Training in progress, step 3130, 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:f58ad5217662a2637b0c471c450b884073d39383023825e11bbc9ff845312305
|
| 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:e115e2bb5456ce31a026dfaf3dec5099f3900bdf3ee797ee49ff9675c63a44d7
|
| 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:d962eb97fd0480a3fe3d84790cc24bb6709855e5a08ab216118c35e76de3639c
|
| 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": 24.
|
| 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,
|
|
@@ -5624,6 +5624,24 @@
|
|
| 5624 |
"mean_token_accuracy": 0.6377548843622207,
|
| 5625 |
"num_tokens": 11378520.0,
|
| 5626 |
"step": 3120
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5627 |
}
|
| 5628 |
],
|
| 5629 |
"logging_steps": 5,
|
|
@@ -5643,7 +5661,7 @@
|
|
| 5643 |
"attributes": {}
|
| 5644 |
}
|
| 5645 |
},
|
| 5646 |
-
"total_flos": 5.
|
| 5647 |
"train_batch_size": 4,
|
| 5648 |
"trial_name": null,
|
| 5649 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 24.076923076923077,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 3130,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 5624 |
"mean_token_accuracy": 0.6377548843622207,
|
| 5625 |
"num_tokens": 11378520.0,
|
| 5626 |
"step": 3120
|
| 5627 |
+
},
|
| 5628 |
+
{
|
| 5629 |
+
"epoch": 24.03846153846154,
|
| 5630 |
+
"grad_norm": 0.0,
|
| 5631 |
+
"learning_rate": 3.438e-05,
|
| 5632 |
+
"loss": 1.7197,
|
| 5633 |
+
"mean_token_accuracy": 0.6562131911516189,
|
| 5634 |
+
"num_tokens": 11397124.0,
|
| 5635 |
+
"step": 3125
|
| 5636 |
+
},
|
| 5637 |
+
{
|
| 5638 |
+
"epoch": 24.076923076923077,
|
| 5639 |
+
"grad_norm": 0.0,
|
| 5640 |
+
"learning_rate": 3.4355000000000006e-05,
|
| 5641 |
+
"loss": 1.7154,
|
| 5642 |
+
"mean_token_accuracy": 0.6540484815835953,
|
| 5643 |
+
"num_tokens": 11415431.0,
|
| 5644 |
+
"step": 3130
|
| 5645 |
}
|
| 5646 |
],
|
| 5647 |
"logging_steps": 5,
|
|
|
|
| 5661 |
"attributes": {}
|
| 5662 |
}
|
| 5663 |
},
|
| 5664 |
+
"total_flos": 5.784894314658202e+17,
|
| 5665 |
"train_batch_size": 4,
|
| 5666 |
"trial_name": null,
|
| 5667 |
"trial_params": null
|