{ "best_metric": 0.2565852403640747, "best_model_checkpoint": "miner_id_24/checkpoint-50", "epoch": 0.04860562610122122, "eval_steps": 25, "global_step": 50, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0009721125220244244, "grad_norm": 39.46260452270508, "learning_rate": 5e-05, "loss": 12.271, "step": 1 }, { "epoch": 0.0009721125220244244, "eval_loss": 13.372447967529297, "eval_runtime": 3.3247, "eval_samples_per_second": 15.039, "eval_steps_per_second": 3.91, "step": 1 }, { "epoch": 0.0019442250440488487, "grad_norm": 40.52149963378906, "learning_rate": 0.0001, "loss": 12.1994, "step": 2 }, { "epoch": 0.002916337566073273, "grad_norm": 33.2764778137207, "learning_rate": 9.990365154573717e-05, "loss": 9.3924, "step": 3 }, { "epoch": 0.0038884500880976974, "grad_norm": 15.774291038513184, "learning_rate": 9.961501876182148e-05, "loss": 3.8717, "step": 4 }, { "epoch": 0.004860562610122122, "grad_norm": 8.374436378479004, "learning_rate": 9.913533761814537e-05, "loss": 1.6584, "step": 5 }, { "epoch": 0.005832675132146546, "grad_norm": 4.43540620803833, "learning_rate": 9.846666218300807e-05, "loss": 0.6469, "step": 6 }, { "epoch": 0.0068047876541709705, "grad_norm": 4.629936218261719, "learning_rate": 9.761185582727977e-05, "loss": 0.575, "step": 7 }, { "epoch": 0.007776900176195395, "grad_norm": 0.8775707483291626, "learning_rate": 9.657457896300791e-05, "loss": 0.4789, "step": 8 }, { "epoch": 0.00874901269821982, "grad_norm": 1.8272663354873657, "learning_rate": 9.535927336897098e-05, "loss": 0.4889, "step": 9 }, { "epoch": 0.009721125220244244, "grad_norm": 0.6909313797950745, "learning_rate": 9.397114317029975e-05, "loss": 0.4673, "step": 10 }, { "epoch": 0.010693237742268668, "grad_norm": 0.9343708157539368, "learning_rate": 9.241613255361455e-05, "loss": 0.4786, "step": 11 }, { "epoch": 0.011665350264293092, "grad_norm": 0.6804273724555969, "learning_rate": 9.070090031310558e-05, "loss": 0.4795, "step": 12 }, { "epoch": 0.012637462786317517, "grad_norm": 0.5879074335098267, "learning_rate": 8.883279133655399e-05, "loss": 0.4749, "step": 13 }, { "epoch": 0.013609575308341941, "grad_norm": 2.0020663738250732, "learning_rate": 8.681980515339464e-05, "loss": 0.4723, "step": 14 }, { "epoch": 0.014581687830366365, "grad_norm": 1.7705625295639038, "learning_rate": 8.467056167950311e-05, "loss": 0.4716, "step": 15 }, { "epoch": 0.01555380035239079, "grad_norm": 0.6135307550430298, "learning_rate": 8.239426430539243e-05, "loss": 0.4504, "step": 16 }, { "epoch": 0.016525912874415214, "grad_norm": 0.31671127676963806, "learning_rate": 8.000066048588211e-05, "loss": 0.444, "step": 17 }, { "epoch": 0.01749802539643964, "grad_norm": 0.4802543520927429, "learning_rate": 7.75e-05, "loss": 0.469, "step": 18 }, { "epoch": 0.018470137918464063, "grad_norm": 0.4141017496585846, "learning_rate": 7.490299105985507e-05, "loss": 0.4469, "step": 19 }, { "epoch": 0.019442250440488487, "grad_norm": 0.49743837118148804, "learning_rate": 7.222075445642904e-05, "loss": 0.4353, "step": 20 }, { "epoch": 0.02041436296251291, "grad_norm": 0.46260589361190796, "learning_rate": 6.946477593864228e-05, "loss": 0.4429, "step": 21 }, { "epoch": 0.021386475484537336, "grad_norm": 0.49967533349990845, "learning_rate": 6.664685702961344e-05, "loss": 0.4311, "step": 22 }, { "epoch": 0.02235858800656176, "grad_norm": 0.5580289959907532, "learning_rate": 6.377906449072578e-05, "loss": 0.4205, "step": 23 }, { "epoch": 0.023330700528586185, "grad_norm": 0.8080323934555054, "learning_rate": 6.087367864990233e-05, "loss": 0.4136, "step": 24 }, { "epoch": 0.02430281305061061, "grad_norm": 2.149657964706421, "learning_rate": 5.794314081535644e-05, "loss": 0.423, "step": 25 }, { "epoch": 0.02430281305061061, "eval_loss": 0.44637736678123474, "eval_runtime": 3.3862, "eval_samples_per_second": 14.766, "eval_steps_per_second": 3.839, "step": 25 }, { "epoch": 0.025274925572635033, "grad_norm": 2.274613380432129, "learning_rate": 5.500000000000001e-05, "loss": 0.4278, "step": 26 }, { "epoch": 0.026247038094659458, "grad_norm": 2.005136489868164, "learning_rate": 5.205685918464356e-05, "loss": 0.3865, "step": 27 }, { "epoch": 0.027219150616683882, "grad_norm": 1.3703882694244385, "learning_rate": 4.912632135009769e-05, "loss": 0.3564, "step": 28 }, { "epoch": 0.028191263138708306, "grad_norm": 2.662112236022949, "learning_rate": 4.6220935509274235e-05, "loss": 0.4548, "step": 29 }, { "epoch": 0.02916337566073273, "grad_norm": 1.5636816024780273, "learning_rate": 4.3353142970386564e-05, "loss": 0.3732, "step": 30 }, { "epoch": 0.030135488182757155, "grad_norm": 0.8259252309799194, "learning_rate": 4.053522406135775e-05, "loss": 0.3298, "step": 31 }, { "epoch": 0.03110760070478158, "grad_norm": 1.1385399103164673, "learning_rate": 3.777924554357096e-05, "loss": 0.36, "step": 32 }, { "epoch": 0.032079713226806, "grad_norm": 1.2352774143218994, "learning_rate": 3.509700894014496e-05, "loss": 0.3025, "step": 33 }, { "epoch": 0.03305182574883043, "grad_norm": 1.3201019763946533, "learning_rate": 3.250000000000001e-05, "loss": 0.3255, "step": 34 }, { "epoch": 0.03402393827085485, "grad_norm": 2.216609239578247, "learning_rate": 2.9999339514117912e-05, "loss": 0.3294, "step": 35 }, { "epoch": 0.03499605079287928, "grad_norm": 1.7982845306396484, "learning_rate": 2.760573569460757e-05, "loss": 0.2809, "step": 36 }, { "epoch": 0.0359681633149037, "grad_norm": 2.063532829284668, "learning_rate": 2.53294383204969e-05, "loss": 0.3373, "step": 37 }, { "epoch": 0.036940275836928126, "grad_norm": 2.5849380493164062, "learning_rate": 2.3180194846605367e-05, "loss": 0.4325, "step": 38 }, { "epoch": 0.037912388358952546, "grad_norm": 1.5866343975067139, "learning_rate": 2.1167208663446025e-05, "loss": 0.3466, "step": 39 }, { "epoch": 0.038884500880976974, "grad_norm": 1.0172760486602783, "learning_rate": 1.9299099686894423e-05, "loss": 0.2981, "step": 40 }, { "epoch": 0.039856613403001395, "grad_norm": 1.2064744234085083, "learning_rate": 1.758386744638546e-05, "loss": 0.2807, "step": 41 }, { "epoch": 0.04082872592502582, "grad_norm": 1.1969460248947144, "learning_rate": 1.602885682970026e-05, "loss": 0.3194, "step": 42 }, { "epoch": 0.041800838447050244, "grad_norm": 1.2646105289459229, "learning_rate": 1.464072663102903e-05, "loss": 0.2595, "step": 43 }, { "epoch": 0.04277295096907467, "grad_norm": 1.483519434928894, "learning_rate": 1.3425421036992098e-05, "loss": 0.241, "step": 44 }, { "epoch": 0.04374506349109909, "grad_norm": 1.630673885345459, "learning_rate": 1.2388144172720251e-05, "loss": 0.2726, "step": 45 }, { "epoch": 0.04471717601312352, "grad_norm": 1.378562331199646, "learning_rate": 1.1533337816991932e-05, "loss": 0.2539, "step": 46 }, { "epoch": 0.04568928853514794, "grad_norm": 1.6784262657165527, "learning_rate": 1.0864662381854632e-05, "loss": 0.2285, "step": 47 }, { "epoch": 0.04666140105717237, "grad_norm": 1.9682538509368896, "learning_rate": 1.0384981238178534e-05, "loss": 0.2745, "step": 48 }, { "epoch": 0.04763351357919679, "grad_norm": 2.4254722595214844, "learning_rate": 1.0096348454262845e-05, "loss": 0.32, "step": 49 }, { "epoch": 0.04860562610122122, "grad_norm": 2.277864456176758, "learning_rate": 1e-05, "loss": 0.3111, "step": 50 }, { "epoch": 0.04860562610122122, "eval_loss": 0.2565852403640747, "eval_runtime": 3.4031, "eval_samples_per_second": 14.693, "eval_steps_per_second": 3.82, "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": 2, "trial_name": null, "trial_params": null }