{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.044444444444444446, "eval_steps": 8, "global_step": 20, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0022222222222222222, "eval_loss": 13.001398086547852, "eval_runtime": 5.8352, "eval_samples_per_second": 32.561, "eval_steps_per_second": 16.28, "step": 1 }, { "epoch": 0.006666666666666667, "grad_norm": 34.67473602294922, "learning_rate": 6e-05, "loss": 12.9449, "step": 3 }, { "epoch": 0.013333333333333334, "grad_norm": 25.128501892089844, "learning_rate": 0.00012, "loss": 12.6226, "step": 6 }, { "epoch": 0.017777777777777778, "eval_loss": 11.73355484008789, "eval_runtime": 5.8384, "eval_samples_per_second": 32.543, "eval_steps_per_second": 16.272, "step": 8 }, { "epoch": 0.02, "grad_norm": 14.999642372131348, "learning_rate": 0.00018, "loss": 11.906, "step": 9 }, { "epoch": 0.02666666666666667, "grad_norm": 7.970412254333496, "learning_rate": 0.00019510565162951537, "loss": 11.296, "step": 12 }, { "epoch": 0.03333333333333333, "grad_norm": 9.736292839050293, "learning_rate": 0.00017071067811865476, "loss": 10.8208, "step": 15 }, { "epoch": 0.035555555555555556, "eval_loss": 10.455474853515625, "eval_runtime": 5.9526, "eval_samples_per_second": 31.919, "eval_steps_per_second": 15.959, "step": 16 }, { "epoch": 0.04, "grad_norm": 5.3760600090026855, "learning_rate": 0.00013090169943749476, "loss": 10.4623, "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": 5328093315072.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }