Training in progress, step 6840, 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:ca7d0afc1a2c2a741846c43e091c782f2114a769f56a74690b475e61950bcfaa
|
| 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:b0e0556cf2a4f262034812d9e556b12c93f14628e2dde31b4cf48aefa5755a97
|
| 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 sha256:9c6236ec10040b878af59547bc614700ea200580514a7ede5593eeac4f7559bb
|
| 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": 52.
|
| 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,
|
|
@@ -12302,6 +12302,24 @@
|
|
| 12302 |
"mean_token_accuracy": 0.6543055295944213,
|
| 12303 |
"num_tokens": 24911502.0,
|
| 12304 |
"step": 6830
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12305 |
}
|
| 12306 |
],
|
| 12307 |
"logging_steps": 5,
|
|
@@ -12321,7 +12339,7 @@
|
|
| 12321 |
"attributes": {}
|
| 12322 |
}
|
| 12323 |
},
|
| 12324 |
-
"total_flos": 1.
|
| 12325 |
"train_batch_size": 4,
|
| 12326 |
"trial_name": null,
|
| 12327 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 52.61538461538461,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 6840,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 12302 |
"mean_token_accuracy": 0.6543055295944213,
|
| 12303 |
"num_tokens": 24911502.0,
|
| 12304 |
"step": 6830
|
| 12305 |
+
},
|
| 12306 |
+
{
|
| 12307 |
+
"epoch": 52.57692307692308,
|
| 12308 |
+
"grad_norm": 0.0,
|
| 12309 |
+
"learning_rate": 1.583e-05,
|
| 12310 |
+
"loss": 1.8051,
|
| 12311 |
+
"mean_token_accuracy": 0.6321907073259354,
|
| 12312 |
+
"num_tokens": 24929552.0,
|
| 12313 |
+
"step": 6835
|
| 12314 |
+
},
|
| 12315 |
+
{
|
| 12316 |
+
"epoch": 52.61538461538461,
|
| 12317 |
+
"grad_norm": 0.0,
|
| 12318 |
+
"learning_rate": 1.5805000000000002e-05,
|
| 12319 |
+
"loss": 1.7726,
|
| 12320 |
+
"mean_token_accuracy": 0.6486641079187393,
|
| 12321 |
+
"num_tokens": 24947565.0,
|
| 12322 |
+
"step": 6840
|
| 12323 |
}
|
| 12324 |
],
|
| 12325 |
"logging_steps": 5,
|
|
|
|
| 12339 |
"attributes": {}
|
| 12340 |
}
|
| 12341 |
},
|
| 12342 |
+
"total_flos": 1.2648865997286605e+18,
|
| 12343 |
"train_batch_size": 4,
|
| 12344 |
"trial_name": null,
|
| 12345 |
"trial_params": null
|