Training in progress, step 1700, 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 sha256:2ec49c3967dff2fa5b4a6a722b16997f9c1a5259c9837d392661c7e6f4ab9850
|
| 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 sha256:4310f9048a90692626545079c9084f0bf6e554f96e223294a7f562ca79488880
|
| 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 sha256:501286c6ba5d51ed8db1a9581b908f10e3b219be550991bef23ea25332a068e3
|
| 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 sha256:5d72a5a59fd1cab254c751670f6dddd1229c370946cade7a7966f22da4d7a37b
|
| 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,
|
|
@@ -1708,6 +1708,16 @@
|
|
| 1708 |
"mean_token_accuracy": 0.7828017815947532,
|
| 1709 |
"num_tokens": 7846783.0,
|
| 1710 |
"step": 1690
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1711 |
}
|
| 1712 |
],
|
| 1713 |
"logging_steps": 10,
|
|
@@ -1727,7 +1737,7 @@
|
|
| 1727 |
"attributes": {}
|
| 1728 |
}
|
| 1729 |
},
|
| 1730 |
-
"total_flos": 3.
|
| 1731 |
"train_batch_size": 4,
|
| 1732 |
"trial_name": null,
|
| 1733 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.3626666666666667,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 1700,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 1708 |
"mean_token_accuracy": 0.7828017815947532,
|
| 1709 |
"num_tokens": 7846783.0,
|
| 1710 |
"step": 1690
|
| 1711 |
+
},
|
| 1712 |
+
{
|
| 1713 |
+
"entropy": 0.9806767851114273,
|
| 1714 |
+
"epoch": 0.3626666666666667,
|
| 1715 |
+
"grad_norm": 0.23127029836177826,
|
| 1716 |
+
"learning_rate": 9.425112774777354e-05,
|
| 1717 |
+
"loss": 1.116124439239502,
|
| 1718 |
+
"mean_token_accuracy": 0.7566492781043053,
|
| 1719 |
+
"num_tokens": 7890665.0,
|
| 1720 |
+
"step": 1700
|
| 1721 |
}
|
| 1722 |
],
|
| 1723 |
"logging_steps": 10,
|
|
|
|
| 1737 |
"attributes": {}
|
| 1738 |
}
|
| 1739 |
},
|
| 1740 |
+
"total_flos": 3.74272548647639e+16,
|
| 1741 |
"train_batch_size": 4,
|
| 1742 |
"trial_name": null,
|
| 1743 |
"trial_params": null
|