Training in progress, step 9330, 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:b3f9f1fdaee4a11e91a19e68a899781abcf1eef1c5c2bd1aed604f2ed21256b4
|
| 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 sha256:90cb24ff9583e40f8006a0c700fbf51a60c42b93a282dbc3f6b387e057cce020
|
| 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:b95d93ff5f5af2eff9f98ca997ba30aa34d3e0968f4c3ca9853f6edd97e4875b
|
| 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": 71.
|
| 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,
|
|
@@ -16784,6 +16784,24 @@
|
|
| 16784 |
"mean_token_accuracy": 0.6501501977443696,
|
| 16785 |
"num_tokens": 33991262.0,
|
| 16786 |
"step": 9320
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 16787 |
}
|
| 16788 |
],
|
| 16789 |
"logging_steps": 5,
|
|
@@ -16803,7 +16821,7 @@
|
|
| 16803 |
"attributes": {}
|
| 16804 |
}
|
| 16805 |
},
|
| 16806 |
-
"total_flos": 1.
|
| 16807 |
"train_batch_size": 4,
|
| 16808 |
"trial_name": null,
|
| 16809 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 71.76923076923077,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 9330,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 16784 |
"mean_token_accuracy": 0.6501501977443696,
|
| 16785 |
"num_tokens": 33991262.0,
|
| 16786 |
"step": 9320
|
| 16787 |
+
},
|
| 16788 |
+
{
|
| 16789 |
+
"epoch": 71.73076923076923,
|
| 16790 |
+
"grad_norm": 0.0,
|
| 16791 |
+
"learning_rate": 3.38e-06,
|
| 16792 |
+
"loss": 1.6826,
|
| 16793 |
+
"mean_token_accuracy": 0.6632235527038575,
|
| 16794 |
+
"num_tokens": 34010592.0,
|
| 16795 |
+
"step": 9325
|
| 16796 |
+
},
|
| 16797 |
+
{
|
| 16798 |
+
"epoch": 71.76923076923077,
|
| 16799 |
+
"grad_norm": 0.0,
|
| 16800 |
+
"learning_rate": 3.3550000000000005e-06,
|
| 16801 |
+
"loss": 1.7825,
|
| 16802 |
+
"mean_token_accuracy": 0.6419746041297912,
|
| 16803 |
+
"num_tokens": 34028492.0,
|
| 16804 |
+
"step": 9330
|
| 16805 |
}
|
| 16806 |
],
|
| 16807 |
"logging_steps": 5,
|
|
|
|
| 16821 |
"attributes": {}
|
| 16822 |
}
|
| 16823 |
},
|
| 16824 |
+
"total_flos": 1.725613825465221e+18,
|
| 16825 |
"train_batch_size": 4,
|
| 16826 |
"trial_name": null,
|
| 16827 |
"trial_params": null
|