| { | |
| "best_metric": 2.8960378170013428, | |
| "best_model_checkpoint": "outputs-6_7/checkpoint-64000", | |
| "epoch": 2.7480548923964756, | |
| "eval_steps": 4000, | |
| "global_step": 64000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.021469178846847466, | |
| "grad_norm": 0.39146578311920166, | |
| "learning_rate": 0.00029989693820586593, | |
| "loss": 2.4186, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.04293835769369493, | |
| "grad_norm": 0.5122425556182861, | |
| "learning_rate": 0.0002997681109631983, | |
| "loss": 2.3709, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.0644075365405424, | |
| "grad_norm": 0.4298762083053589, | |
| "learning_rate": 0.0002996392837205307, | |
| "loss": 2.3735, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.08587671538738986, | |
| "grad_norm": 0.39066824316978455, | |
| "learning_rate": 0.00029951045647786317, | |
| "loss": 2.3524, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.10734589423423734, | |
| "grad_norm": 0.39771586656570435, | |
| "learning_rate": 0.00029938162923519556, | |
| "loss": 2.347, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.1288150730810848, | |
| "grad_norm": 0.47568196058273315, | |
| "learning_rate": 0.000299252801992528, | |
| "loss": 2.3336, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.15028425192793227, | |
| "grad_norm": 0.44162309169769287, | |
| "learning_rate": 0.0002991239747498604, | |
| "loss": 2.334, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.17175343077477973, | |
| "grad_norm": 0.4031461179256439, | |
| "learning_rate": 0.0002989951475071928, | |
| "loss": 2.3266, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.17175343077477973, | |
| "eval_loss": 3.0375378131866455, | |
| "eval_runtime": 174.8485, | |
| "eval_samples_per_second": 14.298, | |
| "eval_steps_per_second": 3.575, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.19322260962162718, | |
| "grad_norm": 0.384034126996994, | |
| "learning_rate": 0.00029886632026452525, | |
| "loss": 2.3344, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.21469178846847467, | |
| "grad_norm": 0.44177886843681335, | |
| "learning_rate": 0.00029873749302185764, | |
| "loss": 2.3157, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.23616096731532213, | |
| "grad_norm": 0.4425281286239624, | |
| "learning_rate": 0.0002986086657791901, | |
| "loss": 2.3232, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.2576301461621696, | |
| "grad_norm": 0.4302816390991211, | |
| "learning_rate": 0.0002984798385365225, | |
| "loss": 2.3141, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.2790993250090171, | |
| "grad_norm": 0.5806054472923279, | |
| "learning_rate": 0.00029835101129385493, | |
| "loss": 2.2975, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 0.30056850385586453, | |
| "grad_norm": 0.5654121041297913, | |
| "learning_rate": 0.00029822218405118733, | |
| "loss": 2.3141, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.322037682702712, | |
| "grad_norm": 0.5454065203666687, | |
| "learning_rate": 0.0002980933568085197, | |
| "loss": 2.3097, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 0.34350686154955945, | |
| "grad_norm": 0.43060022592544556, | |
| "learning_rate": 0.00029796452956585217, | |
| "loss": 2.308, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.34350686154955945, | |
