{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.09324009324009325, "eval_steps": 8, "global_step": 20, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.004662004662004662, "eval_loss": 1.0004037618637085, "eval_runtime": 25.7703, "eval_samples_per_second": 3.531, "eval_steps_per_second": 1.785, "step": 1 }, { "epoch": 0.013986013986013986, "grad_norm": 0.3392694592475891, "learning_rate": 6e-05, "loss": 0.9517, "step": 3 }, { "epoch": 0.027972027972027972, "grad_norm": 0.4344029426574707, "learning_rate": 0.00012, "loss": 0.9839, "step": 6 }, { "epoch": 0.037296037296037296, "eval_loss": 0.8890663385391235, "eval_runtime": 24.876, "eval_samples_per_second": 3.658, "eval_steps_per_second": 1.849, "step": 8 }, { "epoch": 0.04195804195804196, "grad_norm": 0.4226091802120209, "learning_rate": 0.00018, "loss": 0.8539, "step": 9 }, { "epoch": 0.055944055944055944, "grad_norm": 0.37416017055511475, "learning_rate": 0.00019510565162951537, "loss": 0.7767, "step": 12 }, { "epoch": 0.06993006993006994, "grad_norm": 0.3611030876636505, "learning_rate": 0.00017071067811865476, "loss": 0.7492, "step": 15 }, { "epoch": 0.07459207459207459, "eval_loss": 0.7391844391822815, "eval_runtime": 24.8047, "eval_samples_per_second": 3.669, "eval_steps_per_second": 1.854, "step": 16 }, { "epoch": 0.08391608391608392, "grad_norm": 0.42007654905319214, "learning_rate": 0.00013090169943749476, "loss": 0.6869, "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": 6697946569506816.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }