Upload checkpoint-200/trainer_state.json
Browse files
checkpoint-200/trainer_state.json
ADDED
|
@@ -0,0 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 200,
|
| 3 |
+
"best_metric": 0.9943728018757327,
|
| 4 |
+
"best_model_checkpoint": "/content/drive/MyDrive/model/roberta_model/checkpoint-200",
|
| 5 |
+
"epoch": 0.04689331770222743,
|
| 6 |
+
"eval_steps": 200,
|
| 7 |
+
"global_step": 200,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.00023446658851113716,
|
| 14 |
+
"grad_norm": 7.900483131408691,
|
| 15 |
+
"learning_rate": 0.0,
|
| 16 |
+
"loss": 1.2285,
|
| 17 |
+
"step": 1
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.023446658851113716,
|
| 21 |
+
"grad_norm": 2.4035584926605225,
|
| 22 |
+
"learning_rate": 2.9015240328253227e-06,
|
| 23 |
+
"loss": 0.9217,
|
| 24 |
+
"step": 100
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.04689331770222743,
|
| 28 |
+
"grad_norm": 0.31396016478538513,
|
| 29 |
+
"learning_rate": 5.832356389214537e-06,
|
| 30 |
+
"loss": 0.073,
|
| 31 |
+
"step": 200
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.04689331770222743,
|
| 35 |
+
"eval_accuracy": 0.9943728018757327,
|
| 36 |
+
"eval_f1_macro": 0.24929461556548319,
|
| 37 |
+
"eval_f1_weighted": 0.9915671414895327,
|
| 38 |
+
"eval_loss": 0.04064385965466499,
|
| 39 |
+
"eval_runtime": 57.486,
|
| 40 |
+
"eval_samples_per_second": 148.384,
|
| 41 |
+
"eval_steps_per_second": 9.289,
|
| 42 |
+
"step": 200
|
| 43 |
+
}
|
| 44 |
+
],
|
| 45 |
+
"logging_steps": 100,
|
| 46 |
+
"max_steps": 17060,
|
| 47 |
+
"num_input_tokens_seen": 0,
|
| 48 |
+
"num_train_epochs": 4,
|
| 49 |
+
"save_steps": 200,
|
| 50 |
+
"stateful_callbacks": {
|
| 51 |
+
"EarlyStoppingCallback": {
|
| 52 |
+
"args": {
|
| 53 |
+
"early_stopping_patience": 3,
|
| 54 |
+
"early_stopping_threshold": 0.001
|
| 55 |
+
},
|
| 56 |
+
"attributes": {
|
| 57 |
+
"early_stopping_patience_counter": 0
|
| 58 |
+
}
|
| 59 |
+
},
|
| 60 |
+
"TrainerControl": {
|
| 61 |
+
"args": {
|
| 62 |
+
"should_epoch_stop": false,
|
| 63 |
+
"should_evaluate": false,
|
| 64 |
+
"should_log": false,
|
| 65 |
+
"should_save": true,
|
| 66 |
+
"should_training_stop": false
|
| 67 |
+
},
|
| 68 |
+
"attributes": {}
|
| 69 |
+
}
|
| 70 |
+
},
|
| 71 |
+
"total_flos": 631483541913600.0,
|
| 72 |
+
"train_batch_size": 16,
|
| 73 |
+
"trial_name": null,
|
| 74 |
+
"trial_params": null
|
| 75 |
+
}
|