{ "best_metric": 2.090299606323242, "best_model_checkpoint": "./whisper-LoRA-small-ha/checkpoint-750", "epoch": 4.777070063694268, "eval_steps": 250, "global_step": 750, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.1592356687898089, "grad_norm": 10.639625549316406, "learning_rate": 1.3800000000000002e-05, "loss": 5.8923, "step": 25 }, { "epoch": 0.3184713375796178, "grad_norm": 3.0570621490478516, "learning_rate": 2.88e-05, "loss": 5.1217, "step": 50 }, { "epoch": 0.47770700636942676, "grad_norm": 1.420814037322998, "learning_rate": 3e-05, "loss": 4.1046, "step": 75 }, { "epoch": 0.6369426751592356, "grad_norm": 1.6677359342575073, "learning_rate": 3e-05, "loss": 3.5633, "step": 100 }, { "epoch": 0.7961783439490446, "grad_norm": 1.1571909189224243, "learning_rate": 3e-05, "loss": 3.2634, "step": 125 }, { "epoch": 0.9554140127388535, "grad_norm": 1.4416701793670654, "learning_rate": 3e-05, "loss": 3.2152, "step": 150 }, { "epoch": 1.1146496815286624, "grad_norm": 1.3764861822128296, "learning_rate": 3e-05, "loss": 3.1248, "step": 175 }, { "epoch": 1.2738853503184713, "grad_norm": 1.537541389465332, "learning_rate": 3e-05, "loss": 3.0425, "step": 200 }, { "epoch": 1.4331210191082802, "grad_norm": 1.239444613456726, "learning_rate": 3e-05, "loss": 3.0277, "step": 225 }, { "epoch": 1.5923566878980893, "grad_norm": 1.4676295518875122, "learning_rate": 3e-05, "loss": 3.0616, "step": 250 }, { "epoch": 1.5923566878980893, "eval_loss": 2.9989981651306152, "eval_runtime": 130.5989, "eval_samples_per_second": 5.054, "eval_steps_per_second": 0.636, "step": 250 }, { "epoch": 1.7515923566878981, "grad_norm": 1.5393909215927124, "learning_rate": 3e-05, "loss": 2.9165, "step": 275 }, { "epoch": 1.910828025477707, "grad_norm": 1.4913767576217651, "learning_rate": 3e-05, "loss": 2.8888, "step": 300 }, { "epoch": 2.070063694267516, "grad_norm": 1.8603297472000122, "learning_rate": 3e-05, "loss": 2.8715, "step": 325 }, { "epoch": 2.229299363057325, "grad_norm": 1.5909651517868042, "learning_rate": 3e-05, "loss": 2.7833, "step": 350 }, { "epoch": 2.388535031847134, "grad_norm": 33.26897048950195, "learning_rate": 3e-05, "loss": 2.6853, "step": 375 }, { "epoch": 2.5477707006369426, "grad_norm": 1.984903335571289, "learning_rate": 3e-05, "loss": 2.7053, "step": 400 }, { "epoch": 2.7070063694267517, "grad_norm": 1.6659773588180542, "learning_rate": 3e-05, "loss": 2.6967, "step": 425 }, { "epoch": 2.8662420382165603, "grad_norm": 2.684084415435791, "learning_rate": 3e-05, "loss": 2.63, "step": 450 }, { "epoch": 3.0254777070063694, "grad_norm": 1.7889983654022217, "learning_rate": 3e-05, "loss": 2.1224, "step": 475 }, { "epoch": 3.1847133757961785, "grad_norm": 2.101982831954956, "learning_rate": 3e-05, "loss": 2.1053, "step": 500 }, { "epoch": 3.1847133757961785, "eval_loss": 2.131725311279297, "eval_runtime": 131.015, "eval_samples_per_second": 5.038, "eval_steps_per_second": 0.634, "step": 500 }, { "epoch": 3.343949044585987, "grad_norm": 1.9597238302230835, "learning_rate": 3e-05, "loss": 2.1066, "step": 525 }, { "epoch": 3.5031847133757963, "grad_norm": 1.7918522357940674, "learning_rate": 3e-05, "loss": 2.043, "step": 550 }, { "epoch": 3.662420382165605, "grad_norm": 1.6857051849365234, "learning_rate": 3e-05, "loss": 1.9991, "step": 575 }, { "epoch": 3.821656050955414, "grad_norm": 1.8661901950836182, "learning_rate": 3e-05, "loss": 2.0209, "step": 600 }, { "epoch": 3.980891719745223, "grad_norm": 2.1587560176849365, "learning_rate": 3e-05, "loss": 2.0404, "step": 625 }, { "epoch": 4.140127388535032, "grad_norm": 1.7673060894012451, "learning_rate": 3e-05, "loss": 2.052, "step": 650 }, { "epoch": 4.2993630573248405, "grad_norm": 1.8025519847869873, "learning_rate": 3e-05, "loss": 1.9958, "step": 675 }, { "epoch": 4.45859872611465, "grad_norm": 2.0931341648101807, "learning_rate": 3e-05, "loss": 1.9864, "step": 700 }, { "epoch": 4.617834394904459, "grad_norm": 1.7860947847366333, "learning_rate": 3e-05, "loss": 1.998, "step": 725 }, { "epoch": 4.777070063694268, "grad_norm": 2.118542432785034, "learning_rate": 3e-05, "loss": 2.0123, "step": 750 }, { "epoch": 4.777070063694268, "eval_loss": 2.090299606323242, "eval_runtime": 131.9058, "eval_samples_per_second": 5.004, "eval_steps_per_second": 0.629, "step": 750 } ], "logging_steps": 25, "max_steps": 3140, "num_input_tokens_seen": 0, "num_train_epochs": 20, "save_steps": 250, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 3.51947885248512e+18, "train_batch_size": 16, "trial_name": null, "trial_params": null }