Training in progress, step 930, 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 sha256:68db7347c4f600e101a1cdb0e9eb3423ca6e775c14fac84114be3fb375ab0f4c
|
| 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 sha256:0ef367bc1b52871a502e5eddcda363226a16889cce4e938bc6367ab6c8f511c3
|
| 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 sha256:8b0fcd79bec8b4e4efb7be004ff430f7ab5f0cc9e1ea7a43ad5d778f74e3111b
|
| 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,
|
|
@@ -1664,6 +1664,24 @@
|
|
| 1664 |
"mean_token_accuracy": 0.6572122246026992,
|
| 1665 |
"num_tokens": 3356448.0,
|
| 1666 |
"step": 920
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1667 |
}
|
| 1668 |
],
|
| 1669 |
"logging_steps": 5,
|
|
@@ -1683,7 +1701,7 @@
|
|
| 1683 |
"attributes": {}
|
| 1684 |
}
|
| 1685 |
},
|
| 1686 |
-
"total_flos": 1.
|
| 1687 |
"train_batch_size": 4,
|
| 1688 |
"trial_name": null,
|
| 1689 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 7.153846153846154,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 930,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 1664 |
"mean_token_accuracy": 0.6572122246026992,
|
| 1665 |
"num_tokens": 3356448.0,
|
| 1666 |
"step": 920
|
| 1667 |
+
},
|
| 1668 |
+
{
|
| 1669 |
+
"epoch": 7.115384615384615,
|
| 1670 |
+
"grad_norm": 0.0,
|
| 1671 |
+
"learning_rate": 4.538e-05,
|
| 1672 |
+
"loss": 1.7811,
|
| 1673 |
+
"mean_token_accuracy": 0.6435384958982467,
|
| 1674 |
+
"num_tokens": 3374165.0,
|
| 1675 |
+
"step": 925
|
| 1676 |
+
},
|
| 1677 |
+
{
|
| 1678 |
+
"epoch": 7.153846153846154,
|
| 1679 |
+
"grad_norm": 0.0,
|
| 1680 |
+
"learning_rate": 4.5355e-05,
|
| 1681 |
+
"loss": 1.7932,
|
| 1682 |
+
"mean_token_accuracy": 0.643210482597351,
|
| 1683 |
+
"num_tokens": 3391722.0,
|
| 1684 |
+
"step": 930
|
| 1685 |
}
|
| 1686 |
],
|
| 1687 |
"logging_steps": 5,
|
|
|
|
| 1701 |
"attributes": {}
|
| 1702 |
}
|
| 1703 |
},
|
| 1704 |
+
"total_flos": 1.7187572655931392e+17,
|
| 1705 |
"train_batch_size": 4,
|
| 1706 |
"trial_name": null,
|
| 1707 |
"trial_params": null
|