893 |
-
{
|
| 894 |
-
"epoch": 4.968277208394339,
|
| 895 |
-
"grad_norm": 760376.8125,
|
| 896 |
-
"learning_rate": 5e-05,
|
| 897 |
-
"loss": 1106.1675,
|
| 898 |
-
"step": 640
|
| 899 |
-
},
|
| 900 |
-
{
|
| 901 |
-
"epoch": 4.968277208394339,
|
| 902 |
-
"eval_runtime": 19.7415,
|
| 903 |
-
"eval_samples_per_second": 21.883,
|
| 904 |
-
"eval_steps_per_second": 5.471,
|
| 905 |
-
"step": 640
|
| 906 |
}
|
| 907 |
],
|
| 908 |
-
"logging_steps":
|
| 909 |
"max_steps": 1280,
|
| 910 |
"num_input_tokens_seen": 0,
|
| 911 |
"num_train_epochs": 10,
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.0,
|
| 5 |
+
"eval_steps": 50,
|
| 6 |
+
"global_step": 129,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11 |
{
|
| 12 |
"epoch": 0.3904343582235237,
|
| 13 |
+
"grad_norm": 316011.5625,
|
| 14 |
"learning_rate": 9.609375e-05,
|
| 15 |
+
"loss": 14505.3388,
|
| 16 |
"step": 50
|
| 17 |
},
|
| 18 |
{
|
| 19 |
"epoch": 0.3904343582235237,
|
| 20 |
+
"eval_runtime": 19.78,
|
| 21 |
+
"eval_samples_per_second": 21.84,
|
| 22 |
+
"eval_steps_per_second": 5.46,
|
| 23 |
"step": 50
|
| 24 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 25 |
{
|
| 26 |
"epoch": 0.7808687164470474,
|
| 27 |
+
"grad_norm": 484251.53125,
|
| 28 |
"learning_rate": 9.21875e-05,
|
| 29 |
+
"loss": 4453.3172,
|
| 30 |
"step": 100
|
| 31 |
},
|
| 32 |
{
|
| 33 |
"epoch": 0.7808687164470474,
|
| 34 |
+
"eval_runtime": 19.7737,
|
| 35 |
+
"eval_samples_per_second": 21.847,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 36 |
"eval_steps_per_second": 5.462,
|
| 37 |
+
"step": 100
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 38 |
}
|
| 39 |
],
|
| 40 |
+
"logging_steps": 50,
|
| 41 |
"max_steps": 1280,
|
| 42 |
"num_input_tokens_seen": 0,
|
| 43 |
"num_train_epochs": 10,
|
last-checkpoint/training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5368
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:92b5f8d0521197ff491c9441a0c4a83340523a4da4d855bb0373622873120eb0
|
| 3 |
size 5368
|