Training in progress, step 5100, 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:c4dc78a06614b74f2b7993cd2f4ad16e3daecd08d36efab1e342631d48b9793a
|
| 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:e033f05ae018b75c2c7b5b237f01e0f1e6386139b7bb3a6a878d149aebe6d4f8
|
| 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 sha256:9362e68e86622bc0c486fa360901e87403d41efefa49dfa18c3cc0346850378d
|
| 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:cbfc4e557ce12b317d9b824c5de2de360b0c6c861af7a535f3a5a58e102dd318
|
| 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,
|
|
@@ -437,6 +437,13 @@
|
|
| 437 |
"eval_samples_per_second": 19.914,
|
| 438 |
"eval_steps_per_second": 2.49,
|
| 439 |
"step": 5000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 440 |
}
|
| 441 |
],
|
| 442 |
"logging_steps": 100,
|
|
@@ -456,7 +463,7 @@
|
|
| 456 |
"attributes": {}
|
| 457 |
}
|
| 458 |
},
|
| 459 |
-
"total_flos": 7.
|
| 460 |
"train_batch_size": 8,
|
| 461 |
"trial_name": null,
|
| 462 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 10.198406498984534,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 5100,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 437 |
"eval_samples_per_second": 19.914,
|
| 438 |
"eval_steps_per_second": 2.49,
|
| 439 |
"step": 5000
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 10.198406498984534,
|
| 443 |
+
"grad_norm": 0.19540326297283173,
|
| 444 |
+
"learning_rate": 6.6e-05,
|
| 445 |
+
"loss": 1.2515,
|
| 446 |
+
"step": 5100
|
| 447 |
}
|
| 448 |
],
|
| 449 |
"logging_steps": 100,
|
|
|
|
| 463 |
"attributes": {}
|
| 464 |
}
|
| 465 |
},
|
| 466 |
+
"total_flos": 7.959731961893749e+18,
|
| 467 |
"train_batch_size": 8,
|
| 468 |
"trial_name": null,
|
| 469 |
"trial_params": null
|