Training in progress, step 3110, 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 sha256:9f6329464f2aa12c7c781d271c41e9df0c6e3979b7f94e6a0006f50367158493
|
| 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 sha256:21322d80a328f489cdc8dda865103092bd66d8805bb4764e7ab8d437e0da8586
|
| 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 sha256:9c485eb38352848132a5e0ea3ab37d757cc4e67470be3200dc12be8fdca71bf5
|
| 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": 23.
|
| 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,
|
|
@@ -5588,6 +5588,24 @@
|
|
| 5588 |
"mean_token_accuracy": 0.6589304953813553,
|
| 5589 |
"num_tokens": 11306559.0,
|
| 5590 |
"step": 3100
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5591 |
}
|
| 5592 |
],
|
| 5593 |
"logging_steps": 5,
|
|
@@ -5607,7 +5625,7 @@
|
|
| 5607 |
"attributes": {}
|
| 5608 |
}
|
| 5609 |
},
|
| 5610 |
-
"total_flos": 5.
|
| 5611 |
"train_batch_size": 4,
|
| 5612 |
"trial_name": null,
|
| 5613 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 23.923076923076923,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 3110,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 5588 |
"mean_token_accuracy": 0.6589304953813553,
|
| 5589 |
"num_tokens": 11306559.0,
|
| 5590 |
"step": 3100
|
| 5591 |
+
},
|
| 5592 |
+
{
|
| 5593 |
+
"epoch": 23.884615384615383,
|
| 5594 |
+
"grad_norm": 0.0,
|
| 5595 |
+
"learning_rate": 3.448e-05,
|
| 5596 |
+
"loss": 1.7559,
|
| 5597 |
+
"mean_token_accuracy": 0.647815215587616,
|
| 5598 |
+
"num_tokens": 11324582.0,
|
| 5599 |
+
"step": 3105
|
| 5600 |
+
},
|
| 5601 |
+
{
|
| 5602 |
+
"epoch": 23.923076923076923,
|
| 5603 |
+
"grad_norm": 0.0,
|
| 5604 |
+
"learning_rate": 3.4455e-05,
|
| 5605 |
+
"loss": 1.7362,
|
| 5606 |
+
"mean_token_accuracy": 0.6531584694981575,
|
| 5607 |
+
"num_tokens": 11343111.0,
|
| 5608 |
+
"step": 3110
|
| 5609 |
}
|
| 5610 |
],
|
| 5611 |
"logging_steps": 5,
|
|
|
|
| 5625 |
"attributes": {}
|
| 5626 |
}
|
| 5627 |
},
|
| 5628 |
+
"total_flos": 5.748103598682931e+17,
|
| 5629 |
"train_batch_size": 4,
|
| 5630 |
"trial_name": null,
|
| 5631 |
"trial_params": null
|