Training in progress, step 8300, 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:e7256029a6162e4f64306fa23243bf7daba852c3640c4726be63fd02632e8c32
|
| 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:d12aa4b7001cc9749aa710a943f8e6b8973659de0f7da5fd0f4bad4604960548
|
| 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 sha256:07015d81ff39bf85d96ef132cdb68c77d2ee722963d60d84f65e636d3ca65467
|
| 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:fbc076ace1fa163b5ff586c7a411d4a53b209d1441df1cfce60a1dcc812e6664
|
| 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": 16.
|
| 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,
|
|
@@ -709,6 +709,13 @@
|
|
| 709 |
"learning_rate": 4.5333333333333335e-05,
|
| 710 |
"loss": 1.2298,
|
| 711 |
"step": 8200
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 712 |
}
|
| 713 |
],
|
| 714 |
"logging_steps": 100,
|
|
@@ -728,7 +735,7 @@
|
|
| 728 |
"attributes": {}
|
| 729 |
}
|
| 730 |
},
|
| 731 |
-
"total_flos": 1.
|
| 732 |
"train_batch_size": 8,
|
| 733 |
"trial_name": null,
|
| 734 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 16.597406655210122,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 8300,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 709 |
"learning_rate": 4.5333333333333335e-05,
|
| 710 |
"loss": 1.2298,
|
| 711 |
"step": 8200
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 16.597406655210122,
|
| 715 |
+
"grad_norm": 0.22766882181167603,
|
| 716 |
+
"learning_rate": 4.466666666666667e-05,
|
| 717 |
+
"loss": 1.2344,
|
| 718 |
+
"step": 8300
|
| 719 |
}
|
| 720 |
],
|
| 721 |
"logging_steps": 100,
|
|
|
|
| 735 |
"attributes": {}
|
| 736 |
}
|
| 737 |
},
|
| 738 |
+
"total_flos": 1.2954076098693431e+19,
|
| 739 |
"train_batch_size": 8,
|
| 740 |
"trial_name": null,
|
| 741 |
"trial_params": null
|