Training in progress, step 1720, 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:dbde674517b939ef2df8342ec846b5dce1684cf9c0d2f85245a61a6bd0e2abb6
|
| 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:e2449dcfb481a5381fbcd669fa9679935a88b5436a40569e9f0b77a16ecdb754
|
| 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:cd1f64fac85f8a96a4b988ed0d818505c4aa3a89f1cdad1b179c915435773b54
|
| 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 sha256:50beea14553facb781039ba99dd206ef3d17f4788ad7b84d15561314d737a621
|
| 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,
|
|
@@ -1728,6 +1728,16 @@
|
|
| 1728 |
"mean_token_accuracy": 0.7736168324947357,
|
| 1729 |
"num_tokens": 7933849.0,
|
| 1730 |
"step": 1710
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1731 |
}
|
| 1732 |
],
|
| 1733 |
"logging_steps": 10,
|
|
@@ -1747,7 +1757,7 @@
|
|
| 1747 |
"attributes": {}
|
| 1748 |
}
|
| 1749 |
},
|
| 1750 |
-
"total_flos": 3.
|
| 1751 |
"train_batch_size": 4,
|
| 1752 |
"trial_name": null,
|
| 1753 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.36693333333333333,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 1720,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 1728 |
"mean_token_accuracy": 0.7736168324947357,
|
| 1729 |
"num_tokens": 7933849.0,
|
| 1730 |
"step": 1710
|
| 1731 |
+
},
|
| 1732 |
+
{
|
| 1733 |
+
"entropy": 1.0065233081579208,
|
| 1734 |
+
"epoch": 0.36693333333333333,
|
| 1735 |
+
"grad_norm": 0.34241342544555664,
|
| 1736 |
+
"learning_rate": 9.408892248046885e-05,
|
| 1737 |
+
"loss": 1.1022210121154785,
|
| 1738 |
+
"mean_token_accuracy": 0.7556669354438782,
|
| 1739 |
+
"num_tokens": 7981235.0,
|
| 1740 |
+
"step": 1720
|
| 1741 |
}
|
| 1742 |
],
|
| 1743 |
"logging_steps": 10,
|
|
|
|
| 1757 |
"attributes": {}
|
| 1758 |
}
|
| 1759 |
},
|
| 1760 |
+
"total_flos": 3.786099610394726e+16,
|
| 1761 |
"train_batch_size": 4,
|
| 1762 |
"trial_name": null,
|
| 1763 |
"trial_params": null
|