| { |
| "best_metric": 0.38854101300239563, |
| "best_model_checkpoint": "./checkpoints/ultrafeedback_binarized/phi-2-ultrafeedback_binarized-lambda0.25-ORPO-26-6-26/checkpoint-5988", |
| "epoch": 2.0, |
| "eval_steps": 500, |
| "global_step": 5988, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.016700066800267203, |
| "grad_norm": 49.5, |
| "learning_rate": 2.0000000000000002e-07, |
| "loss": 1.0068, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.033400133600534405, |
| "grad_norm": 26.875, |
| "learning_rate": 4.0000000000000003e-07, |
| "loss": 0.5959, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.050100200400801605, |
| "grad_norm": 19.125, |
| "learning_rate": 6.000000000000001e-07, |
| "loss": 0.5394, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.06680026720106881, |
| "grad_norm": 15.625, |
| "learning_rate": 8.000000000000001e-07, |
| "loss": 0.5512, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.08350033400133601, |
| "grad_norm": 24.125, |
| "learning_rate": 1.0000000000000002e-06, |
| "loss": 0.538, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.10020040080160321, |
| "grad_norm": 15.375, |
| "learning_rate": 1.2000000000000002e-06, |
| "loss": 0.5332, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.11690046760187041, |
| "grad_norm": 14.125, |
| "learning_rate": 1.4000000000000001e-06, |
| "loss": 0.5185, |
| "step": 350 |
| }, |
| { |
| "epoch": 0.13360053440213762, |
| "grad_norm": 25.25, |
| "learning_rate": 1.6000000000000001e-06, |
| "loss": 0.5376, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.15030060120240482, |
| "grad_norm": 52.0, |
| "learning_rate": 1.8000000000000001e-06, |
| "loss": 0.5162, |
| "step": 450 |
| }, |
| { |
| "epoch": 0.16700066800267202, |
| "grad_norm": 27.625, |
| "learning_rate": 2.0000000000000003e-06, |
| "loss": 0.53, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.18370073480293922, |
| "grad_norm": 12.25, |
| "learning_rate": 2.2e-06, |
| "loss": 0.4957, |
| "step": 550 |
| }, |
| { |
| "epoch": 0.20040080160320642, |
| "grad_norm": 69.0, |
| "learning_rate": 2.4000000000000003e-06, |
| "loss": 0.5153, |
| "step": 600 |
| }, |
| { |
| "epoch": 0.21710086840347362, |
| "grad_norm": 57.75, |
| "learning_rate": 2.6e-06, |
| "loss": 0.5173, |
| "step": 650 |
| }, |
| { |
| "epoch": 0.23380093520374082, |
| "grad_norm": 29.875, |
| "learning_rate": 2.8000000000000003e-06, |
| "loss": 0.4796, |
| "step": 700 |
| }, |
| { |
| "epoch": 0.250501002004008, |
| "grad_norm": 59.5, |
| "learning_rate": 3e-06, |
| "loss": 0.4932, |
| "step": 750 |
| }, |
| { |
| "epoch": 0.26720106880427524, |
| "grad_norm": 23.375, |
| "learning_rate": 3.2000000000000003e-06, |
| "loss": 0.5257, |
| "step": 800 |
| }, |
| { |
| "epoch": 0.28390113560454244, |
| "grad_norm": 11.4375, |
| "learning_rate": 3.4000000000000005e-06, |
| "loss": 0.4966, |
| "step": 850 |
| }, |
| { |
| "epoch": 0.30060120240480964, |
| "grad_norm": 17.875, |
| "learning_rate": 3.6000000000000003e-06, |
| "loss": 0.4895, |
| "step": 900 |
| }, |
| { |
| "epoch": 0.31730126920507684, |
| "grad_norm": 10.1875, |
| "learning_rate": 3.8000000000000005e-06, |
| "loss": 0.498, |
| "step": 950 |
| }, |
| { |
| "epoch": 0.33400133600534404, |
| "grad_norm": 20.125, |
| "learning_rate": 4.000000000000001e-06, |
| "loss": 0.4825, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.35070140280561124, |
| "grad_norm": 8.375, |
| "learning_rate": 4.2000000000000004e-06, |
| "loss": 0.4675, |
| "step": 1050 |
| }, |
| { |
| "epoch": 0.36740146960587844, |
| "grad_norm": 24.25, |
| "learning_rate": 4.4e-06, |
| "loss": 0.4748, |
| "step": 1100 |
| }, |
| { |
| "epoch": 0.38410153640614564, |
| "grad_norm": 10.4375, |
| "learning_rate": 4.600000000000001e-06, |
| "loss": 0.4863, |
| "step": 1150 |
| }, |
| { |
| "epoch": 0.40080160320641284, |
| "grad_norm": 30.5, |
| "learning_rate": 4.800000000000001e-06, |
| "loss": 0.4844, |
| "step": 1200 |
| }, |
| { |
| "epoch": 0.41750167000668004, |
| "grad_norm": 15.4375, |
| "learning_rate": 5e-06, |
| "loss": 0.4753, |
| "step": 1250 |
| }, |
| { |
| "epoch": 0.43420173680694724, |
| "grad_norm": 15.75, |
| "learning_rate": 5.2e-06, |
| "loss": 0.4683, |
| "step": 1300 |
| }, |
| { |
| "epoch": 0.45090180360721444, |
| "grad_norm": 23.125, |
| "learning_rate": 5.400000000000001e-06, |
| "loss": 0.4617, |
| "step": 1350 |
| }, |
| { |
| "epoch": 0.46760187040748163, |
| "grad_norm": 16.375, |
| "learning_rate": 5.600000000000001e-06, |
| "loss": 0.459, |
| "step": 1400 |
| }, |
| { |
| "epoch": 0.48430193720774883, |
| "grad_norm": 20.375, |
| "learning_rate": 5.8e-06, |
| "loss": 0.4572, |
| "step": 1450 |
| }, |
| { |
| "epoch": 0.501002004008016, |
| "grad_norm": 8.5625, |
| "learning_rate": 6e-06, |
| "loss": 0.4516, |
| "step": 1500 |
| }, |
| { |
| "epoch": 0.5177020708082832, |
| "grad_norm": 37.5, |
| "learning_rate": 6.200000000000001e-06, |
| "loss": 0.4647, |
| "step": 1550 |
| }, |
| { |
| "epoch": 0.5344021376085505, |
| "grad_norm": 7.90625, |
| "learning_rate": 6.4000000000000006e-06, |
| "loss": 0.4535, |
| "step": 1600 |
| }, |
| { |
| "epoch": 0.5511022044088176, |
| "grad_norm": 22.75, |
| "learning_rate": 6.600000000000001e-06, |
| "loss": 0.44, |
| "step": 1650 |
| }, |
| { |
| "epoch": 0.5678022712090849, |
| "grad_norm": 13.0, |
| "learning_rate": 6.800000000000001e-06, |
| "loss": 0.43, |
| "step": 1700 |
| }, |
| { |
| "epoch": 0.584502338009352, |
| "grad_norm": 7.90625, |
| "learning_rate": 7e-06, |
| "loss": 0.4336, |
| "step": 1750 |
| }, |
| { |
| "epoch": 0.6012024048096193, |
| "grad_norm": 22.625, |
| "learning_rate": 7.2000000000000005e-06, |
| "loss": 0.4145, |
| "step": 1800 |
| }, |
| { |
| "epoch": 0.6179024716098864, |
| "grad_norm": 12.6875, |
| "learning_rate": 7.4e-06, |
| "loss": 0.4174, |
| "step": 1850 |
| }, |
| { |
| "epoch": 0.6346025384101537, |
| "grad_norm": 43.0, |
| "learning_rate": 7.600000000000001e-06, |
| "loss": 0.4336, |
| "step": 1900 |
| }, |
| { |
| "epoch": 0.6513026052104208, |
| "grad_norm": 26.625, |
| "learning_rate": 7.800000000000002e-06, |
| "loss": 0.4261, |
| "step": 1950 |
| }, |
| { |
| "epoch": 0.6680026720106881, |
| "grad_norm": 20.5, |
| "learning_rate": 8.000000000000001e-06, |
| "loss": 0.4161, |
| "step": 2000 |
| }, |
| { |
| "epoch": 0.6847027388109552, |
| "grad_norm": 17.875, |
| "learning_rate": 8.2e-06, |
| "loss": 0.4159, |
| "step": 2050 |
| }, |
| { |
| "epoch": 0.7014028056112225, |
| "grad_norm": 8.1875, |
| "learning_rate": 8.400000000000001e-06, |
| "loss": 0.4202, |
| "step": 2100 |
| }, |
| { |
| "epoch": 0.7181028724114896, |
| "grad_norm": 15.1875, |
| "learning_rate": 8.6e-06, |
| "loss": 0.4194, |
| "step": 2150 |
| }, |
| { |
| "epoch": 0.7348029392117569, |
| "grad_norm": 12.6875, |
| "learning_rate": 8.8e-06, |
| "loss": 0.4218, |
| "step": 2200 |
| }, |
| { |
| "epoch": 0.751503006012024, |
| "grad_norm": 19.875, |
| "learning_rate": 9e-06, |
| "loss": 0.4105, |
| "step": 2250 |
| }, |
| { |
| "epoch": 0.7682030728122913, |
| "grad_norm": 13.0625, |
| "learning_rate": 9.200000000000002e-06, |
| "loss": 0.4238, |
| "step": 2300 |
| }, |
| { |
| "epoch": 0.7849031396125584, |
| "grad_norm": 20.5, |
| "learning_rate": 9.4e-06, |
| "loss": 0.4036, |
| "step": 2350 |
| }, |
| { |
| "epoch": 0.8016032064128257, |
| "grad_norm": 13.6875, |
| "learning_rate": 9.600000000000001e-06, |
| "loss": 0.4115, |
| "step": 2400 |
| }, |
| { |
| "epoch": 0.8183032732130928, |
| "grad_norm": 39.5, |
| "learning_rate": 9.800000000000001e-06, |
| "loss": 0.4023, |
| "step": 2450 |
| }, |
| { |
| "epoch": 0.8350033400133601, |
| "grad_norm": 14.8125, |
| "learning_rate": 1e-05, |
| "loss": 0.4255, |
| "step": 2500 |
| }, |
| { |
| "epoch": 0.8517034068136272, |
| "grad_norm": 8.5, |
| "learning_rate": 1.02e-05, |
| "loss": 0.4236, |
| "step": 2550 |
| }, |
| { |
| "epoch": 0.8684034736138945, |
| "grad_norm": 48.5, |
| "learning_rate": 1.04e-05, |
| "loss": 0.4092, |
| "step": 2600 |
| }, |
| { |
| "epoch": 0.8851035404141616, |
| "grad_norm": 47.0, |
| "learning_rate": 1.0600000000000002e-05, |
| "loss": 0.419, |
| "step": 2650 |
| }, |
| { |
| "epoch": 0.9018036072144289, |
| "grad_norm": 26.125, |
| "learning_rate": 1.0800000000000002e-05, |
| "loss": 0.4086, |
| "step": 2700 |
| }, |
| { |
| "epoch": 0.918503674014696, |
| "grad_norm": 18.125, |
| "learning_rate": 1.1000000000000001e-05, |
| "loss": 0.4079, |
| "step": 2750 |
| }, |
| { |
| "epoch": 0.9352037408149633, |
| "grad_norm": 18.5, |
| "learning_rate": 1.1200000000000001e-05, |
| "loss": 0.4234, |
| "step": 2800 |
| }, |
| { |
| "epoch": 0.9519038076152304, |
| "grad_norm": 9.75, |
| "learning_rate": 1.14e-05, |
| "loss": 0.4099, |
| "step": 2850 |
| }, |
| { |
| "epoch": 0.9686038744154977, |
| "grad_norm": 35.25, |
| "learning_rate": 1.16e-05, |
| "loss": 0.4322, |
| "step": 2900 |
| }, |
| { |
| "epoch": 0.9853039412157648, |
| "grad_norm": 9.875, |
| "learning_rate": 1.18e-05, |
| "loss": 0.4057, |
| "step": 2950 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_loss": 0.39666369557380676, |
| "eval_runtime": 183.8029, |
| "eval_samples_per_second": 8.77, |
| "eval_steps_per_second": 0.55, |
| "step": 2994 |
| }, |
| { |
| "epoch": 1.002004008016032, |
| "grad_norm": 15.6875, |
| "learning_rate": 1.2e-05, |
| "loss": 0.4072, |
| "step": 3000 |
| }, |
| { |
| "epoch": 1.0187040748162992, |
| "grad_norm": 17.625, |
| "learning_rate": 1.22e-05, |
| "loss": 0.4181, |
| "step": 3050 |
| }, |
| { |
| "epoch": 1.0354041416165665, |
| "grad_norm": 13.8125, |
| "learning_rate": 1.2400000000000002e-05, |
| "loss": 0.4032, |
| "step": 3100 |
| }, |
| { |
| "epoch": 1.0521042084168337, |
| "grad_norm": 9.25, |
| "learning_rate": 1.2600000000000001e-05, |
| "loss": 0.4, |
| "step": 3150 |
| }, |
| { |
| "epoch": 1.0688042752171008, |
| "grad_norm": 15.125, |
| "learning_rate": 1.2800000000000001e-05, |
| "loss": 0.3988, |
| "step": 3200 |
| }, |
| { |
| "epoch": 1.085504342017368, |
| "grad_norm": 50.0, |
| "learning_rate": 1.3000000000000001e-05, |
| "loss": 0.4193, |
| "step": 3250 |
| }, |
| { |
| "epoch": 1.1022044088176353, |
| "grad_norm": 11.0625, |
| "learning_rate": 1.3200000000000002e-05, |
| "loss": 0.4002, |
| "step": 3300 |
| }, |
| { |
| "epoch": 1.1189044756179025, |
| "grad_norm": 31.25, |
| "learning_rate": 1.3400000000000002e-05, |
| "loss": 0.4172, |
| "step": 3350 |
| }, |
| { |
| "epoch": 1.1356045424181698, |
| "grad_norm": 8.25, |
| "learning_rate": 1.3600000000000002e-05, |
| "loss": 0.4093, |
| "step": 3400 |
| }, |
| { |
| "epoch": 1.1523046092184368, |
| "grad_norm": 7.84375, |
| "learning_rate": 1.38e-05, |
| "loss": 0.3956, |
| "step": 3450 |
| }, |
| { |
| "epoch": 1.169004676018704, |
| "grad_norm": 10.1875, |
| "learning_rate": 1.4e-05, |
| "loss": 0.3951, |
| "step": 3500 |
| }, |
| { |
| "epoch": 1.1857047428189713, |
| "grad_norm": 17.5, |
| "learning_rate": 1.4200000000000001e-05, |
| "loss": 0.3949, |
| "step": 3550 |
| }, |
| { |
| "epoch": 1.2024048096192386, |
| "grad_norm": 14.125, |
| "learning_rate": 1.4400000000000001e-05, |
| "loss": 0.4107, |
| "step": 3600 |
| }, |
| { |
| "epoch": 1.2191048764195056, |
| "grad_norm": 7.0625, |
| "learning_rate": 1.46e-05, |
| "loss": 0.3856, |
| "step": 3650 |
| }, |
| { |
| "epoch": 1.2358049432197729, |
| "grad_norm": 12.125, |
| "learning_rate": 1.48e-05, |
| "loss": 0.4021, |
| "step": 3700 |
| }, |
| { |
| "epoch": 1.25250501002004, |
| "grad_norm": 14.9375, |
| "learning_rate": 1.5000000000000002e-05, |
| "loss": 0.4205, |
| "step": 3750 |
| }, |
| { |
| "epoch": 1.2692050768203074, |
| "grad_norm": 32.25, |
| "learning_rate": 1.5200000000000002e-05, |
| "loss": 0.4111, |
| "step": 3800 |
| }, |
| { |
| "epoch": 1.2859051436205746, |
| "grad_norm": 9.3125, |
| "learning_rate": 1.54e-05, |
| "loss": 0.4111, |
| "step": 3850 |
| }, |
| { |
| "epoch": 1.3026052104208417, |
| "grad_norm": 10.875, |
| "learning_rate": 1.5600000000000003e-05, |
| "loss": 0.4007, |
| "step": 3900 |
| }, |
| { |
| "epoch": 1.319305277221109, |
| "grad_norm": 12.0625, |
| "learning_rate": 1.58e-05, |
| "loss": 0.4006, |
| "step": 3950 |
| }, |
| { |
| "epoch": 1.3360053440213762, |
| "grad_norm": 12.625, |
| "learning_rate": 1.6000000000000003e-05, |
| "loss": 0.4104, |
| "step": 4000 |
| }, |
| { |
| "epoch": 1.3527054108216432, |
| "grad_norm": 10.875, |
| "learning_rate": 1.62e-05, |
| "loss": 0.4114, |
| "step": 4050 |
| }, |
| { |
| "epoch": 1.3694054776219104, |
| "grad_norm": 13.25, |
| "learning_rate": 1.64e-05, |
| "loss": 0.4174, |
| "step": 4100 |
| }, |
| { |
| "epoch": 1.3861055444221777, |
| "grad_norm": 12.625, |
| "learning_rate": 1.66e-05, |
| "loss": 0.39, |
| "step": 4150 |
| }, |
| { |
| "epoch": 1.402805611222445, |
| "grad_norm": 9.4375, |
| "learning_rate": 1.6800000000000002e-05, |
| "loss": 0.4136, |
| "step": 4200 |
| }, |
| { |
| "epoch": 1.4195056780227122, |
| "grad_norm": 12.375, |
| "learning_rate": 1.7e-05, |
| "loss": 0.4163, |
| "step": 4250 |
| }, |
| { |
| "epoch": 1.4362057448229792, |
| "grad_norm": 16.25, |
| "learning_rate": 1.72e-05, |
| "loss": 0.4253, |
| "step": 4300 |
| }, |
| { |
| "epoch": 1.4529058116232465, |
| "grad_norm": 8.9375, |
| "learning_rate": 1.7400000000000003e-05, |
| "loss": 0.4265, |
| "step": 4350 |
| }, |
| { |
| "epoch": 1.4696058784235138, |
| "grad_norm": 9.1875, |
| "learning_rate": 1.76e-05, |
| "loss": 0.4148, |
| "step": 4400 |
| }, |
| { |
| "epoch": 1.4863059452237808, |
| "grad_norm": 8.0, |
| "learning_rate": 1.7800000000000002e-05, |
| "loss": 0.4132, |
| "step": 4450 |
| }, |
| { |
| "epoch": 1.503006012024048, |
| "grad_norm": 19.375, |
| "learning_rate": 1.8e-05, |
| "loss": 0.418, |
| "step": 4500 |
| }, |
| { |
| "epoch": 1.5197060788243153, |
| "grad_norm": 6.9375, |
| "learning_rate": 1.8200000000000002e-05, |
| "loss": 0.3946, |
| "step": 4550 |
| }, |
| { |
| "epoch": 1.5364061456245826, |
| "grad_norm": 9.625, |
| "learning_rate": 1.8400000000000003e-05, |
| "loss": 0.4016, |
| "step": 4600 |
| }, |
| { |
| "epoch": 1.5531062124248498, |
| "grad_norm": 7.9375, |
| "learning_rate": 1.86e-05, |
| "loss": 0.4078, |
| "step": 4650 |
| }, |
| { |
| "epoch": 1.569806279225117, |
| "grad_norm": 31.875, |
| "learning_rate": 1.88e-05, |
| "loss": 0.4023, |
| "step": 4700 |
| }, |
| { |
| "epoch": 1.586506346025384, |
| "grad_norm": 20.375, |
| "learning_rate": 1.9e-05, |
| "loss": 0.4128, |
| "step": 4750 |
| }, |
| { |
| "epoch": 1.6032064128256514, |
| "grad_norm": 7.3125, |
| "learning_rate": 1.9200000000000003e-05, |
| "loss": 0.4093, |
| "step": 4800 |
| }, |
| { |
| "epoch": 1.6199064796259184, |
| "grad_norm": 16.75, |
| "learning_rate": 1.94e-05, |
| "loss": 0.3988, |
| "step": 4850 |
| }, |
| { |
| "epoch": 1.6366065464261856, |
| "grad_norm": 8.5, |
| "learning_rate": 1.9600000000000002e-05, |
| "loss": 0.4023, |
| "step": 4900 |
| }, |
| { |
| "epoch": 1.653306613226453, |
| "grad_norm": 7.1875, |
| "learning_rate": 1.98e-05, |
| "loss": 0.4078, |
| "step": 4950 |
| }, |
| { |
| "epoch": 1.6700066800267201, |
| "grad_norm": 9.0625, |
| "learning_rate": 2e-05, |
| "loss": 0.3918, |
| "step": 5000 |
| }, |
| { |
| "epoch": 1.6867067468269874, |
| "grad_norm": 14.375, |
| "learning_rate": 1.9873880897766597e-05, |
| "loss": 0.404, |
| "step": 5050 |
| }, |
| { |
| "epoch": 1.7034068136272547, |
| "grad_norm": 14.3125, |
| "learning_rate": 1.949870479665602e-05, |
| "loss": 0.4023, |
| "step": 5100 |
| }, |
| { |
| "epoch": 1.7201068804275217, |
| "grad_norm": 16.75, |
| "learning_rate": 1.888393507127856e-05, |
| "loss": 0.3909, |
| "step": 5150 |
| }, |
| { |
| "epoch": 1.736806947227789, |
| "grad_norm": 13.5, |
| "learning_rate": 1.8045078562803203e-05, |
| "loss": 0.3953, |
| "step": 5200 |
| }, |
| { |
| "epoch": 1.753507014028056, |
| "grad_norm": 6.90625, |
| "learning_rate": 1.7003294437180254e-05, |
| "loss": 0.4011, |
| "step": 5250 |
| }, |
| { |
| "epoch": 1.7702070808283232, |
| "grad_norm": 11.125, |
| "learning_rate": 1.5784860470138633e-05, |
| "loss": 0.4031, |
| "step": 5300 |
| }, |
| { |
| "epoch": 1.7869071476285905, |
| "grad_norm": 6.71875, |
| "learning_rate": 1.4420510221289137e-05, |
| "loss": 0.4019, |
| "step": 5350 |
| }, |
| { |
| "epoch": 1.8036072144288577, |
| "grad_norm": 7.03125, |
| "learning_rate": 1.2944657816335124e-05, |
| "loss": 0.4017, |
| "step": 5400 |
| }, |
| { |
| "epoch": 1.820307281229125, |
| "grad_norm": 4.125, |
| "learning_rate": 1.139452989134496e-05, |
| "loss": 0.3947, |
| "step": 5450 |
| }, |
| { |
| "epoch": 1.8370073480293923, |
| "grad_norm": 10.8125, |
| "learning_rate": 9.809226594767979e-06, |
| "loss": 0.4071, |
| "step": 5500 |
| }, |
| { |
| "epoch": 1.8537074148296593, |
| "grad_norm": 7.03125, |
| "learning_rate": 8.228735332310575e-06, |
| "loss": 0.4025, |
| "step": 5550 |
| }, |
| { |
| "epoch": 1.8704074816299265, |
| "grad_norm": 11.6875, |
| "learning_rate": 6.692922131794517e-06, |
| "loss": 0.4016, |
| "step": 5600 |
| }, |
| { |
| "epoch": 1.8871075484301936, |
| "grad_norm": 5.90625, |
| "learning_rate": 5.240526069629265e-06, |
| "loss": 0.4008, |
| "step": 5650 |
| }, |
| { |
| "epoch": 1.9038076152304608, |
| "grad_norm": 5.1875, |
| "learning_rate": 3.908182123304344e-06, |
| "loss": 0.4083, |
| "step": 5700 |
| }, |
| { |
| "epoch": 1.920507682030728, |
| "grad_norm": 3.171875, |
| "learning_rate": 2.729497097295075e-06, |
| "loss": 0.398, |
| "step": 5750 |
| }, |
| { |
| "epoch": 1.9372077488309953, |
| "grad_norm": 12.9375, |
| "learning_rate": 1.7342019310607062e-06, |
| "loss": 0.3936, |
| "step": 5800 |
| }, |
| { |
| "epoch": 1.9539078156312626, |
| "grad_norm": 4.78125, |
| "learning_rate": 9.474017711657835e-07, |
| "loss": 0.3917, |
| "step": 5850 |
| }, |
| { |
| "epoch": 1.9706078824315298, |
| "grad_norm": 5.8125, |
| "learning_rate": 3.889427235709153e-07, |
| "loss": 0.4002, |
| "step": 5900 |
| }, |
| { |
| "epoch": 1.9873079492317969, |
| "grad_norm": 6.375, |
| "learning_rate": 7.291125901946027e-08, |
| "loss": 0.4025, |
| "step": 5950 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_loss": 0.38854101300239563, |
| "eval_runtime": 184.1208, |
| "eval_samples_per_second": 8.755, |
| "eval_steps_per_second": 0.549, |
| "step": 5988 |
| } |
| ], |
| "logging_steps": 50, |
| "max_steps": 5988, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 2, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.5590253079717478e+18, |
| "train_batch_size": 16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
