Training in progress, step 9490, 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 sha256:1e3ca7799220f912988098a64e6fc7e473ba4df71efd4e64ac6ca8c7775a1bed
|
| 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 sha256:8ddf25f24922e324ed1ade8d250bcc23274cad1703e1dbfc55115d83482cde29
|
| 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 sha256:4da5c56bf592ca59aa02475c12794b2597ec0ab7c2570c36b49d82229b5baef6
|
| 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":
|
| 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,
|
|
@@ -17072,6 +17072,24 @@
|
|
| 17072 |
"mean_token_accuracy": 0.6599182695150375,
|
| 17073 |
"num_tokens": 34572061.0,
|
| 17074 |
"step": 9480
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 17075 |
}
|
| 17076 |
],
|
| 17077 |
"logging_steps": 5,
|
|
@@ -17091,7 +17109,7 @@
|
|
| 17091 |
"attributes": {}
|
| 17092 |
}
|
| 17093 |
},
|
| 17094 |
-
"total_flos": 1.
|
| 17095 |
"train_batch_size": 4,
|
| 17096 |
"trial_name": null,
|
| 17097 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 73.0,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 9490,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 17072 |
"mean_token_accuracy": 0.6599182695150375,
|
| 17073 |
"num_tokens": 34572061.0,
|
| 17074 |
"step": 9480
|
| 17075 |
+
},
|
| 17076 |
+
{
|
| 17077 |
+
"epoch": 72.96153846153847,
|
| 17078 |
+
"grad_norm": 0.0,
|
| 17079 |
+
"learning_rate": 2.5800000000000003e-06,
|
| 17080 |
+
"loss": 1.6874,
|
| 17081 |
+
"mean_token_accuracy": 0.6625257313251496,
|
| 17082 |
+
"num_tokens": 34590845.0,
|
| 17083 |
+
"step": 9485
|
| 17084 |
+
},
|
| 17085 |
+
{
|
| 17086 |
+
"epoch": 73.0,
|
| 17087 |
+
"grad_norm": 0.0,
|
| 17088 |
+
"learning_rate": 2.555e-06,
|
| 17089 |
+
"loss": 1.6979,
|
| 17090 |
+
"mean_token_accuracy": 0.6583450496196747,
|
| 17091 |
+
"num_tokens": 34609665.0,
|
| 17092 |
+
"step": 9490
|
| 17093 |
}
|
| 17094 |
],
|
| 17095 |
"logging_steps": 5,
|
|
|
|
| 17109 |
"attributes": {}
|
| 17110 |
}
|
| 17111 |
},
|
| 17112 |
+
"total_flos": 1.755043381441659e+18,
|
| 17113 |
"train_batch_size": 4,
|
| 17114 |
"trial_name": null,
|
| 17115 |
"trial_params": null
|