{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.0010826416456153013, "eval_steps": 3, "global_step": 3, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.00036088054853843375, "grad_norm": 4.020681858062744, "learning_rate": 2e-05, "loss": 8.5712, "step": 1 }, { "epoch": 0.00036088054853843375, "eval_loss": 2.053340196609497, "eval_runtime": 239.3472, "eval_samples_per_second": 4.876, "eval_steps_per_second": 2.44, "step": 1 }, { "epoch": 0.0007217610970768675, "grad_norm": 3.2305173873901367, "learning_rate": 4e-05, "loss": 7.4849, "step": 2 }, { "epoch": 0.0010826416456153013, "grad_norm": 3.2316172122955322, "learning_rate": 6e-05, "loss": 7.9669, "step": 3 }, { "epoch": 0.0010826416456153013, "eval_loss": 2.0378758907318115, "eval_runtime": 196.5802, "eval_samples_per_second": 5.937, "eval_steps_per_second": 2.971, "step": 3 } ], "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": 1711683215032320.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }