Training in progress, step 6980, 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 sha256:64e4c38150fdcae56283c49be7466b11a05b4d6aa06b9edc208053b736293736
|
| 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 sha256:353fb008faa2e9ade8d322f1e799ae0f5e05670c6d6295b567043cb032654f39
|
| 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 sha256:56794f80c78546da3a79cd21ad2359c25db51052829b0f4051231d6712ba9c45
|
| 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": 53.
|
| 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,
|
|
@@ -12554,6 +12554,24 @@
|
|
| 12554 |
"mean_token_accuracy": 0.6540043205022812,
|
| 12555 |
"num_tokens": 25418880.0,
|
| 12556 |
"step": 6970
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12557 |
}
|
| 12558 |
],
|
| 12559 |
"logging_steps": 5,
|
|
@@ -12573,7 +12591,7 @@
|
|
| 12573 |
"attributes": {}
|
| 12574 |
}
|
| 12575 |
},
|
| 12576 |
-
"total_flos": 1.
|
| 12577 |
"train_batch_size": 4,
|
| 12578 |
"trial_name": null,
|
| 12579 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 53.69230769230769,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 6980,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 12554 |
"mean_token_accuracy": 0.6540043205022812,
|
| 12555 |
"num_tokens": 25418880.0,
|
| 12556 |
"step": 6970
|
| 12557 |
+
},
|
| 12558 |
+
{
|
| 12559 |
+
"epoch": 53.65384615384615,
|
| 12560 |
+
"grad_norm": 0.0,
|
| 12561 |
+
"learning_rate": 1.5129999999999999e-05,
|
| 12562 |
+
"loss": 1.6958,
|
| 12563 |
+
"mean_token_accuracy": 0.6611298769712448,
|
| 12564 |
+
"num_tokens": 25437618.0,
|
| 12565 |
+
"step": 6975
|
| 12566 |
+
},
|
| 12567 |
+
{
|
| 12568 |
+
"epoch": 53.69230769230769,
|
| 12569 |
+
"grad_norm": 0.0,
|
| 12570 |
+
"learning_rate": 1.5105e-05,
|
| 12571 |
+
"loss": 1.7339,
|
| 12572 |
+
"mean_token_accuracy": 0.6556006103754044,
|
| 12573 |
+
"num_tokens": 25455960.0,
|
| 12574 |
+
"step": 6980
|
| 12575 |
}
|
| 12576 |
],
|
| 12577 |
"logging_steps": 5,
|
|
|
|
| 12591 |
"attributes": {}
|
| 12592 |
}
|
| 12593 |
},
|
| 12594 |
+
"total_flos": 1.2907433073564058e+18,
|
| 12595 |
"train_batch_size": 4,
|
| 12596 |
"trial_name": null,
|
| 12597 |
"trial_params": null
|