Training in progress, step 7620, 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:d9410d0a2e5dda547d5401da33a35791a9871ede6db0279a332e0eac8f317129
|
| 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 sha256:0f9247142e228ed8ab111250b63610dfa973256c11a9c70800530e62934a8016
|
| 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 sha256:2261d107efedd2ae471ccf05b84c5393306f823f20e726b1b22c08af6c224092
|
| 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": 58.
|
| 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,
|
|
@@ -13706,6 +13706,24 @@
|
|
| 13706 |
"mean_token_accuracy": 0.6518133997917175,
|
| 13707 |
"num_tokens": 27750713.0,
|
| 13708 |
"step": 7610
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 13709 |
}
|
| 13710 |
],
|
| 13711 |
"logging_steps": 5,
|
|
@@ -13725,7 +13743,7 @@
|
|
| 13725 |
"attributes": {}
|
| 13726 |
}
|
| 13727 |
},
|
| 13728 |
-
"total_flos": 1.
|
| 13729 |
"train_batch_size": 4,
|
| 13730 |
"trial_name": null,
|
| 13731 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 58.61538461538461,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 7620,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 13706 |
"mean_token_accuracy": 0.6518133997917175,
|
| 13707 |
"num_tokens": 27750713.0,
|
| 13708 |
"step": 7610
|
| 13709 |
+
},
|
| 13710 |
+
{
|
| 13711 |
+
"epoch": 58.57692307692308,
|
| 13712 |
+
"grad_norm": 0.0,
|
| 13713 |
+
"learning_rate": 1.1930000000000001e-05,
|
| 13714 |
+
"loss": 1.7286,
|
| 13715 |
+
"mean_token_accuracy": 0.6503622680902481,
|
| 13716 |
+
"num_tokens": 27769167.0,
|
| 13717 |
+
"step": 7615
|
| 13718 |
+
},
|
| 13719 |
+
{
|
| 13720 |
+
"epoch": 58.61538461538461,
|
| 13721 |
+
"grad_norm": 0.0,
|
| 13722 |
+
"learning_rate": 1.1905e-05,
|
| 13723 |
+
"loss": 1.6179,
|
| 13724 |
+
"mean_token_accuracy": 0.676550367474556,
|
| 13725 |
+
"num_tokens": 27788253.0,
|
| 13726 |
+
"step": 7620
|
| 13727 |
}
|
| 13728 |
],
|
| 13729 |
"logging_steps": 5,
|
|
|
|
| 13743 |
"attributes": {}
|
| 13744 |
}
|
| 13745 |
},
|
| 13746 |
+
"total_flos": 1.408869276109701e+18,
|
| 13747 |
"train_batch_size": 4,
|
| 13748 |
"trial_name": null,
|
| 13749 |
"trial_params": null
|