ancient-ancient
initial commit
a877374
{
"best_metric": 0.867408520282142,
"best_model_checkpoint": "./save_models/mnli/roberta-base_lr1e-05_run2/checkpoint-220900",
"epoch": 10.0,
"eval_steps": 500,
"global_step": 220900,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.02,
"learning_rate": 3.772446054021428e-07,
"loss": 1.1005,
"step": 500
},
{
"epoch": 0.05,
"learning_rate": 7.544892108042856e-07,
"loss": 1.1004,
"step": 1000
},
{
"epoch": 0.07,
"learning_rate": 1.1317338162064282e-06,
"loss": 1.0915,
"step": 1500
},
{
"epoch": 0.09,
"learning_rate": 1.5089784216085712e-06,
"loss": 0.9695,
"step": 2000
},
{
"epoch": 0.11,
"learning_rate": 1.886223027010714e-06,
"loss": 0.8466,
"step": 2500
},
{
"epoch": 0.14,
"learning_rate": 2.2634676324128565e-06,
"loss": 0.6904,
"step": 3000
},
{
"epoch": 0.16,
"learning_rate": 2.6407122378149996e-06,
"loss": 0.6293,
"step": 3500
},
{
"epoch": 0.18,
"learning_rate": 3.0179568432171424e-06,
"loss": 0.5855,
"step": 4000
},
{
"epoch": 0.2,
"learning_rate": 3.395201448619285e-06,
"loss": 0.5505,
"step": 4500
},
{
"epoch": 0.23,
"learning_rate": 3.772446054021428e-06,
"loss": 0.5519,
"step": 5000
},
{
"epoch": 0.25,
"learning_rate": 4.149690659423571e-06,
"loss": 0.5192,
"step": 5500
},
{
"epoch": 0.27,
"learning_rate": 4.526935264825713e-06,
"loss": 0.5156,
"step": 6000
},
{
"epoch": 0.29,
"learning_rate": 4.904179870227856e-06,
"loss": 0.5082,
"step": 6500
},
{
"epoch": 0.32,
"learning_rate": 5.281424475629999e-06,
"loss": 0.5001,
"step": 7000
},
{
"epoch": 0.34,
"learning_rate": 5.658669081032142e-06,
"loss": 0.489,
"step": 7500
},
{
"epoch": 0.36,
"learning_rate": 6.035913686434285e-06,
"loss": 0.4944,
"step": 8000
},
{
"epoch": 0.38,
"learning_rate": 6.4131582918364275e-06,
"loss": 0.4852,
"step": 8500
},
{
"epoch": 0.41,
"learning_rate": 6.79040289723857e-06,
"loss": 0.4802,
"step": 9000
},
{
"epoch": 0.43,
"learning_rate": 7.167647502640713e-06,
"loss": 0.4721,
"step": 9500
},
{
"epoch": 0.45,
"learning_rate": 7.544892108042856e-06,
"loss": 0.4506,
"step": 10000
},
{
"epoch": 0.48,
"learning_rate": 7.922136713445e-06,
"loss": 0.4756,
"step": 10500
},
{
"epoch": 0.5,
"learning_rate": 8.299381318847142e-06,
"loss": 0.4595,
"step": 11000
},
{
"epoch": 0.52,
"learning_rate": 8.676625924249283e-06,
"loss": 0.474,
"step": 11500
},
{
"epoch": 0.54,
"learning_rate": 9.053870529651426e-06,
"loss": 0.4419,
"step": 12000
},
{
"epoch": 0.57,
"learning_rate": 9.431115135053569e-06,
"loss": 0.4571,
"step": 12500
},
{
"epoch": 0.59,
"learning_rate": 9.808359740455711e-06,
"loss": 0.4544,
"step": 13000
},
{
"epoch": 0.61,
"learning_rate": 9.98815291409418e-06,
"loss": 0.4595,
"step": 13500
},
{
"epoch": 0.63,
"learning_rate": 9.964073471196171e-06,
"loss": 0.441,
"step": 14000
},
{
"epoch": 0.66,
"learning_rate": 9.939994028298163e-06,
"loss": 0.4483,
"step": 14500
},
{
"epoch": 0.68,
"learning_rate": 9.915914585400153e-06,
"loss": 0.4395,
"step": 15000
},
{
"epoch": 0.7,
"learning_rate": 9.891835142502145e-06,
"loss": 0.4484,
"step": 15500
},
{
"epoch": 0.72,
"learning_rate": 9.867755699604135e-06,
"loss": 0.4378,
"step": 16000
},
{
"epoch": 0.75,
"learning_rate": 9.843676256706126e-06,
"loss": 0.4422,
"step": 16500
},
{
"epoch": 0.77,
"learning_rate": 9.819596813808116e-06,
"loss": 0.4293,
"step": 17000
},
{
"epoch": 0.79,
"learning_rate": 9.795517370910108e-06,
"loss": 0.4349,
"step": 17500
},
{
"epoch": 0.81,
"learning_rate": 9.771437928012098e-06,
"loss": 0.4292,
"step": 18000
},
{
"epoch": 0.84,
"learning_rate": 9.74735848511409e-06,
"loss": 0.4403,
"step": 18500
},
{
"epoch": 0.86,
"learning_rate": 9.723279042216081e-06,
"loss": 0.4299,
"step": 19000
},
{
"epoch": 0.88,
"learning_rate": 9.699199599318071e-06,
"loss": 0.4308,
"step": 19500
},
{
"epoch": 0.91,
"learning_rate": 9.675120156420061e-06,
"loss": 0.4141,
"step": 20000
},
{
"epoch": 0.93,
"learning_rate": 9.651040713522053e-06,
"loss": 0.4163,
"step": 20500
},
{
"epoch": 0.95,
"learning_rate": 9.626961270624043e-06,
"loss": 0.41,
"step": 21000
},
{
"epoch": 0.97,
"learning_rate": 9.602881827726035e-06,
"loss": 0.4285,
"step": 21500
},
{
"epoch": 1.0,
"learning_rate": 9.578802384828026e-06,
"loss": 0.4202,
"step": 22000
},
{
"epoch": 1.0,
"eval_accuracy": 0.8505512973950243,
"eval_loss": 0.4125332534313202,
"eval_runtime": 48.6401,
"eval_samples_per_second": 807.379,
"eval_steps_per_second": 50.473,
"step": 22090
},
{
"epoch": 1.02,
"learning_rate": 9.554722941930016e-06,
"loss": 0.3827,
"step": 22500
},
{
"epoch": 1.04,
"learning_rate": 9.530643499032008e-06,
"loss": 0.3678,
"step": 23000
},
{
"epoch": 1.06,
"learning_rate": 9.506564056133998e-06,
"loss": 0.365,
"step": 23500
},
{
"epoch": 1.09,
"learning_rate": 9.48248461323599e-06,
"loss": 0.3697,
"step": 24000
},
{
"epoch": 1.11,
"learning_rate": 9.45840517033798e-06,
"loss": 0.3585,
"step": 24500
},
{
"epoch": 1.13,
"learning_rate": 9.43432572743997e-06,
"loss": 0.3727,
"step": 25000
},
{
"epoch": 1.15,
"learning_rate": 9.410246284541961e-06,
"loss": 0.3513,
"step": 25500
},
{
"epoch": 1.18,
"learning_rate": 9.386166841643953e-06,
"loss": 0.3754,
"step": 26000
},
{
"epoch": 1.2,
"learning_rate": 9.362087398745945e-06,
"loss": 0.3585,
"step": 26500
},
{
"epoch": 1.22,
"learning_rate": 9.338007955847935e-06,
"loss": 0.3661,
"step": 27000
},
{
"epoch": 1.24,
"learning_rate": 9.313928512949925e-06,
"loss": 0.3646,
"step": 27500
},
{
"epoch": 1.27,
"learning_rate": 9.289849070051916e-06,
"loss": 0.3604,
"step": 28000
},
{
"epoch": 1.29,
"learning_rate": 9.265769627153906e-06,
"loss": 0.3721,
"step": 28500
},
{
"epoch": 1.31,
"learning_rate": 9.241690184255898e-06,
"loss": 0.3673,
"step": 29000
},
{
"epoch": 1.34,
"learning_rate": 9.217610741357888e-06,
"loss": 0.3508,
"step": 29500
},
{
"epoch": 1.36,
"learning_rate": 9.19353129845988e-06,
"loss": 0.3543,
"step": 30000
},
{
"epoch": 1.38,
"learning_rate": 9.169451855561871e-06,
"loss": 0.3585,
"step": 30500
},
{
"epoch": 1.4,
"learning_rate": 9.145372412663861e-06,
"loss": 0.359,
"step": 31000
},
{
"epoch": 1.43,
"learning_rate": 9.121292969765853e-06,
"loss": 0.3597,
"step": 31500
},
{
"epoch": 1.45,
"learning_rate": 9.097213526867843e-06,
"loss": 0.3513,
"step": 32000
},
{
"epoch": 1.47,
"learning_rate": 9.073134083969835e-06,
"loss": 0.3618,
"step": 32500
},
{
"epoch": 1.49,
"learning_rate": 9.049054641071825e-06,
"loss": 0.3643,
"step": 33000
},
{
"epoch": 1.52,
"learning_rate": 9.024975198173815e-06,
"loss": 0.3737,
"step": 33500
},
{
"epoch": 1.54,
"learning_rate": 9.000895755275806e-06,
"loss": 0.3586,
"step": 34000
},
{
"epoch": 1.56,
"learning_rate": 8.976816312377798e-06,
"loss": 0.3577,
"step": 34500
},
{
"epoch": 1.58,
"learning_rate": 8.95273686947979e-06,
"loss": 0.3594,
"step": 35000
},
{
"epoch": 1.61,
"learning_rate": 8.92865742658178e-06,
"loss": 0.3438,
"step": 35500
},
{
"epoch": 1.63,
"learning_rate": 8.90457798368377e-06,
"loss": 0.3631,
"step": 36000
},
{
"epoch": 1.65,
"learning_rate": 8.880498540785761e-06,
"loss": 0.3498,
"step": 36500
},
{
"epoch": 1.67,
"learning_rate": 8.856419097887751e-06,
"loss": 0.3611,
"step": 37000
},
{
"epoch": 1.7,
"learning_rate": 8.832339654989743e-06,
"loss": 0.3473,
"step": 37500
},
{
"epoch": 1.72,
"learning_rate": 8.808260212091733e-06,
"loss": 0.3476,
"step": 38000
},
{
"epoch": 1.74,
"learning_rate": 8.784180769193725e-06,
"loss": 0.3565,
"step": 38500
},
{
"epoch": 1.77,
"learning_rate": 8.760101326295716e-06,
"loss": 0.3572,
"step": 39000
},
{
"epoch": 1.79,
"learning_rate": 8.736021883397706e-06,
"loss": 0.3501,
"step": 39500
},
{
"epoch": 1.81,
"learning_rate": 8.711942440499698e-06,
"loss": 0.3535,
"step": 40000
},
{
"epoch": 1.83,
"learning_rate": 8.687862997601688e-06,
"loss": 0.3545,
"step": 40500
},
{
"epoch": 1.86,
"learning_rate": 8.663783554703678e-06,
"loss": 0.3615,
"step": 41000
},
{
"epoch": 1.88,
"learning_rate": 8.63970411180567e-06,
"loss": 0.3651,
"step": 41500
},
{
"epoch": 1.9,
"learning_rate": 8.615624668907661e-06,
"loss": 0.3508,
"step": 42000
},
{
"epoch": 1.92,
"learning_rate": 8.591545226009653e-06,
"loss": 0.344,
"step": 42500
},
{
"epoch": 1.95,
"learning_rate": 8.567465783111643e-06,
"loss": 0.3536,
"step": 43000
},
{
"epoch": 1.97,
"learning_rate": 8.543386340213633e-06,
"loss": 0.359,
"step": 43500
},
{
"epoch": 1.99,
"learning_rate": 8.519306897315625e-06,
"loss": 0.3471,
"step": 44000
},
{
"epoch": 2.0,
"eval_accuracy": 0.8628759135239744,
"eval_loss": 0.3846328854560852,
"eval_runtime": 48.5564,
"eval_samples_per_second": 808.77,
"eval_steps_per_second": 50.56,
"step": 44180
},
{
"epoch": 2.01,
"learning_rate": 8.495227454417615e-06,
"loss": 0.2986,
"step": 44500
},
{
"epoch": 2.04,
"learning_rate": 8.471148011519606e-06,
"loss": 0.2883,
"step": 45000
},
{
"epoch": 2.06,
"learning_rate": 8.447068568621596e-06,
"loss": 0.2719,
"step": 45500
},
{
"epoch": 2.08,
"learning_rate": 8.422989125723588e-06,
"loss": 0.2827,
"step": 46000
},
{
"epoch": 2.11,
"learning_rate": 8.39890968282558e-06,
"loss": 0.2827,
"step": 46500
},
{
"epoch": 2.13,
"learning_rate": 8.37483023992757e-06,
"loss": 0.2976,
"step": 47000
},
{
"epoch": 2.15,
"learning_rate": 8.350750797029561e-06,
"loss": 0.2714,
"step": 47500
},
{
"epoch": 2.17,
"learning_rate": 8.326671354131551e-06,
"loss": 0.2895,
"step": 48000
},
{
"epoch": 2.2,
"learning_rate": 8.302591911233543e-06,
"loss": 0.2826,
"step": 48500
},
{
"epoch": 2.22,
"learning_rate": 8.278512468335533e-06,
"loss": 0.2783,
"step": 49000
},
{
"epoch": 2.24,
"learning_rate": 8.254433025437523e-06,
"loss": 0.2843,
"step": 49500
},
{
"epoch": 2.26,
"learning_rate": 8.230353582539515e-06,
"loss": 0.2913,
"step": 50000
},
{
"epoch": 2.29,
"learning_rate": 8.206274139641506e-06,
"loss": 0.2694,
"step": 50500
},
{
"epoch": 2.31,
"learning_rate": 8.182194696743498e-06,
"loss": 0.2847,
"step": 51000
},
{
"epoch": 2.33,
"learning_rate": 8.158115253845488e-06,
"loss": 0.2911,
"step": 51500
},
{
"epoch": 2.35,
"learning_rate": 8.134035810947478e-06,
"loss": 0.2818,
"step": 52000
},
{
"epoch": 2.38,
"learning_rate": 8.10995636804947e-06,
"loss": 0.282,
"step": 52500
},
{
"epoch": 2.4,
"learning_rate": 8.08587692515146e-06,
"loss": 0.2868,
"step": 53000
},
{
"epoch": 2.42,
"learning_rate": 8.061797482253451e-06,
"loss": 0.2849,
"step": 53500
},
{
"epoch": 2.44,
"learning_rate": 8.037718039355441e-06,
"loss": 0.2791,
"step": 54000
},
{
"epoch": 2.47,
"learning_rate": 8.013638596457433e-06,
"loss": 0.2833,
"step": 54500
},
{
"epoch": 2.49,
"learning_rate": 7.989559153559425e-06,
"loss": 0.2771,
"step": 55000
},
{
"epoch": 2.51,
"learning_rate": 7.965479710661415e-06,
"loss": 0.2865,
"step": 55500
},
{
"epoch": 2.54,
"learning_rate": 7.941400267763406e-06,
"loss": 0.2856,
"step": 56000
},
{
"epoch": 2.56,
"learning_rate": 7.917320824865396e-06,
"loss": 0.2989,
"step": 56500
},
{
"epoch": 2.58,
"learning_rate": 7.893241381967386e-06,
"loss": 0.286,
"step": 57000
},
{
"epoch": 2.6,
"learning_rate": 7.869161939069378e-06,
"loss": 0.2818,
"step": 57500
},
{
"epoch": 2.63,
"learning_rate": 7.84508249617137e-06,
"loss": 0.2781,
"step": 58000
},
{
"epoch": 2.65,
"learning_rate": 7.82100305327336e-06,
"loss": 0.2822,
"step": 58500
},
{
"epoch": 2.67,
"learning_rate": 7.796923610375351e-06,
"loss": 0.2888,
"step": 59000
},
{
"epoch": 2.69,
"learning_rate": 7.772844167477341e-06,
"loss": 0.2922,
"step": 59500
},
{
"epoch": 2.72,
"learning_rate": 7.748764724579333e-06,
"loss": 0.2817,
"step": 60000
},
{
"epoch": 2.74,
"learning_rate": 7.724685281681323e-06,
"loss": 0.2779,
"step": 60500
},
{
"epoch": 2.76,
"learning_rate": 7.700605838783315e-06,
"loss": 0.2846,
"step": 61000
},
{
"epoch": 2.78,
"learning_rate": 7.676526395885305e-06,
"loss": 0.2935,
"step": 61500
},
{
"epoch": 2.81,
"learning_rate": 7.652446952987296e-06,
"loss": 0.2787,
"step": 62000
},
{
"epoch": 2.83,
"learning_rate": 7.628367510089287e-06,
"loss": 0.2701,
"step": 62500
},
{
"epoch": 2.85,
"learning_rate": 7.604288067191278e-06,
"loss": 0.2888,
"step": 63000
},
{
"epoch": 2.87,
"learning_rate": 7.58020862429327e-06,
"loss": 0.2827,
"step": 63500
},
{
"epoch": 2.9,
"learning_rate": 7.55612918139526e-06,
"loss": 0.2746,
"step": 64000
},
{
"epoch": 2.92,
"learning_rate": 7.532049738497251e-06,
"loss": 0.2766,
"step": 64500
},
{
"epoch": 2.94,
"learning_rate": 7.507970295599241e-06,
"loss": 0.2976,
"step": 65000
},
{
"epoch": 2.97,
"learning_rate": 7.483890852701232e-06,
"loss": 0.2902,
"step": 65500
},
{
"epoch": 2.99,
"learning_rate": 7.459811409803224e-06,
"loss": 0.2989,
"step": 66000
},
{
"epoch": 3.0,
"eval_accuracy": 0.8646838634106593,
"eval_loss": 0.4122258126735687,
"eval_runtime": 48.5877,
"eval_samples_per_second": 808.249,
"eval_steps_per_second": 50.527,
"step": 66270
},
{
"epoch": 3.01,
"learning_rate": 7.435731966905214e-06,
"loss": 0.2587,
"step": 66500
},
{
"epoch": 3.03,
"learning_rate": 7.4116525240072056e-06,
"loss": 0.219,
"step": 67000
},
{
"epoch": 3.06,
"learning_rate": 7.387573081109196e-06,
"loss": 0.2385,
"step": 67500
},
{
"epoch": 3.08,
"learning_rate": 7.363493638211186e-06,
"loss": 0.2408,
"step": 68000
},
{
"epoch": 3.1,
"learning_rate": 7.339414195313178e-06,
"loss": 0.2248,
"step": 68500
},
{
"epoch": 3.12,
"learning_rate": 7.315334752415169e-06,
"loss": 0.2335,
"step": 69000
},
{
"epoch": 3.15,
"learning_rate": 7.29125530951716e-06,
"loss": 0.2361,
"step": 69500
},
{
"epoch": 3.17,
"learning_rate": 7.2671758666191506e-06,
"loss": 0.2272,
"step": 70000
},
{
"epoch": 3.19,
"learning_rate": 7.2430964237211406e-06,
"loss": 0.2342,
"step": 70500
},
{
"epoch": 3.21,
"learning_rate": 7.219016980823132e-06,
"loss": 0.2288,
"step": 71000
},
{
"epoch": 3.24,
"learning_rate": 7.194937537925123e-06,
"loss": 0.2266,
"step": 71500
},
{
"epoch": 3.26,
"learning_rate": 7.170858095027115e-06,
"loss": 0.2295,
"step": 72000
},
{
"epoch": 3.28,
"learning_rate": 7.146778652129105e-06,
"loss": 0.2118,
"step": 72500
},
{
"epoch": 3.3,
"learning_rate": 7.1226992092310956e-06,
"loss": 0.2187,
"step": 73000
},
{
"epoch": 3.33,
"learning_rate": 7.098619766333087e-06,
"loss": 0.2349,
"step": 73500
},
{
"epoch": 3.35,
"learning_rate": 7.074540323435077e-06,
"loss": 0.2389,
"step": 74000
},
{
"epoch": 3.37,
"learning_rate": 7.050460880537069e-06,
"loss": 0.2285,
"step": 74500
},
{
"epoch": 3.4,
"learning_rate": 7.026381437639059e-06,
"loss": 0.2197,
"step": 75000
},
{
"epoch": 3.42,
"learning_rate": 7.00230199474105e-06,
"loss": 0.2359,
"step": 75500
},
{
"epoch": 3.44,
"learning_rate": 6.9782225518430414e-06,
"loss": 0.2424,
"step": 76000
},
{
"epoch": 3.46,
"learning_rate": 6.954143108945031e-06,
"loss": 0.2292,
"step": 76500
},
{
"epoch": 3.49,
"learning_rate": 6.930063666047023e-06,
"loss": 0.234,
"step": 77000
},
{
"epoch": 3.51,
"learning_rate": 6.905984223149014e-06,
"loss": 0.2342,
"step": 77500
},
{
"epoch": 3.53,
"learning_rate": 6.881904780251004e-06,
"loss": 0.227,
"step": 78000
},
{
"epoch": 3.55,
"learning_rate": 6.857825337352996e-06,
"loss": 0.2349,
"step": 78500
},
{
"epoch": 3.58,
"learning_rate": 6.8337458944549864e-06,
"loss": 0.2356,
"step": 79000
},
{
"epoch": 3.6,
"learning_rate": 6.809666451556978e-06,
"loss": 0.2322,
"step": 79500
},
{
"epoch": 3.62,
"learning_rate": 6.785587008658968e-06,
"loss": 0.2368,
"step": 80000
},
{
"epoch": 3.64,
"learning_rate": 6.761507565760959e-06,
"loss": 0.2254,
"step": 80500
},
{
"epoch": 3.67,
"learning_rate": 6.73742812286295e-06,
"loss": 0.2488,
"step": 81000
},
{
"epoch": 3.69,
"learning_rate": 6.713348679964941e-06,
"loss": 0.2403,
"step": 81500
},
{
"epoch": 3.71,
"learning_rate": 6.689269237066932e-06,
"loss": 0.2371,
"step": 82000
},
{
"epoch": 3.73,
"learning_rate": 6.665189794168922e-06,
"loss": 0.2305,
"step": 82500
},
{
"epoch": 3.76,
"learning_rate": 6.641110351270914e-06,
"loss": 0.2355,
"step": 83000
},
{
"epoch": 3.78,
"learning_rate": 6.617030908372905e-06,
"loss": 0.2453,
"step": 83500
},
{
"epoch": 3.8,
"learning_rate": 6.592951465474895e-06,
"loss": 0.2406,
"step": 84000
},
{
"epoch": 3.83,
"learning_rate": 6.5688720225768865e-06,
"loss": 0.2417,
"step": 84500
},
{
"epoch": 3.85,
"learning_rate": 6.544792579678877e-06,
"loss": 0.2453,
"step": 85000
},
{
"epoch": 3.87,
"learning_rate": 6.520713136780868e-06,
"loss": 0.2365,
"step": 85500
},
{
"epoch": 3.89,
"learning_rate": 6.496633693882859e-06,
"loss": 0.2447,
"step": 86000
},
{
"epoch": 3.92,
"learning_rate": 6.472554250984849e-06,
"loss": 0.2441,
"step": 86500
},
{
"epoch": 3.94,
"learning_rate": 6.448474808086841e-06,
"loss": 0.2314,
"step": 87000
},
{
"epoch": 3.96,
"learning_rate": 6.4243953651888315e-06,
"loss": 0.2402,
"step": 87500
},
{
"epoch": 3.98,
"learning_rate": 6.400315922290823e-06,
"loss": 0.235,
"step": 88000
},
{
"epoch": 4.0,
"eval_accuracy": 0.8673575921163199,
"eval_loss": 0.500419020652771,
"eval_runtime": 48.6048,
"eval_samples_per_second": 807.965,
"eval_steps_per_second": 50.509,
"step": 88360
},
{
"epoch": 4.01,
"learning_rate": 6.376236479392813e-06,
"loss": 0.2287,
"step": 88500
},
{
"epoch": 4.03,
"learning_rate": 6.352157036494804e-06,
"loss": 0.1927,
"step": 89000
},
{
"epoch": 4.05,
"learning_rate": 6.328077593596796e-06,
"loss": 0.1863,
"step": 89500
},
{
"epoch": 4.07,
"learning_rate": 6.303998150698786e-06,
"loss": 0.1964,
"step": 90000
},
{
"epoch": 4.1,
"learning_rate": 6.279918707800777e-06,
"loss": 0.2044,
"step": 90500
},
{
"epoch": 4.12,
"learning_rate": 6.255839264902767e-06,
"loss": 0.1911,
"step": 91000
},
{
"epoch": 4.14,
"learning_rate": 6.231759822004758e-06,
"loss": 0.2,
"step": 91500
},
{
"epoch": 4.16,
"learning_rate": 6.20768037910675e-06,
"loss": 0.1866,
"step": 92000
},
{
"epoch": 4.19,
"learning_rate": 6.18360093620874e-06,
"loss": 0.2139,
"step": 92500
},
{
"epoch": 4.21,
"learning_rate": 6.1595214933107315e-06,
"loss": 0.2048,
"step": 93000
},
{
"epoch": 4.23,
"learning_rate": 6.135442050412722e-06,
"loss": 0.1956,
"step": 93500
},
{
"epoch": 4.26,
"learning_rate": 6.111362607514712e-06,
"loss": 0.2057,
"step": 94000
},
{
"epoch": 4.28,
"learning_rate": 6.087283164616704e-06,
"loss": 0.1986,
"step": 94500
},
{
"epoch": 4.3,
"learning_rate": 6.063203721718695e-06,
"loss": 0.2022,
"step": 95000
},
{
"epoch": 4.32,
"learning_rate": 6.039124278820686e-06,
"loss": 0.1933,
"step": 95500
},
{
"epoch": 4.35,
"learning_rate": 6.0150448359226765e-06,
"loss": 0.1929,
"step": 96000
},
{
"epoch": 4.37,
"learning_rate": 5.990965393024667e-06,
"loss": 0.2034,
"step": 96500
},
{
"epoch": 4.39,
"learning_rate": 5.966885950126658e-06,
"loss": 0.1978,
"step": 97000
},
{
"epoch": 4.41,
"learning_rate": 5.942806507228649e-06,
"loss": 0.1988,
"step": 97500
},
{
"epoch": 4.44,
"learning_rate": 5.918727064330641e-06,
"loss": 0.2131,
"step": 98000
},
{
"epoch": 4.46,
"learning_rate": 5.894647621432631e-06,
"loss": 0.1982,
"step": 98500
},
{
"epoch": 4.48,
"learning_rate": 5.8705681785346215e-06,
"loss": 0.2076,
"step": 99000
},
{
"epoch": 4.5,
"learning_rate": 5.846488735636613e-06,
"loss": 0.1987,
"step": 99500
},
{
"epoch": 4.53,
"learning_rate": 5.822409292738603e-06,
"loss": 0.2144,
"step": 100000
},
{
"epoch": 4.55,
"learning_rate": 5.798329849840595e-06,
"loss": 0.2038,
"step": 100500
},
{
"epoch": 4.57,
"learning_rate": 5.774250406942586e-06,
"loss": 0.1908,
"step": 101000
},
{
"epoch": 4.59,
"learning_rate": 5.7501709640445765e-06,
"loss": 0.2056,
"step": 101500
},
{
"epoch": 4.62,
"learning_rate": 5.726091521146567e-06,
"loss": 0.2038,
"step": 102000
},
{
"epoch": 4.64,
"learning_rate": 5.702012078248557e-06,
"loss": 0.2099,
"step": 102500
},
{
"epoch": 4.66,
"learning_rate": 5.677932635350549e-06,
"loss": 0.2048,
"step": 103000
},
{
"epoch": 4.69,
"learning_rate": 5.65385319245254e-06,
"loss": 0.2072,
"step": 103500
},
{
"epoch": 4.71,
"learning_rate": 5.6297737495545315e-06,
"loss": 0.2155,
"step": 104000
},
{
"epoch": 4.73,
"learning_rate": 5.6056943066565215e-06,
"loss": 0.2044,
"step": 104500
},
{
"epoch": 4.75,
"learning_rate": 5.581614863758512e-06,
"loss": 0.203,
"step": 105000
},
{
"epoch": 4.78,
"learning_rate": 5.557535420860504e-06,
"loss": 0.2003,
"step": 105500
},
{
"epoch": 4.8,
"learning_rate": 5.533455977962494e-06,
"loss": 0.1985,
"step": 106000
},
{
"epoch": 4.82,
"learning_rate": 5.509376535064486e-06,
"loss": 0.2197,
"step": 106500
},
{
"epoch": 4.84,
"learning_rate": 5.485297092166476e-06,
"loss": 0.1965,
"step": 107000
},
{
"epoch": 4.87,
"learning_rate": 5.4612176492684665e-06,
"loss": 0.2217,
"step": 107500
},
{
"epoch": 4.89,
"learning_rate": 5.437138206370458e-06,
"loss": 0.1977,
"step": 108000
},
{
"epoch": 4.91,
"learning_rate": 5.413058763472448e-06,
"loss": 0.214,
"step": 108500
},
{
"epoch": 4.93,
"learning_rate": 5.38897932057444e-06,
"loss": 0.196,
"step": 109000
},
{
"epoch": 4.96,
"learning_rate": 5.364899877676431e-06,
"loss": 0.2213,
"step": 109500
},
{
"epoch": 4.98,
"learning_rate": 5.340820434778421e-06,
"loss": 0.2114,
"step": 110000
},
{
"epoch": 5.0,
"eval_accuracy": 0.8639454050062387,
"eval_loss": 0.601565957069397,
"eval_runtime": 48.6094,
"eval_samples_per_second": 807.89,
"eval_steps_per_second": 50.505,
"step": 110450
},
{
"epoch": 5.0,
"learning_rate": 5.316740991880412e-06,
"loss": 0.2042,
"step": 110500
},
{
"epoch": 5.02,
"learning_rate": 5.292661548982403e-06,
"loss": 0.1637,
"step": 111000
},
{
"epoch": 5.05,
"learning_rate": 5.268582106084394e-06,
"loss": 0.157,
"step": 111500
},
{
"epoch": 5.07,
"learning_rate": 5.244502663186385e-06,
"loss": 0.1711,
"step": 112000
},
{
"epoch": 5.09,
"learning_rate": 5.220423220288376e-06,
"loss": 0.1664,
"step": 112500
},
{
"epoch": 5.12,
"learning_rate": 5.1963437773903666e-06,
"loss": 0.181,
"step": 113000
},
{
"epoch": 5.14,
"learning_rate": 5.172264334492357e-06,
"loss": 0.1686,
"step": 113500
},
{
"epoch": 5.16,
"learning_rate": 5.148184891594349e-06,
"loss": 0.165,
"step": 114000
},
{
"epoch": 5.18,
"learning_rate": 5.124105448696339e-06,
"loss": 0.1811,
"step": 114500
},
{
"epoch": 5.21,
"learning_rate": 5.10002600579833e-06,
"loss": 0.1765,
"step": 115000
},
{
"epoch": 5.23,
"learning_rate": 5.075946562900322e-06,
"loss": 0.1722,
"step": 115500
},
{
"epoch": 5.25,
"learning_rate": 5.0518671200023116e-06,
"loss": 0.1681,
"step": 116000
},
{
"epoch": 5.27,
"learning_rate": 5.027787677104303e-06,
"loss": 0.1981,
"step": 116500
},
{
"epoch": 5.3,
"learning_rate": 5.003708234206294e-06,
"loss": 0.1709,
"step": 117000
},
{
"epoch": 5.32,
"learning_rate": 4.979628791308285e-06,
"loss": 0.1647,
"step": 117500
},
{
"epoch": 5.34,
"learning_rate": 4.955549348410276e-06,
"loss": 0.1816,
"step": 118000
},
{
"epoch": 5.36,
"learning_rate": 4.931469905512267e-06,
"loss": 0.175,
"step": 118500
},
{
"epoch": 5.39,
"learning_rate": 4.9073904626142574e-06,
"loss": 0.187,
"step": 119000
},
{
"epoch": 5.41,
"learning_rate": 4.883311019716248e-06,
"loss": 0.1799,
"step": 119500
},
{
"epoch": 5.43,
"learning_rate": 4.859231576818239e-06,
"loss": 0.1813,
"step": 120000
},
{
"epoch": 5.45,
"learning_rate": 4.83515213392023e-06,
"loss": 0.1883,
"step": 120500
},
{
"epoch": 5.48,
"learning_rate": 4.811072691022221e-06,
"loss": 0.1863,
"step": 121000
},
{
"epoch": 5.5,
"learning_rate": 4.7869932481242124e-06,
"loss": 0.1856,
"step": 121500
},
{
"epoch": 5.52,
"learning_rate": 4.7629138052262024e-06,
"loss": 0.1633,
"step": 122000
},
{
"epoch": 5.55,
"learning_rate": 4.738834362328193e-06,
"loss": 0.1863,
"step": 122500
},
{
"epoch": 5.57,
"learning_rate": 4.714754919430184e-06,
"loss": 0.1779,
"step": 123000
},
{
"epoch": 5.59,
"learning_rate": 4.690675476532176e-06,
"loss": 0.1851,
"step": 123500
},
{
"epoch": 5.61,
"learning_rate": 4.666596033634167e-06,
"loss": 0.173,
"step": 124000
},
{
"epoch": 5.64,
"learning_rate": 4.642516590736157e-06,
"loss": 0.1748,
"step": 124500
},
{
"epoch": 5.66,
"learning_rate": 4.618437147838148e-06,
"loss": 0.1782,
"step": 125000
},
{
"epoch": 5.68,
"learning_rate": 4.594357704940139e-06,
"loss": 0.1777,
"step": 125500
},
{
"epoch": 5.7,
"learning_rate": 4.57027826204213e-06,
"loss": 0.1807,
"step": 126000
},
{
"epoch": 5.73,
"learning_rate": 4.546198819144121e-06,
"loss": 0.179,
"step": 126500
},
{
"epoch": 5.75,
"learning_rate": 4.522119376246112e-06,
"loss": 0.1745,
"step": 127000
},
{
"epoch": 5.77,
"learning_rate": 4.4980399333481025e-06,
"loss": 0.1886,
"step": 127500
},
{
"epoch": 5.79,
"learning_rate": 4.473960490450093e-06,
"loss": 0.1708,
"step": 128000
},
{
"epoch": 5.82,
"learning_rate": 4.449881047552084e-06,
"loss": 0.1712,
"step": 128500
},
{
"epoch": 5.84,
"learning_rate": 4.425801604654075e-06,
"loss": 0.1946,
"step": 129000
},
{
"epoch": 5.86,
"learning_rate": 4.401722161756066e-06,
"loss": 0.1772,
"step": 129500
},
{
"epoch": 5.89,
"learning_rate": 4.377642718858057e-06,
"loss": 0.1873,
"step": 130000
},
{
"epoch": 5.91,
"learning_rate": 4.3535632759600475e-06,
"loss": 0.1895,
"step": 130500
},
{
"epoch": 5.93,
"learning_rate": 4.329483833062038e-06,
"loss": 0.1782,
"step": 131000
},
{
"epoch": 5.95,
"learning_rate": 4.30540439016403e-06,
"loss": 0.1915,
"step": 131500
},
{
"epoch": 5.98,
"learning_rate": 4.281324947266021e-06,
"loss": 0.1826,
"step": 132000
},
{
"epoch": 6.0,
"learning_rate": 4.257245504368011e-06,
"loss": 0.1833,
"step": 132500
},
{
"epoch": 6.0,
"eval_accuracy": 0.8642509740011713,
"eval_loss": 0.6854547262191772,
"eval_runtime": 48.5441,
"eval_samples_per_second": 808.975,
"eval_steps_per_second": 50.573,
"step": 132540
},
{
"epoch": 6.02,
"learning_rate": 4.2331660614700025e-06,
"loss": 0.1409,
"step": 133000
},
{
"epoch": 6.04,
"learning_rate": 4.209086618571993e-06,
"loss": 0.1583,
"step": 133500
},
{
"epoch": 6.07,
"learning_rate": 4.185007175673984e-06,
"loss": 0.1503,
"step": 134000
},
{
"epoch": 6.09,
"learning_rate": 4.160927732775975e-06,
"loss": 0.1372,
"step": 134500
},
{
"epoch": 6.11,
"learning_rate": 4.136848289877966e-06,
"loss": 0.1332,
"step": 135000
},
{
"epoch": 6.13,
"learning_rate": 4.112768846979957e-06,
"loss": 0.1528,
"step": 135500
},
{
"epoch": 6.16,
"learning_rate": 4.0886894040819475e-06,
"loss": 0.1367,
"step": 136000
},
{
"epoch": 6.18,
"learning_rate": 4.064609961183938e-06,
"loss": 0.1456,
"step": 136500
},
{
"epoch": 6.2,
"learning_rate": 4.040530518285929e-06,
"loss": 0.1674,
"step": 137000
},
{
"epoch": 6.22,
"learning_rate": 4.01645107538792e-06,
"loss": 0.1465,
"step": 137500
},
{
"epoch": 6.25,
"learning_rate": 3.992371632489911e-06,
"loss": 0.1492,
"step": 138000
},
{
"epoch": 6.27,
"learning_rate": 3.968292189591902e-06,
"loss": 0.149,
"step": 138500
},
{
"epoch": 6.29,
"learning_rate": 3.9442127466938925e-06,
"loss": 0.1539,
"step": 139000
},
{
"epoch": 6.32,
"learning_rate": 3.920133303795884e-06,
"loss": 0.1339,
"step": 139500
},
{
"epoch": 6.34,
"learning_rate": 3.896053860897875e-06,
"loss": 0.142,
"step": 140000
},
{
"epoch": 6.36,
"learning_rate": 3.871974417999865e-06,
"loss": 0.1504,
"step": 140500
},
{
"epoch": 6.38,
"learning_rate": 3.847894975101857e-06,
"loss": 0.1578,
"step": 141000
},
{
"epoch": 6.41,
"learning_rate": 3.8238155322038475e-06,
"loss": 0.1491,
"step": 141500
},
{
"epoch": 6.43,
"learning_rate": 3.7997360893058384e-06,
"loss": 0.1673,
"step": 142000
},
{
"epoch": 6.45,
"learning_rate": 3.775656646407829e-06,
"loss": 0.1416,
"step": 142500
},
{
"epoch": 6.47,
"learning_rate": 3.7515772035098196e-06,
"loss": 0.1607,
"step": 143000
},
{
"epoch": 6.5,
"learning_rate": 3.727497760611811e-06,
"loss": 0.1386,
"step": 143500
},
{
"epoch": 6.52,
"learning_rate": 3.7034183177138017e-06,
"loss": 0.1455,
"step": 144000
},
{
"epoch": 6.54,
"learning_rate": 3.6793388748157925e-06,
"loss": 0.152,
"step": 144500
},
{
"epoch": 6.56,
"learning_rate": 3.6552594319177838e-06,
"loss": 0.1533,
"step": 145000
},
{
"epoch": 6.59,
"learning_rate": 3.631179989019774e-06,
"loss": 0.1491,
"step": 145500
},
{
"epoch": 6.61,
"learning_rate": 3.607100546121765e-06,
"loss": 0.1392,
"step": 146000
},
{
"epoch": 6.63,
"learning_rate": 3.583021103223756e-06,
"loss": 0.1454,
"step": 146500
},
{
"epoch": 6.65,
"learning_rate": 3.558941660325747e-06,
"loss": 0.1639,
"step": 147000
},
{
"epoch": 6.68,
"learning_rate": 3.534862217427738e-06,
"loss": 0.1458,
"step": 147500
},
{
"epoch": 6.7,
"learning_rate": 3.5107827745297292e-06,
"loss": 0.1563,
"step": 148000
},
{
"epoch": 6.72,
"learning_rate": 3.4867033316317196e-06,
"loss": 0.1613,
"step": 148500
},
{
"epoch": 6.75,
"learning_rate": 3.4626238887337105e-06,
"loss": 0.1332,
"step": 149000
},
{
"epoch": 6.77,
"learning_rate": 3.4385444458357013e-06,
"loss": 0.1543,
"step": 149500
},
{
"epoch": 6.79,
"learning_rate": 3.4144650029376926e-06,
"loss": 0.1649,
"step": 150000
},
{
"epoch": 6.81,
"learning_rate": 3.3903855600396834e-06,
"loss": 0.1393,
"step": 150500
},
{
"epoch": 6.84,
"learning_rate": 3.366306117141674e-06,
"loss": 0.1463,
"step": 151000
},
{
"epoch": 6.86,
"learning_rate": 3.342226674243665e-06,
"loss": 0.1468,
"step": 151500
},
{
"epoch": 6.88,
"learning_rate": 3.318147231345656e-06,
"loss": 0.152,
"step": 152000
},
{
"epoch": 6.9,
"learning_rate": 3.2940677884476467e-06,
"loss": 0.1509,
"step": 152500
},
{
"epoch": 6.93,
"learning_rate": 3.269988345549638e-06,
"loss": 0.1548,
"step": 153000
},
{
"epoch": 6.95,
"learning_rate": 3.2459089026516284e-06,
"loss": 0.1452,
"step": 153500
},
{
"epoch": 6.97,
"learning_rate": 3.2218294597536192e-06,
"loss": 0.1461,
"step": 154000
},
{
"epoch": 6.99,
"learning_rate": 3.19775001685561e-06,
"loss": 0.1568,
"step": 154500
},
{
"epoch": 7.0,
"eval_accuracy": 0.8665936696289883,
"eval_loss": 0.773478090763092,
"eval_runtime": 48.6355,
"eval_samples_per_second": 807.455,
"eval_steps_per_second": 50.478,
"step": 154630
},
{
"epoch": 7.02,
"learning_rate": 3.1736705739576013e-06,
"loss": 0.1257,
"step": 155000
},
{
"epoch": 7.04,
"learning_rate": 3.149591131059592e-06,
"loss": 0.1142,
"step": 155500
},
{
"epoch": 7.06,
"learning_rate": 3.1255116881615826e-06,
"loss": 0.1063,
"step": 156000
},
{
"epoch": 7.08,
"learning_rate": 3.101432245263574e-06,
"loss": 0.1294,
"step": 156500
},
{
"epoch": 7.11,
"learning_rate": 3.0773528023655647e-06,
"loss": 0.1166,
"step": 157000
},
{
"epoch": 7.13,
"learning_rate": 3.0532733594675555e-06,
"loss": 0.1169,
"step": 157500
},
{
"epoch": 7.15,
"learning_rate": 3.0291939165695468e-06,
"loss": 0.1244,
"step": 158000
},
{
"epoch": 7.18,
"learning_rate": 3.0051144736715376e-06,
"loss": 0.1211,
"step": 158500
},
{
"epoch": 7.2,
"learning_rate": 2.981035030773528e-06,
"loss": 0.131,
"step": 159000
},
{
"epoch": 7.22,
"learning_rate": 2.9569555878755193e-06,
"loss": 0.1229,
"step": 159500
},
{
"epoch": 7.24,
"learning_rate": 2.93287614497751e-06,
"loss": 0.1208,
"step": 160000
},
{
"epoch": 7.27,
"learning_rate": 2.908796702079501e-06,
"loss": 0.1207,
"step": 160500
},
{
"epoch": 7.29,
"learning_rate": 2.884717259181492e-06,
"loss": 0.1161,
"step": 161000
},
{
"epoch": 7.31,
"learning_rate": 2.8606378162834826e-06,
"loss": 0.1362,
"step": 161500
},
{
"epoch": 7.33,
"learning_rate": 2.8365583733854734e-06,
"loss": 0.1261,
"step": 162000
},
{
"epoch": 7.36,
"learning_rate": 2.8124789304874643e-06,
"loss": 0.1091,
"step": 162500
},
{
"epoch": 7.38,
"learning_rate": 2.7883994875894555e-06,
"loss": 0.126,
"step": 163000
},
{
"epoch": 7.4,
"learning_rate": 2.7643200446914464e-06,
"loss": 0.127,
"step": 163500
},
{
"epoch": 7.42,
"learning_rate": 2.7402406017934368e-06,
"loss": 0.118,
"step": 164000
},
{
"epoch": 7.45,
"learning_rate": 2.716161158895428e-06,
"loss": 0.1368,
"step": 164500
},
{
"epoch": 7.47,
"learning_rate": 2.692081715997419e-06,
"loss": 0.1225,
"step": 165000
},
{
"epoch": 7.49,
"learning_rate": 2.6680022730994097e-06,
"loss": 0.1095,
"step": 165500
},
{
"epoch": 7.51,
"learning_rate": 2.643922830201401e-06,
"loss": 0.126,
"step": 166000
},
{
"epoch": 7.54,
"learning_rate": 2.6198433873033918e-06,
"loss": 0.1212,
"step": 166500
},
{
"epoch": 7.56,
"learning_rate": 2.595763944405382e-06,
"loss": 0.1326,
"step": 167000
},
{
"epoch": 7.58,
"learning_rate": 2.5716845015073735e-06,
"loss": 0.1343,
"step": 167500
},
{
"epoch": 7.61,
"learning_rate": 2.5476050586093643e-06,
"loss": 0.1089,
"step": 168000
},
{
"epoch": 7.63,
"learning_rate": 2.523525615711355e-06,
"loss": 0.1358,
"step": 168500
},
{
"epoch": 7.65,
"learning_rate": 2.499446172813346e-06,
"loss": 0.1231,
"step": 169000
},
{
"epoch": 7.67,
"learning_rate": 2.475366729915337e-06,
"loss": 0.1261,
"step": 169500
},
{
"epoch": 7.7,
"learning_rate": 2.4512872870173276e-06,
"loss": 0.122,
"step": 170000
},
{
"epoch": 7.72,
"learning_rate": 2.4272078441193185e-06,
"loss": 0.1233,
"step": 170500
},
{
"epoch": 7.74,
"learning_rate": 2.4031284012213097e-06,
"loss": 0.1327,
"step": 171000
},
{
"epoch": 7.76,
"learning_rate": 2.3790489583233006e-06,
"loss": 0.1214,
"step": 171500
},
{
"epoch": 7.79,
"learning_rate": 2.3549695154252914e-06,
"loss": 0.1225,
"step": 172000
},
{
"epoch": 7.81,
"learning_rate": 2.3308900725272822e-06,
"loss": 0.1247,
"step": 172500
},
{
"epoch": 7.83,
"learning_rate": 2.306810629629273e-06,
"loss": 0.119,
"step": 173000
},
{
"epoch": 7.85,
"learning_rate": 2.282731186731264e-06,
"loss": 0.1275,
"step": 173500
},
{
"epoch": 7.88,
"learning_rate": 2.2586517438332547e-06,
"loss": 0.1158,
"step": 174000
},
{
"epoch": 7.9,
"learning_rate": 2.2345723009352456e-06,
"loss": 0.1156,
"step": 174500
},
{
"epoch": 7.92,
"learning_rate": 2.210492858037237e-06,
"loss": 0.1313,
"step": 175000
},
{
"epoch": 7.94,
"learning_rate": 2.1864134151392277e-06,
"loss": 0.1301,
"step": 175500
},
{
"epoch": 7.97,
"learning_rate": 2.1623339722412185e-06,
"loss": 0.1198,
"step": 176000
},
{
"epoch": 7.99,
"learning_rate": 2.1382545293432093e-06,
"loss": 0.1237,
"step": 176500
},
{
"epoch": 8.0,
"eval_accuracy": 0.8664918132973441,
"eval_loss": 0.8249724507331848,
"eval_runtime": 48.4679,
"eval_samples_per_second": 810.247,
"eval_steps_per_second": 50.652,
"step": 176720
},
{
"epoch": 8.01,
"learning_rate": 2.1141750864452e-06,
"loss": 0.1008,
"step": 177000
},
{
"epoch": 8.04,
"learning_rate": 2.090095643547191e-06,
"loss": 0.0971,
"step": 177500
},
{
"epoch": 8.06,
"learning_rate": 2.066016200649182e-06,
"loss": 0.1021,
"step": 178000
},
{
"epoch": 8.08,
"learning_rate": 2.0419367577511727e-06,
"loss": 0.1067,
"step": 178500
},
{
"epoch": 8.1,
"learning_rate": 2.017857314853164e-06,
"loss": 0.0989,
"step": 179000
},
{
"epoch": 8.13,
"learning_rate": 1.9937778719551548e-06,
"loss": 0.1049,
"step": 179500
},
{
"epoch": 8.15,
"learning_rate": 1.9696984290571456e-06,
"loss": 0.1154,
"step": 180000
},
{
"epoch": 8.17,
"learning_rate": 1.9456189861591364e-06,
"loss": 0.0919,
"step": 180500
},
{
"epoch": 8.19,
"learning_rate": 1.9215395432611273e-06,
"loss": 0.1185,
"step": 181000
},
{
"epoch": 8.22,
"learning_rate": 1.8974601003631183e-06,
"loss": 0.0943,
"step": 181500
},
{
"epoch": 8.24,
"learning_rate": 1.873380657465109e-06,
"loss": 0.1093,
"step": 182000
},
{
"epoch": 8.26,
"learning_rate": 1.8493012145671e-06,
"loss": 0.0948,
"step": 182500
},
{
"epoch": 8.28,
"learning_rate": 1.825221771669091e-06,
"loss": 0.0984,
"step": 183000
},
{
"epoch": 8.31,
"learning_rate": 1.8011423287710816e-06,
"loss": 0.1063,
"step": 183500
},
{
"epoch": 8.33,
"learning_rate": 1.7770628858730727e-06,
"loss": 0.1084,
"step": 184000
},
{
"epoch": 8.35,
"learning_rate": 1.7529834429750633e-06,
"loss": 0.0988,
"step": 184500
},
{
"epoch": 8.37,
"learning_rate": 1.7289040000770544e-06,
"loss": 0.091,
"step": 185000
},
{
"epoch": 8.4,
"learning_rate": 1.7048245571790454e-06,
"loss": 0.1077,
"step": 185500
},
{
"epoch": 8.42,
"learning_rate": 1.680745114281036e-06,
"loss": 0.0997,
"step": 186000
},
{
"epoch": 8.44,
"learning_rate": 1.656665671383027e-06,
"loss": 0.0898,
"step": 186500
},
{
"epoch": 8.47,
"learning_rate": 1.6325862284850181e-06,
"loss": 0.1011,
"step": 187000
},
{
"epoch": 8.49,
"learning_rate": 1.6085067855870087e-06,
"loss": 0.1043,
"step": 187500
},
{
"epoch": 8.51,
"learning_rate": 1.5844273426889998e-06,
"loss": 0.0891,
"step": 188000
},
{
"epoch": 8.53,
"learning_rate": 1.5603478997909904e-06,
"loss": 0.0992,
"step": 188500
},
{
"epoch": 8.56,
"learning_rate": 1.5362684568929815e-06,
"loss": 0.1055,
"step": 189000
},
{
"epoch": 8.58,
"learning_rate": 1.5121890139949725e-06,
"loss": 0.1032,
"step": 189500
},
{
"epoch": 8.6,
"learning_rate": 1.4881095710969631e-06,
"loss": 0.0945,
"step": 190000
},
{
"epoch": 8.62,
"learning_rate": 1.4640301281989542e-06,
"loss": 0.1159,
"step": 190500
},
{
"epoch": 8.65,
"learning_rate": 1.4399506853009452e-06,
"loss": 0.1016,
"step": 191000
},
{
"epoch": 8.67,
"learning_rate": 1.4158712424029358e-06,
"loss": 0.1024,
"step": 191500
},
{
"epoch": 8.69,
"learning_rate": 1.3917917995049269e-06,
"loss": 0.101,
"step": 192000
},
{
"epoch": 8.71,
"learning_rate": 1.3677123566069175e-06,
"loss": 0.0962,
"step": 192500
},
{
"epoch": 8.74,
"learning_rate": 1.3436329137089086e-06,
"loss": 0.0986,
"step": 193000
},
{
"epoch": 8.76,
"learning_rate": 1.3195534708108996e-06,
"loss": 0.0963,
"step": 193500
},
{
"epoch": 8.78,
"learning_rate": 1.2954740279128902e-06,
"loss": 0.1238,
"step": 194000
},
{
"epoch": 8.8,
"learning_rate": 1.2713945850148813e-06,
"loss": 0.1001,
"step": 194500
},
{
"epoch": 8.83,
"learning_rate": 1.247315142116872e-06,
"loss": 0.0972,
"step": 195000
},
{
"epoch": 8.85,
"learning_rate": 1.223235699218863e-06,
"loss": 0.091,
"step": 195500
},
{
"epoch": 8.87,
"learning_rate": 1.199156256320854e-06,
"loss": 0.1058,
"step": 196000
},
{
"epoch": 8.9,
"learning_rate": 1.1750768134228448e-06,
"loss": 0.0957,
"step": 196500
},
{
"epoch": 8.92,
"learning_rate": 1.1509973705248357e-06,
"loss": 0.0979,
"step": 197000
},
{
"epoch": 8.94,
"learning_rate": 1.1269179276268265e-06,
"loss": 0.1084,
"step": 197500
},
{
"epoch": 8.96,
"learning_rate": 1.1028384847288175e-06,
"loss": 0.0963,
"step": 198000
},
{
"epoch": 8.99,
"learning_rate": 1.0787590418308084e-06,
"loss": 0.0908,
"step": 198500
},
{
"epoch": 9.0,
"eval_accuracy": 0.8667973822922768,
"eval_loss": 0.9133633375167847,
"eval_runtime": 48.4125,
"eval_samples_per_second": 811.174,
"eval_steps_per_second": 50.71,
"step": 198810
},
{
"epoch": 9.01,
"learning_rate": 1.0546795989327992e-06,
"loss": 0.084,
"step": 199000
},
{
"epoch": 9.03,
"learning_rate": 1.03060015603479e-06,
"loss": 0.0891,
"step": 199500
},
{
"epoch": 9.05,
"learning_rate": 1.006520713136781e-06,
"loss": 0.1038,
"step": 200000
},
{
"epoch": 9.08,
"learning_rate": 9.82441270238772e-07,
"loss": 0.0778,
"step": 200500
},
{
"epoch": 9.1,
"learning_rate": 9.583618273407628e-07,
"loss": 0.0917,
"step": 201000
},
{
"epoch": 9.12,
"learning_rate": 9.342823844427536e-07,
"loss": 0.0924,
"step": 201500
},
{
"epoch": 9.14,
"learning_rate": 9.102029415447445e-07,
"loss": 0.077,
"step": 202000
},
{
"epoch": 9.17,
"learning_rate": 8.861234986467354e-07,
"loss": 0.0851,
"step": 202500
},
{
"epoch": 9.19,
"learning_rate": 8.620440557487263e-07,
"loss": 0.0897,
"step": 203000
},
{
"epoch": 9.21,
"learning_rate": 8.379646128507171e-07,
"loss": 0.0844,
"step": 203500
},
{
"epoch": 9.23,
"learning_rate": 8.138851699527081e-07,
"loss": 0.0845,
"step": 204000
},
{
"epoch": 9.26,
"learning_rate": 7.898057270546989e-07,
"loss": 0.0918,
"step": 204500
},
{
"epoch": 9.28,
"learning_rate": 7.657262841566899e-07,
"loss": 0.0792,
"step": 205000
},
{
"epoch": 9.3,
"learning_rate": 7.416468412586807e-07,
"loss": 0.0737,
"step": 205500
},
{
"epoch": 9.33,
"learning_rate": 7.175673983606715e-07,
"loss": 0.0806,
"step": 206000
},
{
"epoch": 9.35,
"learning_rate": 6.934879554626625e-07,
"loss": 0.0843,
"step": 206500
},
{
"epoch": 9.37,
"learning_rate": 6.694085125646534e-07,
"loss": 0.0823,
"step": 207000
},
{
"epoch": 9.39,
"learning_rate": 6.453290696666442e-07,
"loss": 0.0851,
"step": 207500
},
{
"epoch": 9.42,
"learning_rate": 6.212496267686352e-07,
"loss": 0.073,
"step": 208000
},
{
"epoch": 9.44,
"learning_rate": 5.97170183870626e-07,
"loss": 0.0872,
"step": 208500
},
{
"epoch": 9.46,
"learning_rate": 5.73090740972617e-07,
"loss": 0.0905,
"step": 209000
},
{
"epoch": 9.48,
"learning_rate": 5.490112980746078e-07,
"loss": 0.0846,
"step": 209500
},
{
"epoch": 9.51,
"learning_rate": 5.249318551765987e-07,
"loss": 0.0733,
"step": 210000
},
{
"epoch": 9.53,
"learning_rate": 5.008524122785896e-07,
"loss": 0.0926,
"step": 210500
},
{
"epoch": 9.55,
"learning_rate": 4.7677296938058045e-07,
"loss": 0.0767,
"step": 211000
},
{
"epoch": 9.57,
"learning_rate": 4.526935264825713e-07,
"loss": 0.0852,
"step": 211500
},
{
"epoch": 9.6,
"learning_rate": 4.286140835845622e-07,
"loss": 0.0815,
"step": 212000
},
{
"epoch": 9.62,
"learning_rate": 4.0453464068655306e-07,
"loss": 0.0965,
"step": 212500
},
{
"epoch": 9.64,
"learning_rate": 3.80455197788544e-07,
"loss": 0.0858,
"step": 213000
},
{
"epoch": 9.67,
"learning_rate": 3.5637575489053483e-07,
"loss": 0.0845,
"step": 213500
},
{
"epoch": 9.69,
"learning_rate": 3.322963119925258e-07,
"loss": 0.0901,
"step": 214000
},
{
"epoch": 9.71,
"learning_rate": 3.0821686909451666e-07,
"loss": 0.0871,
"step": 214500
},
{
"epoch": 9.73,
"learning_rate": 2.8413742619650755e-07,
"loss": 0.0868,
"step": 215000
},
{
"epoch": 9.76,
"learning_rate": 2.6005798329849844e-07,
"loss": 0.0817,
"step": 215500
},
{
"epoch": 9.78,
"learning_rate": 2.3597854040048932e-07,
"loss": 0.0793,
"step": 216000
},
{
"epoch": 9.8,
"learning_rate": 2.118990975024802e-07,
"loss": 0.0981,
"step": 216500
},
{
"epoch": 9.82,
"learning_rate": 1.878196546044711e-07,
"loss": 0.0746,
"step": 217000
},
{
"epoch": 9.85,
"learning_rate": 1.6374021170646199e-07,
"loss": 0.0812,
"step": 217500
},
{
"epoch": 9.87,
"learning_rate": 1.3966076880845285e-07,
"loss": 0.0848,
"step": 218000
},
{
"epoch": 9.89,
"learning_rate": 1.1558132591044375e-07,
"loss": 0.0777,
"step": 218500
},
{
"epoch": 9.91,
"learning_rate": 9.150188301243464e-08,
"loss": 0.0876,
"step": 219000
},
{
"epoch": 9.94,
"learning_rate": 6.742244011442552e-08,
"loss": 0.0948,
"step": 219500
},
{
"epoch": 9.96,
"learning_rate": 4.3342997216416404e-08,
"loss": 0.0859,
"step": 220000
},
{
"epoch": 9.98,
"learning_rate": 1.926355431840729e-08,
"loss": 0.0832,
"step": 220500
},
{
"epoch": 10.0,
"eval_accuracy": 0.867408520282142,
"eval_loss": 0.9269108176231384,
"eval_runtime": 48.3924,
"eval_samples_per_second": 811.511,
"eval_steps_per_second": 50.731,
"step": 220900
},
{
"epoch": 10.0,
"step": 220900,
"total_flos": 1.4385611002158144e+17,
"train_loss": 0.2250993330244459,
"train_runtime": 14146.4436,
"train_samples_per_second": 249.837,
"train_steps_per_second": 15.615
}
],
"logging_steps": 500,
"max_steps": 220900,
"num_train_epochs": 10,
"save_steps": 500,
"total_flos": 1.4385611002158144e+17,
"trial_name": null,
"trial_params": null
}