{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.028288543140028287, "eval_steps": 5, "global_step": 15, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.001885902876001886, "eval_loss": 1.5560035705566406, "eval_runtime": 68.851, "eval_samples_per_second": 12.97, "eval_steps_per_second": 1.627, "step": 1 }, { "epoch": 0.005657708628005658, "grad_norm": 0.48519009351730347, "learning_rate": 3e-05, "loss": 1.5268, "step": 3 }, { "epoch": 0.00942951438000943, "eval_loss": 1.493416428565979, "eval_runtime": 68.726, "eval_samples_per_second": 12.994, "eval_steps_per_second": 1.63, "step": 5 }, { "epoch": 0.011315417256011316, "grad_norm": 0.44942334294319153, "learning_rate": 6e-05, "loss": 1.6204, "step": 6 }, { "epoch": 0.016973125884016973, "grad_norm": 0.3278067708015442, "learning_rate": 9e-05, "loss": 1.53, "step": 9 }, { "epoch": 0.01885902876001886, "eval_loss": 1.3736556768417358, "eval_runtime": 68.8401, "eval_samples_per_second": 12.972, "eval_steps_per_second": 1.627, "step": 10 }, { "epoch": 0.02263083451202263, "grad_norm": 0.3598170578479767, "learning_rate": 9.938441702975689e-05, "loss": 1.4709, "step": 12 }, { "epoch": 0.028288543140028287, "grad_norm": 0.2836269438266754, "learning_rate": 9.619397662556435e-05, "loss": 1.2911, "step": 15 }, { "epoch": 0.028288543140028287, "eval_loss": 1.324967384338379, "eval_runtime": 68.8059, "eval_samples_per_second": 12.979, "eval_steps_per_second": 1.628, "step": 15 } ], "logging_steps": 3, "max_steps": 50, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 5, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 2.168380245147648e+16, "train_batch_size": 8, "trial_name": null, "trial_params": null }