| { | |
| "best_metric": 2.1023528575897217, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.029682398337785694, | |
| "eval_steps": 50, | |
| "global_step": 75, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0003957653111704759, | |
| "grad_norm": 17.165529251098633, | |
| "learning_rate": 5e-06, | |
| "loss": 9.5056, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0003957653111704759, | |
| "eval_loss": 9.463391304016113, | |
| "eval_runtime": 165.7321, | |
| "eval_samples_per_second": 51.354, | |
| "eval_steps_per_second": 12.84, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0007915306223409518, | |
| "grad_norm": 16.710681915283203, | |
| "learning_rate": 1e-05, | |
| "loss": 9.513, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0011872959335114278, | |
| "grad_norm": 16.190683364868164, | |
| "learning_rate": 1.5e-05, | |
| "loss": 9.4406, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0015830612446819036, | |
| "grad_norm": 17.282331466674805, | |
| "learning_rate": 2e-05, | |
| "loss": 9.4612, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0019788265558523797, | |
| "grad_norm": 17.428613662719727, | |
| "learning_rate": 2.5e-05, | |
| "loss": 9.3862, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0023745918670228555, | |
| "grad_norm": 18.054773330688477, | |
| "learning_rate": 3e-05, | |
| "loss": 9.2646, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0027703571781933314, | |
| "grad_norm": 17.870378494262695, | |
| "learning_rate": 3.5e-05, | |
| "loss": 9.0348, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0031661224893638072, | |
| "grad_norm": 17.9739990234375, | |
| "learning_rate": 4e-05, | |
| "loss": 8.7023, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.003561887800534283, | |
| "grad_norm": 17.747678756713867, | |
| "learning_rate": 4.5e-05, | |
| "loss": 8.653, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.003957653111704759, | |
| "grad_norm": 18.454126358032227, | |
| "learning_rate": 5e-05, | |
| "loss": 8.3382, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.004353418422875235, | |
| "grad_norm": 17.509685516357422, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 8.0545, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.004749183734045711, | |
| "grad_norm": 17.798004150390625, | |
| "learning_rate": 6e-05, | |
| "loss": 7.7362, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.005144949045216187, | |
| "grad_norm": 15.242817878723145, | |
| "learning_rate": 6.500000000000001e-05, | |
| "loss": 7.4385, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.005540714356386663, | |
| "grad_norm": 13.07628059387207, | |
| "learning_rate": 7e-05, | |
| "loss": 7.1798, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.005936479667557139, | |
| "grad_norm": 11.167773246765137, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 6.9803, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0063322449787276145, | |
| "grad_norm": 10.047318458557129, | |
| "learning_rate": 8e-05, | |
| "loss": 6.7496, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.00672801028989809, | |
| "grad_norm": 10.476768493652344, | |
| "learning_rate": 8.5e-05, | |
| "loss": 6.5605, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.007123775601068566, | |
| "grad_norm": 10.307733535766602, | |
| "learning_rate": 9e-05, | |
| "loss": 6.2643, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.007519540912239042, | |
| "grad_norm": 10.599945068359375, | |
| "learning_rate": 9.5e-05, | |
| "loss": 6.1297, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.007915306223409519, | |
| "grad_norm": 10.505680084228516, | |
| "learning_rate": 0.0001, | |
| "loss": 5.8766, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.008311071534579995, | |
| "grad_norm": 9.522797584533691, | |
| "learning_rate": 9.991845519630678e-05, | |
| "loss": 5.626, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.00870683684575047, | |
| "grad_norm": 9.296674728393555, | |
| "learning_rate": 9.967408676742751e-05, | |
| "loss": 5.3456, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.009102602156920946, | |
| "grad_norm": 8.635791778564453, | |
| "learning_rate": 9.926769179238466e-05, | |
| "loss": 5.1444, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.009498367468091422, | |
| "grad_norm": 8.5535888671875, | |
| "learning_rate": 9.870059584711668e-05, | |
| "loss": 4.9605, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.009894132779261898, | |
| "grad_norm": 8.049251556396484, | |
| "learning_rate": 9.797464868072488e-05, | |
| "loss": 4.8101, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.010289898090432374, | |
| "grad_norm": 8.621903419494629, | |
| "learning_rate": 9.709221818197624e-05, | |
| "loss": 4.5989, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.01068566340160285, | |
| "grad_norm": 8.04345703125, | |
| "learning_rate": 9.60561826557425e-05, | |
| "loss": 4.4125, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.011081428712773326, | |
| "grad_norm": 7.404324054718018, | |
| "learning_rate": 9.486992143456792e-05, | |
| "loss": 4.2554, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.011477194023943801, | |
| "grad_norm": 7.918259620666504, | |
| "learning_rate": 9.353730385598887e-05, | |
| "loss": 4.0894, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.011872959335114277, | |
| "grad_norm": 7.785238742828369, | |
| "learning_rate": 9.206267664155907e-05, | |
| "loss": 3.9766, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.012268724646284753, | |
| "grad_norm": 7.892620086669922, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 3.806, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.012664489957455229, | |
| "grad_norm": 6.364659786224365, | |
| "learning_rate": 8.870708053195413e-05, | |
| "loss": 3.6896, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.013060255268625705, | |
| "grad_norm": 6.582086086273193, | |
| "learning_rate": 8.683705689382024e-05, | |
| "loss": 3.5419, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.01345602057979618, | |
| "grad_norm": 6.028378963470459, | |
| "learning_rate": 8.484687843276469e-05, | |
| "loss": 3.3398, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.013851785890966656, | |
| "grad_norm": 6.743649005889893, | |
| "learning_rate": 8.274303669726426e-05, | |
| "loss": 3.2613, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.014247551202137132, | |
| "grad_norm": 5.946102142333984, | |
| "learning_rate": 8.053239398177191e-05, | |
| "loss": 3.1901, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.014643316513307608, | |
| "grad_norm": 5.685393333435059, | |
| "learning_rate": 7.822216094333847e-05, | |
| "loss": 3.0342, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.015039081824478084, | |
| "grad_norm": 5.397143363952637, | |
| "learning_rate": 7.58198730819481e-05, | |
| "loss": 2.9706, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.01543484713564856, | |
| "grad_norm": 5.114358425140381, | |
| "learning_rate": 7.333336616128369e-05, | |
| "loss": 2.8392, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.015830612446819037, | |
| "grad_norm": 4.752023696899414, | |
| "learning_rate": 7.077075065009433e-05, | |
| "loss": 2.7408, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.01622637775798951, | |
| "grad_norm": 4.810094356536865, | |
| "learning_rate": 6.814038526753205e-05, | |
| "loss": 2.6399, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.01662214306915999, | |
| "grad_norm": 4.728804111480713, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 2.4988, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.017017908380330463, | |
| "grad_norm": 4.380035400390625, | |
| "learning_rate": 6.271091670967436e-05, | |
| "loss": 2.4686, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.01741367369150094, | |
| "grad_norm": 4.446783542633057, | |
| "learning_rate": 5.992952333228728e-05, | |
| "loss": 2.4156, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.017809439002671415, | |
| "grad_norm": 4.009081840515137, | |
| "learning_rate": 5.7115741913664264e-05, | |
| "loss": 2.3587, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.018205204313841893, | |
| "grad_norm": 3.3682971000671387, | |
| "learning_rate": 5.427875042394199e-05, | |
| "loss": 2.2072, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.018600969625012367, | |
| "grad_norm": 3.4791717529296875, | |
| "learning_rate": 5.142780253968481e-05, | |
| "loss": 2.1792, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.018996734936182844, | |
| "grad_norm": 3.7284488677978516, | |
| "learning_rate": 4.85721974603152e-05, | |
| "loss": 2.2048, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.01939250024735332, | |
| "grad_norm": 2.6523303985595703, | |
| "learning_rate": 4.5721249576058027e-05, | |
| "loss": 2.1867, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.019788265558523796, | |
| "grad_norm": 2.7477378845214844, | |
| "learning_rate": 4.288425808633575e-05, | |
| "loss": 2.1158, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.019788265558523796, | |
| "eval_loss": 2.1023528575897217, | |
| "eval_runtime": 166.1256, | |
| "eval_samples_per_second": 51.232, | |
| "eval_steps_per_second": 12.81, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.02018403086969427, | |
| "grad_norm": 2.083672046661377, | |
| "learning_rate": 4.007047666771274e-05, | |
| "loss": 2.1264, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.020579796180864748, | |
| "grad_norm": 2.1195905208587646, | |
| "learning_rate": 3.728908329032567e-05, | |
| "loss": 2.0814, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.020975561492035222, | |
| "grad_norm": 2.336852550506592, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 2.0431, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.0213713268032057, | |
| "grad_norm": 2.270529270172119, | |
| "learning_rate": 3.1859614732467954e-05, | |
| "loss": 2.0404, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.021767092114376174, | |
| "grad_norm": 1.912915587425232, | |
| "learning_rate": 2.9229249349905684e-05, | |
| "loss": 2.0207, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.02216285742554665, | |
| "grad_norm": 2.281681537628174, | |
| "learning_rate": 2.6666633838716314e-05, | |
| "loss": 2.067, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.022558622736717125, | |
| "grad_norm": 1.9110603332519531, | |
| "learning_rate": 2.418012691805191e-05, | |
| "loss": 1.9778, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.022954388047887603, | |
| "grad_norm": 1.8000211715698242, | |
| "learning_rate": 2.1777839056661554e-05, | |
| "loss": 1.9394, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.023350153359058077, | |
| "grad_norm": 1.7174650430679321, | |
| "learning_rate": 1.946760601822809e-05, | |
| "loss": 1.9967, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.023745918670228554, | |
| "grad_norm": 2.0586373805999756, | |
| "learning_rate": 1.725696330273575e-05, | |
| "loss": 1.9891, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.024141683981399032, | |
| "grad_norm": 2.5579705238342285, | |
| "learning_rate": 1.5153121567235335e-05, | |
| "loss": 1.9442, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.024537449292569506, | |
| "grad_norm": 1.8055744171142578, | |
| "learning_rate": 1.3162943106179749e-05, | |
| "loss": 1.9219, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.024933214603739984, | |
| "grad_norm": 1.803011417388916, | |
| "learning_rate": 1.1292919468045877e-05, | |
| "loss": 2.0183, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.025328979914910458, | |
| "grad_norm": 1.7811270952224731, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 1.8916, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.025724745226080935, | |
| "grad_norm": 1.733910322189331, | |
| "learning_rate": 7.937323358440935e-06, | |
| "loss": 1.9905, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.02612051053725141, | |
| "grad_norm": 1.70806086063385, | |
| "learning_rate": 6.462696144011149e-06, | |
| "loss": 1.8904, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.026516275848421887, | |
| "grad_norm": 1.6646728515625, | |
| "learning_rate": 5.13007856543209e-06, | |
| "loss": 1.9227, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.02691204115959236, | |
| "grad_norm": 1.7067934274673462, | |
| "learning_rate": 3.9438173442575e-06, | |
| "loss": 1.9334, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.02730780647076284, | |
| "grad_norm": 1.6381385326385498, | |
| "learning_rate": 2.9077818180237693e-06, | |
| "loss": 1.9143, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.027703571781933313, | |
| "grad_norm": 1.9795570373535156, | |
| "learning_rate": 2.0253513192751373e-06, | |
| "loss": 1.9075, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.02809933709310379, | |
| "grad_norm": 1.563312292098999, | |
| "learning_rate": 1.2994041528833266e-06, | |
| "loss": 1.907, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.028495102404274265, | |
| "grad_norm": 1.734750747680664, | |
| "learning_rate": 7.323082076153509e-07, | |
| "loss": 1.8587, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.028890867715444742, | |
| "grad_norm": 1.636612892150879, | |
| "learning_rate": 3.2591323257248893e-07, | |
| "loss": 1.9035, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.029286633026615216, | |
| "grad_norm": 2.093644380569458, | |
| "learning_rate": 8.15448036932176e-08, | |
| "loss": 1.9695, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.029682398337785694, | |
| "grad_norm": 1.7379897832870483, | |
| "learning_rate": 0.0, | |
| "loss": 1.8646, | |
| "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": 196236804096000.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |