| { | |
| "best_metric": 1.6952250003814697, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.05136106831022085, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.002054442732408834, | |
| "grad_norm": 72.63911437988281, | |
| "learning_rate": 5e-05, | |
| "loss": 38.3589, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002054442732408834, | |
| "eval_loss": 3.0806236267089844, | |
| "eval_runtime": 215.2339, | |
| "eval_samples_per_second": 15.239, | |
| "eval_steps_per_second": 1.905, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004108885464817668, | |
| "grad_norm": 84.75655364990234, | |
| "learning_rate": 0.0001, | |
| "loss": 41.3745, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0061633281972265025, | |
| "grad_norm": 63.62594223022461, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 38.5362, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.008217770929635337, | |
| "grad_norm": 148.93727111816406, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 37.302, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.01027221366204417, | |
| "grad_norm": 73.28170013427734, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 34.3173, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.012326656394453005, | |
| "grad_norm": 87.36775207519531, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 34.3255, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.014381099126861838, | |
| "grad_norm": 107.49162292480469, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 31.8931, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.016435541859270673, | |
| "grad_norm": 56.272708892822266, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 31.9466, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.01848998459167951, | |
| "grad_norm": 231.95889282226562, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 31.9671, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.02054442732408834, | |
| "grad_norm": 53.92425537109375, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 29.5999, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.022598870056497175, | |
| "grad_norm": 48.65695571899414, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 28.8132, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.02465331278890601, | |
| "grad_norm": 48.8329963684082, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 29.6056, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.02670775552131484, | |
| "grad_norm": 47.05804443359375, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 30.9364, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.028762198253723677, | |
| "grad_norm": 90.31666564941406, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 30.1931, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.030816640986132512, | |
| "grad_norm": 38.44446563720703, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 28.5989, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.03287108371854135, | |
| "grad_norm": 35.618350982666016, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 28.4939, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.03492552645095018, | |
| "grad_norm": 34.55806350708008, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 27.4811, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.03697996918335902, | |
| "grad_norm": 228.94281005859375, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 28.0385, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.03903441191576785, | |
| "grad_norm": 42.987892150878906, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 26.6212, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.04108885464817668, | |
| "grad_norm": 40.11811828613281, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 27.7546, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.04314329738058552, | |
| "grad_norm": 37.71592330932617, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 27.7426, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.04519774011299435, | |
| "grad_norm": 36.94485092163086, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 27.2242, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.04725218284540318, | |
| "grad_norm": 37.85831069946289, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 28.0138, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.04930662557781202, | |
| "grad_norm": 34.742069244384766, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 25.5438, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.05136106831022085, | |
| "grad_norm": 41.137718200683594, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 27.044, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.05136106831022085, | |
| "eval_loss": 1.6952250003814697, | |
| "eval_runtime": 215.2445, | |
| "eval_samples_per_second": 15.238, | |
| "eval_steps_per_second": 1.905, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "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": 2.829013890367488e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |