{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.003711952487008166, "eval_steps": 8, "global_step": 20, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0001855976243504083, "eval_loss": 1.2906131744384766, "eval_runtime": 234.3041, "eval_samples_per_second": 9.684, "eval_steps_per_second": 4.844, "step": 1 }, { "epoch": 0.0005567928730512249, "grad_norm": 1.4204806089401245, "learning_rate": 6e-05, "loss": 3.8724, "step": 3 }, { "epoch": 0.0011135857461024498, "grad_norm": 2.304058313369751, "learning_rate": 0.00012, "loss": 4.5803, "step": 6 }, { "epoch": 0.0014847809948032665, "eval_loss": 1.2551518678665161, "eval_runtime": 235.9886, "eval_samples_per_second": 9.615, "eval_steps_per_second": 4.81, "step": 8 }, { "epoch": 0.0016703786191536749, "grad_norm": 5.708734512329102, "learning_rate": 0.00018, "loss": 5.9305, "step": 9 }, { "epoch": 0.0022271714922048997, "grad_norm": 3.761167287826538, "learning_rate": 0.00019510565162951537, "loss": 4.884, "step": 12 }, { "epoch": 0.0027839643652561247, "grad_norm": 3.1222829818725586, "learning_rate": 0.00017071067811865476, "loss": 5.1134, "step": 15 }, { "epoch": 0.002969561989606533, "eval_loss": 1.2209032773971558, "eval_runtime": 236.0548, "eval_samples_per_second": 9.612, "eval_steps_per_second": 4.808, "step": 16 }, { "epoch": 0.0033407572383073497, "grad_norm": 3.7993876934051514, "learning_rate": 0.00013090169943749476, "loss": 5.0935, "step": 18 } ], "logging_steps": 3, "max_steps": 30, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 10, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 9883555303784448.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }