Training in progress, step 910, 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:b82418fa174f2f63a19f27a6ccf692afc6f19d4fe280adf102779f28b2dea0af
|
| 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 sha256:27ebaa74310f0953bb2b947053f74fae23033b38b058e2d0b70e0aa2365e1fcd
|
| 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 sha256:00ea14a6efe2df55e0c9994ee2598e48a7d6f8939d50f666c76ce95ddf21c2b5
|
| 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":
|
| 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,
|
|
@@ -1628,6 +1628,24 @@
|
|
| 1628 |
"mean_token_accuracy": 0.6435014694929123,
|
| 1629 |
"num_tokens": 3282692.0,
|
| 1630 |
"step": 900
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1631 |
}
|
| 1632 |
],
|
| 1633 |
"logging_steps": 5,
|
|
@@ -1647,7 +1665,7 @@
|
|
| 1647 |
"attributes": {}
|
| 1648 |
}
|
| 1649 |
},
|
| 1650 |
-
"total_flos": 1.
|
| 1651 |
"train_batch_size": 4,
|
| 1652 |
"trial_name": null,
|
| 1653 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 7.0,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 910,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 1628 |
"mean_token_accuracy": 0.6435014694929123,
|
| 1629 |
"num_tokens": 3282692.0,
|
| 1630 |
"step": 900
|
| 1631 |
+
},
|
| 1632 |
+
{
|
| 1633 |
+
"epoch": 6.961538461538462,
|
| 1634 |
+
"grad_norm": 0.0,
|
| 1635 |
+
"learning_rate": 4.548e-05,
|
| 1636 |
+
"loss": 1.8069,
|
| 1637 |
+
"mean_token_accuracy": 0.6398796170949936,
|
| 1638 |
+
"num_tokens": 3300093.0,
|
| 1639 |
+
"step": 905
|
| 1640 |
+
},
|
| 1641 |
+
{
|
| 1642 |
+
"epoch": 7.0,
|
| 1643 |
+
"grad_norm": 0.0,
|
| 1644 |
+
"learning_rate": 4.5455000000000004e-05,
|
| 1645 |
+
"loss": 1.7239,
|
| 1646 |
+
"mean_token_accuracy": 0.6568648606538773,
|
| 1647 |
+
"num_tokens": 3318735.0,
|
| 1648 |
+
"step": 910
|
| 1649 |
}
|
| 1650 |
],
|
| 1651 |
"logging_steps": 5,
|
|
|
|
| 1665 |
"attributes": {}
|
| 1666 |
}
|
| 1667 |
},
|
| 1668 |
+
"total_flos": 1.6819252670398464e+17,
|
| 1669 |
"train_batch_size": 4,
|
| 1670 |
"trial_name": null,
|
| 1671 |
"trial_params": null
|