Training in progress, step 6900, 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:ae50fb16913624ef3c6c3e417ad92f5263de849d4297b7a9b7855b7c1a90aa12
|
| 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:b529112831d3ef3c0a1c58d46db3375d9c615744e36fc10560f30c02e5a59332
|
| 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 sha256:06051ff2563f6929a52be1f2a6173daac8bdf2ae58052429e1cd974260b79ebf
|
| 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 sha256:344062337e3a13dab9ea0f70913ee0c41826ffaef2b21b1cfec0d360964d9faa
|
| 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": 13.
|
| 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,
|
|
@@ -587,6 +587,13 @@
|
|
| 587 |
"learning_rate": 5.466666666666666e-05,
|
| 588 |
"loss": 1.2365,
|
| 589 |
"step": 6800
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 590 |
}
|
| 591 |
],
|
| 592 |
"logging_steps": 100,
|
|
@@ -606,7 +613,7 @@
|
|
| 606 |
"attributes": {}
|
| 607 |
}
|
| 608 |
},
|
| 609 |
-
"total_flos": 1.
|
| 610 |
"train_batch_size": 8,
|
| 611 |
"trial_name": null,
|
| 612 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 13.797844086861428,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 6900,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 587 |
"learning_rate": 5.466666666666666e-05,
|
| 588 |
"loss": 1.2365,
|
| 589 |
"step": 6800
|
| 590 |
+
},
|
| 591 |
+
{
|
| 592 |
+
"epoch": 13.797844086861428,
|
| 593 |
+
"grad_norm": 0.20576031506061554,
|
| 594 |
+
"learning_rate": 5.4000000000000005e-05,
|
| 595 |
+
"loss": 1.236,
|
| 596 |
+
"step": 6900
|
| 597 |
}
|
| 598 |
],
|
| 599 |
"logging_steps": 100,
|
|
|
|
| 613 |
"attributes": {}
|
| 614 |
}
|
| 615 |
},
|
| 616 |
+
"total_flos": 1.0769053972669923e+19,
|
| 617 |
"train_batch_size": 8,
|
| 618 |
"trial_name": null,
|
| 619 |
"trial_params": null
|