Training in progress, step 1630, checkpoint
Browse files
last-checkpoint/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 70430032
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dbc0b9535e0cd7bbd40c325e1df1d620f5e0634732be36e06c6531f780634a51
|
| 3 |
size 70430032
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 141058579
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:201984ae8edf6b6a133b6515a8fcbc3eab2566e3f1873ee0a97aa9fd9218db8b
|
| 3 |
size 141058579
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14645
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:21ecd86e07e61f77465e226ceb43a96afc3eb7e6952e61209c9020ac360d89a4
|
| 3 |
size 14645
|
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:a9d4ee00fbfe2a02df4f98c5ce73c96144020d97c62d625c71fc70631e2a4ce1
|
| 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": 0.
|
| 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,
|
|
@@ -1638,6 +1638,16 @@
|
|
| 1638 |
"mean_token_accuracy": 0.7739639699459075,
|
| 1639 |
"num_tokens": 7527918.0,
|
| 1640 |
"step": 1620
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1641 |
}
|
| 1642 |
],
|
| 1643 |
"logging_steps": 10,
|
|
@@ -1657,7 +1667,7 @@
|
|
| 1657 |
"attributes": {}
|
| 1658 |
}
|
| 1659 |
},
|
| 1660 |
-
"total_flos": 3.
|
| 1661 |
"train_batch_size": 4,
|
| 1662 |
"trial_name": null,
|
| 1663 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.34773333333333334,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 1630,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 1638 |
"mean_token_accuracy": 0.7739639699459075,
|
| 1639 |
"num_tokens": 7527918.0,
|
| 1640 |
"step": 1620
|
| 1641 |
+
},
|
| 1642 |
+
{
|
| 1643 |
+
"entropy": 1.0133905045688152,
|
| 1644 |
+
"epoch": 0.34773333333333334,
|
| 1645 |
+
"grad_norm": 0.22292616963386536,
|
| 1646 |
+
"learning_rate": 9.480209502978869e-05,
|
| 1647 |
+
"loss": 1.0447552680969239,
|
| 1648 |
+
"mean_token_accuracy": 0.7502199374139309,
|
| 1649 |
+
"num_tokens": 7573700.0,
|
| 1650 |
+
"step": 1630
|
| 1651 |
}
|
| 1652 |
],
|
| 1653 |
"logging_steps": 10,
|
|
|
|
| 1667 |
"attributes": {}
|
| 1668 |
}
|
| 1669 |
},
|
| 1670 |
+
"total_flos": 3.5912134444283904e+16,
|
| 1671 |
"train_batch_size": 4,
|
| 1672 |
"trial_name": null,
|
| 1673 |
"trial_params": null
|