End of training
Browse files- all_results.json +8 -0
- train_results.json +8 -0
- trainer_state.json +68 -0
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"total_flos": 0.0,
|
| 4 |
+
"train_loss": 0.6899445915222168,
|
| 5 |
+
"train_runtime": 172.2338,
|
| 6 |
+
"train_samples_per_second": 0.581,
|
| 7 |
+
"train_steps_per_second": 0.145
|
| 8 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"total_flos": 0.0,
|
| 4 |
+
"train_loss": 0.6899445915222168,
|
| 5 |
+
"train_runtime": 172.2338,
|
| 6 |
+
"train_samples_per_second": 0.581,
|
| 7 |
+
"train_steps_per_second": 0.145
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,68 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.8499896205743283,
|
| 3 |
+
"best_model_checkpoint": "/kaggle/working/short_name/checkpoint-1",
|
| 4 |
+
"epoch": 0.04,
|
| 5 |
+
"eval_steps": 1,
|
| 6 |
+
"global_step": 1,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.04,
|
| 13 |
+
"grad_norm": 1.5162408351898193,
|
| 14 |
+
"learning_rate": 6e-06,
|
| 15 |
+
"loss": 0.6767,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.04,
|
| 20 |
+
"eval_EER": 0.27272727272733843,
|
| 21 |
+
"eval_FN": 21,
|
| 22 |
+
"eval_FP": 0,
|
| 23 |
+
"eval_TN": 178,
|
| 24 |
+
"eval_TP": 1,
|
| 25 |
+
"eval_accuracy": 0.895,
|
| 26 |
+
"eval_auc_roc": 0.7295709908069459,
|
| 27 |
+
"eval_f1": 0.8499896205743283,
|
| 28 |
+
"eval_loss": 0.5552121996879578,
|
| 29 |
+
"eval_min_tDCF": 0.028064351378958123,
|
| 30 |
+
"eval_precision": 0.9060804020100502,
|
| 31 |
+
"eval_recall": 0.895,
|
| 32 |
+
"eval_runtime": 66.7052,
|
| 33 |
+
"eval_samples_per_second": 2.998,
|
| 34 |
+
"eval_steps_per_second": 2.998,
|
| 35 |
+
"step": 1
|
| 36 |
+
}
|
| 37 |
+
],
|
| 38 |
+
"logging_steps": 1,
|
| 39 |
+
"max_steps": 50,
|
| 40 |
+
"num_input_tokens_seen": 0,
|
| 41 |
+
"num_train_epochs": 2,
|
| 42 |
+
"save_steps": 1,
|
| 43 |
+
"stateful_callbacks": {
|
| 44 |
+
"EarlyStoppingCallback": {
|
| 45 |
+
"args": {
|
| 46 |
+
"early_stopping_patience": 2,
|
| 47 |
+
"early_stopping_threshold": 0.0
|
| 48 |
+
},
|
| 49 |
+
"attributes": {
|
| 50 |
+
"early_stopping_patience_counter": 0
|
| 51 |
+
}
|
| 52 |
+
},
|
| 53 |
+
"TrainerControl": {
|
| 54 |
+
"args": {
|
| 55 |
+
"should_epoch_stop": false,
|
| 56 |
+
"should_evaluate": false,
|
| 57 |
+
"should_log": false,
|
| 58 |
+
"should_save": true,
|
| 59 |
+
"should_training_stop": false
|
| 60 |
+
},
|
| 61 |
+
"attributes": {}
|
| 62 |
+
}
|
| 63 |
+
},
|
| 64 |
+
"total_flos": 75688006121100.0,
|
| 65 |
+
"train_batch_size": 1,
|
| 66 |
+
"trial_name": null,
|
| 67 |
+
"trial_params": null
|
| 68 |
+
}
|