Training in progress, step 8900, 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 sha256:08665eced5defd9f9f62c9d03058c013a7bdedab5203d7bcb87da8ee5d61a04a
|
| 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 sha256:835c13f0a94711aaf5cd736713ee137524f30ed43dee005a5574f834ddc4bf3d
|
| 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 sha256:94c2ec4d5c3d9a68c84f9fe53d98e28c3cde44efa84e011b7482f2a716ce7159
|
| 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": 68.
|
| 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,
|
|
@@ -16010,6 +16010,24 @@
|
|
| 16010 |
"mean_token_accuracy": 0.6441059678792953,
|
| 16011 |
"num_tokens": 32419418.0,
|
| 16012 |
"step": 8890
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 16013 |
}
|
| 16014 |
],
|
| 16015 |
"logging_steps": 5,
|
|
@@ -16029,7 +16047,7 @@
|
|
| 16029 |
"attributes": {}
|
| 16030 |
}
|
| 16031 |
},
|
| 16032 |
-
"total_flos": 1.
|
| 16033 |
"train_batch_size": 4,
|
| 16034 |
"trial_name": null,
|
| 16035 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 68.46153846153847,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 8900,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 16010 |
"mean_token_accuracy": 0.6441059678792953,
|
| 16011 |
"num_tokens": 32419418.0,
|
| 16012 |
"step": 8890
|
| 16013 |
+
},
|
| 16014 |
+
{
|
| 16015 |
+
"epoch": 68.42307692307692,
|
| 16016 |
+
"grad_norm": 0.0,
|
| 16017 |
+
"learning_rate": 5.53e-06,
|
| 16018 |
+
"loss": 1.8152,
|
| 16019 |
+
"mean_token_accuracy": 0.6348958969116211,
|
| 16020 |
+
"num_tokens": 32436930.0,
|
| 16021 |
+
"step": 8895
|
| 16022 |
+
},
|
| 16023 |
+
{
|
| 16024 |
+
"epoch": 68.46153846153847,
|
| 16025 |
+
"grad_norm": 0.0,
|
| 16026 |
+
"learning_rate": 5.505000000000001e-06,
|
| 16027 |
+
"loss": 1.7356,
|
| 16028 |
+
"mean_token_accuracy": 0.6481510013341903,
|
| 16029 |
+
"num_tokens": 32455486.0,
|
| 16030 |
+
"step": 8900
|
| 16031 |
}
|
| 16032 |
],
|
| 16033 |
"logging_steps": 5,
|
|
|
|
| 16047 |
"attributes": {}
|
| 16048 |
}
|
| 16049 |
},
|
| 16050 |
+
"total_flos": 1.6455985037298893e+18,
|
| 16051 |
"train_batch_size": 4,
|
| 16052 |
"trial_name": null,
|
| 16053 |
"trial_params": null
|