| { | |
| "best_metric": 0.050220850855112076, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 1.400932400932401, | |
| "eval_steps": 50, | |
| "global_step": 75, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.018648018648018648, | |
| "grad_norm": 3.7544713020324707, | |
| "learning_rate": 5e-06, | |
| "loss": 2.5029, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.018648018648018648, | |
| "eval_loss": 2.441243886947632, | |
| "eval_runtime": 15.0491, | |
| "eval_samples_per_second": 6.047, | |
| "eval_steps_per_second": 1.528, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.037296037296037296, | |
| "grad_norm": 3.805962085723877, | |
| "learning_rate": 1e-05, | |
| "loss": 2.496, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.055944055944055944, | |
| "grad_norm": 3.6651675701141357, | |
| "learning_rate": 1.5e-05, | |
| "loss": 2.4683, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.07459207459207459, | |
| "grad_norm": 3.5058395862579346, | |
| "learning_rate": 2e-05, | |
| "loss": 2.4108, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.09324009324009325, | |
| "grad_norm": 3.1128268241882324, | |
| "learning_rate": 2.5e-05, | |
| "loss": 2.2825, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.11188811188811189, | |
| "grad_norm": 2.886013984680176, | |
| "learning_rate": 3e-05, | |
| "loss": 1.9991, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.13053613053613053, | |
| "grad_norm": 2.2185962200164795, | |
| "learning_rate": 3.5e-05, | |
| "loss": 1.8074, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.14918414918414918, | |
| "grad_norm": 2.538952350616455, | |
| "learning_rate": 4e-05, | |
| "loss": 1.6528, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.16783216783216784, | |
| "grad_norm": 2.6650140285491943, | |
| "learning_rate": 4.5e-05, | |
| "loss": 1.3879, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.1864801864801865, | |
| "grad_norm": 2.4783599376678467, | |
| "learning_rate": 5e-05, | |
| "loss": 1.1667, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.20512820512820512, | |
| "grad_norm": 2.2430834770202637, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 0.9177, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.22377622377622378, | |
| "grad_norm": 2.096689462661743, | |
| "learning_rate": 6e-05, | |
| "loss": 0.7368, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.24242424242424243, | |
| "grad_norm": 1.8305144309997559, | |
| "learning_rate": 6.500000000000001e-05, | |
| "loss": 0.5248, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.26107226107226106, | |
| "grad_norm": 1.5723942518234253, | |
| "learning_rate": 7e-05, | |
| "loss": 0.3459, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.27972027972027974, | |
| "grad_norm": 3.2492153644561768, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.213, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.29836829836829837, | |
| "grad_norm": 1.0065910816192627, | |
| "learning_rate": 8e-05, | |
| "loss": 0.1651, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.317016317016317, | |
| "grad_norm": 0.8119553923606873, | |
| "learning_rate": 8.5e-05, | |
| "loss": 0.131, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.3356643356643357, | |
| "grad_norm": 0.5442985892295837, | |
| "learning_rate": 9e-05, | |
| "loss": 0.1094, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.3543123543123543, | |
| "grad_norm": 0.44042328000068665, | |
| "learning_rate": 9.5e-05, | |
| "loss": 0.0855, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.372960372960373, | |
| "grad_norm": 0.5316314101219177, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1114, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.3916083916083916, | |
| "grad_norm": 0.3505031168460846, | |
| "learning_rate": 9.991845519630678e-05, | |
| "loss": 0.0716, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.41025641025641024, | |
| "grad_norm": 0.48583555221557617, | |
| "learning_rate": 9.967408676742751e-05, | |
| "loss": 0.1003, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.4289044289044289, | |
| "grad_norm": 0.3102801740169525, | |
| "learning_rate": 9.926769179238466e-05, | |
| "loss": 0.0606, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.44755244755244755, | |
| "grad_norm": 0.2852686643600464, | |
| "learning_rate": 9.870059584711668e-05, | |
| "loss": 0.0587, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.4662004662004662, | |
| "grad_norm": 0.2183716744184494, | |
| "learning_rate": 9.797464868072488e-05, | |
| "loss": 0.0522, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.48484848484848486, | |
| "grad_norm": 0.26890677213668823, | |
| "learning_rate": 9.709221818197624e-05, | |
| "loss": 0.0858, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.5034965034965035, | |
| "grad_norm": 0.18300114572048187, | |
| "learning_rate": 9.60561826557425e-05, | |
| "loss": 0.0496, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.5221445221445221, | |
| "grad_norm": 0.20950715243816376, | |
| "learning_rate": 9.486992143456792e-05, | |
| "loss": 0.0701, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.5407925407925408, | |
| "grad_norm": 0.1695779263973236, | |
| "learning_rate": 9.353730385598887e-05, | |
| "loss": 0.0521, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.5594405594405595, | |
| "grad_norm": 0.1300334930419922, | |
| "learning_rate": 9.206267664155907e-05, | |
| "loss": 0.0487, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.578088578088578, | |
| "grad_norm": 0.09397494792938232, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 0.0517, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.5967365967365967, | |
| "grad_norm": 0.1267092227935791, | |
| "learning_rate": 8.870708053195413e-05, | |
| "loss": 0.0391, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.6153846153846154, | |
| "grad_norm": 0.13381347060203552, | |
| "learning_rate": 8.683705689382024e-05, | |
| "loss": 0.0398, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.634032634032634, | |
| "grad_norm": 0.1413053721189499, | |
| "learning_rate": 8.484687843276469e-05, | |
| "loss": 0.0406, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.6526806526806527, | |
| "grad_norm": 0.10715018212795258, | |
| "learning_rate": 8.274303669726426e-05, | |
| "loss": 0.0405, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.6713286713286714, | |
| "grad_norm": 0.18798989057540894, | |
| "learning_rate": 8.053239398177191e-05, | |
| "loss": 0.0701, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.6899766899766899, | |
| "grad_norm": 0.10021158307790756, | |
| "learning_rate": 7.822216094333847e-05, | |
| "loss": 0.0415, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.7086247086247086, | |
| "grad_norm": 0.09004908055067062, | |
| "learning_rate": 7.58198730819481e-05, | |
| "loss": 0.0466, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.7272727272727273, | |
| "grad_norm": 0.10785119980573654, | |
| "learning_rate": 7.333336616128369e-05, | |
| "loss": 0.0429, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.745920745920746, | |
| "grad_norm": 0.1452600061893463, | |
| "learning_rate": 7.077075065009433e-05, | |
| "loss": 0.0423, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.7645687645687645, | |
| "grad_norm": 0.09562265872955322, | |
| "learning_rate": 6.814038526753205e-05, | |
| "loss": 0.0466, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.7832167832167832, | |
| "grad_norm": 0.08707461506128311, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 0.0439, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.8018648018648019, | |
| "grad_norm": 0.0825454518198967, | |
| "learning_rate": 6.271091670967436e-05, | |
| "loss": 0.0406, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.8205128205128205, | |
| "grad_norm": 0.09737467020750046, | |
| "learning_rate": 5.992952333228728e-05, | |
| "loss": 0.0419, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.8391608391608392, | |
| "grad_norm": 0.0975765511393547, | |
| "learning_rate": 5.7115741913664264e-05, | |
| "loss": 0.0417, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.8578088578088578, | |
| "grad_norm": 0.06991899758577347, | |
| "learning_rate": 5.427875042394199e-05, | |
| "loss": 0.0454, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.8764568764568764, | |
| "grad_norm": 0.07402784377336502, | |
| "learning_rate": 5.142780253968481e-05, | |
| "loss": 0.0459, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.8951048951048951, | |
| "grad_norm": 0.06774295121431351, | |
| "learning_rate": 4.85721974603152e-05, | |
| "loss": 0.0384, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.9137529137529138, | |
| "grad_norm": 0.10975111275911331, | |
| "learning_rate": 4.5721249576058027e-05, | |
| "loss": 0.0418, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.9324009324009324, | |
| "grad_norm": 0.06744930893182755, | |
| "learning_rate": 4.288425808633575e-05, | |
| "loss": 0.0471, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.9324009324009324, | |
| "eval_loss": 0.050220850855112076, | |
| "eval_runtime": 14.8191, | |
| "eval_samples_per_second": 6.141, | |
| "eval_steps_per_second": 1.552, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.951048951048951, | |
| "grad_norm": 0.13983112573623657, | |
| "learning_rate": 4.007047666771274e-05, | |
| "loss": 0.0631, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.9696969696969697, | |
| "grad_norm": 0.1023995652794838, | |
| "learning_rate": 3.728908329032567e-05, | |
| "loss": 0.0313, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.9883449883449883, | |
| "grad_norm": 0.08331304788589478, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 0.0426, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 1.0093240093240092, | |
| "grad_norm": 0.12266716361045837, | |
| "learning_rate": 3.1859614732467954e-05, | |
| "loss": 0.0565, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 1.027972027972028, | |
| "grad_norm": 0.055081456899642944, | |
| "learning_rate": 2.9229249349905684e-05, | |
| "loss": 0.0395, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 1.0466200466200466, | |
| "grad_norm": 0.08440406620502472, | |
| "learning_rate": 2.6666633838716314e-05, | |
| "loss": 0.0375, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 1.0652680652680653, | |
| "grad_norm": 0.08142155408859253, | |
| "learning_rate": 2.418012691805191e-05, | |
| "loss": 0.0374, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 1.083916083916084, | |
| "grad_norm": 0.0638071596622467, | |
| "learning_rate": 2.1777839056661554e-05, | |
| "loss": 0.0448, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 1.1025641025641026, | |
| "grad_norm": 0.07102889567613602, | |
| "learning_rate": 1.946760601822809e-05, | |
| "loss": 0.038, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 1.121212121212121, | |
| "grad_norm": 0.06918191909790039, | |
| "learning_rate": 1.725696330273575e-05, | |
| "loss": 0.0398, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.1398601398601398, | |
| "grad_norm": 0.06793826073408127, | |
| "learning_rate": 1.5153121567235335e-05, | |
| "loss": 0.037, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 1.1585081585081585, | |
| "grad_norm": 0.060138434171676636, | |
| "learning_rate": 1.3162943106179749e-05, | |
| "loss": 0.0412, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 1.1771561771561772, | |
| "grad_norm": 0.06100895628333092, | |
| "learning_rate": 1.1292919468045877e-05, | |
| "loss": 0.0391, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 1.1958041958041958, | |
| "grad_norm": 0.08120011538267136, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 0.0377, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 1.2144522144522145, | |
| "grad_norm": 0.05974452942609787, | |
| "learning_rate": 7.937323358440935e-06, | |
| "loss": 0.0496, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 1.2331002331002332, | |
| "grad_norm": 0.06714749336242676, | |
| "learning_rate": 6.462696144011149e-06, | |
| "loss": 0.0411, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 1.2517482517482517, | |
| "grad_norm": 0.06198333948850632, | |
| "learning_rate": 5.13007856543209e-06, | |
| "loss": 0.0394, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 1.2703962703962703, | |
| "grad_norm": 0.08504387736320496, | |
| "learning_rate": 3.9438173442575e-06, | |
| "loss": 0.0353, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 1.289044289044289, | |
| "grad_norm": 0.12137630581855774, | |
| "learning_rate": 2.9077818180237693e-06, | |
| "loss": 0.0452, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 1.3076923076923077, | |
| "grad_norm": 0.06834172457456589, | |
| "learning_rate": 2.0253513192751373e-06, | |
| "loss": 0.0434, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.3263403263403264, | |
| "grad_norm": 0.05725034326314926, | |
| "learning_rate": 1.2994041528833266e-06, | |
| "loss": 0.0462, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 1.3449883449883449, | |
| "grad_norm": 0.06547888368368149, | |
| "learning_rate": 7.323082076153509e-07, | |
| "loss": 0.0408, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 1.3636363636363638, | |
| "grad_norm": 0.060845568776130676, | |
| "learning_rate": 3.2591323257248893e-07, | |
| "loss": 0.0457, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 1.3822843822843822, | |
| "grad_norm": 0.05932041257619858, | |
| "learning_rate": 8.15448036932176e-08, | |
| "loss": 0.0422, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 1.400932400932401, | |
| "grad_norm": 0.0670986920595169, | |
| "learning_rate": 0.0, | |
| "loss": 0.0386, | |
| "step": 75 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 75, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "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": 2.262770368118784e+17, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |