Training in progress, step 3580, 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:dd6ae41e5184fcec83804e5c4c12e7617f659ca7b898f42ae9e5768216843335
|
| 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 sha256:3ea3a303d7ebd367caaccf78d0c8380659f31fcad0418c99216ea6a740f55172
|
| 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 sha256:7981cfa7cf169c1cf2db0ca8f75343315ed6fd5df3bf6c315f57800fcee34ca6
|
| 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": 27.
|
| 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,
|
|
@@ -6434,6 +6434,24 @@
|
|
| 6434 |
"mean_token_accuracy": 0.6523656696081161,
|
| 6435 |
"num_tokens": 13019062.0,
|
| 6436 |
"step": 3570
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6437 |
}
|
| 6438 |
],
|
| 6439 |
"logging_steps": 5,
|
|
@@ -6453,7 +6471,7 @@
|
|
| 6453 |
"attributes": {}
|
| 6454 |
}
|
| 6455 |
},
|
| 6456 |
-
"total_flos": 6.
|
| 6457 |
"train_batch_size": 4,
|
| 6458 |
"trial_name": null,
|
| 6459 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 27.53846153846154,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 3580,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 6434 |
"mean_token_accuracy": 0.6523656696081161,
|
| 6435 |
"num_tokens": 13019062.0,
|
| 6436 |
"step": 3570
|
| 6437 |
+
},
|
| 6438 |
+
{
|
| 6439 |
+
"epoch": 27.5,
|
| 6440 |
+
"grad_norm": 0.0,
|
| 6441 |
+
"learning_rate": 3.213e-05,
|
| 6442 |
+
"loss": 1.7927,
|
| 6443 |
+
"mean_token_accuracy": 0.6346830785274505,
|
| 6444 |
+
"num_tokens": 13036934.0,
|
| 6445 |
+
"step": 3575
|
| 6446 |
+
},
|
| 6447 |
+
{
|
| 6448 |
+
"epoch": 27.53846153846154,
|
| 6449 |
+
"grad_norm": 0.0,
|
| 6450 |
+
"learning_rate": 3.2105e-05,
|
| 6451 |
+
"loss": 1.7951,
|
| 6452 |
+
"mean_token_accuracy": 0.6394420713186264,
|
| 6453 |
+
"num_tokens": 13054793.0,
|
| 6454 |
+
"step": 3580
|
| 6455 |
}
|
| 6456 |
],
|
| 6457 |
"logging_steps": 5,
|
|
|
|
| 6471 |
"attributes": {}
|
| 6472 |
}
|
| 6473 |
},
|
| 6474 |
+
"total_flos": 6.614548697382912e+17,
|
| 6475 |
"train_batch_size": 4,
|
| 6476 |
"trial_name": null,
|
| 6477 |
"trial_params": null
|