| "eval_loss": 3.0060064792633057, | |
| "eval_runtime": 171.3325, | |
| "eval_samples_per_second": 14.592, | |
| "eval_steps_per_second": 3.648, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.3649760403964069, | |
| "grad_norm": 0.490461140871048, | |
| "learning_rate": 0.00029783570232318456, | |
| "loss": 2.2985, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 0.38644521924325437, | |
| "grad_norm": 0.5096587538719177, | |
| "learning_rate": 0.000297706875080517, | |
| "loss": 2.3041, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.4079143980901018, | |
| "grad_norm": 0.4906415343284607, | |
| "learning_rate": 0.0002975780478378494, | |
| "loss": 2.2903, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 0.42938357693694934, | |
| "grad_norm": 0.5885447263717651, | |
| "learning_rate": 0.00029744922059518186, | |
| "loss": 2.3069, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.4508527557837968, | |
| "grad_norm": 0.5200388431549072, | |
| "learning_rate": 0.00029732039335251425, | |
| "loss": 2.3025, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 0.47232193463064426, | |
| "grad_norm": 0.6331049799919128, | |
| "learning_rate": 0.00029719156610984664, | |
| "loss": 2.2957, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 0.4937911134774917, | |
| "grad_norm": 0.5442560315132141, | |
| "learning_rate": 0.0002970627388671791, | |
| "loss": 2.2878, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 0.5152602923243392, | |
| "grad_norm": 0.5305426120758057, | |
| "learning_rate": 0.0002969339116245115, | |
| "loss": 2.2903, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 0.5152602923243392, | |
| "eval_loss": 2.973823070526123, | |
| "eval_runtime": 170.1319, | |
| "eval_samples_per_second": 14.694, | |
| "eval_steps_per_second": 3.674, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 0.5367294711711866, | |
| "grad_norm": 0.5756106972694397, | |
| "learning_rate": 0.0002968050843818439, | |
| "loss": 2.2883, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 0.5581986500180341, | |
| "grad_norm": 0.5812390446662903, | |
| "learning_rate": 0.00029667625713917633, | |
| "loss": 2.2807, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 0.5796678288648816, | |
| "grad_norm": 0.4355560541152954, | |
| "learning_rate": 0.0002965474298965088, | |
| "loss": 2.2885, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 0.6011370077117291, | |
| "grad_norm": 0.41715824604034424, | |
| "learning_rate": 0.00029641860265384117, | |
| "loss": 2.2834, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 0.6226061865585765, | |
| "grad_norm": 0.4623817801475525, | |
| "learning_rate": 0.00029628977541117357, | |
| "loss": 2.2748, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 0.644075365405424, | |
| "grad_norm": 0.5191289186477661, | |
| "learning_rate": 0.000296160948168506, | |
| "loss": 2.2811, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 0.6655445442522714, | |
| "grad_norm": 0.6877865791320801, | |
| "learning_rate": 0.0002960321209258384, | |
| "loss": 2.2783, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 0.6870137230991189, | |
| "grad_norm": 0.49987566471099854, | |
| "learning_rate": 0.0002959032936831708, | |
| "loss": 2.2719, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 0.6870137230991189, | |
| "eval_loss": 2.964353561401367, | |
| "eval_runtime": 171.8492, | |
| "eval_samples_per_second": 14.548, | |
| "eval_steps_per_second": 3.637, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 0.7084829019459664, | |
| "grad_norm": 0.5470739006996155, | |
| "learning_rate": 0.00029577446644050325, | |
| "loss": 2.2832, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 0.7299520807928138, | |
| "grad_norm": 0.6002724766731262, | |
| "learning_rate": 0.0002956456391978357, | |
| "loss": 2.2838, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 0.7514212596396613, | |
| "grad_norm": 0.6674920320510864, | |
| "learning_rate": 0.0002955168119551681, | |
| "loss": 2.2686, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 0.7728904384865087, | |
| "grad_norm": 0.5728652477264404, | |
| "learning_rate": 0.0002953879847125005, | |
| "loss": 2.2725, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 0.7943596173333562, | |
| "grad_norm": 0.5590266585350037, | |
| "learning_rate": 0.00029525915746983294, | |
| "loss": 2.2794, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 0.8158287961802037, | |
| "grad_norm": 0.7446316480636597, | |
| "learning_rate": 0.00029513033022716533, | |
| "loss": 2.2676, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 0.8372979750270512, | |
| "grad_norm": 0.4322523772716522, | |
| "learning_rate": 0.0002950015029844977, | |
| "loss": 2.2832, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 0.8587671538738987, | |
| "grad_norm": 0.6566835045814514, | |
| "learning_rate": 0.00029487267574183017, | |
| "loss": 2.2636, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 0.8587671538738987, | |
| "eval_loss": 2.954716920852661, | |
| "eval_runtime": 171.5581, | |
| "eval_samples_per_second": 14.572, | |
| "eval_steps_per_second": 3.643, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 0.8802363327207461, | |
| "grad_norm": 0.5313192009925842, | |
| "learning_rate": 0.0002947438484991626, | |
| "loss": 2.2819, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 0.9017055115675936, | |
| "grad_norm": 0.689608633518219, | |
| "learning_rate": 0.000294615021256495, | |
| "loss": 2.2728, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 0.923174690414441, | |
| "grad_norm": 0.7024255394935608, | |
| "learning_rate": 0.0002944861940138274, | |
| "loss": 2.2746, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 0.9446438692612885, | |
| "grad_norm": 0.6012333035469055, | |
| "learning_rate": 0.00029435736677115986, | |
| "loss": 2.2658, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 0.9661130481081359, | |
| "grad_norm": 0.6304742693901062, | |
| "learning_rate": 0.0002942285395284923, | |
| "loss": 2.2718, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 0.9875822269549834, | |
| "grad_norm": 0.541362464427948, | |
| "learning_rate": 0.0002940997122858247, | |
| "loss": 2.272, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 1.009051405801831, | |
| "grad_norm": 0.5888085961341858, | |
| "learning_rate": 0.0002939708850431571, | |
| "loss": 2.2485, | |
| "step": 23500 | |
| }, | |
| { | |
| "epoch": 1.0305205846486785, | |
| "grad_norm": 0.5453173518180847, | |
| "learning_rate": 0.00029384205780048954, | |
| "loss": 2.2395, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 1.0305205846486785, | |
| "eval_loss": 2.940072774887085, | |
| "eval_runtime": 171.7472, | |
| "eval_samples_per_second": 14.556, | |
| "eval_steps_per_second": 3.639, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 1.0519897634955258, | |
| "grad_norm": 0.7155711054801941, | |
| "learning_rate": 0.00029371323055782194, | |
| "loss": 2.2476, | |
| "step": 24500 | |
| }, | |
| { | |
| "epoch": 1.0734589423423733, | |
| "grad_norm": 0.7307182550430298, | |
| "learning_rate": 0.00029358440331515433, | |
| "loss": 2.2479, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 1.0949281211892208, | |
| "grad_norm": 0.6849473714828491, | |
| "learning_rate": 0.0002934555760724868, | |
| "loss": 2.2407, | |
| "step": 25500 | |
| }, | |
| { | |
| "epoch": 1.1163973000360683, | |
| "grad_norm": 0.7161998152732849, | |
| "learning_rate": 0.00029332674882981923, | |
| "loss": 2.247, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 1.1378664788829158, | |
| "grad_norm": 0.723235011100769, | |
| "learning_rate": 0.0002931979215871516, | |
| "loss": 2.2382, | |
| "step": 26500 | |
| }, | |
| { | |
| "epoch": 1.159335657729763, | |
| "grad_norm": 0.4874274432659149, | |
| "learning_rate": 0.000293069094344484, | |
| "loss": 2.2483, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 1.1808048365766106, | |
| "grad_norm": 0.5381557941436768, | |
| "learning_rate": 0.00029294026710181646, | |
| "loss": 2.2423, | |
| "step": 27500 | |
| }, | |
| { | |
| "epoch": 1.2022740154234581, | |
| "grad_norm": 0.7897226214408875, | |
| "learning_rate": 0.00029281143985914886, | |
| "loss": 2.2538, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 1.2022740154234581, | |
| "eval_loss": 2.926734447479248, | |
| "eval_runtime": 172.6333, | |
| "eval_samples_per_second": 14.482, | |
| "eval_steps_per_second": 3.62, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 1.2237431942703056, | |
| "grad_norm": 0.5494747161865234, | |
| "learning_rate": 0.00029268261261648125, | |
| "loss": 2.2441, | |
| "step": 28500 | |
| }, | |
| { | |
| "epoch": 1.245212373117153, | |
| "grad_norm": 0.5955171585083008, | |
| "learning_rate": 0.0002925537853738137, | |
| "loss": 2.245, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 1.2666815519640005, | |
| "grad_norm": 0.7213128805160522, | |
| "learning_rate": 0.0002924249581311461, | |
| "loss": 2.2488, | |
| "step": 29500 | |
| }, | |
| { | |
| "epoch": 1.288150730810848, | |
| "grad_norm": 0.7488630414009094, | |
| "learning_rate": 0.00029229613088847854, | |
| "loss": 2.2412, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 1.3096199096576955, | |
| "grad_norm": 0.5948154330253601, | |
| "learning_rate": 0.00029216730364581094, | |
| "loss": 2.2378, | |
| "step": 30500 | |
| }, | |
| { | |
| "epoch": 1.3310890885045428, | |
| "grad_norm": 0.7915855050086975, | |
| "learning_rate": 0.0002920384764031434, | |
| "loss": 2.2464, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 1.3525582673513903, | |
| "grad_norm": 0.6043704152107239, | |
| "learning_rate": 0.0002919096491604758, | |
| "loss": 2.2421, | |
| "step": 31500 | |
| }, | |
| { | |
| "epoch": 1.3740274461982378, | |
| "grad_norm": 0.5474274158477783, | |
| "learning_rate": 0.0002917808219178082, | |
| "loss": 2.2507, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 1.3740274461982378, | |
| "eval_loss": 2.9269840717315674, | |
| "eval_runtime": 174.9446, | |
| "eval_samples_per_second": 14.29, | |
