Training in progress, step 920, 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:f1de6d284c603a128647b397e866d7f82ac2242bca19ac3732e4ab39d14422c2
|
| 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 sha256:47b695192f416d70327dc1e7eb8086c7226b121e1dca1650ddbbd17f7072f2fe
|
| 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 sha256:3da3f24a2139c760f80dc2eb8e610c1e4c9d83314ba0a96904eddffc9e632c85
|
| 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": 7.
|
| 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,
|
|
@@ -1646,6 +1646,24 @@
|
|
| 1646 |
"mean_token_accuracy": 0.6568648606538773,
|
| 1647 |
"num_tokens": 3318735.0,
|
| 1648 |
"step": 910
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1649 |
}
|
| 1650 |
],
|
| 1651 |
"logging_steps": 5,
|
|
@@ -1665,7 +1683,7 @@
|
|
| 1665 |
"attributes": {}
|
| 1666 |
}
|
| 1667 |
},
|
| 1668 |
-
"total_flos": 1.
|
| 1669 |
"train_batch_size": 4,
|
| 1670 |
"trial_name": null,
|
| 1671 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 7.076923076923077,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 920,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 1646 |
"mean_token_accuracy": 0.6568648606538773,
|
| 1647 |
"num_tokens": 3318735.0,
|
| 1648 |
"step": 910
|
| 1649 |
+
},
|
| 1650 |
+
{
|
| 1651 |
+
"epoch": 7.038461538461538,
|
| 1652 |
+
"grad_norm": 0.0,
|
| 1653 |
+
"learning_rate": 4.543e-05,
|
| 1654 |
+
"loss": 1.6958,
|
| 1655 |
+
"mean_token_accuracy": 0.657955089211464,
|
| 1656 |
+
"num_tokens": 3337799.0,
|
| 1657 |
+
"step": 915
|
| 1658 |
+
},
|
| 1659 |
+
{
|
| 1660 |
+
"epoch": 7.076923076923077,
|
| 1661 |
+
"grad_norm": 0.0,
|
| 1662 |
+
"learning_rate": 4.5405e-05,
|
| 1663 |
+
"loss": 1.704,
|
| 1664 |
+
"mean_token_accuracy": 0.6572122246026992,
|
| 1665 |
+
"num_tokens": 3356448.0,
|
| 1666 |
+
"step": 920
|
| 1667 |
}
|
| 1668 |
],
|
| 1669 |
"logging_steps": 5,
|
|
|
|
| 1683 |
"attributes": {}
|
| 1684 |
}
|
| 1685 |
},
|
| 1686 |
+
"total_flos": 1.7012677426348032e+17,
|
| 1687 |
"train_batch_size": 4,
|
| 1688 |
"trial_name": null,
|
| 1689 |
"trial_params": null
|