| { | |
| "best_metric": 0.1133032962679863, | |
| "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": 3.6880290508270264, | |
| "learning_rate": 5e-05, | |
| "loss": 2.9145, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004075394803871625, | |
| "eval_loss": 1.8356962203979492, | |
| "eval_runtime": 4.8102, | |
| "eval_samples_per_second": 10.395, | |
| "eval_steps_per_second": 2.703, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00815078960774325, | |
| "grad_norm": 6.949686527252197, | |
| "learning_rate": 0.0001, | |
| "loss": 5.8006, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.012226184411614875, | |
| "grad_norm": 11.85057544708252, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 8.9155, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0163015792154865, | |
| "grad_norm": 17.87611198425293, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 11.6816, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.020376974019358125, | |
| "grad_norm": 24.372392654418945, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 14.1583, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.02445236882322975, | |
| "grad_norm": 26.836442947387695, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 17.8215, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.028527763627101375, | |
| "grad_norm": 56.37813186645508, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 34.1831, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.032603158430973, | |
| "grad_norm": 24.23225212097168, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 15.4885, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.036678553234844626, | |
| "grad_norm": 22.243453979492188, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 7.7114, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.04075394803871625, | |
| "grad_norm": 22.904632568359375, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 8.7383, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.044829342842587876, | |
| "grad_norm": 19.449880599975586, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 8.7931, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0489047376464595, | |
| "grad_norm": 19.61833953857422, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 8.3072, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.052980132450331126, | |
| "grad_norm": 23.143583297729492, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 9.2176, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.05705552725420275, | |
| "grad_norm": 27.774089813232422, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 5.8898, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.061130922058074376, | |
| "grad_norm": 12.567861557006836, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 5.0024, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.065206316861946, | |
| "grad_norm": 7.958722114562988, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 5.0515, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.06928171166581763, | |
| "grad_norm": 8.585467338562012, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 5.7709, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.07335710646968925, | |
| "grad_norm": 13.094317436218262, | |
| "learning_rate": 7.75e-05, | |
| "loss": 6.3559, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.07743250127356088, | |
| "grad_norm": 23.679494857788086, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 9.2488, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0815078960774325, | |
| "grad_norm": 49.4882698059082, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 20.8839, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.08558329088130413, | |
| "grad_norm": 10.968897819519043, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 4.2323, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.08965868568517575, | |
| "grad_norm": 6.621339321136475, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 3.3759, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.09373408048904738, | |
| "grad_norm": 7.691227436065674, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 4.23, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.097809475292919, | |
| "grad_norm": 8.350950241088867, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 2.9104, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.10188487009679063, | |
| "grad_norm": 17.605392456054688, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 4.5359, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.10188487009679063, | |
| "eval_loss": 0.22036908566951752, | |
| "eval_runtime": 4.8591, | |
| "eval_samples_per_second": 10.29, | |
| "eval_steps_per_second": 2.675, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.10596026490066225, | |
| "grad_norm": 14.292779922485352, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 3.1882, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.11003565970453388, | |
| "grad_norm": 12.268036842346191, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 3.3339, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.1141110545084055, | |
| "grad_norm": 7.059298038482666, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 2.9095, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.11818644931227713, | |
| "grad_norm": 6.473829746246338, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 3.2704, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.12226184411614875, | |
| "grad_norm": 7.172585487365723, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 3.0769, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.12633723892002038, | |
| "grad_norm": 13.269759178161621, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 3.7104, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.130412633723892, | |
| "grad_norm": 45.20688247680664, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 10.5883, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.13448802852776362, | |
| "grad_norm": 7.162100791931152, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 2.2444, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.13856342333163527, | |
| "grad_norm": 7.486405849456787, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 2.2902, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.14263881813550688, | |
| "grad_norm": 7.402297019958496, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 2.2322, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.1467142129393785, | |
| "grad_norm": 8.339662551879883, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 2.2498, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.15078960774325012, | |
| "grad_norm": 6.3191704750061035, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 1.8306, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.15486500254712177, | |
| "grad_norm": 16.101682662963867, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 2.3577, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.15894039735099338, | |
| "grad_norm": 3.658964157104492, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 2.0985, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.163015792154865, | |
| "grad_norm": 3.7097461223602295, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 2.4058, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.16709118695873662, | |
| "grad_norm": 3.5799686908721924, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 2.4198, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.17116658176260827, | |
| "grad_norm": 5.910707950592041, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 2.2987, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.17524197656647988, | |
| "grad_norm": 7.766164302825928, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 2.3937, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.1793173713703515, | |
| "grad_norm": 12.289716720581055, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 2.527, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.18339276617422312, | |
| "grad_norm": 26.6347713470459, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 4.4737, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.18746816097809477, | |
| "grad_norm": 8.661320686340332, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 1.6673, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.19154355578196638, | |
| "grad_norm": 5.6989240646362305, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 1.6876, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.195618950585838, | |
| "grad_norm": 6.910922527313232, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 1.6955, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.19969434538970962, | |
| "grad_norm": 9.750502586364746, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 1.8129, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.20376974019358127, | |
| "grad_norm": 8.881779670715332, | |
| "learning_rate": 1e-05, | |
| "loss": 1.5954, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.20376974019358127, | |
| "eval_loss": 0.1133032962679863, | |
| "eval_runtime": 4.8522, | |
| "eval_samples_per_second": 10.305, | |
| "eval_steps_per_second": 2.679, | |
| "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 | |
| } | |