| { | |
| "best_metric": 1.1020288467407227, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-75", | |
| "epoch": 0.38628681796233705, | |
| "eval_steps": 25, | |
| "global_step": 75, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.005150490906164494, | |
| "grad_norm": 1.6126657724380493, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 1.941, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.005150490906164494, | |
| "eval_loss": 1.8850927352905273, | |
| "eval_runtime": 4.0033, | |
| "eval_samples_per_second": 12.49, | |
| "eval_steps_per_second": 3.247, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.010300981812328988, | |
| "grad_norm": 1.6743135452270508, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 1.7523, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.01545147271849348, | |
| "grad_norm": 1.6910467147827148, | |
| "learning_rate": 0.0001, | |
| "loss": 1.7829, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.020601963624657976, | |
| "grad_norm": 1.367571234703064, | |
| "learning_rate": 9.99571699711836e-05, | |
| "loss": 1.5894, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.02575245453082247, | |
| "grad_norm": 1.495391607284546, | |
| "learning_rate": 9.982876141412856e-05, | |
| "loss": 1.5111, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.03090294543698696, | |
| "grad_norm": 1.160764455795288, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 1.4233, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.03605343634315146, | |
| "grad_norm": 0.8878348469734192, | |
| "learning_rate": 9.931634888554937e-05, | |
| "loss": 1.348, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.04120392724931595, | |
| "grad_norm": 0.9640621542930603, | |
| "learning_rate": 9.893332032039701e-05, | |
| "loss": 1.3584, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.04635441815548044, | |
| "grad_norm": 0.9921740889549255, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 1.2667, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.05150490906164494, | |
| "grad_norm": 0.9959519505500793, | |
| "learning_rate": 9.791726278367022e-05, | |
| "loss": 1.1275, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.05665539996780943, | |
| "grad_norm": 1.0067778825759888, | |
| "learning_rate": 9.728616793536588e-05, | |
| "loss": 1.0443, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.06180589087397392, | |
| "grad_norm": 1.338114857673645, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 1.0808, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.06695638178013842, | |
| "grad_norm": 1.3758338689804077, | |
| "learning_rate": 9.578385041664925e-05, | |
| "loss": 1.619, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.07210687268630292, | |
| "grad_norm": 0.9469649195671082, | |
| "learning_rate": 9.491548749301997e-05, | |
| "loss": 1.4238, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0772573635924674, | |
| "grad_norm": 0.6833482384681702, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 1.3451, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0824078544986319, | |
| "grad_norm": 0.8655621409416199, | |
| "learning_rate": 9.295261506157986e-05, | |
| "loss": 1.3856, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0875583454047964, | |
| "grad_norm": 0.7689515948295593, | |
| "learning_rate": 9.186184199300464e-05, | |
| "loss": 1.2611, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.09270883631096088, | |
| "grad_norm": 0.7660016417503357, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 1.236, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.09785932721712538, | |
| "grad_norm": 0.7246228456497192, | |
| "learning_rate": 8.947199994035401e-05, | |
| "loss": 1.1257, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.10300981812328988, | |
| "grad_norm": 0.791655421257019, | |
| "learning_rate": 8.817748015645558e-05, | |
| "loss": 1.1965, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.10816030902945437, | |
| "grad_norm": 0.8405879735946655, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 1.2137, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.11331079993561886, | |
| "grad_norm": 0.7571701407432556, | |
| "learning_rate": 8.540155934270471e-05, | |
| "loss": 1.0821, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.11846129084178336, | |
| "grad_norm": 0.9514710903167725, | |
| "learning_rate": 8.392544243589427e-05, | |
| "loss": 1.0548, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.12361178174794785, | |
| "grad_norm": 1.1480365991592407, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 1.0676, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.12876227265411236, | |
| "grad_norm": 1.1530849933624268, | |
| "learning_rate": 8.081093963579707e-05, | |
| "loss": 0.959, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.12876227265411236, | |
| "eval_loss": 1.2043055295944214, | |
| "eval_runtime": 4.0623, | |
| "eval_samples_per_second": 12.308, | |
| "eval_steps_per_second": 3.2, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.13391276356027684, | |
| "grad_norm": 0.6668666005134583, | |
| "learning_rate": 7.917848237560709e-05, | |
| "loss": 1.4982, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.13906325446644133, | |
| "grad_norm": 0.6831625699996948, | |
| "learning_rate": 7.75e-05, | |
| "loss": 1.3068, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.14421374537260584, | |
| "grad_norm": 0.654782772064209, | |
| "learning_rate": 7.577868759557654e-05, | |
| "loss": 1.3077, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.14936423627877032, | |
| "grad_norm": 0.6191349625587463, | |
| "learning_rate": 7.401782177833148e-05, | |
| "loss": 1.3137, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.1545147271849348, | |
| "grad_norm": 0.6687305569648743, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 1.1626, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.15966521809109932, | |
| "grad_norm": 0.7296125888824463, | |
| "learning_rate": 7.03909064496551e-05, | |
| "loss": 1.1292, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.1648157089972638, | |
| "grad_norm": 0.7525869607925415, | |
| "learning_rate": 6.853176097769229e-05, | |
| "loss": 1.0622, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.1699661999034283, | |
| "grad_norm": 0.7842842936515808, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 1.0998, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.1751166908095928, | |
| "grad_norm": 0.7670237421989441, | |
| "learning_rate": 6.473978262721463e-05, | |
| "loss": 1.0795, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.18026718171575729, | |
| "grad_norm": 0.8848092555999756, | |
| "learning_rate": 6.281416799501188e-05, | |
| "loss": 1.0421, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.18541767262192177, | |
| "grad_norm": 0.9541935324668884, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 0.9614, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.19056816352808628, | |
| "grad_norm": 0.9986409544944763, | |
| "learning_rate": 5.8922008423644624e-05, | |
| "loss": 0.9052, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.19571865443425077, | |
| "grad_norm": 0.7817866206169128, | |
| "learning_rate": 5.696287243144013e-05, | |
| "loss": 1.4343, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.20086914534041525, | |
| "grad_norm": 0.632110059261322, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 1.3297, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.20601963624657976, | |
| "grad_norm": 0.5873474478721619, | |
| "learning_rate": 5.303712756855988e-05, | |
| "loss": 1.225, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.21117012715274425, | |
| "grad_norm": 0.5888330936431885, | |
| "learning_rate": 5.107799157635538e-05, | |
| "loss": 1.2015, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.21632061805890873, | |
| "grad_norm": 0.6649183034896851, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 1.1975, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.22147110896507324, | |
| "grad_norm": 0.7081603407859802, | |
| "learning_rate": 4.718583200498814e-05, | |
| "loss": 1.1672, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.22662159987123773, | |
| "grad_norm": 0.7628908753395081, | |
| "learning_rate": 4.526021737278538e-05, | |
| "loss": 1.1333, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.2317720907774022, | |
| "grad_norm": 0.699059009552002, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 1.1043, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.23692258168356672, | |
| "grad_norm": 0.7549357414245605, | |
| "learning_rate": 4.146823902230772e-05, | |
| "loss": 1.0802, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.2420730725897312, | |
| "grad_norm": 0.7739465236663818, | |
| "learning_rate": 3.960909355034491e-05, | |
| "loss": 1.0429, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.2472235634958957, | |
| "grad_norm": 0.8181856274604797, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 0.8891, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.2523740544020602, | |
| "grad_norm": 0.9725480079650879, | |
| "learning_rate": 3.598217822166854e-05, | |
| "loss": 0.9871, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.2575245453082247, | |
| "grad_norm": 1.2461752891540527, | |
| "learning_rate": 3.422131240442349e-05, | |
| "loss": 0.8804, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.2575245453082247, | |
| "eval_loss": 1.1305104494094849, | |
| "eval_runtime": 4.0432, | |
| "eval_samples_per_second": 12.366, | |
| "eval_steps_per_second": 3.215, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.2626750362143892, | |
| "grad_norm": 0.6626567244529724, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 1.4105, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.2678255271205537, | |
| "grad_norm": 0.6616899371147156, | |
| "learning_rate": 3.082151762439293e-05, | |
| "loss": 1.2103, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.27297601802671817, | |
| "grad_norm": 0.6504210233688354, | |
| "learning_rate": 2.9189060364202943e-05, | |
| "loss": 1.1649, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.27812650893288265, | |
| "grad_norm": 0.6488938331604004, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 1.2075, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.28327699983904714, | |
| "grad_norm": 0.6831638813018799, | |
| "learning_rate": 2.6074557564105727e-05, | |
| "loss": 1.238, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.2884274907452117, | |
| "grad_norm": 0.7102789878845215, | |
| "learning_rate": 2.459844065729529e-05, | |
| "loss": 1.1096, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.29357798165137616, | |
| "grad_norm": 0.697617769241333, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 1.0315, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.29872847255754065, | |
| "grad_norm": 0.789955735206604, | |
| "learning_rate": 2.1822519843544424e-05, | |
| "loss": 1.0317, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.30387896346370513, | |
| "grad_norm": 0.8065967559814453, | |
| "learning_rate": 2.0528000059645997e-05, | |
| "loss": 1.0469, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.3090294543698696, | |
| "grad_norm": 0.7964063286781311, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 0.9775, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.3141799452760341, | |
| "grad_norm": 0.8694634437561035, | |
| "learning_rate": 1.8138158006995364e-05, | |
| "loss": 0.8733, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.31933043618219864, | |
| "grad_norm": 0.9869593381881714, | |
| "learning_rate": 1.7047384938420154e-05, | |
| "loss": 0.9035, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.3244809270883631, | |
| "grad_norm": 0.5871992707252502, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 1.3583, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.3296314179945276, | |
| "grad_norm": 0.5578927397727966, | |
| "learning_rate": 1.5084512506980026e-05, | |
| "loss": 1.3325, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.3347819089006921, | |
| "grad_norm": 0.587887704372406, | |
| "learning_rate": 1.4216149583350754e-05, | |
| "loss": 1.3098, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.3399323998068566, | |
| "grad_norm": 0.6099755764007568, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 1.2052, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.34508289071302106, | |
| "grad_norm": 0.6458743810653687, | |
| "learning_rate": 1.2713832064634126e-05, | |
| "loss": 1.2037, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.3502333816191856, | |
| "grad_norm": 0.6708971261978149, | |
| "learning_rate": 1.2082737216329794e-05, | |
| "loss": 1.1093, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.3553838725253501, | |
| "grad_norm": 0.6868105530738831, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 1.1062, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.36053436343151457, | |
| "grad_norm": 0.7059977650642395, | |
| "learning_rate": 1.1066679679603e-05, | |
| "loss": 1.1001, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.36568485433767906, | |
| "grad_norm": 0.7179769277572632, | |
| "learning_rate": 1.0683651114450641e-05, | |
| "loss": 0.9938, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.37083534524384354, | |
| "grad_norm": 0.7872999310493469, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 1.0442, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.375985836150008, | |
| "grad_norm": 0.914609968662262, | |
| "learning_rate": 1.017123858587145e-05, | |
| "loss": 0.8831, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.38113632705617256, | |
| "grad_norm": 0.9258915185928345, | |
| "learning_rate": 1.00428300288164e-05, | |
| "loss": 0.8793, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.38628681796233705, | |
| "grad_norm": 1.1383943557739258, | |
| "learning_rate": 1e-05, | |
| "loss": 0.841, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.38628681796233705, | |
| "eval_loss": 1.1020288467407227, | |
| "eval_runtime": 4.0849, | |
| "eval_samples_per_second": 12.24, | |
| "eval_steps_per_second": 3.182, | |
| "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": 9.261719016701952e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |