{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.009458500827618822, "eval_steps": 3, "global_step": 10, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0009458500827618822, "grad_norm": NaN, "learning_rate": 2e-05, "loss": 0.0, "step": 1 }, { "epoch": 0.0009458500827618822, "eval_loss": NaN, "eval_runtime": 11.2318, "eval_samples_per_second": 39.709, "eval_steps_per_second": 19.854, "step": 1 }, { "epoch": 0.0018917001655237645, "grad_norm": NaN, "learning_rate": 4e-05, "loss": 0.0, "step": 2 }, { "epoch": 0.0028375502482856467, "grad_norm": NaN, "learning_rate": 6e-05, "loss": 0.0, "step": 3 }, { "epoch": 0.0028375502482856467, "eval_loss": NaN, "eval_runtime": 10.565, "eval_samples_per_second": 42.215, "eval_steps_per_second": 21.107, "step": 3 }, { "epoch": 0.003783400331047529, "grad_norm": NaN, "learning_rate": 8e-05, "loss": 0.0, "step": 4 }, { "epoch": 0.004729250413809411, "grad_norm": NaN, "learning_rate": 0.0001, "loss": 0.0, "step": 5 }, { "epoch": 0.005675100496571293, "grad_norm": NaN, "learning_rate": 0.00012, "loss": 0.0, "step": 6 }, { "epoch": 0.005675100496571293, "eval_loss": NaN, "eval_runtime": 10.6271, "eval_samples_per_second": 41.968, "eval_steps_per_second": 20.984, "step": 6 }, { "epoch": 0.006620950579333176, "grad_norm": NaN, "learning_rate": 0.00014, "loss": 0.0, "step": 7 }, { "epoch": 0.007566800662095058, "grad_norm": NaN, "learning_rate": 0.00016, "loss": 0.0, "step": 8 }, { "epoch": 0.00851265074485694, "grad_norm": NaN, "learning_rate": 0.00018, "loss": 0.0, "step": 9 }, { "epoch": 0.00851265074485694, "eval_loss": NaN, "eval_runtime": 10.5739, "eval_samples_per_second": 42.179, "eval_steps_per_second": 21.09, "step": 9 }, { "epoch": 0.009458500827618822, "grad_norm": NaN, "learning_rate": 0.0002, "loss": 0.0, "step": 10 } ], "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": true }, "attributes": {} } }, "total_flos": 324298258513920.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }