| { | |
| "best_metric": 0.2489974945783615, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.04418668876001105, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0008837337752002209, | |
| "grad_norm": 188.7264404296875, | |
| "learning_rate": 5e-05, | |
| "loss": 78.8559, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0008837337752002209, | |
| "eval_loss": 7.0791120529174805, | |
| "eval_runtime": 3.4145, | |
| "eval_samples_per_second": 14.644, | |
| "eval_steps_per_second": 3.807, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0017674675504004418, | |
| "grad_norm": 134.01148986816406, | |
| "learning_rate": 0.0001, | |
| "loss": 68.5439, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.002651201325600663, | |
| "grad_norm": 205.53016662597656, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 60.0711, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0035349351008008836, | |
| "grad_norm": 346.5276184082031, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 107.7584, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.004418668876001105, | |
| "grad_norm": 189.2183380126953, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 70.1176, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.005302402651201326, | |
| "grad_norm": 65.08003234863281, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 23.8074, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.006186136426401547, | |
| "grad_norm": 188.70327758789062, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 68.932, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.007069870201601767, | |
| "grad_norm": 146.6932373046875, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 68.0882, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.007953603976801988, | |
| "grad_norm": 99.594482421875, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 39.7863, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00883733775200221, | |
| "grad_norm": 226.75144958496094, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 56.68, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00972107152720243, | |
| "grad_norm": 186.5191650390625, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 39.2583, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.010604805302402652, | |
| "grad_norm": 120.8751449584961, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 27.5095, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.011488539077602873, | |
| "grad_norm": 97.58418273925781, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 33.2122, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.012372272852803094, | |
| "grad_norm": 68.11288452148438, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 23.7651, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.013256006628003313, | |
| "grad_norm": 113.01734161376953, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 19.8349, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.014139740403203534, | |
| "grad_norm": 122.89698028564453, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 30.7554, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.015023474178403756, | |
| "grad_norm": 91.34784698486328, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 18.732, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.015907207953603977, | |
| "grad_norm": 246.92771911621094, | |
| "learning_rate": 7.75e-05, | |
| "loss": 21.3745, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.016790941728804198, | |
| "grad_norm": 61.28251647949219, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 11.951, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.01767467550400442, | |
| "grad_norm": 219.4673614501953, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 20.5826, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.01855840927920464, | |
| "grad_norm": 110.95178985595703, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 9.547, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.01944214305440486, | |
| "grad_norm": 129.61492919921875, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 19.496, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.020325876829605082, | |
| "grad_norm": 184.5301513671875, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 15.6161, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.021209610604805303, | |
| "grad_norm": 105.81380462646484, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 23.4072, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.022093344380005524, | |
| "grad_norm": 111.31070709228516, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 21.2348, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.022093344380005524, | |
| "eval_loss": 0.9043247699737549, | |
| "eval_runtime": 3.4856, | |
| "eval_samples_per_second": 14.345, | |
| "eval_steps_per_second": 3.73, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.022977078155205746, | |
| "grad_norm": 53.11459732055664, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 10.3292, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.023860811930405967, | |
| "grad_norm": 59.67228317260742, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 14.2238, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.024744545705606188, | |
| "grad_norm": 76.35183715820312, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 10.0212, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.025628279480806405, | |
| "grad_norm": 81.94586944580078, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 14.2928, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.026512013256006627, | |
| "grad_norm": 57.83568572998047, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 4.3004, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.027395747031206848, | |
| "grad_norm": 37.16580581665039, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 4.3446, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.02827948080640707, | |
| "grad_norm": 43.2403450012207, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 7.3295, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.02916321458160729, | |
| "grad_norm": 92.82877349853516, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 9.9978, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.03004694835680751, | |
| "grad_norm": 47.803977966308594, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 5.1052, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.030930682132007732, | |
| "grad_norm": 71.9683609008789, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 9.7027, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.03181441590720795, | |
| "grad_norm": 50.05008316040039, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 8.7477, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.032698149682408174, | |
| "grad_norm": 52.16643524169922, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 7.9946, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.033581883457608395, | |
| "grad_norm": 44.67985916137695, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 7.7456, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.03446561723280862, | |
| "grad_norm": 26.479564666748047, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 4.5466, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.03534935100800884, | |
| "grad_norm": 38.651485443115234, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 5.1983, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.03623308478320906, | |
| "grad_norm": 33.117156982421875, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 2.2513, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.03711681855840928, | |
| "grad_norm": 60.45636749267578, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 3.6929, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.0380005523336095, | |
| "grad_norm": 18.882118225097656, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 1.9959, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.03888428610880972, | |
| "grad_norm": 17.66207504272461, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 1.375, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.03976801988400994, | |
| "grad_norm": 43.678035736083984, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 2.586, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.040651753659210164, | |
| "grad_norm": 40.00962448120117, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 3.0767, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.041535487434410386, | |
| "grad_norm": 27.8352108001709, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 2.1636, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.04241922120961061, | |
| "grad_norm": 79.74462127685547, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 5.0177, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.04330295498481083, | |
| "grad_norm": 39.04483413696289, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 4.5345, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.04418668876001105, | |
| "grad_norm": 36.16383743286133, | |
| "learning_rate": 1e-05, | |
| "loss": 4.9568, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.04418668876001105, | |
| "eval_loss": 0.2489974945783615, | |
| "eval_runtime": 3.468, | |
| "eval_samples_per_second": 14.418, | |
| "eval_steps_per_second": 3.749, | |
| "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": 2.967137622687744e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |