| { | |
| "best_metric": 2.4370641767745838e-05, | |
| "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": 26.938196182250977, | |
| "learning_rate": 5e-05, | |
| "loss": 13.9096, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0032526936369180726, | |
| "eval_loss": 1.1164056062698364, | |
| "eval_runtime": 2.9495, | |
| "eval_samples_per_second": 16.952, | |
| "eval_steps_per_second": 4.407, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.006505387273836145, | |
| "grad_norm": 30.800067901611328, | |
| "learning_rate": 0.0001, | |
| "loss": 16.4353, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00975808091075422, | |
| "grad_norm": 28.980260848999023, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 15.5479, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.01301077454767229, | |
| "grad_norm": 27.222143173217773, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 11.9474, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.016263468184590364, | |
| "grad_norm": 22.249568939208984, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 6.5466, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.01951616182150844, | |
| "grad_norm": 15.059317588806152, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 3.252, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.02276885545842651, | |
| "grad_norm": 9.444744110107422, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 1.6042, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.02602154909534458, | |
| "grad_norm": 6.794412612915039, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 0.8631, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.029274242732262656, | |
| "grad_norm": 2.7923848628997803, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 0.2988, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.03252693636918073, | |
| "grad_norm": 1.0953826904296875, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 0.0755, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0357796300060988, | |
| "grad_norm": 0.1885637640953064, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 0.0101, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.03903232364301688, | |
| "grad_norm": 0.19117560982704163, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 0.0051, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.042285017279934944, | |
| "grad_norm": 9.700277328491211, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 0.0693, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.04553771091685302, | |
| "grad_norm": 1.511494755744934, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 0.0186, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.048790404553771094, | |
| "grad_norm": 0.6943612098693848, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 0.0167, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.05204309819068916, | |
| "grad_norm": 0.07114950567483902, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 0.0022, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.05529579182760724, | |
| "grad_norm": 0.027020208537578583, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 0.0014, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.05854848546452531, | |
| "grad_norm": 0.8249042630195618, | |
| "learning_rate": 7.75e-05, | |
| "loss": 0.002, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.061801179101443386, | |
| "grad_norm": 0.04792841151356697, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 0.0007, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.06505387273836145, | |
| "grad_norm": 0.5568363070487976, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 0.004, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.06830656637527953, | |
| "grad_norm": 0.04415999725461006, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 0.0009, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0715592600121976, | |
| "grad_norm": 0.12361333519220352, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 0.0019, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.07481195364911568, | |
| "grad_norm": 0.5670086145401001, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 0.0017, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.07806464728603375, | |
| "grad_norm": 1.2928516864776611, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 0.0069, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.08131734092295181, | |
| "grad_norm": 2.51751971244812, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 0.0133, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.08131734092295181, | |
| "eval_loss": 3.148895120830275e-05, | |
| "eval_runtime": 2.9982, | |
| "eval_samples_per_second": 16.676, | |
| "eval_steps_per_second": 4.336, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.08457003455986989, | |
| "grad_norm": 0.2348364293575287, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 0.0016, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.08782272819678796, | |
| "grad_norm": 0.16821667551994324, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 0.0013, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.09107542183370604, | |
| "grad_norm": 0.030762257054448128, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 0.001, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.09432811547062411, | |
| "grad_norm": 0.03775183856487274, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 0.0017, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.09758080910754219, | |
| "grad_norm": 0.006697505712509155, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 0.0006, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.10083350274446026, | |
| "grad_norm": 0.024879690259695053, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 0.0008, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.10408619638137832, | |
| "grad_norm": 0.30223092436790466, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 0.0032, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.1073388900182964, | |
| "grad_norm": 0.014068452641367912, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 0.001, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.11059158365521447, | |
| "grad_norm": 0.023483309894800186, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 0.0009, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.11384427729213255, | |
| "grad_norm": 0.01585865579545498, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 0.0009, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.11709697092905062, | |
| "grad_norm": 0.04529554396867752, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 0.0017, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.1203496645659687, | |
| "grad_norm": 0.25387975573539734, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 0.0021, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.12360235820288677, | |
| "grad_norm": 0.2627509832382202, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 0.0035, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.12685505183980483, | |
| "grad_norm": 0.026653291657567024, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 0.0006, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.1301077454767229, | |
| "grad_norm": 0.009845051914453506, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 0.0008, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.13336043911364098, | |
| "grad_norm": 0.006667473819106817, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 0.0006, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.13661313275055906, | |
| "grad_norm": 0.04519423469901085, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 0.0008, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.13986582638747713, | |
| "grad_norm": 0.7729731798171997, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 0.0024, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.1431185200243952, | |
| "grad_norm": 0.004916268866509199, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 0.0005, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.14637121366131328, | |
| "grad_norm": 0.009590042755007744, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 0.0007, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.14962390729823136, | |
| "grad_norm": 0.014254098758101463, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 0.0008, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.15287660093514943, | |
| "grad_norm": 1.3294068574905396, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 0.0064, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.1561292945720675, | |
| "grad_norm": 0.00593988411128521, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 0.0005, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.15938198820898555, | |
| "grad_norm": 0.008307484909892082, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 0.0007, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.16263468184590363, | |
| "grad_norm": 0.01137072965502739, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0006, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.16263468184590363, | |
| "eval_loss": 2.4370641767745838e-05, | |
| "eval_runtime": 3.0145, | |
| "eval_samples_per_second": 16.586, | |
| "eval_steps_per_second": 4.312, | |
| "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": 5.259156315439104e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |