| { | |
| "best_metric": 7.119235669961199e-05, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.054408814227904924, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0010881762845580984, | |
| "grad_norm": 8.488767623901367, | |
| "learning_rate": 5e-05, | |
| "loss": 5.2384, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0010881762845580984, | |
| "eval_loss": 0.4561319053173065, | |
| "eval_runtime": 4.1709, | |
| "eval_samples_per_second": 11.988, | |
| "eval_steps_per_second": 3.117, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0021763525691161968, | |
| "grad_norm": 12.473525047302246, | |
| "learning_rate": 0.0001, | |
| "loss": 7.3057, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0032645288536742954, | |
| "grad_norm": 13.172096252441406, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 8.1381, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0043527051382323935, | |
| "grad_norm": 12.740236282348633, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 6.7608, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.005440881422790492, | |
| "grad_norm": 10.972394943237305, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 4.3499, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.006529057707348591, | |
| "grad_norm": 9.73342227935791, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 2.7862, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.007617233991906689, | |
| "grad_norm": 8.87482738494873, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 1.4533, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.008705410276464787, | |
| "grad_norm": 7.187124729156494, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 0.5967, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.009793586561022886, | |
| "grad_norm": 3.336824655532837, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 0.1768, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.010881762845580983, | |
| "grad_norm": 1.0351998805999756, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 0.0488, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.011969939130139082, | |
| "grad_norm": 1.6404157876968384, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 0.0692, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.013058115414697181, | |
| "grad_norm": 1.8609697818756104, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 0.07, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.014146291699255279, | |
| "grad_norm": 5.1143269538879395, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 0.2308, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.015234467983813378, | |
| "grad_norm": 2.8937344551086426, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 0.0796, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.016322644268371475, | |
| "grad_norm": 0.8888844847679138, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 0.0157, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.017410820552929574, | |
| "grad_norm": 1.7481740713119507, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 0.0342, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.018498996837487673, | |
| "grad_norm": 2.1718719005584717, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 0.0169, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.019587173122045772, | |
| "grad_norm": 0.21131518483161926, | |
| "learning_rate": 7.75e-05, | |
| "loss": 0.005, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.02067534940660387, | |
| "grad_norm": 0.1480499505996704, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 0.0027, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.021763525691161967, | |
| "grad_norm": 0.09550140798091888, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 0.0029, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.022851701975720066, | |
| "grad_norm": 0.039920106530189514, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 0.0013, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.023939878260278165, | |
| "grad_norm": 0.11236383020877838, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 0.0016, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.025028054544836264, | |
| "grad_norm": 0.13724114000797272, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 0.0021, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.026116230829394363, | |
| "grad_norm": 0.007396350614726543, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 0.0007, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.027204407113952462, | |
| "grad_norm": 0.028984805569052696, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 0.0011, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.027204407113952462, | |
| "eval_loss": 0.0008776781032793224, | |
| "eval_runtime": 4.1329, | |
| "eval_samples_per_second": 12.098, | |
| "eval_steps_per_second": 3.145, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.028292583398510558, | |
| "grad_norm": 0.6503666639328003, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 0.0142, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.029380759683068657, | |
| "grad_norm": 1.4432364702224731, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 0.0236, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.030468935967626756, | |
| "grad_norm": 1.0091779232025146, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 0.0089, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.031557112252184855, | |
| "grad_norm": 0.029920252040028572, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 0.0008, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.03264528853674295, | |
| "grad_norm": 0.5346688032150269, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 0.002, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.03373346482130105, | |
| "grad_norm": 0.006169620435684919, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 0.0005, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.03482164110585915, | |
| "grad_norm": 0.07874411344528198, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 0.0013, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.03590981739041725, | |
| "grad_norm": 0.3163844645023346, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 0.0019, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.036997993674975346, | |
| "grad_norm": 0.006217717658728361, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 0.0005, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.03808616995953344, | |
| "grad_norm": 0.8465691804885864, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 0.0049, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.039174346244091544, | |
| "grad_norm": 0.16441190242767334, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 0.0012, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.04026252252864964, | |
| "grad_norm": 0.03539092838764191, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 0.0006, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.04135069881320774, | |
| "grad_norm": 0.31494778394699097, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 0.0045, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.04243887509776584, | |
| "grad_norm": 0.08970910310745239, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 0.0013, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.043527051382323934, | |
| "grad_norm": 0.34870007634162903, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 0.0026, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.044615227666882036, | |
| "grad_norm": 0.6943385004997253, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 0.006, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.04570340395144013, | |
| "grad_norm": 0.005790391471236944, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 0.0004, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.046791580235998234, | |
| "grad_norm": 0.23590277135372162, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 0.0019, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.04787975652055633, | |
| "grad_norm": 0.06693784892559052, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 0.0009, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.048967932805114425, | |
| "grad_norm": 0.007141406647861004, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 0.0004, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.05005610908967253, | |
| "grad_norm": 0.2533439099788666, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 0.0018, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.05114428537423062, | |
| "grad_norm": 0.02547360584139824, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 0.0005, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.052232461658788726, | |
| "grad_norm": 0.0453345812857151, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 0.0004, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.05332063794334682, | |
| "grad_norm": 2.0085508823394775, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 0.0051, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.054408814227904924, | |
| "grad_norm": 0.009647084400057793, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0004, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.054408814227904924, | |
| "eval_loss": 7.119235669961199e-05, | |
| "eval_runtime": 4.1934, | |
| "eval_samples_per_second": 11.924, | |
| "eval_steps_per_second": 3.1, | |
| "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": 5.259926510449459e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |