Training in progress, step 6330, 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 sha256:2c6077d30920ff8869e74fda273b8f2217556f6d74ae7a81764ff20cb99886b6
|
| 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:fa309ab12db560e2f2c344e9c6dad4fd3d08f372ce0fe36697b235ad2f52b25c
|
| 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 sha256:51b85f99a185afefc73e27d7916e637b26fa66e7d234c1aae0da7d6735477120
|
| 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": 48.
|
| 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,
|
|
@@ -11384,6 +11384,24 @@
|
|
| 11384 |
"mean_token_accuracy": 0.6463797986507416,
|
| 11385 |
"num_tokens": 23047988.0,
|
| 11386 |
"step": 6320
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11387 |
}
|
| 11388 |
],
|
| 11389 |
"logging_steps": 5,
|
|
@@ -11403,7 +11421,7 @@
|
|
| 11403 |
"attributes": {}
|
| 11404 |
}
|
| 11405 |
},
|
| 11406 |
-
"total_flos": 1.
|
| 11407 |
"train_batch_size": 4,
|
| 11408 |
"trial_name": null,
|
| 11409 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 48.69230769230769,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 6330,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 11384 |
"mean_token_accuracy": 0.6463797986507416,
|
| 11385 |
"num_tokens": 23047988.0,
|
| 11386 |
"step": 6320
|
| 11387 |
+
},
|
| 11388 |
+
{
|
| 11389 |
+
"epoch": 48.65384615384615,
|
| 11390 |
+
"grad_norm": 0.0,
|
| 11391 |
+
"learning_rate": 1.838e-05,
|
| 11392 |
+
"loss": 1.7542,
|
| 11393 |
+
"mean_token_accuracy": 0.6464673429727554,
|
| 11394 |
+
"num_tokens": 23065816.0,
|
| 11395 |
+
"step": 6325
|
| 11396 |
+
},
|
| 11397 |
+
{
|
| 11398 |
+
"epoch": 48.69230769230769,
|
| 11399 |
+
"grad_norm": 0.0,
|
| 11400 |
+
"learning_rate": 1.8355e-05,
|
| 11401 |
+
"loss": 1.742,
|
| 11402 |
+
"mean_token_accuracy": 0.6510752677917481,
|
| 11403 |
+
"num_tokens": 23083562.0,
|
| 11404 |
+
"step": 6330
|
| 11405 |
}
|
| 11406 |
],
|
| 11407 |
"logging_steps": 5,
|
|
|
|
| 11421 |
"attributes": {}
|
| 11422 |
}
|
| 11423 |
},
|
| 11424 |
+
"total_flos": 1.17008322342912e+18,
|
| 11425 |
"train_batch_size": 4,
|
| 11426 |
"trial_name": null,
|
| 11427 |
"trial_params": null
|