Training in progress, step 4450, 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 sha256:2b4cc577e3a3be45fbd3e8dabc4f343c49733f2cdbfa7d897cca88de90eff8f9
|
| 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 sha256:54ff1962a2e802e90d6898652e6f769108a41896aa4f5b3d69d67bc81759fe05
|
| 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 sha256:079fccebe61507ee0c7b79c3c9e0083fee33510c58b7cae0295b83b04aa00626
|
| 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": 34.
|
| 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,
|
|
@@ -8000,6 +8000,24 @@
|
|
| 8000 |
"mean_token_accuracy": 0.6575721591711045,
|
| 8001 |
"num_tokens": 16194451.0,
|
| 8002 |
"step": 4440
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8003 |
}
|
| 8004 |
],
|
| 8005 |
"logging_steps": 5,
|
|
@@ -8019,7 +8037,7 @@
|
|
| 8019 |
"attributes": {}
|
| 8020 |
}
|
| 8021 |
},
|
| 8022 |
-
"total_flos": 8.
|
| 8023 |
"train_batch_size": 4,
|
| 8024 |
"trial_name": null,
|
| 8025 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 34.23076923076923,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 4450,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 8000 |
"mean_token_accuracy": 0.6575721591711045,
|
| 8001 |
"num_tokens": 16194451.0,
|
| 8002 |
"step": 4440
|
| 8003 |
+
},
|
| 8004 |
+
{
|
| 8005 |
+
"epoch": 34.19230769230769,
|
| 8006 |
+
"grad_norm": 0.0,
|
| 8007 |
+
"learning_rate": 2.778e-05,
|
| 8008 |
+
"loss": 1.751,
|
| 8009 |
+
"mean_token_accuracy": 0.6504880547523498,
|
| 8010 |
+
"num_tokens": 16212789.0,
|
| 8011 |
+
"step": 4445
|
| 8012 |
+
},
|
| 8013 |
+
{
|
| 8014 |
+
"epoch": 34.23076923076923,
|
| 8015 |
+
"grad_norm": 0.0,
|
| 8016 |
+
"learning_rate": 2.7755000000000004e-05,
|
| 8017 |
+
"loss": 1.8498,
|
| 8018 |
+
"mean_token_accuracy": 0.6282713234424591,
|
| 8019 |
+
"num_tokens": 16230046.0,
|
| 8020 |
+
"step": 4450
|
| 8021 |
}
|
| 8022 |
],
|
| 8023 |
"logging_steps": 5,
|
|
|
|
| 8037 |
"attributes": {}
|
| 8038 |
}
|
| 8039 |
},
|
| 8040 |
+
"total_flos": 8.224909027629466e+17,
|
| 8041 |
"train_batch_size": 4,
|
| 8042 |
"trial_name": null,
|
| 8043 |
"trial_params": null
|