Training in progress, step 7080, checkpoint
Browse files
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1657
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:42265afeb804220d37fd083a509345b4ffc59b8d9247363bcd44119e84c55250
|
| 3 |
size 1657
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14709
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aa101db175af77b99d22d392bfe36bb14cf196e0d9ca97b4eea678b4049e32ce
|
| 3 |
size 14709
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1465
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fb2643e933f7846939be769a1fb85052c90bdf7edd54e8ec7bd56a76ceaf2f69
|
| 3 |
size 1465
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -2,9 +2,9 @@
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
-
"epoch": 54.
|
| 6 |
"eval_steps": 500,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -12734,6 +12734,24 @@
|
|
| 12734 |
"mean_token_accuracy": 0.6605098664760589,
|
| 12735 |
"num_tokens": 25787124.0,
|
| 12736 |
"step": 7070
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12737 |
}
|
| 12738 |
],
|
| 12739 |
"logging_steps": 5,
|
|
@@ -12753,7 +12771,7 @@
|
|
| 12753 |
"attributes": {}
|
| 12754 |
}
|
| 12755 |
},
|
| 12756 |
-
"total_flos": 1.
|
| 12757 |
"train_batch_size": 4,
|
| 12758 |
"trial_name": null,
|
| 12759 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 54.46153846153846,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 7080,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 12734 |
"mean_token_accuracy": 0.6605098664760589,
|
| 12735 |
"num_tokens": 25787124.0,
|
| 12736 |
"step": 7070
|
| 12737 |
+
},
|
| 12738 |
+
{
|
| 12739 |
+
"epoch": 54.42307692307692,
|
| 12740 |
+
"grad_norm": 0.0,
|
| 12741 |
+
"learning_rate": 1.4630000000000002e-05,
|
| 12742 |
+
"loss": 1.7444,
|
| 12743 |
+
"mean_token_accuracy": 0.6469592988491059,
|
| 12744 |
+
"num_tokens": 25805583.0,
|
| 12745 |
+
"step": 7075
|
| 12746 |
+
},
|
| 12747 |
+
{
|
| 12748 |
+
"epoch": 54.46153846153846,
|
| 12749 |
+
"grad_norm": 0.0,
|
| 12750 |
+
"learning_rate": 1.4605000000000002e-05,
|
| 12751 |
+
"loss": 1.7117,
|
| 12752 |
+
"mean_token_accuracy": 0.6542593479156494,
|
| 12753 |
+
"num_tokens": 25824061.0,
|
| 12754 |
+
"step": 7080
|
| 12755 |
}
|
| 12756 |
],
|
| 12757 |
"logging_steps": 5,
|
|
|
|
| 12771 |
"attributes": {}
|
| 12772 |
}
|
| 12773 |
},
|
| 12774 |
+
"total_flos": 1.3094176403039846e+18,
|
| 12775 |
"train_batch_size": 4,
|
| 12776 |
"trial_name": null,
|
| 12777 |
"trial_params": null
|