{ "best_metric": null, "best_model_checkpoint": null, "epoch": 2.9156626506024095, "eval_steps": 500, "global_step": 30, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.963855421686747, "grad_norm": 19.159939693146534, "learning_rate": 5e-06, "loss": 1.1757, "step": 10 }, { "epoch": 0.963855421686747, "eval_loss": 1.1205402612686157, "eval_runtime": 12.7363, "eval_samples_per_second": 21.906, "eval_steps_per_second": 0.393, "step": 10 }, { "epoch": 1.9397590361445785, "grad_norm": 4.198527960558323, "learning_rate": 5e-06, "loss": 1.1431, "step": 20 }, { "epoch": 1.9397590361445785, "eval_loss": 1.060249924659729, "eval_runtime": 12.6645, "eval_samples_per_second": 22.03, "eval_steps_per_second": 0.395, "step": 20 }, { "epoch": 2.9156626506024095, "grad_norm": 1.5481540430469, "learning_rate": 5e-06, "loss": 1.0686, "step": 30 }, { "epoch": 2.9156626506024095, "eval_loss": 1.0308853387832642, "eval_runtime": 11.7626, "eval_samples_per_second": 23.719, "eval_steps_per_second": 0.425, "step": 30 }, { "epoch": 2.9156626506024095, "step": 30, "total_flos": 50041737707520.0, "train_loss": 1.1291534741719564, "train_runtime": 2062.6963, "train_samples_per_second": 7.705, "train_steps_per_second": 0.015 } ], "logging_steps": 10, "max_steps": 30, "num_input_tokens_seen": 0, "num_train_epochs": 3, "save_steps": 500, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 50041737707520.0, "train_batch_size": 8, "trial_name": null, "trial_params": null }