{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.006453174155037509, "eval_steps": 8, "global_step": 20, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.00032265870775187547, "eval_loss": 4.1613311767578125, "eval_runtime": 23.9151, "eval_samples_per_second": 54.568, "eval_steps_per_second": 27.305, "step": 1 }, { "epoch": 0.0009679761232556264, "grad_norm": 1.7457234859466553, "learning_rate": 6e-05, "loss": 3.516, "step": 3 }, { "epoch": 0.0019359522465112527, "grad_norm": 1.6416014432907104, "learning_rate": 0.00012, "loss": 3.6706, "step": 6 }, { "epoch": 0.0025812696620150038, "eval_loss": 3.9660162925720215, "eval_runtime": 22.7709, "eval_samples_per_second": 57.31, "eval_steps_per_second": 28.677, "step": 8 }, { "epoch": 0.002903928369766879, "grad_norm": 1.9313857555389404, "learning_rate": 0.00018, "loss": 3.9218, "step": 9 }, { "epoch": 0.0038719044930225054, "grad_norm": 1.7717081308364868, "learning_rate": 0.00019510565162951537, "loss": 3.6313, "step": 12 }, { "epoch": 0.004839880616278132, "grad_norm": 1.8436789512634277, "learning_rate": 0.00017071067811865476, "loss": 3.2659, "step": 15 }, { "epoch": 0.0051625393240300075, "eval_loss": 3.5366051197052, "eval_runtime": 22.8756, "eval_samples_per_second": 57.048, "eval_steps_per_second": 28.546, "step": 16 }, { "epoch": 0.005807856739533758, "grad_norm": 2.4033315181732178, "learning_rate": 0.00013090169943749476, "loss": 3.3646, "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": 1042235881684992.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }