Training in progress, step 3590, 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 sha256:4fef70b56eda9963586651a402e55279fee8299b8fdc5219efc9af3044e754ee
|
| 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 sha256:88d371ae83a9be1754981c02e03cc25632b999ede4bfa722aa71515f9c90eefc
|
| 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 sha256:437d5fe20d0fa51416a20ec5725530e5c7273a3d2c303906076066659703dd3e
|
| 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,
|
|
@@ -6452,6 +6452,24 @@
|
|
| 6452 |
"mean_token_accuracy": 0.6394420713186264,
|
| 6453 |
"num_tokens": 13054793.0,
|
| 6454 |
"step": 3580
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6455 |
}
|
| 6456 |
],
|
| 6457 |
"logging_steps": 5,
|
|
@@ -6471,7 +6489,7 @@
|
|
| 6471 |
"attributes": {}
|
| 6472 |
}
|
| 6473 |
},
|
| 6474 |
-
"total_flos": 6.
|
| 6475 |
"train_batch_size": 4,
|
| 6476 |
"trial_name": null,
|
| 6477 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 27.615384615384617,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 3590,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 6452 |
"mean_token_accuracy": 0.6394420713186264,
|
| 6453 |
"num_tokens": 13054793.0,
|
| 6454 |
"step": 3580
|
| 6455 |
+
},
|
| 6456 |
+
{
|
| 6457 |
+
"epoch": 27.576923076923077,
|
| 6458 |
+
"grad_norm": 0.0,
|
| 6459 |
+
"learning_rate": 3.208e-05,
|
| 6460 |
+
"loss": 1.771,
|
| 6461 |
+
"mean_token_accuracy": 0.6480452120304108,
|
| 6462 |
+
"num_tokens": 13072483.0,
|
| 6463 |
+
"step": 3585
|
| 6464 |
+
},
|
| 6465 |
+
{
|
| 6466 |
+
"epoch": 27.615384615384617,
|
| 6467 |
+
"grad_norm": 0.0,
|
| 6468 |
+
"learning_rate": 3.2055000000000004e-05,
|
| 6469 |
+
"loss": 1.614,
|
| 6470 |
+
"mean_token_accuracy": 0.6677554935216904,
|
| 6471 |
+
"num_tokens": 13092135.0,
|
| 6472 |
+
"step": 3590
|
| 6473 |
}
|
| 6474 |
],
|
| 6475 |
"logging_steps": 5,
|
|
|
|
| 6489 |
"attributes": {}
|
| 6490 |
}
|
| 6491 |
},
|
| 6492 |
+
"total_flos": 6.633764149660877e+17,
|
| 6493 |
"train_batch_size": 4,
|
| 6494 |
"trial_name": null,
|
| 6495 |
"trial_params": null
|