{ "best_metric": 8.976583480834961, "best_model_checkpoint": "miner_id_24/checkpoint-50", "epoch": 0.23564064801178203, "eval_steps": 25, "global_step": 50, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.00471281296023564, "grad_norm": 11.932207107543945, "learning_rate": 5e-05, "loss": 11.9289, "step": 1 }, { "epoch": 0.00471281296023564, "eval_loss": 11.466318130493164, "eval_runtime": 0.2733, "eval_samples_per_second": 182.951, "eval_steps_per_second": 47.567, "step": 1 }, { "epoch": 0.00942562592047128, "grad_norm": 11.80747127532959, "learning_rate": 0.0001, "loss": 11.8923, "step": 2 }, { "epoch": 0.014138438880706922, "grad_norm": 11.80627727508545, "learning_rate": 9.990365154573717e-05, "loss": 11.8495, "step": 3 }, { "epoch": 0.01885125184094256, "grad_norm": 10.285013198852539, "learning_rate": 9.961501876182148e-05, "loss": 11.5343, "step": 4 }, { "epoch": 0.023564064801178203, "grad_norm": 9.46924114227295, "learning_rate": 9.913533761814537e-05, "loss": 11.3134, "step": 5 }, { "epoch": 0.028276877761413844, "grad_norm": 9.285470008850098, "learning_rate": 9.846666218300807e-05, "loss": 11.1314, "step": 6 }, { "epoch": 0.032989690721649485, "grad_norm": 9.64939022064209, "learning_rate": 9.761185582727977e-05, "loss": 10.9697, "step": 7 }, { "epoch": 0.03770250368188512, "grad_norm": 9.303040504455566, "learning_rate": 9.657457896300791e-05, "loss": 10.7524, "step": 8 }, { "epoch": 0.04241531664212077, "grad_norm": 9.011505126953125, "learning_rate": 9.535927336897098e-05, "loss": 10.5939, "step": 9 }, { "epoch": 0.047128129602356406, "grad_norm": 8.873916625976562, "learning_rate": 9.397114317029975e-05, "loss": 10.4448, "step": 10 }, { "epoch": 0.05184094256259205, "grad_norm": 8.19795036315918, "learning_rate": 9.241613255361455e-05, "loss": 10.2765, "step": 11 }, { "epoch": 0.05655375552282769, "grad_norm": 7.416764736175537, "learning_rate": 9.070090031310558e-05, "loss": 10.0904, "step": 12 }, { "epoch": 0.061266568483063326, "grad_norm": 6.711239337921143, "learning_rate": 8.883279133655399e-05, "loss": 10.1096, "step": 13 }, { "epoch": 0.06597938144329897, "grad_norm": 6.1158127784729, "learning_rate": 8.681980515339464e-05, "loss": 10.0172, "step": 14 }, { "epoch": 0.07069219440353461, "grad_norm": 5.647707939147949, "learning_rate": 8.467056167950311e-05, "loss": 9.914, "step": 15 }, { "epoch": 0.07540500736377025, "grad_norm": 5.225461483001709, "learning_rate": 8.239426430539243e-05, "loss": 9.8377, "step": 16 }, { "epoch": 0.0801178203240059, "grad_norm": 4.8900227546691895, "learning_rate": 8.000066048588211e-05, "loss": 9.7757, "step": 17 }, { "epoch": 0.08483063328424154, "grad_norm": 4.296078681945801, "learning_rate": 7.75e-05, "loss": 9.682, "step": 18 }, { "epoch": 0.08954344624447717, "grad_norm": 4.111123085021973, "learning_rate": 7.490299105985507e-05, "loss": 9.6565, "step": 19 }, { "epoch": 0.09425625920471281, "grad_norm": 3.808967351913452, "learning_rate": 7.222075445642904e-05, "loss": 9.5633, "step": 20 }, { "epoch": 0.09896907216494845, "grad_norm": 3.6438040733337402, "learning_rate": 6.946477593864228e-05, "loss": 9.4928, "step": 21 }, { "epoch": 0.1036818851251841, "grad_norm": 3.6163392066955566, "learning_rate": 6.664685702961344e-05, "loss": 9.465, "step": 22 }, { "epoch": 0.10839469808541974, "grad_norm": 3.513592481613159, "learning_rate": 6.377906449072578e-05, "loss": 9.3972, "step": 23 }, { "epoch": 0.11310751104565538, "grad_norm": 3.4856817722320557, "learning_rate": 6.087367864990233e-05, "loss": 9.3694, "step": 24 }, { "epoch": 0.11782032400589101, "grad_norm": 4.087053298950195, "learning_rate": 5.794314081535644e-05, "loss": 9.2896, "step": 25 }, { "epoch": 0.11782032400589101, "eval_loss": 9.246109962463379, "eval_runtime": 0.28, "eval_samples_per_second": 178.563, "eval_steps_per_second": 46.426, "step": 25 }, { "epoch": 0.12253313696612665, "grad_norm": 2.965689182281494, "learning_rate": 5.500000000000001e-05, "loss": 9.37, "step": 26 }, { "epoch": 0.1272459499263623, "grad_norm": 2.868656873703003, "learning_rate": 5.205685918464356e-05, "loss": 9.3271, "step": 27 }, { "epoch": 0.13195876288659794, "grad_norm": 2.586918592453003, "learning_rate": 4.912632135009769e-05, "loss": 9.2831, "step": 28 }, { "epoch": 0.13667157584683357, "grad_norm": 2.540886402130127, "learning_rate": 4.6220935509274235e-05, "loss": 9.2554, "step": 29 }, { "epoch": 0.14138438880706922, "grad_norm": 2.4895763397216797, "learning_rate": 4.3353142970386564e-05, "loss": 9.2658, "step": 30 }, { "epoch": 0.14609720176730487, "grad_norm": 2.181830406188965, "learning_rate": 4.053522406135775e-05, "loss": 9.2177, "step": 31 }, { "epoch": 0.1508100147275405, "grad_norm": 2.153486967086792, "learning_rate": 3.777924554357096e-05, "loss": 9.2031, "step": 32 }, { "epoch": 0.15552282768777614, "grad_norm": 2.118992805480957, "learning_rate": 3.509700894014496e-05, "loss": 9.194, "step": 33 }, { "epoch": 0.1602356406480118, "grad_norm": 2.1694352626800537, "learning_rate": 3.250000000000001e-05, "loss": 9.1453, "step": 34 }, { "epoch": 0.16494845360824742, "grad_norm": 2.3047266006469727, "learning_rate": 2.9999339514117912e-05, "loss": 9.12, "step": 35 }, { "epoch": 0.16966126656848307, "grad_norm": 2.5099029541015625, "learning_rate": 2.760573569460757e-05, "loss": 9.1125, "step": 36 }, { "epoch": 0.1743740795287187, "grad_norm": 2.925784111022949, "learning_rate": 2.53294383204969e-05, "loss": 9.078, "step": 37 }, { "epoch": 0.17908689248895435, "grad_norm": 2.911679267883301, "learning_rate": 2.3180194846605367e-05, "loss": 9.1566, "step": 38 }, { "epoch": 0.18379970544919, "grad_norm": 2.5921273231506348, "learning_rate": 2.1167208663446025e-05, "loss": 9.1378, "step": 39 }, { "epoch": 0.18851251840942562, "grad_norm": 2.3401689529418945, "learning_rate": 1.9299099686894423e-05, "loss": 9.1303, "step": 40 }, { "epoch": 0.19322533136966127, "grad_norm": 2.2154057025909424, "learning_rate": 1.758386744638546e-05, "loss": 9.1271, "step": 41 }, { "epoch": 0.1979381443298969, "grad_norm": 2.124439001083374, "learning_rate": 1.602885682970026e-05, "loss": 9.1033, "step": 42 }, { "epoch": 0.20265095729013255, "grad_norm": 1.984527349472046, "learning_rate": 1.464072663102903e-05, "loss": 9.1068, "step": 43 }, { "epoch": 0.2073637702503682, "grad_norm": 1.848252773284912, "learning_rate": 1.3425421036992098e-05, "loss": 9.0778, "step": 44 }, { "epoch": 0.21207658321060383, "grad_norm": 1.807987093925476, "learning_rate": 1.2388144172720251e-05, "loss": 9.0737, "step": 45 }, { "epoch": 0.21678939617083948, "grad_norm": 1.8763501644134521, "learning_rate": 1.1533337816991932e-05, "loss": 9.0675, "step": 46 }, { "epoch": 0.2215022091310751, "grad_norm": 2.026942729949951, "learning_rate": 1.0864662381854632e-05, "loss": 9.0569, "step": 47 }, { "epoch": 0.22621502209131075, "grad_norm": 2.279087543487549, "learning_rate": 1.0384981238178534e-05, "loss": 9.0495, "step": 48 }, { "epoch": 0.2309278350515464, "grad_norm": 2.5268728733062744, "learning_rate": 1.0096348454262845e-05, "loss": 8.9968, "step": 49 }, { "epoch": 0.23564064801178203, "grad_norm": 4.308773517608643, "learning_rate": 1e-05, "loss": 8.9847, "step": 50 }, { "epoch": 0.23564064801178203, "eval_loss": 8.976583480834961, "eval_runtime": 0.2765, "eval_samples_per_second": 180.809, "eval_steps_per_second": 47.01, "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": 232376319344640.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }