Training in progress, step 50, checkpoint
Browse files- last-checkpoint/README.md +1 -1
- last-checkpoint/adapter_config.json +4 -4
- last-checkpoint/adapter_model.safetensors +2 -2
- last-checkpoint/optimizer.pt +2 -2
- last-checkpoint/rng_state.pth +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +222 -954
- last-checkpoint/training_args.bin +1 -1
last-checkpoint/README.md
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
---
|
| 2 |
-
base_model: unsloth/Llama-3.2-
|
| 3 |
library_name: peft
|
| 4 |
---
|
| 5 |
|
|
|
|
| 1 |
---
|
| 2 |
+
base_model: unsloth/Llama-3.2-3B-Instruct
|
| 3 |
library_name: peft
|
| 4 |
---
|
| 5 |
|
last-checkpoint/adapter_config.json
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
{
|
| 2 |
"alpha_pattern": {},
|
| 3 |
"auto_mapping": null,
|
| 4 |
-
"base_model_name_or_path": "unsloth/Llama-3.2-
|
| 5 |
"bias": "none",
|
| 6 |
"fan_in_fan_out": null,
|
| 7 |
"inference_mode": true,
|
|
@@ -20,12 +20,12 @@
|
|
| 20 |
"rank_pattern": {},
|
| 21 |
"revision": null,
|
| 22 |
"target_modules": [
|
| 23 |
-
"q_proj",
|
| 24 |
-
"v_proj",
|
| 25 |
-
"gate_proj",
|
| 26 |
"k_proj",
|
|
|
|
| 27 |
"up_proj",
|
| 28 |
"o_proj",
|
|
|
|
|
|
|
| 29 |
"down_proj"
|
| 30 |
],
|
| 31 |
"task_type": "CAUSAL_LM",
|
|
|
|
| 1 |
{
|
| 2 |
"alpha_pattern": {},
|
| 3 |
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "unsloth/Llama-3.2-3B-Instruct",
|
| 5 |
"bias": "none",
|
| 6 |
"fan_in_fan_out": null,
|
| 7 |
"inference_mode": true,
|
|
|
|
| 20 |
"rank_pattern": {},
|
| 21 |
"revision": null,
|
| 22 |
"target_modules": [
|
|
|
|
|
|
|
|
|
|
| 23 |
"k_proj",
|
| 24 |
+
"gate_proj",
|
| 25 |
"up_proj",
|
| 26 |
"o_proj",
|
| 27 |
+
"v_proj",
|
| 28 |
+
"q_proj",
|
| 29 |
"down_proj"
|
| 30 |
],
|
| 31 |
"task_type": "CAUSAL_LM",
|
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:ef850e00f6ddccf7a92baced38593af32bacbc7deb92d8d8407aa4aa0408de1a
|
| 3 |
+
size 97307544
|
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:c1bc63593d20de9621903470fe84da0c3845eac9f62fcf47fa7fc53c31b55e0a
|
| 3 |
+
size 194840426
|
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 sha256:9985d87c9fe1230092403fc0c5f05d287ced3986c4900ee14ddc69775bac2f24
|
| 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 sha256:6a3057cc3055b088ac745445a3a938968f2d198c20a2487c1a93787006959980
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,1122 +1,390 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 2.
|
| 3 |
-
"best_model_checkpoint": "miner_id_24/checkpoint-
|
| 4 |
-
"epoch": 0.
|
| 5 |
"eval_steps": 25,
|
| 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":
|
| 14 |
-
"learning_rate":
|
| 15 |
-
"loss": 3.
|
| 16 |
"step": 1
|
| 17 |
},
|
| 18 |
{
|
| 19 |
-
"epoch": 0.
|
| 20 |
-
"eval_loss": 3.
|
| 21 |
-
"eval_runtime":
|
| 22 |
-
"eval_samples_per_second":
|
| 23 |
-
"eval_steps_per_second":
|
| 24 |
"step": 1
|
| 25 |
},
|
| 26 |
{
|
| 27 |
-
"epoch": 0.
|
| 28 |
-
"grad_norm": 0.
|
| 29 |
-
"learning_rate":
|
| 30 |
-
"loss": 3.
|
| 31 |
"step": 2
|
| 32 |
},
|
| 33 |
{
|
| 34 |
-
"epoch": 0.
|
| 35 |
-
"grad_norm":
|
| 36 |
-
"learning_rate":
|
| 37 |
-
"loss": 3.
|
| 38 |
"step": 3
|
| 39 |
},
|
| 40 |
{
|
| 41 |
-
"epoch": 0.
|
| 42 |
-
"grad_norm":
|
| 43 |
-
"learning_rate":
|
| 44 |
-
"loss": 3.
|
| 45 |
"step": 4
|
| 46 |
},
|
| 47 |
{
|
| 48 |
-
"epoch": 0.
|
| 49 |
-
"grad_norm":
|
| 50 |
-
"learning_rate":
|
| 51 |
-
"loss": 3.
|
| 52 |
"step": 5
|
| 53 |
},
|
| 54 |
{
|
| 55 |
-
"epoch": 0.
|
| 56 |
-
"grad_norm": 0.
|
| 57 |
-
"learning_rate":
|
| 58 |
-
"loss": 3.
|
| 59 |
"step": 6
|
| 60 |
},
|
| 61 |
{
|
| 62 |
-
"epoch": 0.
|
| 63 |
-
"grad_norm":
|
| 64 |
-
"learning_rate":
|
| 65 |
-
"loss": 3.
|
| 66 |
"step": 7
|
| 67 |
},
|
| 68 |
{
|
| 69 |
-
"epoch": 0.
|
| 70 |
-
"grad_norm":
|
| 71 |
-
"learning_rate":
|
| 72 |
-
"loss": 3.
|
| 73 |
"step": 8
|
| 74 |
},
|
| 75 |
{
|
| 76 |
-
"epoch": 0.
|
| 77 |
-
"grad_norm":
|
| 78 |
-
"learning_rate":
|
| 79 |
-
"loss":
|
| 80 |
"step": 9
|
| 81 |
},
|
| 82 |
{
|
| 83 |
-
"epoch": 0.
|
| 84 |
-
"grad_norm":
|
| 85 |
-
"learning_rate":
|
| 86 |
-
"loss": 3.
|
| 87 |
"step": 10
|
| 88 |
},
|
| 89 |
{
|
| 90 |
-
"epoch": 0.
|
| 91 |
-
"grad_norm":
|
| 92 |
-
"learning_rate":
|
| 93 |
-
"loss": 3.
|
| 94 |
"step": 11
|
| 95 |
},
|
| 96 |
{
|
| 97 |
-
"epoch": 0.
|
| 98 |
-
"grad_norm":
|
| 99 |
-
"learning_rate":
|
| 100 |
-
"loss":
|
| 101 |
"step": 12
|
| 102 |
},
|
| 103 |
{
|
| 104 |
-
"epoch": 0.
|
| 105 |
-
"grad_norm":
|
| 106 |
-
"learning_rate":
|
| 107 |
-
"loss": 3.
|
| 108 |
"step": 13
|
| 109 |
},
|
| 110 |
{
|
| 111 |
-
"epoch": 0.
|
| 112 |
-
"grad_norm":
|
| 113 |
-
"learning_rate":
|
| 114 |
-
"loss":
|
| 115 |
"step": 14
|
| 116 |
},
|
| 117 |
{
|
| 118 |
-
"epoch": 0.
|
| 119 |
-
"grad_norm": 0.
|
| 120 |
-
"learning_rate":
|
| 121 |
-
"loss":
|
| 122 |
"step": 15
|
| 123 |
},
|
| 124 |
{
|
| 125 |
-
"epoch": 0.
|
| 126 |
-
"grad_norm": 0.
|
| 127 |
-
"learning_rate":
|
| 128 |
-
"loss":
|
| 129 |
"step": 16
|
| 130 |
},
|
| 131 |
{
|
| 132 |
-
"epoch": 0.
|
| 133 |
-
"grad_norm": 0.
|
| 134 |
-
"learning_rate":
|
| 135 |
-
"loss":
|
| 136 |
"step": 17
|
| 137 |
},
|
| 138 |
{
|
| 139 |
-
"epoch": 0.
|
| 140 |
-
"grad_norm": 0.
|
| 141 |
-
"learning_rate":
|
| 142 |
-
"loss":
|
| 143 |
"step": 18
|
| 144 |
},
|
| 145 |
{
|
| 146 |
-
"epoch": 0.
|
| 147 |
-
"grad_norm": 0.
|
| 148 |
-
"learning_rate":
|
| 149 |
-
"loss":
|
| 150 |
"step": 19
|
| 151 |
},
|
| 152 |
{
|
| 153 |
-
"epoch": 0.
|
| 154 |
-
"grad_norm": 0.
|
| 155 |
-
"learning_rate":
|
| 156 |
-
"loss":
|
| 157 |
"step": 20
|
| 158 |
},
|
| 159 |
{
|
| 160 |
-
"epoch": 0.
|
| 161 |
-
"grad_norm": 0.
|
| 162 |
-
"learning_rate":
|
| 163 |
-
"loss":
|
| 164 |
"step": 21
|
| 165 |
},
|
| 166 |
{
|
| 167 |
-
"epoch": 0.
|
| 168 |
-
"grad_norm": 0.
|
| 169 |
-
"learning_rate":
|
| 170 |
-
"loss": 2.
|
| 171 |
"step": 22
|
| 172 |
},
|
| 173 |
{
|
| 174 |
-
"epoch": 0.
|
| 175 |
-
"grad_norm": 0.
|
| 176 |
-
"learning_rate":
|
| 177 |
-
"loss": 2.
|
| 178 |
"step": 23
|
| 179 |
},
|
| 180 |
{
|
| 181 |
-
"epoch": 0.
|
| 182 |
-
"grad_norm": 0.
|
| 183 |
-
"learning_rate":
|
| 184 |
-
"loss":
|
| 185 |
"step": 24
|
| 186 |
},
|
| 187 |
{
|
| 188 |
-
"epoch": 0.
|
| 189 |
-
"grad_norm": 0.
|
| 190 |
-
"learning_rate":
|
| 191 |
-
"loss": 2.
|
| 192 |
"step": 25
|
| 193 |
},
|
| 194 |
{
|
| 195 |
-
"epoch": 0.
|
| 196 |
-
"eval_loss":
|
| 197 |
-
"eval_runtime":
|
| 198 |
-
"eval_samples_per_second":
|
| 199 |
-
"eval_steps_per_second":
|
| 200 |
"step": 25
|
| 201 |
},
|
| 202 |
{
|
| 203 |
-
"epoch": 0.
|
| 204 |
-
"grad_norm": 0.
|
| 205 |
-
"learning_rate":
|
| 206 |
-
"loss": 2.
|
| 207 |
"step": 26
|
| 208 |
},
|
| 209 |
{
|
| 210 |
-
"epoch": 0.
|
| 211 |
-
"grad_norm": 0.
|
| 212 |
-
"learning_rate":
|
| 213 |
-
"loss": 2.
|
| 214 |
"step": 27
|
| 215 |
},
|
| 216 |
{
|
| 217 |
-
"epoch": 0.
|
| 218 |
-
"grad_norm": 0.
|
| 219 |
-
"learning_rate":
|
| 220 |
-
"loss":
|
| 221 |
"step": 28
|
| 222 |
},
|
| 223 |
{
|
| 224 |
-
"epoch": 0.
|
| 225 |
-
"grad_norm": 0.
|
| 226 |
-
"learning_rate":
|
| 227 |
-
"loss": 2.
|
| 228 |
"step": 29
|
| 229 |
},
|
| 230 |
{
|
| 231 |
-
"epoch": 0.
|
| 232 |
-
"grad_norm": 0.
|
| 233 |
-
"learning_rate":
|
| 234 |
-
"loss": 2.
|
| 235 |
"step": 30
|
| 236 |
},
|
| 237 |
{
|
| 238 |
-
"epoch": 0.
|
| 239 |
-
"grad_norm": 0.
|
| 240 |
-
"learning_rate":
|
| 241 |
-
"loss": 2.
|
| 242 |
"step": 31
|
| 243 |
},
|
| 244 |
{
|
| 245 |
-
"epoch": 0.
|
| 246 |
-
"grad_norm": 0.
|
| 247 |
-
"learning_rate":
|
| 248 |
-
"loss": 2.
|
| 249 |
"step": 32
|
| 250 |
},
|
| 251 |
{
|
| 252 |
-
"epoch": 0.
|
| 253 |
-
"grad_norm": 0.
|
| 254 |
-
"learning_rate":
|
| 255 |
-
"loss": 2.
|
| 256 |
"step": 33
|
| 257 |
},
|
| 258 |
{
|
| 259 |
-
"epoch": 0.
|
| 260 |
-
"grad_norm": 0.
|
| 261 |
-
"learning_rate":
|
| 262 |
-
"loss": 2.
|
| 263 |
"step": 34
|
| 264 |
},
|
| 265 |
{
|
| 266 |
-
"epoch": 0.
|
| 267 |
-
"grad_norm": 0.
|
| 268 |
-
"learning_rate": 0.
|
| 269 |
-
"loss": 2.
|
| 270 |
"step": 35
|
| 271 |
},
|
| 272 |
{
|
| 273 |
-
"epoch": 0.
|
| 274 |
-
"grad_norm": 0.
|
| 275 |
-
"learning_rate": 0.
|
| 276 |
-
"loss": 2.
|
| 277 |
"step": 36
|
| 278 |
},
|
| 279 |
{
|
| 280 |
-
"epoch": 0.
|
| 281 |
-
"grad_norm": 0.
|
| 282 |
-
"learning_rate": 0.
|
| 283 |
-
"loss": 2.
|
| 284 |
"step": 37
|
| 285 |
},
|
| 286 |
{
|
| 287 |
-
"epoch": 0.
|
| 288 |
-
"grad_norm": 0.
|
| 289 |
-
"learning_rate": 0.
|
| 290 |
-
"loss": 2.
|
| 291 |
"step": 38
|
| 292 |
},
|
| 293 |
{
|
| 294 |
-
"epoch": 0.
|
| 295 |
-
"grad_norm": 0.
|
| 296 |
-
"learning_rate": 0.
|
| 297 |
-
"loss": 2.
|
| 298 |
"step": 39
|
| 299 |
},
|
| 300 |
{
|
| 301 |
-
"epoch": 0.
|
| 302 |
-
"grad_norm": 0.
|
| 303 |
-
"learning_rate": 0.
|
| 304 |
-
"loss": 2.
|
| 305 |
"step": 40
|
| 306 |
},
|
| 307 |
{
|
| 308 |
-
"epoch": 0.
|
| 309 |
-
"grad_norm":
|
| 310 |
-
"learning_rate": 0.
|
| 311 |
-
"loss": 2.
|
| 312 |
"step": 41
|
| 313 |
},
|
| 314 |
{
|
| 315 |
-
"epoch": 0.
|
| 316 |
-
"grad_norm": 0.
|
| 317 |
-
"learning_rate": 0.
|
| 318 |
-
"loss": 2.
|
| 319 |
"step": 42
|
| 320 |
},
|
| 321 |
{
|
| 322 |
-
"epoch": 0.
|
| 323 |
-
"grad_norm":
|
| 324 |
-
"learning_rate": 0.
|
| 325 |
-
"loss": 2.
|
| 326 |
"step": 43
|
| 327 |
},
|
| 328 |
{
|
| 329 |
-
"epoch": 0.
|
| 330 |
-
"grad_norm": 0.
|
| 331 |
-
"learning_rate": 0.
|
| 332 |
-
"loss": 2.
|
| 333 |
"step": 44
|
| 334 |
},
|
| 335 |
{
|
| 336 |
-
"epoch": 0.
|
| 337 |
-
"grad_norm": 0.
|
| 338 |
-
"learning_rate": 0.
|
| 339 |
-
"loss":
|
| 340 |
"step": 45
|
| 341 |
},
|
| 342 |
{
|
| 343 |
-
"epoch": 0.
|
| 344 |
-
"grad_norm": 0.
|
| 345 |
-
"learning_rate": 0.
|
| 346 |
-
"loss": 2.
|
| 347 |
"step": 46
|
| 348 |
},
|
| 349 |
{
|
| 350 |
-
"epoch": 0.
|
| 351 |
-
"grad_norm": 0.
|
| 352 |
-
"learning_rate": 0.
|
| 353 |
-
"loss": 2.
|
| 354 |
"step": 47
|
| 355 |
},
|
| 356 |
{
|
| 357 |
-
"epoch": 0.
|
| 358 |
-
"grad_norm":
|
| 359 |
-
"learning_rate": 0.
|
| 360 |
-
"loss": 2.
|
| 361 |
"step": 48
|
| 362 |
},
|
| 363 |
{
|
| 364 |
-
"epoch": 0.
|
| 365 |
-
"grad_norm":
|
| 366 |
-
"learning_rate": 0.
|
| 367 |
-
"loss": 2.
|
| 368 |
"step": 49
|
| 369 |
},
|
| 370 |
{
|
| 371 |
-
"epoch": 0.
|
| 372 |
-
"grad_norm":
|
| 373 |
-
"learning_rate": 0.
|
| 374 |
-
"loss": 2.
|
| 375 |
"step": 50
|
| 376 |
},
|
| 377 |
{
|
| 378 |
-
"epoch": 0.
|
| 379 |
-
"eval_loss": 2.
|
| 380 |
-
"eval_runtime":
|
| 381 |
-
"eval_samples_per_second":
|
| 382 |
-
"eval_steps_per_second":
|
| 383 |
"step": 50
|
| 384 |
-
},
|
| 385 |
-
{
|
| 386 |
-
"epoch": 0.012736467503277768,
|
| 387 |
-
"grad_norm": 1.0722112655639648,
|
| 388 |
-
"learning_rate": 0.00014571428571428572,
|
| 389 |
-
"loss": 3.1445,
|
| 390 |
-
"step": 51
|
| 391 |
-
},
|
| 392 |
-
{
|
| 393 |
-
"epoch": 0.012986202160204782,
|
| 394 |
-
"grad_norm": 1.0569753646850586,
|
| 395 |
-
"learning_rate": 0.00014857142857142857,
|
| 396 |
-
"loss": 2.9575,
|
| 397 |
-
"step": 52
|
| 398 |
-
},
|
| 399 |
-
{
|
| 400 |
-
"epoch": 0.013235936817131798,
|
| 401 |
-
"grad_norm": 0.8477814197540283,
|
| 402 |
-
"learning_rate": 0.00015142857142857143,
|
| 403 |
-
"loss": 2.9096,
|
| 404 |
-
"step": 53
|
| 405 |
-
},
|
| 406 |
-
{
|
| 407 |
-
"epoch": 0.013485671474058812,
|
| 408 |
-
"grad_norm": 0.7475413084030151,
|
| 409 |
-
"learning_rate": 0.0001542857142857143,
|
| 410 |
-
"loss": 2.7139,
|
| 411 |
-
"step": 54
|
| 412 |
-
},
|
| 413 |
-
{
|
| 414 |
-
"epoch": 0.013735406130985827,
|
| 415 |
-
"grad_norm": 0.6939762234687805,
|
| 416 |
-
"learning_rate": 0.00015714285714285716,
|
| 417 |
-
"loss": 2.9446,
|
| 418 |
-
"step": 55
|
| 419 |
-
},
|
| 420 |
-
{
|
| 421 |
-
"epoch": 0.013985140787912843,
|
| 422 |
-
"grad_norm": 0.772847056388855,
|
| 423 |
-
"learning_rate": 0.00016,
|
| 424 |
-
"loss": 2.7692,
|
| 425 |
-
"step": 56
|
| 426 |
-
},
|
| 427 |
-
{
|
| 428 |
-
"epoch": 0.014234875444839857,
|
| 429 |
-
"grad_norm": 0.7479884028434753,
|
| 430 |
-
"learning_rate": 0.00016285714285714287,
|
| 431 |
-
"loss": 2.7092,
|
| 432 |
-
"step": 57
|
| 433 |
-
},
|
| 434 |
-
{
|
| 435 |
-
"epoch": 0.014484610101766873,
|
| 436 |
-
"grad_norm": 0.7816758155822754,
|
| 437 |
-
"learning_rate": 0.00016571428571428575,
|
| 438 |
-
"loss": 2.8473,
|
| 439 |
-
"step": 58
|
| 440 |
-
},
|
| 441 |
-
{
|
| 442 |
-
"epoch": 0.014734344758693887,
|
| 443 |
-
"grad_norm": 0.7092522382736206,
|
| 444 |
-
"learning_rate": 0.00016857142857142857,
|
| 445 |
-
"loss": 2.706,
|
| 446 |
-
"step": 59
|
| 447 |
-
},
|
| 448 |
-
{
|
| 449 |
-
"epoch": 0.014984079415620903,
|
| 450 |
-
"grad_norm": 0.6997970938682556,
|
| 451 |
-
"learning_rate": 0.00017142857142857143,
|
| 452 |
-
"loss": 2.8594,
|
| 453 |
-
"step": 60
|
| 454 |
-
},
|
| 455 |
-
{
|
| 456 |
-
"epoch": 0.015233814072547917,
|
| 457 |
-
"grad_norm": 0.654046356678009,
|
| 458 |
-
"learning_rate": 0.0001742857142857143,
|
| 459 |
-
"loss": 2.7968,
|
| 460 |
-
"step": 61
|
| 461 |
-
},
|
| 462 |
-
{
|
| 463 |
-
"epoch": 0.015483548729474933,
|
| 464 |
-
"grad_norm": 0.6976904273033142,
|
| 465 |
-
"learning_rate": 0.00017714285714285713,
|
| 466 |
-
"loss": 2.8346,
|
| 467 |
-
"step": 62
|
| 468 |
-
},
|
| 469 |
-
{
|
| 470 |
-
"epoch": 0.01573328338640195,
|
| 471 |
-
"grad_norm": 0.7366370558738708,
|
| 472 |
-
"learning_rate": 0.00018,
|
| 473 |
-
"loss": 2.8191,
|
| 474 |
-
"step": 63
|
| 475 |
-
},
|
| 476 |
-
{
|
| 477 |
-
"epoch": 0.015983018043328964,
|
| 478 |
-
"grad_norm": 0.7815442085266113,
|
| 479 |
-
"learning_rate": 0.00018285714285714286,
|
| 480 |
-
"loss": 2.8074,
|
| 481 |
-
"step": 64
|
| 482 |
-
},
|
| 483 |
-
{
|
| 484 |
-
"epoch": 0.016232752700255978,
|
| 485 |
-
"grad_norm": 0.7780041694641113,
|
| 486 |
-
"learning_rate": 0.00018571428571428572,
|
| 487 |
-
"loss": 2.7443,
|
| 488 |
-
"step": 65
|
| 489 |
-
},
|
| 490 |
-
{
|
| 491 |
-
"epoch": 0.016482487357182992,
|
| 492 |
-
"grad_norm": 0.6779807806015015,
|
| 493 |
-
"learning_rate": 0.00018857142857142857,
|
| 494 |
-
"loss": 2.6378,
|
| 495 |
-
"step": 66
|
| 496 |
-
},
|
| 497 |
-
{
|
| 498 |
-
"epoch": 0.01673222201411001,
|
| 499 |
-
"grad_norm": 0.6851223111152649,
|
| 500 |
-
"learning_rate": 0.00019142857142857145,
|
| 501 |
-
"loss": 2.4737,
|
| 502 |
-
"step": 67
|
| 503 |
-
},
|
| 504 |
-
{
|
| 505 |
-
"epoch": 0.016981956671037024,
|
| 506 |
-
"grad_norm": 0.741107702255249,
|
| 507 |
-
"learning_rate": 0.0001942857142857143,
|
| 508 |
-
"loss": 2.708,
|
| 509 |
-
"step": 68
|
| 510 |
-
},
|
| 511 |
-
{
|
| 512 |
-
"epoch": 0.017231691327964038,
|
| 513 |
-
"grad_norm": 0.7790065407752991,
|
| 514 |
-
"learning_rate": 0.00019714285714285716,
|
| 515 |
-
"loss": 2.7973,
|
| 516 |
-
"step": 69
|
| 517 |
-
},
|
| 518 |
-
{
|
| 519 |
-
"epoch": 0.017481425984891052,
|
| 520 |
-
"grad_norm": 0.8207802176475525,
|
| 521 |
-
"learning_rate": 0.0002,
|
| 522 |
-
"loss": 2.7328,
|
| 523 |
-
"step": 70
|
| 524 |
-
},
|
| 525 |
-
{
|
| 526 |
-
"epoch": 0.017731160641818067,
|
| 527 |
-
"grad_norm": 0.8045083284378052,
|
| 528 |
-
"learning_rate": 0.00019999984264028182,
|
| 529 |
-
"loss": 2.6503,
|
| 530 |
-
"step": 71
|
| 531 |
-
},
|
| 532 |
-
{
|
| 533 |
-
"epoch": 0.017980895298745084,
|
| 534 |
-
"grad_norm": 0.8912211060523987,
|
| 535 |
-
"learning_rate": 0.0001999993705616775,
|
| 536 |
-
"loss": 2.6638,
|
| 537 |
-
"step": 72
|
| 538 |
-
},
|
| 539 |
-
{
|
| 540 |
-
"epoch": 0.0182306299556721,
|
| 541 |
-
"grad_norm": 0.8193833231925964,
|
| 542 |
-
"learning_rate": 0.0001999985837658379,
|
| 543 |
-
"loss": 2.3789,
|
| 544 |
-
"step": 73
|
| 545 |
-
},
|
| 546 |
-
{
|
| 547 |
-
"epoch": 0.018480364612599113,
|
| 548 |
-
"grad_norm": 0.8749593496322632,
|
| 549 |
-
"learning_rate": 0.0001999974822555143,
|
| 550 |
-
"loss": 2.6006,
|
| 551 |
-
"step": 74
|
| 552 |
-
},
|
| 553 |
-
{
|
| 554 |
-
"epoch": 0.018730099269526127,
|
| 555 |
-
"grad_norm": 0.911247730255127,
|
| 556 |
-
"learning_rate": 0.00019999606603455857,
|
| 557 |
-
"loss": 2.6721,
|
| 558 |
-
"step": 75
|
| 559 |
-
},
|
| 560 |
-
{
|
| 561 |
-
"epoch": 0.018730099269526127,
|
| 562 |
-
"eval_loss": 2.6788198947906494,
|
| 563 |
-
"eval_runtime": 2.6857,
|
| 564 |
-
"eval_samples_per_second": 18.617,
|
| 565 |
-
"eval_steps_per_second": 2.979,
|
| 566 |
-
"step": 75
|
| 567 |
-
},
|
| 568 |
-
{
|
| 569 |
-
"epoch": 0.018979833926453145,
|
| 570 |
-
"grad_norm": 0.9761448502540588,
|
| 571 |
-
"learning_rate": 0.00019999433510792307,
|
| 572 |
-
"loss": 2.7212,
|
| 573 |
-
"step": 76
|
| 574 |
-
},
|
| 575 |
-
{
|
| 576 |
-
"epoch": 0.01922956858338016,
|
| 577 |
-
"grad_norm": 0.7784520983695984,
|
| 578 |
-
"learning_rate": 0.00019999228948166064,
|
| 579 |
-
"loss": 2.7151,
|
| 580 |
-
"step": 77
|
| 581 |
-
},
|
| 582 |
-
{
|
| 583 |
-
"epoch": 0.019479303240307173,
|
| 584 |
-
"grad_norm": 0.8097946047782898,
|
| 585 |
-
"learning_rate": 0.00019998992916292463,
|
| 586 |
-
"loss": 2.4256,
|
| 587 |
-
"step": 78
|
| 588 |
-
},
|
| 589 |
-
{
|
| 590 |
-
"epoch": 0.019729037897234188,
|
| 591 |
-
"grad_norm": 0.8229548931121826,
|
| 592 |
-
"learning_rate": 0.00019998725415996875,
|
| 593 |
-
"loss": 2.482,
|
| 594 |
-
"step": 79
|
| 595 |
-
},
|
| 596 |
-
{
|
| 597 |
-
"epoch": 0.019978772554161205,
|
| 598 |
-
"grad_norm": 0.8396543860435486,
|
| 599 |
-
"learning_rate": 0.00019998426448214718,
|
| 600 |
-
"loss": 2.5676,
|
| 601 |
-
"step": 80
|
| 602 |
-
},
|
| 603 |
-
{
|
| 604 |
-
"epoch": 0.02022850721108822,
|
| 605 |
-
"grad_norm": 0.84672611951828,
|
| 606 |
-
"learning_rate": 0.0001999809601399145,
|
| 607 |
-
"loss": 2.4699,
|
| 608 |
-
"step": 81
|
| 609 |
-
},
|
| 610 |
-
{
|
| 611 |
-
"epoch": 0.020478241868015234,
|
| 612 |
-
"grad_norm": 0.8323167562484741,
|
| 613 |
-
"learning_rate": 0.0001999773411448256,
|
| 614 |
-
"loss": 2.6894,
|
| 615 |
-
"step": 82
|
| 616 |
-
},
|
| 617 |
-
{
|
| 618 |
-
"epoch": 0.020727976524942248,
|
| 619 |
-
"grad_norm": 0.9671497344970703,
|
| 620 |
-
"learning_rate": 0.00019997340750953566,
|
| 621 |
-
"loss": 2.6653,
|
| 622 |
-
"step": 83
|
| 623 |
-
},
|
| 624 |
-
{
|
| 625 |
-
"epoch": 0.020977711181869262,
|
| 626 |
-
"grad_norm": 1.0757114887237549,
|
| 627 |
-
"learning_rate": 0.00019996915924780015,
|
| 628 |
-
"loss": 2.6165,
|
| 629 |
-
"step": 84
|
| 630 |
-
},
|
| 631 |
-
{
|
| 632 |
-
"epoch": 0.02122744583879628,
|
| 633 |
-
"grad_norm": 0.8748140335083008,
|
| 634 |
-
"learning_rate": 0.00019996459637447477,
|
| 635 |
-
"loss": 2.582,
|
| 636 |
-
"step": 85
|
| 637 |
-
},
|
| 638 |
-
{
|
| 639 |
-
"epoch": 0.021477180495723294,
|
| 640 |
-
"grad_norm": 0.8593396544456482,
|
| 641 |
-
"learning_rate": 0.0001999597189055153,
|
| 642 |
-
"loss": 2.4936,
|
| 643 |
-
"step": 86
|
| 644 |
-
},
|
| 645 |
-
{
|
| 646 |
-
"epoch": 0.02172691515265031,
|
| 647 |
-
"grad_norm": 0.933760941028595,
|
| 648 |
-
"learning_rate": 0.00019995452685797773,
|
| 649 |
-
"loss": 2.8435,
|
| 650 |
-
"step": 87
|
| 651 |
-
},
|
| 652 |
-
{
|
| 653 |
-
"epoch": 0.021976649809577323,
|
| 654 |
-
"grad_norm": 0.8785303235054016,
|
| 655 |
-
"learning_rate": 0.00019994902025001802,
|
| 656 |
-
"loss": 2.4451,
|
| 657 |
-
"step": 88
|
| 658 |
-
},
|
| 659 |
-
{
|
| 660 |
-
"epoch": 0.02222638446650434,
|
| 661 |
-
"grad_norm": 0.8894078731536865,
|
| 662 |
-
"learning_rate": 0.0001999431991008921,
|
| 663 |
-
"loss": 2.5532,
|
| 664 |
-
"step": 89
|
| 665 |
-
},
|
| 666 |
-
{
|
| 667 |
-
"epoch": 0.022476119123431355,
|
| 668 |
-
"grad_norm": 0.9705137610435486,
|
| 669 |
-
"learning_rate": 0.00019993706343095588,
|
| 670 |
-
"loss": 2.7539,
|
| 671 |
-
"step": 90
|
| 672 |
-
},
|
| 673 |
-
{
|
| 674 |
-
"epoch": 0.02272585378035837,
|
| 675 |
-
"grad_norm": 1.0564568042755127,
|
| 676 |
-
"learning_rate": 0.0001999306132616651,
|
| 677 |
-
"loss": 2.7694,
|
| 678 |
-
"step": 91
|
| 679 |
-
},
|
| 680 |
-
{
|
| 681 |
-
"epoch": 0.022975588437285383,
|
| 682 |
-
"grad_norm": 1.0100560188293457,
|
| 683 |
-
"learning_rate": 0.00019992384861557515,
|
| 684 |
-
"loss": 2.6056,
|
| 685 |
-
"step": 92
|
| 686 |
-
},
|
| 687 |
-
{
|
| 688 |
-
"epoch": 0.0232253230942124,
|
| 689 |
-
"grad_norm": 1.0753816366195679,
|
| 690 |
-
"learning_rate": 0.00019991676951634132,
|
| 691 |
-
"loss": 2.4921,
|
| 692 |
-
"step": 93
|
| 693 |
-
},
|
| 694 |
-
{
|
| 695 |
-
"epoch": 0.023475057751139415,
|
| 696 |
-
"grad_norm": 0.9264618158340454,
|
| 697 |
-
"learning_rate": 0.00019990937598871834,
|
| 698 |
-
"loss": 2.6055,
|
| 699 |
-
"step": 94
|
| 700 |
-
},
|
| 701 |
-
{
|
| 702 |
-
"epoch": 0.02372479240806643,
|
| 703 |
-
"grad_norm": 1.0126386880874634,
|
| 704 |
-
"learning_rate": 0.00019990166805856048,
|
| 705 |
-
"loss": 2.4358,
|
| 706 |
-
"step": 95
|
| 707 |
-
},
|
| 708 |
-
{
|
| 709 |
-
"epoch": 0.023974527064993444,
|
| 710 |
-
"grad_norm": 0.9737821817398071,
|
| 711 |
-
"learning_rate": 0.0001998936457528215,
|
| 712 |
-
"loss": 2.7028,
|
| 713 |
-
"step": 96
|
| 714 |
-
},
|
| 715 |
-
{
|
| 716 |
-
"epoch": 0.024224261721920458,
|
| 717 |
-
"grad_norm": 1.0489351749420166,
|
| 718 |
-
"learning_rate": 0.00019988530909955448,
|
| 719 |
-
"loss": 2.6114,
|
| 720 |
-
"step": 97
|
| 721 |
-
},
|
| 722 |
-
{
|
| 723 |
-
"epoch": 0.024473996378847476,
|
| 724 |
-
"grad_norm": 1.1334600448608398,
|
| 725 |
-
"learning_rate": 0.00019987665812791166,
|
| 726 |
-
"loss": 2.8804,
|
| 727 |
-
"step": 98
|
| 728 |
-
},
|
| 729 |
-
{
|
| 730 |
-
"epoch": 0.02472373103577449,
|
| 731 |
-
"grad_norm": 1.2668412923812866,
|
| 732 |
-
"learning_rate": 0.0001998676928681445,
|
| 733 |
-
"loss": 2.9214,
|
| 734 |
-
"step": 99
|
| 735 |
-
},
|
| 736 |
-
{
|
| 737 |
-
"epoch": 0.024973465692701504,
|
| 738 |
-
"grad_norm": 2.203848361968994,
|
| 739 |
-
"learning_rate": 0.0001998584133516035,
|
| 740 |
-
"loss": 2.9326,
|
| 741 |
-
"step": 100
|
| 742 |
-
},
|
| 743 |
-
{
|
| 744 |
-
"epoch": 0.024973465692701504,
|
| 745 |
-
"eval_loss": 2.6431591510772705,
|
| 746 |
-
"eval_runtime": 2.6774,
|
| 747 |
-
"eval_samples_per_second": 18.675,
|
| 748 |
-
"eval_steps_per_second": 2.988,
|
| 749 |
-
"step": 100
|
| 750 |
-
},
|
| 751 |
-
{
|
| 752 |
-
"epoch": 0.02522320034962852,
|
| 753 |
-
"grad_norm": 0.9147284030914307,
|
| 754 |
-
"learning_rate": 0.00019984881961073798,
|
| 755 |
-
"loss": 2.6948,
|
| 756 |
-
"step": 101
|
| 757 |
-
},
|
| 758 |
-
{
|
| 759 |
-
"epoch": 0.025472935006555536,
|
| 760 |
-
"grad_norm": 0.8852336406707764,
|
| 761 |
-
"learning_rate": 0.00019983891167909616,
|
| 762 |
-
"loss": 2.5529,
|
| 763 |
-
"step": 102
|
| 764 |
-
},
|
| 765 |
-
{
|
| 766 |
-
"epoch": 0.02572266966348255,
|
| 767 |
-
"grad_norm": 0.7818748354911804,
|
| 768 |
-
"learning_rate": 0.00019982868959132492,
|
| 769 |
-
"loss": 2.7862,
|
| 770 |
-
"step": 103
|
| 771 |
-
},
|
| 772 |
-
{
|
| 773 |
-
"epoch": 0.025972404320409564,
|
| 774 |
-
"grad_norm": 0.6491966247558594,
|
| 775 |
-
"learning_rate": 0.00019981815338316968,
|
| 776 |
-
"loss": 2.6352,
|
| 777 |
-
"step": 104
|
| 778 |
-
},
|
| 779 |
-
{
|
| 780 |
-
"epoch": 0.02622213897733658,
|
| 781 |
-
"grad_norm": 0.6427002549171448,
|
| 782 |
-
"learning_rate": 0.00019980730309147434,
|
| 783 |
-
"loss": 2.7408,
|
| 784 |
-
"step": 105
|
| 785 |
-
},
|
| 786 |
-
{
|
| 787 |
-
"epoch": 0.026471873634263596,
|
| 788 |
-
"grad_norm": 0.6891926527023315,
|
| 789 |
-
"learning_rate": 0.00019979613875418107,
|
| 790 |
-
"loss": 2.6471,
|
| 791 |
-
"step": 106
|
| 792 |
-
},
|
| 793 |
-
{
|
| 794 |
-
"epoch": 0.02672160829119061,
|
| 795 |
-
"grad_norm": 0.8082403540611267,
|
| 796 |
-
"learning_rate": 0.00019978466041033026,
|
| 797 |
-
"loss": 2.5825,
|
| 798 |
-
"step": 107
|
| 799 |
-
},
|
| 800 |
-
{
|
| 801 |
-
"epoch": 0.026971342948117625,
|
| 802 |
-
"grad_norm": 0.7740591764450073,
|
| 803 |
-
"learning_rate": 0.00019977286810006034,
|
| 804 |
-
"loss": 2.9007,
|
| 805 |
-
"step": 108
|
| 806 |
-
},
|
| 807 |
-
{
|
| 808 |
-
"epoch": 0.02722107760504464,
|
| 809 |
-
"grad_norm": 0.7396791577339172,
|
| 810 |
-
"learning_rate": 0.00019976076186460764,
|
| 811 |
-
"loss": 2.6945,
|
| 812 |
-
"step": 109
|
| 813 |
-
},
|
| 814 |
-
{
|
| 815 |
-
"epoch": 0.027470812261971653,
|
| 816 |
-
"grad_norm": 0.6720578670501709,
|
| 817 |
-
"learning_rate": 0.00019974834174630622,
|
| 818 |
-
"loss": 2.7139,
|
| 819 |
-
"step": 110
|
| 820 |
-
},
|
| 821 |
-
{
|
| 822 |
-
"epoch": 0.02772054691889867,
|
| 823 |
-
"grad_norm": 0.8105450868606567,
|
| 824 |
-
"learning_rate": 0.0001997356077885878,
|
| 825 |
-
"loss": 2.7112,
|
| 826 |
-
"step": 111
|
| 827 |
-
},
|
| 828 |
-
{
|
| 829 |
-
"epoch": 0.027970281575825685,
|
| 830 |
-
"grad_norm": 0.7144357562065125,
|
| 831 |
-
"learning_rate": 0.00019972256003598153,
|
| 832 |
-
"loss": 2.3851,
|
| 833 |
-
"step": 112
|
| 834 |
-
},
|
| 835 |
-
{
|
| 836 |
-
"epoch": 0.0282200162327527,
|
| 837 |
-
"grad_norm": 0.7595510482788086,
|
| 838 |
-
"learning_rate": 0.00019970919853411385,
|
| 839 |
-
"loss": 2.6396,
|
| 840 |
-
"step": 113
|
| 841 |
-
},
|
| 842 |
-
{
|
| 843 |
-
"epoch": 0.028469750889679714,
|
| 844 |
-
"grad_norm": 0.7179970145225525,
|
| 845 |
-
"learning_rate": 0.0001996955233297084,
|
| 846 |
-
"loss": 2.3639,
|
| 847 |
-
"step": 114
|
| 848 |
-
},
|
| 849 |
-
{
|
| 850 |
-
"epoch": 0.02871948554660673,
|
| 851 |
-
"grad_norm": 0.7306939959526062,
|
| 852 |
-
"learning_rate": 0.00019968153447058576,
|
| 853 |
-
"loss": 2.5145,
|
| 854 |
-
"step": 115
|
| 855 |
-
},
|
| 856 |
-
{
|
| 857 |
-
"epoch": 0.028969220203533746,
|
| 858 |
-
"grad_norm": 0.7519063353538513,
|
| 859 |
-
"learning_rate": 0.00019966723200566327,
|
| 860 |
-
"loss": 2.4479,
|
| 861 |
-
"step": 116
|
| 862 |
-
},
|
| 863 |
-
{
|
| 864 |
-
"epoch": 0.02921895486046076,
|
| 865 |
-
"grad_norm": 0.8461882472038269,
|
| 866 |
-
"learning_rate": 0.00019965261598495502,
|
| 867 |
-
"loss": 2.5828,
|
| 868 |
-
"step": 117
|
| 869 |
-
},
|
| 870 |
-
{
|
| 871 |
-
"epoch": 0.029468689517387774,
|
| 872 |
-
"grad_norm": 0.7643318772315979,
|
| 873 |
-
"learning_rate": 0.00019963768645957152,
|
| 874 |
-
"loss": 2.5821,
|
| 875 |
-
"step": 118
|
| 876 |
-
},
|
| 877 |
-
{
|
| 878 |
-
"epoch": 0.029718424174314792,
|
| 879 |
-
"grad_norm": 0.7931061387062073,
|
| 880 |
-
"learning_rate": 0.00019962244348171958,
|
| 881 |
-
"loss": 2.5467,
|
| 882 |
-
"step": 119
|
| 883 |
-
},
|
| 884 |
-
{
|
| 885 |
-
"epoch": 0.029968158831241806,
|
| 886 |
-
"grad_norm": 0.7353018522262573,
|
| 887 |
-
"learning_rate": 0.00019960688710470205,
|
| 888 |
-
"loss": 2.5064,
|
| 889 |
-
"step": 120
|
| 890 |
-
},
|
| 891 |
-
{
|
| 892 |
-
"epoch": 0.03021789348816882,
|
| 893 |
-
"grad_norm": 0.7961385846138,
|
| 894 |
-
"learning_rate": 0.0001995910173829178,
|
| 895 |
-
"loss": 2.2525,
|
| 896 |
-
"step": 121
|
| 897 |
-
},
|
| 898 |
-
{
|
| 899 |
-
"epoch": 0.030467628145095835,
|
| 900 |
-
"grad_norm": 0.8227445483207703,
|
| 901 |
-
"learning_rate": 0.00019957483437186137,
|
| 902 |
-
"loss": 2.3514,
|
| 903 |
-
"step": 122
|
| 904 |
-
},
|
| 905 |
-
{
|
| 906 |
-
"epoch": 0.030717362802022852,
|
| 907 |
-
"grad_norm": 0.8792641758918762,
|
| 908 |
-
"learning_rate": 0.0001995583381281229,
|
| 909 |
-
"loss": 2.6704,
|
| 910 |
-
"step": 123
|
| 911 |
-
},
|
| 912 |
-
{
|
| 913 |
-
"epoch": 0.030967097458949867,
|
| 914 |
-
"grad_norm": 0.8991889357566833,
|
| 915 |
-
"learning_rate": 0.0001995415287093877,
|
| 916 |
-
"loss": 2.7915,
|
| 917 |
-
"step": 124
|
| 918 |
-
},
|
| 919 |
-
{
|
| 920 |
-
"epoch": 0.03121683211587688,
|
| 921 |
-
"grad_norm": 0.8456166982650757,
|
| 922 |
-
"learning_rate": 0.00019952440617443647,
|
| 923 |
-
"loss": 2.5482,
|
| 924 |
-
"step": 125
|
| 925 |
-
},
|
| 926 |
-
{
|
| 927 |
-
"epoch": 0.03121683211587688,
|
| 928 |
-
"eval_loss": 2.5769076347351074,
|
| 929 |
-
"eval_runtime": 2.6825,
|
| 930 |
-
"eval_samples_per_second": 18.639,
|
| 931 |
-
"eval_steps_per_second": 2.982,
|
| 932 |
-
"step": 125
|
| 933 |
-
},
|
| 934 |
-
{
|
| 935 |
-
"epoch": 0.0314665667728039,
|
| 936 |
-
"grad_norm": 0.9480443000793457,
|
| 937 |
-
"learning_rate": 0.0001995069705831446,
|
| 938 |
-
"loss": 2.6215,
|
| 939 |
-
"step": 126
|
| 940 |
-
},
|
| 941 |
-
{
|
| 942 |
-
"epoch": 0.03171630142973091,
|
| 943 |
-
"grad_norm": 0.8263009786605835,
|
| 944 |
-
"learning_rate": 0.00019948922199648235,
|
| 945 |
-
"loss": 2.5919,
|
| 946 |
-
"step": 127
|
| 947 |
-
},
|
| 948 |
-
{
|
| 949 |
-
"epoch": 0.03196603608665793,
|
| 950 |
-
"grad_norm": 0.7829933166503906,
|
| 951 |
-
"learning_rate": 0.00019947116047651448,
|
| 952 |
-
"loss": 2.4247,
|
| 953 |
-
"step": 128
|
| 954 |
-
},
|
| 955 |
-
{
|
| 956 |
-
"epoch": 0.03221577074358494,
|
| 957 |
-
"grad_norm": 0.7913976311683655,
|
| 958 |
-
"learning_rate": 0.00019945278608639994,
|
| 959 |
-
"loss": 2.5516,
|
| 960 |
-
"step": 129
|
| 961 |
-
},
|
| 962 |
-
{
|
| 963 |
-
"epoch": 0.032465505400511956,
|
| 964 |
-
"grad_norm": 0.8564252257347107,
|
| 965 |
-
"learning_rate": 0.00019943409889039188,
|
| 966 |
-
"loss": 2.3555,
|
| 967 |
-
"step": 130
|
| 968 |
-
},
|
| 969 |
-
{
|
| 970 |
-
"epoch": 0.03271524005743897,
|
| 971 |
-
"grad_norm": 0.809696614742279,
|
| 972 |
-
"learning_rate": 0.0001994150989538371,
|
| 973 |
-
"loss": 2.4586,
|
| 974 |
-
"step": 131
|
| 975 |
-
},
|
| 976 |
-
{
|
| 977 |
-
"epoch": 0.032964974714365984,
|
| 978 |
-
"grad_norm": 0.8882852792739868,
|
| 979 |
-
"learning_rate": 0.0001993957863431763,
|
| 980 |
-
"loss": 2.459,
|
| 981 |
-
"step": 132
|
| 982 |
-
},
|
| 983 |
-
{
|
| 984 |
-
"epoch": 0.033214709371293,
|
| 985 |
-
"grad_norm": 0.9187607765197754,
|
| 986 |
-
"learning_rate": 0.0001993761611259434,
|
| 987 |
-
"loss": 2.6238,
|
| 988 |
-
"step": 133
|
| 989 |
-
},
|
| 990 |
-
{
|
| 991 |
-
"epoch": 0.03346444402822002,
|
| 992 |
-
"grad_norm": 0.8577990531921387,
|
| 993 |
-
"learning_rate": 0.00019935622337076536,
|
| 994 |
-
"loss": 2.5431,
|
| 995 |
-
"step": 134
|
| 996 |
-
},
|
| 997 |
-
{
|
| 998 |
-
"epoch": 0.033714178685147034,
|
| 999 |
-
"grad_norm": 0.8696761727333069,
|
| 1000 |
-
"learning_rate": 0.00019933597314736228,
|
| 1001 |
-
"loss": 2.5734,
|
| 1002 |
-
"step": 135
|
| 1003 |
-
},
|
| 1004 |
-
{
|
| 1005 |
-
"epoch": 0.03396391334207405,
|
| 1006 |
-
"grad_norm": 0.828972578048706,
|
| 1007 |
-
"learning_rate": 0.0001993154105265468,
|
| 1008 |
-
"loss": 2.6162,
|
| 1009 |
-
"step": 136
|
| 1010 |
-
},
|
| 1011 |
-
{
|
| 1012 |
-
"epoch": 0.03421364799900106,
|
| 1013 |
-
"grad_norm": 0.9171616435050964,
|
| 1014 |
-
"learning_rate": 0.00019929453558022392,
|
| 1015 |
-
"loss": 2.4986,
|
| 1016 |
-
"step": 137
|
| 1017 |
-
},
|
| 1018 |
-
{
|
| 1019 |
-
"epoch": 0.034463382655928076,
|
| 1020 |
-
"grad_norm": 0.8592952489852905,
|
| 1021 |
-
"learning_rate": 0.00019927334838139098,
|
| 1022 |
-
"loss": 2.4374,
|
| 1023 |
-
"step": 138
|
| 1024 |
-
},
|
| 1025 |
-
{
|
| 1026 |
-
"epoch": 0.03471311731285509,
|
| 1027 |
-
"grad_norm": 0.969752311706543,
|
| 1028 |
-
"learning_rate": 0.00019925184900413705,
|
| 1029 |
-
"loss": 2.3063,
|
| 1030 |
-
"step": 139
|
| 1031 |
-
},
|
| 1032 |
-
{
|
| 1033 |
-
"epoch": 0.034962851969782105,
|
| 1034 |
-
"grad_norm": 0.863645076751709,
|
| 1035 |
-
"learning_rate": 0.00019923003752364297,
|
| 1036 |
-
"loss": 2.3734,
|
| 1037 |
-
"step": 140
|
| 1038 |
-
},
|
| 1039 |
-
{
|
| 1040 |
-
"epoch": 0.03521258662670912,
|
| 1041 |
-
"grad_norm": 1.038589596748352,
|
| 1042 |
-
"learning_rate": 0.00019920791401618088,
|
| 1043 |
-
"loss": 2.6056,
|
| 1044 |
-
"step": 141
|
| 1045 |
-
},
|
| 1046 |
-
{
|
| 1047 |
-
"epoch": 0.03546232128363613,
|
| 1048 |
-
"grad_norm": 1.0344328880310059,
|
| 1049 |
-
"learning_rate": 0.00019918547855911413,
|
| 1050 |
-
"loss": 2.5048,
|
| 1051 |
-
"step": 142
|
| 1052 |
-
},
|
| 1053 |
-
{
|
| 1054 |
-
"epoch": 0.035712055940563155,
|
| 1055 |
-
"grad_norm": 0.883296012878418,
|
| 1056 |
-
"learning_rate": 0.0001991627312308969,
|
| 1057 |
-
"loss": 2.4579,
|
| 1058 |
-
"step": 143
|
| 1059 |
-
},
|
| 1060 |
-
{
|
| 1061 |
-
"epoch": 0.03596179059749017,
|
| 1062 |
-
"grad_norm": 0.9329782724380493,
|
| 1063 |
-
"learning_rate": 0.00019913967211107386,
|
| 1064 |
-
"loss": 2.4917,
|
| 1065 |
-
"step": 144
|
| 1066 |
-
},
|
| 1067 |
-
{
|
| 1068 |
-
"epoch": 0.03621152525441718,
|
| 1069 |
-
"grad_norm": 0.9287551641464233,
|
| 1070 |
-
"learning_rate": 0.00019911630128028012,
|
| 1071 |
-
"loss": 2.648,
|
| 1072 |
-
"step": 145
|
| 1073 |
-
},
|
| 1074 |
-
{
|
| 1075 |
-
"epoch": 0.0364612599113442,
|
| 1076 |
-
"grad_norm": 0.9368601441383362,
|
| 1077 |
-
"learning_rate": 0.00019909261882024065,
|
| 1078 |
-
"loss": 2.4704,
|
| 1079 |
-
"step": 146
|
| 1080 |
-
},
|
| 1081 |
-
{
|
| 1082 |
-
"epoch": 0.03671099456827121,
|
| 1083 |
-
"grad_norm": 0.9918820261955261,
|
| 1084 |
-
"learning_rate": 0.00019906862481377033,
|
| 1085 |
-
"loss": 2.3632,
|
| 1086 |
-
"step": 147
|
| 1087 |
-
},
|
| 1088 |
-
{
|
| 1089 |
-
"epoch": 0.036960729225198226,
|
| 1090 |
-
"grad_norm": 1.0322192907333374,
|
| 1091 |
-
"learning_rate": 0.0001990443193447733,
|
| 1092 |
-
"loss": 2.5039,
|
| 1093 |
-
"step": 148
|
| 1094 |
-
},
|
| 1095 |
-
{
|
| 1096 |
-
"epoch": 0.03721046388212524,
|
| 1097 |
-
"grad_norm": 1.307169795036316,
|
| 1098 |
-
"learning_rate": 0.000199019702498243,
|
| 1099 |
-
"loss": 2.483,
|
| 1100 |
-
"step": 149
|
| 1101 |
-
},
|
| 1102 |
-
{
|
| 1103 |
-
"epoch": 0.037460198539052254,
|
| 1104 |
-
"grad_norm": 2.3513553142547607,
|
| 1105 |
-
"learning_rate": 0.00019899477436026157,
|
| 1106 |
-
"loss": 2.3276,
|
| 1107 |
-
"step": 150
|
| 1108 |
-
},
|
| 1109 |
-
{
|
| 1110 |
-
"epoch": 0.037460198539052254,
|
| 1111 |
-
"eval_loss": 2.570774555206299,
|
| 1112 |
-
"eval_runtime": 2.6997,
|
| 1113 |
-
"eval_samples_per_second": 18.521,
|
| 1114 |
-
"eval_steps_per_second": 2.963,
|
| 1115 |
-
"step": 150
|
| 1116 |
}
|
| 1117 |
],
|
| 1118 |
"logging_steps": 1,
|
| 1119 |
-
"max_steps":
|
| 1120 |
"num_input_tokens_seen": 0,
|
| 1121 |
"num_train_epochs": 1,
|
| 1122 |
"save_steps": 50,
|
|
@@ -1141,8 +409,8 @@
|
|
| 1141 |
"attributes": {}
|
| 1142 |
}
|
| 1143 |
},
|
| 1144 |
-
"total_flos": 5.
|
| 1145 |
-
"train_batch_size":
|
| 1146 |
"trial_name": null,
|
| 1147 |
"trial_params": null
|
| 1148 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 2.556696653366089,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-50",
|
| 4 |
+
"epoch": 0.014271060964188556,
|
| 5 |
"eval_steps": 25,
|
| 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": 0.0002854212192837711,
|
| 13 |
+
"grad_norm": 0.9852302670478821,
|
| 14 |
+
"learning_rate": 5.7142857142857145e-06,
|
| 15 |
+
"loss": 3.0904,
|
| 16 |
"step": 1
|
| 17 |
},
|
| 18 |
{
|
| 19 |
+
"epoch": 0.0002854212192837711,
|
| 20 |
+
"eval_loss": 3.2887184619903564,
|
| 21 |
+
"eval_runtime": 6.5686,
|
| 22 |
+
"eval_samples_per_second": 7.612,
|
| 23 |
+
"eval_steps_per_second": 7.612,
|
| 24 |
"step": 1
|
| 25 |
},
|
| 26 |
{
|
| 27 |
+
"epoch": 0.0005708424385675422,
|
| 28 |
+
"grad_norm": 0.8380288481712341,
|
| 29 |
+
"learning_rate": 1.1428571428571429e-05,
|
| 30 |
+
"loss": 3.1387,
|
| 31 |
"step": 2
|
| 32 |
},
|
| 33 |
{
|
| 34 |
+
"epoch": 0.0008562636578513134,
|
| 35 |
+
"grad_norm": 0.8498082160949707,
|
| 36 |
+
"learning_rate": 1.7142857142857145e-05,
|
| 37 |
+
"loss": 3.1155,
|
| 38 |
"step": 3
|
| 39 |
},
|
| 40 |
{
|
| 41 |
+
"epoch": 0.0011416848771350844,
|
| 42 |
+
"grad_norm": 0.932189404964447,
|
| 43 |
+
"learning_rate": 2.2857142857142858e-05,
|
| 44 |
+
"loss": 3.1839,
|
| 45 |
"step": 4
|
| 46 |
},
|
| 47 |
{
|
| 48 |
+
"epoch": 0.0014271060964188556,
|
| 49 |
+
"grad_norm": 0.8401004076004028,
|
| 50 |
+
"learning_rate": 2.857142857142857e-05,
|
| 51 |
+
"loss": 3.149,
|
| 52 |
"step": 5
|
| 53 |
},
|
| 54 |
{
|
| 55 |
+
"epoch": 0.0017125273157026267,
|
| 56 |
+
"grad_norm": 0.8718746900558472,
|
| 57 |
+
"learning_rate": 3.428571428571429e-05,
|
| 58 |
+
"loss": 3.1855,
|
| 59 |
"step": 6
|
| 60 |
},
|
| 61 |
{
|
| 62 |
+
"epoch": 0.001997948534986398,
|
| 63 |
+
"grad_norm": 0.8892223238945007,
|
| 64 |
+
"learning_rate": 4e-05,
|
| 65 |
+
"loss": 3.0531,
|
| 66 |
"step": 7
|
| 67 |
},
|
| 68 |
{
|
| 69 |
+
"epoch": 0.002283369754270169,
|
| 70 |
+
"grad_norm": 0.8379232287406921,
|
| 71 |
+
"learning_rate": 4.5714285714285716e-05,
|
| 72 |
+
"loss": 3.042,
|
| 73 |
"step": 8
|
| 74 |
},
|
| 75 |
{
|
| 76 |
+
"epoch": 0.00256879097355394,
|
| 77 |
+
"grad_norm": 0.8372194170951843,
|
| 78 |
+
"learning_rate": 5.142857142857143e-05,
|
| 79 |
+
"loss": 2.9784,
|
| 80 |
"step": 9
|
| 81 |
},
|
| 82 |
{
|
| 83 |
+
"epoch": 0.002854212192837711,
|
| 84 |
+
"grad_norm": 0.7960942983627319,
|
| 85 |
+
"learning_rate": 5.714285714285714e-05,
|
| 86 |
+
"loss": 3.1879,
|
| 87 |
"step": 10
|
| 88 |
},
|
| 89 |
{
|
| 90 |
+
"epoch": 0.0031396334121214825,
|
| 91 |
+
"grad_norm": 0.8907091021537781,
|
| 92 |
+
"learning_rate": 6.285714285714286e-05,
|
| 93 |
+
"loss": 3.0808,
|
| 94 |
"step": 11
|
| 95 |
},
|
| 96 |
{
|
| 97 |
+
"epoch": 0.0034250546314052535,
|
| 98 |
+
"grad_norm": 0.6043815016746521,
|
| 99 |
+
"learning_rate": 6.857142857142858e-05,
|
| 100 |
+
"loss": 2.9428,
|
| 101 |
"step": 12
|
| 102 |
},
|
| 103 |
{
|
| 104 |
+
"epoch": 0.003710475850689025,
|
| 105 |
+
"grad_norm": 0.564944863319397,
|
| 106 |
+
"learning_rate": 7.428571428571429e-05,
|
| 107 |
+
"loss": 3.0157,
|
| 108 |
"step": 13
|
| 109 |
},
|
| 110 |
{
|
| 111 |
+
"epoch": 0.003995897069972796,
|
| 112 |
+
"grad_norm": 0.5410389304161072,
|
| 113 |
+
"learning_rate": 8e-05,
|
| 114 |
+
"loss": 2.9157,
|
| 115 |
"step": 14
|
| 116 |
},
|
| 117 |
{
|
| 118 |
+
"epoch": 0.004281318289256567,
|
| 119 |
+
"grad_norm": 0.5174809098243713,
|
| 120 |
+
"learning_rate": 8.571428571428571e-05,
|
| 121 |
+
"loss": 2.7908,
|
| 122 |
"step": 15
|
| 123 |
},
|
| 124 |
{
|
| 125 |
+
"epoch": 0.004566739508540338,
|
| 126 |
+
"grad_norm": 0.5930260419845581,
|
| 127 |
+
"learning_rate": 9.142857142857143e-05,
|
| 128 |
+
"loss": 2.8472,
|
| 129 |
"step": 16
|
| 130 |
},
|
| 131 |
{
|
| 132 |
+
"epoch": 0.0048521607278241095,
|
| 133 |
+
"grad_norm": 0.6121829152107239,
|
| 134 |
+
"learning_rate": 9.714285714285715e-05,
|
| 135 |
+
"loss": 2.8535,
|
| 136 |
"step": 17
|
| 137 |
},
|
| 138 |
{
|
| 139 |
+
"epoch": 0.00513758194710788,
|
| 140 |
+
"grad_norm": 0.5915908813476562,
|
| 141 |
+
"learning_rate": 0.00010285714285714286,
|
| 142 |
+
"loss": 2.6747,
|
| 143 |
"step": 18
|
| 144 |
},
|
| 145 |
{
|
| 146 |
+
"epoch": 0.005423003166391651,
|
| 147 |
+
"grad_norm": 0.5632700324058533,
|
| 148 |
+
"learning_rate": 0.00010857142857142856,
|
| 149 |
+
"loss": 2.6425,
|
| 150 |
"step": 19
|
| 151 |
},
|
| 152 |
{
|
| 153 |
+
"epoch": 0.005708424385675422,
|
| 154 |
+
"grad_norm": 0.5865013599395752,
|
| 155 |
+
"learning_rate": 0.00011428571428571428,
|
| 156 |
+
"loss": 2.8892,
|
| 157 |
"step": 20
|
| 158 |
},
|
| 159 |
{
|
| 160 |
+
"epoch": 0.005993845604959194,
|
| 161 |
+
"grad_norm": 0.6056029796600342,
|
| 162 |
+
"learning_rate": 0.00012,
|
| 163 |
+
"loss": 2.9813,
|
| 164 |
"step": 21
|
| 165 |
},
|
| 166 |
{
|
| 167 |
+
"epoch": 0.006279266824242965,
|
| 168 |
+
"grad_norm": 0.5435022711753845,
|
| 169 |
+
"learning_rate": 0.00012571428571428572,
|
| 170 |
+
"loss": 2.6502,
|
| 171 |
"step": 22
|
| 172 |
},
|
| 173 |
{
|
| 174 |
+
"epoch": 0.006564688043526736,
|
| 175 |
+
"grad_norm": 0.5630282163619995,
|
| 176 |
+
"learning_rate": 0.00013142857142857143,
|
| 177 |
+
"loss": 2.6238,
|
| 178 |
"step": 23
|
| 179 |
},
|
| 180 |
{
|
| 181 |
+
"epoch": 0.006850109262810507,
|
| 182 |
+
"grad_norm": 0.6111990213394165,
|
| 183 |
+
"learning_rate": 0.00013714285714285716,
|
| 184 |
+
"loss": 2.7437,
|
| 185 |
"step": 24
|
| 186 |
},
|
| 187 |
{
|
| 188 |
+
"epoch": 0.007135530482094278,
|
| 189 |
+
"grad_norm": 0.5657336115837097,
|
| 190 |
+
"learning_rate": 0.00014285714285714287,
|
| 191 |
+
"loss": 2.6898,
|
| 192 |
"step": 25
|
| 193 |
},
|
| 194 |
{
|
| 195 |
+
"epoch": 0.007135530482094278,
|
| 196 |
+
"eval_loss": 2.7006003856658936,
|
| 197 |
+
"eval_runtime": 6.6882,
|
| 198 |
+
"eval_samples_per_second": 7.476,
|
| 199 |
+
"eval_steps_per_second": 7.476,
|
| 200 |
"step": 25
|
| 201 |
},
|
| 202 |
{
|
| 203 |
+
"epoch": 0.00742095170137805,
|
| 204 |
+
"grad_norm": 0.5724318623542786,
|
| 205 |
+
"learning_rate": 0.00014857142857142857,
|
| 206 |
+
"loss": 2.6936,
|
| 207 |
"step": 26
|
| 208 |
},
|
| 209 |
{
|
| 210 |
+
"epoch": 0.007706372920661821,
|
| 211 |
+
"grad_norm": 0.47816792130470276,
|
| 212 |
+
"learning_rate": 0.0001542857142857143,
|
| 213 |
+
"loss": 2.6312,
|
| 214 |
"step": 27
|
| 215 |
},
|
| 216 |
{
|
| 217 |
+
"epoch": 0.007991794139945592,
|
| 218 |
+
"grad_norm": 0.5189191102981567,
|
| 219 |
+
"learning_rate": 0.00016,
|
| 220 |
+
"loss": 2.8591,
|
| 221 |
"step": 28
|
| 222 |
},
|
| 223 |
{
|
| 224 |
+
"epoch": 0.008277215359229362,
|
| 225 |
+
"grad_norm": 0.5170201063156128,
|
| 226 |
+
"learning_rate": 0.00016571428571428575,
|
| 227 |
+
"loss": 2.5753,
|
| 228 |
"step": 29
|
| 229 |
},
|
| 230 |
{
|
| 231 |
+
"epoch": 0.008562636578513133,
|
| 232 |
+
"grad_norm": 0.4780126214027405,
|
| 233 |
+
"learning_rate": 0.00017142857142857143,
|
| 234 |
+
"loss": 2.5154,
|
| 235 |
"step": 30
|
| 236 |
},
|
| 237 |
{
|
| 238 |
+
"epoch": 0.008848057797796904,
|
| 239 |
+
"grad_norm": 0.46953848004341125,
|
| 240 |
+
"learning_rate": 0.00017714285714285713,
|
| 241 |
+
"loss": 2.5638,
|
| 242 |
"step": 31
|
| 243 |
},
|
| 244 |
{
|
| 245 |
+
"epoch": 0.009133479017080675,
|
| 246 |
+
"grad_norm": 0.5048589706420898,
|
| 247 |
+
"learning_rate": 0.00018285714285714286,
|
| 248 |
+
"loss": 2.6244,
|
| 249 |
"step": 32
|
| 250 |
},
|
| 251 |
{
|
| 252 |
+
"epoch": 0.009418900236364448,
|
| 253 |
+
"grad_norm": 0.5477012395858765,
|
| 254 |
+
"learning_rate": 0.00018857142857142857,
|
| 255 |
+
"loss": 2.7039,
|
| 256 |
"step": 33
|
| 257 |
},
|
| 258 |
{
|
| 259 |
+
"epoch": 0.009704321455648219,
|
| 260 |
+
"grad_norm": 0.510737955570221,
|
| 261 |
+
"learning_rate": 0.0001942857142857143,
|
| 262 |
+
"loss": 2.6319,
|
| 263 |
"step": 34
|
| 264 |
},
|
| 265 |
{
|
| 266 |
+
"epoch": 0.00998974267493199,
|
| 267 |
+
"grad_norm": 0.5701810121536255,
|
| 268 |
+
"learning_rate": 0.0002,
|
| 269 |
+
"loss": 2.6441,
|
| 270 |
"step": 35
|
| 271 |
},
|
| 272 |
{
|
| 273 |
+
"epoch": 0.01027516389421576,
|
| 274 |
+
"grad_norm": 0.49409958720207214,
|
| 275 |
+
"learning_rate": 0.00019999938960115114,
|
| 276 |
+
"loss": 2.5378,
|
| 277 |
"step": 36
|
| 278 |
},
|
| 279 |
{
|
| 280 |
+
"epoch": 0.010560585113499532,
|
| 281 |
+
"grad_norm": 0.5363864302635193,
|
| 282 |
+
"learning_rate": 0.0001999975584128843,
|
| 283 |
+
"loss": 2.4543,
|
| 284 |
"step": 37
|
| 285 |
},
|
| 286 |
{
|
| 287 |
+
"epoch": 0.010846006332783303,
|
| 288 |
+
"grad_norm": 0.511552095413208,
|
| 289 |
+
"learning_rate": 0.00019999450646003843,
|
| 290 |
+
"loss": 2.6913,
|
| 291 |
"step": 38
|
| 292 |
},
|
| 293 |
{
|
| 294 |
+
"epoch": 0.011131427552067074,
|
| 295 |
+
"grad_norm": 0.568918764591217,
|
| 296 |
+
"learning_rate": 0.0001999902337840116,
|
| 297 |
+
"loss": 2.5901,
|
| 298 |
"step": 39
|
| 299 |
},
|
| 300 |
{
|
| 301 |
+
"epoch": 0.011416848771350845,
|
| 302 |
+
"grad_norm": 0.5946168899536133,
|
| 303 |
+
"learning_rate": 0.00019998474044276,
|
| 304 |
+
"loss": 2.6054,
|
| 305 |
"step": 40
|
| 306 |
},
|
| 307 |
{
|
| 308 |
+
"epoch": 0.011702269990634616,
|
| 309 |
+
"grad_norm": 0.6025540232658386,
|
| 310 |
+
"learning_rate": 0.00019997802651079778,
|
| 311 |
+
"loss": 2.7296,
|
| 312 |
"step": 41
|
| 313 |
},
|
| 314 |
{
|
| 315 |
+
"epoch": 0.011987691209918388,
|
| 316 |
+
"grad_norm": 0.589484453201294,
|
| 317 |
+
"learning_rate": 0.00019997009207919545,
|
| 318 |
+
"loss": 2.6412,
|
| 319 |
"step": 42
|
| 320 |
},
|
| 321 |
{
|
| 322 |
+
"epoch": 0.01227311242920216,
|
| 323 |
+
"grad_norm": 0.6304107308387756,
|
| 324 |
+
"learning_rate": 0.00019996093725557898,
|
| 325 |
+
"loss": 2.6191,
|
| 326 |
"step": 43
|
| 327 |
},
|
| 328 |
{
|
| 329 |
+
"epoch": 0.01255853364848593,
|
| 330 |
+
"grad_norm": 0.6326958537101746,
|
| 331 |
+
"learning_rate": 0.00019995056216412824,
|
| 332 |
+
"loss": 2.5749,
|
| 333 |
"step": 44
|
| 334 |
},
|
| 335 |
{
|
| 336 |
+
"epoch": 0.012843954867769701,
|
| 337 |
+
"grad_norm": 0.6734350919723511,
|
| 338 |
+
"learning_rate": 0.0001999389669455753,
|
| 339 |
+
"loss": 2.7463,
|
| 340 |
"step": 45
|
| 341 |
},
|
| 342 |
{
|
| 343 |
+
"epoch": 0.013129376087053472,
|
| 344 |
+
"grad_norm": 0.6757857203483582,
|
| 345 |
+
"learning_rate": 0.00019992615175720257,
|
| 346 |
+
"loss": 2.4429,
|
| 347 |
"step": 46
|
| 348 |
},
|
| 349 |
{
|
| 350 |
+
"epoch": 0.013414797306337243,
|
| 351 |
+
"grad_norm": 0.687453031539917,
|
| 352 |
+
"learning_rate": 0.00019991211677284062,
|
| 353 |
+
"loss": 2.595,
|
| 354 |
"step": 47
|
| 355 |
},
|
| 356 |
{
|
| 357 |
+
"epoch": 0.013700218525621014,
|
| 358 |
+
"grad_norm": 0.7763611078262329,
|
| 359 |
+
"learning_rate": 0.00019989686218286587,
|
| 360 |
+
"loss": 2.7578,
|
| 361 |
"step": 48
|
| 362 |
},
|
| 363 |
{
|
| 364 |
+
"epoch": 0.013985639744904785,
|
| 365 |
+
"grad_norm": 0.9888719916343689,
|
| 366 |
+
"learning_rate": 0.00019988038819419797,
|
| 367 |
+
"loss": 2.5648,
|
| 368 |
"step": 49
|
| 369 |
},
|
| 370 |
{
|
| 371 |
+
"epoch": 0.014271060964188556,
|
| 372 |
+
"grad_norm": 1.6425894498825073,
|
| 373 |
+
"learning_rate": 0.00019986269503029697,
|
| 374 |
+
"loss": 2.5132,
|
| 375 |
"step": 50
|
| 376 |
},
|
| 377 |
{
|
| 378 |
+
"epoch": 0.014271060964188556,
|
| 379 |
+
"eval_loss": 2.556696653366089,
|
| 380 |
+
"eval_runtime": 6.6833,
|
| 381 |
+
"eval_samples_per_second": 7.481,
|
| 382 |
+
"eval_steps_per_second": 7.481,
|
| 383 |
"step": 50
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 384 |
}
|
| 385 |
],
|
| 386 |
"logging_steps": 1,
|
| 387 |
+
"max_steps": 888,
|
| 388 |
"num_input_tokens_seen": 0,
|
| 389 |
"num_train_epochs": 1,
|
| 390 |
"save_steps": 50,
|
|
|
|
| 409 |
"attributes": {}
|
| 410 |
}
|
| 411 |
},
|
| 412 |
+
"total_flos": 5.593179412129382e+16,
|
| 413 |
+
"train_batch_size": 1,
|
| 414 |
"trial_name": null,
|
| 415 |
"trial_params": null
|
| 416 |
}
|
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 sha256:2c10884f4be4e91add9795afd80f7b25e35f322adac12d6b37b6d44aa702d50c
|
| 3 |
size 6776
|