Training in progress, step 6530, 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:fdd18734f36ef7fdf64b95672b1b904103a3bf865bf07e5d860260945d773e9a
|
| 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 sha256:87a014122b9535356372489d0a53e79f75f143cde67f44fdbb9be8cf2055bc0f
|
| 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:c5da4ec5d976a58baed396fc429f746b27c313f8c9b1a5258264e77b572e2c15
|
| 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": 50.
|
| 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,
|
|
@@ -11744,6 +11744,24 @@
|
|
| 11744 |
"mean_token_accuracy": 0.6426906883716583,
|
| 11745 |
"num_tokens": 23776842.0,
|
| 11746 |
"step": 6520
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11747 |
}
|
| 11748 |
],
|
| 11749 |
"logging_steps": 5,
|
|
@@ -11763,7 +11781,7 @@
|
|
| 11763 |
"attributes": {}
|
| 11764 |
}
|
| 11765 |
},
|
| 11766 |
-
"total_flos": 1.
|
| 11767 |
"train_batch_size": 4,
|
| 11768 |
"trial_name": null,
|
| 11769 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 50.23076923076923,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 6530,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 11744 |
"mean_token_accuracy": 0.6426906883716583,
|
| 11745 |
"num_tokens": 23776842.0,
|
| 11746 |
"step": 6520
|
| 11747 |
+
},
|
| 11748 |
+
{
|
| 11749 |
+
"epoch": 50.19230769230769,
|
| 11750 |
+
"grad_norm": 0.0,
|
| 11751 |
+
"learning_rate": 1.7380000000000003e-05,
|
| 11752 |
+
"loss": 1.7058,
|
| 11753 |
+
"mean_token_accuracy": 0.6551610261201859,
|
| 11754 |
+
"num_tokens": 23795678.0,
|
| 11755 |
+
"step": 6525
|
| 11756 |
+
},
|
| 11757 |
+
{
|
| 11758 |
+
"epoch": 50.23076923076923,
|
| 11759 |
+
"grad_norm": 0.0,
|
| 11760 |
+
"learning_rate": 1.7355000000000002e-05,
|
| 11761 |
+
"loss": 1.713,
|
| 11762 |
+
"mean_token_accuracy": 0.6565469861030578,
|
| 11763 |
+
"num_tokens": 23814122.0,
|
| 11764 |
+
"step": 6530
|
| 11765 |
}
|
| 11766 |
],
|
| 11767 |
"logging_steps": 5,
|
|
|
|
| 11781 |
"attributes": {}
|
| 11782 |
}
|
| 11783 |
},
|
| 11784 |
+
"total_flos": 1.2073005789703373e+18,
|
| 11785 |
"train_batch_size": 4,
|
| 11786 |
"trial_name": null,
|
| 11787 |
"trial_params": null
|