Training in progress, step 2050, 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 sha256:21f2d9ef4b09f594e5e6e1ee9f75ffcbdbfa56ace0bd4bf4151264c73e945bea
|
| 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 sha256:41ba2b9ed35f39ce24d05b2b5b2aa858363871e673d1d2f08061fcab960fbab7
|
| 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 sha256:548d4fff0686ba3fee9372424b14d8f360eaf4db34787cc2c145056559522914
|
| 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": 15.
|
| 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,
|
|
@@ -3680,6 +3680,24 @@
|
|
| 3680 |
"mean_token_accuracy": 0.6589993953704834,
|
| 3681 |
"num_tokens": 7438755.0,
|
| 3682 |
"step": 2040
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3683 |
}
|
| 3684 |
],
|
| 3685 |
"logging_steps": 5,
|
|
@@ -3699,7 +3717,7 @@
|
|
| 3699 |
"attributes": {}
|
| 3700 |
}
|
| 3701 |
},
|
| 3702 |
-
"total_flos": 3.
|
| 3703 |
"train_batch_size": 4,
|
| 3704 |
"trial_name": null,
|
| 3705 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 15.76923076923077,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 2050,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 3680 |
"mean_token_accuracy": 0.6589993953704834,
|
| 3681 |
"num_tokens": 7438755.0,
|
| 3682 |
"step": 2040
|
| 3683 |
+
},
|
| 3684 |
+
{
|
| 3685 |
+
"epoch": 15.73076923076923,
|
| 3686 |
+
"grad_norm": 0.0,
|
| 3687 |
+
"learning_rate": 3.978e-05,
|
| 3688 |
+
"loss": 1.741,
|
| 3689 |
+
"mean_token_accuracy": 0.6524647355079651,
|
| 3690 |
+
"num_tokens": 7456837.0,
|
| 3691 |
+
"step": 2045
|
| 3692 |
+
},
|
| 3693 |
+
{
|
| 3694 |
+
"epoch": 15.76923076923077,
|
| 3695 |
+
"grad_norm": 0.0,
|
| 3696 |
+
"learning_rate": 3.9755e-05,
|
| 3697 |
+
"loss": 1.8081,
|
| 3698 |
+
"mean_token_accuracy": 0.6410402476787567,
|
| 3699 |
+
"num_tokens": 7473972.0,
|
| 3700 |
+
"step": 2050
|
| 3701 |
}
|
| 3702 |
],
|
| 3703 |
"logging_steps": 5,
|
|
|
|
| 3717 |
"attributes": {}
|
| 3718 |
}
|
| 3719 |
},
|
| 3720 |
+
"total_flos": 3.786506331247411e+17,
|
| 3721 |
"train_batch_size": 4,
|
| 3722 |
"trial_name": null,
|
| 3723 |
"trial_params": null
|