| { | |
| "best_metric": 0.6973173022270203, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.4778972520908005, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.009557945041816009, | |
| "grad_norm": 21.285463333129883, | |
| "learning_rate": 5e-05, | |
| "loss": 9.3815, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.009557945041816009, | |
| "eval_loss": 9.480135917663574, | |
| "eval_runtime": 2.6864, | |
| "eval_samples_per_second": 18.613, | |
| "eval_steps_per_second": 4.839, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.019115890083632018, | |
| "grad_norm": 22.216529846191406, | |
| "learning_rate": 0.0001, | |
| "loss": 8.9927, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.02867383512544803, | |
| "grad_norm": 33.82709503173828, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 8.9342, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.038231780167264036, | |
| "grad_norm": 23.029653549194336, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 4.7554, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.04778972520908005, | |
| "grad_norm": 11.564626693725586, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 2.7114, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.05734767025089606, | |
| "grad_norm": 7.584926128387451, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 1.3655, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.06690561529271206, | |
| "grad_norm": 3.4117257595062256, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 0.8595, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.07646356033452807, | |
| "grad_norm": 2.665032386779785, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 0.7759, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.08602150537634409, | |
| "grad_norm": 4.858867168426514, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 0.7931, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0955794504181601, | |
| "grad_norm": 1.6382043361663818, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 0.7167, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.10513739545997611, | |
| "grad_norm": 1.435800313949585, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 0.7138, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.11469534050179211, | |
| "grad_norm": 1.3022730350494385, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 0.7065, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.12425328554360812, | |
| "grad_norm": 1.7790203094482422, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 0.7603, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.13381123058542413, | |
| "grad_norm": 2.145930528640747, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 0.6962, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.14336917562724014, | |
| "grad_norm": 3.6625754833221436, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 0.7318, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.15292712066905614, | |
| "grad_norm": 3.043951988220215, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 0.7142, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.16248506571087215, | |
| "grad_norm": 2.281741142272949, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 0.7058, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.17204301075268819, | |
| "grad_norm": 1.8166581392288208, | |
| "learning_rate": 7.75e-05, | |
| "loss": 0.7094, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.1816009557945042, | |
| "grad_norm": 3.3029603958129883, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 0.745, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.1911589008363202, | |
| "grad_norm": 2.1072375774383545, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 0.7117, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.2007168458781362, | |
| "grad_norm": 4.407688140869141, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 0.7202, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.21027479091995221, | |
| "grad_norm": 1.135046124458313, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 0.7043, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.21983273596176822, | |
| "grad_norm": 1.131081461906433, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 0.6843, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.22939068100358423, | |
| "grad_norm": 0.6918812990188599, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 0.6942, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.23894862604540024, | |
| "grad_norm": 2.052278518676758, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 0.748, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.23894862604540024, | |
| "eval_loss": 0.6997354626655579, | |
| "eval_runtime": 2.0322, | |
| "eval_samples_per_second": 24.604, | |
| "eval_steps_per_second": 6.397, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.24850657108721624, | |
| "grad_norm": 0.7586610913276672, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 0.7004, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.25806451612903225, | |
| "grad_norm": 1.076542854309082, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 0.6972, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.26762246117084826, | |
| "grad_norm": 1.4424303770065308, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 0.6967, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.27718040621266427, | |
| "grad_norm": 1.472855806350708, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 0.7022, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.2867383512544803, | |
| "grad_norm": 0.6519089341163635, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 0.6861, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.2962962962962963, | |
| "grad_norm": 1.0849039554595947, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 0.7029, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.3058542413381123, | |
| "grad_norm": 0.612296462059021, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 0.6895, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.3154121863799283, | |
| "grad_norm": 0.9275369048118591, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 0.7005, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.3249701314217443, | |
| "grad_norm": 0.8235135674476624, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 0.697, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.3345280764635603, | |
| "grad_norm": 0.6381819248199463, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 0.6879, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.34408602150537637, | |
| "grad_norm": 1.0177886486053467, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 0.7004, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.3536439665471924, | |
| "grad_norm": 0.8794744610786438, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 0.7023, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.3632019115890084, | |
| "grad_norm": 0.8776364922523499, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 0.6876, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.3727598566308244, | |
| "grad_norm": 0.612334132194519, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 0.6956, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.3823178016726404, | |
| "grad_norm": 1.2593517303466797, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 0.6988, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.3918757467144564, | |
| "grad_norm": 1.0815540552139282, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 0.7007, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.4014336917562724, | |
| "grad_norm": 0.7590096592903137, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 0.6985, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.4109916367980884, | |
| "grad_norm": 0.6991857290267944, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 0.6941, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.42054958183990443, | |
| "grad_norm": 1.1214922666549683, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 0.7013, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.43010752688172044, | |
| "grad_norm": 1.3420926332473755, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 0.6983, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.43966547192353644, | |
| "grad_norm": 0.8333279490470886, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 0.6937, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.44922341696535245, | |
| "grad_norm": 0.8321746587753296, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 0.6935, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.45878136200716846, | |
| "grad_norm": 0.8994906544685364, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 0.6884, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.46833930704898447, | |
| "grad_norm": 0.8762169480323792, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 0.6981, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.4778972520908005, | |
| "grad_norm": 1.2555692195892334, | |
| "learning_rate": 1e-05, | |
| "loss": 0.7074, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.4778972520908005, | |
| "eval_loss": 0.6973173022270203, | |
| "eval_runtime": 2.0327, | |
| "eval_samples_per_second": 24.598, | |
| "eval_steps_per_second": 6.395, | |
| "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": 5.968083617316864e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |