| { | |
| "best_metric": 1.2362135648727417, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-300", | |
| "epoch": 0.03813912836200389, | |
| "eval_steps": 100, | |
| "global_step": 300, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0001271304278733463, | |
| "grad_norm": 0.5326213836669922, | |
| "learning_rate": 2e-05, | |
| "loss": 1.7856, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0001271304278733463, | |
| "eval_loss": 1.7346340417861938, | |
| "eval_runtime": 1249.3361, | |
| "eval_samples_per_second": 4.002, | |
| "eval_steps_per_second": 1.001, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0002542608557466926, | |
| "grad_norm": 0.5624520778656006, | |
| "learning_rate": 4e-05, | |
| "loss": 1.7626, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00038139128362003893, | |
| "grad_norm": 0.5890633463859558, | |
| "learning_rate": 6e-05, | |
| "loss": 1.739, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0005085217114933852, | |
| "grad_norm": 0.5437400937080383, | |
| "learning_rate": 8e-05, | |
| "loss": 1.6671, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0006356521393667316, | |
| "grad_norm": 0.6639446020126343, | |
| "learning_rate": 0.0001, | |
| "loss": 1.7684, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0007627825672400779, | |
| "grad_norm": 0.7031175494194031, | |
| "learning_rate": 0.00012, | |
| "loss": 1.7247, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0008899129951134241, | |
| "grad_norm": 0.5311002731323242, | |
| "learning_rate": 0.00014, | |
| "loss": 1.6195, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0010170434229867704, | |
| "grad_norm": 0.25101518630981445, | |
| "learning_rate": 0.00016, | |
| "loss": 1.5182, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0011441738508601168, | |
| "grad_norm": 0.8389205932617188, | |
| "learning_rate": 0.00018, | |
| "loss": 1.6646, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0012713042787334632, | |
| "grad_norm": 0.9317983388900757, | |
| "learning_rate": 0.0002, | |
| "loss": 1.6395, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0013984347066068094, | |
| "grad_norm": 0.48066481947898865, | |
| "learning_rate": 0.00019999832015210023, | |
| "loss": 1.5921, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0015255651344801557, | |
| "grad_norm": 0.2073744535446167, | |
| "learning_rate": 0.00019999328066483865, | |
| "loss": 1.4335, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0016526955623535021, | |
| "grad_norm": 0.22661754488945007, | |
| "learning_rate": 0.0001999848817075267, | |
| "loss": 1.477, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0017798259902268483, | |
| "grad_norm": 0.3149760663509369, | |
| "learning_rate": 0.00019997312356234386, | |
| "loss": 1.5713, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0019069564181001947, | |
| "grad_norm": 0.31392771005630493, | |
| "learning_rate": 0.00019995800662432798, | |
| "loss": 1.5414, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.002034086845973541, | |
| "grad_norm": 0.2748984396457672, | |
| "learning_rate": 0.0001999395314013622, | |
| "loss": 1.5452, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0021612172738468874, | |
| "grad_norm": 0.19064395129680634, | |
| "learning_rate": 0.00019991769851415781, | |
| "loss": 1.5742, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0022883477017202336, | |
| "grad_norm": 0.1578415036201477, | |
| "learning_rate": 0.00019989250869623343, | |
| "loss": 1.5214, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0024154781295935798, | |
| "grad_norm": 0.20229928195476532, | |
| "learning_rate": 0.0001998639627938903, | |
| "loss": 1.3921, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0025426085574669264, | |
| "grad_norm": 0.2705669403076172, | |
| "learning_rate": 0.00019983206176618388, | |
| "loss": 1.4712, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0026697389853402725, | |
| "grad_norm": 0.27215054631233215, | |
| "learning_rate": 0.00019979680668489165, | |
| "loss": 1.4969, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0027968694132136187, | |
| "grad_norm": 0.20431619882583618, | |
| "learning_rate": 0.00019975819873447717, | |
| "loss": 1.431, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0029239998410869653, | |
| "grad_norm": 0.14068549871444702, | |
| "learning_rate": 0.00019971623921205005, | |
| "loss": 1.4543, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0030511302689603115, | |
| "grad_norm": 0.1594925820827484, | |
| "learning_rate": 0.00019967092952732264, | |
| "loss": 1.364, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0031782606968336576, | |
| "grad_norm": 0.17738410830497742, | |
| "learning_rate": 0.00019962227120256252, | |
| "loss": 1.4377, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0033053911247070042, | |
| "grad_norm": 0.1752498745918274, | |
| "learning_rate": 0.00019957026587254134, | |
| "loss": 1.3827, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0034325215525803504, | |
| "grad_norm": 0.18004052340984344, | |
| "learning_rate": 0.00019951491528448004, | |
| "loss": 1.3867, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0035596519804536966, | |
| "grad_norm": 0.1525774598121643, | |
| "learning_rate": 0.00019945622129799, | |
| "loss": 1.4164, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.003686782408327043, | |
| "grad_norm": 0.1710219830274582, | |
| "learning_rate": 0.00019939418588501057, | |
| "loss": 1.4155, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.0038139128362003893, | |
| "grad_norm": 0.20903100073337555, | |
| "learning_rate": 0.000199328811129743, | |
| "loss": 1.5239, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.003941043264073736, | |
| "grad_norm": 0.18399456143379211, | |
| "learning_rate": 0.00019926009922858006, | |
| "loss": 1.3889, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.004068173691947082, | |
| "grad_norm": 0.13330113887786865, | |
| "learning_rate": 0.0001991880524900327, | |
| "loss": 1.3587, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.004195304119820428, | |
| "grad_norm": 0.13807597756385803, | |
| "learning_rate": 0.00019911267333465218, | |
| "loss": 1.4211, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.004322434547693775, | |
| "grad_norm": 0.1550034135580063, | |
| "learning_rate": 0.0001990339642949488, | |
| "loss": 1.4317, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.004449564975567121, | |
| "grad_norm": 0.1827971190214157, | |
| "learning_rate": 0.00019895192801530685, | |
| "loss": 1.4176, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.004576695403440467, | |
| "grad_norm": 0.16028065979480743, | |
| "learning_rate": 0.00019886656725189575, | |
| "loss": 1.4122, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.004703825831313814, | |
| "grad_norm": 0.14322146773338318, | |
| "learning_rate": 0.00019877788487257753, | |
| "loss": 1.423, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.0048309562591871595, | |
| "grad_norm": 0.1685505211353302, | |
| "learning_rate": 0.00019868588385681032, | |
| "loss": 1.3702, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.004958086687060506, | |
| "grad_norm": 0.1632552444934845, | |
| "learning_rate": 0.00019859056729554844, | |
| "loss": 1.3164, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.005085217114933853, | |
| "grad_norm": 0.17149530351161957, | |
| "learning_rate": 0.00019849193839113833, | |
| "loss": 1.2799, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0052123475428071985, | |
| "grad_norm": 0.14993086457252502, | |
| "learning_rate": 0.00019839000045721118, | |
| "loss": 1.3412, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.005339477970680545, | |
| "grad_norm": 0.15981823205947876, | |
| "learning_rate": 0.00019828475691857145, | |
| "loss": 1.3698, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.005466608398553892, | |
| "grad_norm": 0.15311439335346222, | |
| "learning_rate": 0.00019817621131108196, | |
| "loss": 1.3792, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.005593738826427237, | |
| "grad_norm": 0.19757720828056335, | |
| "learning_rate": 0.00019806436728154485, | |
| "loss": 1.4082, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.005720869254300584, | |
| "grad_norm": 0.15765132009983063, | |
| "learning_rate": 0.00019794922858757928, | |
| "loss": 1.282, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.005847999682173931, | |
| "grad_norm": 0.15940701961517334, | |
| "learning_rate": 0.00019783079909749515, | |
| "loss": 1.4016, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.005975130110047276, | |
| "grad_norm": 0.1622331291437149, | |
| "learning_rate": 0.00019770908279016309, | |
| "loss": 1.3624, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.006102260537920623, | |
| "grad_norm": 0.14866457879543304, | |
| "learning_rate": 0.00019758408375488071, | |
| "loss": 1.2807, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.0062293909657939696, | |
| "grad_norm": 0.16648173332214355, | |
| "learning_rate": 0.00019745580619123535, | |
| "loss": 1.3617, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.006356521393667315, | |
| "grad_norm": 0.16083629429340363, | |
| "learning_rate": 0.00019732425440896297, | |
| "loss": 1.3903, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.006483651821540662, | |
| "grad_norm": 0.18012581765651703, | |
| "learning_rate": 0.00019718943282780323, | |
| "loss": 1.3472, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.0066107822494140085, | |
| "grad_norm": 0.16914351284503937, | |
| "learning_rate": 0.00019705134597735113, | |
| "loss": 1.3765, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.006737912677287354, | |
| "grad_norm": 0.15967325866222382, | |
| "learning_rate": 0.00019690999849690484, | |
| "loss": 1.3312, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.006865043105160701, | |
| "grad_norm": 0.15996071696281433, | |
| "learning_rate": 0.00019676539513530968, | |
| "loss": 1.4227, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.006992173533034047, | |
| "grad_norm": 0.1715613752603531, | |
| "learning_rate": 0.0001966175407507987, | |
| "loss": 1.3634, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.007119303960907393, | |
| "grad_norm": 0.16633041203022003, | |
| "learning_rate": 0.00019646644031082948, | |
| "loss": 1.3279, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.00724643438878074, | |
| "grad_norm": 0.16247525811195374, | |
| "learning_rate": 0.00019631209889191712, | |
| "loss": 1.3721, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.007373564816654086, | |
| "grad_norm": 0.1603326052427292, | |
| "learning_rate": 0.00019615452167946385, | |
| "loss": 1.3212, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.007500695244527432, | |
| "grad_norm": 0.16569744050502777, | |
| "learning_rate": 0.00019599371396758456, | |
| "loss": 1.3224, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.007627825672400779, | |
| "grad_norm": 0.16010916233062744, | |
| "learning_rate": 0.0001958296811589293, | |
| "loss": 1.3022, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.007754956100274125, | |
| "grad_norm": 0.1680569052696228, | |
| "learning_rate": 0.00019566242876450137, | |
| "loss": 1.3197, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.007882086528147472, | |
| "grad_norm": 0.16432645916938782, | |
| "learning_rate": 0.00019549196240347248, | |
| "loss": 1.3167, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.008009216956020818, | |
| "grad_norm": 0.17412547767162323, | |
| "learning_rate": 0.00019531828780299383, | |
| "loss": 1.3196, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.008136347383894163, | |
| "grad_norm": 0.1736118346452713, | |
| "learning_rate": 0.0001951414107980036, | |
| "loss": 1.2966, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.00826347781176751, | |
| "grad_norm": 0.16254910826683044, | |
| "learning_rate": 0.00019496133733103112, | |
| "loss": 1.3416, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.008390608239640857, | |
| "grad_norm": 0.16831637918949127, | |
| "learning_rate": 0.00019477807345199714, | |
| "loss": 1.3396, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.008517738667514202, | |
| "grad_norm": 0.1759282648563385, | |
| "learning_rate": 0.00019459162531801046, | |
| "loss": 1.3101, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.00864486909538755, | |
| "grad_norm": 0.17314572632312775, | |
| "learning_rate": 0.00019440199919316123, | |
| "loss": 1.4026, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.008771999523260895, | |
| "grad_norm": 0.17074303328990936, | |
| "learning_rate": 0.00019420920144831044, | |
| "loss": 1.3088, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.008899129951134241, | |
| "grad_norm": 0.17773644626140594, | |
| "learning_rate": 0.0001940132385608757, | |
| "loss": 1.32, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.009026260379007589, | |
| "grad_norm": 0.1736891269683838, | |
| "learning_rate": 0.0001938141171146141, | |
| "loss": 1.2865, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.009153390806880934, | |
| "grad_norm": 0.17593072354793549, | |
| "learning_rate": 0.0001936118437994003, | |
| "loss": 1.3276, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.00928052123475428, | |
| "grad_norm": 0.16799978911876678, | |
| "learning_rate": 0.00019340642541100248, | |
| "loss": 1.2585, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.009407651662627628, | |
| "grad_norm": 0.17271657288074493, | |
| "learning_rate": 0.00019319786885085364, | |
| "loss": 1.3838, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.009534782090500973, | |
| "grad_norm": 0.18318656086921692, | |
| "learning_rate": 0.0001929861811258197, | |
| "loss": 1.3857, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.009661912518374319, | |
| "grad_norm": 0.1850346177816391, | |
| "learning_rate": 0.0001927713693479643, | |
| "loss": 1.3884, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.009789042946247667, | |
| "grad_norm": 0.1707659363746643, | |
| "learning_rate": 0.0001925534407343097, | |
| "loss": 1.2674, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.009916173374121012, | |
| "grad_norm": 0.1803124099969864, | |
| "learning_rate": 0.0001923324026065944, | |
| "loss": 1.2899, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.010043303801994358, | |
| "grad_norm": 0.18143856525421143, | |
| "learning_rate": 0.0001921082623910271, | |
| "loss": 1.2967, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.010170434229867705, | |
| "grad_norm": 0.17903882265090942, | |
| "learning_rate": 0.00019188102761803717, | |
| "loss": 1.2913, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.010297564657741051, | |
| "grad_norm": 0.181906595826149, | |
| "learning_rate": 0.00019165070592202173, | |
| "loss": 1.2568, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.010424695085614397, | |
| "grad_norm": 0.1655733585357666, | |
| "learning_rate": 0.00019141730504108922, | |
| "loss": 1.2758, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.010551825513487744, | |
| "grad_norm": 0.17457562685012817, | |
| "learning_rate": 0.00019118083281679913, | |
| "loss": 1.2506, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.01067895594136109, | |
| "grad_norm": 0.18457446992397308, | |
| "learning_rate": 0.00019094129719389886, | |
| "loss": 1.3701, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.010806086369234436, | |
| "grad_norm": 0.17702506482601166, | |
| "learning_rate": 0.0001906987062200567, | |
| "loss": 1.3071, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.010933216797107783, | |
| "grad_norm": 0.1763213723897934, | |
| "learning_rate": 0.0001904530680455914, | |
| "loss": 1.2996, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.011060347224981129, | |
| "grad_norm": 0.17649979889392853, | |
| "learning_rate": 0.0001902043909231984, | |
| "loss": 1.314, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.011187477652854475, | |
| "grad_norm": 0.1817278414964676, | |
| "learning_rate": 0.00018995268320767252, | |
| "loss": 1.315, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.011314608080727822, | |
| "grad_norm": 0.17668454349040985, | |
| "learning_rate": 0.0001896979533556273, | |
| "loss": 1.2914, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.011441738508601168, | |
| "grad_norm": 0.17107272148132324, | |
| "learning_rate": 0.0001894402099252109, | |
| "loss": 1.2884, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.011568868936474514, | |
| "grad_norm": 0.18352022767066956, | |
| "learning_rate": 0.0001891794615758185, | |
| "loss": 1.3404, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.011695999364347861, | |
| "grad_norm": 0.17999856173992157, | |
| "learning_rate": 0.00018891571706780146, | |
| "loss": 1.3001, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.011823129792221207, | |
| "grad_norm": 0.17374040186405182, | |
| "learning_rate": 0.00018864898526217293, | |
| "loss": 1.266, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.011950260220094553, | |
| "grad_norm": 0.18675245344638824, | |
| "learning_rate": 0.0001883792751203102, | |
| "loss": 1.3347, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.0120773906479679, | |
| "grad_norm": 0.18314674496650696, | |
| "learning_rate": 0.0001881065957036536, | |
| "loss": 1.3224, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.012204521075841246, | |
| "grad_norm": 0.17483913898468018, | |
| "learning_rate": 0.00018783095617340193, | |
| "loss": 1.2926, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.012331651503714592, | |
| "grad_norm": 0.19491428136825562, | |
| "learning_rate": 0.00018755236579020502, | |
| "loss": 1.2636, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.012458781931587939, | |
| "grad_norm": 0.17128659784793854, | |
| "learning_rate": 0.0001872708339138522, | |
| "loss": 1.2653, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.012585912359461285, | |
| "grad_norm": 0.172018900513649, | |
| "learning_rate": 0.00018698637000295816, | |
| "loss": 1.2686, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.01271304278733463, | |
| "grad_norm": 0.18891726434230804, | |
| "learning_rate": 0.0001866989836146449, | |
| "loss": 1.4058, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.01271304278733463, | |
| "eval_loss": 1.2906723022460938, | |
| "eval_runtime": 1258.4463, | |
| "eval_samples_per_second": 3.973, | |
| "eval_steps_per_second": 0.993, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.012840173215207978, | |
| "grad_norm": 0.1781390905380249, | |
| "learning_rate": 0.0001864086844042209, | |
| "loss": 1.3021, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.012967303643081324, | |
| "grad_norm": 0.17100100219249725, | |
| "learning_rate": 0.00018611548212485647, | |
| "loss": 1.2574, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.01309443407095467, | |
| "grad_norm": 0.18398095667362213, | |
| "learning_rate": 0.00018581938662725632, | |
| "loss": 1.2839, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.013221564498828017, | |
| "grad_norm": 0.18981115520000458, | |
| "learning_rate": 0.00018552040785932845, | |
| "loss": 1.3149, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.013348694926701363, | |
| "grad_norm": 0.18872378766536713, | |
| "learning_rate": 0.00018521855586584995, | |
| "loss": 1.279, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.013475825354574708, | |
| "grad_norm": 0.1824631690979004, | |
| "learning_rate": 0.00018491384078812959, | |
| "loss": 1.2743, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.013602955782448056, | |
| "grad_norm": 0.1971443146467209, | |
| "learning_rate": 0.000184606272863667, | |
| "loss": 1.3365, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.013730086210321402, | |
| "grad_norm": 0.19964328408241272, | |
| "learning_rate": 0.00018429586242580884, | |
| "loss": 1.3184, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.013857216638194747, | |
| "grad_norm": 0.17624543607234955, | |
| "learning_rate": 0.00018398261990340152, | |
| "loss": 1.2755, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.013984347066068095, | |
| "grad_norm": 0.18599238991737366, | |
| "learning_rate": 0.00018366655582044094, | |
| "loss": 1.3025, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.01411147749394144, | |
| "grad_norm": 0.19051305949687958, | |
| "learning_rate": 0.00018334768079571884, | |
| "loss": 1.351, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.014238607921814786, | |
| "grad_norm": 0.1858106255531311, | |
| "learning_rate": 0.00018302600554246601, | |
| "loss": 1.2386, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.014365738349688134, | |
| "grad_norm": 0.17598244547843933, | |
| "learning_rate": 0.00018270154086799239, | |
| "loss": 1.2687, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.01449286877756148, | |
| "grad_norm": 0.18105947971343994, | |
| "learning_rate": 0.00018237429767332405, | |
| "loss": 1.2843, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.014619999205434825, | |
| "grad_norm": 0.18796177208423615, | |
| "learning_rate": 0.00018204428695283687, | |
| "loss": 1.2999, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.014747129633308173, | |
| "grad_norm": 0.18702763319015503, | |
| "learning_rate": 0.00018171151979388714, | |
| "loss": 1.2391, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.014874260061181518, | |
| "grad_norm": 0.17469799518585205, | |
| "learning_rate": 0.00018137600737643913, | |
| "loss": 1.2915, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.015001390489054864, | |
| "grad_norm": 0.1871766746044159, | |
| "learning_rate": 0.00018103776097268942, | |
| "loss": 1.2429, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.015128520916928212, | |
| "grad_norm": 0.18426093459129333, | |
| "learning_rate": 0.00018069679194668826, | |
| "loss": 1.2678, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.015255651344801557, | |
| "grad_norm": 0.1830713450908661, | |
| "learning_rate": 0.0001803531117539577, | |
| "loss": 1.3231, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.015382781772674903, | |
| "grad_norm": 0.19156108796596527, | |
| "learning_rate": 0.00018000673194110668, | |
| "loss": 1.3426, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 0.01550991220054825, | |
| "grad_norm": 0.18232569098472595, | |
| "learning_rate": 0.00017965766414544326, | |
| "loss": 1.2227, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.015637042628421596, | |
| "grad_norm": 0.18696987628936768, | |
| "learning_rate": 0.00017930592009458352, | |
| "loss": 1.2933, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.015764173056294944, | |
| "grad_norm": 0.18148070573806763, | |
| "learning_rate": 0.00017895151160605757, | |
| "loss": 1.3598, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.015891303484168288, | |
| "grad_norm": 0.1859319657087326, | |
| "learning_rate": 0.00017859445058691247, | |
| "loss": 1.2688, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.016018433912041635, | |
| "grad_norm": 0.18133966624736786, | |
| "learning_rate": 0.00017823474903331233, | |
| "loss": 1.2912, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.016145564339914983, | |
| "grad_norm": 0.16695751249790192, | |
| "learning_rate": 0.0001778724190301351, | |
| "loss": 1.2772, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 0.016272694767788327, | |
| "grad_norm": 0.17694084346294403, | |
| "learning_rate": 0.0001775074727505667, | |
| "loss": 1.2998, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.016399825195661674, | |
| "grad_norm": 0.18545518815517426, | |
| "learning_rate": 0.0001771399224556919, | |
| "loss": 1.2996, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.01652695562353502, | |
| "grad_norm": 0.1763446033000946, | |
| "learning_rate": 0.00017676978049408263, | |
| "loss": 1.2942, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.016654086051408366, | |
| "grad_norm": 0.1751178801059723, | |
| "learning_rate": 0.00017639705930138272, | |
| "loss": 1.2491, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 0.016781216479281713, | |
| "grad_norm": 0.17463481426239014, | |
| "learning_rate": 0.00017602177139989044, | |
| "loss": 1.3015, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.01690834690715506, | |
| "grad_norm": 0.1884208619594574, | |
| "learning_rate": 0.0001756439293981377, | |
| "loss": 1.2555, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 0.017035477335028405, | |
| "grad_norm": 0.1824871301651001, | |
| "learning_rate": 0.00017526354599046635, | |
| "loss": 1.3321, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 0.017162607762901752, | |
| "grad_norm": 0.17852945625782013, | |
| "learning_rate": 0.00017488063395660177, | |
| "loss": 1.2134, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.0172897381907751, | |
| "grad_norm": 0.17903351783752441, | |
| "learning_rate": 0.00017449520616122344, | |
| "loss": 1.202, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.017416868618648444, | |
| "grad_norm": 0.19624289870262146, | |
| "learning_rate": 0.00017410727555353282, | |
| "loss": 1.2983, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 0.01754399904652179, | |
| "grad_norm": 0.20271572470664978, | |
| "learning_rate": 0.00017371685516681825, | |
| "loss": 1.331, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.01767112947439514, | |
| "grad_norm": 0.19160455465316772, | |
| "learning_rate": 0.00017332395811801707, | |
| "loss": 1.2325, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 0.017798259902268482, | |
| "grad_norm": 0.19286282360553741, | |
| "learning_rate": 0.00017292859760727493, | |
| "loss": 1.3632, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.01792539033014183, | |
| "grad_norm": 0.18525561690330505, | |
| "learning_rate": 0.00017253078691750227, | |
| "loss": 1.302, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 0.018052520758015177, | |
| "grad_norm": 0.17999610304832458, | |
| "learning_rate": 0.00017213053941392818, | |
| "loss": 1.2617, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 0.01817965118588852, | |
| "grad_norm": 0.1817435920238495, | |
| "learning_rate": 0.00017172786854365116, | |
| "loss": 1.285, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 0.01830678161376187, | |
| "grad_norm": 0.18393941223621368, | |
| "learning_rate": 0.00017132278783518756, | |
| "loss": 1.2033, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.018433912041635216, | |
| "grad_norm": 0.18280182778835297, | |
| "learning_rate": 0.00017091531089801694, | |
| "loss": 1.2454, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.01856104246950856, | |
| "grad_norm": 0.17269238829612732, | |
| "learning_rate": 0.00017050545142212483, | |
| "loss": 1.2137, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 0.018688172897381908, | |
| "grad_norm": 0.18515561521053314, | |
| "learning_rate": 0.00017009322317754278, | |
| "loss": 1.2876, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 0.018815303325255255, | |
| "grad_norm": 0.18649280071258545, | |
| "learning_rate": 0.0001696786400138859, | |
| "loss": 1.3279, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 0.0189424337531286, | |
| "grad_norm": 0.18008284270763397, | |
| "learning_rate": 0.00016926171585988727, | |
| "loss": 1.1943, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 0.019069564181001947, | |
| "grad_norm": 0.18855896592140198, | |
| "learning_rate": 0.00016884246472293016, | |
| "loss": 1.3458, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.019196694608875294, | |
| "grad_norm": 0.18721222877502441, | |
| "learning_rate": 0.00016842090068857742, | |
| "loss": 1.205, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 0.019323825036748638, | |
| "grad_norm": 0.18609726428985596, | |
| "learning_rate": 0.00016799703792009827, | |
| "loss": 1.3147, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 0.019450955464621986, | |
| "grad_norm": 0.18827542662620544, | |
| "learning_rate": 0.00016757089065799226, | |
| "loss": 1.2053, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 0.019578085892495333, | |
| "grad_norm": 0.19211921095848083, | |
| "learning_rate": 0.00016714247321951106, | |
| "loss": 1.2881, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 0.019705216320368677, | |
| "grad_norm": 0.1911146342754364, | |
| "learning_rate": 0.0001667117999981774, | |
| "loss": 1.2841, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.019832346748242025, | |
| "grad_norm": 0.1876746416091919, | |
| "learning_rate": 0.00016627888546330138, | |
| "loss": 1.2795, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 0.019959477176115372, | |
| "grad_norm": 0.18275220692157745, | |
| "learning_rate": 0.00016584374415949443, | |
| "loss": 1.2646, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 0.020086607603988716, | |
| "grad_norm": 0.19240595400333405, | |
| "learning_rate": 0.0001654063907061807, | |
| "loss": 1.2286, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 0.020213738031862064, | |
| "grad_norm": 0.17621144652366638, | |
| "learning_rate": 0.00016496683979710575, | |
| "loss": 1.2623, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 0.02034086845973541, | |
| "grad_norm": 0.18566247820854187, | |
| "learning_rate": 0.000164525106199843, | |
| "loss": 1.2915, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.020467998887608755, | |
| "grad_norm": 0.19843867421150208, | |
| "learning_rate": 0.00016408120475529763, | |
| "loss": 1.1703, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 0.020595129315482102, | |
| "grad_norm": 0.20230089128017426, | |
| "learning_rate": 0.00016363515037720773, | |
| "loss": 1.274, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 0.02072225974335545, | |
| "grad_norm": 0.1874382644891739, | |
| "learning_rate": 0.00016318695805164359, | |
| "loss": 1.267, | |
| "step": 163 | |
| }, | |
| { | |
| "epoch": 0.020849390171228794, | |
| "grad_norm": 0.19301468133926392, | |
| "learning_rate": 0.0001627366428365039, | |
| "loss": 1.3385, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 0.02097652059910214, | |
| "grad_norm": 0.1960678994655609, | |
| "learning_rate": 0.00016228421986101005, | |
| "loss": 1.2469, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.02110365102697549, | |
| "grad_norm": 0.2149035483598709, | |
| "learning_rate": 0.00016182970432519772, | |
| "loss": 1.2695, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 0.021230781454848833, | |
| "grad_norm": 0.1928316354751587, | |
| "learning_rate": 0.00016137311149940633, | |
| "loss": 1.2581, | |
| "step": 167 | |
| }, | |
| { | |
| "epoch": 0.02135791188272218, | |
| "grad_norm": 0.18403369188308716, | |
| "learning_rate": 0.0001609144567237658, | |
| "loss": 1.2872, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 0.021485042310595528, | |
| "grad_norm": 0.18688054382801056, | |
| "learning_rate": 0.00016045375540768136, | |
| "loss": 1.2762, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 0.021612172738468872, | |
| "grad_norm": 0.19875864684581757, | |
| "learning_rate": 0.00015999102302931585, | |
| "loss": 1.2773, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.02173930316634222, | |
| "grad_norm": 0.19474861025810242, | |
| "learning_rate": 0.0001595262751350695, | |
| "loss": 1.2329, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 0.021866433594215567, | |
| "grad_norm": 0.1946505606174469, | |
| "learning_rate": 0.00015905952733905775, | |
| "loss": 1.1726, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 0.02199356402208891, | |
| "grad_norm": 0.18479324877262115, | |
| "learning_rate": 0.00015859079532258677, | |
| "loss": 1.3177, | |
| "step": 173 | |
| }, | |
| { | |
| "epoch": 0.022120694449962258, | |
| "grad_norm": 0.19268646836280823, | |
| "learning_rate": 0.00015812009483362642, | |
| "loss": 1.2721, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 0.022247824877835606, | |
| "grad_norm": 0.18371957540512085, | |
| "learning_rate": 0.0001576474416862812, | |
| "loss": 1.3083, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.02237495530570895, | |
| "grad_norm": 0.1987624615430832, | |
| "learning_rate": 0.00015717285176025913, | |
| "loss": 1.2582, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 0.022502085733582297, | |
| "grad_norm": 0.19360652565956116, | |
| "learning_rate": 0.00015669634100033797, | |
| "loss": 1.2597, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 0.022629216161455645, | |
| "grad_norm": 0.1875244826078415, | |
| "learning_rate": 0.00015621792541582966, | |
| "loss": 1.2637, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 0.02275634658932899, | |
| "grad_norm": 0.19594229757785797, | |
| "learning_rate": 0.00015573762108004262, | |
| "loss": 1.2907, | |
| "step": 179 | |
| }, | |
| { | |
| "epoch": 0.022883477017202336, | |
| "grad_norm": 0.1935066133737564, | |
| "learning_rate": 0.00015525544412974132, | |
| "loss": 1.2446, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.023010607445075684, | |
| "grad_norm": 0.19178606569766998, | |
| "learning_rate": 0.0001547714107646046, | |
| "loss": 1.2644, | |
| "step": 181 | |
| }, | |
| { | |
| "epoch": 0.023137737872949028, | |
| "grad_norm": 0.18824580311775208, | |
| "learning_rate": 0.00015428553724668103, | |
| "loss": 1.2592, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 0.023264868300822375, | |
| "grad_norm": 0.1857818067073822, | |
| "learning_rate": 0.00015379783989984277, | |
| "loss": 1.2547, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 0.023391998728695722, | |
| "grad_norm": 0.18491147458553314, | |
| "learning_rate": 0.00015330833510923718, | |
| "loss": 1.3073, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 0.023519129156569066, | |
| "grad_norm": 0.19134363532066345, | |
| "learning_rate": 0.00015281703932073612, | |
| "loss": 1.2456, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.023646259584442414, | |
| "grad_norm": 0.18579505383968353, | |
| "learning_rate": 0.0001523239690403835, | |
| "loss": 1.2626, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 0.02377339001231576, | |
| "grad_norm": 0.18687140941619873, | |
| "learning_rate": 0.0001518291408338409, | |
| "loss": 1.2795, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 0.023900520440189105, | |
| "grad_norm": 0.1869836449623108, | |
| "learning_rate": 0.00015133257132583073, | |
| "loss": 1.2111, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 0.024027650868062453, | |
| "grad_norm": 0.18433886766433716, | |
| "learning_rate": 0.00015083427719957793, | |
| "loss": 1.1969, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 0.0241547812959358, | |
| "grad_norm": 0.19012001156806946, | |
| "learning_rate": 0.0001503342751962493, | |
| "loss": 1.2973, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.024281911723809144, | |
| "grad_norm": 0.18975861370563507, | |
| "learning_rate": 0.00014983258211439117, | |
| "loss": 1.2964, | |
| "step": 191 | |
| }, | |
| { | |
| "epoch": 0.024409042151682492, | |
| "grad_norm": 0.17685554921627045, | |
| "learning_rate": 0.0001493292148093649, | |
| "loss": 1.2763, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 0.02453617257955584, | |
| "grad_norm": 0.19333194196224213, | |
| "learning_rate": 0.00014882419019278075, | |
| "loss": 1.3203, | |
| "step": 193 | |
| }, | |
| { | |
| "epoch": 0.024663303007429183, | |
| "grad_norm": 0.19778768718242645, | |
| "learning_rate": 0.00014831752523192948, | |
| "loss": 1.3204, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 0.02479043343530253, | |
| "grad_norm": 0.1869363635778427, | |
| "learning_rate": 0.00014780923694921255, | |
| "loss": 1.2258, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.024917563863175878, | |
| "grad_norm": 0.17671674489974976, | |
| "learning_rate": 0.00014729934242157004, | |
| "loss": 1.1667, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 0.025044694291049222, | |
| "grad_norm": 0.1893490105867386, | |
| "learning_rate": 0.00014678785877990697, | |
| "loss": 1.3572, | |
| "step": 197 | |
| }, | |
| { | |
| "epoch": 0.02517182471892257, | |
| "grad_norm": 0.19606593251228333, | |
| "learning_rate": 0.00014627480320851774, | |
| "loss": 1.2507, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 0.025298955146795917, | |
| "grad_norm": 0.20087891817092896, | |
| "learning_rate": 0.00014576019294450888, | |
| "loss": 1.3149, | |
| "step": 199 | |
| }, | |
| { | |
| "epoch": 0.02542608557466926, | |
| "grad_norm": 0.1857730895280838, | |
| "learning_rate": 0.00014524404527721977, | |
| "loss": 1.2893, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.02542608557466926, | |
| "eval_loss": 1.2551084756851196, | |
| "eval_runtime": 1258.1994, | |
| "eval_samples_per_second": 3.974, | |
| "eval_steps_per_second": 0.993, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.02555321600254261, | |
| "grad_norm": 0.18368631601333618, | |
| "learning_rate": 0.00014472637754764196, | |
| "loss": 1.2125, | |
| "step": 201 | |
| }, | |
| { | |
| "epoch": 0.025680346430415956, | |
| "grad_norm": 0.18972043693065643, | |
| "learning_rate": 0.00014420720714783636, | |
| "loss": 1.2131, | |
| "step": 202 | |
| }, | |
| { | |
| "epoch": 0.0258074768582893, | |
| "grad_norm": 0.18747109174728394, | |
| "learning_rate": 0.00014368655152034908, | |
| "loss": 1.2224, | |
| "step": 203 | |
| }, | |
| { | |
| "epoch": 0.025934607286162648, | |
| "grad_norm": 0.18962696194648743, | |
| "learning_rate": 0.00014316442815762544, | |
| "loss": 1.2613, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 0.026061737714035995, | |
| "grad_norm": 0.18641987442970276, | |
| "learning_rate": 0.00014264085460142202, | |
| "loss": 1.2525, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 0.02618886814190934, | |
| "grad_norm": 0.19106072187423706, | |
| "learning_rate": 0.0001421158484422177, | |
| "loss": 1.2549, | |
| "step": 206 | |
| }, | |
| { | |
| "epoch": 0.026315998569782686, | |
| "grad_norm": 0.19771872460842133, | |
| "learning_rate": 0.0001415894273186223, | |
| "loss": 1.2612, | |
| "step": 207 | |
| }, | |
| { | |
| "epoch": 0.026443128997656034, | |
| "grad_norm": 0.18108506500720978, | |
| "learning_rate": 0.0001410616089167842, | |
| "loss": 1.2114, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 0.026570259425529378, | |
| "grad_norm": 0.17011211812496185, | |
| "learning_rate": 0.0001405324109697961, | |
| "loss": 1.2695, | |
| "step": 209 | |
| }, | |
| { | |
| "epoch": 0.026697389853402725, | |
| "grad_norm": 0.1930396556854248, | |
| "learning_rate": 0.00014000185125709918, | |
| "loss": 1.211, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.026824520281276073, | |
| "grad_norm": 0.19416122138500214, | |
| "learning_rate": 0.00013946994760388582, | |
| "loss": 1.1772, | |
| "step": 211 | |
| }, | |
| { | |
| "epoch": 0.026951650709149417, | |
| "grad_norm": 0.18353648483753204, | |
| "learning_rate": 0.00013893671788050074, | |
| "loss": 1.2672, | |
| "step": 212 | |
| }, | |
| { | |
| "epoch": 0.027078781137022764, | |
| "grad_norm": 0.18951141834259033, | |
| "learning_rate": 0.00013840218000184053, | |
| "loss": 1.3209, | |
| "step": 213 | |
| }, | |
| { | |
| "epoch": 0.027205911564896112, | |
| "grad_norm": 0.19500471651554108, | |
| "learning_rate": 0.00013786635192675184, | |
| "loss": 1.2519, | |
| "step": 214 | |
| }, | |
| { | |
| "epoch": 0.027333041992769456, | |
| "grad_norm": 0.1958056539297104, | |
| "learning_rate": 0.00013732925165742805, | |
| "loss": 1.208, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 0.027460172420642803, | |
| "grad_norm": 0.1859259307384491, | |
| "learning_rate": 0.00013679089723880427, | |
| "loss": 1.2715, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 0.02758730284851615, | |
| "grad_norm": 0.18673139810562134, | |
| "learning_rate": 0.00013625130675795134, | |
| "loss": 1.292, | |
| "step": 217 | |
| }, | |
| { | |
| "epoch": 0.027714433276389495, | |
| "grad_norm": 0.17959700524806976, | |
| "learning_rate": 0.00013571049834346799, | |
| "loss": 1.1896, | |
| "step": 218 | |
| }, | |
| { | |
| "epoch": 0.027841563704262842, | |
| "grad_norm": 0.1903347671031952, | |
| "learning_rate": 0.0001351684901648718, | |
| "loss": 1.3381, | |
| "step": 219 | |
| }, | |
| { | |
| "epoch": 0.02796869413213619, | |
| "grad_norm": 0.18993370234966278, | |
| "learning_rate": 0.00013462530043198873, | |
| "loss": 1.2739, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.028095824560009534, | |
| "grad_norm": 0.18846477568149567, | |
| "learning_rate": 0.0001340809473943415, | |
| "loss": 1.2399, | |
| "step": 221 | |
| }, | |
| { | |
| "epoch": 0.02822295498788288, | |
| "grad_norm": 0.18699532747268677, | |
| "learning_rate": 0.00013353544934053616, | |
| "loss": 1.2061, | |
| "step": 222 | |
| }, | |
| { | |
| "epoch": 0.02835008541575623, | |
| "grad_norm": 0.19469809532165527, | |
| "learning_rate": 0.00013298882459764798, | |
| "loss": 1.2455, | |
| "step": 223 | |
| }, | |
| { | |
| "epoch": 0.028477215843629573, | |
| "grad_norm": 0.19830243289470673, | |
| "learning_rate": 0.00013244109153060548, | |
| "loss": 1.2542, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 0.02860434627150292, | |
| "grad_norm": 0.20483078062534332, | |
| "learning_rate": 0.0001318922685415735, | |
| "loss": 1.2287, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.028731476699376268, | |
| "grad_norm": 0.190695121884346, | |
| "learning_rate": 0.00013134237406933492, | |
| "loss": 1.2165, | |
| "step": 226 | |
| }, | |
| { | |
| "epoch": 0.02885860712724961, | |
| "grad_norm": 0.19430223107337952, | |
| "learning_rate": 0.00013079142658867124, | |
| "loss": 1.2922, | |
| "step": 227 | |
| }, | |
| { | |
| "epoch": 0.02898573755512296, | |
| "grad_norm": 0.1994917094707489, | |
| "learning_rate": 0.00013023944460974183, | |
| "loss": 1.2402, | |
| "step": 228 | |
| }, | |
| { | |
| "epoch": 0.029112867982996306, | |
| "grad_norm": 0.20195803046226501, | |
| "learning_rate": 0.00012968644667746206, | |
| "loss": 1.2594, | |
| "step": 229 | |
| }, | |
| { | |
| "epoch": 0.02923999841086965, | |
| "grad_norm": 0.19695453345775604, | |
| "learning_rate": 0.00012913245137088024, | |
| "loss": 1.2762, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.029367128838742998, | |
| "grad_norm": 0.19726547598838806, | |
| "learning_rate": 0.00012857747730255338, | |
| "loss": 1.2494, | |
| "step": 231 | |
| }, | |
| { | |
| "epoch": 0.029494259266616345, | |
| "grad_norm": 0.19146564602851868, | |
| "learning_rate": 0.00012802154311792197, | |
| "loss": 1.2312, | |
| "step": 232 | |
| }, | |
| { | |
| "epoch": 0.02962138969448969, | |
| "grad_norm": 0.19849611818790436, | |
| "learning_rate": 0.00012746466749468345, | |
| "loss": 1.2186, | |
| "step": 233 | |
| }, | |
| { | |
| "epoch": 0.029748520122363037, | |
| "grad_norm": 0.18684804439544678, | |
| "learning_rate": 0.00012690686914216474, | |
| "loss": 1.1775, | |
| "step": 234 | |
| }, | |
| { | |
| "epoch": 0.029875650550236384, | |
| "grad_norm": 0.19955115020275116, | |
| "learning_rate": 0.0001263481668006937, | |
| "loss": 1.2476, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 0.03000278097810973, | |
| "grad_norm": 0.20034034550189972, | |
| "learning_rate": 0.00012578857924096934, | |
| "loss": 1.2307, | |
| "step": 236 | |
| }, | |
| { | |
| "epoch": 0.030129911405983076, | |
| "grad_norm": 0.1980581283569336, | |
| "learning_rate": 0.00012522812526343148, | |
| "loss": 1.2332, | |
| "step": 237 | |
| }, | |
| { | |
| "epoch": 0.030257041833856423, | |
| "grad_norm": 0.1966305524110794, | |
| "learning_rate": 0.00012466682369762882, | |
| "loss": 1.2219, | |
| "step": 238 | |
| }, | |
| { | |
| "epoch": 0.030384172261729767, | |
| "grad_norm": 0.19543439149856567, | |
| "learning_rate": 0.00012410469340158655, | |
| "loss": 1.2998, | |
| "step": 239 | |
| }, | |
| { | |
| "epoch": 0.030511302689603115, | |
| "grad_norm": 0.19517168402671814, | |
| "learning_rate": 0.00012354175326117253, | |
| "loss": 1.2451, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.030638433117476462, | |
| "grad_norm": 0.18800078332424164, | |
| "learning_rate": 0.00012297802218946306, | |
| "loss": 1.2349, | |
| "step": 241 | |
| }, | |
| { | |
| "epoch": 0.030765563545349806, | |
| "grad_norm": 0.20408718287944794, | |
| "learning_rate": 0.00012241351912610726, | |
| "loss": 1.3123, | |
| "step": 242 | |
| }, | |
| { | |
| "epoch": 0.030892693973223154, | |
| "grad_norm": 0.19570188224315643, | |
| "learning_rate": 0.00012184826303669083, | |
| "loss": 1.2181, | |
| "step": 243 | |
| }, | |
| { | |
| "epoch": 0.0310198244010965, | |
| "grad_norm": 0.1854136884212494, | |
| "learning_rate": 0.00012128227291209891, | |
| "loss": 1.2298, | |
| "step": 244 | |
| }, | |
| { | |
| "epoch": 0.031146954828969845, | |
| "grad_norm": 0.19532455503940582, | |
| "learning_rate": 0.00012071556776787786, | |
| "loss": 1.3124, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 0.03127408525684319, | |
| "grad_norm": 0.18832701444625854, | |
| "learning_rate": 0.00012014816664359671, | |
| "loss": 1.1565, | |
| "step": 246 | |
| }, | |
| { | |
| "epoch": 0.03140121568471654, | |
| "grad_norm": 0.19303160905838013, | |
| "learning_rate": 0.0001195800886022071, | |
| "loss": 1.2329, | |
| "step": 247 | |
| }, | |
| { | |
| "epoch": 0.03152834611258989, | |
| "grad_norm": 0.1881171315908432, | |
| "learning_rate": 0.0001190113527294032, | |
| "loss": 1.2456, | |
| "step": 248 | |
| }, | |
| { | |
| "epoch": 0.03165547654046323, | |
| "grad_norm": 0.19656208157539368, | |
| "learning_rate": 0.00011844197813298017, | |
| "loss": 1.2959, | |
| "step": 249 | |
| }, | |
| { | |
| "epoch": 0.031782606968336576, | |
| "grad_norm": 0.19458794593811035, | |
| "learning_rate": 0.0001178719839421925, | |
| "loss": 1.2968, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.031909737396209926, | |
| "grad_norm": 0.1953679323196411, | |
| "learning_rate": 0.00011730138930711101, | |
| "loss": 1.3225, | |
| "step": 251 | |
| }, | |
| { | |
| "epoch": 0.03203686782408327, | |
| "grad_norm": 0.18624471127986908, | |
| "learning_rate": 0.00011673021339797967, | |
| "loss": 1.2895, | |
| "step": 252 | |
| }, | |
| { | |
| "epoch": 0.032163998251956614, | |
| "grad_norm": 0.1975700408220291, | |
| "learning_rate": 0.00011615847540457157, | |
| "loss": 1.2272, | |
| "step": 253 | |
| }, | |
| { | |
| "epoch": 0.032291128679829965, | |
| "grad_norm": 0.18464815616607666, | |
| "learning_rate": 0.000115586194535544, | |
| "loss": 1.1589, | |
| "step": 254 | |
| }, | |
| { | |
| "epoch": 0.03241825910770331, | |
| "grad_norm": 0.19085770845413208, | |
| "learning_rate": 0.00011501339001779332, | |
| "loss": 1.2129, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 0.03254538953557665, | |
| "grad_norm": 0.19415773451328278, | |
| "learning_rate": 0.00011444008109580884, | |
| "loss": 1.2209, | |
| "step": 256 | |
| }, | |
| { | |
| "epoch": 0.032672519963450004, | |
| "grad_norm": 0.20239484310150146, | |
| "learning_rate": 0.00011386628703102633, | |
| "loss": 1.2872, | |
| "step": 257 | |
| }, | |
| { | |
| "epoch": 0.03279965039132335, | |
| "grad_norm": 0.18557807803153992, | |
| "learning_rate": 0.00011329202710118088, | |
| "loss": 1.2661, | |
| "step": 258 | |
| }, | |
| { | |
| "epoch": 0.03292678081919669, | |
| "grad_norm": 0.19118450582027435, | |
| "learning_rate": 0.00011271732059965925, | |
| "loss": 1.2781, | |
| "step": 259 | |
| }, | |
| { | |
| "epoch": 0.03305391124707004, | |
| "grad_norm": 0.1958242654800415, | |
| "learning_rate": 0.00011214218683485158, | |
| "loss": 1.2579, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.03318104167494339, | |
| "grad_norm": 0.1829763948917389, | |
| "learning_rate": 0.00011156664512950287, | |
| "loss": 1.2359, | |
| "step": 261 | |
| }, | |
| { | |
| "epoch": 0.03330817210281673, | |
| "grad_norm": 0.18603093922138214, | |
| "learning_rate": 0.00011099071482006361, | |
| "loss": 1.2487, | |
| "step": 262 | |
| }, | |
| { | |
| "epoch": 0.03343530253069008, | |
| "grad_norm": 0.18507151305675507, | |
| "learning_rate": 0.00011041441525604014, | |
| "loss": 1.2339, | |
| "step": 263 | |
| }, | |
| { | |
| "epoch": 0.033562432958563426, | |
| "grad_norm": 0.198081374168396, | |
| "learning_rate": 0.00010983776579934482, | |
| "loss": 1.1937, | |
| "step": 264 | |
| }, | |
| { | |
| "epoch": 0.03368956338643677, | |
| "grad_norm": 0.19567249715328217, | |
| "learning_rate": 0.00010926078582364514, | |
| "loss": 1.2447, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 0.03381669381431012, | |
| "grad_norm": 0.1892256885766983, | |
| "learning_rate": 0.00010868349471371315, | |
| "loss": 1.2011, | |
| "step": 266 | |
| }, | |
| { | |
| "epoch": 0.033943824242183465, | |
| "grad_norm": 0.19196678698062897, | |
| "learning_rate": 0.000108105911864774, | |
| "loss": 1.2341, | |
| "step": 267 | |
| }, | |
| { | |
| "epoch": 0.03407095467005681, | |
| "grad_norm": 0.20349054038524628, | |
| "learning_rate": 0.00010752805668185442, | |
| "loss": 1.2582, | |
| "step": 268 | |
| }, | |
| { | |
| "epoch": 0.03419808509793016, | |
| "grad_norm": 0.19051875174045563, | |
| "learning_rate": 0.0001069499485791307, | |
| "loss": 1.2593, | |
| "step": 269 | |
| }, | |
| { | |
| "epoch": 0.034325215525803504, | |
| "grad_norm": 0.18554829061031342, | |
| "learning_rate": 0.00010637160697927651, | |
| "loss": 1.1395, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.03445234595367685, | |
| "grad_norm": 0.18687109649181366, | |
| "learning_rate": 0.00010579305131281025, | |
| "loss": 1.2079, | |
| "step": 271 | |
| }, | |
| { | |
| "epoch": 0.0345794763815502, | |
| "grad_norm": 0.19098562002182007, | |
| "learning_rate": 0.00010521430101744239, | |
| "loss": 1.2147, | |
| "step": 272 | |
| }, | |
| { | |
| "epoch": 0.03470660680942354, | |
| "grad_norm": 0.19619682431221008, | |
| "learning_rate": 0.00010463537553742225, | |
| "loss": 1.1458, | |
| "step": 273 | |
| }, | |
| { | |
| "epoch": 0.03483373723729689, | |
| "grad_norm": 0.1930547058582306, | |
| "learning_rate": 0.00010405629432288488, | |
| "loss": 1.2704, | |
| "step": 274 | |
| }, | |
| { | |
| "epoch": 0.03496086766517024, | |
| "grad_norm": 0.19838818907737732, | |
| "learning_rate": 0.00010347707682919754, | |
| "loss": 1.2228, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.03508799809304358, | |
| "grad_norm": 0.1933777928352356, | |
| "learning_rate": 0.00010289774251630602, | |
| "loss": 1.189, | |
| "step": 276 | |
| }, | |
| { | |
| "epoch": 0.035215128520916926, | |
| "grad_norm": 0.20109447836875916, | |
| "learning_rate": 0.0001023183108480809, | |
| "loss": 1.2199, | |
| "step": 277 | |
| }, | |
| { | |
| "epoch": 0.03534225894879028, | |
| "grad_norm": 0.18909600377082825, | |
| "learning_rate": 0.00010173880129166358, | |
| "loss": 1.1529, | |
| "step": 278 | |
| }, | |
| { | |
| "epoch": 0.03546938937666362, | |
| "grad_norm": 0.18809406459331512, | |
| "learning_rate": 0.00010115923331681232, | |
| "loss": 1.2183, | |
| "step": 279 | |
| }, | |
| { | |
| "epoch": 0.035596519804536965, | |
| "grad_norm": 0.191794291138649, | |
| "learning_rate": 0.00010057962639524798, | |
| "loss": 1.2621, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.035723650232410316, | |
| "grad_norm": 0.19512364268302917, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1575, | |
| "step": 281 | |
| }, | |
| { | |
| "epoch": 0.03585078066028366, | |
| "grad_norm": 0.18720309436321259, | |
| "learning_rate": 9.942037360475205e-05, | |
| "loss": 1.2435, | |
| "step": 282 | |
| }, | |
| { | |
| "epoch": 0.035977911088157004, | |
| "grad_norm": 0.20254142582416534, | |
| "learning_rate": 9.884076668318773e-05, | |
| "loss": 1.3042, | |
| "step": 283 | |
| }, | |
| { | |
| "epoch": 0.036105041516030355, | |
| "grad_norm": 0.1859116405248642, | |
| "learning_rate": 9.826119870833643e-05, | |
| "loss": 1.2607, | |
| "step": 284 | |
| }, | |
| { | |
| "epoch": 0.0362321719439037, | |
| "grad_norm": 0.20392954349517822, | |
| "learning_rate": 9.768168915191913e-05, | |
| "loss": 1.2478, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 0.03635930237177704, | |
| "grad_norm": 0.20078176259994507, | |
| "learning_rate": 9.710225748369401e-05, | |
| "loss": 1.2359, | |
| "step": 286 | |
| }, | |
| { | |
| "epoch": 0.036486432799650394, | |
| "grad_norm": 0.1939856857061386, | |
| "learning_rate": 9.65229231708025e-05, | |
| "loss": 1.2484, | |
| "step": 287 | |
| }, | |
| { | |
| "epoch": 0.03661356322752374, | |
| "grad_norm": 0.19322216510772705, | |
| "learning_rate": 9.594370567711513e-05, | |
| "loss": 1.3249, | |
| "step": 288 | |
| }, | |
| { | |
| "epoch": 0.03674069365539708, | |
| "grad_norm": 0.1958608329296112, | |
| "learning_rate": 9.536462446257776e-05, | |
| "loss": 1.2212, | |
| "step": 289 | |
| }, | |
| { | |
| "epoch": 0.03686782408327043, | |
| "grad_norm": 0.2111774981021881, | |
| "learning_rate": 9.478569898255765e-05, | |
| "loss": 1.3251, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.03699495451114378, | |
| "grad_norm": 0.20403634011745453, | |
| "learning_rate": 9.420694868718977e-05, | |
| "loss": 1.1831, | |
| "step": 291 | |
| }, | |
| { | |
| "epoch": 0.03712208493901712, | |
| "grad_norm": 0.20421482622623444, | |
| "learning_rate": 9.362839302072354e-05, | |
| "loss": 1.2513, | |
| "step": 292 | |
| }, | |
| { | |
| "epoch": 0.03724921536689047, | |
| "grad_norm": 0.1911601573228836, | |
| "learning_rate": 9.305005142086932e-05, | |
| "loss": 1.1875, | |
| "step": 293 | |
| }, | |
| { | |
| "epoch": 0.037376345794763816, | |
| "grad_norm": 0.20054025948047638, | |
| "learning_rate": 9.247194331814562e-05, | |
| "loss": 1.214, | |
| "step": 294 | |
| }, | |
| { | |
| "epoch": 0.03750347622263716, | |
| "grad_norm": 0.198801651597023, | |
| "learning_rate": 9.1894088135226e-05, | |
| "loss": 1.1993, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 0.03763060665051051, | |
| "grad_norm": 0.1995508074760437, | |
| "learning_rate": 9.131650528628687e-05, | |
| "loss": 1.1986, | |
| "step": 296 | |
| }, | |
| { | |
| "epoch": 0.037757737078383855, | |
| "grad_norm": 0.20325009524822235, | |
| "learning_rate": 9.073921417635486e-05, | |
| "loss": 1.2292, | |
| "step": 297 | |
| }, | |
| { | |
| "epoch": 0.0378848675062572, | |
| "grad_norm": 0.193388894200325, | |
| "learning_rate": 9.016223420065519e-05, | |
| "loss": 1.2304, | |
| "step": 298 | |
| }, | |
| { | |
| "epoch": 0.03801199793413055, | |
| "grad_norm": 0.1861080676317215, | |
| "learning_rate": 8.958558474395987e-05, | |
| "loss": 1.2843, | |
| "step": 299 | |
| }, | |
| { | |
| "epoch": 0.03813912836200389, | |
| "grad_norm": 0.19273944199085236, | |
| "learning_rate": 8.900928517993644e-05, | |
| "loss": 1.111, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.03813912836200389, | |
| "eval_loss": 1.2362135648727417, | |
| "eval_runtime": 1257.3039, | |
| "eval_samples_per_second": 3.977, | |
| "eval_steps_per_second": 0.994, | |
| "step": 300 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 552, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 2, | |
| "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": 3.1092000681885696e+18, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |