{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.0008297618998228458, "eval_steps": 10, "global_step": 50, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 1.6595237996456916e-05, "eval_loss": 0.9319517016410828, "eval_runtime": 684.835, "eval_samples_per_second": 37.048, "eval_steps_per_second": 18.524, "step": 1 }, { "epoch": 8.297618998228458e-05, "grad_norm": 3.183830499649048, "learning_rate": 5e-05, "loss": 3.624, "step": 5 }, { "epoch": 0.00016595237996456917, "grad_norm": 4.00230598449707, "learning_rate": 0.0001, "loss": 3.7706, "step": 10 }, { "epoch": 0.00016595237996456917, "eval_loss": 0.7170787453651428, "eval_runtime": 692.7042, "eval_samples_per_second": 36.627, "eval_steps_per_second": 18.314, "step": 10 }, { "epoch": 0.00024892856994685375, "grad_norm": 2.8913145065307617, "learning_rate": 9.619397662556435e-05, "loss": 2.088, "step": 15 }, { "epoch": 0.00033190475992913833, "grad_norm": 5.755887985229492, "learning_rate": 8.535533905932738e-05, "loss": 1.4491, "step": 20 }, { "epoch": 0.00033190475992913833, "eval_loss": 0.2670595943927765, "eval_runtime": 689.8036, "eval_samples_per_second": 36.781, "eval_steps_per_second": 18.391, "step": 20 }, { "epoch": 0.0004148809499114229, "grad_norm": 5.549856185913086, "learning_rate": 6.91341716182545e-05, "loss": 0.9362, "step": 25 }, { "epoch": 0.0004978571398937075, "grad_norm": 7.281345844268799, "learning_rate": 5e-05, "loss": 0.5976, "step": 30 }, { "epoch": 0.0004978571398937075, "eval_loss": 0.12552273273468018, "eval_runtime": 689.2345, "eval_samples_per_second": 36.812, "eval_steps_per_second": 18.406, "step": 30 }, { "epoch": 0.0005808333298759921, "grad_norm": 5.342987060546875, "learning_rate": 3.086582838174551e-05, "loss": 0.488, "step": 35 }, { "epoch": 0.0006638095198582767, "grad_norm": 6.433207035064697, "learning_rate": 1.4644660940672627e-05, "loss": 0.4755, "step": 40 }, { "epoch": 0.0006638095198582767, "eval_loss": 0.09560307115316391, "eval_runtime": 690.6129, "eval_samples_per_second": 36.738, "eval_steps_per_second": 18.369, "step": 40 }, { "epoch": 0.0007467857098405612, "grad_norm": 6.775955677032471, "learning_rate": 3.8060233744356633e-06, "loss": 0.4671, "step": 45 }, { "epoch": 0.0008297618998228458, "grad_norm": 2.749504327774048, "learning_rate": 0.0, "loss": 0.3641, "step": 50 }, { "epoch": 0.0008297618998228458, "eval_loss": 0.0893232449889183, "eval_runtime": 689.7774, "eval_samples_per_second": 36.783, "eval_steps_per_second": 18.391, "step": 50 } ], "logging_steps": 5, "max_steps": 50, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 13, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 1507790463959040.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }