Upload trainer_state.json with huggingface_hub
Browse files- trainer_state.json +54 -0
trainer_state.json
ADDED
|
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 234,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.64,
|
| 13 |
+
"learning_rate": 1.5726495726495726e-05,
|
| 14 |
+
"loss": 0.723,
|
| 15 |
+
"step": 50
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 1.28,
|
| 19 |
+
"learning_rate": 1.1452991452991454e-05,
|
| 20 |
+
"loss": 0.6984,
|
| 21 |
+
"step": 100
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 1.92,
|
| 25 |
+
"learning_rate": 7.17948717948718e-06,
|
| 26 |
+
"loss": 0.6927,
|
| 27 |
+
"step": 150
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 2.56,
|
| 31 |
+
"learning_rate": 2.9059829059829063e-06,
|
| 32 |
+
"loss": 0.6454,
|
| 33 |
+
"step": 200
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 3.0,
|
| 37 |
+
"step": 234,
|
| 38 |
+
"total_flos": 3117081067848216.0,
|
| 39 |
+
"train_loss": 0.6812209675454686,
|
| 40 |
+
"train_runtime": 234.5865,
|
| 41 |
+
"train_samples_per_second": 31.843,
|
| 42 |
+
"train_steps_per_second": 0.997
|
| 43 |
+
}
|
| 44 |
+
],
|
| 45 |
+
"logging_steps": 50,
|
| 46 |
+
"max_steps": 234,
|
| 47 |
+
"num_input_tokens_seen": 0,
|
| 48 |
+
"num_train_epochs": 3,
|
| 49 |
+
"save_steps": 500,
|
| 50 |
+
"total_flos": 3117081067848216.0,
|
| 51 |
+
"train_batch_size": 32,
|
| 52 |
+
"trial_name": null,
|
| 53 |
+
"trial_params": null
|
| 54 |
+
}
|