Training in progress, step 1690, 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 sha256:94de166f603c580846b2226a31beeabbb238467609b5e6e9114492df8eab17e4
|
| 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 sha256:7bf5586a75203937e73915e987a31e39627c5dfc5e136fd6b93ed84d97c95b72
|
| 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:bfb8b02dc2d4e7440705c405387ae3b68e979ae0520f390aae8383f5a3d7fe1e
|
| 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 sha256:48b156a95c654efe59ae1d9293b9ab5890c663f8aae22da0e917c9be278fb9e3
|
| 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,
|
|
@@ -1698,6 +1698,16 @@
|
|
| 1698 |
"mean_token_accuracy": 0.7652302265167237,
|
| 1699 |
"num_tokens": 7806335.0,
|
| 1700 |
"step": 1680
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1701 |
}
|
| 1702 |
],
|
| 1703 |
"logging_steps": 10,
|
|
@@ -1717,7 +1727,7 @@
|
|
| 1717 |
"attributes": {}
|
| 1718 |
}
|
| 1719 |
},
|
| 1720 |
-
"total_flos": 3.
|
| 1721 |
"train_batch_size": 4,
|
| 1722 |
"trial_name": null,
|
| 1723 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.3605333333333333,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 1690,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 1698 |
"mean_token_accuracy": 0.7652302265167237,
|
| 1699 |
"num_tokens": 7806335.0,
|
| 1700 |
"step": 1680
|
| 1701 |
+
},
|
| 1702 |
+
{
|
| 1703 |
+
"entropy": 0.833198781311512,
|
| 1704 |
+
"epoch": 0.3605333333333333,
|
| 1705 |
+
"grad_norm": 0.2658802568912506,
|
| 1706 |
+
"learning_rate": 9.43314355749399e-05,
|
| 1707 |
+
"loss": 0.8842006683349609,
|
| 1708 |
+
"mean_token_accuracy": 0.7828017815947532,
|
| 1709 |
+
"num_tokens": 7846783.0,
|
| 1710 |
+
"step": 1690
|
| 1711 |
}
|
| 1712 |
],
|
| 1713 |
"logging_steps": 10,
|
|
|
|
| 1727 |
"attributes": {}
|
| 1728 |
}
|
| 1729 |
},
|
| 1730 |
+
"total_flos": 3.720806819492352e+16,
|
| 1731 |
"train_batch_size": 4,
|
| 1732 |
"trial_name": null,
|
| 1733 |
"trial_params": null
|