Training in progress, step 6600, 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 sha256:226037ed51cf29e6f6935fb9d02b9519ae8399e61d0390414abca43439cb221e
|
| 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 sha256:0f78e827128328b26bd32b2788df0b37c2318816793f3ff6b2eb7ed84608617a
|
| 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:c09c310a0528966f266e76b53c9c860757191aa5e44426565ec75c5d5191507e
|
| 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 sha256:48fe23598f3b0b18ba0b0f25ee605e0d1b66a506b5230afe424ad4c433c9275d
|
| 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,
|
|
@@ -566,6 +566,13 @@
|
|
| 566 |
"eval_samples_per_second": 19.917,
|
| 567 |
"eval_steps_per_second": 2.491,
|
| 568 |
"step": 6500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 569 |
}
|
| 570 |
],
|
| 571 |
"logging_steps": 100,
|
|
@@ -585,7 +592,7 @@
|
|
| 585 |
"attributes": {}
|
| 586 |
}
|
| 587 |
},
|
| 588 |
-
"total_flos": 1.
|
| 589 |
"train_batch_size": 8,
|
| 590 |
"trial_name": null,
|
| 591 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 13.197937822215279,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 6600,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 566 |
"eval_samples_per_second": 19.917,
|
| 567 |
"eval_steps_per_second": 2.491,
|
| 568 |
"step": 6500
|
| 569 |
+
},
|
| 570 |
+
{
|
| 571 |
+
"epoch": 13.197937822215279,
|
| 572 |
+
"grad_norm": 0.20639556646347046,
|
| 573 |
+
"learning_rate": 5.6000000000000006e-05,
|
| 574 |
+
"loss": 1.2461,
|
| 575 |
+
"step": 6600
|
| 576 |
}
|
| 577 |
],
|
| 578 |
"logging_steps": 100,
|
|
|
|
| 592 |
"attributes": {}
|
| 593 |
}
|
| 594 |
},
|
| 595 |
+
"total_flos": 1.0300829059105423e+19,
|
| 596 |
"train_batch_size": 8,
|
| 597 |
"trial_name": null,
|
| 598 |
"trial_params": null
|