{ "best_metric": 0.9768159985542297, "best_model_checkpoint": "miner_id_24/checkpoint-150", "epoch": 0.0052059834102661995, "eval_steps": 50, "global_step": 150, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 3.470655606844133e-05, "eval_loss": 1.5390846729278564, "eval_runtime": 273.4595, "eval_samples_per_second": 44.365, "eval_steps_per_second": 11.091, "step": 1 }, { "epoch": 0.0003470655606844133, "grad_norm": 0.5712449550628662, "learning_rate": 5.05e-06, "loss": 0.5196, "step": 10 }, { "epoch": 0.0006941311213688266, "grad_norm": 0.9507728815078735, "learning_rate": 1.01e-05, "loss": 0.6129, "step": 20 }, { "epoch": 0.00104119668205324, "grad_norm": 2.0956873893737793, "learning_rate": 9.323076923076924e-06, "loss": 0.983, "step": 30 }, { "epoch": 0.0013882622427376532, "grad_norm": 4.227148532867432, "learning_rate": 8.546153846153847e-06, "loss": 1.5109, "step": 40 }, { "epoch": 0.0017353278034220663, "grad_norm": 24.842472076416016, "learning_rate": 7.76923076923077e-06, "loss": 2.601, "step": 50 }, { "epoch": 0.0017353278034220663, "eval_loss": 1.2068699598312378, "eval_runtime": 273.0714, "eval_samples_per_second": 44.428, "eval_steps_per_second": 11.107, "step": 50 }, { "epoch": 0.00208239336410648, "grad_norm": 0.7354454398155212, "learning_rate": 6.992307692307692e-06, "loss": 0.5196, "step": 60 }, { "epoch": 0.002429458924790893, "grad_norm": 0.7986167669296265, "learning_rate": 6.215384615384615e-06, "loss": 0.6819, "step": 70 }, { "epoch": 0.0027765244854753065, "grad_norm": 1.4324290752410889, "learning_rate": 5.438461538461538e-06, "loss": 0.9526, "step": 80 }, { "epoch": 0.0031235900461597196, "grad_norm": 3.554446220397949, "learning_rate": 4.661538461538462e-06, "loss": 1.2829, "step": 90 }, { "epoch": 0.0034706556068441327, "grad_norm": 30.22225570678711, "learning_rate": 3.884615384615385e-06, "loss": 2.0732, "step": 100 }, { "epoch": 0.0034706556068441327, "eval_loss": 1.0001741647720337, "eval_runtime": 274.0964, "eval_samples_per_second": 44.262, "eval_steps_per_second": 11.065, "step": 100 }, { "epoch": 0.003817721167528546, "grad_norm": 0.7673032283782959, "learning_rate": 3.1076923076923076e-06, "loss": 0.4904, "step": 110 }, { "epoch": 0.00416478672821296, "grad_norm": 1.0892831087112427, "learning_rate": 2.330769230769231e-06, "loss": 0.5508, "step": 120 }, { "epoch": 0.004511852288897372, "grad_norm": 1.4933292865753174, "learning_rate": 1.5538461538461538e-06, "loss": 0.8418, "step": 130 }, { "epoch": 0.004858917849581786, "grad_norm": 3.312762498855591, "learning_rate": 7.769230769230769e-07, "loss": 1.2403, "step": 140 }, { "epoch": 0.0052059834102661995, "grad_norm": 29.821260452270508, "learning_rate": 0.0, "loss": 2.0093, "step": 150 }, { "epoch": 0.0052059834102661995, "eval_loss": 0.9768159985542297, "eval_runtime": 272.9548, "eval_samples_per_second": 44.447, "eval_steps_per_second": 11.112, "step": 150 } ], "logging_steps": 10, "max_steps": 150, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 50, "stateful_callbacks": { "EarlyStoppingCallback": { "args": { "early_stopping_patience": 3, "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": true }, "attributes": {} } }, "total_flos": 1.040953594871808e+16, "train_batch_size": 8, "trial_name": null, "trial_params": null }