Training in progress, step 4600, 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 sha256:2c3e1f7c44595c4b675935ad3d8674639177cdcee47be9824ea47769e81aaf09
|
| 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 sha256:5aa550e0c728bb2e8f76c3a9ad45f42c0f8e7aa63842ec6c3a3e99b6a881237b
|
| 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:ec099fcb75a906dcf1c83a48565cc08ac15daac4d5acd594720d9e43a3d79ab9
|
| 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 sha256:90219fa8302fe36d5d4dff8e94b61a15005b7b2e9b028b16ed94ebbdb7a97185
|
| 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":
|
| 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,
|
|
@@ -394,6 +394,13 @@
|
|
| 394 |
"eval_samples_per_second": 19.845,
|
| 395 |
"eval_steps_per_second": 2.482,
|
| 396 |
"step": 4500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 397 |
}
|
| 398 |
],
|
| 399 |
"logging_steps": 100,
|
|
@@ -413,7 +420,7 @@
|
|
| 413 |
"attributes": {}
|
| 414 |
}
|
| 415 |
},
|
| 416 |
-
"total_flos": 7.
|
| 417 |
"train_batch_size": 8,
|
| 418 |
"trial_name": null,
|
| 419 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 9.198562724574286,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 4600,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 394 |
"eval_samples_per_second": 19.845,
|
| 395 |
"eval_steps_per_second": 2.482,
|
| 396 |
"step": 4500
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 9.198562724574286,
|
| 400 |
+
"grad_norm": 0.189661905169487,
|
| 401 |
+
"learning_rate": 6.933333333333334e-05,
|
| 402 |
+
"loss": 1.2599,
|
| 403 |
+
"step": 4600
|
| 404 |
}
|
| 405 |
],
|
| 406 |
"logging_steps": 100,
|
|
|
|
| 420 |
"attributes": {}
|
| 421 |
}
|
| 422 |
},
|
| 423 |
+
"total_flos": 7.179366262823191e+18,
|
| 424 |
"train_batch_size": 8,
|
| 425 |
"trial_name": null,
|
| 426 |
"trial_params": null
|