Delete trainer_state.json with huggingface_hub
Browse files- trainer_state.json +0 -100
trainer_state.json
DELETED
|
@@ -1,100 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"best_global_step": 1338,
|
| 3 |
-
"best_metric": 0.8786015776943197,
|
| 4 |
-
"best_model_checkpoint": "outputs/sphobert-spam-binary/checkpoint-1338",
|
| 5 |
-
"epoch": 3.0,
|
| 6 |
-
"eval_steps": 500,
|
| 7 |
-
"global_step": 1338,
|
| 8 |
-
"is_hyper_param_search": false,
|
| 9 |
-
"is_local_process_zero": true,
|
| 10 |
-
"is_world_process_zero": true,
|
| 11 |
-
"log_history": [
|
| 12 |
-
{
|
| 13 |
-
"epoch": 1.0,
|
| 14 |
-
"grad_norm": 0.4428337812423706,
|
| 15 |
-
"learning_rate": 4.998771926094749e-05,
|
| 16 |
-
"loss": 0.3018,
|
| 17 |
-
"step": 446
|
| 18 |
-
},
|
| 19 |
-
{
|
| 20 |
-
"epoch": 1.0,
|
| 21 |
-
"eval_accuracy": 0.9073724007561437,
|
| 22 |
-
"eval_f1": 0.8758155809022719,
|
| 23 |
-
"eval_loss": 0.27634894847869873,
|
| 24 |
-
"eval_precision": 0.9034638245542119,
|
| 25 |
-
"eval_recall": 0.856103394906635,
|
| 26 |
-
"eval_runtime": 6.114,
|
| 27 |
-
"eval_samples_per_second": 259.568,
|
| 28 |
-
"eval_steps_per_second": 8.178,
|
| 29 |
-
"step": 446
|
| 30 |
-
},
|
| 31 |
-
{
|
| 32 |
-
"epoch": 2.0,
|
| 33 |
-
"grad_norm": 9.62130355834961,
|
| 34 |
-
"learning_rate": 4.995077872180951e-05,
|
| 35 |
-
"loss": 0.2142,
|
| 36 |
-
"step": 892
|
| 37 |
-
},
|
| 38 |
-
{
|
| 39 |
-
"epoch": 2.0,
|
| 40 |
-
"eval_accuracy": 0.909892879647133,
|
| 41 |
-
"eval_f1": 0.8781504551216691,
|
| 42 |
-
"eval_loss": 0.29870447516441345,
|
| 43 |
-
"eval_precision": 0.9112078181649159,
|
| 44 |
-
"eval_recall": 0.8556400876364294,
|
| 45 |
-
"eval_runtime": 6.1075,
|
| 46 |
-
"eval_samples_per_second": 259.846,
|
| 47 |
-
"eval_steps_per_second": 8.187,
|
| 48 |
-
"step": 892
|
| 49 |
-
},
|
| 50 |
-
{
|
| 51 |
-
"epoch": 3.0,
|
| 52 |
-
"grad_norm": 8.09521484375,
|
| 53 |
-
"learning_rate": 4.988921477641713e-05,
|
| 54 |
-
"loss": 0.1644,
|
| 55 |
-
"step": 1338
|
| 56 |
-
},
|
| 57 |
-
{
|
| 58 |
-
"epoch": 3.0,
|
| 59 |
-
"eval_accuracy": 0.908002520478891,
|
| 60 |
-
"eval_f1": 0.8786015776943197,
|
| 61 |
-
"eval_loss": 0.3062317669391632,
|
| 62 |
-
"eval_precision": 0.8975415956568336,
|
| 63 |
-
"eval_recall": 0.8638419328254708,
|
| 64 |
-
"eval_runtime": 6.1159,
|
| 65 |
-
"eval_samples_per_second": 259.489,
|
| 66 |
-
"eval_steps_per_second": 8.175,
|
| 67 |
-
"step": 1338
|
| 68 |
-
}
|
| 69 |
-
],
|
| 70 |
-
"logging_steps": 446,
|
| 71 |
-
"max_steps": 44600,
|
| 72 |
-
"num_input_tokens_seen": 0,
|
| 73 |
-
"num_train_epochs": 100,
|
| 74 |
-
"save_steps": 500,
|
| 75 |
-
"stateful_callbacks": {
|
| 76 |
-
"EarlyStoppingCallback": {
|
| 77 |
-
"args": {
|
| 78 |
-
"early_stopping_patience": 5,
|
| 79 |
-
"early_stopping_threshold": 0.0
|
| 80 |
-
},
|
| 81 |
-
"attributes": {
|
| 82 |
-
"early_stopping_patience_counter": 0
|
| 83 |
-
}
|
| 84 |
-
},
|
| 85 |
-
"TrainerControl": {
|
| 86 |
-
"args": {
|
| 87 |
-
"should_epoch_stop": false,
|
| 88 |
-
"should_evaluate": false,
|
| 89 |
-
"should_log": false,
|
| 90 |
-
"should_save": true,
|
| 91 |
-
"should_training_stop": false
|
| 92 |
-
},
|
| 93 |
-
"attributes": {}
|
| 94 |
-
}
|
| 95 |
-
},
|
| 96 |
-
"total_flos": 0.0,
|
| 97 |
-
"train_batch_size": 32,
|
| 98 |
-
"trial_name": null,
|
| 99 |
-
"trial_params": null
|
| 100 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|