Commit
•
7ee74cb
1
Parent(s):
fa298a8
End of training
Browse files
runs/Feb26_20-23-38_b0051077c075/events.out.tfevents.1677443024.b0051077c075.1132.4
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e635546e379d75f8355e3d5e91a2a056e1425d46227b909bcfc0ae2c17ad38b2
|
| 3 |
+
size 6582
|
trainer_state.json
ADDED
|
@@ -0,0 +1,95 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 5.0,
|
| 5 |
+
"global_step": 470,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 1.0,
|
| 12 |
+
"learning_rate": 8e-05,
|
| 13 |
+
"loss": 3.4965,
|
| 14 |
+
"step": 94
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 1.0,
|
| 18 |
+
"eval_loss": 2.779850721359253,
|
| 19 |
+
"eval_runtime": 23.1518,
|
| 20 |
+
"eval_samples_per_second": 8.639,
|
| 21 |
+
"eval_steps_per_second": 1.08,
|
| 22 |
+
"step": 94
|
| 23 |
+
},
|
| 24 |
+
{
|
| 25 |
+
"epoch": 2.0,
|
| 26 |
+
"learning_rate": 6e-05,
|
| 27 |
+
"loss": 3.4526,
|
| 28 |
+
"step": 188
|
| 29 |
+
},
|
| 30 |
+
{
|
| 31 |
+
"epoch": 2.0,
|
| 32 |
+
"eval_loss": 2.738048791885376,
|
| 33 |
+
"eval_runtime": 24.2844,
|
| 34 |
+
"eval_samples_per_second": 8.236,
|
| 35 |
+
"eval_steps_per_second": 1.029,
|
| 36 |
+
"step": 188
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"epoch": 3.0,
|
| 40 |
+
"learning_rate": 4e-05,
|
| 41 |
+
"loss": 3.4012,
|
| 42 |
+
"step": 282
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 3.0,
|
| 46 |
+
"eval_loss": 2.6721441745758057,
|
| 47 |
+
"eval_runtime": 23.2045,
|
| 48 |
+
"eval_samples_per_second": 8.619,
|
| 49 |
+
"eval_steps_per_second": 1.077,
|
| 50 |
+
"step": 282
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 4.0,
|
| 54 |
+
"learning_rate": 2e-05,
|
| 55 |
+
"loss": 3.2776,
|
| 56 |
+
"step": 376
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 4.0,
|
| 60 |
+
"eval_loss": 2.6650607585906982,
|
| 61 |
+
"eval_runtime": 24.0682,
|
| 62 |
+
"eval_samples_per_second": 8.31,
|
| 63 |
+
"eval_steps_per_second": 1.039,
|
| 64 |
+
"step": 376
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 5.0,
|
| 68 |
+
"learning_rate": 0.0,
|
| 69 |
+
"loss": 3.2164,
|
| 70 |
+
"step": 470
|
| 71 |
+
},
|
| 72 |
+
{
|
| 73 |
+
"epoch": 5.0,
|
| 74 |
+
"eval_loss": 2.6554956436157227,
|
| 75 |
+
"eval_runtime": 22.8547,
|
| 76 |
+
"eval_samples_per_second": 8.751,
|
| 77 |
+
"eval_steps_per_second": 1.094,
|
| 78 |
+
"step": 470
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 5.0,
|
| 82 |
+
"step": 470,
|
| 83 |
+
"total_flos": 1.1450900938752e+17,
|
| 84 |
+
"train_loss": 3.3688572660405587,
|
| 85 |
+
"train_runtime": 692.9876,
|
| 86 |
+
"train_samples_per_second": 5.411,
|
| 87 |
+
"train_steps_per_second": 0.678
|
| 88 |
+
}
|
| 89 |
+
],
|
| 90 |
+
"max_steps": 470,
|
| 91 |
+
"num_train_epochs": 5,
|
| 92 |
+
"total_flos": 1.1450900938752e+17,
|
| 93 |
+
"trial_name": null,
|
| 94 |
+
"trial_params": null
|
| 95 |
+
}
|