Training in progress, step 9780, 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:ffe37ab427bb0e1c117f454c64b0d597f9d275c016048677532148c9e97511ad
|
| 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:fe9e08bacf265c29f3212e8b0b56fd332f92c9a49ad5b6480277227801174314
|
| 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:f53a7321406aada0b703d3332a20a8b64b8e2b26d75722101a61ed391972f537
|
| 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": 75.
|
| 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,
|
|
@@ -17594,6 +17594,24 @@
|
|
| 17594 |
"mean_token_accuracy": 0.6380451053380967,
|
| 17595 |
"num_tokens": 35630549.0,
|
| 17596 |
"step": 9770
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 17597 |
}
|
| 17598 |
],
|
| 17599 |
"logging_steps": 5,
|
|
@@ -17613,7 +17631,7 @@
|
|
| 17613 |
"attributes": {}
|
| 17614 |
}
|
| 17615 |
},
|
| 17616 |
-
"total_flos": 1.
|
| 17617 |
"train_batch_size": 4,
|
| 17618 |
"trial_name": null,
|
| 17619 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 75.23076923076923,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 9780,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 17594 |
"mean_token_accuracy": 0.6380451053380967,
|
| 17595 |
"num_tokens": 35630549.0,
|
| 17596 |
"step": 9770
|
| 17597 |
+
},
|
| 17598 |
+
{
|
| 17599 |
+
"epoch": 75.1923076923077,
|
| 17600 |
+
"grad_norm": 0.0,
|
| 17601 |
+
"learning_rate": 1.13e-06,
|
| 17602 |
+
"loss": 1.8032,
|
| 17603 |
+
"mean_token_accuracy": 0.6359036058187485,
|
| 17604 |
+
"num_tokens": 35648480.0,
|
| 17605 |
+
"step": 9775
|
| 17606 |
+
},
|
| 17607 |
+
{
|
| 17608 |
+
"epoch": 75.23076923076923,
|
| 17609 |
+
"grad_norm": 0.0,
|
| 17610 |
+
"learning_rate": 1.1050000000000002e-06,
|
| 17611 |
+
"loss": 1.763,
|
| 17612 |
+
"mean_token_accuracy": 0.6435405910015106,
|
| 17613 |
+
"num_tokens": 35666156.0,
|
| 17614 |
+
"step": 9780
|
| 17615 |
}
|
| 17616 |
],
|
| 17617 |
"logging_steps": 5,
|
|
|
|
| 17631 |
"attributes": {}
|
| 17632 |
}
|
| 17633 |
},
|
| 17634 |
+
"total_flos": 1.8087158138034586e+18,
|
| 17635 |
"train_batch_size": 4,
|
| 17636 |
"trial_name": null,
|
| 17637 |
"trial_params": null
|