Training in progress, step 3700, checkpoint
Browse files
last-checkpoint/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 8137792
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:94352bb286002b5de8d47b18622740886178c34a156c4609a6f45691ff44c981
|
| 3 |
size 8137792
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 16386426
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ef468f68a96521f6bee7c692e468dc10c41c752b1607c9ac9814858346421297
|
| 3 |
size 16386426
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15006
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:febb26adf02b9e52f8f87bd7852971cd3a0f9cf9148f2e6994932af620362dcf
|
| 3 |
size 15006
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1064
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b1f401d1a194070902a8068e17d1a8fd51a2d77e7384e27a0135c57b9ff89743
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch": 7.
|
| 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,
|
|
@@ -315,6 +315,13 @@
|
|
| 315 |
"learning_rate": 7.6e-05,
|
| 316 |
"loss": 1.2688,
|
| 317 |
"step": 3600
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 318 |
}
|
| 319 |
],
|
| 320 |
"logging_steps": 100,
|
|
@@ -334,7 +341,7 @@
|
|
| 334 |
"attributes": {}
|
| 335 |
}
|
| 336 |
},
|
| 337 |
-
"total_flos": 5.
|
| 338 |
"train_batch_size": 8,
|
| 339 |
"trial_name": null,
|
| 340 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 7.398843930635838,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 3700,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 315 |
"learning_rate": 7.6e-05,
|
| 316 |
"loss": 1.2688,
|
| 317 |
"step": 3600
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 7.398843930635838,
|
| 321 |
+
"grad_norm": 0.18176878988742828,
|
| 322 |
+
"learning_rate": 7.533333333333334e-05,
|
| 323 |
+
"loss": 1.2622,
|
| 324 |
+
"step": 3700
|
| 325 |
}
|
| 326 |
],
|
| 327 |
"logging_steps": 100,
|
|
|
|
| 341 |
"attributes": {}
|
| 342 |
}
|
| 343 |
},
|
| 344 |
+
"total_flos": 5.774709835870241e+18,
|
| 345 |
"train_batch_size": 8,
|
| 346 |
"trial_name": null,
|
| 347 |
"trial_params": null
|