| { | |
| "best_metric": 4.46038818359375, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.03422899195618689, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0006845798391237378, | |
| "grad_norm": 1.8983988761901855, | |
| "learning_rate": 5e-05, | |
| "loss": 5.5369, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0006845798391237378, | |
| "eval_loss": 5.087055683135986, | |
| "eval_runtime": 1.8291, | |
| "eval_samples_per_second": 27.336, | |
| "eval_steps_per_second": 7.107, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0013691596782474755, | |
| "grad_norm": 1.7235485315322876, | |
| "learning_rate": 0.0001, | |
| "loss": 5.2483, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0020537395173712133, | |
| "grad_norm": 1.5233309268951416, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 5.085, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.002738319356494951, | |
| "grad_norm": 1.1321425437927246, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 4.9184, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.003422899195618689, | |
| "grad_norm": 2.263650417327881, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 4.8358, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.004107479034742427, | |
| "grad_norm": 0.9546835422515869, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 4.8692, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.004792058873866164, | |
| "grad_norm": 0.7501165270805359, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 4.9064, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.005476638712989902, | |
| "grad_norm": 0.5767120122909546, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 4.8118, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00616121855211364, | |
| "grad_norm": 0.6856655478477478, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 4.8149, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.006845798391237378, | |
| "grad_norm": 0.7905865907669067, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 4.8121, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0075303782303611155, | |
| "grad_norm": 1.2904866933822632, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 4.8751, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.008214958069484853, | |
| "grad_norm": 0.7690590620040894, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 4.8562, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.008899537908608592, | |
| "grad_norm": 1.3141318559646606, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 5.1032, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.009584117747732329, | |
| "grad_norm": 1.111348271369934, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 5.0121, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.010268697586856067, | |
| "grad_norm": 0.9109743237495422, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 4.7557, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.010953277425979804, | |
| "grad_norm": 0.5635835528373718, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 4.6933, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.011637857265103543, | |
| "grad_norm": 1.2304234504699707, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 4.5971, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.01232243710422728, | |
| "grad_norm": 1.4028397798538208, | |
| "learning_rate": 7.75e-05, | |
| "loss": 4.6146, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.013007016943351019, | |
| "grad_norm": 1.7947639226913452, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 4.611, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.013691596782474755, | |
| "grad_norm": 1.5065919160842896, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 4.622, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.014376176621598494, | |
| "grad_norm": 0.48089975118637085, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 4.6141, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.015060756460722231, | |
| "grad_norm": 0.5148659348487854, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 4.6095, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.01574533629984597, | |
| "grad_norm": 0.6612058281898499, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 4.5889, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.016429916138969707, | |
| "grad_norm": 0.5617333650588989, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 4.6246, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.017114495978093443, | |
| "grad_norm": 0.5102720260620117, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 4.6922, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.017114495978093443, | |
| "eval_loss": 4.555571556091309, | |
| "eval_runtime": 0.3228, | |
| "eval_samples_per_second": 154.902, | |
| "eval_steps_per_second": 40.274, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.017799075817217184, | |
| "grad_norm": 0.652305006980896, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 4.8983, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.01848365565634092, | |
| "grad_norm": 0.7992231249809265, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 4.7073, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.019168235495464658, | |
| "grad_norm": 0.38415586948394775, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 4.5686, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.019852815334588398, | |
| "grad_norm": 0.38379648327827454, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 4.4937, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.020537395173712135, | |
| "grad_norm": 0.38786450028419495, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 4.4419, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.021221975012835872, | |
| "grad_norm": 0.49159541726112366, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 4.5172, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.02190655485195961, | |
| "grad_norm": 0.5576838254928589, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 4.5385, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.02259113469108335, | |
| "grad_norm": 0.3310554623603821, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 4.5236, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.023275714530207086, | |
| "grad_norm": 0.3554631769657135, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 4.5445, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.023960294369330823, | |
| "grad_norm": 0.3332033157348633, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 4.4697, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.02464487420845456, | |
| "grad_norm": 0.4032423198223114, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 4.4963, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.0253294540475783, | |
| "grad_norm": 0.48033788800239563, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 4.5964, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.026014033886702037, | |
| "grad_norm": 0.6050848364830017, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 4.9098, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.026698613725825774, | |
| "grad_norm": 0.5689930319786072, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 4.7628, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.02738319356494951, | |
| "grad_norm": 0.35218316316604614, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 4.544, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.02806777340407325, | |
| "grad_norm": 0.2895558774471283, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 4.4886, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.028752353243196988, | |
| "grad_norm": 0.3760088384151459, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 4.4021, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.029436933082320725, | |
| "grad_norm": 0.2829365134239197, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 4.4461, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.030121512921444462, | |
| "grad_norm": 0.3910805583000183, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 4.4129, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.030806092760568202, | |
| "grad_norm": 0.3998270034790039, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 4.4577, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.03149067259969194, | |
| "grad_norm": 0.3465791344642639, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 4.4583, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.03217525243881568, | |
| "grad_norm": 0.31564465165138245, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 4.4946, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.03285983227793941, | |
| "grad_norm": 0.37373700737953186, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 4.4635, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.03354441211706315, | |
| "grad_norm": 0.39719510078430176, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 4.5366, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.03422899195618689, | |
| "grad_norm": 0.44478699564933777, | |
| "learning_rate": 1e-05, | |
| "loss": 4.6088, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.03422899195618689, | |
| "eval_loss": 4.46038818359375, | |
| "eval_runtime": 0.3251, | |
| "eval_samples_per_second": 153.796, | |
| "eval_steps_per_second": 39.987, | |
| "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": 1.194596482678784e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |