Training in progress, step 5250, 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 sha256:5bb8f8dde2c73daad6405e1f592f2cd30b54cb5a8e79991c23f214f747e862e0
|
| 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 sha256:039e74aaff385746aafdbb27120201639349078e694e7b3ed6973d22a7b624bd
|
| 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:ec8fdcbd2a01cd3ee3586313065cdbda3a4d4ce0a1e986dd705afed43243df46
|
| 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": 40.
|
| 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,
|
|
@@ -9440,6 +9440,24 @@
|
|
| 9440 |
"mean_token_accuracy": 0.651043924689293,
|
| 9441 |
"num_tokens": 19107710.0,
|
| 9442 |
"step": 5240
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 9443 |
}
|
| 9444 |
],
|
| 9445 |
"logging_steps": 5,
|
|
@@ -9459,7 +9477,7 @@
|
|
| 9459 |
"attributes": {}
|
| 9460 |
}
|
| 9461 |
},
|
| 9462 |
-
"total_flos": 9.
|
| 9463 |
"train_batch_size": 4,
|
| 9464 |
"trial_name": null,
|
| 9465 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 40.38461538461539,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 5250,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 9440 |
"mean_token_accuracy": 0.651043924689293,
|
| 9441 |
"num_tokens": 19107710.0,
|
| 9442 |
"step": 5240
|
| 9443 |
+
},
|
| 9444 |
+
{
|
| 9445 |
+
"epoch": 40.34615384615385,
|
| 9446 |
+
"grad_norm": 0.0,
|
| 9447 |
+
"learning_rate": 2.3780000000000003e-05,
|
| 9448 |
+
"loss": 1.7209,
|
| 9449 |
+
"mean_token_accuracy": 0.6562368720769882,
|
| 9450 |
+
"num_tokens": 19125352.0,
|
| 9451 |
+
"step": 5245
|
| 9452 |
+
},
|
| 9453 |
+
{
|
| 9454 |
+
"epoch": 40.38461538461539,
|
| 9455 |
+
"grad_norm": 0.0,
|
| 9456 |
+
"learning_rate": 2.3755000000000002e-05,
|
| 9457 |
+
"loss": 1.7579,
|
| 9458 |
+
"mean_token_accuracy": 0.6454941630363464,
|
| 9459 |
+
"num_tokens": 19142899.0,
|
| 9460 |
+
"step": 5250
|
| 9461 |
}
|
| 9462 |
],
|
| 9463 |
"logging_steps": 5,
|
|
|
|
| 9477 |
"attributes": {}
|
| 9478 |
}
|
| 9479 |
},
|
| 9480 |
+
"total_flos": 9.699513187840819e+17,
|
| 9481 |
"train_batch_size": 4,
|
| 9482 |
"trial_name": null,
|
| 9483 |
"trial_params": null
|