Training in progress, step 9300, 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 sha256:9d301b8926a39e58638685287c9d06da482b4cd1bcaa9e622094f9f2ab3a5e91
|
| 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 sha256:8131748924bcc5c29f1b2cfcba850247db727fbde8ec10d0f5494b31db6ac01d
|
| 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 sha256:823429bce5944771efedf2edd0b241900af0b72e6e3b3e9d8913fdfc17fbcd02
|
| 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": 71.
|
| 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,
|
|
@@ -16730,6 +16730,24 @@
|
|
| 16730 |
"mean_token_accuracy": 0.6527814954519272,
|
| 16731 |
"num_tokens": 33881172.0,
|
| 16732 |
"step": 9290
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 16733 |
}
|
| 16734 |
],
|
| 16735 |
"logging_steps": 5,
|
|
@@ -16749,7 +16767,7 @@
|
|
| 16749 |
"attributes": {}
|
| 16750 |
}
|
| 16751 |
},
|
| 16752 |
-
"total_flos": 1.
|
| 16753 |
"train_batch_size": 4,
|
| 16754 |
"trial_name": null,
|
| 16755 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 71.53846153846153,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 9300,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 16730 |
"mean_token_accuracy": 0.6527814954519272,
|
| 16731 |
"num_tokens": 33881172.0,
|
| 16732 |
"step": 9290
|
| 16733 |
+
},
|
| 16734 |
+
{
|
| 16735 |
+
"epoch": 71.5,
|
| 16736 |
+
"grad_norm": 0.0,
|
| 16737 |
+
"learning_rate": 3.53e-06,
|
| 16738 |
+
"loss": 1.6943,
|
| 16739 |
+
"mean_token_accuracy": 0.661613667011261,
|
| 16740 |
+
"num_tokens": 33899656.0,
|
| 16741 |
+
"step": 9295
|
| 16742 |
+
},
|
| 16743 |
+
{
|
| 16744 |
+
"epoch": 71.53846153846153,
|
| 16745 |
+
"grad_norm": 0.0,
|
| 16746 |
+
"learning_rate": 3.505e-06,
|
| 16747 |
+
"loss": 1.7055,
|
| 16748 |
+
"mean_token_accuracy": 0.647359648346901,
|
| 16749 |
+
"num_tokens": 33918686.0,
|
| 16750 |
+
"step": 9300
|
| 16751 |
}
|
| 16752 |
],
|
| 16753 |
"logging_steps": 5,
|
|
|
|
| 16767 |
"attributes": {}
|
| 16768 |
}
|
| 16769 |
},
|
| 16770 |
+
"total_flos": 1.7199862161850368e+18,
|
| 16771 |
"train_batch_size": 4,
|
| 16772 |
"trial_name": null,
|
| 16773 |
"trial_params": null
|