{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.004203888596952181, "eval_steps": 3, "global_step": 10, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.00042038885969521806, "grad_norm": NaN, "learning_rate": 2e-05, "loss": 0.0, "step": 1 }, { "epoch": 0.00042038885969521806, "eval_loss": NaN, "eval_runtime": 47.8938, "eval_samples_per_second": 20.921, "eval_steps_per_second": 10.461, "step": 1 }, { "epoch": 0.0008407777193904361, "grad_norm": NaN, "learning_rate": 4e-05, "loss": 0.0, "step": 2 }, { "epoch": 0.0012611665790856542, "grad_norm": NaN, "learning_rate": 6e-05, "loss": 0.0, "step": 3 }, { "epoch": 0.0012611665790856542, "eval_loss": NaN, "eval_runtime": 46.5235, "eval_samples_per_second": 21.538, "eval_steps_per_second": 10.769, "step": 3 }, { "epoch": 0.0016815554387808723, "grad_norm": NaN, "learning_rate": 8e-05, "loss": 0.0, "step": 4 }, { "epoch": 0.0021019442984760903, "grad_norm": NaN, "learning_rate": 0.0001, "loss": 0.0, "step": 5 }, { "epoch": 0.0025223331581713084, "grad_norm": NaN, "learning_rate": 0.00012, "loss": 0.0, "step": 6 }, { "epoch": 0.0025223331581713084, "eval_loss": NaN, "eval_runtime": 46.7611, "eval_samples_per_second": 21.428, "eval_steps_per_second": 10.714, "step": 6 }, { "epoch": 0.0029427220178665264, "grad_norm": NaN, "learning_rate": 0.00014, "loss": 0.0, "step": 7 }, { "epoch": 0.0033631108775617445, "grad_norm": NaN, "learning_rate": 0.00016, "loss": 0.0, "step": 8 }, { "epoch": 0.0037834997372569626, "grad_norm": NaN, "learning_rate": 0.00018, "loss": 0.0, "step": 9 }, { "epoch": 0.0037834997372569626, "eval_loss": NaN, "eval_runtime": 46.5816, "eval_samples_per_second": 21.511, "eval_steps_per_second": 10.755, "step": 9 }, { "epoch": 0.004203888596952181, "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": 2880129906769920.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }