| { | |
| "best_metric": 0.41836661100387573, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.07928249343441851, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0015856498686883703, | |
| "grad_norm": 1.2695943117141724, | |
| "learning_rate": 5e-05, | |
| "loss": 14.701, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0015856498686883703, | |
| "eval_loss": 0.7034574151039124, | |
| "eval_runtime": 32.2742, | |
| "eval_samples_per_second": 1.549, | |
| "eval_steps_per_second": 1.549, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0031712997373767406, | |
| "grad_norm": 1.7672878503799438, | |
| "learning_rate": 0.0001, | |
| "loss": 15.9017, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00475694960606511, | |
| "grad_norm": 1.6396403312683105, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 14.1394, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.006342599474753481, | |
| "grad_norm": 2.486941337585449, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 17.648, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.007928249343441851, | |
| "grad_norm": 2.6891353130340576, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 17.1247, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00951389921213022, | |
| "grad_norm": 3.120403528213501, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 18.4393, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.011099549080818592, | |
| "grad_norm": 3.2562410831451416, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 16.208, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.012685198949506963, | |
| "grad_norm": 3.946000099182129, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 18.0389, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.014270848818195332, | |
| "grad_norm": 4.844947814941406, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 16.1009, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.015856498686883703, | |
| "grad_norm": 5.804704666137695, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 16.2563, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.017442148555572072, | |
| "grad_norm": 5.010881423950195, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 14.875, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.01902779842426044, | |
| "grad_norm": 4.86008882522583, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 15.9194, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.020613448292948814, | |
| "grad_norm": 4.434284687042236, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 12.6462, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.022199098161637183, | |
| "grad_norm": 4.004912376403809, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 14.5125, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.023784748030325552, | |
| "grad_norm": 4.139750957489014, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 13.1571, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.025370397899013925, | |
| "grad_norm": 4.041270732879639, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 13.7225, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.026956047767702294, | |
| "grad_norm": 3.7319929599761963, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 13.4277, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.028541697636390664, | |
| "grad_norm": 4.708305835723877, | |
| "learning_rate": 7.75e-05, | |
| "loss": 13.6227, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.030127347505079036, | |
| "grad_norm": 3.9304122924804688, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 12.0749, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.031712997373767406, | |
| "grad_norm": 4.36229133605957, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 12.5221, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.03329864724245578, | |
| "grad_norm": 4.089043617248535, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 12.4809, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.034884297111144144, | |
| "grad_norm": 4.526259899139404, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 13.1436, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.03646994697983252, | |
| "grad_norm": 4.510824680328369, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 13.9883, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.03805559684852088, | |
| "grad_norm": 4.993456840515137, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 11.316, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.039641246717209255, | |
| "grad_norm": 4.436211585998535, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 13.9108, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.039641246717209255, | |
| "eval_loss": 0.45079493522644043, | |
| "eval_runtime": 32.3943, | |
| "eval_samples_per_second": 1.543, | |
| "eval_steps_per_second": 1.543, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.04122689658589763, | |
| "grad_norm": 4.445535182952881, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 15.3734, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.042812546454585994, | |
| "grad_norm": 4.722578525543213, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 15.0681, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.044398196323274366, | |
| "grad_norm": 4.662483215332031, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 12.8593, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.04598384619196274, | |
| "grad_norm": 4.774641036987305, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 14.9759, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.047569496060651105, | |
| "grad_norm": 4.80148458480835, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 14.2648, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.04915514592933948, | |
| "grad_norm": 4.728338718414307, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 13.1279, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.05074079579802785, | |
| "grad_norm": 4.526378631591797, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 12.6951, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.052326445666716216, | |
| "grad_norm": 4.543455600738525, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 12.6935, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.05391209553540459, | |
| "grad_norm": 4.797730922698975, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 12.7275, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.05549774540409296, | |
| "grad_norm": 5.633406162261963, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 15.7208, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.05708339527278133, | |
| "grad_norm": 5.659888744354248, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 15.1841, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.0586690451414697, | |
| "grad_norm": 6.257349967956543, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 18.2712, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.06025469501015807, | |
| "grad_norm": 5.911546230316162, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 15.9163, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.06184034487884644, | |
| "grad_norm": 5.786442756652832, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 15.7632, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.06342599474753481, | |
| "grad_norm": 6.7470879554748535, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 15.5596, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.06501164461622318, | |
| "grad_norm": 6.114599227905273, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 16.4764, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.06659729448491156, | |
| "grad_norm": 7.806087493896484, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 16.9766, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.06818294435359992, | |
| "grad_norm": 7.94345760345459, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 16.4281, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.06976859422228829, | |
| "grad_norm": 7.828482151031494, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 18.5273, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.07135424409097667, | |
| "grad_norm": 8.026106834411621, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 16.7366, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.07293989395966503, | |
| "grad_norm": 8.980546951293945, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 18.6461, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.0745255438283534, | |
| "grad_norm": 9.830076217651367, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 21.7088, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.07611119369704177, | |
| "grad_norm": 13.883023262023926, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 25.3251, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.07769684356573014, | |
| "grad_norm": 17.941938400268555, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 25.1379, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.07928249343441851, | |
| "grad_norm": 19.284452438354492, | |
| "learning_rate": 1e-05, | |
| "loss": 27.9763, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.07928249343441851, | |
| "eval_loss": 0.41836661100387573, | |
| "eval_runtime": 32.3564, | |
| "eval_samples_per_second": 1.545, | |
| "eval_steps_per_second": 1.545, | |
| "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": 2.5578156589056e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |