Upload checkpoint-200/trainer_state.json with huggingface_hub
Browse files
checkpoint-200/trainer_state.json
ADDED
|
@@ -0,0 +1,107 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.5542770299609205,
|
| 3 |
+
"best_model_checkpoint": "./whisper-large-v3-quantized/checkpoint-200",
|
| 4 |
+
"epoch": 0.12292562999385372,
|
| 5 |
+
"eval_steps": 200,
|
| 6 |
+
"global_step": 200,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.015365703749231715,
|
| 13 |
+
"grad_norm": 0.47920289635658264,
|
| 14 |
+
"learning_rate": 5.000000000000001e-07,
|
| 15 |
+
"loss": 1.5655,
|
| 16 |
+
"step": 25
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.03073140749846343,
|
| 20 |
+
"grad_norm": 0.15030227601528168,
|
| 21 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 22 |
+
"loss": 1.0487,
|
| 23 |
+
"step": 50
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.046097111247695145,
|
| 27 |
+
"grad_norm": 0.5764341354370117,
|
| 28 |
+
"learning_rate": 1.5e-06,
|
| 29 |
+
"loss": 1.6787,
|
| 30 |
+
"step": 75
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.06146281499692686,
|
| 34 |
+
"grad_norm": 0.6326006650924683,
|
| 35 |
+
"learning_rate": 2.0000000000000003e-06,
|
| 36 |
+
"loss": 1.3895,
|
| 37 |
+
"step": 100
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.07682851874615858,
|
| 41 |
+
"grad_norm": 0.5107858180999756,
|
| 42 |
+
"learning_rate": 2.5e-06,
|
| 43 |
+
"loss": 1.5308,
|
| 44 |
+
"step": 125
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.09219422249539029,
|
| 48 |
+
"grad_norm": 0.4186854362487793,
|
| 49 |
+
"learning_rate": 3e-06,
|
| 50 |
+
"loss": 1.1231,
|
| 51 |
+
"step": 150
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.107559926244622,
|
| 55 |
+
"grad_norm": 0.580566942691803,
|
| 56 |
+
"learning_rate": 3.5e-06,
|
| 57 |
+
"loss": 1.8924,
|
| 58 |
+
"step": 175
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.12292562999385372,
|
| 62 |
+
"grad_norm": 0.3107517957687378,
|
| 63 |
+
"learning_rate": 4.000000000000001e-06,
|
| 64 |
+
"loss": 1.3077,
|
| 65 |
+
"step": 200
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.12292562999385372,
|
| 69 |
+
"eval_loss": 1.5075420141220093,
|
| 70 |
+
"eval_runtime": 620.2783,
|
| 71 |
+
"eval_samples_per_second": 0.656,
|
| 72 |
+
"eval_steps_per_second": 0.082,
|
| 73 |
+
"eval_wer": 0.5542770299609205,
|
| 74 |
+
"step": 200
|
| 75 |
+
}
|
| 76 |
+
],
|
| 77 |
+
"logging_steps": 25,
|
| 78 |
+
"max_steps": 1000,
|
| 79 |
+
"num_input_tokens_seen": 0,
|
| 80 |
+
"num_train_epochs": 1,
|
| 81 |
+
"save_steps": 200,
|
| 82 |
+
"stateful_callbacks": {
|
| 83 |
+
"EarlyStoppingCallback": {
|
| 84 |
+
"args": {
|
| 85 |
+
"early_stopping_patience": 3,
|
| 86 |
+
"early_stopping_threshold": 0.0
|
| 87 |
+
},
|
| 88 |
+
"attributes": {
|
| 89 |
+
"early_stopping_patience_counter": 0
|
| 90 |
+
}
|
| 91 |
+
},
|
| 92 |
+
"TrainerControl": {
|
| 93 |
+
"args": {
|
| 94 |
+
"should_epoch_stop": false,
|
| 95 |
+
"should_evaluate": false,
|
| 96 |
+
"should_log": false,
|
| 97 |
+
"should_save": true,
|
| 98 |
+
"should_training_stop": false
|
| 99 |
+
},
|
| 100 |
+
"attributes": {}
|
| 101 |
+
}
|
| 102 |
+
},
|
| 103 |
+
"total_flos": 7.326498816e+17,
|
| 104 |
+
"train_batch_size": 1,
|
| 105 |
+
"trial_name": null,
|
| 106 |
+
"trial_params": null
|
| 107 |
+
}
|