| { |
| "best_global_step": 100, |
| "best_metric": 208.3406884377758, |
| "best_model_checkpoint": "MediBeng-Whisper-Tiny/checkpoint-100", |
| "epoch": 0.5867014341590613, |
| "eval_steps": 50, |
| "global_step": 450, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.03259452411994785, |
| "grad_norm": 156.1190948486328, |
| "learning_rate": 4.800000000000001e-06, |
| "loss": 2.7938, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.0651890482398957, |
| "grad_norm": 2829.250244140625, |
| "learning_rate": 9.800000000000001e-06, |
| "loss": 2.5945, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.0651890482398957, |
| "eval_loss": 2.3590500354766846, |
| "eval_runtime": 118.4384, |
| "eval_samples_per_second": 1.621, |
| "eval_steps_per_second": 1.621, |
| "eval_wer": 328.59664607237426, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.09778357235984354, |
| "grad_norm": 1883.8115234375, |
| "learning_rate": 9.466666666666667e-06, |
| "loss": 1.988, |
| "step": 75 |
| }, |
| { |
| "epoch": 0.1303780964797914, |
| "grad_norm": 22638.033203125, |
| "learning_rate": 8.91111111111111e-06, |
| "loss": 1.6344, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.1303780964797914, |
| "eval_loss": 1.6414451599121094, |
| "eval_runtime": 86.3667, |
| "eval_samples_per_second": 2.223, |
| "eval_steps_per_second": 2.223, |
| "eval_wer": 208.3406884377758, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.16297262059973924, |
| "grad_norm": 13134.7939453125, |
| "learning_rate": 8.355555555555556e-06, |
| "loss": 1.3976, |
| "step": 125 |
| }, |
| { |
| "epoch": 0.19556714471968709, |
| "grad_norm": 12304.18359375, |
| "learning_rate": 7.800000000000002e-06, |
| "loss": 1.4483, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.19556714471968709, |
| "eval_loss": 1.2572917938232422, |
| "eval_runtime": 270.8478, |
| "eval_samples_per_second": 0.709, |
| "eval_steps_per_second": 0.709, |
| "eval_wer": 937.5992939099735, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.22816166883963493, |
| "grad_norm": 12071.1162109375, |
| "learning_rate": 7.244444444444445e-06, |
| "loss": 1.2517, |
| "step": 175 |
| }, |
| { |
| "epoch": 0.2607561929595828, |
| "grad_norm": 2244.650390625, |
| "learning_rate": 6.688888888888889e-06, |
| "loss": 1.2265, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.2607561929595828, |
| "eval_loss": 1.1812282800674438, |
| "eval_runtime": 214.9167, |
| "eval_samples_per_second": 0.893, |
| "eval_steps_per_second": 0.893, |
| "eval_wer": 692.6301853486319, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.29335071707953064, |
| "grad_norm": 19943.55859375, |
| "learning_rate": 6.133333333333334e-06, |
| "loss": 1.0333, |
| "step": 225 |
| }, |
| { |
| "epoch": 0.3259452411994785, |
| "grad_norm": 6705.62451171875, |
| "learning_rate": 5.577777777777778e-06, |
| "loss": 1.1211, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.3259452411994785, |
| "eval_loss": 1.1117546558380127, |
| "eval_runtime": 325.5353, |
| "eval_samples_per_second": 0.59, |
| "eval_steps_per_second": 0.59, |
| "eval_wer": 1057.0167696381288, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.35853976531942633, |
| "grad_norm": 23125.337890625, |
| "learning_rate": 5.022222222222223e-06, |
| "loss": 1.1068, |
| "step": 275 |
| }, |
| { |
| "epoch": 0.39113428943937417, |
| "grad_norm": 15931.6171875, |
| "learning_rate": 4.4666666666666665e-06, |
| "loss": 1.1036, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.39113428943937417, |
| "eval_loss": 1.1001551151275635, |
| "eval_runtime": 338.8657, |
| "eval_samples_per_second": 0.567, |
| "eval_steps_per_second": 0.567, |
| "eval_wer": 1116.946160635481, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.423728813559322, |
| "grad_norm": 5472.0078125, |
| "learning_rate": 3.911111111111112e-06, |
| "loss": 1.2578, |
| "step": 325 |
| }, |
| { |
| "epoch": 0.45632333767926986, |
| "grad_norm": 42.80149459838867, |
| "learning_rate": 3.3555555555555557e-06, |
| "loss": 1.0646, |
| "step": 350 |
| }, |
| { |
| "epoch": 0.45632333767926986, |
| "eval_loss": 1.0977901220321655, |
| "eval_runtime": 301.6203, |
| "eval_samples_per_second": 0.637, |
| "eval_steps_per_second": 0.637, |
| "eval_wer": 996.6902030008827, |
| "step": 350 |
| }, |
| { |
| "epoch": 0.48891786179921776, |
| "grad_norm": 35.73124313354492, |
| "learning_rate": 2.8000000000000003e-06, |
| "loss": 1.1108, |
| "step": 375 |
| }, |
| { |
| "epoch": 0.5215123859191656, |
| "grad_norm": 53.73215103149414, |
| "learning_rate": 2.2444444444444445e-06, |
| "loss": 1.1886, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.5215123859191656, |
| "eval_loss": 1.190717339515686, |
| "eval_runtime": 349.354, |
| "eval_samples_per_second": 0.55, |
| "eval_steps_per_second": 0.55, |
| "eval_wer": 1124.2277140335393, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.5541069100391134, |
| "grad_norm": 0.5215519070625305, |
| "learning_rate": 1.688888888888889e-06, |
| "loss": 0.8321, |
| "step": 425 |
| }, |
| { |
| "epoch": 0.5867014341590613, |
| "grad_norm": 0.21405276656150818, |
| "learning_rate": 1.1333333333333334e-06, |
| "loss": 1.3247, |
| "step": 450 |
| }, |
| { |
| "epoch": 0.5867014341590613, |
| "eval_loss": 1.1728113889694214, |
| "eval_runtime": 336.5864, |
| "eval_samples_per_second": 0.57, |
| "eval_steps_per_second": 0.57, |
| "eval_wer": 1135.2603706972639, |
| "step": 450 |
| } |
| ], |
| "logging_steps": 25, |
| "max_steps": 500, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 50, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.1078498304e+16, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
