{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.9950248756218906, "eval_steps": 50, "global_step": 50, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.19900497512437812, "grad_norm": 0.19027178231490433, "learning_rate": 9.698463103929542e-06, "loss": 0.5402, "step": 10 }, { "epoch": 0.39800995024875624, "grad_norm": 0.12440838049539037, "learning_rate": 7.500000000000001e-06, "loss": 0.3396, "step": 20 }, { "epoch": 0.5970149253731343, "grad_norm": 0.11640778541261446, "learning_rate": 4.131759111665349e-06, "loss": 0.3003, "step": 30 }, { "epoch": 0.7960199004975125, "grad_norm": 0.09686661118572953, "learning_rate": 1.1697777844051105e-06, "loss": 0.2797, "step": 40 }, { "epoch": 0.9950248756218906, "grad_norm": 0.10848416001160903, "learning_rate": 0.0, "loss": 0.2947, "step": 50 }, { "epoch": 0.9950248756218906, "eval_loss": 0.3058350384235382, "eval_runtime": 129.5662, "eval_samples_per_second": 5.511, "eval_steps_per_second": 0.695, "step": 50 }, { "epoch": 0.9950248756218906, "step": 50, "total_flos": 15500995461120.0, "train_loss": 0.35090127468109134, "train_runtime": 2675.3606, "train_samples_per_second": 2.402, "train_steps_per_second": 0.019 } ], "logging_steps": 10, "max_steps": 50, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 50, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 15500995461120.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }