Training in progress, step 50, checkpoint
Browse files
last-checkpoint/adapter_config.json
CHANGED
|
@@ -16,17 +16,17 @@
|
|
| 16 |
"megatron_core": "megatron.core",
|
| 17 |
"modules_to_save": null,
|
| 18 |
"peft_type": "LORA",
|
| 19 |
-
"r":
|
| 20 |
"rank_pattern": {},
|
| 21 |
"revision": null,
|
| 22 |
"target_modules": [
|
| 23 |
-
"q_proj",
|
| 24 |
-
"k_proj",
|
| 25 |
-
"up_proj",
|
| 26 |
-
"v_proj",
|
| 27 |
"down_proj",
|
|
|
|
|
|
|
|
|
|
| 28 |
"gate_proj",
|
| 29 |
-
"
|
|
|
|
| 30 |
],
|
| 31 |
"task_type": "CAUSAL_LM",
|
| 32 |
"use_dora": false,
|
|
|
|
| 16 |
"megatron_core": "megatron.core",
|
| 17 |
"modules_to_save": null,
|
| 18 |
"peft_type": "LORA",
|
| 19 |
+
"r": 32,
|
| 20 |
"rank_pattern": {},
|
| 21 |
"revision": null,
|
| 22 |
"target_modules": [
|
|
|
|
|
|
|
|
|
|
|
|
|
| 23 |
"down_proj",
|
| 24 |
+
"k_proj",
|
| 25 |
+
"o_proj",
|
| 26 |
+
"q_proj",
|
| 27 |
"gate_proj",
|
| 28 |
+
"up_proj",
|
| 29 |
+
"v_proj"
|
| 30 |
],
|
| 31 |
"task_type": "CAUSAL_LM",
|
| 32 |
"use_dora": false,
|
last-checkpoint/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:43756c87d3c353cd42eeb6185a59e755a36f9b382d2d1141fdd67b110a8adbc4
|
| 3 |
+
size 319876032
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e2df7d962df4e50580d38c384c9f5830d70e0b87aebfd1ee3eca672bf2f43f95
|
| 3 |
+
size 639908666
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14244
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:58ae2ba232b823e0685960e3c048b41a588f00aea0d1bea73208b1f786b5c9f9
|
| 3 |
size 14244
|
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:f48d04a21be75a42496761f8a6d10bd6bbb09a3805770c41b54fa6f987df24ff
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,756 +1,407 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric":
|
| 3 |
-
"best_model_checkpoint":
|
| 4 |
-
"epoch": 0.
|
| 5 |
"eval_steps": 50,
|
| 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.
|
| 13 |
-
"grad_norm": 0.
|
| 14 |
-
"learning_rate":
|
| 15 |
-
"loss": 2.
|
| 16 |
"step": 1
|
| 17 |
},
|
| 18 |
{
|
| 19 |
-
"epoch": 0.
|
| 20 |
"eval_loss": 3.0125324726104736,
|
| 21 |
-
"eval_runtime": 4.
|
| 22 |
-
"eval_samples_per_second": 4.
|
| 23 |
-
"eval_steps_per_second": 4.
|
| 24 |
"step": 1
|
| 25 |
},
|
| 26 |
{
|
| 27 |
-
"epoch": 0.
|
| 28 |
-
"grad_norm": 0.
|
| 29 |
-
"learning_rate":
|
| 30 |
-
"loss": 2.
|
| 31 |
"step": 2
|
| 32 |
},
|
| 33 |
{
|
| 34 |
-
"epoch": 0.
|
| 35 |
-
"grad_norm": 0.
|
| 36 |
-
"learning_rate":
|
| 37 |
-
"loss":
|
| 38 |
"step": 3
|
| 39 |
},
|
| 40 |
{
|
| 41 |
-
"epoch": 0.
|
| 42 |
-
"grad_norm": 0.
|
| 43 |
-
"learning_rate":
|
| 44 |
-
"loss": 2.
|
| 45 |
"step": 4
|
| 46 |
},
|
| 47 |
{
|
| 48 |
-
"epoch": 0.
|
| 49 |
-
"grad_norm":
|
| 50 |
-
"learning_rate": 0.
|
| 51 |
-
"loss": 2.
|
| 52 |
"step": 5
|
| 53 |
},
|
| 54 |
{
|
| 55 |
-
"epoch": 0.
|
| 56 |
-
"grad_norm":
|
| 57 |
-
"learning_rate": 0.
|
| 58 |
-
"loss":
|
| 59 |
"step": 6
|
| 60 |
},
|
| 61 |
{
|
| 62 |
-
"epoch": 0.
|
| 63 |
-
"grad_norm":
|
| 64 |
-
"learning_rate": 0.
|
| 65 |
-
"loss": 2.
|
| 66 |
"step": 7
|
| 67 |
},
|
| 68 |
{
|
| 69 |
-
"epoch": 0.
|
| 70 |
-
"grad_norm": 0.
|
| 71 |
-
"learning_rate": 0.
|
| 72 |
-
"loss": 2.
|
| 73 |
"step": 8
|
| 74 |
},
|
| 75 |
{
|
| 76 |
-
"epoch": 0.
|
| 77 |
-
"grad_norm":
|
| 78 |
-
"learning_rate": 0.
|
| 79 |
-
"loss":
|
| 80 |
"step": 9
|
| 81 |
},
|
| 82 |
{
|
| 83 |
-
"epoch": 0.
|
| 84 |
-
"grad_norm":
|
| 85 |
-
"learning_rate": 0.
|
| 86 |
-
"loss": 2.
|
| 87 |
"step": 10
|
| 88 |
},
|
| 89 |
{
|
| 90 |
-
"epoch": 0.
|
| 91 |
-
"grad_norm":
|
| 92 |
-
"learning_rate": 0.
|
| 93 |
-
"loss": 2.
|
| 94 |
"step": 11
|
| 95 |
},
|
| 96 |
{
|
| 97 |
-
"epoch": 0.
|
| 98 |
-
"grad_norm": 0.
|
| 99 |
-
"learning_rate": 0.
|
| 100 |
-
"loss": 2.
|
| 101 |
"step": 12
|
| 102 |
},
|
| 103 |
{
|
| 104 |
-
"epoch": 0.
|
| 105 |
-
"grad_norm":
|
| 106 |
-
"learning_rate": 0.
|
| 107 |
-
"loss": 2.
|
| 108 |
"step": 13
|
| 109 |
},
|
| 110 |
{
|
| 111 |
-
"epoch": 0.
|
| 112 |
-
"grad_norm":
|
| 113 |
-
"learning_rate": 0.
|
| 114 |
-
"loss": 2.
|
| 115 |
"step": 14
|
| 116 |
},
|
| 117 |
{
|
| 118 |
-
"epoch": 0.
|
| 119 |
-
"grad_norm":
|
| 120 |
-
"learning_rate": 0.
|
| 121 |
-
"loss": 2.
|
| 122 |
"step": 15
|
| 123 |
},
|
| 124 |
{
|
| 125 |
-
"epoch": 0.
|
| 126 |
-
"grad_norm":
|
| 127 |
-
"learning_rate": 0.
|
| 128 |
-
"loss": 2.
|
| 129 |
"step": 16
|
| 130 |
},
|
| 131 |
{
|
| 132 |
-
"epoch": 0.
|
| 133 |
-
"grad_norm":
|
| 134 |
-
"learning_rate": 0.
|
| 135 |
-
"loss": 2.
|
| 136 |
"step": 17
|
| 137 |
},
|
| 138 |
{
|
| 139 |
-
"epoch": 0.
|
| 140 |
-
"grad_norm":
|
| 141 |
-
"learning_rate": 0.
|
| 142 |
-
"loss": 2.
|
| 143 |
"step": 18
|
| 144 |
},
|
| 145 |
{
|
| 146 |
-
"epoch": 0.
|
| 147 |
-
"grad_norm":
|
| 148 |
-
"learning_rate": 0.
|
| 149 |
-
"loss": 2.
|
| 150 |
"step": 19
|
| 151 |
},
|
| 152 |
{
|
| 153 |
-
"epoch": 0.
|
| 154 |
-
"grad_norm":
|
| 155 |
-
"learning_rate": 0.
|
| 156 |
-
"loss": 2.
|
| 157 |
"step": 20
|
| 158 |
},
|
| 159 |
{
|
| 160 |
-
"epoch": 0.
|
| 161 |
-
"grad_norm":
|
| 162 |
-
"learning_rate": 0.
|
| 163 |
-
"loss":
|
| 164 |
"step": 21
|
| 165 |
},
|
| 166 |
{
|
| 167 |
-
"epoch": 0.
|
| 168 |
-
"grad_norm":
|
| 169 |
-
"learning_rate": 0.
|
| 170 |
-
"loss": 2.
|
| 171 |
"step": 22
|
| 172 |
},
|
| 173 |
{
|
| 174 |
-
"epoch": 0.
|
| 175 |
-
"grad_norm":
|
| 176 |
-
"learning_rate": 0.
|
| 177 |
-
"loss": 2.
|
| 178 |
"step": 23
|
| 179 |
},
|
| 180 |
{
|
| 181 |
-
"epoch": 0.
|
| 182 |
-
"grad_norm":
|
| 183 |
-
"learning_rate": 0.
|
| 184 |
-
"loss": 2.
|
| 185 |
"step": 24
|
| 186 |
},
|
| 187 |
{
|
| 188 |
-
"epoch": 0.
|
| 189 |
-
"grad_norm":
|
| 190 |
-
"learning_rate": 0.
|
| 191 |
-
"loss": 2.
|
| 192 |
"step": 25
|
| 193 |
},
|
| 194 |
{
|
| 195 |
-
"epoch": 0.
|
| 196 |
-
"grad_norm":
|
| 197 |
-
"learning_rate": 0.
|
| 198 |
-
"loss": 2.
|
| 199 |
"step": 26
|
| 200 |
},
|
| 201 |
{
|
| 202 |
-
"epoch": 0.
|
| 203 |
-
"grad_norm":
|
| 204 |
-
"learning_rate": 0.
|
| 205 |
-
"loss": 2.
|
| 206 |
"step": 27
|
| 207 |
},
|
| 208 |
{
|
| 209 |
-
"epoch": 0.
|
| 210 |
-
"grad_norm":
|
| 211 |
-
"learning_rate": 0.
|
| 212 |
-
"loss": 2.
|
| 213 |
"step": 28
|
| 214 |
},
|
| 215 |
{
|
| 216 |
-
"epoch": 0.
|
| 217 |
-
"grad_norm":
|
| 218 |
-
"learning_rate": 0.
|
| 219 |
-
"loss": 2.
|
| 220 |
"step": 29
|
| 221 |
},
|
| 222 |
{
|
| 223 |
-
"epoch": 0.
|
| 224 |
-
"grad_norm":
|
| 225 |
-
"learning_rate": 0.
|
| 226 |
-
"loss": 2.
|
| 227 |
"step": 30
|
| 228 |
},
|
| 229 |
{
|
| 230 |
-
"epoch": 0.
|
| 231 |
-
"grad_norm": 0.
|
| 232 |
-
"learning_rate": 0.
|
| 233 |
-
"loss": 2.
|
| 234 |
"step": 31
|
| 235 |
},
|
| 236 |
{
|
| 237 |
-
"epoch": 0.
|
| 238 |
-
"grad_norm":
|
| 239 |
-
"learning_rate": 0.
|
| 240 |
-
"loss": 2.
|
| 241 |
"step": 32
|
| 242 |
},
|
| 243 |
{
|
| 244 |
-
"epoch": 0.
|
| 245 |
-
"grad_norm":
|
| 246 |
-
"learning_rate": 0.
|
| 247 |
-
"loss": 2.
|
| 248 |
"step": 33
|
| 249 |
},
|
| 250 |
{
|
| 251 |
-
"epoch": 0.
|
| 252 |
-
"grad_norm": 0.
|
| 253 |
-
"learning_rate": 0.
|
| 254 |
-
"loss": 2.
|
| 255 |
"step": 34
|
| 256 |
},
|
| 257 |
{
|
| 258 |
-
"epoch": 0.
|
| 259 |
-
"grad_norm":
|
| 260 |
-
"learning_rate": 0.
|
| 261 |
-
"loss": 2.
|
| 262 |
"step": 35
|
| 263 |
},
|
| 264 |
{
|
| 265 |
-
"epoch": 0.
|
| 266 |
-
"grad_norm":
|
| 267 |
-
"learning_rate": 0.
|
| 268 |
-
"loss": 2.
|
| 269 |
"step": 36
|
| 270 |
},
|
| 271 |
{
|
| 272 |
-
"epoch": 0.
|
| 273 |
-
"grad_norm": 0.
|
| 274 |
-
"learning_rate": 0.
|
| 275 |
-
"loss": 2.
|
| 276 |
"step": 37
|
| 277 |
},
|
| 278 |
{
|
| 279 |
-
"epoch": 0.
|
| 280 |
-
"grad_norm":
|
| 281 |
-
"learning_rate": 0.
|
| 282 |
-
"loss": 2.
|
| 283 |
"step": 38
|
| 284 |
},
|
| 285 |
{
|
| 286 |
-
"epoch": 0.
|
| 287 |
-
"grad_norm": 0.
|
| 288 |
-
"learning_rate": 0.
|
| 289 |
-
"loss": 2.
|
| 290 |
"step": 39
|
| 291 |
},
|
| 292 |
{
|
| 293 |
-
"epoch": 0.
|
| 294 |
-
"grad_norm": 0.
|
| 295 |
-
"learning_rate": 0.
|
| 296 |
-
"loss":
|
| 297 |
"step": 40
|
| 298 |
},
|
| 299 |
{
|
| 300 |
-
"epoch": 0.
|
| 301 |
-
"grad_norm": 0.
|
| 302 |
-
"learning_rate": 0.
|
| 303 |
-
"loss": 2.
|
| 304 |
"step": 41
|
| 305 |
},
|
| 306 |
{
|
| 307 |
-
"epoch": 0.
|
| 308 |
-
"grad_norm": 0.
|
| 309 |
-
"learning_rate": 0.
|
| 310 |
-
"loss": 2.
|
| 311 |
"step": 42
|
| 312 |
},
|
| 313 |
{
|
| 314 |
-
"epoch": 0.
|
| 315 |
-
"grad_norm": 0.
|
| 316 |
-
"learning_rate": 0.
|
| 317 |
-
"loss": 2.
|
| 318 |
"step": 43
|
| 319 |
},
|
| 320 |
{
|
| 321 |
-
"epoch": 0.
|
| 322 |
-
"grad_norm": 0.
|
| 323 |
-
"learning_rate": 0.
|
| 324 |
-
"loss": 2.
|
| 325 |
"step": 44
|
| 326 |
},
|
| 327 |
{
|
| 328 |
-
"epoch": 0.
|
| 329 |
-
"grad_norm": 0.
|
| 330 |
-
"learning_rate": 0.
|
| 331 |
-
"loss": 2.
|
| 332 |
"step": 45
|
| 333 |
},
|
| 334 |
{
|
| 335 |
-
"epoch": 0.
|
| 336 |
-
"grad_norm": 0.
|
| 337 |
-
"learning_rate": 0.
|
| 338 |
-
"loss": 2.
|
| 339 |
"step": 46
|
| 340 |
},
|
| 341 |
{
|
| 342 |
-
"epoch": 0.
|
| 343 |
-
"grad_norm": 0.
|
| 344 |
-
"learning_rate": 0.
|
| 345 |
-
"loss": 2.
|
| 346 |
"step": 47
|
| 347 |
},
|
| 348 |
{
|
| 349 |
-
"epoch": 0.
|
| 350 |
-
"grad_norm":
|
| 351 |
-
"learning_rate": 0.
|
| 352 |
-
"loss": 2.
|
| 353 |
"step": 48
|
| 354 |
},
|
| 355 |
{
|
| 356 |
-
"epoch": 0.
|
| 357 |
-
"grad_norm": 0.
|
| 358 |
-
"learning_rate": 0.
|
| 359 |
-
"loss": 2.
|
| 360 |
"step": 49
|
| 361 |
},
|
| 362 |
{
|
| 363 |
-
"epoch": 0.
|
| 364 |
-
"grad_norm":
|
| 365 |
-
"learning_rate": 0.
|
| 366 |
-
"loss": 2.
|
| 367 |
"step": 50
|
| 368 |
},
|
| 369 |
{
|
| 370 |
-
"epoch": 0.
|
| 371 |
-
"eval_loss": 2.
|
| 372 |
-
"eval_runtime": 4.
|
| 373 |
-
"eval_samples_per_second": 4.
|
| 374 |
-
"eval_steps_per_second": 4.
|
| 375 |
"step": 50
|
| 376 |
-
},
|
| 377 |
-
{
|
| 378 |
-
"epoch": 0.102,
|
| 379 |
-
"grad_norm": 0.6844251751899719,
|
| 380 |
-
"learning_rate": 0.0005695865504800327,
|
| 381 |
-
"loss": 2.4118,
|
| 382 |
-
"step": 51
|
| 383 |
-
},
|
| 384 |
-
{
|
| 385 |
-
"epoch": 0.104,
|
| 386 |
-
"grad_norm": 1.1709848642349243,
|
| 387 |
-
"learning_rate": 0.0005522642316338268,
|
| 388 |
-
"loss": 2.444,
|
| 389 |
-
"step": 52
|
| 390 |
-
},
|
| 391 |
-
{
|
| 392 |
-
"epoch": 0.106,
|
| 393 |
-
"grad_norm": 0.9435467720031738,
|
| 394 |
-
"learning_rate": 0.0005348782368720626,
|
| 395 |
-
"loss": 2.5568,
|
| 396 |
-
"step": 53
|
| 397 |
-
},
|
| 398 |
-
{
|
| 399 |
-
"epoch": 0.108,
|
| 400 |
-
"grad_norm": 1.0800719261169434,
|
| 401 |
-
"learning_rate": 0.0005174497483512506,
|
| 402 |
-
"loss": 2.5766,
|
| 403 |
-
"step": 54
|
| 404 |
-
},
|
| 405 |
-
{
|
| 406 |
-
"epoch": 0.11,
|
| 407 |
-
"grad_norm": 1.001356840133667,
|
| 408 |
-
"learning_rate": 0.0005,
|
| 409 |
-
"loss": 2.2205,
|
| 410 |
-
"step": 55
|
| 411 |
-
},
|
| 412 |
-
{
|
| 413 |
-
"epoch": 0.112,
|
| 414 |
-
"grad_norm": 1.4582829475402832,
|
| 415 |
-
"learning_rate": 0.0004825502516487497,
|
| 416 |
-
"loss": 2.7271,
|
| 417 |
-
"step": 56
|
| 418 |
-
},
|
| 419 |
-
{
|
| 420 |
-
"epoch": 0.114,
|
| 421 |
-
"grad_norm": 0.8312236666679382,
|
| 422 |
-
"learning_rate": 0.00046512176312793734,
|
| 423 |
-
"loss": 2.3204,
|
| 424 |
-
"step": 57
|
| 425 |
-
},
|
| 426 |
-
{
|
| 427 |
-
"epoch": 0.116,
|
| 428 |
-
"grad_norm": 1.2127161026000977,
|
| 429 |
-
"learning_rate": 0.00044773576836617336,
|
| 430 |
-
"loss": 2.0169,
|
| 431 |
-
"step": 58
|
| 432 |
-
},
|
| 433 |
-
{
|
| 434 |
-
"epoch": 0.118,
|
| 435 |
-
"grad_norm": 1.6428215503692627,
|
| 436 |
-
"learning_rate": 0.0004304134495199674,
|
| 437 |
-
"loss": 2.4521,
|
| 438 |
-
"step": 59
|
| 439 |
-
},
|
| 440 |
-
{
|
| 441 |
-
"epoch": 0.12,
|
| 442 |
-
"grad_norm": 1.7682443857192993,
|
| 443 |
-
"learning_rate": 0.00041317591116653486,
|
| 444 |
-
"loss": 2.6753,
|
| 445 |
-
"step": 60
|
| 446 |
-
},
|
| 447 |
-
{
|
| 448 |
-
"epoch": 0.122,
|
| 449 |
-
"grad_norm": 1.0919681787490845,
|
| 450 |
-
"learning_rate": 0.0003960441545911204,
|
| 451 |
-
"loss": 2.4022,
|
| 452 |
-
"step": 61
|
| 453 |
-
},
|
| 454 |
-
{
|
| 455 |
-
"epoch": 0.124,
|
| 456 |
-
"grad_norm": 2.5304136276245117,
|
| 457 |
-
"learning_rate": 0.0003790390522001662,
|
| 458 |
-
"loss": 2.4325,
|
| 459 |
-
"step": 62
|
| 460 |
-
},
|
| 461 |
-
{
|
| 462 |
-
"epoch": 0.126,
|
| 463 |
-
"grad_norm": 1.1737953424453735,
|
| 464 |
-
"learning_rate": 0.00036218132209150044,
|
| 465 |
-
"loss": 2.2653,
|
| 466 |
-
"step": 63
|
| 467 |
-
},
|
| 468 |
-
{
|
| 469 |
-
"epoch": 0.128,
|
| 470 |
-
"grad_norm": 0.7943472862243652,
|
| 471 |
-
"learning_rate": 0.00034549150281252633,
|
| 472 |
-
"loss": 2.6079,
|
| 473 |
-
"step": 64
|
| 474 |
-
},
|
| 475 |
-
{
|
| 476 |
-
"epoch": 0.13,
|
| 477 |
-
"grad_norm": 1.3269349336624146,
|
| 478 |
-
"learning_rate": 0.0003289899283371657,
|
| 479 |
-
"loss": 2.3745,
|
| 480 |
-
"step": 65
|
| 481 |
-
},
|
| 482 |
-
{
|
| 483 |
-
"epoch": 0.132,
|
| 484 |
-
"grad_norm": 0.8898394107818604,
|
| 485 |
-
"learning_rate": 0.00031269670329204396,
|
| 486 |
-
"loss": 2.3862,
|
| 487 |
-
"step": 66
|
| 488 |
-
},
|
| 489 |
-
{
|
| 490 |
-
"epoch": 0.134,
|
| 491 |
-
"grad_norm": 0.8309778571128845,
|
| 492 |
-
"learning_rate": 0.0002966316784621,
|
| 493 |
-
"loss": 2.5131,
|
| 494 |
-
"step": 67
|
| 495 |
-
},
|
| 496 |
-
{
|
| 497 |
-
"epoch": 0.136,
|
| 498 |
-
"grad_norm": 1.2103646993637085,
|
| 499 |
-
"learning_rate": 0.00028081442660546124,
|
| 500 |
-
"loss": 2.5138,
|
| 501 |
-
"step": 68
|
| 502 |
-
},
|
| 503 |
-
{
|
| 504 |
-
"epoch": 0.138,
|
| 505 |
-
"grad_norm": 0.9281813502311707,
|
| 506 |
-
"learning_rate": 0.00026526421860705474,
|
| 507 |
-
"loss": 2.5798,
|
| 508 |
-
"step": 69
|
| 509 |
-
},
|
| 510 |
-
{
|
| 511 |
-
"epoch": 0.14,
|
| 512 |
-
"grad_norm": 0.8275775909423828,
|
| 513 |
-
"learning_rate": 0.0002500000000000001,
|
| 514 |
-
"loss": 2.5348,
|
| 515 |
-
"step": 70
|
| 516 |
-
},
|
| 517 |
-
{
|
| 518 |
-
"epoch": 0.142,
|
| 519 |
-
"grad_norm": 1.5009329319000244,
|
| 520 |
-
"learning_rate": 0.0002350403678833976,
|
| 521 |
-
"loss": 2.5156,
|
| 522 |
-
"step": 71
|
| 523 |
-
},
|
| 524 |
-
{
|
| 525 |
-
"epoch": 0.144,
|
| 526 |
-
"grad_norm": 1.4796998500823975,
|
| 527 |
-
"learning_rate": 0.00022040354826462666,
|
| 528 |
-
"loss": 2.3567,
|
| 529 |
-
"step": 72
|
| 530 |
-
},
|
| 531 |
-
{
|
| 532 |
-
"epoch": 0.146,
|
| 533 |
-
"grad_norm": 0.7437081933021545,
|
| 534 |
-
"learning_rate": 0.00020610737385376348,
|
| 535 |
-
"loss": 2.4399,
|
| 536 |
-
"step": 73
|
| 537 |
-
},
|
| 538 |
-
{
|
| 539 |
-
"epoch": 0.148,
|
| 540 |
-
"grad_norm": 0.7033576369285583,
|
| 541 |
-
"learning_rate": 0.00019216926233717085,
|
| 542 |
-
"loss": 2.3149,
|
| 543 |
-
"step": 74
|
| 544 |
-
},
|
| 545 |
-
{
|
| 546 |
-
"epoch": 0.15,
|
| 547 |
-
"grad_norm": 0.9651651978492737,
|
| 548 |
-
"learning_rate": 0.0001786061951567303,
|
| 549 |
-
"loss": 2.5816,
|
| 550 |
-
"step": 75
|
| 551 |
-
},
|
| 552 |
-
{
|
| 553 |
-
"epoch": 0.152,
|
| 554 |
-
"grad_norm": 1.0059478282928467,
|
| 555 |
-
"learning_rate": 0.00016543469682057105,
|
| 556 |
-
"loss": 2.6395,
|
| 557 |
-
"step": 76
|
| 558 |
-
},
|
| 559 |
-
{
|
| 560 |
-
"epoch": 0.154,
|
| 561 |
-
"grad_norm": 1.6795697212219238,
|
| 562 |
-
"learning_rate": 0.00015267081477050133,
|
| 563 |
-
"loss": 2.3551,
|
| 564 |
-
"step": 77
|
| 565 |
-
},
|
| 566 |
-
{
|
| 567 |
-
"epoch": 0.156,
|
| 568 |
-
"grad_norm": 0.7962441444396973,
|
| 569 |
-
"learning_rate": 0.00014033009983067452,
|
| 570 |
-
"loss": 2.2151,
|
| 571 |
-
"step": 78
|
| 572 |
-
},
|
| 573 |
-
{
|
| 574 |
-
"epoch": 0.158,
|
| 575 |
-
"grad_norm": 0.880089282989502,
|
| 576 |
-
"learning_rate": 0.00012842758726130281,
|
| 577 |
-
"loss": 2.4376,
|
| 578 |
-
"step": 79
|
| 579 |
-
},
|
| 580 |
-
{
|
| 581 |
-
"epoch": 0.16,
|
| 582 |
-
"grad_norm": 1.0629572868347168,
|
| 583 |
-
"learning_rate": 0.00011697777844051105,
|
| 584 |
-
"loss": 2.6063,
|
| 585 |
-
"step": 80
|
| 586 |
-
},
|
| 587 |
-
{
|
| 588 |
-
"epoch": 0.162,
|
| 589 |
-
"grad_norm": 0.8691402077674866,
|
| 590 |
-
"learning_rate": 0.00010599462319663906,
|
| 591 |
-
"loss": 2.4764,
|
| 592 |
-
"step": 81
|
| 593 |
-
},
|
| 594 |
-
{
|
| 595 |
-
"epoch": 0.164,
|
| 596 |
-
"grad_norm": 0.8258126378059387,
|
| 597 |
-
"learning_rate": 9.549150281252633e-05,
|
| 598 |
-
"loss": 2.3996,
|
| 599 |
-
"step": 82
|
| 600 |
-
},
|
| 601 |
-
{
|
| 602 |
-
"epoch": 0.166,
|
| 603 |
-
"grad_norm": 2.253006935119629,
|
| 604 |
-
"learning_rate": 8.548121372247918e-05,
|
| 605 |
-
"loss": 2.7106,
|
| 606 |
-
"step": 83
|
| 607 |
-
},
|
| 608 |
-
{
|
| 609 |
-
"epoch": 0.168,
|
| 610 |
-
"grad_norm": 0.9351361393928528,
|
| 611 |
-
"learning_rate": 7.597595192178702e-05,
|
| 612 |
-
"loss": 2.3613,
|
| 613 |
-
"step": 84
|
| 614 |
-
},
|
| 615 |
-
{
|
| 616 |
-
"epoch": 0.17,
|
| 617 |
-
"grad_norm": 0.8624694347381592,
|
| 618 |
-
"learning_rate": 6.698729810778065e-05,
|
| 619 |
-
"loss": 2.4328,
|
| 620 |
-
"step": 85
|
| 621 |
-
},
|
| 622 |
-
{
|
| 623 |
-
"epoch": 0.172,
|
| 624 |
-
"grad_norm": 0.6949071884155273,
|
| 625 |
-
"learning_rate": 5.852620357053651e-05,
|
| 626 |
-
"loss": 2.4157,
|
| 627 |
-
"step": 86
|
| 628 |
-
},
|
| 629 |
-
{
|
| 630 |
-
"epoch": 0.174,
|
| 631 |
-
"grad_norm": 0.7830259203910828,
|
| 632 |
-
"learning_rate": 5.060297685041659e-05,
|
| 633 |
-
"loss": 2.2797,
|
| 634 |
-
"step": 87
|
| 635 |
-
},
|
| 636 |
-
{
|
| 637 |
-
"epoch": 0.176,
|
| 638 |
-
"grad_norm": 1.3727121353149414,
|
| 639 |
-
"learning_rate": 4.322727117869951e-05,
|
| 640 |
-
"loss": 2.6155,
|
| 641 |
-
"step": 88
|
| 642 |
-
},
|
| 643 |
-
{
|
| 644 |
-
"epoch": 0.178,
|
| 645 |
-
"grad_norm": 0.6731472611427307,
|
| 646 |
-
"learning_rate": 3.6408072716606344e-05,
|
| 647 |
-
"loss": 2.4149,
|
| 648 |
-
"step": 89
|
| 649 |
-
},
|
| 650 |
-
{
|
| 651 |
-
"epoch": 0.18,
|
| 652 |
-
"grad_norm": 0.846976101398468,
|
| 653 |
-
"learning_rate": 3.0153689607045842e-05,
|
| 654 |
-
"loss": 2.3137,
|
| 655 |
-
"step": 90
|
| 656 |
-
},
|
| 657 |
-
{
|
| 658 |
-
"epoch": 0.182,
|
| 659 |
-
"grad_norm": 0.9294453859329224,
|
| 660 |
-
"learning_rate": 2.4471741852423235e-05,
|
| 661 |
-
"loss": 2.5798,
|
| 662 |
-
"step": 91
|
| 663 |
-
},
|
| 664 |
-
{
|
| 665 |
-
"epoch": 0.184,
|
| 666 |
-
"grad_norm": 0.766918957233429,
|
| 667 |
-
"learning_rate": 1.9369152030840554e-05,
|
| 668 |
-
"loss": 2.6766,
|
| 669 |
-
"step": 92
|
| 670 |
-
},
|
| 671 |
-
{
|
| 672 |
-
"epoch": 0.186,
|
| 673 |
-
"grad_norm": 1.3079534769058228,
|
| 674 |
-
"learning_rate": 1.4852136862001764e-05,
|
| 675 |
-
"loss": 2.6047,
|
| 676 |
-
"step": 93
|
| 677 |
-
},
|
| 678 |
-
{
|
| 679 |
-
"epoch": 0.188,
|
| 680 |
-
"grad_norm": 1.1351994276046753,
|
| 681 |
-
"learning_rate": 1.0926199633097156e-05,
|
| 682 |
-
"loss": 2.6034,
|
| 683 |
-
"step": 94
|
| 684 |
-
},
|
| 685 |
-
{
|
| 686 |
-
"epoch": 0.19,
|
| 687 |
-
"grad_norm": 0.8010856509208679,
|
| 688 |
-
"learning_rate": 7.59612349389599e-06,
|
| 689 |
-
"loss": 2.2994,
|
| 690 |
-
"step": 95
|
| 691 |
-
},
|
| 692 |
-
{
|
| 693 |
-
"epoch": 0.192,
|
| 694 |
-
"grad_norm": 0.9184717535972595,
|
| 695 |
-
"learning_rate": 4.865965629214819e-06,
|
| 696 |
-
"loss": 2.5489,
|
| 697 |
-
"step": 96
|
| 698 |
-
},
|
| 699 |
-
{
|
| 700 |
-
"epoch": 0.194,
|
| 701 |
-
"grad_norm": 0.9543655514717102,
|
| 702 |
-
"learning_rate": 2.739052315863355e-06,
|
| 703 |
-
"loss": 2.5186,
|
| 704 |
-
"step": 97
|
| 705 |
-
},
|
| 706 |
-
{
|
| 707 |
-
"epoch": 0.196,
|
| 708 |
-
"grad_norm": 0.9216803908348083,
|
| 709 |
-
"learning_rate": 1.2179748700879012e-06,
|
| 710 |
-
"loss": 2.5627,
|
| 711 |
-
"step": 98
|
| 712 |
-
},
|
| 713 |
-
{
|
| 714 |
-
"epoch": 0.198,
|
| 715 |
-
"grad_norm": 0.8810911178588867,
|
| 716 |
-
"learning_rate": 3.0458649045211895e-07,
|
| 717 |
-
"loss": 2.6527,
|
| 718 |
-
"step": 99
|
| 719 |
-
},
|
| 720 |
-
{
|
| 721 |
-
"epoch": 0.2,
|
| 722 |
-
"grad_norm": 0.7426478266716003,
|
| 723 |
-
"learning_rate": 0.0,
|
| 724 |
-
"loss": 2.1737,
|
| 725 |
-
"step": 100
|
| 726 |
-
},
|
| 727 |
-
{
|
| 728 |
-
"epoch": 0.2,
|
| 729 |
-
"eval_loss": 2.527949094772339,
|
| 730 |
-
"eval_runtime": 4.9855,
|
| 731 |
-
"eval_samples_per_second": 4.212,
|
| 732 |
-
"eval_steps_per_second": 4.212,
|
| 733 |
-
"step": 100
|
| 734 |
}
|
| 735 |
],
|
| 736 |
"logging_steps": 1,
|
| 737 |
-
"max_steps":
|
| 738 |
"num_input_tokens_seen": 0,
|
| 739 |
-
"num_train_epochs":
|
| 740 |
-
"save_steps":
|
| 741 |
"stateful_callbacks": {
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 742 |
"TrainerControl": {
|
| 743 |
"args": {
|
| 744 |
"should_epoch_stop": false,
|
| 745 |
"should_evaluate": false,
|
| 746 |
"should_log": false,
|
| 747 |
"should_save": true,
|
| 748 |
-
"should_training_stop":
|
| 749 |
},
|
| 750 |
"attributes": {}
|
| 751 |
}
|
| 752 |
},
|
| 753 |
-
"total_flos":
|
| 754 |
"train_batch_size": 1,
|
| 755 |
"trial_name": null,
|
| 756 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 2.580864906311035,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-50",
|
| 4 |
+
"epoch": 0.05,
|
| 5 |
"eval_steps": 50,
|
| 6 |
+
"global_step": 50,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
+
"epoch": 0.001,
|
| 13 |
+
"grad_norm": 0.2811749279499054,
|
| 14 |
+
"learning_rate": 2e-05,
|
| 15 |
+
"loss": 2.6895,
|
| 16 |
"step": 1
|
| 17 |
},
|
| 18 |
{
|
| 19 |
+
"epoch": 0.001,
|
| 20 |
"eval_loss": 3.0125324726104736,
|
| 21 |
+
"eval_runtime": 4.6936,
|
| 22 |
+
"eval_samples_per_second": 4.474,
|
| 23 |
+
"eval_steps_per_second": 4.474,
|
| 24 |
"step": 1
|
| 25 |
},
|
| 26 |
{
|
| 27 |
+
"epoch": 0.002,
|
| 28 |
+
"grad_norm": 0.2987586557865143,
|
| 29 |
+
"learning_rate": 4e-05,
|
| 30 |
+
"loss": 2.8912,
|
| 31 |
"step": 2
|
| 32 |
},
|
| 33 |
{
|
| 34 |
+
"epoch": 0.003,
|
| 35 |
+
"grad_norm": 0.452608197927475,
|
| 36 |
+
"learning_rate": 6e-05,
|
| 37 |
+
"loss": 3.4357,
|
| 38 |
"step": 3
|
| 39 |
},
|
| 40 |
{
|
| 41 |
+
"epoch": 0.004,
|
| 42 |
+
"grad_norm": 0.38785919547080994,
|
| 43 |
+
"learning_rate": 8e-05,
|
| 44 |
+
"loss": 2.5889,
|
| 45 |
"step": 4
|
| 46 |
},
|
| 47 |
{
|
| 48 |
+
"epoch": 0.005,
|
| 49 |
+
"grad_norm": 0.38931822776794434,
|
| 50 |
+
"learning_rate": 0.0001,
|
| 51 |
+
"loss": 2.7513,
|
| 52 |
"step": 5
|
| 53 |
},
|
| 54 |
{
|
| 55 |
+
"epoch": 0.006,
|
| 56 |
+
"grad_norm": 0.516417384147644,
|
| 57 |
+
"learning_rate": 0.00012,
|
| 58 |
+
"loss": 3.2128,
|
| 59 |
"step": 6
|
| 60 |
},
|
| 61 |
{
|
| 62 |
+
"epoch": 0.007,
|
| 63 |
+
"grad_norm": 0.4206741750240326,
|
| 64 |
+
"learning_rate": 0.00014,
|
| 65 |
+
"loss": 2.9368,
|
| 66 |
"step": 7
|
| 67 |
},
|
| 68 |
{
|
| 69 |
+
"epoch": 0.008,
|
| 70 |
+
"grad_norm": 0.48171964287757874,
|
| 71 |
+
"learning_rate": 0.00016,
|
| 72 |
+
"loss": 2.8618,
|
| 73 |
"step": 8
|
| 74 |
},
|
| 75 |
{
|
| 76 |
+
"epoch": 0.009,
|
| 77 |
+
"grad_norm": 0.8544142842292786,
|
| 78 |
+
"learning_rate": 0.00018,
|
| 79 |
+
"loss": 3.0312,
|
| 80 |
"step": 9
|
| 81 |
},
|
| 82 |
{
|
| 83 |
+
"epoch": 0.01,
|
| 84 |
+
"grad_norm": 0.848558247089386,
|
| 85 |
+
"learning_rate": 0.0002,
|
| 86 |
+
"loss": 2.9334,
|
| 87 |
"step": 10
|
| 88 |
},
|
| 89 |
{
|
| 90 |
+
"epoch": 0.011,
|
| 91 |
+
"grad_norm": 0.8914313316345215,
|
| 92 |
+
"learning_rate": 0.00019999996900269505,
|
| 93 |
+
"loss": 2.7981,
|
| 94 |
"step": 11
|
| 95 |
},
|
| 96 |
{
|
| 97 |
+
"epoch": 0.012,
|
| 98 |
+
"grad_norm": 0.6103464365005493,
|
| 99 |
+
"learning_rate": 0.0001999998760107994,
|
| 100 |
+
"loss": 2.7247,
|
| 101 |
"step": 12
|
| 102 |
},
|
| 103 |
{
|
| 104 |
+
"epoch": 0.013,
|
| 105 |
+
"grad_norm": 0.7618600726127625,
|
| 106 |
+
"learning_rate": 0.00019999972102437074,
|
| 107 |
+
"loss": 2.472,
|
| 108 |
"step": 13
|
| 109 |
},
|
| 110 |
{
|
| 111 |
+
"epoch": 0.014,
|
| 112 |
+
"grad_norm": 0.6825264692306519,
|
| 113 |
+
"learning_rate": 0.00019999950404350512,
|
| 114 |
+
"loss": 2.6008,
|
| 115 |
"step": 14
|
| 116 |
},
|
| 117 |
{
|
| 118 |
+
"epoch": 0.015,
|
| 119 |
+
"grad_norm": 0.5940832495689392,
|
| 120 |
+
"learning_rate": 0.00019999922506833704,
|
| 121 |
+
"loss": 2.1996,
|
| 122 |
"step": 15
|
| 123 |
},
|
| 124 |
{
|
| 125 |
+
"epoch": 0.016,
|
| 126 |
+
"grad_norm": 0.6273623108863831,
|
| 127 |
+
"learning_rate": 0.00019999888409903948,
|
| 128 |
+
"loss": 2.3565,
|
| 129 |
"step": 16
|
| 130 |
},
|
| 131 |
{
|
| 132 |
+
"epoch": 0.017,
|
| 133 |
+
"grad_norm": 0.7437952160835266,
|
| 134 |
+
"learning_rate": 0.00019999848113582384,
|
| 135 |
+
"loss": 2.7232,
|
| 136 |
"step": 17
|
| 137 |
},
|
| 138 |
{
|
| 139 |
+
"epoch": 0.018,
|
| 140 |
+
"grad_norm": 0.5971533060073853,
|
| 141 |
+
"learning_rate": 0.0001999980161789399,
|
| 142 |
+
"loss": 2.509,
|
| 143 |
"step": 18
|
| 144 |
},
|
| 145 |
{
|
| 146 |
+
"epoch": 0.019,
|
| 147 |
+
"grad_norm": 0.5190719962120056,
|
| 148 |
+
"learning_rate": 0.00019999748922867592,
|
| 149 |
+
"loss": 2.3535,
|
| 150 |
"step": 19
|
| 151 |
},
|
| 152 |
{
|
| 153 |
+
"epoch": 0.02,
|
| 154 |
+
"grad_norm": 0.9244285821914673,
|
| 155 |
+
"learning_rate": 0.00019999690028535855,
|
| 156 |
+
"loss": 2.7599,
|
| 157 |
"step": 20
|
| 158 |
},
|
| 159 |
{
|
| 160 |
+
"epoch": 0.021,
|
| 161 |
+
"grad_norm": 0.8340674638748169,
|
| 162 |
+
"learning_rate": 0.00019999624934935296,
|
| 163 |
+
"loss": 3.0057,
|
| 164 |
"step": 21
|
| 165 |
},
|
| 166 |
{
|
| 167 |
+
"epoch": 0.022,
|
| 168 |
+
"grad_norm": 1.0633089542388916,
|
| 169 |
+
"learning_rate": 0.00019999553642106266,
|
| 170 |
+
"loss": 2.2808,
|
| 171 |
"step": 22
|
| 172 |
},
|
| 173 |
{
|
| 174 |
+
"epoch": 0.023,
|
| 175 |
+
"grad_norm": 4.8767266273498535,
|
| 176 |
+
"learning_rate": 0.00019999476150092967,
|
| 177 |
+
"loss": 2.8268,
|
| 178 |
"step": 23
|
| 179 |
},
|
| 180 |
{
|
| 181 |
+
"epoch": 0.024,
|
| 182 |
+
"grad_norm": 2.7197344303131104,
|
| 183 |
+
"learning_rate": 0.00019999392458943432,
|
| 184 |
+
"loss": 2.6517,
|
| 185 |
"step": 24
|
| 186 |
},
|
| 187 |
{
|
| 188 |
+
"epoch": 0.025,
|
| 189 |
+
"grad_norm": 0.9329593777656555,
|
| 190 |
+
"learning_rate": 0.00019999302568709547,
|
| 191 |
+
"loss": 2.212,
|
| 192 |
"step": 25
|
| 193 |
},
|
| 194 |
{
|
| 195 |
+
"epoch": 0.026,
|
| 196 |
+
"grad_norm": 0.6679103374481201,
|
| 197 |
+
"learning_rate": 0.00019999206479447045,
|
| 198 |
+
"loss": 2.0117,
|
| 199 |
"step": 26
|
| 200 |
},
|
| 201 |
{
|
| 202 |
+
"epoch": 0.027,
|
| 203 |
+
"grad_norm": 0.5428286790847778,
|
| 204 |
+
"learning_rate": 0.00019999104191215493,
|
| 205 |
+
"loss": 2.7582,
|
| 206 |
"step": 27
|
| 207 |
},
|
| 208 |
{
|
| 209 |
+
"epoch": 0.028,
|
| 210 |
+
"grad_norm": 0.5552177429199219,
|
| 211 |
+
"learning_rate": 0.00019998995704078305,
|
| 212 |
+
"loss": 2.54,
|
| 213 |
"step": 28
|
| 214 |
},
|
| 215 |
{
|
| 216 |
+
"epoch": 0.029,
|
| 217 |
+
"grad_norm": 0.5453671216964722,
|
| 218 |
+
"learning_rate": 0.00019998881018102737,
|
| 219 |
+
"loss": 2.5358,
|
| 220 |
"step": 29
|
| 221 |
},
|
| 222 |
{
|
| 223 |
+
"epoch": 0.03,
|
| 224 |
+
"grad_norm": 0.47653189301490784,
|
| 225 |
+
"learning_rate": 0.00019998760133359885,
|
| 226 |
+
"loss": 2.2443,
|
| 227 |
"step": 30
|
| 228 |
},
|
| 229 |
{
|
| 230 |
+
"epoch": 0.031,
|
| 231 |
+
"grad_norm": 0.755976140499115,
|
| 232 |
+
"learning_rate": 0.0001999863304992469,
|
| 233 |
+
"loss": 2.5519,
|
| 234 |
"step": 31
|
| 235 |
},
|
| 236 |
{
|
| 237 |
+
"epoch": 0.032,
|
| 238 |
+
"grad_norm": 0.7680912017822266,
|
| 239 |
+
"learning_rate": 0.00019998499767875943,
|
| 240 |
+
"loss": 2.7503,
|
| 241 |
"step": 32
|
| 242 |
},
|
| 243 |
{
|
| 244 |
+
"epoch": 0.033,
|
| 245 |
+
"grad_norm": 3.768080472946167,
|
| 246 |
+
"learning_rate": 0.0001999836028729627,
|
| 247 |
+
"loss": 2.6051,
|
| 248 |
"step": 33
|
| 249 |
},
|
| 250 |
{
|
| 251 |
+
"epoch": 0.034,
|
| 252 |
+
"grad_norm": 0.5304062962532043,
|
| 253 |
+
"learning_rate": 0.00019998214608272136,
|
| 254 |
+
"loss": 2.2065,
|
| 255 |
"step": 34
|
| 256 |
},
|
| 257 |
{
|
| 258 |
+
"epoch": 0.035,
|
| 259 |
+
"grad_norm": 1.1568998098373413,
|
| 260 |
+
"learning_rate": 0.00019998062730893862,
|
| 261 |
+
"loss": 2.444,
|
| 262 |
"step": 35
|
| 263 |
},
|
| 264 |
{
|
| 265 |
+
"epoch": 0.036,
|
| 266 |
+
"grad_norm": 0.8356309533119202,
|
| 267 |
+
"learning_rate": 0.000199979046552556,
|
| 268 |
+
"loss": 2.5763,
|
| 269 |
"step": 36
|
| 270 |
},
|
| 271 |
{
|
| 272 |
+
"epoch": 0.037,
|
| 273 |
+
"grad_norm": 0.5210471749305725,
|
| 274 |
+
"learning_rate": 0.00019997740381455346,
|
| 275 |
+
"loss": 2.8545,
|
| 276 |
"step": 37
|
| 277 |
},
|
| 278 |
{
|
| 279 |
+
"epoch": 0.038,
|
| 280 |
+
"grad_norm": 1.550714373588562,
|
| 281 |
+
"learning_rate": 0.00019997569909594947,
|
| 282 |
+
"loss": 2.6236,
|
| 283 |
"step": 38
|
| 284 |
},
|
| 285 |
{
|
| 286 |
+
"epoch": 0.039,
|
| 287 |
+
"grad_norm": 0.6044741868972778,
|
| 288 |
+
"learning_rate": 0.0001999739323978008,
|
| 289 |
+
"loss": 2.5349,
|
| 290 |
"step": 39
|
| 291 |
},
|
| 292 |
{
|
| 293 |
+
"epoch": 0.04,
|
| 294 |
+
"grad_norm": 0.9703565239906311,
|
| 295 |
+
"learning_rate": 0.00019997210372120274,
|
| 296 |
+
"loss": 3.1004,
|
| 297 |
"step": 40
|
| 298 |
},
|
| 299 |
{
|
| 300 |
+
"epoch": 0.041,
|
| 301 |
+
"grad_norm": 0.7796650528907776,
|
| 302 |
+
"learning_rate": 0.000199970213067289,
|
| 303 |
+
"loss": 2.5757,
|
| 304 |
"step": 41
|
| 305 |
},
|
| 306 |
{
|
| 307 |
+
"epoch": 0.042,
|
| 308 |
+
"grad_norm": 0.6824871301651001,
|
| 309 |
+
"learning_rate": 0.00019996826043723162,
|
| 310 |
+
"loss": 2.6766,
|
| 311 |
"step": 42
|
| 312 |
},
|
| 313 |
{
|
| 314 |
+
"epoch": 0.043,
|
| 315 |
+
"grad_norm": 0.8048773407936096,
|
| 316 |
+
"learning_rate": 0.00019996624583224114,
|
| 317 |
+
"loss": 2.3065,
|
| 318 |
"step": 43
|
| 319 |
},
|
| 320 |
{
|
| 321 |
+
"epoch": 0.044,
|
| 322 |
+
"grad_norm": 0.5458154082298279,
|
| 323 |
+
"learning_rate": 0.00019996416925356652,
|
| 324 |
+
"loss": 2.4336,
|
| 325 |
"step": 44
|
| 326 |
},
|
| 327 |
{
|
| 328 |
+
"epoch": 0.045,
|
| 329 |
+
"grad_norm": 0.623190701007843,
|
| 330 |
+
"learning_rate": 0.00019996203070249516,
|
| 331 |
+
"loss": 2.3835,
|
| 332 |
"step": 45
|
| 333 |
},
|
| 334 |
{
|
| 335 |
+
"epoch": 0.046,
|
| 336 |
+
"grad_norm": 0.5928781032562256,
|
| 337 |
+
"learning_rate": 0.00019995983018035278,
|
| 338 |
+
"loss": 2.3408,
|
| 339 |
"step": 46
|
| 340 |
},
|
| 341 |
{
|
| 342 |
+
"epoch": 0.047,
|
| 343 |
+
"grad_norm": 0.5790976881980896,
|
| 344 |
+
"learning_rate": 0.00019995756768850364,
|
| 345 |
+
"loss": 2.3878,
|
| 346 |
"step": 47
|
| 347 |
},
|
| 348 |
{
|
| 349 |
+
"epoch": 0.048,
|
| 350 |
+
"grad_norm": 0.5648425817489624,
|
| 351 |
+
"learning_rate": 0.00019995524322835034,
|
| 352 |
+
"loss": 2.2885,
|
| 353 |
"step": 48
|
| 354 |
},
|
| 355 |
{
|
| 356 |
+
"epoch": 0.049,
|
| 357 |
+
"grad_norm": 0.526339054107666,
|
| 358 |
+
"learning_rate": 0.00019995285680133394,
|
| 359 |
+
"loss": 2.408,
|
| 360 |
"step": 49
|
| 361 |
},
|
| 362 |
{
|
| 363 |
+
"epoch": 0.05,
|
| 364 |
+
"grad_norm": 0.6333803534507751,
|
| 365 |
+
"learning_rate": 0.00019995040840893388,
|
| 366 |
+
"loss": 2.4391,
|
| 367 |
"step": 50
|
| 368 |
},
|
| 369 |
{
|
| 370 |
+
"epoch": 0.05,
|
| 371 |
+
"eval_loss": 2.580864906311035,
|
| 372 |
+
"eval_runtime": 4.8038,
|
| 373 |
+
"eval_samples_per_second": 4.372,
|
| 374 |
+
"eval_steps_per_second": 4.372,
|
| 375 |
"step": 50
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 376 |
}
|
| 377 |
],
|
| 378 |
"logging_steps": 1,
|
| 379 |
+
"max_steps": 4000,
|
| 380 |
"num_input_tokens_seen": 0,
|
| 381 |
+
"num_train_epochs": 4,
|
| 382 |
+
"save_steps": 50,
|
| 383 |
"stateful_callbacks": {
|
| 384 |
+
"EarlyStoppingCallback": {
|
| 385 |
+
"args": {
|
| 386 |
+
"early_stopping_patience": 2,
|
| 387 |
+
"early_stopping_threshold": 0.0
|
| 388 |
+
},
|
| 389 |
+
"attributes": {
|
| 390 |
+
"early_stopping_patience_counter": 0
|
| 391 |
+
}
|
| 392 |
+
},
|
| 393 |
"TrainerControl": {
|
| 394 |
"args": {
|
| 395 |
"should_epoch_stop": false,
|
| 396 |
"should_evaluate": false,
|
| 397 |
"should_log": false,
|
| 398 |
"should_save": true,
|
| 399 |
+
"should_training_stop": false
|
| 400 |
},
|
| 401 |
"attributes": {}
|
| 402 |
}
|
| 403 |
},
|
| 404 |
+
"total_flos": 4108715871436800.0,
|
| 405 |
"train_batch_size": 1,
|
| 406 |
"trial_name": null,
|
| 407 |
"trial_params": null
|
last-checkpoint/training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 6776
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:587385ca4b3a6c2778a0b2f3cca66b2116c2d78e99e16d5766eaff5ef6eeb893
|
| 3 |
size 6776
|