Training in progress, step 1670, 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:d18f4bede538fb77c43a62bdca00e26aa30dcf195248f62a3598659814ec19c0
|
| 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 sha256:1165ab4e11ab7bcec1ea7321355d19fb814e136f6352a5dd5dcdf9d80ed349ae
|
| 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:a8a2f69f3f90165766f90290a98ab2f3907ab00e4e729f214bf01d66571e9a07
|
| 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 sha256:91584877eaa067f530efefaa9e443f0d57fc27ba3f3efdab77901f5c93132e56
|
| 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,
|
|
@@ -1678,6 +1678,16 @@
|
|
| 1678 |
"mean_token_accuracy": 0.7573757611215115,
|
| 1679 |
"num_tokens": 7717686.0,
|
| 1680 |
"step": 1660
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1681 |
}
|
| 1682 |
],
|
| 1683 |
"logging_steps": 10,
|
|
@@ -1697,7 +1707,7 @@
|
|
| 1697 |
"attributes": {}
|
| 1698 |
}
|
| 1699 |
},
|
| 1700 |
-
"total_flos": 3.
|
| 1701 |
"train_batch_size": 4,
|
| 1702 |
"trial_name": null,
|
| 1703 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.3562666666666667,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 1670,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 1678 |
"mean_token_accuracy": 0.7573757611215115,
|
| 1679 |
"num_tokens": 7717686.0,
|
| 1680 |
"step": 1660
|
| 1681 |
+
},
|
| 1682 |
+
{
|
| 1683 |
+
"entropy": 0.8418352358043194,
|
| 1684 |
+
"epoch": 0.3562666666666667,
|
| 1685 |
+
"grad_norm": 0.2636827826499939,
|
| 1686 |
+
"learning_rate": 9.449045680528041e-05,
|
| 1687 |
+
"loss": 0.9572833061218262,
|
| 1688 |
+
"mean_token_accuracy": 0.7885566264390945,
|
| 1689 |
+
"num_tokens": 7760984.0,
|
| 1690 |
+
"step": 1670
|
| 1691 |
}
|
| 1692 |
],
|
| 1693 |
"logging_steps": 10,
|
|
|
|
| 1707 |
"attributes": {}
|
| 1708 |
}
|
| 1709 |
},
|
| 1710 |
+
"total_flos": 3.681182534128435e+16,
|
| 1711 |
"train_batch_size": 4,
|
| 1712 |
"trial_name": null,
|
| 1713 |
"trial_params": null
|