Training in progress, step 6450, 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 sha256:42b11b5c500b16af7ca4eb341747ee6cd3d8da4cef2aca4387e738324c5ed2d9
|
| 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:ad94b75a7d280df1c9243b8b24eb44da2cdf5f54dbec8f564a6c14abf8ac67d9
|
| 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:c14e2e5db571eb74395a9f570a47cd487ad5752288d9c1f4bdc01e96b249b279
|
| 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,
|
|
@@ -11600,6 +11600,24 @@
|
|
| 11600 |
"mean_token_accuracy": 0.6625799834728241,
|
| 11601 |
"num_tokens": 23485932.0,
|
| 11602 |
"step": 6440
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11603 |
}
|
| 11604 |
],
|
| 11605 |
"logging_steps": 5,
|
|
@@ -11619,7 +11637,7 @@
|
|
| 11619 |
"attributes": {}
|
| 11620 |
}
|
| 11621 |
},
|
| 11622 |
-
"total_flos": 1.
|
| 11623 |
"train_batch_size": 4,
|
| 11624 |
"trial_name": null,
|
| 11625 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 49.61538461538461,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 6450,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 11600 |
"mean_token_accuracy": 0.6625799834728241,
|
| 11601 |
"num_tokens": 23485932.0,
|
| 11602 |
"step": 6440
|
| 11603 |
+
},
|
| 11604 |
+
{
|
| 11605 |
+
"epoch": 49.57692307692308,
|
| 11606 |
+
"grad_norm": 0.0,
|
| 11607 |
+
"learning_rate": 1.7780000000000003e-05,
|
| 11608 |
+
"loss": 1.7437,
|
| 11609 |
+
"mean_token_accuracy": 0.6509669572114944,
|
| 11610 |
+
"num_tokens": 23504065.0,
|
| 11611 |
+
"step": 6445
|
| 11612 |
+
},
|
| 11613 |
+
{
|
| 11614 |
+
"epoch": 49.61538461538461,
|
| 11615 |
+
"grad_norm": 0.0,
|
| 11616 |
+
"learning_rate": 1.7755000000000002e-05,
|
| 11617 |
+
"loss": 1.705,
|
| 11618 |
+
"mean_token_accuracy": 0.6565153568983078,
|
| 11619 |
+
"num_tokens": 23522965.0,
|
| 11620 |
+
"step": 6450
|
| 11621 |
}
|
| 11622 |
],
|
| 11623 |
"logging_steps": 5,
|
|
|
|
| 11637 |
"attributes": {}
|
| 11638 |
}
|
| 11639 |
},
|
| 11640 |
+
"total_flos": 1.1923801025981645e+18,
|
| 11641 |
"train_batch_size": 4,
|
| 11642 |
"trial_name": null,
|
| 11643 |
"trial_params": null
|