| { |
| "best_metric": 71.37931034482759, |
| "best_model_checkpoint": "./whisper-large-v3-cv17-dv/checkpoint-2700", |
| "epoch": 9.908794788273616, |
| "eval_steps": 300, |
| "global_step": 3300, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.3257328990228013, |
| "grad_norm": 38.63404846191406, |
| "learning_rate": 1.9200000000000003e-06, |
| "loss": 4.5676, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.6514657980456026, |
| "grad_norm": 37.98774719238281, |
| "learning_rate": 3.920000000000001e-06, |
| "loss": 2.8219, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.9771986970684039, |
| "grad_norm": 7.7040252685546875, |
| "learning_rate": 5.92e-06, |
| "loss": 1.4644, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.9771986970684039, |
| "eval_loss": 1.0653657913208008, |
| "eval_runtime": 142.8846, |
| "eval_samples_per_second": 0.7, |
| "eval_steps_per_second": 0.021, |
| "eval_wer": 203.96551724137933, |
| "step": 300 |
| }, |
| { |
| "epoch": 1.3029315960912053, |
| "grad_norm": 3.3996422290802, |
| "learning_rate": 7.9e-06, |
| "loss": 0.6065, |
| "step": 400 |
| }, |
| { |
| "epoch": 1.6286644951140063, |
| "grad_norm": 2.5693020820617676, |
| "learning_rate": 9.9e-06, |
| "loss": 0.303, |
| "step": 500 |
| }, |
| { |
| "epoch": 1.9543973941368078, |
| "grad_norm": 2.019421339035034, |
| "learning_rate": 9.72857142857143e-06, |
| "loss": 0.2384, |
| "step": 600 |
| }, |
| { |
| "epoch": 1.9543973941368078, |
| "eval_loss": 0.3341977596282959, |
| "eval_runtime": 138.0417, |
| "eval_samples_per_second": 0.724, |
| "eval_steps_per_second": 0.022, |
| "eval_wer": 84.82758620689656, |
| "step": 600 |
| }, |
| { |
| "epoch": 2.2801302931596092, |
| "grad_norm": 1.6545788049697876, |
| "learning_rate": 9.442857142857144e-06, |
| "loss": 0.1718, |
| "step": 700 |
| }, |
| { |
| "epoch": 2.6058631921824107, |
| "grad_norm": 1.4984415769577026, |
| "learning_rate": 9.157142857142857e-06, |
| "loss": 0.1555, |
| "step": 800 |
| }, |
| { |
| "epoch": 2.9315960912052117, |
| "grad_norm": 1.6755363941192627, |
| "learning_rate": 8.871428571428571e-06, |
| "loss": 0.1481, |
| "step": 900 |
| }, |
| { |
| "epoch": 2.9315960912052117, |
| "eval_loss": 0.2715227007865906, |
| "eval_runtime": 137.1492, |
| "eval_samples_per_second": 0.729, |
| "eval_steps_per_second": 0.022, |
| "eval_wer": 78.79310344827586, |
| "step": 900 |
| }, |
| { |
| "epoch": 2.3257328990228014, |
| "grad_norm": 1.167482852935791, |
| "learning_rate": 8.585714285714286e-06, |
| "loss": 0.0978, |
| "step": 1000 |
| }, |
| { |
| "epoch": 2.6514657980456025, |
| "grad_norm": 1.9179445505142212, |
| "learning_rate": 8.3e-06, |
| "loss": 0.0876, |
| "step": 1100 |
| }, |
| { |
| "epoch": 2.977198697068404, |
| "grad_norm": 1.3239954710006714, |
| "learning_rate": 8.014285714285715e-06, |
| "loss": 0.0975, |
| "step": 1200 |
| }, |
| { |
| "epoch": 2.977198697068404, |
| "eval_loss": 0.2634916603565216, |
| "eval_runtime": 138.2093, |
| "eval_samples_per_second": 0.724, |
| "eval_steps_per_second": 0.022, |
| "eval_wer": 76.0344827586207, |
| "step": 1200 |
| }, |
| { |
| "epoch": 3.3029315960912053, |
| "grad_norm": 1.5532219409942627, |
| "learning_rate": 7.72857142857143e-06, |
| "loss": 0.0637, |
| "step": 1300 |
| }, |
| { |
| "epoch": 3.6286644951140063, |
| "grad_norm": 1.0479369163513184, |
| "learning_rate": 7.442857142857144e-06, |
| "loss": 0.0626, |
| "step": 1400 |
| }, |
| { |
| "epoch": 3.954397394136808, |
| "grad_norm": 0.9303975105285645, |
| "learning_rate": 7.1571428571428584e-06, |
| "loss": 0.0616, |
| "step": 1500 |
| }, |
| { |
| "epoch": 3.954397394136808, |
| "eval_loss": 0.2841312289237976, |
| "eval_runtime": 138.8794, |
| "eval_samples_per_second": 0.72, |
| "eval_steps_per_second": 0.022, |
| "eval_wer": 73.10344827586206, |
| "step": 1500 |
| }, |
| { |
| "epoch": 4.3257328990228014, |
| "grad_norm": 1.0117665529251099, |
| "learning_rate": 6.871428571428572e-06, |
| "loss": 0.0357, |
| "step": 1600 |
| }, |
| { |
| "epoch": 4.651465798045603, |
| "grad_norm": 1.661333441734314, |
| "learning_rate": 6.585714285714286e-06, |
| "loss": 0.0372, |
| "step": 1700 |
| }, |
| { |
| "epoch": 4.977198697068404, |
| "grad_norm": 2.5246667861938477, |
