Training in progress, step 9150, 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 sha256:1402c933f486ac99967d844be16cc6b2f29c3f343be948d2a79a69221bcd0366
|
| 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:af1a1dac5b4918c6f46c386fccc95a838532ee912cf0a6ef9a00e37c62a660e2
|
| 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 sha256:07c179bd0411eaed4004eca8f00c29e1ce9f8ca922652766b25eb7db861fc3b7
|
| 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": 70.
|
| 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,
|
|
@@ -16460,6 +16460,24 @@
|
|
| 16460 |
"mean_token_accuracy": 0.649817219376564,
|
| 16461 |
"num_tokens": 33336143.0,
|
| 16462 |
"step": 9140
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 16463 |
}
|
| 16464 |
],
|
| 16465 |
"logging_steps": 5,
|
|
@@ -16479,7 +16497,7 @@
|
|
| 16479 |
"attributes": {}
|
| 16480 |
}
|
| 16481 |
},
|
| 16482 |
-
"total_flos": 1.
|
| 16483 |
"train_batch_size": 4,
|
| 16484 |
"trial_name": null,
|
| 16485 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 70.38461538461539,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 9150,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 16460 |
"mean_token_accuracy": 0.649817219376564,
|
| 16461 |
"num_tokens": 33336143.0,
|
| 16462 |
"step": 9140
|
| 16463 |
+
},
|
| 16464 |
+
{
|
| 16465 |
+
"epoch": 70.34615384615384,
|
| 16466 |
+
"grad_norm": 0.0,
|
| 16467 |
+
"learning_rate": 4.28e-06,
|
| 16468 |
+
"loss": 1.7933,
|
| 16469 |
+
"mean_token_accuracy": 0.6456594437360763,
|
| 16470 |
+
"num_tokens": 33353477.0,
|
| 16471 |
+
"step": 9145
|
| 16472 |
+
},
|
| 16473 |
+
{
|
| 16474 |
+
"epoch": 70.38461538461539,
|
| 16475 |
+
"grad_norm": 0.0,
|
| 16476 |
+
"learning_rate": 4.255e-06,
|
| 16477 |
+
"loss": 1.7628,
|
| 16478 |
+
"mean_token_accuracy": 0.6442059248685836,
|
| 16479 |
+
"num_tokens": 33371827.0,
|
| 16480 |
+
"step": 9150
|
| 16481 |
}
|
| 16482 |
],
|
| 16483 |
"logging_steps": 5,
|
|
|
|
| 16497 |
"attributes": {}
|
| 16498 |
}
|
| 16499 |
},
|
| 16500 |
+
"total_flos": 1.692234320667771e+18,
|
| 16501 |
"train_batch_size": 4,
|
| 16502 |
"trial_name": null,
|
| 16503 |
"trial_params": null
|