{ "best_metric": 2.026219367980957, "best_model_checkpoint": "miner_id_24/checkpoint-10", "epoch": 0.0021158423697434543, "eval_steps": 5, "global_step": 10, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0002115842369743454, "eval_loss": 2.2490975856781006, "eval_runtime": 492.1632, "eval_samples_per_second": 4.043, "eval_steps_per_second": 2.022, "step": 1 }, { "epoch": 0.0006347527109230362, "grad_norm": 0.5573651194572449, "learning_rate": 6e-05, "loss": 2.2336, "step": 3 }, { "epoch": 0.0010579211848717272, "eval_loss": 2.151787757873535, "eval_runtime": 494.8632, "eval_samples_per_second": 4.021, "eval_steps_per_second": 2.011, "step": 5 }, { "epoch": 0.0012695054218460724, "grad_norm": 0.5345481634140015, "learning_rate": 0.00012, "loss": 2.2414, "step": 6 }, { "epoch": 0.0019042581327691087, "grad_norm": 0.38476917147636414, "learning_rate": 0.00018, "loss": 2.0395, "step": 9 }, { "epoch": 0.0021158423697434543, "eval_loss": 2.026219367980957, "eval_runtime": 494.729, "eval_samples_per_second": 4.022, "eval_steps_per_second": 2.011, "step": 10 } ], "logging_steps": 3, "max_steps": 30, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 10, "stateful_callbacks": { "EarlyStoppingCallback": { "args": { "early_stopping_patience": 1, "early_stopping_threshold": 0.0 }, "attributes": { "early_stopping_patience_counter": 0 } }, "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 1.223121419894784e+16, "train_batch_size": 2, "trial_name": null, "trial_params": null }