| "learning_rate": 6.300000000000001e-06, |
| "loss": 0.0399, |
| "step": 1800 |
| }, |
| { |
| "epoch": 4.977198697068404, |
| "eval_loss": 0.32145407795906067, |
| "eval_runtime": 141.4007, |
| "eval_samples_per_second": 0.707, |
| "eval_steps_per_second": 0.021, |
| "eval_wer": 72.24137931034483, |
| "step": 1800 |
| }, |
| { |
| "epoch": 5.3257328990228014, |
| "grad_norm": 0.9164466261863708, |
| "learning_rate": 6.014285714285715e-06, |
| "loss": 0.0203, |
| "step": 1900 |
| }, |
| { |
| "epoch": 5.651465798045603, |
| "grad_norm": 1.748327374458313, |
| "learning_rate": 5.7285714285714285e-06, |
| "loss": 0.0222, |
| "step": 2000 |
| }, |
| { |
| "epoch": 5.977198697068404, |
| "grad_norm": 1.8888225555419922, |
| "learning_rate": 5.442857142857143e-06, |
| "loss": 0.0218, |
| "step": 2100 |
| }, |
| { |
| "epoch": 5.977198697068404, |
| "eval_loss": 0.38806796073913574, |
| "eval_runtime": 138.8021, |
| "eval_samples_per_second": 0.72, |
| "eval_steps_per_second": 0.022, |
| "eval_wer": 73.79310344827587, |
| "step": 2100 |
| }, |
| { |
| "epoch": 6.3257328990228014, |
| "grad_norm": 1.3422770500183105, |
| "learning_rate": 5.157142857142857e-06, |
| "loss": 0.0529, |
| "step": 2200 |
| }, |
| { |
| "epoch": 6.651465798045603, |
| "grad_norm": 1.5599135160446167, |
| "learning_rate": 4.871428571428572e-06, |
| "loss": 0.0488, |
| "step": 2300 |
| }, |
| { |
| "epoch": 6.977198697068404, |
| "grad_norm": 1.3102701902389526, |
| "learning_rate": 4.585714285714286e-06, |
| "loss": 0.046, |
| "step": 2400 |
| }, |
| { |
| "epoch": 6.977198697068404, |
| "eval_loss": 0.27721107006073, |
| "eval_runtime": 147.7865, |
| "eval_samples_per_second": 0.677, |
| "eval_steps_per_second": 0.02, |
| "eval_wer": 74.13793103448276, |
| "step": 2400 |
| }, |
| { |
| "epoch": 7.302931596091205, |
| "grad_norm": 1.040212869644165, |
| "learning_rate": 4.3e-06, |
| "loss": 0.0198, |
| "step": 2500 |
| }, |
| { |
| "epoch": 7.628664495114006, |
| "grad_norm": 0.8678199648857117, |
| "learning_rate": 4.014285714285715e-06, |
| "loss": 0.0174, |
| "step": 2600 |
| }, |
| { |
| "epoch": 7.954397394136808, |
| "grad_norm": 1.5105644464492798, |
| "learning_rate": 3.7285714285714286e-06, |
| "loss": 0.018, |
| "step": 2700 |
| }, |
| { |
| "epoch": 7.954397394136808, |
| "eval_loss": 0.3344331681728363, |
| "eval_runtime": 150.3178, |
| "eval_samples_per_second": 0.665, |
| "eval_steps_per_second": 0.02, |
| "eval_wer": 71.37931034482759, |
| "step": 2700 |
| }, |
| { |
| "epoch": 8.280130293159608, |
| "grad_norm": 0.5797841548919678, |
| "learning_rate": 3.4428571428571434e-06, |
| "loss": 0.0079, |
| "step": 2800 |
| }, |
| { |
| "epoch": 8.60586319218241, |
| "grad_norm": 0.5921549797058105, |
| "learning_rate": 3.1571428571428573e-06, |
| "loss": 0.0068, |
| "step": 2900 |
| }, |
| { |
| "epoch": 8.931596091205211, |
| "grad_norm": 0.7851368188858032, |
| "learning_rate": 2.8714285714285717e-06, |
| "loss": 0.0067, |
| "step": 3000 |
| }, |
| { |
| "epoch": 8.931596091205211, |
| "eval_loss": 0.39471304416656494, |
| "eval_runtime": 145.8938, |
| "eval_samples_per_second": 0.685, |
| "eval_steps_per_second": 0.021, |
| "eval_wer": 71.72413793103448, |
| "step": 3000 |
| }, |
| { |
| "epoch": 9.257328990228013, |
| "grad_norm": 0.23316721618175507, |
| "learning_rate": 2.5857142857142856e-06, |
| "loss": 0.0031, |
| "step": 3100 |
| }, |
| { |
| "epoch": 9.583061889250814, |
| "grad_norm": 0.7372754216194153, |
| "learning_rate": 2.3000000000000004e-06, |
| "loss": 0.0027, |
| "step": 3200 |
| }, |
| { |
| "epoch": 9.908794788273616, |
| "grad_norm": 0.2684876322746277, |
| "learning_rate": 2.0142857142857144e-06, |
| "loss": 0.0023, |
| "step": 3300 |
| }, |
| { |
| "epoch": 9.908794788273616, |
| "eval_loss": 0.42460787296295166, |
| "eval_runtime": 146.943, |
| "eval_samples_per_second": 0.681, |
| "eval_steps_per_second": 0.02, |
| "eval_wer": 72.58620689655172, |
| "step": 3300 |
| } |
| ], |
| "logging_steps": 100, |
| "max_steps": 4000, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 14, |
| "save_steps": 300, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.791840606879744e+20, |
| "train_batch_size": 16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
