| { | |
| "best_metric": 0.08122972398996353, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-75", | |
| "epoch": 0.05336535254486025, | |
| "eval_steps": 25, | |
| "global_step": 75, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00071153803393147, | |
| "grad_norm": 4.1395392417907715, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 3.1572, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00071153803393147, | |
| "eval_loss": 4.378438949584961, | |
| "eval_runtime": 3.4572, | |
| "eval_samples_per_second": 14.463, | |
| "eval_steps_per_second": 3.76, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00142307606786294, | |
| "grad_norm": 4.174035549163818, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 3.5344, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00213461410179441, | |
| "grad_norm": 4.1275458335876465, | |
| "learning_rate": 0.0001, | |
| "loss": 3.6334, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00284615213572588, | |
| "grad_norm": 3.8864400386810303, | |
| "learning_rate": 9.99571699711836e-05, | |
| "loss": 3.1984, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00355769016965735, | |
| "grad_norm": 5.862198829650879, | |
| "learning_rate": 9.982876141412856e-05, | |
| "loss": 2.5223, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00426922820358882, | |
| "grad_norm": 4.417128562927246, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 1.8482, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00498076623752029, | |
| "grad_norm": 3.6660585403442383, | |
| "learning_rate": 9.931634888554937e-05, | |
| "loss": 1.3222, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.00569230427145176, | |
| "grad_norm": 2.8245842456817627, | |
| "learning_rate": 9.893332032039701e-05, | |
| "loss": 0.9788, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00640384230538323, | |
| "grad_norm": 2.523778200149536, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 0.7001, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0071153803393147, | |
| "grad_norm": 2.617717742919922, | |
| "learning_rate": 9.791726278367022e-05, | |
| "loss": 0.5022, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00782691837324617, | |
| "grad_norm": 2.721231698989868, | |
| "learning_rate": 9.728616793536588e-05, | |
| "loss": 0.4812, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.00853845640717764, | |
| "grad_norm": 2.917170524597168, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 0.407, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.00924999444110911, | |
| "grad_norm": 4.139233112335205, | |
| "learning_rate": 9.578385041664925e-05, | |
| "loss": 0.965, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.00996153247504058, | |
| "grad_norm": 3.3612873554229736, | |
| "learning_rate": 9.491548749301997e-05, | |
| "loss": 0.7595, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.01067307050897205, | |
| "grad_norm": 3.3063018321990967, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 0.5902, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.01138460854290352, | |
| "grad_norm": 3.0980429649353027, | |
| "learning_rate": 9.295261506157986e-05, | |
| "loss": 0.4998, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.01209614657683499, | |
| "grad_norm": 1.7593947649002075, | |
| "learning_rate": 9.186184199300464e-05, | |
| "loss": 0.3775, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.01280768461076646, | |
| "grad_norm": 0.964061439037323, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 0.3036, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.01351922264469793, | |
| "grad_norm": 1.0408120155334473, | |
| "learning_rate": 8.947199994035401e-05, | |
| "loss": 0.2508, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0142307606786294, | |
| "grad_norm": 0.7718386650085449, | |
| "learning_rate": 8.817748015645558e-05, | |
| "loss": 0.1979, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.01494229871256087, | |
| "grad_norm": 1.073320746421814, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 0.1971, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.01565383674649234, | |
| "grad_norm": 0.6882893443107605, | |
| "learning_rate": 8.540155934270471e-05, | |
| "loss": 0.1843, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.01636537478042381, | |
| "grad_norm": 0.8627312183380127, | |
| "learning_rate": 8.392544243589427e-05, | |
| "loss": 0.1888, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.01707691281435528, | |
| "grad_norm": 0.8838256597518921, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 0.1508, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.01778845084828675, | |
| "grad_norm": 1.3713014125823975, | |
| "learning_rate": 8.081093963579707e-05, | |
| "loss": 0.1561, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.01778845084828675, | |
| "eval_loss": 0.30335336923599243, | |
| "eval_runtime": 3.496, | |
| "eval_samples_per_second": 14.302, | |
| "eval_steps_per_second": 3.719, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.01849998888221822, | |
| "grad_norm": 2.975804090499878, | |
| "learning_rate": 7.917848237560709e-05, | |
| "loss": 0.5658, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.01921152691614969, | |
| "grad_norm": 2.311894416809082, | |
| "learning_rate": 7.75e-05, | |
| "loss": 0.429, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.01992306495008116, | |
| "grad_norm": 1.3672640323638916, | |
| "learning_rate": 7.577868759557654e-05, | |
| "loss": 0.2389, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.02063460298401263, | |
| "grad_norm": 0.7648161053657532, | |
| "learning_rate": 7.401782177833148e-05, | |
| "loss": 0.2071, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.0213461410179441, | |
| "grad_norm": 1.1158180236816406, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 0.1953, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.02205767905187557, | |
| "grad_norm": 1.5425399541854858, | |
| "learning_rate": 7.03909064496551e-05, | |
| "loss": 0.1899, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.02276921708580704, | |
| "grad_norm": 1.3230940103530884, | |
| "learning_rate": 6.853176097769229e-05, | |
| "loss": 0.131, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.02348075511973851, | |
| "grad_norm": 0.7612606287002563, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 0.112, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.02419229315366998, | |
| "grad_norm": 0.4409436285495758, | |
| "learning_rate": 6.473978262721463e-05, | |
| "loss": 0.107, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.02490383118760145, | |
| "grad_norm": 0.4337151050567627, | |
| "learning_rate": 6.281416799501188e-05, | |
| "loss": 0.088, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.02561536922153292, | |
| "grad_norm": 0.5711820125579834, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 0.1323, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.02632690725546439, | |
| "grad_norm": 0.6534641981124878, | |
| "learning_rate": 5.8922008423644624e-05, | |
| "loss": 0.1032, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.02703844528939586, | |
| "grad_norm": 1.1616266965866089, | |
| "learning_rate": 5.696287243144013e-05, | |
| "loss": 0.3308, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.02774998332332733, | |
| "grad_norm": 1.08228600025177, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 0.2675, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.0284615213572588, | |
| "grad_norm": 0.8149510025978088, | |
| "learning_rate": 5.303712756855988e-05, | |
| "loss": 0.177, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.02917305939119027, | |
| "grad_norm": 0.7890299558639526, | |
| "learning_rate": 5.107799157635538e-05, | |
| "loss": 0.1581, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.02988459742512174, | |
| "grad_norm": 0.46428173780441284, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 0.1306, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.03059613545905321, | |
| "grad_norm": 0.4688973128795624, | |
| "learning_rate": 4.718583200498814e-05, | |
| "loss": 0.0909, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.03130767349298468, | |
| "grad_norm": 0.5706167817115784, | |
| "learning_rate": 4.526021737278538e-05, | |
| "loss": 0.0766, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.03201921152691615, | |
| "grad_norm": 0.7713613510131836, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 0.093, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.03273074956084762, | |
| "grad_norm": 0.7292242646217346, | |
| "learning_rate": 4.146823902230772e-05, | |
| "loss": 0.0818, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.03344228759477909, | |
| "grad_norm": 0.745477557182312, | |
| "learning_rate": 3.960909355034491e-05, | |
| "loss": 0.0861, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.03415382562871056, | |
| "grad_norm": 0.8162257671356201, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 0.1041, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.03486536366264203, | |
| "grad_norm": 0.8203452229499817, | |
| "learning_rate": 3.598217822166854e-05, | |
| "loss": 0.0862, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.0355769016965735, | |
| "grad_norm": 0.8991295695304871, | |
| "learning_rate": 3.422131240442349e-05, | |
| "loss": 0.0849, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0355769016965735, | |
| "eval_loss": 0.12278789281845093, | |
| "eval_runtime": 3.5088, | |
| "eval_samples_per_second": 14.25, | |
| "eval_steps_per_second": 3.705, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.03628843973050497, | |
| "grad_norm": 1.0250176191329956, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 0.2113, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.03699997776443644, | |
| "grad_norm": 0.8808900713920593, | |
| "learning_rate": 3.082151762439293e-05, | |
| "loss": 0.1611, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.03771151579836791, | |
| "grad_norm": 0.8555270433425903, | |
| "learning_rate": 2.9189060364202943e-05, | |
| "loss": 0.127, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.03842305383229938, | |
| "grad_norm": 0.9593107104301453, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 0.1143, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.03913459186623085, | |
| "grad_norm": 0.8327104449272156, | |
| "learning_rate": 2.6074557564105727e-05, | |
| "loss": 0.0989, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.03984612990016232, | |
| "grad_norm": 0.6464086174964905, | |
| "learning_rate": 2.459844065729529e-05, | |
| "loss": 0.0817, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.04055766793409379, | |
| "grad_norm": 0.49059954285621643, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 0.0748, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.04126920596802526, | |
| "grad_norm": 0.3070560097694397, | |
| "learning_rate": 2.1822519843544424e-05, | |
| "loss": 0.0581, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.04198074400195673, | |
| "grad_norm": 0.3088557720184326, | |
| "learning_rate": 2.0528000059645997e-05, | |
| "loss": 0.051, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.0426922820358882, | |
| "grad_norm": 0.3666839301586151, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 0.0588, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.04340382006981967, | |
| "grad_norm": 0.4506279230117798, | |
| "learning_rate": 1.8138158006995364e-05, | |
| "loss": 0.0734, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.04411535810375114, | |
| "grad_norm": 0.6894549131393433, | |
| "learning_rate": 1.7047384938420154e-05, | |
| "loss": 0.0656, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.044826896137682606, | |
| "grad_norm": 2.1693735122680664, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 0.1742, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.04553843417161408, | |
| "grad_norm": 0.7992150783538818, | |
| "learning_rate": 1.5084512506980026e-05, | |
| "loss": 0.1506, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.046249972205545546, | |
| "grad_norm": 0.5185897350311279, | |
| "learning_rate": 1.4216149583350754e-05, | |
| "loss": 0.113, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.04696151023947702, | |
| "grad_norm": 0.43015819787979126, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 0.0864, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.04767304827340849, | |
| "grad_norm": 0.38855844736099243, | |
| "learning_rate": 1.2713832064634126e-05, | |
| "loss": 0.0895, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.04838458630733996, | |
| "grad_norm": 0.2907514274120331, | |
| "learning_rate": 1.2082737216329794e-05, | |
| "loss": 0.0589, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.04909612434127143, | |
| "grad_norm": 0.34849977493286133, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 0.0473, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.0498076623752029, | |
| "grad_norm": 0.2817358672618866, | |
| "learning_rate": 1.1066679679603e-05, | |
| "loss": 0.0527, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.05051920040913437, | |
| "grad_norm": 0.3551785349845886, | |
| "learning_rate": 1.0683651114450641e-05, | |
| "loss": 0.0596, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.05123073844306584, | |
| "grad_norm": 0.3679645359516144, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 0.0543, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.05194227647699731, | |
| "grad_norm": 0.4032980799674988, | |
| "learning_rate": 1.017123858587145e-05, | |
| "loss": 0.0499, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.05265381451092878, | |
| "grad_norm": 0.48960503935813904, | |
| "learning_rate": 1.00428300288164e-05, | |
| "loss": 0.0701, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.05336535254486025, | |
| "grad_norm": 0.8739669322967529, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0798, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.05336535254486025, | |
| "eval_loss": 0.08122972398996353, | |
| "eval_runtime": 3.517, | |
| "eval_samples_per_second": 14.217, | |
| "eval_steps_per_second": 3.696, | |
| "step": 75 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 75, | |
| "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": 8.952125425975296e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |