Training in progress, step 150, 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 sha256:06f2176e7a4fc0879fc1ea3c6a82debf331c585d316efbfbdaecf9648216f751
|
| 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 sha256:374867d83d2ee8d0b48d139e090ffcb2eae19447dec20513e1f3ccd7798a6104
|
| 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 sha256:80c2758c3ead60c28e1ac1c04f0ebbbd04e9c150e5b5c0f74dfd6d29180f67a6
|
| 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": 1.
|
| 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,
|
|
@@ -260,6 +260,24 @@
|
|
| 260 |
"mean_token_accuracy": 0.6435200899839402,
|
| 261 |
"num_tokens": 510988.0,
|
| 262 |
"step": 140
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 263 |
}
|
| 264 |
],
|
| 265 |
"logging_steps": 5,
|
|
@@ -279,7 +297,7 @@
|
|
| 279 |
"attributes": {}
|
| 280 |
}
|
| 281 |
},
|
| 282 |
-
"total_flos": 2.
|
| 283 |
"train_batch_size": 4,
|
| 284 |
"trial_name": null,
|
| 285 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 1.1538461538461537,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 150,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 260 |
"mean_token_accuracy": 0.6435200899839402,
|
| 261 |
"num_tokens": 510988.0,
|
| 262 |
"step": 140
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 1.1153846153846154,
|
| 266 |
+
"grad_norm": 0.0,
|
| 267 |
+
"learning_rate": 4.928e-05,
|
| 268 |
+
"loss": 1.8093,
|
| 269 |
+
"mean_token_accuracy": 0.6363381177186966,
|
| 270 |
+
"num_tokens": 528455.0,
|
| 271 |
+
"step": 145
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 1.1538461538461537,
|
| 275 |
+
"grad_norm": 0.0,
|
| 276 |
+
"learning_rate": 4.9255e-05,
|
| 277 |
+
"loss": 1.7437,
|
| 278 |
+
"mean_token_accuracy": 0.651939743757248,
|
| 279 |
+
"num_tokens": 546439.0,
|
| 280 |
+
"step": 150
|
| 281 |
}
|
| 282 |
],
|
| 283 |
"logging_steps": 5,
|
|
|
|
| 297 |
"attributes": {}
|
| 298 |
}
|
| 299 |
},
|
| 300 |
+
"total_flos": 2.757072851140608e+16,
|
| 301 |
"train_batch_size": 4,
|
| 302 |
"trial_name": null,
|
| 303 |
"trial_params": null
|