{ "best_metric": null, "best_model_checkpoint": null, "epoch": 7.662737385218579e-05, "eval_steps": 3, "global_step": 6, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 1.2771228975364299e-05, "grad_norm": 1.6853578090667725, "learning_rate": 2e-05, "loss": 12.8567, "step": 1 }, { "epoch": 1.2771228975364299e-05, "eval_loss": 3.4389500617980957, "eval_runtime": 284.8559, "eval_samples_per_second": 115.739, "eval_steps_per_second": 57.871, "step": 1 }, { "epoch": 2.5542457950728598e-05, "grad_norm": 1.7145562171936035, "learning_rate": 4e-05, "loss": 12.9693, "step": 2 }, { "epoch": 3.8313686926092896e-05, "grad_norm": 1.7134019136428833, "learning_rate": 6e-05, "loss": 14.4764, "step": 3 }, { "epoch": 3.8313686926092896e-05, "eval_loss": 3.4378418922424316, "eval_runtime": 283.2099, "eval_samples_per_second": 116.412, "eval_steps_per_second": 58.208, "step": 3 }, { "epoch": 5.1084915901457196e-05, "grad_norm": 1.6709320545196533, "learning_rate": 8e-05, "loss": 13.5146, "step": 4 }, { "epoch": 6.38561448768215e-05, "grad_norm": 1.7994674444198608, "learning_rate": 0.0001, "loss": 12.8968, "step": 5 }, { "epoch": 7.662737385218579e-05, "grad_norm": 1.6614803075790405, "learning_rate": 0.00012, "loss": 13.3827, "step": 6 }, { "epoch": 7.662737385218579e-05, "eval_loss": 3.432285785675049, "eval_runtime": 283.3258, "eval_samples_per_second": 116.364, "eval_steps_per_second": 58.184, "step": 6 } ], "logging_steps": 1, "max_steps": 10, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 3, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 12733630119936.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }