Training in progress, step 2630, 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:b5144a38e11a67a8cd97e61c42de302a8650321a4739ff8fbcb0e79128f27b87
|
| 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 sha256:7b13452adf5acc61e19a2d8cd0a42d3e464119db61500f1b0e516dffaef983e6
|
| 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 sha256:25cc91e89b674a4a3310cb5160a44dd1d38b81d467e3fa71d570498119a9581a
|
| 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": 20.
|
| 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,
|
|
@@ -4724,6 +4724,24 @@
|
|
| 4724 |
"mean_token_accuracy": 0.6421493351459503,
|
| 4725 |
"num_tokens": 9554049.0,
|
| 4726 |
"step": 2620
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4727 |
}
|
| 4728 |
],
|
| 4729 |
"logging_steps": 5,
|
|
@@ -4743,7 +4761,7 @@
|
|
| 4743 |
"attributes": {}
|
| 4744 |
}
|
| 4745 |
},
|
| 4746 |
-
"total_flos": 4.
|
| 4747 |
"train_batch_size": 4,
|
| 4748 |
"trial_name": null,
|
| 4749 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 20.23076923076923,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 2630,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 4724 |
"mean_token_accuracy": 0.6421493351459503,
|
| 4725 |
"num_tokens": 9554049.0,
|
| 4726 |
"step": 2620
|
| 4727 |
+
},
|
| 4728 |
+
{
|
| 4729 |
+
"epoch": 20.192307692307693,
|
| 4730 |
+
"grad_norm": 0.0,
|
| 4731 |
+
"learning_rate": 3.6880000000000006e-05,
|
| 4732 |
+
"loss": 1.7075,
|
| 4733 |
+
"mean_token_accuracy": 0.6625353038311005,
|
| 4734 |
+
"num_tokens": 9572125.0,
|
| 4735 |
+
"step": 2625
|
| 4736 |
+
},
|
| 4737 |
+
{
|
| 4738 |
+
"epoch": 20.23076923076923,
|
| 4739 |
+
"grad_norm": 0.0,
|
| 4740 |
+
"learning_rate": 3.6855e-05,
|
| 4741 |
+
"loss": 1.7367,
|
| 4742 |
+
"mean_token_accuracy": 0.6516992777585984,
|
| 4743 |
+
"num_tokens": 9590370.0,
|
| 4744 |
+
"step": 2630
|
| 4745 |
}
|
| 4746 |
],
|
| 4747 |
"logging_steps": 5,
|
|
|
|
| 4761 |
"attributes": {}
|
| 4762 |
}
|
| 4763 |
},
|
| 4764 |
+
"total_flos": 4.860756813171917e+17,
|
| 4765 |
"train_batch_size": 4,
|
| 4766 |
"trial_name": null,
|
| 4767 |
"trial_params": null
|