| "eval_steps_per_second": 3.573, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 1.3954966250450853, | |
| "grad_norm": 0.5420586466789246, | |
| "learning_rate": 0.0002916519946751406, | |
| "loss": 2.2405, | |
| "step": 32500 | |
| }, | |
| { | |
| "epoch": 1.4169658038919328, | |
| "grad_norm": 0.4751032888889313, | |
| "learning_rate": 0.000291523167432473, | |
| "loss": 2.2497, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 1.4384349827387801, | |
| "grad_norm": 0.5793635249137878, | |
| "learning_rate": 0.00029139434018980547, | |
| "loss": 2.2448, | |
| "step": 33500 | |
| }, | |
| { | |
| "epoch": 1.4599041615856276, | |
| "grad_norm": 0.6635434031486511, | |
| "learning_rate": 0.00029126551294713786, | |
| "loss": 2.2434, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 1.4813733404324751, | |
| "grad_norm": 0.5708619356155396, | |
| "learning_rate": 0.0002911366857044703, | |
| "loss": 2.2343, | |
| "step": 34500 | |
| }, | |
| { | |
| "epoch": 1.5028425192793224, | |
| "grad_norm": 0.5989744067192078, | |
| "learning_rate": 0.0002910078584618027, | |
| "loss": 2.2388, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 1.5243116981261702, | |
| "grad_norm": 0.746486246585846, | |
| "learning_rate": 0.0002908790312191351, | |
| "loss": 2.2484, | |
| "step": 35500 | |
| }, | |
| { | |
| "epoch": 1.5457808769730175, | |
| "grad_norm": 0.6059302687644958, | |
| "learning_rate": 0.00029075020397646755, | |
| "loss": 2.2409, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 1.5457808769730175, | |
| "eval_loss": 2.918299913406372, | |
| "eval_runtime": 171.3628, | |
| "eval_samples_per_second": 14.589, | |
| "eval_steps_per_second": 3.647, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 1.567250055819865, | |
| "grad_norm": 0.5767127871513367, | |
| "learning_rate": 0.00029062137673379994, | |
| "loss": 2.2459, | |
| "step": 36500 | |
| }, | |
| { | |
| "epoch": 1.5887192346667125, | |
| "grad_norm": 0.6815518736839294, | |
| "learning_rate": 0.0002904925494911324, | |
| "loss": 2.2565, | |
| "step": 37000 | |
| }, | |
| { | |
| "epoch": 1.6101884135135598, | |
| "grad_norm": 0.6565374732017517, | |
| "learning_rate": 0.0002903637222484648, | |
| "loss": 2.2388, | |
| "step": 37500 | |
| }, | |
| { | |
| "epoch": 1.6316575923604075, | |
| "grad_norm": 0.6622541546821594, | |
| "learning_rate": 0.0002902348950057972, | |
| "loss": 2.261, | |
| "step": 38000 | |
| }, | |
| { | |
| "epoch": 1.6531267712072548, | |
| "grad_norm": 0.8162985444068909, | |
| "learning_rate": 0.0002901060677631296, | |
| "loss": 2.2495, | |
| "step": 38500 | |
| }, | |
| { | |
| "epoch": 1.6745959500541023, | |
| "grad_norm": 0.5659546852111816, | |
| "learning_rate": 0.000289977240520462, | |
| "loss": 2.2385, | |
| "step": 39000 | |
| }, | |
| { | |
| "epoch": 1.6960651289009498, | |
| "grad_norm": 0.5625469088554382, | |
| "learning_rate": 0.00028984841327779447, | |
| "loss": 2.2372, | |
| "step": 39500 | |
| }, | |
| { | |
| "epoch": 1.7175343077477971, | |
| "grad_norm": 0.5423092842102051, | |
| "learning_rate": 0.00028971958603512686, | |
| "loss": 2.2424, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 1.7175343077477971, | |
| "eval_loss": 2.92061710357666, | |
| "eval_runtime": 172.1102, | |
| "eval_samples_per_second": 14.526, | |
| "eval_steps_per_second": 3.631, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 1.7390034865946449, | |
| "grad_norm": 0.7644880414009094, | |
| "learning_rate": 0.0002895907587924593, | |
| "loss": 2.2368, | |
| "step": 40500 | |
| }, | |
| { | |
| "epoch": 1.7604726654414922, | |
| "grad_norm": 0.8192068934440613, | |
| "learning_rate": 0.0002894619315497917, | |
| "loss": 2.2357, | |
| "step": 41000 | |
| }, | |
| { | |
| "epoch": 1.7819418442883397, | |
| "grad_norm": 0.6234991550445557, | |
| "learning_rate": 0.0002893331043071241, | |
| "loss": 2.2418, | |
| "step": 41500 | |
| }, | |
| { | |
| "epoch": 1.8034110231351872, | |
| "grad_norm": 0.5751623511314392, | |
| "learning_rate": 0.00028920427706445655, | |
| "loss": 2.2413, | |
| "step": 42000 | |
| }, | |
| { | |
| "epoch": 1.8248802019820345, | |
| "grad_norm": 0.8999291062355042, | |
| "learning_rate": 0.00028907544982178894, | |
| "loss": 2.2356, | |
| "step": 42500 | |
| }, | |
| { | |
| "epoch": 1.846349380828882, | |
| "grad_norm": 0.7696816325187683, | |
| "learning_rate": 0.00028894662257912133, | |
| "loss": 2.2427, | |
| "step": 43000 | |
| }, | |
| { | |
| "epoch": 1.8678185596757295, | |
| "grad_norm": 0.6660240292549133, | |
| "learning_rate": 0.0002888177953364538, | |
| "loss": 2.2507, | |
| "step": 43500 | |
| }, | |
| { | |
| "epoch": 1.889287738522577, | |
| "grad_norm": 0.6106180548667908, | |
| "learning_rate": 0.00028868896809378623, | |
| "loss": 2.2428, | |
| "step": 44000 | |
| }, | |
| { | |
| "epoch": 1.889287738522577, | |
| "eval_loss": 2.9116756916046143, | |
| "eval_runtime": 172.218, | |
| "eval_samples_per_second": 14.516, | |
| "eval_steps_per_second": 3.629, | |
| "step": 44000 | |
| }, | |
| { | |
| "epoch": 1.9107569173694245, | |
| "grad_norm": 0.6366661190986633, | |
| "learning_rate": 0.0002885601408511186, | |
| "loss": 2.2408, | |
| "step": 44500 | |
| }, | |
| { | |
| "epoch": 1.9322260962162718, | |
| "grad_norm": 0.7893187403678894, | |
| "learning_rate": 0.000288431313608451, | |
| "loss": 2.2369, | |
| "step": 45000 | |
| }, | |
| { | |
| "epoch": 1.9536952750631194, | |
| "grad_norm": 0.633651077747345, | |
| "learning_rate": 0.00028830248636578347, | |
| "loss": 2.2431, | |
| "step": 45500 | |
| }, | |
| { | |
| "epoch": 1.9751644539099669, | |
| "grad_norm": 0.7481298446655273, | |
| "learning_rate": 0.00028817365912311586, | |
| "loss": 2.2371, | |
| "step": 46000 | |
| }, | |
| { | |
| "epoch": 1.9966336327568142, | |
| "grad_norm": 0.596591055393219, | |
| "learning_rate": 0.00028804483188044826, | |
| "loss": 2.2358, | |
| "step": 46500 | |
| }, | |
| { | |
| "epoch": 2.018102811603662, | |
| "grad_norm": 0.7450771927833557, | |
| "learning_rate": 0.0002879160046377807, | |
| "loss": 2.2238, | |
| "step": 47000 | |
| }, | |
| { | |
| "epoch": 2.039571990450509, | |
| "grad_norm": 0.6886998414993286, | |
| "learning_rate": 0.00028778717739511315, | |
| "loss": 2.218, | |
| "step": 47500 | |
| }, | |
| { | |
| "epoch": 2.061041169297357, | |
| "grad_norm": 0.5555692911148071, | |
| "learning_rate": 0.00028765835015244555, | |
| "loss": 2.2151, | |
| "step": 48000 | |
| }, | |
| { | |
| "epoch": 2.061041169297357, | |
| "eval_loss": 2.909609317779541, | |
| "eval_runtime": 175.1711, | |
| "eval_samples_per_second": 14.272, | |
| "eval_steps_per_second": 3.568, | |
| "step": 48000 | |
| }, | |
| { | |
| "epoch": 2.082510348144204, | |
| "grad_norm": 0.7904226183891296, | |
| "learning_rate": 0.00028752952290977794, | |
| "loss": 2.2271, | |
| "step": 48500 | |
| }, | |
| { | |
| "epoch": 2.1039795269910515, | |
| "grad_norm": 0.8151206374168396, | |
| "learning_rate": 0.0002874006956671104, | |
| "loss": 2.2104, | |
| "step": 49000 | |
| }, | |
| { | |
| "epoch": 2.1254487058378992, | |
| "grad_norm": 0.6942662596702576, | |
| "learning_rate": 0.0002872718684244428, | |
| "loss": 2.2197, | |
| "step": 49500 | |
| }, | |
| { | |
| "epoch": 2.1469178846847465, | |
| "grad_norm": 0.6846303939819336, | |
| "learning_rate": 0.0002871430411817752, | |
| "loss": 2.2286, | |
| "step": 50000 | |
| }, | |
| { | |
| "epoch": 2.1683870635315943, | |
| "grad_norm": 0.8961315155029297, | |
| "learning_rate": 0.0002870142139391076, | |
| "loss": 2.2329, | |
| "step": 50500 | |
| }, | |
| { | |
| "epoch": 2.1898562423784416, | |
| "grad_norm": 0.5635807514190674, | |
| "learning_rate": 0.0002868853866964401, | |
| "loss": 2.2216, | |
| "step": 51000 | |
| }, | |
| { | |
| "epoch": 2.211325421225289, | |
| "grad_norm": 0.6454870700836182, | |
| "learning_rate": 0.00028675655945377247, | |
| "loss": 2.2119, | |
| "step": 51500 | |
| }, | |
| { | |
| "epoch": 2.2327946000721366, | |
| "grad_norm": 0.5770113468170166, | |
| "learning_rate": 0.00028662773221110486, | |
| "loss": 2.2216, | |
| "step": 52000 | |
| }, | |
| { | |
| "epoch": 2.2327946000721366, | |
| "eval_loss": 2.9131178855895996, | |
| "eval_runtime": 170.3262, | |
| "eval_samples_per_second": 14.678, | |
| "eval_steps_per_second": 3.669, | |
| "step": 52000 | |
| }, | |
| { | |
| "epoch": 2.254263778918984, | |
| "grad_norm": 0.6589009165763855, | |
| "learning_rate": 0.0002864989049684373, | |
| "loss": 2.2237, | |
| "step": 52500 | |
| }, | |
| { | |
| "epoch": 2.2757329577658316, | |
| "grad_norm": 0.6595714688301086, | |
| "learning_rate": 0.0002863700777257697, | |
| "loss": 2.2331, | |
| "step": 53000 | |
| }, | |
| { | |
| "epoch": 2.297202136612679, | |
| "grad_norm": 0.5528385639190674, | |
| "learning_rate": 0.0002862412504831021, | |
| "loss": 2.2316, | |
| "step": 53500 | |
| }, | |
| { | |
| "epoch": 2.318671315459526, | |
| "grad_norm": 0.6706179976463318, | |
| "learning_rate": 0.00028611242324043455, | |
| "loss": 2.2312, | |
| "step": 54000 | |
| }, | |
| { | |
| "epoch": 2.340140494306374, | |
| "grad_norm": 0.6599323153495789, | |
| "learning_rate": 0.000285983595997767, | |
| "loss": 2.2228, | |
| "step": 54500 | |
| }, | |
| { | |
| "epoch": 2.3616096731532212, | |
| "grad_norm": 0.7218915820121765, | |
| "learning_rate": 0.0002858547687550994, | |
| "loss": 2.2269, | |
| "step": 55000 | |
| }, | |
| { | |
| "epoch": 2.3830788520000685, | |
| "grad_norm": 0.6501777768135071, | |
| "learning_rate": 0.0002857259415124318, | |
| "loss": 2.225, | |
| "step": 55500 | |
| }, | |
| { | |
| "epoch": 2.4045480308469163, | |
| "grad_norm": 0.6774255037307739, | |
| "learning_rate": 0.00028559711426976423, | |
| "loss": 2.2193, | |
| "step": 56000 | |
| }, | |
| { | |
| "epoch": 2.4045480308469163, | |
| "eval_loss": 2.90551495552063, | |
| "eval_runtime": 173.4554, | |
| "eval_samples_per_second": 14.413, | |
| "eval_steps_per_second": 3.603, | |
| "step": 56000 | |
| }, | |
| { | |
| "epoch": 2.4260172096937636, | |
| "grad_norm": 0.667073130607605, | |
| "learning_rate": 0.00028546828702709663, | |
| "loss": 2.2228, | |
| "step": 56500 | |
| }, | |
| { | |
| "epoch": 2.4474863885406113, | |
| "grad_norm": 0.776077389717102, | |
| "learning_rate": 0.000285339459784429, | |
| "loss": 2.226, | |
| "step": 57000 | |
| }, | |
| { | |
| "epoch": 2.4689555673874586, | |
| "grad_norm": 0.7873576879501343, | |
| "learning_rate": 0.00028521063254176147, | |
| "loss": 2.2219, | |
| "step": 57500 | |
| }, | |
| { | |
| "epoch": 2.490424746234306, | |
| "grad_norm": 0.7621210813522339, | |
| "learning_rate": 0.0002850818052990939, | |
| "loss": 2.2226, | |
| "step": 58000 | |
| }, | |
| { | |
| "epoch": 2.5118939250811536, | |
| "grad_norm": 0.774750828742981, | |
| "learning_rate": 0.0002849529780564263, | |
| "loss": 2.2328, | |
| "step": 58500 | |
| }, | |
| { | |
| "epoch": 2.533363103928001, | |
| "grad_norm": 0.707665205001831, | |
| "learning_rate": 0.0002848241508137587, | |
| "loss": 2.2342, | |
| "step": 59000 | |
| }, | |
| { | |
| "epoch": 2.554832282774848, | |
| "grad_norm": 0.7524703741073608, | |
| "learning_rate": 0.00028469532357109116, | |
| "loss": 2.2296, | |
| "step": 59500 | |
| }, | |
| { | |
| "epoch": 2.576301461621696, | |
| "grad_norm": 0.6186488270759583, | |
| "learning_rate": 0.00028456649632842355, | |
| "loss": 2.2282, | |
| "step": 60000 | |
| }, | |
| { | |
| "epoch": 2.576301461621696, | |
| "eval_loss": 2.907226085662842, | |
| "eval_runtime": 176.429, | |
| "eval_samples_per_second": 14.17, | |
| "eval_steps_per_second": 3.543, | |
| "step": 60000 | |
| }, | |
| { | |
| "epoch": 2.5977706404685432, | |
| "grad_norm": 0.6811486482620239, | |
| "learning_rate": 0.00028443766908575594, | |
| "loss": 2.2357, | |
| "step": 60500 | |
| }, | |
| { | |
| "epoch": 2.619239819315391, | |
| "grad_norm": 0.7401767373085022, | |
| "learning_rate": 0.0002843088418430884, | |
| "loss": 2.2264, | |
| "step": 61000 | |
| }, | |
| { | |
| "epoch": 2.6407089981622383, | |
| "grad_norm": 0.6240813136100769, | |
| "learning_rate": 0.00028418001460042084, | |
| "loss": 2.2402, | |
| "step": 61500 | |
| }, | |
| { | |
| "epoch": 2.6621781770090855, | |
| "grad_norm": 0.6217384338378906, | |
| "learning_rate": 0.00028405118735775324, | |
| "loss": 2.2294, | |
| "step": 62000 | |
| }, | |
| { | |
| "epoch": 2.6836473558559333, | |
| "grad_norm": 0.5563312768936157, | |
| "learning_rate": 0.00028392236011508563, | |
| "loss": 2.2344, | |
| "step": 62500 | |
| }, | |
| { | |
| "epoch": 2.7051165347027806, | |
| "grad_norm": 0.7275550961494446, | |
| "learning_rate": 0.0002837935328724181, | |
| "loss": 2.2233, | |
| "step": 63000 | |
| }, | |
| { | |
| "epoch": 2.7265857135496283, | |
| "grad_norm": 0.6657426953315735, | |
| "learning_rate": 0.00028366470562975047, | |
| "loss": 2.2269, | |
| "step": 63500 | |
| }, | |
| { | |
| "epoch": 2.7480548923964756, | |
| "grad_norm": 0.5833483934402466, | |
| "learning_rate": 0.0002835358783870829, | |
| "loss": 2.2234, | |
| "step": 64000 | |
| }, | |
| { | |
| "epoch": 2.7480548923964756, | |
| "eval_loss": 2.8960378170013428, | |
| "eval_runtime": 165.7901, | |
| "eval_samples_per_second": 15.079, | |
| "eval_steps_per_second": 3.77, | |
| "step": 64000 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 1164450, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 50, | |
| "save_steps": 8000, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 7.740828282336215e+18, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |