Training in progress, step 7920, 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:e77c0e19e4e18e0adfe25ddf0c30e5d9050bbe988cb5381d99284ee5cbbdc058
|
| 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 sha256:7e890f5ff223946d579d2528745e0cbfdb5b5e23c9f994054fed63fc799d47f9
|
| 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:c86e734ceb8dcc3c35ed71f104cff24762c39418373dfce7df3094cf41986310
|
| 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": 60.
|
| 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,
|
|
@@ -14246,6 +14246,24 @@
|
|
| 14246 |
"mean_token_accuracy": 0.6478750109672546,
|
| 14247 |
"num_tokens": 28846473.0,
|
| 14248 |
"step": 7910
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 14249 |
}
|
| 14250 |
],
|
| 14251 |
"logging_steps": 5,
|
|
@@ -14265,7 +14283,7 @@
|
|
| 14265 |
"attributes": {}
|
| 14266 |
}
|
| 14267 |
},
|
| 14268 |
-
"total_flos": 1.
|
| 14269 |
"train_batch_size": 4,
|
| 14270 |
"trial_name": null,
|
| 14271 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 60.92307692307692,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 7920,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 14246 |
"mean_token_accuracy": 0.6478750109672546,
|
| 14247 |
"num_tokens": 28846473.0,
|
| 14248 |
"step": 7910
|
| 14249 |
+
},
|
| 14250 |
+
{
|
| 14251 |
+
"epoch": 60.88461538461539,
|
| 14252 |
+
"grad_norm": 0.0,
|
| 14253 |
+
"learning_rate": 1.043e-05,
|
| 14254 |
+
"loss": 1.7125,
|
| 14255 |
+
"mean_token_accuracy": 0.6560309410095215,
|
| 14256 |
+
"num_tokens": 28864548.0,
|
| 14257 |
+
"step": 7915
|
| 14258 |
+
},
|
| 14259 |
+
{
|
| 14260 |
+
"epoch": 60.92307692307692,
|
| 14261 |
+
"grad_norm": 0.0,
|
| 14262 |
+
"learning_rate": 1.0405000000000001e-05,
|
| 14263 |
+
"loss": 1.7297,
|
| 14264 |
+
"mean_token_accuracy": 0.6469286412000657,
|
| 14265 |
+
"num_tokens": 28882849.0,
|
| 14266 |
+
"step": 7920
|
| 14267 |
}
|
| 14268 |
],
|
| 14269 |
"logging_steps": 5,
|
|
|
|
| 14283 |
"attributes": {}
|
| 14284 |
}
|
| 14285 |
},
|
| 14286 |
+
"total_flos": 1.464492151503913e+18,
|
| 14287 |
"train_batch_size": 4,
|
| 14288 |
"trial_name": null,
|
| 14289 |
"trial_params": null
|