{ "best_metric": 1.1396163702011108, "best_model_checkpoint": "miner_id_24/checkpoint-50", "epoch": 0.15273004963726614, "eval_steps": 25, "global_step": 50, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0030546009927453228, "grad_norm": 411.8155212402344, "learning_rate": 5e-05, "loss": 72.0418, "step": 1 }, { "epoch": 0.0030546009927453228, "eval_loss": 5.549919128417969, "eval_runtime": 56.6085, "eval_samples_per_second": 38.969, "eval_steps_per_second": 4.876, "step": 1 }, { "epoch": 0.0061092019854906456, "grad_norm": 517.7806396484375, "learning_rate": 0.0001, "loss": 77.2635, "step": 2 }, { "epoch": 0.009163802978235968, "grad_norm": 375.3448181152344, "learning_rate": 9.989294616193017e-05, "loss": 51.8792, "step": 3 }, { "epoch": 0.012218403970981291, "grad_norm": 1181.99462890625, "learning_rate": 9.957224306869053e-05, "loss": 76.3616, "step": 4 }, { "epoch": 0.015273004963726614, "grad_norm": 512.3447875976562, "learning_rate": 9.903926402016153e-05, "loss": 40.4179, "step": 5 }, { "epoch": 0.018327605956471937, "grad_norm": 190.83563232421875, "learning_rate": 9.829629131445342e-05, "loss": 34.7413, "step": 6 }, { "epoch": 0.021382206949217258, "grad_norm": 295.7945861816406, "learning_rate": 9.73465064747553e-05, "loss": 32.2792, "step": 7 }, { "epoch": 0.024436807941962582, "grad_norm": 154.5236053466797, "learning_rate": 9.619397662556435e-05, "loss": 28.1299, "step": 8 }, { "epoch": 0.027491408934707903, "grad_norm": 179.23910522460938, "learning_rate": 9.484363707663442e-05, "loss": 27.647, "step": 9 }, { "epoch": 0.030546009927453228, "grad_norm": 154.86285400390625, "learning_rate": 9.330127018922194e-05, "loss": 29.4737, "step": 10 }, { "epoch": 0.03360061092019855, "grad_norm": 205.29489135742188, "learning_rate": 9.157348061512727e-05, "loss": 31.0466, "step": 11 }, { "epoch": 0.03665521191294387, "grad_norm": 173.7435760498047, "learning_rate": 8.966766701456177e-05, "loss": 32.8035, "step": 12 }, { "epoch": 0.039709812905689194, "grad_norm": 177.4287567138672, "learning_rate": 8.759199037394887e-05, "loss": 35.287, "step": 13 }, { "epoch": 0.042764413898434515, "grad_norm": 132.8975372314453, "learning_rate": 8.535533905932738e-05, "loss": 28.0127, "step": 14 }, { "epoch": 0.045819014891179836, "grad_norm": 100.02606201171875, "learning_rate": 8.296729075500344e-05, "loss": 24.2048, "step": 15 }, { "epoch": 0.048873615883925164, "grad_norm": 144.72496032714844, "learning_rate": 8.043807145043604e-05, "loss": 24.6628, "step": 16 }, { "epoch": 0.051928216876670485, "grad_norm": 99.14219665527344, "learning_rate": 7.777851165098012e-05, "loss": 22.3685, "step": 17 }, { "epoch": 0.054982817869415807, "grad_norm": 91.8460922241211, "learning_rate": 7.500000000000001e-05, "loss": 20.5469, "step": 18 }, { "epoch": 0.05803741886216113, "grad_norm": 91.75062561035156, "learning_rate": 7.211443451095007e-05, "loss": 20.878, "step": 19 }, { "epoch": 0.061092019854906456, "grad_norm": 87.56897735595703, "learning_rate": 6.91341716182545e-05, "loss": 20.1802, "step": 20 }, { "epoch": 0.06414662084765177, "grad_norm": 111.00213623046875, "learning_rate": 6.607197326515808e-05, "loss": 23.1227, "step": 21 }, { "epoch": 0.0672012218403971, "grad_norm": 112.78516387939453, "learning_rate": 6.294095225512603e-05, "loss": 23.5927, "step": 22 }, { "epoch": 0.07025582283314243, "grad_norm": 120.71290588378906, "learning_rate": 5.9754516100806423e-05, "loss": 24.7728, "step": 23 }, { "epoch": 0.07331042382588775, "grad_norm": 110.4635009765625, "learning_rate": 5.6526309611002594e-05, "loss": 23.4427, "step": 24 }, { "epoch": 0.07636502481863307, "grad_norm": 152.16371154785156, "learning_rate": 5.327015646150716e-05, "loss": 30.3582, "step": 25 }, { "epoch": 0.07636502481863307, "eval_loss": 1.358454704284668, "eval_runtime": 56.6567, "eval_samples_per_second": 38.936, "eval_steps_per_second": 4.871, "step": 25 }, { "epoch": 0.07941962581137839, "grad_norm": 102.45426177978516, "learning_rate": 5e-05, "loss": 22.9259, "step": 26 }, { "epoch": 0.08247422680412371, "grad_norm": 90.15953826904297, "learning_rate": 4.6729843538492847e-05, "loss": 21.9522, "step": 27 }, { "epoch": 0.08552882779686903, "grad_norm": 92.5013427734375, "learning_rate": 4.347369038899744e-05, "loss": 22.2064, "step": 28 }, { "epoch": 0.08858342878961435, "grad_norm": 72.16334533691406, "learning_rate": 4.0245483899193595e-05, "loss": 18.7869, "step": 29 }, { "epoch": 0.09163802978235967, "grad_norm": 81.92129516601562, "learning_rate": 3.705904774487396e-05, "loss": 15.8735, "step": 30 }, { "epoch": 0.09469263077510501, "grad_norm": 101.18927764892578, "learning_rate": 3.392802673484193e-05, "loss": 19.6555, "step": 31 }, { "epoch": 0.09774723176785033, "grad_norm": 81.10553741455078, "learning_rate": 3.086582838174551e-05, "loss": 19.2793, "step": 32 }, { "epoch": 0.10080183276059565, "grad_norm": 72.74671936035156, "learning_rate": 2.7885565489049946e-05, "loss": 18.6, "step": 33 }, { "epoch": 0.10385643375334097, "grad_norm": 86.57416534423828, "learning_rate": 2.500000000000001e-05, "loss": 18.3163, "step": 34 }, { "epoch": 0.10691103474608629, "grad_norm": 91.92635345458984, "learning_rate": 2.2221488349019903e-05, "loss": 19.9557, "step": 35 }, { "epoch": 0.10996563573883161, "grad_norm": 120.62100982666016, "learning_rate": 1.9561928549563968e-05, "loss": 20.4593, "step": 36 }, { "epoch": 0.11302023673157693, "grad_norm": 102.29236602783203, "learning_rate": 1.703270924499656e-05, "loss": 21.8171, "step": 37 }, { "epoch": 0.11607483772432226, "grad_norm": 94.89315032958984, "learning_rate": 1.4644660940672627e-05, "loss": 23.6319, "step": 38 }, { "epoch": 0.11912943871706758, "grad_norm": 80.66189575195312, "learning_rate": 1.2408009626051137e-05, "loss": 18.8452, "step": 39 }, { "epoch": 0.12218403970981291, "grad_norm": 89.5391616821289, "learning_rate": 1.0332332985438248e-05, "loss": 20.5874, "step": 40 }, { "epoch": 0.12523864070255822, "grad_norm": 81.86558532714844, "learning_rate": 8.426519384872733e-06, "loss": 20.799, "step": 41 }, { "epoch": 0.12829324169530354, "grad_norm": 89.75981140136719, "learning_rate": 6.698729810778065e-06, "loss": 19.7842, "step": 42 }, { "epoch": 0.13134784268804886, "grad_norm": 89.26224517822266, "learning_rate": 5.156362923365588e-06, "loss": 17.2257, "step": 43 }, { "epoch": 0.1344024436807942, "grad_norm": 84.56063842773438, "learning_rate": 3.8060233744356633e-06, "loss": 17.7931, "step": 44 }, { "epoch": 0.13745704467353953, "grad_norm": 77.53307342529297, "learning_rate": 2.653493525244721e-06, "loss": 19.046, "step": 45 }, { "epoch": 0.14051164566628485, "grad_norm": 71.67435455322266, "learning_rate": 1.70370868554659e-06, "loss": 16.1301, "step": 46 }, { "epoch": 0.14356624665903017, "grad_norm": 72.81458282470703, "learning_rate": 9.607359798384785e-07, "loss": 17.1189, "step": 47 }, { "epoch": 0.1466208476517755, "grad_norm": 105.62673950195312, "learning_rate": 4.277569313094809e-07, "loss": 17.1779, "step": 48 }, { "epoch": 0.14967544864452081, "grad_norm": 95.08515167236328, "learning_rate": 1.0705383806982606e-07, "loss": 20.9969, "step": 49 }, { "epoch": 0.15273004963726614, "grad_norm": 113.62215423583984, "learning_rate": 0.0, "loss": 27.1015, "step": 50 }, { "epoch": 0.15273004963726614, "eval_loss": 1.1396163702011108, "eval_runtime": 56.656, "eval_samples_per_second": 38.937, "eval_steps_per_second": 4.872, "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": 5.658124417499136e+17, "train_batch_size": 2, "trial_name": null, "trial_params": null }