{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.0033883947479881405, "eval_steps": 3, "global_step": 6, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0005647324579980235, "grad_norm": 6.638052463531494, "learning_rate": 2e-05, "loss": 3.0027, "step": 1 }, { "epoch": 0.0005647324579980235, "eval_loss": 2.7413086891174316, "eval_runtime": 209.2602, "eval_samples_per_second": 3.565, "eval_steps_per_second": 1.782, "step": 1 }, { "epoch": 0.001129464915996047, "grad_norm": 4.598910331726074, "learning_rate": 4e-05, "loss": 2.5806, "step": 2 }, { "epoch": 0.0016941973739940702, "grad_norm": 4.744904041290283, "learning_rate": 6e-05, "loss": 3.2161, "step": 3 }, { "epoch": 0.0016941973739940702, "eval_loss": 2.631173849105835, "eval_runtime": 213.0702, "eval_samples_per_second": 3.501, "eval_steps_per_second": 1.751, "step": 3 }, { "epoch": 0.002258929831992094, "grad_norm": 5.976100444793701, "learning_rate": 8e-05, "loss": 3.5525, "step": 4 }, { "epoch": 0.002823662289990117, "grad_norm": 3.7647323608398438, "learning_rate": 0.0001, "loss": 3.0432, "step": 5 }, { "epoch": 0.0033883947479881405, "grad_norm": 3.4719369411468506, "learning_rate": 0.00012, "loss": 2.3622, "step": 6 }, { "epoch": 0.0033883947479881405, "eval_loss": 2.1884851455688477, "eval_runtime": 211.9746, "eval_samples_per_second": 3.519, "eval_steps_per_second": 1.76, "step": 6 } ], "logging_steps": 1, "max_steps": 10, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 3, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 9202732338511872.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }