| { | |
| "best_metric": 3.973642748178463e-08, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.006960213678559932, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00013920427357119863, | |
| "grad_norm": 66.76570129394531, | |
| "learning_rate": 5e-05, | |
| "loss": 7.3347, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00013920427357119863, | |
| "eval_loss": 7.334649562835693, | |
| "eval_runtime": 5.218, | |
| "eval_samples_per_second": 9.582, | |
| "eval_steps_per_second": 2.491, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00027840854714239726, | |
| "grad_norm": 66.82315826416016, | |
| "learning_rate": 0.0001, | |
| "loss": 7.3347, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0004176128207135959, | |
| "grad_norm": 17.973814010620117, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 2.21, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0005568170942847945, | |
| "grad_norm": 9.87483024597168, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 0.9469, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0006960213678559932, | |
| "grad_norm": 4.042817115783691, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 0.2736, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0008352256414271918, | |
| "grad_norm": 0.7625594735145569, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 0.0226, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0009744299149983905, | |
| "grad_norm": 0.5857932567596436, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 0.0019, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.001113634188569589, | |
| "grad_norm": 0.011121207848191261, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 0.0001, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0012528384621407877, | |
| "grad_norm": 0.006695534568279982, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 0.0001, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0013920427357119864, | |
| "grad_norm": 0.0028506112284958363, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.001531247009283185, | |
| "grad_norm": 0.0027052212972193956, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0016704512828543837, | |
| "grad_norm": 0.0030260086059570312, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0018096555564255823, | |
| "grad_norm": 0.0018961799796670675, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.001948859829996781, | |
| "grad_norm": 0.0010025562951341271, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0020880641035679794, | |
| "grad_norm": 0.0005600674776360393, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.002227268377139178, | |
| "grad_norm": 0.0004226661112625152, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0023664726507103767, | |
| "grad_norm": 0.0003113994898740202, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0025056769242815754, | |
| "grad_norm": 0.0002461711410433054, | |
| "learning_rate": 7.75e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.002644881197852774, | |
| "grad_norm": 0.0001630903861951083, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0027840854714239727, | |
| "grad_norm": 0.000140488293254748, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0029232897449951714, | |
| "grad_norm": 0.0001187040688819252, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.00306249401856637, | |
| "grad_norm": 0.00011745603114832193, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0032016982921375687, | |
| "grad_norm": 9.022743324749172e-05, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0033409025657087674, | |
| "grad_norm": 7.21417018212378e-05, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.003480106839279966, | |
| "grad_norm": 8.124095620587468e-05, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.003480106839279966, | |
| "eval_loss": 1.7881389169360773e-07, | |
| "eval_runtime": 5.1938, | |
| "eval_samples_per_second": 9.627, | |
| "eval_steps_per_second": 2.503, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0036193111128511647, | |
| "grad_norm": 6.752758054062724e-05, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0037585153864223633, | |
| "grad_norm": 5.6042164942482486e-05, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.003897719659993562, | |
| "grad_norm": 4.698020711657591e-05, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.004036923933564761, | |
| "grad_norm": 4.064290624228306e-05, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 0.0, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.004176128207135959, | |
| "grad_norm": 3.3646061638137326e-05, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.004315332480707158, | |
| "grad_norm": 2.9114757126080804e-05, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 0.0, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.004454536754278356, | |
| "grad_norm": 3.0572762625524774e-05, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 0.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.004593741027849555, | |
| "grad_norm": 2.7114840122521855e-05, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.0047329453014207535, | |
| "grad_norm": 2.4281154765048996e-05, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 0.0, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.004872149574991953, | |
| "grad_norm": 2.2557736883754842e-05, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.005011353848563151, | |
| "grad_norm": 2.0800394850084558e-05, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.00515055812213435, | |
| "grad_norm": 2.0314013454481028e-05, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 0.0, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.005289762395705548, | |
| "grad_norm": 1.936802436830476e-05, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 0.0, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.005428966669276747, | |
| "grad_norm": 1.9238419554312713e-05, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.0055681709428479454, | |
| "grad_norm": 1.91349427041132e-05, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.005707375216419144, | |
| "grad_norm": 1.6851270629558712e-05, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 0.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.005846579489990343, | |
| "grad_norm": 1.6155534467543475e-05, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.005985783763561541, | |
| "grad_norm": 1.6756492186686955e-05, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 0.0, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.00612498803713274, | |
| "grad_norm": 1.688018710410688e-05, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 0.0, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.006264192310703938, | |
| "grad_norm": 1.6521807992830873e-05, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.006403396584275137, | |
| "grad_norm": 1.6070989659056067e-05, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 0.0, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.006542600857846336, | |
| "grad_norm": 1.5321618775487877e-05, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 0.0, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.006681805131417535, | |
| "grad_norm": 1.7318605387117714e-05, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.006821009404988733, | |
| "grad_norm": 1.6765192413004115e-05, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 0.0, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.006960213678559932, | |
| "grad_norm": 1.6366233467124403e-05, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.006960213678559932, | |
| "eval_loss": 3.973642748178463e-08, | |
| "eval_runtime": 5.1019, | |
| "eval_samples_per_second": 9.8, | |
| "eval_steps_per_second": 2.548, | |
| "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": 6.631381723512832e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |