Training in progress, step 950, checkpoint
Browse files
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1657
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:792d3239918470d8586cbf31fe2ba00bc350a643f529148057a3e32cc71b62ae
|
| 3 |
size 1657
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14709
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c210b00962853bb28804b7b324c8e37fde133247572cc4496e39445fc7ab6992
|
| 3 |
size 14709
|
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 sha256:1005a3781ae3467ea1853f1d712020d2144a7e34697735f0b5794791fdedbbbb
|
| 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": 7.
|
| 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,
|
|
@@ -1700,6 +1700,24 @@
|
|
| 1700 |
"mean_token_accuracy": 0.672014307975769,
|
| 1701 |
"num_tokens": 3428160.0,
|
| 1702 |
"step": 940
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1703 |
}
|
| 1704 |
],
|
| 1705 |
"logging_steps": 5,
|
|
@@ -1719,7 +1737,7 @@
|
|
| 1719 |
"attributes": {}
|
| 1720 |
}
|
| 1721 |
},
|
| 1722 |
-
"total_flos": 1.
|
| 1723 |
"train_batch_size": 4,
|
| 1724 |
"trial_name": null,
|
| 1725 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 7.3076923076923075,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 950,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 1700 |
"mean_token_accuracy": 0.672014307975769,
|
| 1701 |
"num_tokens": 3428160.0,
|
| 1702 |
"step": 940
|
| 1703 |
+
},
|
| 1704 |
+
{
|
| 1705 |
+
"epoch": 7.269230769230769,
|
| 1706 |
+
"grad_norm": 0.0,
|
| 1707 |
+
"learning_rate": 4.528e-05,
|
| 1708 |
+
"loss": 1.7143,
|
| 1709 |
+
"mean_token_accuracy": 0.6540875136852264,
|
| 1710 |
+
"num_tokens": 3447098.0,
|
| 1711 |
+
"step": 945
|
| 1712 |
+
},
|
| 1713 |
+
{
|
| 1714 |
+
"epoch": 7.3076923076923075,
|
| 1715 |
+
"grad_norm": 0.0,
|
| 1716 |
+
"learning_rate": 4.5255000000000006e-05,
|
| 1717 |
+
"loss": 1.7804,
|
| 1718 |
+
"mean_token_accuracy": 0.6401316851377488,
|
| 1719 |
+
"num_tokens": 3465037.0,
|
| 1720 |
+
"step": 950
|
| 1721 |
}
|
| 1722 |
],
|
| 1723 |
"logging_steps": 5,
|
|
|
|
| 1737 |
"attributes": {}
|
| 1738 |
}
|
| 1739 |
},
|
| 1740 |
+
"total_flos": 1.7558480741548032e+17,
|
| 1741 |
"train_batch_size": 4,
|
| 1742 |
"trial_name": null,
|
| 1743 |
"trial_params": null
|