{ "best_metric": null, "best_model_checkpoint": null, "epoch": 1.04, "eval_steps": 4, "global_step": 13, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.08, "eval_loss": 2.0923311710357666, "eval_runtime": 0.7891, "eval_samples_per_second": 10.138, "eval_steps_per_second": 5.069, "step": 1 }, { "epoch": 0.24, "grad_norm": 1.0800840854644775, "learning_rate": 6e-05, "loss": 1.9861, "step": 3 }, { "epoch": 0.32, "eval_loss": 2.061372756958008, "eval_runtime": 0.2556, "eval_samples_per_second": 31.3, "eval_steps_per_second": 15.65, "step": 4 }, { "epoch": 0.48, "grad_norm": 0.8765755295753479, "learning_rate": 0.00012, "loss": 2.0359, "step": 6 }, { "epoch": 0.64, "eval_loss": 1.8452266454696655, "eval_runtime": 0.2557, "eval_samples_per_second": 31.286, "eval_steps_per_second": 15.643, "step": 8 }, { "epoch": 0.72, "grad_norm": 0.6558836102485657, "learning_rate": 0.00018, "loss": 1.7598, "step": 9 }, { "epoch": 0.96, "grad_norm": 0.7826021909713745, "learning_rate": 5.000000000000002e-05, "loss": 1.6732, "step": 12 }, { "epoch": 0.96, "eval_loss": 1.7637643814086914, "eval_runtime": 0.2607, "eval_samples_per_second": 30.686, "eval_steps_per_second": 15.343, "step": 12 } ], "logging_steps": 3, "max_steps": 13, "num_input_tokens_seen": 0, "num_train_epochs": 2, "save_steps": 10, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 1273612115902464.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }