Training in progress, step 940, 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 sha256:992f5f39cd5a689d7dff26ae32b3c501c3483f1bb321175bc4bf6c793abfbc68
|
| 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 sha256:0b981b784606c1e118f74f5fd046555c9b2413350b3ebb522bd416770084e9cc
|
| 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 sha256:86203269507ac9bd34eee662ab5fab820b5e95894d3c10db2c440dc01b179c75
|
| 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,
|
|
@@ -1682,6 +1682,24 @@
|
|
| 1682 |
"mean_token_accuracy": 0.643210482597351,
|
| 1683 |
"num_tokens": 3391722.0,
|
| 1684 |
"step": 930
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1685 |
}
|
| 1686 |
],
|
| 1687 |
"logging_steps": 5,
|
|
@@ -1701,7 +1719,7 @@
|
|
| 1701 |
"attributes": {}
|
| 1702 |
}
|
| 1703 |
},
|
| 1704 |
-
"total_flos": 1.
|
| 1705 |
"train_batch_size": 4,
|
| 1706 |
"trial_name": null,
|
| 1707 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 7.230769230769231,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 940,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 1682 |
"mean_token_accuracy": 0.643210482597351,
|
| 1683 |
"num_tokens": 3391722.0,
|
| 1684 |
"step": 930
|
| 1685 |
+
},
|
| 1686 |
+
{
|
| 1687 |
+
"epoch": 7.1923076923076925,
|
| 1688 |
+
"grad_norm": 0.0,
|
| 1689 |
+
"learning_rate": 4.533e-05,
|
| 1690 |
+
"loss": 1.7659,
|
| 1691 |
+
"mean_token_accuracy": 0.6444118946790696,
|
| 1692 |
+
"num_tokens": 3409413.0,
|
| 1693 |
+
"step": 935
|
| 1694 |
+
},
|
| 1695 |
+
{
|
| 1696 |
+
"epoch": 7.230769230769231,
|
| 1697 |
+
"grad_norm": 0.0,
|
| 1698 |
+
"learning_rate": 4.5305e-05,
|
| 1699 |
+
"loss": 1.6323,
|
| 1700 |
+
"mean_token_accuracy": 0.672014307975769,
|
| 1701 |
+
"num_tokens": 3428160.0,
|
| 1702 |
+
"step": 940
|
| 1703 |
}
|
| 1704 |
],
|
| 1705 |
"logging_steps": 5,
|
|
|
|
| 1719 |
"attributes": {}
|
| 1720 |
}
|
| 1721 |
},
|
| 1722 |
+
"total_flos": 1.7371978756374528e+17,
|
| 1723 |
"train_batch_size": 4,
|
| 1724 |
"trial_name": null,
|
| 1725 |
"trial_params": null
|