Training in progress, step 7640, 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 sha256:4c1508e672a711f3e275a334b3de6fe974567027388112cb45cf5f038a30d68f
|
| 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 sha256:3e8525db078b8e515c9773e2b021c4622c3ac2e2fc67c88258e628e5bb896231
|
| 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 sha256:10267d884c25cb661d011c78a6c32de3079a7c5257691de76cf15e82ef6ca0d4
|
| 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,
|
|
@@ -13742,6 +13742,24 @@
|
|
| 13742 |
"mean_token_accuracy": 0.6421011120080948,
|
| 13743 |
"num_tokens": 27825718.0,
|
| 13744 |
"step": 7630
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 13745 |
}
|
| 13746 |
],
|
| 13747 |
"logging_steps": 5,
|
|
@@ -13761,7 +13779,7 @@
|
|
| 13761 |
"attributes": {}
|
| 13762 |
}
|
| 13763 |
},
|
| 13764 |
-
"total_flos": 1.
|
| 13765 |
"train_batch_size": 4,
|
| 13766 |
"trial_name": null,
|
| 13767 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 58.76923076923077,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 7640,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 13742 |
"mean_token_accuracy": 0.6421011120080948,
|
| 13743 |
"num_tokens": 27825718.0,
|
| 13744 |
"step": 7630
|
| 13745 |
+
},
|
| 13746 |
+
{
|
| 13747 |
+
"epoch": 58.73076923076923,
|
| 13748 |
+
"grad_norm": 0.0,
|
| 13749 |
+
"learning_rate": 1.183e-05,
|
| 13750 |
+
"loss": 1.7286,
|
| 13751 |
+
"mean_token_accuracy": 0.6499491780996323,
|
| 13752 |
+
"num_tokens": 27843945.0,
|
| 13753 |
+
"step": 7635
|
| 13754 |
+
},
|
| 13755 |
+
{
|
| 13756 |
+
"epoch": 58.76923076923077,
|
| 13757 |
+
"grad_norm": 0.0,
|
| 13758 |
+
"learning_rate": 1.1805000000000001e-05,
|
| 13759 |
+
"loss": 1.7409,
|
| 13760 |
+
"mean_token_accuracy": 0.6533534795045852,
|
| 13761 |
+
"num_tokens": 27862495.0,
|
| 13762 |
+
"step": 7640
|
| 13763 |
}
|
| 13764 |
],
|
| 13765 |
"logging_steps": 5,
|
|
|
|
| 13779 |
"attributes": {}
|
| 13780 |
}
|
| 13781 |
},
|
| 13782 |
+
"total_flos": 1.412661398459351e+18,
|
| 13783 |
"train_batch_size": 4,
|
| 13784 |
"trial_name": null,
|
| 13785 |
"trial_params": null
|