| { | |
| "best_metric": 10.293888092041016, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-200", | |
| "epoch": 0.03175532521918617, | |
| "eval_steps": 25, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00015877662609593086, | |
| "grad_norm": 0.07810629904270172, | |
| "learning_rate": 2.9999999999999997e-05, | |
| "loss": 10.3764, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00015877662609593086, | |
| "eval_loss": 10.363986015319824, | |
| "eval_runtime": 0.0965, | |
| "eval_samples_per_second": 518.162, | |
| "eval_steps_per_second": 72.543, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00031755325219186173, | |
| "grad_norm": 0.061406999826431274, | |
| "learning_rate": 5.9999999999999995e-05, | |
| "loss": 10.3633, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00047632987828779254, | |
| "grad_norm": 0.05004843696951866, | |
| "learning_rate": 8.999999999999999e-05, | |
| "loss": 10.3681, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0006351065043837235, | |
| "grad_norm": 0.05747171863913536, | |
| "learning_rate": 0.00011999999999999999, | |
| "loss": 10.3682, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0007938831304796542, | |
| "grad_norm": 0.05080826207995415, | |
| "learning_rate": 0.00015, | |
| "loss": 10.3647, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0009526597565755851, | |
| "grad_norm": 0.046676479279994965, | |
| "learning_rate": 0.00017999999999999998, | |
| "loss": 10.3577, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.001111436382671516, | |
| "grad_norm": 0.046294715255498886, | |
| "learning_rate": 0.00020999999999999998, | |
| "loss": 10.366, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.001270213008767447, | |
| "grad_norm": 0.04639292135834694, | |
| "learning_rate": 0.00023999999999999998, | |
| "loss": 10.3691, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0014289896348633777, | |
| "grad_norm": 0.04217684268951416, | |
| "learning_rate": 0.00027, | |
| "loss": 10.3534, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0015877662609593084, | |
| "grad_norm": 0.04545888677239418, | |
| "learning_rate": 0.0003, | |
| "loss": 10.3577, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0017465428870552394, | |
| "grad_norm": 0.045676153153181076, | |
| "learning_rate": 0.0002999794957488703, | |
| "loss": 10.3567, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0019053195131511701, | |
| "grad_norm": 0.044181909412145615, | |
| "learning_rate": 0.0002999179886011389, | |
| "loss": 10.3612, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.002064096139247101, | |
| "grad_norm": 0.04575149342417717, | |
| "learning_rate": 0.0002998154953722457, | |
| "loss": 10.3539, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.002222872765343032, | |
| "grad_norm": 0.04331066459417343, | |
| "learning_rate": 0.00029967204408281613, | |
| "loss": 10.357, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.002381649391438963, | |
| "grad_norm": 0.04593302682042122, | |
| "learning_rate": 0.00029948767395100045, | |
| "loss": 10.3536, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.002540426017534894, | |
| "grad_norm": 0.046111367642879486, | |
| "learning_rate": 0.0002992624353817517, | |
| "loss": 10.3586, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0026992026436308244, | |
| "grad_norm": 0.05106338486075401, | |
| "learning_rate": 0.0002989963899530457, | |
| "loss": 10.3551, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0028579792697267553, | |
| "grad_norm": 0.052090976387262344, | |
| "learning_rate": 0.00029868961039904624, | |
| "loss": 10.3548, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0030167558958226863, | |
| "grad_norm": 0.04916371405124664, | |
| "learning_rate": 0.00029834218059022024, | |
| "loss": 10.3536, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.003175532521918617, | |
| "grad_norm": 0.05516723915934563, | |
| "learning_rate": 0.00029795419551040833, | |
| "loss": 10.3551, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.003334309148014548, | |
| "grad_norm": 0.053350552916526794, | |
| "learning_rate": 0.00029752576123085736, | |
| "loss": 10.3571, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.003493085774110479, | |
| "grad_norm": 0.05715618655085564, | |
| "learning_rate": 0.0002970569948812214, | |
| "loss": 10.3542, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0036518624002064098, | |
| "grad_norm": 0.06765611469745636, | |
| "learning_rate": 0.0002965480246175399, | |
| "loss": 10.349, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0038106390263023403, | |
| "grad_norm": 0.06198740378022194, | |
| "learning_rate": 0.0002959989895872009, | |
| "loss": 10.3561, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.003969415652398271, | |
| "grad_norm": 0.05947557091712952, | |
