Training in progress, step 4280, 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:a073a3b687ba26bc3adb345ad0cf3623c830268e3a7fddcdb42219d310902fdd
|
| 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 sha256:44ce0a73d3ecba92a95b6ee76ca95f2985e1958db1af0efdc6dc7bb100ba7e98
|
| 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 sha256:83f1052b507b0c40af2fd79ab365ab6898136f60cef57e9b13d359bde185c21c
|
| 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": 32.
|
| 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,
|
|
@@ -7694,6 +7694,24 @@
|
|
| 7694 |
"mean_token_accuracy": 0.6468859910964966,
|
| 7695 |
"num_tokens": 15573396.0,
|
| 7696 |
"step": 4270
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7697 |
}
|
| 7698 |
],
|
| 7699 |
"logging_steps": 5,
|
|
@@ -7713,7 +7731,7 @@
|
|
| 7713 |
"attributes": {}
|
| 7714 |
}
|
| 7715 |
},
|
| 7716 |
-
"total_flos": 7.
|
| 7717 |
"train_batch_size": 4,
|
| 7718 |
"trial_name": null,
|
| 7719 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 32.92307692307692,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 4280,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 7694 |
"mean_token_accuracy": 0.6468859910964966,
|
| 7695 |
"num_tokens": 15573396.0,
|
| 7696 |
"step": 4270
|
| 7697 |
+
},
|
| 7698 |
+
{
|
| 7699 |
+
"epoch": 32.88461538461539,
|
| 7700 |
+
"grad_norm": 0.0,
|
| 7701 |
+
"learning_rate": 2.8630000000000002e-05,
|
| 7702 |
+
"loss": 1.7352,
|
| 7703 |
+
"mean_token_accuracy": 0.654278576374054,
|
| 7704 |
+
"num_tokens": 15592035.0,
|
| 7705 |
+
"step": 4275
|
| 7706 |
+
},
|
| 7707 |
+
{
|
| 7708 |
+
"epoch": 32.92307692307692,
|
| 7709 |
+
"grad_norm": 0.0,
|
| 7710 |
+
"learning_rate": 2.8605000000000005e-05,
|
| 7711 |
+
"loss": 1.7305,
|
| 7712 |
+
"mean_token_accuracy": 0.6594868719577789,
|
| 7713 |
+
"num_tokens": 15610531.0,
|
| 7714 |
+
"step": 4280
|
| 7715 |
}
|
| 7716 |
],
|
| 7717 |
"logging_steps": 5,
|
|
|
|
| 7731 |
"attributes": {}
|
| 7732 |
}
|
| 7733 |
},
|
| 7734 |
+
"total_flos": 7.911688581424742e+17,
|
| 7735 |
"train_batch_size": 4,
|
| 7736 |
"trial_name": null,
|
| 7737 |
"trial_params": null
|