Training in progress, step 30, 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:de4437decf89efd5665f9257674ebf7ce74620bc4e47cd0bf24e9e593dd76f22
|
| 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 sha256:49559d54e9cacf6481f645434de320f34286a1e8d87f66a7d91f2ac9f5eb2c49
|
| 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:e465f188039be06a052aaa57dc8572a86905de55c9ad3a7b125efe825b8f1df0
|
| 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,
|
|
@@ -44,6 +44,24 @@
|
|
| 44 |
"mean_token_accuracy": 0.6484396398067475,
|
| 45 |
"num_tokens": 71860.0,
|
| 46 |
"step": 20
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 47 |
}
|
| 48 |
],
|
| 49 |
"logging_steps": 5,
|
|
@@ -63,7 +81,7 @@
|
|
| 63 |
"attributes": {}
|
| 64 |
}
|
| 65 |
},
|
| 66 |
-
"total_flos":
|
| 67 |
"train_batch_size": 4,
|
| 68 |
"trial_name": null,
|
| 69 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.23076923076923078,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 30,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 44 |
"mean_token_accuracy": 0.6484396398067475,
|
| 45 |
"num_tokens": 71860.0,
|
| 46 |
"step": 20
|
| 47 |
+
},
|
| 48 |
+
{
|
| 49 |
+
"epoch": 0.19230769230769232,
|
| 50 |
+
"grad_norm": 0.0,
|
| 51 |
+
"learning_rate": 4.9880000000000004e-05,
|
| 52 |
+
"loss": 1.669,
|
| 53 |
+
"mean_token_accuracy": 0.6693991690874099,
|
| 54 |
+
"num_tokens": 90064.0,
|
| 55 |
+
"step": 25
|
| 56 |
+
},
|
| 57 |
+
{
|
| 58 |
+
"epoch": 0.23076923076923078,
|
| 59 |
+
"grad_norm": 0.0,
|
| 60 |
+
"learning_rate": 4.9855e-05,
|
| 61 |
+
"loss": 1.7247,
|
| 62 |
+
"mean_token_accuracy": 0.6533850133419037,
|
| 63 |
+
"num_tokens": 108700.0,
|
| 64 |
+
"step": 30
|
| 65 |
}
|
| 66 |
],
|
| 67 |
"logging_steps": 5,
|
|
|
|
| 81 |
"attributes": {}
|
| 82 |
}
|
| 83 |
},
|
| 84 |
+
"total_flos": 5475340078940160.0,
|
| 85 |
"train_batch_size": 4,
|
| 86 |
"trial_name": null,
|
| 87 |
"trial_params": null
|