Training in progress, step 40, 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 sha256:50612d39a96ad270d6d8c5e42a383c3bc80511699eb89ba140ce01ffa1aabd0b
|
| 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 sha256:9c5b1477a573f74ca14df4f1f51b259437c4cf605061fc54a93fd377f656b2a9
|
| 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 sha256:483b4af8b862aa037e57e4e8a409c9695fdfb55ba1d142ee51278fb88f739e3c
|
| 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": 0.
|
| 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,
|
|
@@ -62,6 +62,24 @@
|
|
| 62 |
"mean_token_accuracy": 0.6533850133419037,
|
| 63 |
"num_tokens": 108700.0,
|
| 64 |
"step": 30
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 65 |
}
|
| 66 |
],
|
| 67 |
"logging_steps": 5,
|
|
@@ -81,7 +99,7 @@
|
|
| 81 |
"attributes": {}
|
| 82 |
}
|
| 83 |
},
|
| 84 |
-
"total_flos":
|
| 85 |
"train_batch_size": 4,
|
| 86 |
"trial_name": null,
|
| 87 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.3076923076923077,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 40,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 62 |
"mean_token_accuracy": 0.6533850133419037,
|
| 63 |
"num_tokens": 108700.0,
|
| 64 |
"step": 30
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 0.2692307692307692,
|
| 68 |
+
"grad_norm": 0.0,
|
| 69 |
+
"learning_rate": 4.983e-05,
|
| 70 |
+
"loss": 1.7422,
|
| 71 |
+
"mean_token_accuracy": 0.6492581188678741,
|
| 72 |
+
"num_tokens": 126746.0,
|
| 73 |
+
"step": 35
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.3076923076923077,
|
| 77 |
+
"grad_norm": 0.0,
|
| 78 |
+
"learning_rate": 4.9805e-05,
|
| 79 |
+
"loss": 1.8267,
|
| 80 |
+
"mean_token_accuracy": 0.6348982483148575,
|
| 81 |
+
"num_tokens": 144478.0,
|
| 82 |
+
"step": 40
|
| 83 |
}
|
| 84 |
],
|
| 85 |
"logging_steps": 5,
|
|
|
|
| 99 |
"attributes": {}
|
| 100 |
}
|
| 101 |
},
|
| 102 |
+
"total_flos": 7246203896954880.0,
|
| 103 |
"train_batch_size": 4,
|
| 104 |
"trial_name": null,
|
| 105 |
"trial_params": null
|