| { | |
| "best_metric": 2.2149920653191657e-07, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.11714174150722374, | |
| "eval_steps": 50, | |
| "global_step": 75, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0015618898867629833, | |
| "grad_norm": 98.61892700195312, | |
| "learning_rate": 5e-06, | |
| "loss": 32.9851, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0015618898867629833, | |
| "eval_loss": 8.434075355529785, | |
| "eval_runtime": 131.5507, | |
| "eval_samples_per_second": 8.195, | |
| "eval_steps_per_second": 1.026, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0031237797735259665, | |
| "grad_norm": 101.88670349121094, | |
| "learning_rate": 1e-05, | |
| "loss": 33.6919, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.004685669660288949, | |
| "grad_norm": 102.52140808105469, | |
| "learning_rate": 1.5e-05, | |
| "loss": 33.6445, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.006247559547051933, | |
| "grad_norm": 101.51856994628906, | |
| "learning_rate": 2e-05, | |
| "loss": 32.0187, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.007809449433814916, | |
| "grad_norm": 101.1911392211914, | |
| "learning_rate": 2.5e-05, | |
| "loss": 29.0392, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.009371339320577899, | |
| "grad_norm": 115.63481903076172, | |
| "learning_rate": 3e-05, | |
| "loss": 23.4667, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.010933229207340883, | |
| "grad_norm": 127.65371704101562, | |
| "learning_rate": 3.5e-05, | |
| "loss": 14.4537, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.012495119094103866, | |
| "grad_norm": 96.5782470703125, | |
| "learning_rate": 4e-05, | |
| "loss": 6.0554, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.014057008980866849, | |
| "grad_norm": 23.205415725708008, | |
| "learning_rate": 4.5e-05, | |
| "loss": 0.862, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.015618898867629832, | |
| "grad_norm": 7.010463714599609, | |
| "learning_rate": 5e-05, | |
| "loss": 1.269, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.017180788754392814, | |
| "grad_norm": 2.8492934703826904, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 1.4726, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.018742678641155797, | |
| "grad_norm": 1.6024590730667114, | |
| "learning_rate": 6e-05, | |
| "loss": 0.011, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.02030456852791878, | |
| "grad_norm": 0.028355423361063004, | |
| "learning_rate": 6.500000000000001e-05, | |
| "loss": 0.0008, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.021866458414681766, | |
| "grad_norm": 0.01454650703817606, | |
| "learning_rate": 7e-05, | |
| "loss": 0.0004, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.02342834830144475, | |
| "grad_norm": 0.016405019909143448, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.0003, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.024990238188207732, | |
| "grad_norm": 0.01066912617534399, | |
| "learning_rate": 8e-05, | |
| "loss": 0.0002, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.026552128074970715, | |
| "grad_norm": 0.00642524054273963, | |
| "learning_rate": 8.5e-05, | |
| "loss": 0.0001, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.028114017961733698, | |
| "grad_norm": 0.004217273555696011, | |
| "learning_rate": 9e-05, | |
| "loss": 0.0001, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.02967590784849668, | |
| "grad_norm": 0.0021315179765224457, | |
| "learning_rate": 9.5e-05, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.031237797735259663, | |
| "grad_norm": 0.00157815997954458, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.03279968762202265, | |
| "grad_norm": 0.0009499505395069718, | |
| "learning_rate": 9.991845519630678e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.03436157750878563, | |
| "grad_norm": 0.0005398875218816102, | |
| "learning_rate": 9.967408676742751e-05, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.035923467395548615, | |
| "grad_norm": 0.00042756047332659364, | |
| "learning_rate": 9.926769179238466e-05, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.037485357282311595, | |
| "grad_norm": 0.00030578853329643607, | |
| "learning_rate": 9.870059584711668e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.03904724716907458, | |
| "grad_norm": 0.00040090526454150677, | |
| "learning_rate": 9.797464868072488e-05, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.04060913705583756, | |
| "grad_norm": 0.0003341698902659118, | |
| "learning_rate": 9.709221818197624e-05, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.04217102694260055, | |
| "grad_norm": 0.0003867969790007919, | |
| "learning_rate": 9.60561826557425e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.04373291682936353, | |
| "grad_norm": 0.0003099101595580578, | |
| "learning_rate": 9.486992143456792e-05, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.04529480671612651, | |
| "grad_norm": 0.00023561953275930136, | |
| "learning_rate": 9.353730385598887e-05, | |
| "loss": 0.0, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.0468566966028895, | |
| "grad_norm": 0.00026002241065725684, | |
| "learning_rate": 9.206267664155907e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.04841858648965248, | |
| "grad_norm": 0.0001232671202160418, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 0.0, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.049980476376415464, | |
| "grad_norm": 0.000312990479869768, | |
| "learning_rate": 8.870708053195413e-05, | |
| "loss": 0.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.051542366263178443, | |
| "grad_norm": 0.0001929818681674078, | |
| "learning_rate": 8.683705689382024e-05, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.05310425614994143, | |
| "grad_norm": 0.00021537607244681567, | |
| "learning_rate": 8.484687843276469e-05, | |
| "loss": 0.0, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.05466614603670441, | |
| "grad_norm": 0.00023825050448067486, | |
| "learning_rate": 8.274303669726426e-05, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.056228035923467395, | |
| "grad_norm": 0.0002484881551936269, | |
| "learning_rate": 8.053239398177191e-05, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.05778992581023038, | |
| "grad_norm": 0.00022945506498217583, | |
| "learning_rate": 7.822216094333847e-05, | |
| "loss": 0.0, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.05935181569699336, | |
| "grad_norm": 0.00020148875773884356, | |
| "learning_rate": 7.58198730819481e-05, | |
| "loss": 0.0, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.06091370558375635, | |
| "grad_norm": 0.0001627219025976956, | |
| "learning_rate": 7.333336616128369e-05, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.06247559547051933, | |
| "grad_norm": 0.00020812929142266512, | |
| "learning_rate": 7.077075065009433e-05, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0640374853572823, | |
| "grad_norm": 0.0001692381629254669, | |
| "learning_rate": 6.814038526753205e-05, | |
| "loss": 0.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.0655993752440453, | |
| "grad_norm": 0.00015132878615986556, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.06716126513080828, | |
| "grad_norm": 3.081911087036133, | |
| "learning_rate": 6.271091670967436e-05, | |
| "loss": 0.73, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.06872315501757126, | |
| "grad_norm": 8.377726044273004e-05, | |
| "learning_rate": 5.992952333228728e-05, | |
| "loss": 0.0, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.07028504490433425, | |
| "grad_norm": 5.907801823923364e-05, | |
| "learning_rate": 5.7115741913664264e-05, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.07184693479109723, | |
| "grad_norm": 7.357277354458347e-05, | |
| "learning_rate": 5.427875042394199e-05, | |
| "loss": 0.0, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.07340882467786021, | |
| "grad_norm": 8.98546859389171e-05, | |
| "learning_rate": 5.142780253968481e-05, | |
| "loss": 0.0, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.07497071456462319, | |
| "grad_norm": 8.352519944310188e-05, | |
| "learning_rate": 4.85721974603152e-05, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.07653260445138618, | |
| "grad_norm": 8.221614552894607e-05, | |
| "learning_rate": 4.5721249576058027e-05, | |
| "loss": 0.0, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.07809449433814916, | |
| "grad_norm": 6.574123108293861e-05, | |
| "learning_rate": 4.288425808633575e-05, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.07809449433814916, | |
| "eval_loss": 2.2149920653191657e-07, | |
| "eval_runtime": 133.019, | |
| "eval_samples_per_second": 8.104, | |
| "eval_steps_per_second": 1.015, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.07965638422491214, | |
| "grad_norm": 7.894937880337238e-05, | |
| "learning_rate": 4.007047666771274e-05, | |
| "loss": 0.0, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.08121827411167512, | |
| "grad_norm": 6.547181692440063e-05, | |
| "learning_rate": 3.728908329032567e-05, | |
| "loss": 0.0, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.08278016399843811, | |
| "grad_norm": 8.983476436696947e-05, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 0.0, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.0843420538852011, | |
| "grad_norm": 8.567280747229233e-05, | |
| "learning_rate": 3.1859614732467954e-05, | |
| "loss": 0.0, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.08590394377196407, | |
| "grad_norm": 7.29016974219121e-05, | |
| "learning_rate": 2.9229249349905684e-05, | |
| "loss": 0.0, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.08746583365872707, | |
| "grad_norm": 7.546821871073917e-05, | |
| "learning_rate": 2.6666633838716314e-05, | |
| "loss": 0.0, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.08902772354549005, | |
| "grad_norm": 8.067455200944096e-05, | |
| "learning_rate": 2.418012691805191e-05, | |
| "loss": 0.0, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.09058961343225302, | |
| "grad_norm": 8.359667845070362e-05, | |
| "learning_rate": 2.1777839056661554e-05, | |
| "loss": 0.0, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.092151503319016, | |
| "grad_norm": 7.18247247277759e-05, | |
| "learning_rate": 1.946760601822809e-05, | |
| "loss": 0.0, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.093713393205779, | |
| "grad_norm": 6.643526285188273e-05, | |
| "learning_rate": 1.725696330273575e-05, | |
| "loss": 0.0, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.09527528309254198, | |
| "grad_norm": 8.725138468435034e-05, | |
| "learning_rate": 1.5153121567235335e-05, | |
| "loss": 0.0, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.09683717297930496, | |
| "grad_norm": 8.253858686657622e-05, | |
| "learning_rate": 1.3162943106179749e-05, | |
| "loss": 0.0, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.09839906286606795, | |
| "grad_norm": 8.31460565677844e-05, | |
| "learning_rate": 1.1292919468045877e-05, | |
| "loss": 0.0, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.09996095275283093, | |
| "grad_norm": 7.785527122905478e-05, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 0.0, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.10152284263959391, | |
| "grad_norm": 8.430494926869869e-05, | |
| "learning_rate": 7.937323358440935e-06, | |
| "loss": 0.0, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.10308473252635689, | |
| "grad_norm": 8.321902714669704e-05, | |
| "learning_rate": 6.462696144011149e-06, | |
| "loss": 0.0, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.10464662241311988, | |
| "grad_norm": 0.0001040767747326754, | |
| "learning_rate": 5.13007856543209e-06, | |
| "loss": 0.0, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.10620851229988286, | |
| "grad_norm": 7.150931196520105e-05, | |
| "learning_rate": 3.9438173442575e-06, | |
| "loss": 0.0, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.10777040218664584, | |
| "grad_norm": 0.00010513537563383579, | |
| "learning_rate": 2.9077818180237693e-06, | |
| "loss": 0.0, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.10933229207340882, | |
| "grad_norm": 9.533106640446931e-05, | |
| "learning_rate": 2.0253513192751373e-06, | |
| "loss": 0.0, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.11089418196017181, | |
| "grad_norm": 6.648513954132795e-05, | |
| "learning_rate": 1.2994041528833266e-06, | |
| "loss": 0.0, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.11245607184693479, | |
| "grad_norm": 9.498356666881591e-05, | |
| "learning_rate": 7.323082076153509e-07, | |
| "loss": 0.0, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.11401796173369777, | |
| "grad_norm": 8.942888234741986e-05, | |
| "learning_rate": 3.2591323257248893e-07, | |
| "loss": 0.0, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.11557985162046076, | |
| "grad_norm": 7.500114588765427e-05, | |
| "learning_rate": 8.15448036932176e-08, | |
| "loss": 0.0, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.11714174150722374, | |
| "grad_norm": 8.365325629711151e-05, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 75 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 75, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "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": 2.015720618632151e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |