{ "best_metric": null, "best_model_checkpoint": null, "epoch": 4.69437652811736, "eval_steps": 500, "global_step": 30, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.15647921760391198, "grad_norm": 28.315964157029956, "learning_rate": 4.986304738420684e-06, "loss": 1.2256, "step": 1 }, { "epoch": 0.78239608801956, "grad_norm": 3.4969729149181044, "learning_rate": 4.665063509461098e-06, "loss": 0.498, "step": 5 }, { "epoch": 1.56479217603912, "grad_norm": 0.7858910617796858, "learning_rate": 3.7500000000000005e-06, "loss": 0.3066, "step": 10 }, { "epoch": 2.34718826405868, "grad_norm": 0.7570505706327129, "learning_rate": 2.5e-06, "loss": 0.2275, "step": 15 }, { "epoch": 3.12958435207824, "grad_norm": 0.996759187549583, "learning_rate": 1.2500000000000007e-06, "loss": 0.1621, "step": 20 }, { "epoch": 3.9119804400977998, "grad_norm": 0.7081324468145692, "learning_rate": 3.3493649053890325e-07, "loss": 0.1101, "step": 25 }, { "epoch": 4.69437652811736, "grad_norm": 0.6150654142270598, "learning_rate": 0.0, "loss": 0.1074, "step": 30 }, { "epoch": 4.69437652811736, "step": 30, "total_flos": 23213255753728.0, "train_loss": 0.2595372219880422, "train_runtime": 3125.9531, "train_samples_per_second": 2.615, "train_steps_per_second": 0.01 } ], "logging_steps": 5, "max_steps": 30, "num_input_tokens_seen": 0, "num_train_epochs": 5, "save_steps": 500, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": false, "should_training_stop": false }, "attributes": {} } }, "total_flos": 23213255753728.0, "train_batch_size": 1, "trial_name": null, "trial_params": null }