| { | |
| "best_metric": 0.10608885437250137, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.20376974019358127, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.004075394803871625, | |
| "grad_norm": 3.827404737472534, | |
| "learning_rate": 5e-05, | |
| "loss": 2.9145, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004075394803871625, | |
| "eval_loss": 1.8356962203979492, | |
| "eval_runtime": 4.8486, | |
| "eval_samples_per_second": 10.312, | |
| "eval_steps_per_second": 2.681, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00815078960774325, | |
| "grad_norm": 7.24910306930542, | |
| "learning_rate": 0.0001, | |
| "loss": 5.8006, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.012226184411614875, | |
| "grad_norm": 12.240799903869629, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 8.9029, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0163015792154865, | |
| "grad_norm": 18.35515022277832, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 11.6094, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.020376974019358125, | |
| "grad_norm": 24.526424407958984, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 14.0281, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.02445236882322975, | |
| "grad_norm": 27.1960391998291, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 17.6728, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.028527763627101375, | |
| "grad_norm": 58.4085578918457, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 33.8795, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.032603158430973, | |
| "grad_norm": 25.113037109375, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 15.4508, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.036678553234844626, | |
| "grad_norm": 22.0405330657959, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 7.6782, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.04075394803871625, | |
| "grad_norm": 22.838218688964844, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 8.6714, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.044829342842587876, | |
| "grad_norm": 19.132617950439453, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 8.6813, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0489047376464595, | |
| "grad_norm": 19.33534812927246, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 8.182, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.052980132450331126, | |
| "grad_norm": 23.340688705444336, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 9.1016, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.05705552725420275, | |
| "grad_norm": 28.65967559814453, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 5.9646, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.061130922058074376, | |
| "grad_norm": 12.671440124511719, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 5.0144, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.065206316861946, | |
| "grad_norm": 8.083102226257324, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 5.0446, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.06928171166581763, | |
| "grad_norm": 8.632357597351074, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 5.7235, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.07335710646968925, | |
| "grad_norm": 13.137079238891602, | |
| "learning_rate": 7.75e-05, | |
| "loss": 6.2918, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.07743250127356088, | |
| "grad_norm": 24.043968200683594, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 9.0448, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0815078960774325, | |
| "grad_norm": 51.93798065185547, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 20.4983, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.08558329088130413, | |
| "grad_norm": 11.572328567504883, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 4.2346, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.08965868568517575, | |
| "grad_norm": 7.37239933013916, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 3.3478, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.09373408048904738, | |
| "grad_norm": 7.5706281661987305, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 4.1856, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.097809475292919, | |
| "grad_norm": 8.155221939086914, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 2.8269, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.10188487009679063, | |
| "grad_norm": 18.45476531982422, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 4.5504, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.10188487009679063, | |
| "eval_loss": 0.20966766774654388, | |
| "eval_runtime": 4.8918, | |
| "eval_samples_per_second": 10.221, | |
| "eval_steps_per_second": 2.658, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.10596026490066225, | |
| "grad_norm": 14.012548446655273, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 3.1354, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.11003565970453388, | |
| "grad_norm": 12.140026092529297, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 3.2918, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.1141110545084055, | |
| "grad_norm": 7.307669639587402, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 2.8834, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.11818644931227713, | |
| "grad_norm": 6.482525825500488, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 3.2235, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.12226184411614875, | |
| "grad_norm": 6.61669921875, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 3.0302, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.12633723892002038, | |
| "grad_norm": 14.014857292175293, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 3.6282, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.130412633723892, | |
| "grad_norm": 44.7835693359375, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 10.3638, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.13448802852776362, | |
| "grad_norm": 7.154061317443848, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 2.2156, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.13856342333163527, | |
| "grad_norm": 7.64763879776001, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 2.2094, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.14263881813550688, | |
| "grad_norm": 8.679080963134766, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 2.1754, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.1467142129393785, | |
| "grad_norm": 8.896808624267578, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 2.2206, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.15078960774325012, | |
| "grad_norm": 6.064028263092041, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 1.7617, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.15486500254712177, | |
| "grad_norm": 14.632406234741211, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 2.3032, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.15894039735099338, | |
| "grad_norm": 3.615339994430542, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 2.0701, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.163015792154865, | |
| "grad_norm": 3.444420099258423, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 2.3679, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.16709118695873662, | |
| "grad_norm": 3.5726735591888428, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 2.3856, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.17116658176260827, | |
| "grad_norm": 5.774728298187256, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 2.2382, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.17524197656647988, | |
| "grad_norm": 7.59352970123291, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 2.3525, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.1793173713703515, | |
| "grad_norm": 12.746742248535156, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 2.4931, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.18339276617422312, | |
| "grad_norm": 32.45207214355469, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 4.3111, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.18746816097809477, | |
| "grad_norm": 9.602239608764648, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 1.5958, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.19154355578196638, | |
| "grad_norm": 5.826984882354736, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 1.6729, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.195618950585838, | |
| "grad_norm": 8.131805419921875, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 1.7031, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.19969434538970962, | |
| "grad_norm": 8.51675033569336, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 1.7887, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.20376974019358127, | |
| "grad_norm": 10.093128204345703, | |
| "learning_rate": 1e-05, | |
| "loss": 1.5667, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.20376974019358127, | |
| "eval_loss": 0.10608885437250137, | |
| "eval_runtime": 4.8603, | |
| "eval_samples_per_second": 10.287, | |
| "eval_steps_per_second": 2.675, | |
| "step": 50 | |
| } | |
| ], | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 8.238716314986742e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |