Training in progress, step 7320, 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 sha256:718c0d139077c9e557d2107dc3b8be86693a9d64181bab6aa0415eba6501edee
|
| 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 sha256:9b7ebd5338d59076e1f361f8e6595f1769d8c0e523e86c3d958fae784ecd94f0
|
| 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 sha256:45e4a03411ec971c0977a2b208c9671fbf0c3b915f368328e6a0e958dea289e8
|
| 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": 56.
|
| 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,
|
|
@@ -13166,6 +13166,24 @@
|
|
| 13166 |
"mean_token_accuracy": 0.6511315196752548,
|
| 13167 |
"num_tokens": 26659096.0,
|
| 13168 |
"step": 7310
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 13169 |
}
|
| 13170 |
],
|
| 13171 |
"logging_steps": 5,
|
|
@@ -13185,7 +13203,7 @@
|
|
| 13185 |
"attributes": {}
|
| 13186 |
}
|
| 13187 |
},
|
| 13188 |
-
"total_flos": 1.
|
| 13189 |
"train_batch_size": 4,
|
| 13190 |
"trial_name": null,
|
| 13191 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 56.30769230769231,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 7320,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 13166 |
"mean_token_accuracy": 0.6511315196752548,
|
| 13167 |
"num_tokens": 26659096.0,
|
| 13168 |
"step": 7310
|
| 13169 |
+
},
|
| 13170 |
+
{
|
| 13171 |
+
"epoch": 56.26923076923077,
|
| 13172 |
+
"grad_norm": 0.0,
|
| 13173 |
+
"learning_rate": 1.343e-05,
|
| 13174 |
+
"loss": 1.7669,
|
| 13175 |
+
"mean_token_accuracy": 0.6419103145599365,
|
| 13176 |
+
"num_tokens": 26677122.0,
|
| 13177 |
+
"step": 7315
|
| 13178 |
+
},
|
| 13179 |
+
{
|
| 13180 |
+
"epoch": 56.30769230769231,
|
| 13181 |
+
"grad_norm": 0.0,
|
| 13182 |
+
"learning_rate": 1.3405000000000001e-05,
|
| 13183 |
+
"loss": 1.7607,
|
| 13184 |
+
"mean_token_accuracy": 0.6484110444784165,
|
| 13185 |
+
"num_tokens": 26694580.0,
|
| 13186 |
+
"step": 7320
|
| 13187 |
}
|
| 13188 |
],
|
| 13189 |
"logging_steps": 5,
|
|
|
|
| 13203 |
"attributes": {}
|
| 13204 |
}
|
| 13205 |
},
|
| 13206 |
+
"total_flos": 1.3534343952246374e+18,
|
| 13207 |
"train_batch_size": 4,
|
| 13208 |
"trial_name": null,
|
| 13209 |
"trial_params": null
|