{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.012938702895034774, "eval_steps": 8, "global_step": 20, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0006469351447517387, "eval_loss": 10.379254341125488, "eval_runtime": 1.9562, "eval_samples_per_second": 332.785, "eval_steps_per_second": 166.648, "step": 1 }, { "epoch": 0.0019408054342552159, "grad_norm": 0.05709757283329964, "learning_rate": 6e-05, "loss": 10.3773, "step": 3 }, { "epoch": 0.0038816108685104317, "grad_norm": 0.05442696809768677, "learning_rate": 0.00012, "loss": 10.3785, "step": 6 }, { "epoch": 0.005175481158013909, "eval_loss": 10.37868881225586, "eval_runtime": 1.9441, "eval_samples_per_second": 334.862, "eval_steps_per_second": 167.688, "step": 8 }, { "epoch": 0.005822416302765648, "grad_norm": 0.05555945262312889, "learning_rate": 0.00018, "loss": 10.3785, "step": 9 }, { "epoch": 0.0077632217370208634, "grad_norm": 0.061655160039663315, "learning_rate": 0.00019510565162951537, "loss": 10.3803, "step": 12 }, { "epoch": 0.009704027171276079, "grad_norm": 0.053998760879039764, "learning_rate": 0.00017071067811865476, "loss": 10.3789, "step": 15 }, { "epoch": 0.010350962316027819, "eval_loss": 10.377120018005371, "eval_runtime": 1.9667, "eval_samples_per_second": 331.018, "eval_steps_per_second": 165.763, "step": 16 }, { "epoch": 0.011644832605531296, "grad_norm": 0.04903817176818848, "learning_rate": 0.00013090169943749476, "loss": 10.3751, "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": 523024465920.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }