Training in progress, step 8970, 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:b106b5fc5e6ce083e727d5aad3aa9a4fcf2ace6b4563ff62e2657a7ca6f196e2
|
| 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 sha256:7e50eef292ec915c026cfe6e22da4b7ce7bafe0857f1e43f142c9d777ecc7a91
|
| 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:ae5ce75e508d80b9520dcbf03da9f6e2b339959eb524eb655ad6e20d1a25bc97
|
| 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":
|
| 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,
|
|
@@ -16136,6 +16136,24 @@
|
|
| 16136 |
"mean_token_accuracy": 0.6607306629419327,
|
| 16137 |
"num_tokens": 32676715.0,
|
| 16138 |
"step": 8960
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 16139 |
}
|
| 16140 |
],
|
| 16141 |
"logging_steps": 5,
|
|
@@ -16155,7 +16173,7 @@
|
|
| 16155 |
"attributes": {}
|
| 16156 |
}
|
| 16157 |
},
|
| 16158 |
-
"total_flos": 1.
|
| 16159 |
"train_batch_size": 4,
|
| 16160 |
"trial_name": null,
|
| 16161 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 69.0,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 8970,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 16136 |
"mean_token_accuracy": 0.6607306629419327,
|
| 16137 |
"num_tokens": 32676715.0,
|
| 16138 |
"step": 8960
|
| 16139 |
+
},
|
| 16140 |
+
{
|
| 16141 |
+
"epoch": 68.96153846153847,
|
| 16142 |
+
"grad_norm": 0.0,
|
| 16143 |
+
"learning_rate": 5.18e-06,
|
| 16144 |
+
"loss": 1.7511,
|
| 16145 |
+
"mean_token_accuracy": 0.6513434231281281,
|
| 16146 |
+
"num_tokens": 32694775.0,
|
| 16147 |
+
"step": 8965
|
| 16148 |
+
},
|
| 16149 |
+
{
|
| 16150 |
+
"epoch": 69.0,
|
| 16151 |
+
"grad_norm": 0.0,
|
| 16152 |
+
"learning_rate": 5.155e-06,
|
| 16153 |
+
"loss": 1.7027,
|
| 16154 |
+
"mean_token_accuracy": 0.6560029089450836,
|
| 16155 |
+
"num_tokens": 32713245.0,
|
| 16156 |
+
"step": 8970
|
| 16157 |
}
|
| 16158 |
],
|
| 16159 |
"logging_steps": 5,
|
|
|
|
| 16173 |
"attributes": {}
|
| 16174 |
}
|
| 16175 |
},
|
| 16176 |
+
"total_flos": 1.6588440188883763e+18,
|
| 16177 |
"train_batch_size": 4,
|
| 16178 |
"trial_name": null,
|
| 16179 |
"trial_params": null
|