Training in progress, step 6430, 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 sha256:16c28b25278abbe5ad99f8b05db007fdadbc2ecbae14aed06df46f50c2e1d0d6
|
| 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:f7f9dcc714820ddc1d166aa0f9ae42ae3f5c58b5326e3c5243f384fd8a7ac90f
|
| 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 sha256:4b11a87fd700c1a488979edfd360308b6b33244bd3beeb29a04049c3ba98edd1
|
| 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": 49.
|
| 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,
|
|
@@ -11564,6 +11564,24 @@
|
|
| 11564 |
"mean_token_accuracy": 0.6516094326972961,
|
| 11565 |
"num_tokens": 23413811.0,
|
| 11566 |
"step": 6420
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11567 |
}
|
| 11568 |
],
|
| 11569 |
"logging_steps": 5,
|
|
@@ -11583,7 +11601,7 @@
|
|
| 11583 |
"attributes": {}
|
| 11584 |
}
|
| 11585 |
},
|
| 11586 |
-
"total_flos": 1.
|
| 11587 |
"train_batch_size": 4,
|
| 11588 |
"trial_name": null,
|
| 11589 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 49.46153846153846,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 6430,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 11564 |
"mean_token_accuracy": 0.6516094326972961,
|
| 11565 |
"num_tokens": 23413811.0,
|
| 11566 |
"step": 6420
|
| 11567 |
+
},
|
| 11568 |
+
{
|
| 11569 |
+
"epoch": 49.42307692307692,
|
| 11570 |
+
"grad_norm": 0.0,
|
| 11571 |
+
"learning_rate": 1.7879999999999998e-05,
|
| 11572 |
+
"loss": 1.7673,
|
| 11573 |
+
"mean_token_accuracy": 0.6500208914279938,
|
| 11574 |
+
"num_tokens": 23431562.0,
|
| 11575 |
+
"step": 6425
|
| 11576 |
+
},
|
| 11577 |
+
{
|
| 11578 |
+
"epoch": 49.46153846153846,
|
| 11579 |
+
"grad_norm": 0.0,
|
| 11580 |
+
"learning_rate": 1.7855e-05,
|
| 11581 |
+
"loss": 1.7738,
|
| 11582 |
+
"mean_token_accuracy": 0.6465479761362076,
|
| 11583 |
+
"num_tokens": 23449644.0,
|
| 11584 |
+
"step": 6430
|
| 11585 |
}
|
| 11586 |
],
|
| 11587 |
"logging_steps": 5,
|
|
|
|
| 11601 |
"attributes": {}
|
| 11602 |
}
|
| 11603 |
},
|
| 11604 |
+
"total_flos": 1.1886435529496986e+18,
|
| 11605 |
"train_batch_size": 4,
|
| 11606 |
"trial_name": null,
|
| 11607 |
"trial_params": null
|