| "learning_rate": 0.0002954100398908995, | |
| "loss": 10.3525, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.003969415652398271, | |
| "eval_loss": 10.353515625, | |
| "eval_runtime": 0.0934, | |
| "eval_samples_per_second": 535.238, | |
| "eval_steps_per_second": 74.933, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.004128192278494202, | |
| "grad_norm": 0.071525439620018, | |
| "learning_rate": 0.0002947813365416023, | |
| "loss": 10.3526, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.004286968904590133, | |
| "grad_norm": 0.07154348492622375, | |
| "learning_rate": 0.0002941130514205272, | |
| "loss": 10.3504, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.004445745530686064, | |
| "grad_norm": 0.06603620201349258, | |
| "learning_rate": 0.0002934053672301536, | |
| "loss": 10.3462, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.004604522156781995, | |
| "grad_norm": 0.07479649782180786, | |
| "learning_rate": 0.00029265847744427303, | |
| "loss": 10.3493, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.004763298782877926, | |
| "grad_norm": 0.0767395943403244, | |
| "learning_rate": 0.00029187258625509513, | |
| "loss": 10.349, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.004922075408973856, | |
| "grad_norm": 0.07685164362192154, | |
| "learning_rate": 0.00029104790851742417, | |
| "loss": 10.3495, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.005080852035069788, | |
| "grad_norm": 0.08169625699520111, | |
| "learning_rate": 0.0002901846696899191, | |
| "loss": 10.3573, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.005239628661165718, | |
| "grad_norm": 0.07723478972911835, | |
| "learning_rate": 0.00028928310577345606, | |
| "loss": 10.3489, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.005398405287261649, | |
| "grad_norm": 0.0714058205485344, | |
| "learning_rate": 0.0002883434632466077, | |
| "loss": 10.344, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.00555718191335758, | |
| "grad_norm": 0.07186929881572723, | |
| "learning_rate": 0.00028736599899825856, | |
| "loss": 10.3461, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.005715958539453511, | |
| "grad_norm": 0.07883802056312561, | |
| "learning_rate": 0.00028635098025737434, | |
| "loss": 10.3465, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.005874735165549441, | |
| "grad_norm": 0.07939917594194412, | |
| "learning_rate": 0.00028529868451994384, | |
| "loss": 10.3391, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.006033511791645373, | |
| "grad_norm": 0.07693421095609665, | |
| "learning_rate": 0.0002842093994731145, | |
| "loss": 10.3466, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.006192288417741303, | |
| "grad_norm": 0.08108057081699371, | |
| "learning_rate": 0.00028308342291654174, | |
| "loss": 10.3399, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.006351065043837234, | |
| "grad_norm": 0.07625582814216614, | |
| "learning_rate": 0.00028192106268097334, | |
| "loss": 10.3424, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.006509841669933165, | |
| "grad_norm": 0.08772553503513336, | |
| "learning_rate": 0.00028072263654409154, | |
| "loss": 10.3357, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.006668618296029096, | |
| "grad_norm": 0.09969928115606308, | |
| "learning_rate": 0.0002794884721436361, | |
| "loss": 10.3313, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.006827394922125027, | |
| "grad_norm": 0.10627187043428421, | |
| "learning_rate": 0.00027821890688783083, | |
| "loss": 10.334, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.006986171548220958, | |
| "grad_norm": 0.11822281032800674, | |
| "learning_rate": 0.0002769142878631403, | |
| "loss": 10.3403, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.007144948174316888, | |
| "grad_norm": 0.13020247220993042, | |
| "learning_rate": 0.00027557497173937923, | |
| "loss": 10.3354, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0073037248004128195, | |
| "grad_norm": 0.153047114610672, | |
| "learning_rate": 0.000274201324672203, | |
| "loss": 10.3254, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.00746250142650875, | |
| "grad_norm": 0.18278735876083374, | |
| "learning_rate": 0.00027279372220300385, | |
| "loss": 10.3353, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.007621278052604681, | |
| "grad_norm": 0.2163456678390503, | |
| "learning_rate": 0.0002713525491562421, | |
| "loss": 10.3213, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.007780054678700612, | |
| "grad_norm": 0.16671767830848694, | |
| "learning_rate": 0.00026987819953423867, | |
| "loss": 10.3174, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.007938831304796543, | |
| "grad_norm": 0.22391104698181152, | |
| "learning_rate": 0.00026837107640945905, | |
| "loss": 10.3147, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.007938831304796543, | |
| "eval_loss": 10.32917594909668, | |
| "eval_runtime": 0.0932, | |
| "eval_samples_per_second": 536.364, | |
| "eval_steps_per_second": 75.091, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.008097607930892474, | |
| "grad_norm": 0.1727171391248703, | |
| "learning_rate": 0.0002668315918143169, | |
| "loss": 10.3255, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.008256384556988404, | |
| "grad_norm": 0.1261977106332779, | |
| "learning_rate": 0.00026526016662852886, | |
| "loss": 10.3373, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.008415161183084335, | |
| "grad_norm": 0.19324587285518646, | |
| "learning_rate": 0.00026365723046405023, | |
| "loss": 10.3299, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.008573937809180266, | |
| "grad_norm": 0.16581648588180542, | |
| "learning_rate": 0.0002620232215476231, | |
| "loss": 10.3303, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.008732714435276196, | |
| "grad_norm": 0.16929411888122559, | |
| "learning_rate": 0.0002603585866009697, | |
| "loss": 10.3314, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.008891491061372127, | |
| "grad_norm": 0.14727461338043213, | |
| "learning_rate": 0.00025866378071866334, | |
| "loss": 10.3248, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.009050267687468059, | |
| "grad_norm": 0.1087571531534195, | |
| "learning_rate": 0.00025693926724370956, | |
| "loss": 10.325, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.00920904431356399, | |
| "grad_norm": 0.09721245616674423, | |
| "learning_rate": 0.00025518551764087326, | |
| "loss": 10.3173, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.00936782093965992, | |
| "grad_norm": 0.08206453919410706, | |
| "learning_rate": 0.00025340301136778483, | |
| "loss": 10.3209, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.009526597565755851, | |
| "grad_norm": 0.09024045616388321, | |
| "learning_rate": 0.00025159223574386114, | |
| "loss": 10.3219, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.009685374191851783, | |
| "grad_norm": 0.07984571903944016, | |
| "learning_rate": 0.0002497536858170772, | |
| "loss": 10.3224, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.009844150817947712, | |
| "grad_norm": 0.11346311867237091, | |
| "learning_rate": 0.00024788786422862526, | |
| "loss": 10.3194, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.010002927444043644, | |
| "grad_norm": 0.10196421295404434, | |
| "learning_rate": 0.00024599528107549745, | |
| "loss": 10.3233, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.010161704070139575, | |
| "grad_norm": 0.11686540395021439, | |
| "learning_rate": 0.00024407645377103054, | |
| "loss": 10.3199, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.010320480696235505, | |
| "grad_norm": 0.10796058177947998, | |
| "learning_rate": 0.00024213190690345018, | |
| "loss": 10.3213, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.010479257322331436, | |
| "grad_norm": 0.10543781518936157, | |
| "learning_rate": 0.00024016217209245374, | |
| "loss": 10.3191, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.010638033948427368, | |
| "grad_norm": 0.1500771939754486, | |
| "learning_rate": 0.00023816778784387094, | |
| "loss": 10.3217, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.010796810574523297, | |
| "grad_norm": 0.13386686146259308, | |
| "learning_rate": 0.0002361492994024415, | |
| "loss": 10.3224, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.010955587200619229, | |
| "grad_norm": 0.17342054843902588, | |
| "learning_rate": 0.0002341072586027509, | |
| "loss": 10.3188, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.01111436382671516, | |
| "grad_norm": 0.1327526718378067, | |
| "learning_rate": 0.00023204222371836405, | |
| "loss": 10.3154, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.01127314045281109, | |
| "grad_norm": 0.15230214595794678, | |
| "learning_rate": 0.00022995475930919905, | |
| "loss": 10.3179, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.011431917078907021, | |
| "grad_norm": 0.1093672513961792, | |
| "learning_rate": 0.00022784543606718227, | |
| "loss": 10.3217, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.011590693705002953, | |
| "grad_norm": 0.10216083377599716, | |
| "learning_rate": 0.00022571483066022657, | |
| "loss": 10.321, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.011749470331098882, | |
| "grad_norm": 0.11733946949243546, | |
| "learning_rate": 0.0002235635255745762, | |
| "loss": 10.3107, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.011908246957194814, | |
| "grad_norm": 0.1087634265422821, | |
| "learning_rate": 0.00022139210895556104, | |
| "loss": 10.3107, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.011908246957194814, | |
| "eval_loss": 10.310944557189941, | |
| "eval_runtime": 0.0928, | |
| "eval_samples_per_second": 538.899, | |
| "eval_steps_per_second": 75.446, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.012067023583290745, | |
| "grad_norm": 0.09749813377857208, | |
| "learning_rate": 0.00021920117444680317, | |
| "loss": 10.3223, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.012225800209386675, | |
| "grad_norm": 0.08614695817232132, | |
| "learning_rate": 0.00021699132102792097, | |
| "loss": 10.3191, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.012384576835482606, | |
| "grad_norm": 0.10386686772108078, | |
| "learning_rate": 0.0002147631528507739, | |
| "loss": 10.3194, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.012543353461578538, | |
| "grad_norm": 0.09013906866312027, | |
| "learning_rate": 0.00021251727907429355, | |
| "loss": 10.3176, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.012702130087674467, | |
| "grad_norm": 0.12356393784284592, | |
| "learning_rate": 0.0002102543136979454, | |
| "loss": 10.3124, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.012860906713770399, | |
| "grad_norm": 0.11175656318664551, | |
| "learning_rate": 0.0002079748753938678, | |
| "loss": 10.313, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.01301968333986633, | |
| "grad_norm": 0.10210341215133667, | |
| "learning_rate": 0.0002056795873377331, | |
| "loss": 10.3088, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.013178459965962262, | |
| "grad_norm": 0.11279959231615067, | |
| "learning_rate": 0.00020336907703837748, | |
| "loss": 10.3101, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.013337236592058191, | |
| "grad_norm": 0.09707577526569366, | |
| "learning_rate": 0.00020104397616624645, | |
| "loss": 10.3137, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.013496013218154123, | |
| "grad_norm": 0.0997617170214653, | |
| "learning_rate": 0.00019870492038070252, | |
| "loss": 10.3163, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.013654789844250054, | |
| "grad_norm": 0.12623490393161774, | |
| "learning_rate": 0.0001963525491562421, | |
| "loss": 10.3136, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.013813566470345984, | |
| "grad_norm": 0.10603071749210358, | |
| "learning_rate": 0.0001939875056076697, | |
| "loss": 10.308, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.013972343096441915, | |
| "grad_norm": 0.10383056104183197, | |
| "learning_rate": 0.00019161043631427666, | |
| "loss": 10.3122, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.014131119722537847, | |
| "grad_norm": 0.11057064682245255, | |
| "learning_rate": 0.00018922199114307294, | |
| "loss": 10.317, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.014289896348633776, | |
| "grad_norm": 0.1066858321428299, | |
| "learning_rate": 0.00018682282307111987, | |
| "loss": 10.3097, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.014448672974729708, | |
| "grad_norm": 0.08680516481399536, | |
| "learning_rate": 0.00018441358800701273, | |
| "loss": 10.3105, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.014607449600825639, | |
| "grad_norm": 0.10082846879959106, | |
| "learning_rate": 0.00018199494461156203, | |
| "loss": 10.3076, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.014766226226921569, | |
| "grad_norm": 0.11305494606494904, | |
| "learning_rate": 0.000179567554117722, | |
| "loss": 10.3123, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.0149250028530175, | |
| "grad_norm": 0.09946515411138535, | |
| "learning_rate": 0.00017713208014981648, | |
| "loss": 10.2971, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.015083779479113432, | |
| "grad_norm": 0.11427634954452515, | |
| "learning_rate": 0.00017468918854211007, | |
| "loss": 10.3018, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.015242556105209361, | |
| "grad_norm": 0.11798146367073059, | |
| "learning_rate": 0.00017223954715677627, | |
| "loss": 10.3051, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.015401332731305293, | |
| "grad_norm": 0.13001081347465515, | |
| "learning_rate": 0.00016978382570131034, | |
| "loss": 10.2983, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.015560109357401224, | |
| "grad_norm": 0.11518680304288864, | |
| "learning_rate": 0.00016732269554543794, | |
| "loss": 10.3018, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.015718885983497154, | |
| "grad_norm": 0.15253396332263947, | |
| "learning_rate": 0.00016485682953756942, | |
| "loss": 10.2871, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.015877662609593085, | |
| "grad_norm": 0.20822547376155853, | |
| "learning_rate": 0.00016238690182084986, | |
| "loss": 10.288, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.015877662609593085, | |
| "eval_loss": 10.301692008972168, | |
| "eval_runtime": 0.0933, | |
| "eval_samples_per_second": 535.978, | |
| "eval_steps_per_second": 75.037, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.016036439235689016, | |
| "grad_norm": 0.24361427128314972, | |
| "learning_rate": 0.0001599135876488549, | |
| "loss": 10.3028, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.016195215861784948, | |
| "grad_norm": 0.23904871940612793, | |
| "learning_rate": 0.00015743756320098332, | |
| "loss": 10.2934, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.01635399248788088, | |
| "grad_norm": 0.19915081560611725, | |
| "learning_rate": 0.0001549595053975962, | |
| "loss": 10.3083, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.016512769113976807, | |
| "grad_norm": 0.15487897396087646, | |
| "learning_rate": 0.00015248009171495378, | |
| "loss": 10.3023, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.01667154574007274, | |
| "grad_norm": 0.17113174498081207, | |
| "learning_rate": 0.00015, | |
| "loss": 10.2996, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.01683032236616867, | |
| "grad_norm": 0.12119137495756149, | |
| "learning_rate": 0.00014751990828504622, | |
| "loss": 10.3016, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.0169890989922646, | |
| "grad_norm": 0.15259002149105072, | |
| "learning_rate": 0.00014504049460240375, | |
| "loss": 10.2929, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.017147875618360533, | |
| "grad_norm": 0.11336802691221237, | |
| "learning_rate": 0.00014256243679901663, | |
| "loss": 10.2947, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.017306652244456464, | |
| "grad_norm": 0.10615869611501694, | |
| "learning_rate": 0.00014008641235114508, | |
| "loss": 10.2989, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.017465428870552392, | |
| "grad_norm": 0.10214941948652267, | |
| "learning_rate": 0.00013761309817915014, | |
| "loss": 10.2982, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.017624205496648324, | |
| "grad_norm": 0.07917061448097229, | |
| "learning_rate": 0.00013514317046243058, | |
| "loss": 10.2973, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.017782982122744255, | |
| "grad_norm": 0.11092983931303024, | |
| "learning_rate": 0.00013267730445456208, | |
| "loss": 10.2984, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.017941758748840186, | |
| "grad_norm": 0.08627593517303467, | |
| "learning_rate": 0.00013021617429868963, | |
| "loss": 10.2967, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.018100535374936118, | |
| "grad_norm": 0.10853682458400726, | |
| "learning_rate": 0.00012776045284322368, | |
| "loss": 10.3083, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.01825931200103205, | |
| "grad_norm": 0.08355826884508133, | |
| "learning_rate": 0.00012531081145788987, | |
| "loss": 10.3039, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.01841808862712798, | |
| "grad_norm": 0.12834160029888153, | |
| "learning_rate": 0.00012286791985018355, | |
| "loss": 10.3058, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.01857686525322391, | |
| "grad_norm": 0.10183387994766235, | |
| "learning_rate": 0.00012043244588227796, | |
| "loss": 10.3207, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.01873564187931984, | |
| "grad_norm": 0.0810333862900734, | |
| "learning_rate": 0.00011800505538843798, | |
| "loss": 10.3022, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.01889441850541577, | |
| "grad_norm": 0.11709333211183548, | |
| "learning_rate": 0.00011558641199298727, | |
| "loss": 10.3086, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.019053195131511703, | |
| "grad_norm": 0.06999313831329346, | |
| "learning_rate": 0.00011317717692888012, | |
| "loss": 10.3066, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.019211971757607634, | |
| "grad_norm": 0.0975615531206131, | |
| "learning_rate": 0.00011077800885692702, | |
| "loss": 10.3069, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 0.019370748383703566, | |
| "grad_norm": 0.08743242919445038, | |
| "learning_rate": 0.00010838956368572334, | |
| "loss": 10.3202, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.019529525009799494, | |
| "grad_norm": 0.12698757648468018, | |
| "learning_rate": 0.0001060124943923303, | |
| "loss": 10.2906, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.019688301635895425, | |
| "grad_norm": 0.06964551657438278, | |
| "learning_rate": 0.0001036474508437579, | |
| "loss": 10.3047, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.019847078261991356, | |
| "grad_norm": 0.0764366015791893, | |
| "learning_rate": 0.00010129507961929748, | |
| "loss": 10.2964, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.019847078261991356, | |
| "eval_loss": 10.29774284362793, | |
| "eval_runtime": 0.0936, | |
| "eval_samples_per_second": 534.393, | |
| "eval_steps_per_second": 74.815, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.020005854888087288, | |
| "grad_norm": 0.08608151227235794, | |
| "learning_rate": 9.895602383375353e-05, | |
| "loss": 10.2955, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.02016463151418322, | |
| "grad_norm": 0.08954727649688721, | |
| "learning_rate": 9.663092296162251e-05, | |
| "loss": 10.3007, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 0.02032340814027915, | |
| "grad_norm": 0.10686002671718597, | |
| "learning_rate": 9.432041266226686e-05, | |
| "loss": 10.3021, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.02048218476637508, | |
| "grad_norm": 0.08813920617103577, | |
| "learning_rate": 9.202512460613219e-05, | |
| "loss": 10.3064, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.02064096139247101, | |
| "grad_norm": 0.07965640723705292, | |
| "learning_rate": 8.97456863020546e-05, | |
| "loss": 10.299, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.02079973801856694, | |
| "grad_norm": 0.09392104297876358, | |
| "learning_rate": 8.748272092570646e-05, | |
| "loss": 10.2917, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 0.020958514644662873, | |
| "grad_norm": 0.08309674263000488, | |
| "learning_rate": 8.523684714922608e-05, | |
| "loss": 10.2916, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.021117291270758804, | |
| "grad_norm": 0.09519728273153305, | |
| "learning_rate": 8.300867897207903e-05, | |
| "loss": 10.3004, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 0.021276067896854736, | |
| "grad_norm": 0.06975460052490234, | |
| "learning_rate": 8.079882555319684e-05, | |
| "loss": 10.3025, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 0.021434844522950663, | |
| "grad_norm": 0.07696589082479477, | |
| "learning_rate": 7.860789104443896e-05, | |
| "loss": 10.2976, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.021593621149046595, | |
| "grad_norm": 0.10613939166069031, | |
| "learning_rate": 7.643647442542382e-05, | |
| "loss": 10.3022, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.021752397775142526, | |
| "grad_norm": 0.11416519433259964, | |
| "learning_rate": 7.428516933977347e-05, | |
| "loss": 10.3094, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 0.021911174401238458, | |
| "grad_norm": 0.0883881077170372, | |
| "learning_rate": 7.215456393281776e-05, | |
| "loss": 10.2996, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.02206995102733439, | |
| "grad_norm": 0.10318446159362793, | |
| "learning_rate": 7.004524069080096e-05, | |
| "loss": 10.3031, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 0.02222872765343032, | |
| "grad_norm": 0.10122831910848618, | |
| "learning_rate": 6.795777628163599e-05, | |
| "loss": 10.2992, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.022387504279526252, | |
| "grad_norm": 0.0863846093416214, | |
| "learning_rate": 6.58927413972491e-05, | |
| "loss": 10.307, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 0.02254628090562218, | |
| "grad_norm": 0.10809484869241714, | |
| "learning_rate": 6.385070059755846e-05, | |
| "loss": 10.3024, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 0.02270505753171811, | |
| "grad_norm": 0.0929742157459259, | |
| "learning_rate": 6.183221215612904e-05, | |
| "loss": 10.2905, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 0.022863834157814043, | |
| "grad_norm": 0.11549130827188492, | |
| "learning_rate": 5.983782790754623e-05, | |
| "loss": 10.2985, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.023022610783909974, | |
| "grad_norm": 0.13555151224136353, | |
| "learning_rate": 5.786809309654982e-05, | |
| "loss": 10.2905, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.023181387410005905, | |
| "grad_norm": 0.08594315499067307, | |
| "learning_rate": 5.592354622896944e-05, | |
| "loss": 10.2922, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 0.023340164036101837, | |
| "grad_norm": 0.1327342391014099, | |
| "learning_rate": 5.40047189245025e-05, | |
| "loss": 10.2812, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 0.023498940662197765, | |
| "grad_norm": 0.09222450852394104, | |
| "learning_rate": 5.211213577137469e-05, | |
| "loss": 10.2914, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 0.023657717288293696, | |
| "grad_norm": 0.12407458573579788, | |
| "learning_rate": 5.024631418292274e-05, | |
| "loss": 10.2818, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 0.023816493914389628, | |
| "grad_norm": 0.10363201797008514, | |
| "learning_rate": 4.840776425613886e-05, | |
| "loss": 10.2824, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.023816493914389628, | |
| "eval_loss": 10.295632362365723, | |
| "eval_runtime": 0.093, | |
| "eval_samples_per_second": 537.649, | |
| "eval_steps_per_second": 75.271, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.02397527054048556, | |
| "grad_norm": 0.23319634795188904, | |
| "learning_rate": 4.659698863221513e-05, | |
| "loss": 10.2971, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 0.02413404716658149, | |
| "grad_norm": 0.17366944253444672, | |
| "learning_rate": 4.481448235912671e-05, | |
| "loss": 10.2898, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 0.024292823792677422, | |
| "grad_norm": 0.1751234531402588, | |
| "learning_rate": 4.306073275629044e-05, | |
| "loss": 10.2979, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 0.02445160041877335, | |
| "grad_norm": 0.20233570039272308, | |
| "learning_rate": 4.133621928133665e-05, | |
| "loss": 10.2901, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 0.02461037704486928, | |
| "grad_norm": 0.2154175490140915, | |
| "learning_rate": 3.964141339903026e-05, | |
| "loss": 10.2894, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.024769153670965213, | |
| "grad_norm": 0.15442685782909393, | |
| "learning_rate": 3.797677845237696e-05, | |
| "loss": 10.297, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 0.024927930297061144, | |
| "grad_norm": 0.12210218608379364, | |
| "learning_rate": 3.634276953594982e-05, | |
| "loss": 10.2925, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 0.025086706923157075, | |
| "grad_norm": 0.10777822881937027, | |
| "learning_rate": 3.473983337147118e-05, | |
| "loss": 10.2849, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 0.025245483549253007, | |
| "grad_norm": 0.07246610522270203, | |
| "learning_rate": 3.316840818568315e-05, | |
| "loss": 10.2933, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 0.025404260175348935, | |
| "grad_norm": 0.08766282349824905, | |
| "learning_rate": 3.162892359054098e-05, | |
| "loss": 10.2998, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.025563036801444866, | |
| "grad_norm": 0.06367377191781998, | |
| "learning_rate": 3.0121800465761293e-05, | |
| "loss": 10.3024, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 0.025721813427540798, | |
| "grad_norm": 0.10457596927881241, | |
| "learning_rate": 2.8647450843757897e-05, | |
| "loss": 10.289, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 0.02588059005363673, | |
| "grad_norm": 0.0702897310256958, | |
| "learning_rate": 2.7206277796996144e-05, | |
| "loss": 10.3078, | |
| "step": 163 | |
| }, | |
| { | |
| "epoch": 0.02603936667973266, | |
| "grad_norm": 0.09472493827342987, | |
| "learning_rate": 2.5798675327796993e-05, | |
| "loss": 10.2987, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 0.026198143305828592, | |
| "grad_norm": 0.08356080204248428, | |
| "learning_rate": 2.4425028260620715e-05, | |
| "loss": 10.3073, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.026356919931924523, | |
| "grad_norm": 0.06730841100215912, | |
| "learning_rate": 2.3085712136859668e-05, | |
| "loss": 10.3081, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 0.02651569655802045, | |
| "grad_norm": 0.07436297088861465, | |
| "learning_rate": 2.178109311216913e-05, | |
| "loss": 10.3148, | |
| "step": 167 | |
| }, | |
| { | |
| "epoch": 0.026674473184116382, | |
| "grad_norm": 0.09109427034854889, | |
| "learning_rate": 2.0511527856363912e-05, | |
| "loss": 10.2942, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 0.026833249810212314, | |
| "grad_norm": 0.07138719409704208, | |
| "learning_rate": 1.927736345590839e-05, | |
| "loss": 10.2939, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 0.026992026436308245, | |
| "grad_norm": 0.0833205133676529, | |
| "learning_rate": 1.8078937319026654e-05, | |
| "loss": 10.3001, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.027150803062404177, | |
| "grad_norm": 0.08817581087350845, | |
| "learning_rate": 1.6916577083458228e-05, | |
| "loss": 10.3022, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 0.027309579688500108, | |
| "grad_norm": 0.08368958532810211, | |
| "learning_rate": 1.579060052688548e-05, | |
| "loss": 10.3065, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 0.027468356314596036, | |
| "grad_norm": 0.11247318983078003, | |
| "learning_rate": 1.4701315480056164e-05, | |
| "loss": 10.3019, | |
| "step": 173 | |
| }, | |
| { | |
| "epoch": 0.027627132940691967, | |
| "grad_norm": 0.10502248257398605, | |
| "learning_rate": 1.3649019742625623e-05, | |
| "loss": 10.3019, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 0.0277859095667879, | |
| "grad_norm": 0.0866779237985611, | |
| "learning_rate": 1.2634001001741373e-05, | |
| "loss": 10.3097, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.0277859095667879, | |
| "eval_loss": 10.29531478881836, | |
| "eval_runtime": 0.0934, | |
| "eval_samples_per_second": 535.372, | |
| "eval_steps_per_second": 74.952, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.02794468619288383, | |
| "grad_norm": 0.0854175016283989, | |
| "learning_rate": 1.1656536753392287e-05, | |
| "loss": 10.3084, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 0.02810346281897976, | |
| "grad_norm": 0.07053595036268234, | |
| "learning_rate": 1.0716894226543953e-05, | |
| "loss": 10.3021, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 0.028262239445075693, | |
| "grad_norm": 0.07512841373682022, | |
| "learning_rate": 9.815330310080887e-06, | |
| "loss": 10.3039, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 0.02842101607117162, | |
| "grad_norm": 0.06513608247041702, | |
| "learning_rate": 8.952091482575824e-06, | |
| "loss": 10.2931, | |
| "step": 179 | |
| }, | |
| { | |
| "epoch": 0.028579792697267552, | |
| "grad_norm": 0.0893177017569542, | |
| "learning_rate": 8.127413744904804e-06, | |
| "loss": 10.2949, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.028738569323363484, | |
| "grad_norm": 0.0912618339061737, | |
| "learning_rate": 7.34152255572697e-06, | |
| "loss": 10.2961, | |
| "step": 181 | |
| }, | |
| { | |
| "epoch": 0.028897345949459415, | |
| "grad_norm": 0.07610266655683517, | |
| "learning_rate": 6.594632769846353e-06, | |
| "loss": 10.3046, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 0.029056122575555347, | |
| "grad_norm": 0.07157953828573227, | |
| "learning_rate": 5.886948579472778e-06, | |
| "loss": 10.3041, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 0.029214899201651278, | |
| "grad_norm": 0.07713142782449722, | |
| "learning_rate": 5.218663458397715e-06, | |
| "loss": 10.2997, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 0.02937367582774721, | |
| "grad_norm": 0.07938244193792343, | |
| "learning_rate": 4.589960109100444e-06, | |
| "loss": 10.3044, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.029532452453843137, | |
| "grad_norm": 0.11273758113384247, | |
| "learning_rate": 4.001010412799138e-06, | |
| "loss": 10.306, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 0.02969122907993907, | |
| "grad_norm": 0.08427654206752777, | |
| "learning_rate": 3.451975382460109e-06, | |
| "loss": 10.3039, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 0.029850005706035, | |
| "grad_norm": 0.09040991216897964, | |
| "learning_rate": 2.9430051187785962e-06, | |
| "loss": 10.2942, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 0.03000878233213093, | |
| "grad_norm": 0.0981961265206337, | |
| "learning_rate": 2.4742387691426445e-06, | |
| "loss": 10.296, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 0.030167558958226863, | |
| "grad_norm": 0.06700126826763153, | |
| "learning_rate": 2.0458044895916513e-06, | |
| "loss": 10.3013, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.030326335584322794, | |
| "grad_norm": 0.07272301614284515, | |
| "learning_rate": 1.6578194097797258e-06, | |
| "loss": 10.2967, | |
| "step": 191 | |
| }, | |
| { | |
| "epoch": 0.030485112210418722, | |
| "grad_norm": 0.10850653797388077, | |
| "learning_rate": 1.3103896009537207e-06, | |
| "loss": 10.2957, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 0.030643888836514654, | |
| "grad_norm": 0.08605331182479858, | |
| "learning_rate": 1.0036100469542786e-06, | |
| "loss": 10.2992, | |
| "step": 193 | |
| }, | |
| { | |
| "epoch": 0.030802665462610585, | |
| "grad_norm": 0.08742884546518326, | |
| "learning_rate": 7.375646182482875e-07, | |
| "loss": 10.2881, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 0.030961442088706517, | |
| "grad_norm": 0.12425903230905533, | |
| "learning_rate": 5.123260489995229e-07, | |
| "loss": 10.3004, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.031120218714802448, | |
| "grad_norm": 0.14287036657333374, | |
| "learning_rate": 3.2795591718381975e-07, | |
| "loss": 10.2931, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 0.031278995340898376, | |
| "grad_norm": 0.10366120934486389, | |
| "learning_rate": 1.8450462775428942e-07, | |
| "loss": 10.2972, | |
| "step": 197 | |
| }, | |
| { | |
| "epoch": 0.03143777196699431, | |
| "grad_norm": 0.14705786108970642, | |
| "learning_rate": 8.201139886109264e-08, | |
| "loss": 10.2905, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 0.03159654859309024, | |
| "grad_norm": 0.10673689842224121, | |
| "learning_rate": 2.0504251129649374e-08, | |
| "loss": 10.288, | |
| "step": 199 | |
| }, | |
| { | |
| "epoch": 0.03175532521918617, | |
| "grad_norm": 0.14931601285934448, | |
| "learning_rate": 0.0, | |
| "loss": 10.2792, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.03175532521918617, | |
| "eval_loss": 10.293888092041016, | |
| "eval_runtime": 0.0926, | |
| "eval_samples_per_second": 539.938, | |
| "eval_steps_per_second": 75.591, | |
| "step": 200 | |
| } | |
| ], | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 22228539801600.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |