{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.00044936246699994384, "eval_steps": 8, "global_step": 20, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 2.246812334999719e-05, "eval_loss": 2.708707571029663, "eval_runtime": 2271.309, "eval_samples_per_second": 8.251, "eval_steps_per_second": 4.125, "step": 1 }, { "epoch": 6.740437004999158e-05, "grad_norm": 1.9373347759246826, "learning_rate": 6e-05, "loss": 2.5699, "step": 3 }, { "epoch": 0.00013480874009998316, "grad_norm": 1.7457520961761475, "learning_rate": 0.00012, "loss": 2.4162, "step": 6 }, { "epoch": 0.00017974498679997753, "eval_loss": 2.27852725982666, "eval_runtime": 2282.078, "eval_samples_per_second": 8.212, "eval_steps_per_second": 4.106, "step": 8 }, { "epoch": 0.00020221311014997472, "grad_norm": 1.6379685401916504, "learning_rate": 0.00018, "loss": 2.1973, "step": 9 }, { "epoch": 0.0002696174801999663, "grad_norm": 1.656538724899292, "learning_rate": 0.00019510565162951537, "loss": 1.8866, "step": 12 }, { "epoch": 0.00033702185024995785, "grad_norm": 2.4117918014526367, "learning_rate": 0.00017071067811865476, "loss": 1.5794, "step": 15 }, { "epoch": 0.00035948997359995505, "eval_loss": 1.7519029378890991, "eval_runtime": 2278.5479, "eval_samples_per_second": 8.225, "eval_steps_per_second": 4.112, "step": 16 }, { "epoch": 0.00040442622029994945, "grad_norm": 2.3444559574127197, "learning_rate": 0.00013090169943749476, "loss": 1.5926, "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": 6610941168844800.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }