{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.00033190475992913833, "eval_steps": 2, "global_step": 5, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 6.638095198582766e-05, "grad_norm": 10.480119705200195, "learning_rate": 1e-05, "loss": 15.1992, "step": 1 }, { "epoch": 6.638095198582766e-05, "eval_loss": 0.9316858053207397, "eval_runtime": 292.6157, "eval_samples_per_second": 86.708, "eval_steps_per_second": 43.354, "step": 1 }, { "epoch": 0.00013276190397165533, "grad_norm": 11.314657211303711, "learning_rate": 2e-05, "loss": 14.1055, "step": 2 }, { "epoch": 0.00013276190397165533, "eval_loss": 0.9178802371025085, "eval_runtime": 244.5722, "eval_samples_per_second": 103.74, "eval_steps_per_second": 51.87, "step": 2 }, { "epoch": 0.000199142855957483, "grad_norm": 11.809197425842285, "learning_rate": 3e-05, "loss": 16.4297, "step": 3 }, { "epoch": 0.00026552380794331066, "grad_norm": 10.205855369567871, "learning_rate": 4e-05, "loss": 12.7148, "step": 4 }, { "epoch": 0.00026552380794331066, "eval_loss": 0.8961522579193115, "eval_runtime": 250.7588, "eval_samples_per_second": 101.181, "eval_steps_per_second": 50.59, "step": 4 }, { "epoch": 0.00033190475992913833, "grad_norm": 13.494939804077148, "learning_rate": 5e-05, "loss": 15.8984, "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": 604609047429120.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }