Training in progress, step 8100, 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 sha256:7887c8051384a117232d99101066172a916a5bfcceca250562323a4627c2cd96
|
| 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 sha256:6fb4df708ee8b6821cebe083367e9a6748aa1bb5e013a3e2941450fc0f86ce44
|
| 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 sha256:97b648da67b4f3b6a4de3641df5b07a88978483643f88f93aafc0ba059496f04
|
| 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 sha256:82d63c10456a4a292f1cca78fc49696869546259e06c702322f086a8b2df3e48
|
| 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,
|
|
@@ -695,6 +695,13 @@
|
|
| 695 |
"eval_samples_per_second": 19.86,
|
| 696 |
"eval_steps_per_second": 2.483,
|
| 697 |
"step": 8000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 698 |
}
|
| 699 |
],
|
| 700 |
"logging_steps": 100,
|
|
@@ -714,7 +721,7 @@
|
|
| 714 |
"attributes": {}
|
| 715 |
}
|
| 716 |
},
|
| 717 |
-
"total_flos": 1.
|
| 718 |
"train_batch_size": 8,
|
| 719 |
"trial_name": null,
|
| 720 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 16.197469145446025,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 8100,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 695 |
"eval_samples_per_second": 19.86,
|
| 696 |
"eval_steps_per_second": 2.483,
|
| 697 |
"step": 8000
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 16.197469145446025,
|
| 701 |
+
"grad_norm": 0.21470457315444946,
|
| 702 |
+
"learning_rate": 4.600000000000001e-05,
|
| 703 |
+
"loss": 1.2356,
|
| 704 |
+
"step": 8100
|
| 705 |
}
|
| 706 |
],
|
| 707 |
"logging_steps": 100,
|
|
|
|
| 721 |
"attributes": {}
|
| 722 |
}
|
| 723 |
},
|
| 724 |
+
"total_flos": 1.2641926156317098e+19,
|
| 725 |
"train_batch_size": 8,
|
| 726 |
"trial_name": null,
|
| 727 |
"trial_params": null
|