| { | |
| "best_metric": 0.2368658483028412, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.11056595950521733, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0022113191901043465, | |
| "grad_norm": 1266.8173828125, | |
| "learning_rate": 5e-05, | |
| "loss": 130.6273, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0022113191901043465, | |
| "eval_loss": 3.3367362022399902, | |
| "eval_runtime": 3.0918, | |
| "eval_samples_per_second": 16.172, | |
| "eval_steps_per_second": 4.205, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004422638380208693, | |
| "grad_norm": 1228.9942626953125, | |
| "learning_rate": 0.0001, | |
| "loss": 135.8005, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00663395757031304, | |
| "grad_norm": 893.6980590820312, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 81.7229, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.008845276760417386, | |
| "grad_norm": 616.2275390625, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 50.632, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.011056595950521733, | |
| "grad_norm": 1459.5819091796875, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 75.3263, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.01326791514062608, | |
| "grad_norm": 315.1625671386719, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 21.8838, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.015479234330730427, | |
| "grad_norm": 1401.111083984375, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 39.3447, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.017690553520834772, | |
| "grad_norm": 298.81280517578125, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 19.4309, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.01990187271093912, | |
| "grad_norm": 422.7381591796875, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 22.1325, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.022113191901043466, | |
| "grad_norm": 443.7731628417969, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 19.4608, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.02432451109114781, | |
| "grad_norm": 230.34886169433594, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 14.7356, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.02653583028125216, | |
| "grad_norm": 370.49786376953125, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 11.2922, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.028747149471356506, | |
| "grad_norm": 249.0677947998047, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 13.2127, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.030958468661460854, | |
| "grad_norm": 180.40122985839844, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 11.3355, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0331697878515652, | |
| "grad_norm": 233.73875427246094, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 12.585, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.035381107041669545, | |
| "grad_norm": 191.15699768066406, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 13.1807, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.03759242623177389, | |
| "grad_norm": 191.31100463867188, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 14.3639, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.03980374542187824, | |
| "grad_norm": 175.0061798095703, | |
| "learning_rate": 7.75e-05, | |
| "loss": 11.2044, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.04201506461198259, | |
| "grad_norm": 147.7163848876953, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 12.4057, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.04422638380208693, | |
| "grad_norm": 163.385009765625, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 9.6362, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.04643770299219128, | |
| "grad_norm": 140.2444610595703, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 7.4195, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.04864902218229562, | |
| "grad_norm": 136.61859130859375, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 10.4054, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.050860341372399975, | |
| "grad_norm": 157.8791961669922, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 10.6133, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.05307166056250432, | |
| "grad_norm": 169.0653839111328, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 9.754, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.055282979752608666, | |
| "grad_norm": 191.57464599609375, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 11.1938, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.055282979752608666, | |
| "eval_loss": 0.30715107917785645, | |
| "eval_runtime": 3.0653, | |
| "eval_samples_per_second": 16.312, | |
| "eval_steps_per_second": 4.241, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.05749429894271301, | |
| "grad_norm": 112.55488586425781, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 9.1382, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.059705618132817356, | |
| "grad_norm": 166.33534240722656, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 9.9689, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.06191693732292171, | |
| "grad_norm": 146.36526489257812, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 10.5303, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.06412825651302605, | |
| "grad_norm": 121.34736633300781, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 9.7238, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.0663395757031304, | |
| "grad_norm": 87.24940490722656, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 6.6125, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.06855089489323475, | |
| "grad_norm": 96.96258544921875, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 8.0596, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.07076221408333909, | |
| "grad_norm": 122.00680541992188, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 8.7681, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.07297353327344344, | |
| "grad_norm": 114.9303207397461, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 10.3328, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.07518485246354778, | |
| "grad_norm": 112.72858428955078, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 8.9349, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.07739617165365213, | |
| "grad_norm": 100.95106506347656, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 8.6053, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.07960749084375648, | |
| "grad_norm": 95.06898498535156, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 7.9513, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.08181881003386082, | |
| "grad_norm": 101.6524658203125, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 8.3089, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.08403012922396517, | |
| "grad_norm": 89.02762603759766, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 6.7646, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.08624144841406951, | |
| "grad_norm": 184.59141540527344, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 12.0435, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.08845276760417387, | |
| "grad_norm": 123.04720306396484, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 8.9847, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.09066408679427822, | |
| "grad_norm": 127.1465072631836, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 9.742, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.09287540598438256, | |
| "grad_norm": 91.50184631347656, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 8.8613, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.09508672517448691, | |
| "grad_norm": 121.56517791748047, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 11.1114, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.09729804436459125, | |
| "grad_norm": 167.5218048095703, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 8.5462, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.0995093635546956, | |
| "grad_norm": 109.18016815185547, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 6.4312, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.10172068274479995, | |
| "grad_norm": 119.26715087890625, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 6.6959, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.10393200193490429, | |
| "grad_norm": 88.47723388671875, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 7.4441, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.10614332112500864, | |
| "grad_norm": 90.03621673583984, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 6.4245, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.10835464031511298, | |
| "grad_norm": 180.63720703125, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 9.3648, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.11056595950521733, | |
| "grad_norm": 119.29557800292969, | |
| "learning_rate": 1e-05, | |
| "loss": 9.1602, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.11056595950521733, | |
| "eval_loss": 0.2368658483028412, | |
| "eval_runtime": 3.0471, | |
| "eval_samples_per_second": 16.409, | |
| "eval_steps_per_second": 4.266, | |
| "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": 5.658027780734976e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |