{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.0007086167800453515, "eval_steps": 2, "global_step": 5, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0001417233560090703, "grad_norm": 0.5957324504852295, "learning_rate": 1e-05, "loss": 2.0283, "step": 1 }, { "epoch": 0.0001417233560090703, "eval_loss": 2.0170388221740723, "eval_runtime": 410.1804, "eval_samples_per_second": 28.973, "eval_steps_per_second": 14.486, "step": 1 }, { "epoch": 0.0002834467120181406, "grad_norm": 0.6832846999168396, "learning_rate": 2e-05, "loss": 2.2197, "step": 2 }, { "epoch": 0.0002834467120181406, "eval_loss": 2.0073771476745605, "eval_runtime": 335.1034, "eval_samples_per_second": 35.464, "eval_steps_per_second": 17.732, "step": 2 }, { "epoch": 0.00042517006802721087, "grad_norm": 0.6752426028251648, "learning_rate": 3e-05, "loss": 1.9325, "step": 3 }, { "epoch": 0.0005668934240362812, "grad_norm": 0.7417239546775818, "learning_rate": 4e-05, "loss": 1.9727, "step": 4 }, { "epoch": 0.0005668934240362812, "eval_loss": 1.9949430227279663, "eval_runtime": 365.8823, "eval_samples_per_second": 32.48, "eval_steps_per_second": 16.24, "step": 4 }, { "epoch": 0.0007086167800453515, "grad_norm": 0.6897047162055969, "learning_rate": 5e-05, "loss": 2.1082, "step": 5 } ], "logging_steps": 1, "max_steps": 5, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 2, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 4438954195550208.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }