| { | |
| "best_metric": 1.927670955657959, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.6069802731411229, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.024279210925644917, | |
| "grad_norm": 41.75309371948242, | |
| "learning_rate": 5e-05, | |
| "loss": 6.5026, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.024279210925644917, | |
| "eval_loss": 5.656565189361572, | |
| "eval_runtime": 8.3025, | |
| "eval_samples_per_second": 33.484, | |
| "eval_steps_per_second": 4.216, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.048558421851289835, | |
| "grad_norm": 39.876243591308594, | |
| "learning_rate": 0.0001, | |
| "loss": 6.3875, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.07283763277693475, | |
| "grad_norm": 22.86069107055664, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 5.6568, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.09711684370257967, | |
| "grad_norm": 12.098616600036621, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 5.0062, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.12139605462822459, | |
| "grad_norm": 6.628508567810059, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 4.546, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.1456752655538695, | |
| "grad_norm": 5.374814510345459, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 4.0775, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.16995447647951442, | |
| "grad_norm": 4.38949728012085, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 3.7581, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.19423368740515934, | |
| "grad_norm": 4.288176536560059, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 3.5205, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.21851289833080426, | |
| "grad_norm": 4.242329120635986, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 3.1674, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.24279210925644917, | |
| "grad_norm": 3.8530588150024414, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 2.6543, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.26707132018209406, | |
| "grad_norm": 12.302727699279785, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 3.9427, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.291350531107739, | |
| "grad_norm": 7.0023603439331055, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 3.5035, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.3156297420333839, | |
| "grad_norm": 5.381596088409424, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 3.1127, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.33990895295902884, | |
| "grad_norm": 4.2896599769592285, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 2.8267, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.36418816388467373, | |
| "grad_norm": 3.7407398223876953, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 2.662, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.3884673748103187, | |
| "grad_norm": 2.9491171836853027, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 2.4588, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.41274658573596357, | |
| "grad_norm": 2.5228219032287598, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 2.2669, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.4370257966616085, | |
| "grad_norm": 2.3768715858459473, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 2.143, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.4613050075872534, | |
| "grad_norm": 2.3113930225372314, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 2.0853, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.48558421851289835, | |
| "grad_norm": 2.5413949489593506, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.9679, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.5098634294385432, | |
| "grad_norm": 6.092654228210449, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 2.7577, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.5341426403641881, | |
| "grad_norm": 4.576383590698242, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 2.5038, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.5584218512898331, | |
| "grad_norm": 3.2663581371307373, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 2.167, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.582701062215478, | |
| "grad_norm": 3.275437593460083, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 2.0019, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.6069802731411229, | |
| "grad_norm": 2.5334155559539795, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 1.905, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.6069802731411229, | |
| "eval_loss": 1.927670955657959, | |
| "eval_runtime": 7.4944, | |
| "eval_samples_per_second": 37.094, | |
| "eval_steps_per_second": 4.67, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 25, | |
| "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": 8.33416392081408e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |