Training in progress, step 6830, 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:fd2ea99418ea12adc3977a4947627c7da27094ce918abbb6604dcb16b3c58a0a
|
| 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:afdde35e19d4957b8bf3d7cb53d334f8718e7865d6973001aa16cc029eda7935
|
| 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 sha256:7d0acff6a3f7a197cc34fda6e3ca80ecefbaaf1736dad23406a9d4d8bea35105
|
| 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,
|
|
@@ -12284,6 +12284,24 @@
|
|
| 12284 |
"mean_token_accuracy": 0.6554641664028168,
|
| 12285 |
"num_tokens": 24874368.0,
|
| 12286 |
"step": 6820
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12287 |
}
|
| 12288 |
],
|
| 12289 |
"logging_steps": 5,
|
|
@@ -12303,7 +12321,7 @@
|
|
| 12303 |
"attributes": {}
|
| 12304 |
}
|
| 12305 |
},
|
| 12306 |
-
"total_flos": 1.
|
| 12307 |
"train_batch_size": 4,
|
| 12308 |
"trial_name": null,
|
| 12309 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 52.53846153846154,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 6830,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 12284 |
"mean_token_accuracy": 0.6554641664028168,
|
| 12285 |
"num_tokens": 24874368.0,
|
| 12286 |
"step": 6820
|
| 12287 |
+
},
|
| 12288 |
+
{
|
| 12289 |
+
"epoch": 52.5,
|
| 12290 |
+
"grad_norm": 0.0,
|
| 12291 |
+
"learning_rate": 1.588e-05,
|
| 12292 |
+
"loss": 1.7152,
|
| 12293 |
+
"mean_token_accuracy": 0.6568386435508728,
|
| 12294 |
+
"num_tokens": 24893164.0,
|
| 12295 |
+
"step": 6825
|
| 12296 |
+
},
|
| 12297 |
+
{
|
| 12298 |
+
"epoch": 52.53846153846154,
|
| 12299 |
+
"grad_norm": 0.0,
|
| 12300 |
+
"learning_rate": 1.5855e-05,
|
| 12301 |
+
"loss": 1.7097,
|
| 12302 |
+
"mean_token_accuracy": 0.6543055295944213,
|
| 12303 |
+
"num_tokens": 24911502.0,
|
| 12304 |
+
"step": 6830
|
| 12305 |
}
|
| 12306 |
],
|
| 12307 |
"logging_steps": 5,
|
|
|
|
| 12321 |
"attributes": {}
|
| 12322 |
}
|
| 12323 |
},
|
| 12324 |
+
"total_flos": 1.2630390455830118e+18,
|
| 12325 |
"train_batch_size": 4,
|
| 12326 |
"trial_name": null,
|
| 12327 |
"trial_params": null
|