| { | |
| "best_metric": 0.09180089831352234, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-150", | |
| "epoch": 0.14584346135148274, | |
| "eval_steps": 25, | |
| "global_step": 150, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0009722897423432182, | |
| "grad_norm": 0.8657536506652832, | |
| "learning_rate": 2.9999999999999997e-05, | |
| "loss": 0.2454, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0009722897423432182, | |
| "eval_loss": 0.49785929918289185, | |
| "eval_runtime": 3.5592, | |
| "eval_samples_per_second": 14.048, | |
| "eval_steps_per_second": 1.967, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0019445794846864365, | |
| "grad_norm": 0.915185272693634, | |
| "learning_rate": 5.9999999999999995e-05, | |
| "loss": 0.2505, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.002916869227029655, | |
| "grad_norm": 0.9991545081138611, | |
| "learning_rate": 8.999999999999999e-05, | |
| "loss": 0.2478, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.003889158969372873, | |
| "grad_norm": 0.44825488328933716, | |
| "learning_rate": 0.00011999999999999999, | |
| "loss": 0.21, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.004861448711716091, | |
| "grad_norm": 0.28227540850639343, | |
| "learning_rate": 0.00015, | |
| "loss": 0.1547, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00583373845405931, | |
| "grad_norm": 0.32708004117012024, | |
| "learning_rate": 0.00017999999999999998, | |
| "loss": 0.1404, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.006806028196402528, | |
| "grad_norm": 0.288328617811203, | |
| "learning_rate": 0.00020999999999999998, | |
| "loss": 0.1264, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.007778317938745746, | |
| "grad_norm": 0.25696828961372375, | |
| "learning_rate": 0.00023999999999999998, | |
| "loss": 0.1166, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.008750607681088965, | |
| "grad_norm": 0.23258011043071747, | |
| "learning_rate": 0.00027, | |
| "loss": 0.1004, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.009722897423432183, | |
| "grad_norm": 0.23922766745090485, | |
| "learning_rate": 0.0003, | |
| "loss": 0.0788, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0106951871657754, | |
| "grad_norm": 0.387058287858963, | |
| "learning_rate": 0.0002999794957488703, | |
| "loss": 0.0928, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.01166747690811862, | |
| "grad_norm": 0.17249208688735962, | |
| "learning_rate": 0.0002999179886011389, | |
| "loss": 0.074, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.012639766650461837, | |
| "grad_norm": 0.1309785097837448, | |
| "learning_rate": 0.0002998154953722457, | |
| "loss": 0.0584, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.013612056392805057, | |
| "grad_norm": 0.1812700778245926, | |
| "learning_rate": 0.00029967204408281613, | |
| "loss": 0.0645, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.014584346135148274, | |
| "grad_norm": 0.12967181205749512, | |
| "learning_rate": 0.00029948767395100045, | |
| "loss": 0.0599, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.015556635877491492, | |
| "grad_norm": 0.12690943479537964, | |
| "learning_rate": 0.0002992624353817517, | |
| "loss": 0.0532, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.01652892561983471, | |
| "grad_norm": 0.14767378568649292, | |
| "learning_rate": 0.0002989963899530457, | |
| "loss": 0.0614, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.01750121536217793, | |
| "grad_norm": 0.11901306360960007, | |
| "learning_rate": 0.00029868961039904624, | |
| "loss": 0.0528, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.018473505104521146, | |
| "grad_norm": 0.13424420356750488, | |
| "learning_rate": 0.00029834218059022024, | |
| "loss": 0.0627, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.019445794846864366, | |
| "grad_norm": 0.13712000846862793, | |
| "learning_rate": 0.00029795419551040833, | |
| "loss": 0.0539, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.020418084589207585, | |
| "grad_norm": 0.16320212185382843, | |
| "learning_rate": 0.00029752576123085736, | |
| "loss": 0.0543, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0213903743315508, | |
| "grad_norm": 0.11892902851104736, | |
| "learning_rate": 0.0002970569948812214, | |
| "loss": 0.0406, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.02236266407389402, | |
| "grad_norm": 0.17433710396289825, | |
| "learning_rate": 0.0002965480246175399, | |
| "loss": 0.0654, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.02333495381623724, | |
| "grad_norm": 0.18646477162837982, | |
| "learning_rate": 0.0002959989895872009, | |
| "loss": 0.0608, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.024307243558580455, | |
| "grad_norm": 0.16546477377414703, | |
| "learning_rate": 0.0002954100398908995, | |
| "loss": 0.07, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.024307243558580455, | |
| "eval_loss": 0.12305433303117752, | |
| "eval_runtime": 3.8062, | |
| "eval_samples_per_second": 13.136, | |
| "eval_steps_per_second": 1.839, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.025279533300923675, | |
| "grad_norm": 0.156415656208992, | |
| "learning_rate": 0.0002947813365416023, | |
| "loss": 0.0802, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.026251823043266894, | |
| "grad_norm": 0.1979251652956009, | |
| "learning_rate": 0.0002941130514205272, | |
| "loss": 0.1002, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.027224112785610113, | |
| "grad_norm": 0.153579980134964, | |
| "learning_rate": 0.0002934053672301536, | |
| "loss": 0.0814, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.02819640252795333, | |
| "grad_norm": 0.2506410479545593, | |
| "learning_rate": 0.00029265847744427303, | |
| "loss": 0.0807, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.02916869227029655, | |
| "grad_norm": 0.1667831689119339, | |
| "learning_rate": 0.00029187258625509513, | |
| "loss": 0.0692, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.030140982012639768, | |
| "grad_norm": 0.1767091304063797, | |
| "learning_rate": 0.00029104790851742417, | |
| "loss": 0.0929, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.031113271754982984, | |
| "grad_norm": 0.1997700184583664, | |
| "learning_rate": 0.0002901846696899191, | |
| "loss": 0.1169, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.03208556149732621, | |
| "grad_norm": 0.4836466610431671, | |
| "learning_rate": 0.00028928310577345606, | |
| "loss": 0.1228, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.03305785123966942, | |
| "grad_norm": 0.20822934806346893, | |
| "learning_rate": 0.0002883434632466077, | |
| "loss": 0.1195, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.03403014098201264, | |
| "grad_norm": 0.2419443577528, | |
| "learning_rate": 0.00028736599899825856, | |
| "loss": 0.1413, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.03500243072435586, | |
| "grad_norm": 0.3413419723510742, | |
| "learning_rate": 0.00028635098025737434, | |
| "loss": 0.1595, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.03597472046669908, | |
| "grad_norm": 0.30608636140823364, | |
| "learning_rate": 0.00028529868451994384, | |
| "loss": 0.1827, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.03694701020904229, | |
| "grad_norm": 0.30667898058891296, | |
| "learning_rate": 0.0002842093994731145, | |
| "loss": 0.161, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.037919299951385516, | |
| "grad_norm": 0.3554874360561371, | |
| "learning_rate": 0.00028308342291654174, | |
| "loss": 0.1801, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.03889158969372873, | |
| "grad_norm": 0.3086106777191162, | |
| "learning_rate": 0.00028192106268097334, | |
| "loss": 0.1888, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.03986387943607195, | |
| "grad_norm": 0.26156407594680786, | |
| "learning_rate": 0.00028072263654409154, | |
| "loss": 0.1606, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.04083616917841517, | |
| "grad_norm": 0.35756373405456543, | |
| "learning_rate": 0.0002794884721436361, | |
| "loss": 0.2412, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.041808458920758386, | |
| "grad_norm": 0.3686249852180481, | |
| "learning_rate": 0.00027821890688783083, | |
| "loss": 0.2308, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.0427807486631016, | |
| "grad_norm": 0.4308541417121887, | |
| "learning_rate": 0.0002769142878631403, | |
| "loss": 0.2267, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.043753038405444825, | |
| "grad_norm": 0.5061919093132019, | |
| "learning_rate": 0.00027557497173937923, | |
| "loss": 0.3109, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.04472532814778804, | |
| "grad_norm": 0.43579161167144775, | |
| "learning_rate": 0.000274201324672203, | |
| "loss": 0.2456, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.045697617890131256, | |
| "grad_norm": 0.6933690905570984, | |
| "learning_rate": 0.00027279372220300385, | |
| "loss": 0.4574, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.04666990763247448, | |
| "grad_norm": 0.6277015209197998, | |
| "learning_rate": 0.0002713525491562421, | |
| "loss": 0.4584, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.047642197374817695, | |
| "grad_norm": 0.8218262195587158, | |
| "learning_rate": 0.00026987819953423867, | |
| "loss": 0.5391, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.04861448711716091, | |
| "grad_norm": 1.0224953889846802, | |
| "learning_rate": 0.00026837107640945905, | |
| "loss": 0.5288, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.04861448711716091, | |
| "eval_loss": 0.1336946040391922, | |
| "eval_runtime": 4.0118, | |
| "eval_samples_per_second": 12.463, | |
| "eval_steps_per_second": 1.745, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.049586776859504134, | |
| "grad_norm": 1.1134988069534302, | |
| "learning_rate": 0.0002668315918143169, | |
| "loss": 0.114, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.05055906660184735, | |
| "grad_norm": 0.23551532626152039, | |
| "learning_rate": 0.00026526016662852886, | |
| "loss": 0.0835, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.051531356344190565, | |
| "grad_norm": 0.24570299685001373, | |
| "learning_rate": 0.00026365723046405023, | |
| "loss": 0.0685, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.05250364608653379, | |
| "grad_norm": 0.19383001327514648, | |
| "learning_rate": 0.0002620232215476231, | |
| "loss": 0.05, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.053475935828877004, | |
| "grad_norm": 0.23110246658325195, | |
| "learning_rate": 0.0002603585866009697, | |
| "loss": 0.0522, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.05444822557122023, | |
| "grad_norm": 0.18834188580513, | |
| "learning_rate": 0.00025866378071866334, | |
| "loss": 0.0732, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.05542051531356344, | |
| "grad_norm": 0.14947369694709778, | |
| "learning_rate": 0.00025693926724370956, | |
| "loss": 0.0514, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.05639280505590666, | |
| "grad_norm": 0.13261213898658752, | |
| "learning_rate": 0.00025518551764087326, | |
| "loss": 0.0529, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.05736509479824988, | |
| "grad_norm": 0.2039453238248825, | |
| "learning_rate": 0.00025340301136778483, | |
| "loss": 0.0555, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.0583373845405931, | |
| "grad_norm": 0.18386036157608032, | |
| "learning_rate": 0.00025159223574386114, | |
| "loss": 0.067, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.05930967428293631, | |
| "grad_norm": 0.11324752122163773, | |
| "learning_rate": 0.0002497536858170772, | |
| "loss": 0.0413, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.060281964025279536, | |
| "grad_norm": 0.11208714544773102, | |
| "learning_rate": 0.00024788786422862526, | |
| "loss": 0.0496, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.06125425376762275, | |
| "grad_norm": 0.09385313838720322, | |
| "learning_rate": 0.00024599528107549745, | |
| "loss": 0.047, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.06222654350996597, | |
| "grad_norm": 0.08256314694881439, | |
| "learning_rate": 0.00024407645377103054, | |
| "loss": 0.0368, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.06319883325230918, | |
| "grad_norm": 0.08847391605377197, | |
| "learning_rate": 0.00024213190690345018, | |
| "loss": 0.0375, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.06417112299465241, | |
| "grad_norm": 0.1306406408548355, | |
| "learning_rate": 0.00024016217209245374, | |
| "loss": 0.048, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.06514341273699563, | |
| "grad_norm": 0.11775556206703186, | |
| "learning_rate": 0.00023816778784387094, | |
| "loss": 0.042, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.06611570247933884, | |
| "grad_norm": 0.08764883130788803, | |
| "learning_rate": 0.0002361492994024415, | |
| "loss": 0.0364, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.06708799222168206, | |
| "grad_norm": 0.12429194152355194, | |
| "learning_rate": 0.0002341072586027509, | |
| "loss": 0.0485, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.06806028196402528, | |
| "grad_norm": 0.09290876984596252, | |
| "learning_rate": 0.00023204222371836405, | |
| "loss": 0.0435, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.06903257170636849, | |
| "grad_norm": 0.11098179966211319, | |
| "learning_rate": 0.00022995475930919905, | |
| "loss": 0.0558, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.07000486144871172, | |
| "grad_norm": 0.11447007209062576, | |
| "learning_rate": 0.00022784543606718227, | |
| "loss": 0.0694, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.07097715119105494, | |
| "grad_norm": 0.09141000360250473, | |
| "learning_rate": 0.00022571483066022657, | |
| "loss": 0.038, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.07194944093339815, | |
| "grad_norm": 0.109103262424469, | |
| "learning_rate": 0.0002235635255745762, | |
| "loss": 0.0489, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.07292173067574137, | |
| "grad_norm": 0.1455768644809723, | |
| "learning_rate": 0.00022139210895556104, | |
| "loss": 0.0818, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.07292173067574137, | |
| "eval_loss": 0.10055980086326599, | |
| "eval_runtime": 3.9854, | |
| "eval_samples_per_second": 12.546, | |
| "eval_steps_per_second": 1.756, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.07389402041808459, | |
| "grad_norm": 0.15560583770275116, | |
| "learning_rate": 0.00021920117444680317, | |
| "loss": 0.094, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.0748663101604278, | |
| "grad_norm": 0.15243405103683472, | |
| "learning_rate": 0.00021699132102792097, | |
| "loss": 0.0811, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.07583859990277103, | |
| "grad_norm": 0.14389897882938385, | |
| "learning_rate": 0.0002147631528507739, | |
| "loss": 0.0955, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.07681088964511425, | |
| "grad_norm": 0.21825049817562103, | |
| "learning_rate": 0.00021251727907429355, | |
| "loss": 0.1112, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.07778317938745746, | |
| "grad_norm": 0.18719053268432617, | |
| "learning_rate": 0.0002102543136979454, | |
| "loss": 0.1203, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.07875546912980068, | |
| "grad_norm": 0.2221420407295227, | |
| "learning_rate": 0.0002079748753938678, | |
| "loss": 0.162, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.0797277588721439, | |
| "grad_norm": 0.17710459232330322, | |
| "learning_rate": 0.0002056795873377331, | |
| "loss": 0.0792, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.08070004861448711, | |
| "grad_norm": 0.2508675754070282, | |
| "learning_rate": 0.00020336907703837748, | |
| "loss": 0.1702, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.08167233835683034, | |
| "grad_norm": 0.34161412715911865, | |
| "learning_rate": 0.00020104397616624645, | |
| "loss": 0.1894, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.08264462809917356, | |
| "grad_norm": 0.22855708003044128, | |
| "learning_rate": 0.00019870492038070252, | |
| "loss": 0.1288, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.08361691784151677, | |
| "grad_norm": 0.24569354951381683, | |
| "learning_rate": 0.0001963525491562421, | |
| "loss": 0.1454, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.08458920758385999, | |
| "grad_norm": 0.2825170159339905, | |
| "learning_rate": 0.0001939875056076697, | |
| "loss": 0.1396, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.0855614973262032, | |
| "grad_norm": 0.3594852685928345, | |
| "learning_rate": 0.00019161043631427666, | |
| "loss": 0.1615, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.08653378706854643, | |
| "grad_norm": 0.35308271646499634, | |
| "learning_rate": 0.00018922199114307294, | |
| "loss": 0.2612, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.08750607681088965, | |
| "grad_norm": 0.36867859959602356, | |
| "learning_rate": 0.00018682282307111987, | |
| "loss": 0.2518, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.08847836655323287, | |
| "grad_norm": 0.3401321470737457, | |
| "learning_rate": 0.00018441358800701273, | |
| "loss": 0.2185, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.08945065629557608, | |
| "grad_norm": 0.3880937397480011, | |
| "learning_rate": 0.00018199494461156203, | |
| "loss": 0.2246, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.0904229460379193, | |
| "grad_norm": 0.3770473897457123, | |
| "learning_rate": 0.000179567554117722, | |
| "loss": 0.1804, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.09139523578026251, | |
| "grad_norm": 0.31104758381843567, | |
| "learning_rate": 0.00017713208014981648, | |
| "loss": 0.1733, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.09236752552260574, | |
| "grad_norm": 0.4791819453239441, | |
| "learning_rate": 0.00017468918854211007, | |
| "loss": 0.2412, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.09333981526494896, | |
| "grad_norm": 0.45134127140045166, | |
| "learning_rate": 0.00017223954715677627, | |
| "loss": 0.2741, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.09431210500729217, | |
| "grad_norm": 0.5456284880638123, | |
| "learning_rate": 0.00016978382570131034, | |
| "loss": 0.4073, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.09528439474963539, | |
| "grad_norm": 0.6170369982719421, | |
| "learning_rate": 0.00016732269554543794, | |
| "loss": 0.3737, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.0962566844919786, | |
| "grad_norm": 0.6821739673614502, | |
| "learning_rate": 0.00016485682953756942, | |
| "loss": 0.4857, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.09722897423432182, | |
| "grad_norm": 0.7691540122032166, | |
| "learning_rate": 0.00016238690182084986, | |
| "loss": 0.4505, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.09722897423432182, | |
| "eval_loss": 0.09960367530584335, | |
| "eval_runtime": 3.9183, | |
| "eval_samples_per_second": 12.76, | |
| "eval_steps_per_second": 1.786, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.09820126397666505, | |
| "grad_norm": 0.1519579142332077, | |
| "learning_rate": 0.0001599135876488549, | |
| "loss": 0.06, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.09917355371900827, | |
| "grad_norm": 0.1643187403678894, | |
| "learning_rate": 0.00015743756320098332, | |
| "loss": 0.0632, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.10014584346135148, | |
| "grad_norm": 0.11599410325288773, | |
| "learning_rate": 0.0001549595053975962, | |
| "loss": 0.0648, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.1011181332036947, | |
| "grad_norm": 0.12460173666477203, | |
| "learning_rate": 0.00015248009171495378, | |
| "loss": 0.0614, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.10209042294603791, | |
| "grad_norm": 0.07840460538864136, | |
| "learning_rate": 0.00015, | |
| "loss": 0.0461, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.10306271268838113, | |
| "grad_norm": 0.09137758612632751, | |
| "learning_rate": 0.00014751990828504622, | |
| "loss": 0.047, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.10403500243072436, | |
| "grad_norm": 0.08994504064321518, | |
| "learning_rate": 0.00014504049460240375, | |
| "loss": 0.0392, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.10500729217306758, | |
| "grad_norm": 0.0770004540681839, | |
| "learning_rate": 0.00014256243679901663, | |
| "loss": 0.0453, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.10597958191541079, | |
| "grad_norm": 0.08238277584314346, | |
| "learning_rate": 0.00014008641235114508, | |
| "loss": 0.0397, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.10695187165775401, | |
| "grad_norm": 0.12823158502578735, | |
| "learning_rate": 0.00013761309817915014, | |
| "loss": 0.0375, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.10792416140009722, | |
| "grad_norm": 0.07921775430440903, | |
| "learning_rate": 0.00013514317046243058, | |
| "loss": 0.0399, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.10889645114244045, | |
| "grad_norm": 0.09790435433387756, | |
| "learning_rate": 0.00013267730445456208, | |
| "loss": 0.0307, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.10986874088478367, | |
| "grad_norm": 0.09248471260070801, | |
| "learning_rate": 0.00013021617429868963, | |
| "loss": 0.0403, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.11084103062712689, | |
| "grad_norm": 0.09994786232709885, | |
| "learning_rate": 0.00012776045284322368, | |
| "loss": 0.0428, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.1118133203694701, | |
| "grad_norm": 0.08010675758123398, | |
| "learning_rate": 0.00012531081145788987, | |
| "loss": 0.0354, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.11278561011181332, | |
| "grad_norm": 0.11402561515569687, | |
| "learning_rate": 0.00012286791985018355, | |
| "loss": 0.059, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.11375789985415653, | |
| "grad_norm": 0.08841165900230408, | |
| "learning_rate": 0.00012043244588227796, | |
| "loss": 0.0342, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.11473018959649976, | |
| "grad_norm": 0.08822940289974213, | |
| "learning_rate": 0.00011800505538843798, | |
| "loss": 0.0445, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.11570247933884298, | |
| "grad_norm": 0.1175551563501358, | |
| "learning_rate": 0.00011558641199298727, | |
| "loss": 0.0471, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.1166747690811862, | |
| "grad_norm": 0.15154576301574707, | |
| "learning_rate": 0.00011317717692888012, | |
| "loss": 0.079, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.11764705882352941, | |
| "grad_norm": 0.10886827856302261, | |
| "learning_rate": 0.00011077800885692702, | |
| "loss": 0.0548, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 0.11861934856587263, | |
| "grad_norm": 0.1060369536280632, | |
| "learning_rate": 0.00010838956368572334, | |
| "loss": 0.042, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.11959163830821584, | |
| "grad_norm": 0.11565347760915756, | |
| "learning_rate": 0.0001060124943923303, | |
| "loss": 0.0596, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.12056392805055907, | |
| "grad_norm": 0.11722910404205322, | |
| "learning_rate": 0.0001036474508437579, | |
| "loss": 0.0562, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.12153621779290229, | |
| "grad_norm": 0.12110079824924469, | |
| "learning_rate": 0.00010129507961929748, | |
| "loss": 0.0742, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.12153621779290229, | |
| "eval_loss": 0.09679846465587616, | |
| "eval_runtime": 4.0215, | |
| "eval_samples_per_second": 12.433, | |
| "eval_steps_per_second": 1.741, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.1225085075352455, | |
| "grad_norm": 0.0917026549577713, | |
| "learning_rate": 9.895602383375353e-05, | |
| "loss": 0.0453, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.12348079727758872, | |
| "grad_norm": 0.18777845799922943, | |
| "learning_rate": 9.663092296162251e-05, | |
| "loss": 0.0661, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 0.12445308701993194, | |
| "grad_norm": 0.10484489798545837, | |
| "learning_rate": 9.432041266226686e-05, | |
| "loss": 0.0516, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.12542537676227516, | |
| "grad_norm": 0.14925585687160492, | |
| "learning_rate": 9.202512460613219e-05, | |
| "loss": 0.0574, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.12639766650461837, | |
| "grad_norm": 0.12964065372943878, | |
| "learning_rate": 8.97456863020546e-05, | |
| "loss": 0.084, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.1273699562469616, | |
| "grad_norm": 0.14066071808338165, | |
| "learning_rate": 8.748272092570646e-05, | |
| "loss": 0.0826, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 0.12834224598930483, | |
| "grad_norm": 0.17143459618091583, | |
| "learning_rate": 8.523684714922608e-05, | |
| "loss": 0.1232, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.12931453573164803, | |
| "grad_norm": 0.14534994959831238, | |
| "learning_rate": 8.300867897207903e-05, | |
| "loss": 0.0783, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 0.13028682547399126, | |
| "grad_norm": 0.17438603937625885, | |
| "learning_rate": 8.079882555319684e-05, | |
| "loss": 0.1032, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 0.13125911521633446, | |
| "grad_norm": 0.21413007378578186, | |
| "learning_rate": 7.860789104443896e-05, | |
| "loss": 0.1421, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.1322314049586777, | |
| "grad_norm": 0.20025412738323212, | |
| "learning_rate": 7.643647442542382e-05, | |
| "loss": 0.1545, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.1332036947010209, | |
| "grad_norm": 0.22498586773872375, | |
| "learning_rate": 7.428516933977347e-05, | |
| "loss": 0.1427, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 0.13417598444336412, | |
| "grad_norm": 0.22663052380084991, | |
| "learning_rate": 7.215456393281776e-05, | |
| "loss": 0.1396, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.13514827418570735, | |
| "grad_norm": 0.23404861986637115, | |
| "learning_rate": 7.004524069080096e-05, | |
| "loss": 0.1501, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 0.13612056392805055, | |
| "grad_norm": 0.3112930953502655, | |
| "learning_rate": 6.795777628163599e-05, | |
| "loss": 0.1979, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.13709285367039378, | |
| "grad_norm": 0.38309967517852783, | |
| "learning_rate": 6.58927413972491e-05, | |
| "loss": 0.2962, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 0.13806514341273698, | |
| "grad_norm": 0.3294512927532196, | |
| "learning_rate": 6.385070059755846e-05, | |
| "loss": 0.1978, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 0.13903743315508021, | |
| "grad_norm": 0.3819890320301056, | |
| "learning_rate": 6.183221215612904e-05, | |
| "loss": 0.2528, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 0.14000972289742344, | |
| "grad_norm": 0.4122176170349121, | |
| "learning_rate": 5.983782790754623e-05, | |
| "loss": 0.2841, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.14098201263976665, | |
| "grad_norm": 0.4129266142845154, | |
| "learning_rate": 5.786809309654982e-05, | |
| "loss": 0.2905, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.14195430238210988, | |
| "grad_norm": 0.47997596859931946, | |
| "learning_rate": 5.592354622896944e-05, | |
| "loss": 0.3009, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 0.14292659212445308, | |
| "grad_norm": 0.5365499258041382, | |
| "learning_rate": 5.40047189245025e-05, | |
| "loss": 0.3335, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 0.1438988818667963, | |
| "grad_norm": 0.5594547390937805, | |
| "learning_rate": 5.211213577137469e-05, | |
| "loss": 0.3667, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 0.14487117160913954, | |
| "grad_norm": 0.778071939945221, | |
| "learning_rate": 5.024631418292274e-05, | |
| "loss": 0.5081, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 0.14584346135148274, | |
| "grad_norm": 0.9648370146751404, | |
| "learning_rate": 4.840776425613886e-05, | |
| "loss": 0.533, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.14584346135148274, | |
| "eval_loss": 0.09180089831352234, | |
| "eval_runtime": 3.7999, | |
| "eval_samples_per_second": 13.158, | |
| "eval_steps_per_second": 1.842, | |
| "step": 150 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 8.748837118358323e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |