Training in progress, step 8690, 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 sha256:50d3e9ba44efab12fe25c02e567a41c06de65d6b7f5d9fc624fdd6d1d73597cc
|
| 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 sha256:8eccd57cc03a59a61b2c5e295944a25ca007779f3ad15ff6b42c07a65783c187
|
| 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 sha256:30e2b70c1a5be73196ed3a872efcfa909a0c3ff6b48e6e02572188fca792cc14
|
| 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": 66.
|
| 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,
|
|
@@ -15632,6 +15632,24 @@
|
|
| 15632 |
"mean_token_accuracy": 0.6654472947120667,
|
| 15633 |
"num_tokens": 31657320.0,
|
| 15634 |
"step": 8680
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 15635 |
}
|
| 15636 |
],
|
| 15637 |
"logging_steps": 5,
|
|
@@ -15651,7 +15669,7 @@
|
|
| 15651 |
"attributes": {}
|
| 15652 |
}
|
| 15653 |
},
|
| 15654 |
-
"total_flos": 1.
|
| 15655 |
"train_batch_size": 4,
|
| 15656 |
"trial_name": null,
|
| 15657 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 66.84615384615384,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 8690,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 15632 |
"mean_token_accuracy": 0.6654472947120667,
|
| 15633 |
"num_tokens": 31657320.0,
|
| 15634 |
"step": 8680
|
| 15635 |
+
},
|
| 15636 |
+
{
|
| 15637 |
+
"epoch": 66.8076923076923,
|
| 15638 |
+
"grad_norm": 0.0,
|
| 15639 |
+
"learning_rate": 6.58e-06,
|
| 15640 |
+
"loss": 1.7904,
|
| 15641 |
+
"mean_token_accuracy": 0.6401758790016174,
|
| 15642 |
+
"num_tokens": 31674990.0,
|
| 15643 |
+
"step": 8685
|
| 15644 |
+
},
|
| 15645 |
+
{
|
| 15646 |
+
"epoch": 66.84615384615384,
|
| 15647 |
+
"grad_norm": 0.0,
|
| 15648 |
+
"learning_rate": 6.555e-06,
|
| 15649 |
+
"loss": 1.7889,
|
| 15650 |
+
"mean_token_accuracy": 0.6432503432035446,
|
| 15651 |
+
"num_tokens": 31692632.0,
|
| 15652 |
+
"step": 8690
|
| 15653 |
}
|
| 15654 |
],
|
| 15655 |
"logging_steps": 5,
|
|
|
|
| 15669 |
"attributes": {}
|
| 15670 |
}
|
| 15671 |
},
|
| 15672 |
+
"total_flos": 1.6069962764751667e+18,
|
| 15673 |
"train_batch_size": 4,
|
| 15674 |
"trial_name": null,
|
| 15675 |
"trial_params": null
|