Training in progress, step 3750, 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 sha256:5cc88f39188c982b92c7b55e7512d13ee7ac945d0254e22cd3cfb10e6ceabaf6
|
| 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 sha256:6a0dbdc83ed19560f3fda7ee35193fbd4e299da15af271a67bb3f07182d028d9
|
| 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 sha256:8414541636d1c53bd42f7f0f334c01c89868b680ad9e1ac39e99d475df0eec01
|
| 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": 28.
|
| 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,
|
|
@@ -6740,6 +6740,24 @@
|
|
| 6740 |
"mean_token_accuracy": 0.6618104815483093,
|
| 6741 |
"num_tokens": 13640943.0,
|
| 6742 |
"step": 3740
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6743 |
}
|
| 6744 |
],
|
| 6745 |
"logging_steps": 5,
|
|
@@ -6759,7 +6777,7 @@
|
|
| 6759 |
"attributes": {}
|
| 6760 |
}
|
| 6761 |
},
|
| 6762 |
-
"total_flos": 6.
|
| 6763 |
"train_batch_size": 4,
|
| 6764 |
"trial_name": null,
|
| 6765 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 28.846153846153847,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 3750,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 6740 |
"mean_token_accuracy": 0.6618104815483093,
|
| 6741 |
"num_tokens": 13640943.0,
|
| 6742 |
"step": 3740
|
| 6743 |
+
},
|
| 6744 |
+
{
|
| 6745 |
+
"epoch": 28.807692307692307,
|
| 6746 |
+
"grad_norm": 0.0,
|
| 6747 |
+
"learning_rate": 3.1280000000000005e-05,
|
| 6748 |
+
"loss": 1.8519,
|
| 6749 |
+
"mean_token_accuracy": 0.6293092161417008,
|
| 6750 |
+
"num_tokens": 13658372.0,
|
| 6751 |
+
"step": 3745
|
| 6752 |
+
},
|
| 6753 |
+
{
|
| 6754 |
+
"epoch": 28.846153846153847,
|
| 6755 |
+
"grad_norm": 0.0,
|
| 6756 |
+
"learning_rate": 3.1255e-05,
|
| 6757 |
+
"loss": 1.7723,
|
| 6758 |
+
"mean_token_accuracy": 0.6427496522665024,
|
| 6759 |
+
"num_tokens": 13676355.0,
|
| 6760 |
+
"step": 3750
|
| 6761 |
}
|
| 6762 |
],
|
| 6763 |
"logging_steps": 5,
|
|
|
|
| 6777 |
"attributes": {}
|
| 6778 |
}
|
| 6779 |
},
|
| 6780 |
+
"total_flos": 6.931030467251405e+17,
|
| 6781 |
"train_batch_size": 4,
|
| 6782 |
"trial_name": null,
|
| 6783 |
"trial_params": null
|