| { | |
| "best_metric": 0.36945176124572754, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.16263468184590363, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0032526936369180726, | |
| "grad_norm": 26.336450576782227, | |
| "learning_rate": 5e-05, | |
| "loss": 9.0581, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0032526936369180726, | |
| "eval_loss": 9.123590469360352, | |
| "eval_runtime": 1.4799, | |
| "eval_samples_per_second": 33.787, | |
| "eval_steps_per_second": 8.785, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.006505387273836145, | |
| "grad_norm": 26.824033737182617, | |
| "learning_rate": 0.0001, | |
| "loss": 9.0362, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00975808091075422, | |
| "grad_norm": 23.17852020263672, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 8.1441, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.01301077454767229, | |
| "grad_norm": 15.278055191040039, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 5.2184, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.016263468184590364, | |
| "grad_norm": 11.492183685302734, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 3.9312, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.01951616182150844, | |
| "grad_norm": 12.07217788696289, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 2.8775, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.02276885545842651, | |
| "grad_norm": 11.371002197265625, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 1.8724, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.02602154909534458, | |
| "grad_norm": 8.905228614807129, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 1.1029, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.029274242732262656, | |
| "grad_norm": 8.547820091247559, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 0.6571, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.03252693636918073, | |
| "grad_norm": 11.54881477355957, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 0.6135, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0357796300060988, | |
| "grad_norm": 4.279499053955078, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 0.4434, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.03903232364301688, | |
| "grad_norm": 5.570874214172363, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 0.439, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.042285017279934944, | |
| "grad_norm": 5.5681843757629395, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 0.4204, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.04553771091685302, | |
| "grad_norm": 2.0453896522521973, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 0.3679, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.048790404553771094, | |
| "grad_norm": 5.847940921783447, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 0.4333, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.05204309819068916, | |
| "grad_norm": 7.754000663757324, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 0.5244, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.05529579182760724, | |
| "grad_norm": 6.063351154327393, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 0.4551, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.05854848546452531, | |
| "grad_norm": 3.6564249992370605, | |
| "learning_rate": 7.75e-05, | |
| "loss": 0.3922, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.061801179101443386, | |
| "grad_norm": 4.903731346130371, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 0.4288, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.06505387273836145, | |
| "grad_norm": 5.632251262664795, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 0.4817, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.06830656637527953, | |
| "grad_norm": 5.78528356552124, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 0.4657, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0715592600121976, | |
| "grad_norm": 3.3132612705230713, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 0.3785, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.07481195364911568, | |
| "grad_norm": 2.9017672538757324, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 0.3931, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.07806464728603375, | |
| "grad_norm": 2.158385992050171, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 0.3776, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.08131734092295181, | |
| "grad_norm": 5.685708045959473, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 0.4381, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.08131734092295181, | |
| "eval_loss": 0.4012819528579712, | |
| "eval_runtime": 0.9585, | |
| "eval_samples_per_second": 52.165, | |
| "eval_steps_per_second": 13.563, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.08457003455986989, | |
| "grad_norm": 1.9013361930847168, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 0.3487, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.08782272819678796, | |
| "grad_norm": 1.1355395317077637, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 0.3625, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.09107542183370604, | |
| "grad_norm": 1.7093337774276733, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 0.3684, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.09432811547062411, | |
| "grad_norm": 2.666853427886963, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 0.4088, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.09758080910754219, | |
| "grad_norm": 3.9227817058563232, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 0.3787, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.10083350274446026, | |
| "grad_norm": 2.1414694786071777, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 0.3545, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.10408619638137832, | |
| "grad_norm": 2.217756986618042, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 0.3893, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.1073388900182964, | |
| "grad_norm": 1.2464871406555176, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 0.3589, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.11059158365521447, | |
| "grad_norm": 2.3798458576202393, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 0.3977, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.11384427729213255, | |
| "grad_norm": 0.625939667224884, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 0.3654, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.11709697092905062, | |
| "grad_norm": 1.7202353477478027, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 0.3876, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.1203496645659687, | |
| "grad_norm": 3.1904664039611816, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 0.3818, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.12360235820288677, | |
| "grad_norm": 2.18723201751709, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 0.4145, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.12685505183980483, | |
| "grad_norm": 5.541439533233643, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 0.4644, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.1301077454767229, | |
| "grad_norm": 5.606419563293457, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 0.4775, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.13336043911364098, | |
| "grad_norm": 3.325843095779419, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 0.4146, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.13661313275055906, | |
| "grad_norm": 2.5272328853607178, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 0.3798, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.13986582638747713, | |
| "grad_norm": 0.6817333102226257, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 0.3452, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.1431185200243952, | |
| "grad_norm": 0.49600663781166077, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 0.3539, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.14637121366131328, | |
| "grad_norm": 1.7873883247375488, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 0.3806, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.14962390729823136, | |
| "grad_norm": 2.138842821121216, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 0.3836, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.15287660093514943, | |
| "grad_norm": 1.6219154596328735, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 0.3823, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.1561292945720675, | |
| "grad_norm": 2.0069103240966797, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 0.3583, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.15938198820898555, | |
| "grad_norm": 3.421016216278076, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 0.4189, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.16263468184590363, | |
| "grad_norm": 2.984545946121216, | |
| "learning_rate": 1e-05, | |
| "loss": 0.4189, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.16263468184590363, | |
| "eval_loss": 0.36945176124572754, | |
| "eval_runtime": 0.9603, | |
| "eval_samples_per_second": 52.065, | |
| "eval_steps_per_second": 13.537, | |
| "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": 7.83042868150272e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |