| { | |
| "best_metric": 2.5323638916015625, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-75", | |
| "epoch": 1.2397330595482545, | |
| "eval_steps": 25, | |
| "global_step": 75, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01642710472279261, | |
| "grad_norm": 0.83213871717453, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 4.1897, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01642710472279261, | |
| "eval_loss": 4.481392860412598, | |
| "eval_runtime": 2.0431, | |
| "eval_samples_per_second": 24.472, | |
| "eval_steps_per_second": 6.363, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.03285420944558522, | |
| "grad_norm": 0.8668023943901062, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 4.2593, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.049281314168377825, | |
| "grad_norm": 0.893962025642395, | |
| "learning_rate": 0.0001, | |
| "loss": 4.1721, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.06570841889117043, | |
| "grad_norm": 0.9961223602294922, | |
| "learning_rate": 9.99571699711836e-05, | |
| "loss": 4.157, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.08213552361396304, | |
| "grad_norm": 1.0611786842346191, | |
| "learning_rate": 9.982876141412856e-05, | |
| "loss": 4.1331, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.09856262833675565, | |
| "grad_norm": 1.086363673210144, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 4.0068, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.11498973305954825, | |
| "grad_norm": 1.2030413150787354, | |
| "learning_rate": 9.931634888554937e-05, | |
| "loss": 3.7748, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.13141683778234087, | |
| "grad_norm": 1.2147985696792603, | |
| "learning_rate": 9.893332032039701e-05, | |
| "loss": 3.7078, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.14784394250513347, | |
| "grad_norm": 1.1192842721939087, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 3.4211, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.16427104722792607, | |
| "grad_norm": 1.0096282958984375, | |
| "learning_rate": 9.791726278367022e-05, | |
| "loss": 3.4068, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.1806981519507187, | |
| "grad_norm": 1.0285571813583374, | |
| "learning_rate": 9.728616793536588e-05, | |
| "loss": 3.2925, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.1971252566735113, | |
| "grad_norm": 1.28445303440094, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 3.2952, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.2135523613963039, | |
| "grad_norm": 0.6762813925743103, | |
| "learning_rate": 9.578385041664925e-05, | |
| "loss": 3.0429, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.2299794661190965, | |
| "grad_norm": 0.7080486416816711, | |
| "learning_rate": 9.491548749301997e-05, | |
| "loss": 3.2334, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.2464065708418891, | |
| "grad_norm": 0.7197335362434387, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 3.1313, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.26283367556468173, | |
| "grad_norm": 0.742653489112854, | |
| "learning_rate": 9.295261506157986e-05, | |
| "loss": 3.0879, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.2792607802874743, | |
| "grad_norm": 0.6773972511291504, | |
| "learning_rate": 9.186184199300464e-05, | |
| "loss": 2.9061, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.29568788501026694, | |
| "grad_norm": 0.6461683511734009, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 2.8895, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.31211498973305957, | |
| "grad_norm": 0.5850861072540283, | |
| "learning_rate": 8.947199994035401e-05, | |
| "loss": 2.9273, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.32854209445585214, | |
| "grad_norm": 0.6079311966896057, | |
| "learning_rate": 8.817748015645558e-05, | |
| "loss": 2.8932, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.34496919917864477, | |
| "grad_norm": 0.6674569845199585, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 2.65, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.3613963039014374, | |
| "grad_norm": 0.7020171284675598, | |
| "learning_rate": 8.540155934270471e-05, | |
| "loss": 2.79, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.37782340862423, | |
| "grad_norm": 0.6968078017234802, | |
| "learning_rate": 8.392544243589427e-05, | |
| "loss": 2.883, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.3942505133470226, | |
| "grad_norm": 0.9217126965522766, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 2.7329, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.4106776180698152, | |
| "grad_norm": 1.5251928567886353, | |
| "learning_rate": 8.081093963579707e-05, | |
| "loss": 2.4426, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.4106776180698152, | |
| "eval_loss": 2.718066692352295, | |
| "eval_runtime": 2.0417, | |
| "eval_samples_per_second": 24.49, | |
| "eval_steps_per_second": 6.367, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.4271047227926078, | |
| "grad_norm": 0.8887903690338135, | |
| "learning_rate": 7.917848237560709e-05, | |
| "loss": 3.0674, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.44353182751540043, | |
| "grad_norm": 0.8925255537033081, | |
| "learning_rate": 7.75e-05, | |
| "loss": 2.9501, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.459958932238193, | |
| "grad_norm": 0.8643532395362854, | |
| "learning_rate": 7.577868759557654e-05, | |
| "loss": 2.8978, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.47638603696098564, | |
| "grad_norm": 0.781319797039032, | |
| "learning_rate": 7.401782177833148e-05, | |
| "loss": 3.0056, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.4928131416837782, | |
| "grad_norm": 0.6614418625831604, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 2.794, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.5092402464065708, | |
| "grad_norm": 0.5951665043830872, | |
| "learning_rate": 7.03909064496551e-05, | |
| "loss": 2.8334, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.5256673511293635, | |
| "grad_norm": 0.5194978713989258, | |
| "learning_rate": 6.853176097769229e-05, | |
| "loss": 2.7077, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.5420944558521561, | |
| "grad_norm": 0.5276866555213928, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 2.6171, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.5585215605749486, | |
| "grad_norm": 0.5625050663948059, | |
| "learning_rate": 6.473978262721463e-05, | |
| "loss": 2.549, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.5749486652977412, | |
| "grad_norm": 0.6556904911994934, | |
| "learning_rate": 6.281416799501188e-05, | |
| "loss": 2.7686, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.5913757700205339, | |
| "grad_norm": 0.8730102181434631, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 2.8905, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.6078028747433265, | |
| "grad_norm": 1.161773681640625, | |
| "learning_rate": 5.8922008423644624e-05, | |
| "loss": 2.7177, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.6242299794661191, | |
| "grad_norm": 0.5960615277290344, | |
| "learning_rate": 5.696287243144013e-05, | |
| "loss": 2.7356, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.6406570841889117, | |
| "grad_norm": 0.5807135105133057, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 2.7539, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.6570841889117043, | |
| "grad_norm": 0.5186903476715088, | |
| "learning_rate": 5.303712756855988e-05, | |
| "loss": 2.8117, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.6735112936344969, | |
| "grad_norm": 0.5063162446022034, | |
| "learning_rate": 5.107799157635538e-05, | |
| "loss": 2.9084, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.6899383983572895, | |
| "grad_norm": 0.5014790892601013, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 2.7374, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.7063655030800822, | |
| "grad_norm": 0.43926894664764404, | |
| "learning_rate": 4.718583200498814e-05, | |
| "loss": 2.6996, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.7227926078028748, | |
| "grad_norm": 0.49418267607688904, | |
| "learning_rate": 4.526021737278538e-05, | |
| "loss": 2.6503, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.7392197125256673, | |
| "grad_norm": 0.5326753258705139, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 2.7032, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.75564681724846, | |
| "grad_norm": 0.6158781051635742, | |
| "learning_rate": 4.146823902230772e-05, | |
| "loss": 2.7546, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.7720739219712526, | |
| "grad_norm": 0.687337338924408, | |
| "learning_rate": 3.960909355034491e-05, | |
| "loss": 2.7108, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.7885010266940452, | |
| "grad_norm": 0.8074669241905212, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 2.735, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.8049281314168378, | |
| "grad_norm": 1.0225483179092407, | |
| "learning_rate": 3.598217822166854e-05, | |
| "loss": 2.5535, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.8213552361396304, | |
| "grad_norm": 1.648162841796875, | |
| "learning_rate": 3.422131240442349e-05, | |
| "loss": 2.565, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.8213552361396304, | |
| "eval_loss": 2.5712802410125732, | |
| "eval_runtime": 2.0469, | |
| "eval_samples_per_second": 24.427, | |
| "eval_steps_per_second": 6.351, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.837782340862423, | |
| "grad_norm": 0.6522903442382812, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 2.9041, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.8542094455852156, | |
| "grad_norm": 0.635415256023407, | |
| "learning_rate": 3.082151762439293e-05, | |
| "loss": 2.7645, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.8706365503080082, | |
| "grad_norm": 0.6358153820037842, | |
| "learning_rate": 2.9189060364202943e-05, | |
| "loss": 2.756, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.8870636550308009, | |
| "grad_norm": 0.5567989945411682, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 2.6265, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.9034907597535934, | |
| "grad_norm": 0.5632911324501038, | |
| "learning_rate": 2.6074557564105727e-05, | |
| "loss": 2.7177, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.919917864476386, | |
| "grad_norm": 0.6154216527938843, | |
| "learning_rate": 2.459844065729529e-05, | |
| "loss": 2.65, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.9363449691991786, | |
| "grad_norm": 0.6227327585220337, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 2.6083, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.9527720739219713, | |
| "grad_norm": 0.5644506812095642, | |
| "learning_rate": 2.1822519843544424e-05, | |
| "loss": 2.6311, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.9691991786447639, | |
| "grad_norm": 0.7271634936332703, | |
| "learning_rate": 2.0528000059645997e-05, | |
| "loss": 2.7145, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.9856262833675564, | |
| "grad_norm": 0.9412290453910828, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 2.5722, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.0097535934291582, | |
| "grad_norm": 1.2142462730407715, | |
| "learning_rate": 1.8138158006995364e-05, | |
| "loss": 4.4605, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 1.0261806981519508, | |
| "grad_norm": 0.6724117994308472, | |
| "learning_rate": 1.7047384938420154e-05, | |
| "loss": 2.7223, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 1.0426078028747434, | |
| "grad_norm": 0.6196894645690918, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 2.5821, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 1.0590349075975358, | |
| "grad_norm": 0.6005904078483582, | |
| "learning_rate": 1.5084512506980026e-05, | |
| "loss": 2.6824, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 1.0754620123203285, | |
| "grad_norm": 0.5330093502998352, | |
| "learning_rate": 1.4216149583350754e-05, | |
| "loss": 2.5775, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 1.091889117043121, | |
| "grad_norm": 0.5218847393989563, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 2.642, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 1.1083162217659137, | |
| "grad_norm": 0.5194135904312134, | |
| "learning_rate": 1.2713832064634126e-05, | |
| "loss": 2.5922, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 1.1247433264887063, | |
| "grad_norm": 0.5434170365333557, | |
| "learning_rate": 1.2082737216329794e-05, | |
| "loss": 2.4498, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 1.141170431211499, | |
| "grad_norm": 0.5660905838012695, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 2.6018, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 1.1575975359342916, | |
| "grad_norm": 0.6597437262535095, | |
| "learning_rate": 1.1066679679603e-05, | |
| "loss": 2.5986, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.1740246406570842, | |
| "grad_norm": 0.8075286746025085, | |
| "learning_rate": 1.0683651114450641e-05, | |
| "loss": 2.6485, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 1.1904517453798769, | |
| "grad_norm": 1.09507155418396, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 2.577, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 1.2068788501026695, | |
| "grad_norm": 0.9469268918037415, | |
| "learning_rate": 1.017123858587145e-05, | |
| "loss": 1.7967, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 1.2233059548254621, | |
| "grad_norm": 0.9090391993522644, | |
| "learning_rate": 1.00428300288164e-05, | |
| "loss": 3.4325, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 1.2397330595482545, | |
| "grad_norm": 0.629118025302887, | |
| "learning_rate": 1e-05, | |
| "loss": 2.5815, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 1.2397330595482545, | |
| "eval_loss": 2.5323638916015625, | |
| "eval_runtime": 2.0652, | |
| "eval_samples_per_second": 24.21, | |
| "eval_steps_per_second": 6.295, | |
| "step": 75 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 75, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "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": 1.582762825875456e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |