| { | |
| "best_metric": 0.26503002643585205, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.14217167229429536, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0028434334458859074, | |
| "grad_norm": 22.415369033813477, | |
| "learning_rate": 5e-05, | |
| "loss": 5.3378, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0028434334458859074, | |
| "eval_loss": 5.232264995574951, | |
| "eval_runtime": 3.9483, | |
| "eval_samples_per_second": 12.664, | |
| "eval_steps_per_second": 3.293, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.005686866891771815, | |
| "grad_norm": 23.209169387817383, | |
| "learning_rate": 0.0001, | |
| "loss": 5.2597, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.008530300337657722, | |
| "grad_norm": 15.02617073059082, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 3.7897, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.01137373378354363, | |
| "grad_norm": 14.549369812011719, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 1.8205, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.014217167229429535, | |
| "grad_norm": 7.76815938949585, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 0.6944, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.017060600675315445, | |
| "grad_norm": 4.215451717376709, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 0.47, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.019904034121201352, | |
| "grad_norm": 2.1003599166870117, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 0.3876, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.02274746756708726, | |
| "grad_norm": 1.887962818145752, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 0.3898, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.025590901012973163, | |
| "grad_norm": 1.115380883216858, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 0.3581, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.02843433445885907, | |
| "grad_norm": 1.0263733863830566, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 0.3522, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03127776790474498, | |
| "grad_norm": 3.604118585586548, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 0.4661, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.03412120135063089, | |
| "grad_norm": 1.8551830053329468, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 0.3639, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.03696463479651679, | |
| "grad_norm": 1.1953414678573608, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 0.3007, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.039808068242402704, | |
| "grad_norm": 1.147956371307373, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 0.3732, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.04265150168828861, | |
| "grad_norm": 0.7729864716529846, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 0.3532, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.04549493513417452, | |
| "grad_norm": 2.4076788425445557, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 0.3822, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.04833836858006042, | |
| "grad_norm": 2.3338794708251953, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 0.3718, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.05118180202594633, | |
| "grad_norm": 1.7410494089126587, | |
| "learning_rate": 7.75e-05, | |
| "loss": 0.361, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.05402523547183224, | |
| "grad_norm": 0.8371558785438538, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 0.3156, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.05686866891771814, | |
| "grad_norm": 2.5813608169555664, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 0.3617, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.05971210236360405, | |
| "grad_norm": 1.6700718402862549, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 0.3385, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.06255553580948996, | |
| "grad_norm": 1.207481026649475, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 0.3765, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.06539896925537586, | |
| "grad_norm": 1.1957097053527832, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 0.3412, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.06824240270126178, | |
| "grad_norm": 1.484207272529602, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 0.3145, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.07108583614714768, | |
| "grad_norm": 1.7423596382141113, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 0.2979, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.07108583614714768, | |
| "eval_loss": 0.31171107292175293, | |
| "eval_runtime": 4.0078, | |
| "eval_samples_per_second": 12.476, | |
| "eval_steps_per_second": 3.244, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.07392926959303359, | |
| "grad_norm": 1.1360609531402588, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 0.3498, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.07677270303891949, | |
| "grad_norm": 1.0913562774658203, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 0.3328, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.07961613648480541, | |
| "grad_norm": 2.2489614486694336, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 0.3531, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.08245956993069131, | |
| "grad_norm": 1.245743751525879, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 0.3458, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.08530300337657722, | |
| "grad_norm": 0.9143818616867065, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 0.3279, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.08814643682246312, | |
| "grad_norm": 0.9616953134536743, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 0.3483, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.09098987026834904, | |
| "grad_norm": 1.3551769256591797, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 0.3119, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.09383330371423494, | |
| "grad_norm": 0.7638424038887024, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 0.2966, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.09667673716012085, | |
| "grad_norm": 0.7949358820915222, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 0.3511, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.09952017060600675, | |
| "grad_norm": 0.8913821578025818, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 0.3015, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.10236360405189265, | |
| "grad_norm": 1.1559334993362427, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 0.3538, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.10520703749777857, | |
| "grad_norm": 1.223947286605835, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 0.3099, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.10805047094366448, | |
| "grad_norm": 0.9780659675598145, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 0.306, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.11089390438955038, | |
| "grad_norm": 1.0553867816925049, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 0.318, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.11373733783543628, | |
| "grad_norm": 1.149210810661316, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 0.2961, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.1165807712813222, | |
| "grad_norm": 1.1460851430892944, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 0.2907, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.1194242047272081, | |
| "grad_norm": 1.234253168106079, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 0.3047, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.12226763817309401, | |
| "grad_norm": 1.5525425672531128, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 0.3576, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.1251110716189799, | |
| "grad_norm": 1.1359039545059204, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 0.3114, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.12795450506486583, | |
| "grad_norm": 1.2153254747390747, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 0.3103, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.13079793851075172, | |
| "grad_norm": 1.3485732078552246, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 0.3211, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.13364137195663764, | |
| "grad_norm": 0.954004168510437, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 0.2795, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.13648480540252356, | |
| "grad_norm": 0.9658924341201782, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 0.3035, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.13932823884840945, | |
| "grad_norm": 0.9231831431388855, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 0.2799, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.14217167229429536, | |
| "grad_norm": 0.8936429619789124, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2711, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.14217167229429536, | |
| "eval_loss": 0.26503002643585205, | |
| "eval_runtime": 4.0026, | |
| "eval_samples_per_second": 12.492, | |
| "eval_steps_per_second": 3.248, | |
| "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": 6.174479344467968e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |