| { | |
| "best_metric": 0.42311346530914307, | |
| "best_model_checkpoint": "speecht5_finetuned_bphc/checkpoint-500", | |
| "epoch": 2.6595744680851063, | |
| "eval_steps": 100, | |
| "global_step": 500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.13297872340425532, | |
| "grad_norm": 3.937445640563965, | |
| "learning_rate": 2.4e-05, | |
| "loss": 1.0732, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.26595744680851063, | |
| "grad_norm": 3.3802008628845215, | |
| "learning_rate": 4.9e-05, | |
| "loss": 0.7567, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.39893617021276595, | |
| "grad_norm": 7.172617435455322, | |
| "learning_rate": 7.3e-05, | |
| "loss": 0.6624, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.5319148936170213, | |
| "grad_norm": 5.82205867767334, | |
| "learning_rate": 9.8e-05, | |
| "loss": 0.6294, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.5319148936170213, | |
| "eval_loss": 0.5470437407493591, | |
| "eval_runtime": 19.8146, | |
| "eval_samples_per_second": 33.763, | |
| "eval_steps_per_second": 16.907, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.6648936170212766, | |
| "grad_norm": 3.176703929901123, | |
| "learning_rate": 9.425e-05, | |
| "loss": 0.6045, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.7978723404255319, | |
| "grad_norm": 2.801500082015991, | |
| "learning_rate": 8.800000000000001e-05, | |
| "loss": 0.5722, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.9308510638297872, | |
| "grad_norm": 7.730113506317139, | |
| "learning_rate": 8.175000000000001e-05, | |
| "loss": 0.5563, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 1.0638297872340425, | |
| "grad_norm": 11.911551475524902, | |
| "learning_rate": 7.55e-05, | |
| "loss": 0.5486, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.0638297872340425, | |
| "eval_loss": 0.4846374988555908, | |
| "eval_runtime": 18.6315, | |
| "eval_samples_per_second": 35.907, | |
| "eval_steps_per_second": 17.98, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.196808510638298, | |
| "grad_norm": 4.457734107971191, | |
| "learning_rate": 6.925e-05, | |
| "loss": 0.5378, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 1.3297872340425532, | |
| "grad_norm": 2.7005956172943115, | |
| "learning_rate": 6.3e-05, | |
| "loss": 0.5355, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.4627659574468086, | |
| "grad_norm": 2.9917397499084473, | |
| "learning_rate": 5.6750000000000004e-05, | |
| "loss": 0.5138, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 1.5957446808510638, | |
| "grad_norm": 3.650026321411133, | |
| "learning_rate": 5.05e-05, | |
| "loss": 0.5046, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.5957446808510638, | |
| "eval_loss": 0.45161741971969604, | |
| "eval_runtime": 18.3387, | |
| "eval_samples_per_second": 36.48, | |
| "eval_steps_per_second": 18.267, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.728723404255319, | |
| "grad_norm": 3.8126158714294434, | |
| "learning_rate": 4.4250000000000005e-05, | |
| "loss": 0.4897, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 1.8617021276595744, | |
| "grad_norm": 4.279622554779053, | |
| "learning_rate": 3.8e-05, | |
| "loss": 0.4865, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.9946808510638299, | |
| "grad_norm": 4.044638633728027, | |
| "learning_rate": 3.175e-05, | |
| "loss": 0.4823, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 2.127659574468085, | |
| "grad_norm": 4.797245979309082, | |
| "learning_rate": 2.5500000000000003e-05, | |
| "loss": 0.4732, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 2.127659574468085, | |
| "eval_loss": 0.43503323197364807, | |
| "eval_runtime": 18.8477, | |
| "eval_samples_per_second": 35.495, | |
| "eval_steps_per_second": 17.774, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 2.2606382978723403, | |
| "grad_norm": 2.5267035961151123, | |
| "learning_rate": 1.925e-05, | |
| "loss": 0.4774, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 2.393617021276596, | |
| "grad_norm": 3.2455756664276123, | |
| "learning_rate": 1.3000000000000001e-05, | |
| "loss": 0.4646, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 2.526595744680851, | |
| "grad_norm": 3.491698980331421, | |
| "learning_rate": 6.750000000000001e-06, | |
| "loss": 0.4601, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 2.6595744680851063, | |
| "grad_norm": 3.7166852951049805, | |
| "learning_rate": 5.000000000000001e-07, | |
| "loss": 0.4601, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.6595744680851063, | |
| "eval_loss": 0.42311346530914307, | |
| "eval_runtime": 18.8917, | |
| "eval_samples_per_second": 35.412, | |
| "eval_steps_per_second": 17.733, | |
| "step": 500 | |
| } | |
| ], | |
| "logging_steps": 25, | |
| "max_steps": 500, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1481834827297440.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |