Training in progress, step 7110, 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:b8657cf9c2ea4da50f0ed05510844dcbb285ee6e0aa22a14eaddc109796e77ce
|
| 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 sha256:3c2a07e8053df6e40d382ea336a1e7649101c5f27bf84a0cdb1b29893e62f779
|
| 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 sha256:8174fea7050a5b4e76a4425d3c0c8d0f1128be6afe673c5783e6c7c6a18da60b
|
| 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": 54.
|
| 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,
|
|
@@ -12788,6 +12788,24 @@
|
|
| 12788 |
"mean_token_accuracy": 0.6497918337583541,
|
| 12789 |
"num_tokens": 25896813.0,
|
| 12790 |
"step": 7100
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12791 |
}
|
| 12792 |
],
|
| 12793 |
"logging_steps": 5,
|
|
@@ -12807,7 +12825,7 @@
|
|
| 12807 |
"attributes": {}
|
| 12808 |
}
|
| 12809 |
},
|
| 12810 |
-
"total_flos": 1.
|
| 12811 |
"train_batch_size": 4,
|
| 12812 |
"trial_name": null,
|
| 12813 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 54.69230769230769,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 7110,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 12788 |
"mean_token_accuracy": 0.6497918337583541,
|
| 12789 |
"num_tokens": 25896813.0,
|
| 12790 |
"step": 7100
|
| 12791 |
+
},
|
| 12792 |
+
{
|
| 12793 |
+
"epoch": 54.65384615384615,
|
| 12794 |
+
"grad_norm": 0.0,
|
| 12795 |
+
"learning_rate": 1.4480000000000002e-05,
|
| 12796 |
+
"loss": 1.85,
|
| 12797 |
+
"mean_token_accuracy": 0.6287777543067932,
|
| 12798 |
+
"num_tokens": 25913707.0,
|
| 12799 |
+
"step": 7105
|
| 12800 |
+
},
|
| 12801 |
+
{
|
| 12802 |
+
"epoch": 54.69230769230769,
|
| 12803 |
+
"grad_norm": 0.0,
|
| 12804 |
+
"learning_rate": 1.4455000000000001e-05,
|
| 12805 |
+
"loss": 1.739,
|
| 12806 |
+
"mean_token_accuracy": 0.6525210946798324,
|
| 12807 |
+
"num_tokens": 25931516.0,
|
| 12808 |
+
"step": 7110
|
| 12809 |
}
|
| 12810 |
],
|
| 12811 |
"logging_steps": 5,
|
|
|
|
| 12825 |
"attributes": {}
|
| 12826 |
}
|
| 12827 |
},
|
| 12828 |
+
"total_flos": 1.314878531480617e+18,
|
| 12829 |
"train_batch_size": 4,
|
| 12830 |
"trial_name": null,
|
| 12831 |
"trial_params": null
|