{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.9906191369606003, "eval_steps": 50, "global_step": 66, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.150093808630394, "grad_norm": 21.152034759521484, "learning_rate": 9.936341773606723e-06, "loss": 9.9147, "step": 10 }, { "epoch": 0.300187617260788, "grad_norm": 11.003325462341309, "learning_rate": 8.849169917149532e-06, "loss": 4.5306, "step": 20 }, { "epoch": 0.450281425891182, "grad_norm": 9.566656112670898, "learning_rate": 6.6961943305901515e-06, "loss": 3.1766, "step": 30 }, { "epoch": 0.600375234521576, "grad_norm": 5.71157693862915, "learning_rate": 4.073556379564429e-06, "loss": 2.2901, "step": 40 }, { "epoch": 0.7504690431519699, "grad_norm": 4.610980033874512, "learning_rate": 1.7074431046748075e-06, "loss": 1.8468, "step": 50 }, { "epoch": 0.7504690431519699, "eval_loss": 0.20180517435073853, "eval_runtime": 616.3523, "eval_samples_per_second": 1.535, "eval_steps_per_second": 0.193, "step": 50 }, { "epoch": 0.900562851782364, "grad_norm": 4.245090961456299, "learning_rate": 2.530119576580936e-07, "loss": 1.6721, "step": 60 }, { "epoch": 0.9906191369606003, "step": 66, "total_flos": 1.6879216147520553e+18, "train_loss": 3.6938722783868965, "train_runtime": 17349.0422, "train_samples_per_second": 0.491, "train_steps_per_second": 0.004 } ], "logging_steps": 10, "max_steps": 66, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 100, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 1.6879216147520553e+18, "train_batch_size": 2, "trial_name": null, "trial_params": null }