Training in progress, step 2500, 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 891558696
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3d253ddcfd4df2acb84a6afc37ea897625fd4823975484b2722f1d732a807a42
|
| 3 |
size 891558696
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1783272762
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:80072666b3be47f53f317ccfe6322071cfa6706038da8de25f13ce6816f3172e
|
| 3 |
size 1783272762
|
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 sha256:2f2667454d6cffb59aea7917c33b6757bc9e126470ce377cf6d3d3b895b28bce
|
| 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:f9e7d6d8721d0efdf284e8ea86037aff29ca12a45581cd9384185af5e287f2cf
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 0.
|
| 3 |
-
"best_model_checkpoint": "./fine-tuned/checkpoint-
|
| 4 |
-
"epoch": 0.
|
| 5 |
"eval_steps": 500,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -81,9 +81,9 @@
|
|
| 81 |
{
|
| 82 |
"epoch": 0.08,
|
| 83 |
"eval_loss": 0.09235642850399017,
|
| 84 |
-
"eval_runtime":
|
| 85 |
-
"eval_samples_per_second":
|
| 86 |
-
"eval_steps_per_second": 2.
|
| 87 |
"step": 500
|
| 88 |
},
|
| 89 |
{
|
|
@@ -159,9 +159,9 @@
|
|
| 159 |
{
|
| 160 |
"epoch": 0.16,
|
| 161 |
"eval_loss": 0.08949962258338928,
|
| 162 |
-
"eval_runtime":
|
| 163 |
-
"eval_samples_per_second":
|
| 164 |
-
"eval_steps_per_second": 2.
|
| 165 |
"step": 1000
|
| 166 |
},
|
| 167 |
{
|
|
@@ -237,9 +237,9 @@
|
|
| 237 |
{
|
| 238 |
"epoch": 0.24,
|
| 239 |
"eval_loss": 0.08808805048465729,
|
| 240 |
-
"eval_runtime":
|
| 241 |
-
"eval_samples_per_second":
|
| 242 |
-
"eval_steps_per_second": 2.
|
| 243 |
"step": 1500
|
| 244 |
},
|
| 245 |
{
|
|
@@ -315,10 +315,88 @@
|
|
| 315 |
{
|
| 316 |
"epoch": 0.32,
|
| 317 |
"eval_loss": 0.08704760670661926,
|
| 318 |
-
"eval_runtime":
|
| 319 |
-
"eval_samples_per_second":
|
| 320 |
-
"eval_steps_per_second": 2.
|
| 321 |
"step": 2000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 322 |
}
|
| 323 |
],
|
| 324 |
"logging_steps": 50,
|
|
@@ -338,7 +416,7 @@
|
|
| 338 |
"attributes": {}
|
| 339 |
}
|
| 340 |
},
|
| 341 |
-
"total_flos":
|
| 342 |
"train_batch_size": 8,
|
| 343 |
"trial_name": null,
|
| 344 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.08615937829017639,
|
| 3 |
+
"best_model_checkpoint": "./fine-tuned/checkpoint-2500",
|
| 4 |
+
"epoch": 0.4,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 2500,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 81 |
{
|
| 82 |
"epoch": 0.08,
|
| 83 |
"eval_loss": 0.09235642850399017,
|
| 84 |
+
"eval_runtime": 109.274,
|
| 85 |
+
"eval_samples_per_second": 18.303,
|
| 86 |
+
"eval_steps_per_second": 2.288,
|
| 87 |
"step": 500
|
| 88 |
},
|
| 89 |
{
|
|
|
|
| 159 |
{
|
| 160 |
"epoch": 0.16,
|
| 161 |
"eval_loss": 0.08949962258338928,
|
| 162 |
+
"eval_runtime": 109.2536,
|
| 163 |
+
"eval_samples_per_second": 18.306,
|
| 164 |
+
"eval_steps_per_second": 2.288,
|
| 165 |
"step": 1000
|
| 166 |
},
|
| 167 |
{
|
|
|
|
| 237 |
{
|
| 238 |
"epoch": 0.24,
|
| 239 |
"eval_loss": 0.08808805048465729,
|
| 240 |
+
"eval_runtime": 109.2355,
|
| 241 |
+
"eval_samples_per_second": 18.309,
|
| 242 |
+
"eval_steps_per_second": 2.289,
|
| 243 |
"step": 1500
|
| 244 |
},
|
| 245 |
{
|
|
|
|
| 315 |
{
|
| 316 |
"epoch": 0.32,
|
| 317 |
"eval_loss": 0.08704760670661926,
|
| 318 |
+
"eval_runtime": 109.4348,
|
| 319 |
+
"eval_samples_per_second": 18.276,
|
| 320 |
+
"eval_steps_per_second": 2.284,
|
| 321 |
"step": 2000
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 0.328,
|
| 325 |
+
"grad_norm": 6016.46826171875,
|
| 326 |
+
"learning_rate": 2.672e-05,
|
| 327 |
+
"loss": 0.0663,
|
| 328 |
+
"step": 2050
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 0.336,
|
| 332 |
+
"grad_norm": 6869.53076171875,
|
| 333 |
+
"learning_rate": 2.6640000000000002e-05,
|
| 334 |
+
"loss": 0.073,
|
| 335 |
+
"step": 2100
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 0.344,
|
| 339 |
+
"grad_norm": 6099.595703125,
|
| 340 |
+
"learning_rate": 2.656e-05,
|
| 341 |
+
"loss": 0.0667,
|
| 342 |
+
"step": 2150
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 0.352,
|
| 346 |
+
"grad_norm": 6923.919921875,
|
| 347 |
+
"learning_rate": 2.648e-05,
|
| 348 |
+
"loss": 0.0653,
|
| 349 |
+
"step": 2200
|
| 350 |
+
},
|
| 351 |
+
{
|
| 352 |
+
"epoch": 0.36,
|
| 353 |
+
"grad_norm": 8005.85595703125,
|
| 354 |
+
"learning_rate": 2.64e-05,
|
| 355 |
+
"loss": 0.0685,
|
| 356 |
+
"step": 2250
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 0.368,
|
| 360 |
+
"grad_norm": 6473.466796875,
|
| 361 |
+
"learning_rate": 2.632e-05,
|
| 362 |
+
"loss": 0.0678,
|
| 363 |
+
"step": 2300
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 0.376,
|
| 367 |
+
"grad_norm": 7177.6328125,
|
| 368 |
+
"learning_rate": 2.6240000000000003e-05,
|
| 369 |
+
"loss": 0.0637,
|
| 370 |
+
"step": 2350
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 0.384,
|
| 374 |
+
"grad_norm": 5574.75439453125,
|
| 375 |
+
"learning_rate": 2.616e-05,
|
| 376 |
+
"loss": 0.0698,
|
| 377 |
+
"step": 2400
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 0.392,
|
| 381 |
+
"grad_norm": 6910.39599609375,
|
| 382 |
+
"learning_rate": 2.608e-05,
|
| 383 |
+
"loss": 0.0645,
|
| 384 |
+
"step": 2450
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 0.4,
|
| 388 |
+
"grad_norm": 5913.9775390625,
|
| 389 |
+
"learning_rate": 2.6000000000000002e-05,
|
| 390 |
+
"loss": 0.068,
|
| 391 |
+
"step": 2500
|
| 392 |
+
},
|
| 393 |
+
{
|
| 394 |
+
"epoch": 0.4,
|
| 395 |
+
"eval_loss": 0.08615937829017639,
|
| 396 |
+
"eval_runtime": 109.2621,
|
| 397 |
+
"eval_samples_per_second": 18.305,
|
| 398 |
+
"eval_steps_per_second": 2.288,
|
| 399 |
+
"step": 2500
|
| 400 |
}
|
| 401 |
],
|
| 402 |
"logging_steps": 50,
|
|
|
|
| 416 |
"attributes": {}
|
| 417 |
}
|
| 418 |
},
|
| 419 |
+
"total_flos": 1.21791578112e+16,
|
| 420 |
"train_batch_size": 8,
|
| 421 |
"trial_name": null,
|
| 422 |
"trial_params": null
|