Training in progress, step 2780, 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 sha256:6bab3f1d0ef69111671550c65bf44cdbb1cec4b93a3c4d58f2c248bcaa503585
|
| 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 sha256:5fd79140a97a6b1fc0f4b243d51729aac89dd9dc05f86730e252c2ef7a18949b
|
| 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 sha256:475a4978313e8c49629e95a4505f140869cedc07e5d717597553e0a55b8a0691
|
| 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": 21.
|
| 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,
|
|
@@ -4994,6 +4994,24 @@
|
|
| 4994 |
"mean_token_accuracy": 0.6509008765220642,
|
| 4995 |
"num_tokens": 10100522.0,
|
| 4996 |
"step": 2770
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4997 |
}
|
| 4998 |
],
|
| 4999 |
"logging_steps": 5,
|
|
@@ -5013,7 +5031,7 @@
|
|
| 5013 |
"attributes": {}
|
| 5014 |
}
|
| 5015 |
},
|
| 5016 |
-
"total_flos": 5.
|
| 5017 |
"train_batch_size": 4,
|
| 5018 |
"trial_name": null,
|
| 5019 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 21.384615384615383,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 2780,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 4994 |
"mean_token_accuracy": 0.6509008765220642,
|
| 4995 |
"num_tokens": 10100522.0,
|
| 4996 |
"step": 2770
|
| 4997 |
+
},
|
| 4998 |
+
{
|
| 4999 |
+
"epoch": 21.346153846153847,
|
| 5000 |
+
"grad_norm": 0.0,
|
| 5001 |
+
"learning_rate": 3.613e-05,
|
| 5002 |
+
"loss": 1.7474,
|
| 5003 |
+
"mean_token_accuracy": 0.6551948994398117,
|
| 5004 |
+
"num_tokens": 10118325.0,
|
| 5005 |
+
"step": 2775
|
| 5006 |
+
},
|
| 5007 |
+
{
|
| 5008 |
+
"epoch": 21.384615384615383,
|
| 5009 |
+
"grad_norm": 0.0,
|
| 5010 |
+
"learning_rate": 3.6105e-05,
|
| 5011 |
+
"loss": 1.6998,
|
| 5012 |
+
"mean_token_accuracy": 0.6569103240966797,
|
| 5013 |
+
"num_tokens": 10137261.0,
|
| 5014 |
+
"step": 2780
|
| 5015 |
}
|
| 5016 |
],
|
| 5017 |
"logging_steps": 5,
|
|
|
|
| 5031 |
"attributes": {}
|
| 5032 |
}
|
| 5033 |
},
|
| 5034 |
+
"total_flos": 5.137040466586829e+17,
|
| 5035 |
"train_batch_size": 4,
|
| 5036 |
"trial_name": null,
|
| 5037 |
"trial_params": null
|