{ "best_metric": 0.9367274641990662, "best_model_checkpoint": "miner_id_24/checkpoint-50", "epoch": 0.45351473922902497, "eval_steps": 25, "global_step": 50, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.009070294784580499, "grad_norm": 23.725589752197266, "learning_rate": 5e-05, "loss": 65.7301, "step": 1 }, { "epoch": 0.009070294784580499, "eval_loss": 2.014394521713257, "eval_runtime": 3.0847, "eval_samples_per_second": 16.209, "eval_steps_per_second": 4.214, "step": 1 }, { "epoch": 0.018140589569160998, "grad_norm": 23.24586296081543, "learning_rate": 0.0001, "loss": 62.5048, "step": 2 }, { "epoch": 0.027210884353741496, "grad_norm": 21.9019775390625, "learning_rate": 9.990365154573717e-05, "loss": 63.3692, "step": 3 }, { "epoch": 0.036281179138321996, "grad_norm": 25.747800827026367, "learning_rate": 9.961501876182148e-05, "loss": 57.2083, "step": 4 }, { "epoch": 0.045351473922902494, "grad_norm": 25.553625106811523, "learning_rate": 9.913533761814537e-05, "loss": 51.1463, "step": 5 }, { "epoch": 0.05442176870748299, "grad_norm": 26.685422897338867, "learning_rate": 9.846666218300807e-05, "loss": 42.539, "step": 6 }, { "epoch": 0.06349206349206349, "grad_norm": 26.46235466003418, "learning_rate": 9.761185582727977e-05, "loss": 39.438, "step": 7 }, { "epoch": 0.07256235827664399, "grad_norm": 26.154319763183594, "learning_rate": 9.657457896300791e-05, "loss": 34.0311, "step": 8 }, { "epoch": 0.08163265306122448, "grad_norm": 32.253196716308594, "learning_rate": 9.535927336897098e-05, "loss": 35.102, "step": 9 }, { "epoch": 0.09070294784580499, "grad_norm": 35.70768356323242, "learning_rate": 9.397114317029975e-05, "loss": 32.8223, "step": 10 }, { "epoch": 0.09977324263038549, "grad_norm": 29.746322631835938, "learning_rate": 9.241613255361455e-05, "loss": 31.2532, "step": 11 }, { "epoch": 0.10884353741496598, "grad_norm": 45.55724334716797, "learning_rate": 9.070090031310558e-05, "loss": 29.104, "step": 12 }, { "epoch": 0.11791383219954649, "grad_norm": 50.86054992675781, "learning_rate": 8.883279133655399e-05, "loss": 38.5253, "step": 13 }, { "epoch": 0.12698412698412698, "grad_norm": 58.23904800415039, "learning_rate": 8.681980515339464e-05, "loss": 41.008, "step": 14 }, { "epoch": 0.1360544217687075, "grad_norm": 38.54997634887695, "learning_rate": 8.467056167950311e-05, "loss": 39.6464, "step": 15 }, { "epoch": 0.14512471655328799, "grad_norm": 26.06702423095703, "learning_rate": 8.239426430539243e-05, "loss": 37.4845, "step": 16 }, { "epoch": 0.15419501133786848, "grad_norm": 19.131418228149414, "learning_rate": 8.000066048588211e-05, "loss": 34.5248, "step": 17 }, { "epoch": 0.16326530612244897, "grad_norm": 22.719026565551758, "learning_rate": 7.75e-05, "loss": 34.576, "step": 18 }, { "epoch": 0.17233560090702948, "grad_norm": 19.789934158325195, "learning_rate": 7.490299105985507e-05, "loss": 30.3506, "step": 19 }, { "epoch": 0.18140589569160998, "grad_norm": 17.266712188720703, "learning_rate": 7.222075445642904e-05, "loss": 30.6046, "step": 20 }, { "epoch": 0.19047619047619047, "grad_norm": 16.514543533325195, "learning_rate": 6.946477593864228e-05, "loss": 29.2396, "step": 21 }, { "epoch": 0.19954648526077098, "grad_norm": 15.277443885803223, "learning_rate": 6.664685702961344e-05, "loss": 28.9811, "step": 22 }, { "epoch": 0.20861678004535147, "grad_norm": 17.505090713500977, "learning_rate": 6.377906449072578e-05, "loss": 30.5061, "step": 23 }, { "epoch": 0.21768707482993196, "grad_norm": 16.256650924682617, "learning_rate": 6.087367864990233e-05, "loss": 27.0452, "step": 24 }, { "epoch": 0.22675736961451248, "grad_norm": 18.64777183532715, "learning_rate": 5.794314081535644e-05, "loss": 23.541, "step": 25 }, { "epoch": 0.22675736961451248, "eval_loss": 0.9916588664054871, "eval_runtime": 3.131, "eval_samples_per_second": 15.969, "eval_steps_per_second": 4.152, "step": 25 }, { "epoch": 0.23582766439909297, "grad_norm": 34.72603988647461, "learning_rate": 5.500000000000001e-05, "loss": 41.4229, "step": 26 }, { "epoch": 0.24489795918367346, "grad_norm": 29.00994873046875, "learning_rate": 5.205685918464356e-05, "loss": 37.8385, "step": 27 }, { "epoch": 0.25396825396825395, "grad_norm": 29.791704177856445, "learning_rate": 4.912632135009769e-05, "loss": 37.1688, "step": 28 }, { "epoch": 0.26303854875283444, "grad_norm": 21.486818313598633, "learning_rate": 4.6220935509274235e-05, "loss": 33.5763, "step": 29 }, { "epoch": 0.272108843537415, "grad_norm": 17.391510009765625, "learning_rate": 4.3353142970386564e-05, "loss": 31.8093, "step": 30 }, { "epoch": 0.2811791383219955, "grad_norm": 14.429960250854492, "learning_rate": 4.053522406135775e-05, "loss": 29.819, "step": 31 }, { "epoch": 0.29024943310657597, "grad_norm": 13.572725296020508, "learning_rate": 3.777924554357096e-05, "loss": 29.4895, "step": 32 }, { "epoch": 0.29931972789115646, "grad_norm": 16.76784896850586, "learning_rate": 3.509700894014496e-05, "loss": 29.3145, "step": 33 }, { "epoch": 0.30839002267573695, "grad_norm": 18.062070846557617, "learning_rate": 3.250000000000001e-05, "loss": 26.8548, "step": 34 }, { "epoch": 0.31746031746031744, "grad_norm": 20.56993293762207, "learning_rate": 2.9999339514117912e-05, "loss": 27.9149, "step": 35 }, { "epoch": 0.32653061224489793, "grad_norm": 23.277589797973633, "learning_rate": 2.760573569460757e-05, "loss": 28.7237, "step": 36 }, { "epoch": 0.3356009070294785, "grad_norm": 22.635587692260742, "learning_rate": 2.53294383204969e-05, "loss": 22.4117, "step": 37 }, { "epoch": 0.34467120181405897, "grad_norm": 18.91414451599121, "learning_rate": 2.3180194846605367e-05, "loss": 32.7469, "step": 38 }, { "epoch": 0.35374149659863946, "grad_norm": 13.754558563232422, "learning_rate": 2.1167208663446025e-05, "loss": 35.7876, "step": 39 }, { "epoch": 0.36281179138321995, "grad_norm": 15.152359962463379, "learning_rate": 1.9299099686894423e-05, "loss": 34.6626, "step": 40 }, { "epoch": 0.37188208616780044, "grad_norm": 13.985898971557617, "learning_rate": 1.758386744638546e-05, "loss": 32.2783, "step": 41 }, { "epoch": 0.38095238095238093, "grad_norm": 13.5012845993042, "learning_rate": 1.602885682970026e-05, "loss": 32.2167, "step": 42 }, { "epoch": 0.3900226757369615, "grad_norm": 13.727423667907715, "learning_rate": 1.464072663102903e-05, "loss": 31.4028, "step": 43 }, { "epoch": 0.39909297052154197, "grad_norm": 13.151164054870605, "learning_rate": 1.3425421036992098e-05, "loss": 28.9454, "step": 44 }, { "epoch": 0.40816326530612246, "grad_norm": 12.17611026763916, "learning_rate": 1.2388144172720251e-05, "loss": 28.3156, "step": 45 }, { "epoch": 0.41723356009070295, "grad_norm": 13.333844184875488, "learning_rate": 1.1533337816991932e-05, "loss": 26.8998, "step": 46 }, { "epoch": 0.42630385487528344, "grad_norm": 13.045530319213867, "learning_rate": 1.0864662381854632e-05, "loss": 27.8567, "step": 47 }, { "epoch": 0.43537414965986393, "grad_norm": 14.13997745513916, "learning_rate": 1.0384981238178534e-05, "loss": 27.0215, "step": 48 }, { "epoch": 0.4444444444444444, "grad_norm": 15.954257011413574, "learning_rate": 1.0096348454262845e-05, "loss": 24.4307, "step": 49 }, { "epoch": 0.45351473922902497, "grad_norm": 22.00568389892578, "learning_rate": 1e-05, "loss": 22.3285, "step": 50 }, { "epoch": 0.45351473922902497, "eval_loss": 0.9367274641990662, "eval_runtime": 3.102, "eval_samples_per_second": 16.119, "eval_steps_per_second": 4.191, "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": 5.262429617389568e+17, "train_batch_size": 1, "trial_name": null, "trial_params": null }