| { | |
| "best_metric": 3.1323347091674805, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.009828009828009828, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00019656019656019656, | |
| "grad_norm": 3.758068084716797, | |
| "learning_rate": 5e-05, | |
| "loss": 4.4277, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00019656019656019656, | |
| "eval_loss": 5.373585224151611, | |
| "eval_runtime": 1.4828, | |
| "eval_samples_per_second": 33.72, | |
| "eval_steps_per_second": 8.767, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0003931203931203931, | |
| "grad_norm": 4.782472610473633, | |
| "learning_rate": 0.0001, | |
| "loss": 5.0038, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0005896805896805897, | |
| "grad_norm": 4.263391971588135, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 5.0291, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0007862407862407862, | |
| "grad_norm": 3.7667124271392822, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 4.7841, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0009828009828009828, | |
| "grad_norm": 4.337853908538818, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 4.613, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0011793611793611794, | |
| "grad_norm": 5.1650614738464355, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 4.4618, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0013759213759213758, | |
| "grad_norm": 5.857794284820557, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 4.1691, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0015724815724815725, | |
| "grad_norm": 5.995926380157471, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 4.1516, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0017690417690417691, | |
| "grad_norm": 4.659512996673584, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 4.0268, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0019656019656019656, | |
| "grad_norm": 7.119444370269775, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 3.9753, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.002162162162162162, | |
| "grad_norm": 7.171023845672607, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 3.8129, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.002358722358722359, | |
| "grad_norm": 4.602221965789795, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 3.5625, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0025552825552825555, | |
| "grad_norm": 10.224493980407715, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 3.6479, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0027518427518427517, | |
| "grad_norm": 8.645211219787598, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 3.9153, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0029484029484029483, | |
| "grad_norm": 4.623680114746094, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 3.845, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.003144963144963145, | |
| "grad_norm": 3.61069393157959, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 3.8399, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0033415233415233416, | |
| "grad_norm": 4.654061794281006, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 3.7679, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0035380835380835383, | |
| "grad_norm": 5.0176544189453125, | |
| "learning_rate": 7.75e-05, | |
| "loss": 3.6448, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0037346437346437345, | |
| "grad_norm": 5.086390972137451, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 3.7069, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.003931203931203931, | |
| "grad_norm": 3.475961923599243, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 3.6616, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.004127764127764128, | |
| "grad_norm": 2.971919536590576, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 3.7266, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.004324324324324324, | |
| "grad_norm": 3.0936100482940674, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 3.597, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.004520884520884521, | |
| "grad_norm": 3.1046195030212402, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 3.4993, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.004717444717444718, | |
| "grad_norm": 3.3191919326782227, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 3.4105, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.004914004914004914, | |
| "grad_norm": 4.340789794921875, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 3.2663, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.004914004914004914, | |
| "eval_loss": 3.2968196868896484, | |
| "eval_runtime": 1.4996, | |
| "eval_samples_per_second": 33.341, | |
| "eval_steps_per_second": 8.669, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.005110565110565111, | |
| "grad_norm": 2.572341203689575, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 3.3732, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.005307125307125307, | |
| "grad_norm": 3.403599977493286, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 3.5602, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.005503685503685503, | |
| "grad_norm": 3.0410282611846924, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 3.6618, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.0057002457002457005, | |
| "grad_norm": 2.961358070373535, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 3.6719, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.005896805896805897, | |
| "grad_norm": 2.4283437728881836, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 3.6161, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.006093366093366094, | |
| "grad_norm": 1.9574626684188843, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 3.5441, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.00628992628992629, | |
| "grad_norm": 1.8170067071914673, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 3.5679, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.006486486486486486, | |
| "grad_norm": 1.8830921649932861, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 3.5489, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.006683046683046683, | |
| "grad_norm": 1.862863540649414, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 3.4594, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.0068796068796068794, | |
| "grad_norm": 1.9999181032180786, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 3.3772, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0070761670761670765, | |
| "grad_norm": 2.3578336238861084, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 3.3478, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.007272727272727273, | |
| "grad_norm": 2.8680801391601562, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 3.2627, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.007469287469287469, | |
| "grad_norm": 1.4693502187728882, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 3.0606, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.007665847665847666, | |
| "grad_norm": 1.6032438278198242, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 3.4613, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.007862407862407862, | |
| "grad_norm": 1.457249641418457, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 3.5225, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.00805896805896806, | |
| "grad_norm": 1.222512125968933, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 3.5046, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.008255528255528256, | |
| "grad_norm": 1.281494140625, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 3.5168, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.008452088452088452, | |
| "grad_norm": 1.415714144706726, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 3.6238, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.008648648648648649, | |
| "grad_norm": 1.6013180017471313, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 3.4776, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.008845208845208846, | |
| "grad_norm": 1.7021321058273315, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 3.5909, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.009041769041769041, | |
| "grad_norm": 1.7219823598861694, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 3.4036, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.009238329238329238, | |
| "grad_norm": 1.8510271310806274, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 3.4587, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.009434889434889435, | |
| "grad_norm": 2.234412431716919, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 3.5253, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.00963144963144963, | |
| "grad_norm": 2.6374800205230713, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 3.4089, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.009828009828009828, | |
| "grad_norm": 3.493394136428833, | |
| "learning_rate": 1e-05, | |
| "loss": 3.0774, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.009828009828009828, | |
| "eval_loss": 3.1323347091674805, | |
| "eval_runtime": 1.5396, | |
| "eval_samples_per_second": 32.476, | |
| "eval_steps_per_second": 8.444, | |
| "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": 2.95300912644096e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |