| { | |
| "best_metric": 2.398091419308912e-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": 26.712371826171875, | |
| "learning_rate": 5e-05, | |
| "loss": 13.9096, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0032526936369180726, | |
| "eval_loss": 1.1164056062698364, | |
| "eval_runtime": 2.9801, | |
| "eval_samples_per_second": 16.778, | |
| "eval_steps_per_second": 4.362, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.006505387273836145, | |
| "grad_norm": 30.42289161682129, | |
| "learning_rate": 0.0001, | |
| "loss": 16.4353, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00975808091075422, | |
| "grad_norm": 28.80431365966797, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 15.5446, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.01301077454767229, | |
| "grad_norm": 27.237125396728516, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 11.9457, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.016263468184590364, | |
| "grad_norm": 22.341909408569336, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 6.5323, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.01951616182150844, | |
| "grad_norm": 15.01369857788086, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 3.2113, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.02276885545842651, | |
| "grad_norm": 9.229114532470703, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 1.575, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.02602154909534458, | |
| "grad_norm": 6.6448798179626465, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 0.8369, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.029274242732262656, | |
| "grad_norm": 2.6261746883392334, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 0.281, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.03252693636918073, | |
| "grad_norm": 1.0150703191757202, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 0.0699, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0357796300060988, | |
| "grad_norm": 0.1931096911430359, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 0.0098, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.03903232364301688, | |
| "grad_norm": 0.23602637648582458, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 0.0052, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.042285017279934944, | |
| "grad_norm": 8.177572250366211, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 0.0579, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.04553771091685302, | |
| "grad_norm": 1.2461020946502686, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 0.0166, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.048790404553771094, | |
| "grad_norm": 0.680696964263916, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 0.0155, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.05204309819068916, | |
| "grad_norm": 0.06047433242201805, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 0.0021, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.05529579182760724, | |
| "grad_norm": 0.023200832307338715, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 0.0014, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.05854848546452531, | |
| "grad_norm": 3.277186870574951, | |
| "learning_rate": 7.75e-05, | |
| "loss": 0.0114, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.061801179101443386, | |
| "grad_norm": 0.02421419695019722, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 0.0007, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.06505387273836145, | |
| "grad_norm": 0.599700391292572, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 0.0041, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.06830656637527953, | |
| "grad_norm": 0.2749795615673065, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 0.0016, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0715592600121976, | |
| "grad_norm": 0.12743216753005981, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 0.0018, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.07481195364911568, | |
| "grad_norm": 1.3546181917190552, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 0.0044, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.07806464728603375, | |
| "grad_norm": 1.1135410070419312, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 0.0136, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.08131734092295181, | |
| "grad_norm": 4.629287242889404, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 0.0087, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.08131734092295181, | |
| "eval_loss": 3.5030836443183944e-05, | |
| "eval_runtime": 2.9973, | |
| "eval_samples_per_second": 16.682, | |
| "eval_steps_per_second": 4.337, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.08457003455986989, | |
| "grad_norm": 0.5809001326560974, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 0.0041, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.08782272819678796, | |
| "grad_norm": 0.7393910884857178, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 0.0034, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.09107542183370604, | |
| "grad_norm": 0.7353512644767761, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 0.0025, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.09432811547062411, | |
| "grad_norm": 0.04128008335828781, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 0.0018, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.09758080910754219, | |
| "grad_norm": 0.007420813199132681, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 0.0006, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.10083350274446026, | |
| "grad_norm": 0.03794967010617256, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 0.0009, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.10408619638137832, | |
| "grad_norm": 0.15001359581947327, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 0.0019, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.1073388900182964, | |
| "grad_norm": 0.011495936661958694, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 0.0009, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.11059158365521447, | |
| "grad_norm": 0.030072197318077087, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 0.0011, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.11384427729213255, | |
| "grad_norm": 0.01134544238448143, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 0.0008, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.11709697092905062, | |
| "grad_norm": 0.055174022912979126, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 0.002, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.1203496645659687, | |
| "grad_norm": 0.048915062099695206, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 0.0015, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.12360235820288677, | |
| "grad_norm": 2.390549659729004, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 0.1271, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.12685505183980483, | |
| "grad_norm": 0.6761870980262756, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 0.0114, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.1301077454767229, | |
| "grad_norm": 0.011089229956269264, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 0.0007, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.13336043911364098, | |
| "grad_norm": 0.00595944095402956, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 0.0006, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.13661313275055906, | |
| "grad_norm": 0.011473946273326874, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 0.0006, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.13986582638747713, | |
| "grad_norm": 0.08607928454875946, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 0.0021, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.1431185200243952, | |
| "grad_norm": 0.0036287973634898663, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 0.0004, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.14637121366131328, | |
| "grad_norm": 0.008640116080641747, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 0.0007, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.14962390729823136, | |
| "grad_norm": 0.010114687494933605, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 0.0007, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.15287660093514943, | |
| "grad_norm": 7.031486988067627, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 0.0345, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.1561292945720675, | |
| "grad_norm": 0.1903190314769745, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 0.0009, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.15938198820898555, | |
| "grad_norm": 0.00516266655176878, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 0.0005, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.16263468184590363, | |
| "grad_norm": 0.008884044364094734, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0006, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.16263468184590363, | |
| "eval_loss": 2.398091419308912e-05, | |
| "eval_runtime": 2.9987, | |
| "eval_samples_per_second": 16.674, | |
| "eval_steps_per_second": 4.335, | |
| "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 | |
| } | |