{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.01278772378516624, "eval_steps": 3, "global_step": 10, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0012787723785166241, "grad_norm": NaN, "learning_rate": 2e-05, "loss": 0.0, "step": 1 }, { "epoch": 0.0012787723785166241, "eval_loss": NaN, "eval_runtime": 39.654, "eval_samples_per_second": 8.322, "eval_steps_per_second": 4.161, "step": 1 }, { "epoch": 0.0025575447570332483, "grad_norm": NaN, "learning_rate": 4e-05, "loss": 0.0, "step": 2 }, { "epoch": 0.0038363171355498722, "grad_norm": NaN, "learning_rate": 6e-05, "loss": 0.0, "step": 3 }, { "epoch": 0.0038363171355498722, "eval_loss": NaN, "eval_runtime": 39.2883, "eval_samples_per_second": 8.399, "eval_steps_per_second": 4.2, "step": 3 }, { "epoch": 0.005115089514066497, "grad_norm": NaN, "learning_rate": 8e-05, "loss": 0.0, "step": 4 }, { "epoch": 0.00639386189258312, "grad_norm": NaN, "learning_rate": 0.0001, "loss": 0.0, "step": 5 }, { "epoch": 0.0076726342710997444, "grad_norm": NaN, "learning_rate": 0.00012, "loss": 0.0, "step": 6 }, { "epoch": 0.0076726342710997444, "eval_loss": NaN, "eval_runtime": 39.595, "eval_samples_per_second": 8.334, "eval_steps_per_second": 4.167, "step": 6 }, { "epoch": 0.008951406649616368, "grad_norm": NaN, "learning_rate": 0.00014, "loss": 0.0, "step": 7 }, { "epoch": 0.010230179028132993, "grad_norm": NaN, "learning_rate": 0.00016, "loss": 0.0, "step": 8 }, { "epoch": 0.011508951406649617, "grad_norm": NaN, "learning_rate": 0.00018, "loss": 0.0, "step": 9 }, { "epoch": 0.011508951406649617, "eval_loss": NaN, "eval_runtime": 39.6053, "eval_samples_per_second": 8.332, "eval_steps_per_second": 4.166, "step": 9 }, { "epoch": 0.01278772378516624, "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": 5, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 3699128496291840.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }