project-code-py-neo / trainer_state.json
gagan3012's picture
Initial commit updates
e28fae4
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 5.0,
"global_step": 56765,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.04,
"learning_rate": 4.9562230247511674e-05,
"loss": 2.0275,
"step": 500
},
{
"epoch": 0.09,
"learning_rate": 4.912269884611997e-05,
"loss": 2.0037,
"step": 1000
},
{
"epoch": 0.13,
"learning_rate": 4.868228662027658e-05,
"loss": 1.9314,
"step": 1500
},
{
"epoch": 0.18,
"learning_rate": 4.824187439443319e-05,
"loss": 1.9222,
"step": 2000
},
{
"epoch": 0.22,
"learning_rate": 4.78014621685898e-05,
"loss": 1.9162,
"step": 2500
},
{
"epoch": 0.26,
"learning_rate": 4.736104994274641e-05,
"loss": 1.77,
"step": 3000
},
{
"epoch": 0.31,
"learning_rate": 4.692151854135471e-05,
"loss": 1.7844,
"step": 3500
},
{
"epoch": 0.35,
"learning_rate": 4.648110631551132e-05,
"loss": 1.8885,
"step": 4000
},
{
"epoch": 0.4,
"learning_rate": 4.604069408966793e-05,
"loss": 1.7094,
"step": 4500
},
{
"epoch": 0.44,
"learning_rate": 4.560028186382454e-05,
"loss": 1.8179,
"step": 5000
},
{
"epoch": 0.48,
"learning_rate": 4.515986963798115e-05,
"loss": 1.8352,
"step": 5500
},
{
"epoch": 0.53,
"learning_rate": 4.471945741213776e-05,
"loss": 1.7946,
"step": 6000
},
{
"epoch": 0.57,
"learning_rate": 4.427904518629437e-05,
"loss": 1.7258,
"step": 6500
},
{
"epoch": 0.62,
"learning_rate": 4.383863296045098e-05,
"loss": 1.671,
"step": 7000
},
{
"epoch": 0.66,
"learning_rate": 4.339910155905928e-05,
"loss": 1.8649,
"step": 7500
},
{
"epoch": 0.7,
"learning_rate": 4.295868933321589e-05,
"loss": 1.9734,
"step": 8000
},
{
"epoch": 0.75,
"learning_rate": 4.25182771073725e-05,
"loss": 1.8717,
"step": 8500
},
{
"epoch": 0.79,
"learning_rate": 4.207786488152911e-05,
"loss": 1.7005,
"step": 9000
},
{
"epoch": 0.84,
"learning_rate": 4.163745265568572e-05,
"loss": 1.6136,
"step": 9500
},
{
"epoch": 0.88,
"learning_rate": 4.1197040429842334e-05,
"loss": 1.7965,
"step": 10000
},
{
"epoch": 0.92,
"learning_rate": 4.075662820399894e-05,
"loss": 1.6852,
"step": 10500
},
{
"epoch": 0.97,
"learning_rate": 4.031709680260724e-05,
"loss": 1.5454,
"step": 11000
},
{
"epoch": 1.01,
"learning_rate": 3.987668457676385e-05,
"loss": 1.6019,
"step": 11500
},
{
"epoch": 1.06,
"learning_rate": 3.943627235092046e-05,
"loss": 1.7469,
"step": 12000
},
{
"epoch": 1.1,
"learning_rate": 3.8995860125077074e-05,
"loss": 1.8031,
"step": 12500
},
{
"epoch": 1.15,
"learning_rate": 3.855544789923368e-05,
"loss": 1.6901,
"step": 13000
},
{
"epoch": 1.19,
"learning_rate": 3.811503567339029e-05,
"loss": 1.6653,
"step": 13500
},
{
"epoch": 1.23,
"learning_rate": 3.767462344754691e-05,
"loss": 1.6627,
"step": 14000
},
{
"epoch": 1.28,
"learning_rate": 3.723421122170352e-05,
"loss": 1.6196,
"step": 14500
},
{
"epoch": 1.32,
"learning_rate": 3.679379899586013e-05,
"loss": 1.7333,
"step": 15000
},
{
"epoch": 1.37,
"learning_rate": 3.635426759446842e-05,
"loss": 1.6364,
"step": 15500
},
{
"epoch": 1.41,
"learning_rate": 3.591385536862503e-05,
"loss": 1.6258,
"step": 16000
},
{
"epoch": 1.45,
"learning_rate": 3.547344314278164e-05,
"loss": 1.7038,
"step": 16500
},
{
"epoch": 1.5,
"learning_rate": 3.5033030916938255e-05,
"loss": 1.6104,
"step": 17000
},
{
"epoch": 1.54,
"learning_rate": 3.459438033999824e-05,
"loss": 1.707,
"step": 17500
},
{
"epoch": 1.59,
"learning_rate": 3.415396811415485e-05,
"loss": 1.6641,
"step": 18000
},
{
"epoch": 1.63,
"learning_rate": 3.371355588831146e-05,
"loss": 1.7144,
"step": 18500
},
{
"epoch": 1.67,
"learning_rate": 3.327314366246807e-05,
"loss": 1.7934,
"step": 19000
},
{
"epoch": 1.72,
"learning_rate": 3.283273143662468e-05,
"loss": 1.6137,
"step": 19500
},
{
"epoch": 1.76,
"learning_rate": 3.239231921078129e-05,
"loss": 1.6195,
"step": 20000
},
{
"epoch": 1.81,
"learning_rate": 3.1951906984937905e-05,
"loss": 1.6228,
"step": 20500
},
{
"epoch": 1.85,
"learning_rate": 3.151149475909451e-05,
"loss": 1.5511,
"step": 21000
},
{
"epoch": 1.89,
"learning_rate": 3.107196335770281e-05,
"loss": 1.5842,
"step": 21500
},
{
"epoch": 1.94,
"learning_rate": 3.063155113185942e-05,
"loss": 1.6081,
"step": 22000
},
{
"epoch": 1.98,
"learning_rate": 3.0191138906016033e-05,
"loss": 1.6629,
"step": 22500
},
{
"epoch": 2.03,
"learning_rate": 2.975072668017264e-05,
"loss": 1.6513,
"step": 23000
},
{
"epoch": 2.07,
"learning_rate": 2.9310314454329253e-05,
"loss": 1.5899,
"step": 23500
},
{
"epoch": 2.11,
"learning_rate": 2.8869902228485862e-05,
"loss": 1.6249,
"step": 24000
},
{
"epoch": 2.16,
"learning_rate": 2.8429490002642474e-05,
"loss": 1.6052,
"step": 24500
},
{
"epoch": 2.2,
"learning_rate": 2.7989077776799083e-05,
"loss": 1.5361,
"step": 25000
},
{
"epoch": 2.25,
"learning_rate": 2.7548665550955695e-05,
"loss": 1.6174,
"step": 25500
},
{
"epoch": 2.29,
"learning_rate": 2.7108253325112303e-05,
"loss": 1.5097,
"step": 26000
},
{
"epoch": 2.33,
"learning_rate": 2.66687219237206e-05,
"loss": 1.4344,
"step": 26500
},
{
"epoch": 2.38,
"learning_rate": 2.6228309697877214e-05,
"loss": 1.6261,
"step": 27000
},
{
"epoch": 2.42,
"learning_rate": 2.5787897472033822e-05,
"loss": 1.5999,
"step": 27500
},
{
"epoch": 2.47,
"learning_rate": 2.5347485246190434e-05,
"loss": 1.5727,
"step": 28000
},
{
"epoch": 2.51,
"learning_rate": 2.4907953844798733e-05,
"loss": 1.5557,
"step": 28500
},
{
"epoch": 2.55,
"learning_rate": 2.4467541618955345e-05,
"loss": 1.7235,
"step": 29000
},
{
"epoch": 2.6,
"learning_rate": 2.4027129393111957e-05,
"loss": 1.5407,
"step": 29500
},
{
"epoch": 2.64,
"learning_rate": 2.3586717167268565e-05,
"loss": 1.5626,
"step": 30000
},
{
"epoch": 2.69,
"learning_rate": 2.3146304941425177e-05,
"loss": 1.6137,
"step": 30500
},
{
"epoch": 2.73,
"learning_rate": 2.2706773540033472e-05,
"loss": 1.6471,
"step": 31000
},
{
"epoch": 2.77,
"learning_rate": 2.226636131419008e-05,
"loss": 1.685,
"step": 31500
},
{
"epoch": 2.82,
"learning_rate": 2.1825949088346693e-05,
"loss": 1.5579,
"step": 32000
},
{
"epoch": 2.86,
"learning_rate": 2.1385536862503305e-05,
"loss": 1.5701,
"step": 32500
},
{
"epoch": 2.91,
"learning_rate": 2.0945124636659917e-05,
"loss": 1.6108,
"step": 33000
},
{
"epoch": 2.95,
"learning_rate": 2.0505593235268212e-05,
"loss": 1.6338,
"step": 33500
},
{
"epoch": 2.99,
"learning_rate": 2.006518100942482e-05,
"loss": 1.623,
"step": 34000
},
{
"epoch": 3.04,
"learning_rate": 1.9624768783581433e-05,
"loss": 1.5039,
"step": 34500
},
{
"epoch": 3.08,
"learning_rate": 1.918435655773804e-05,
"loss": 1.6072,
"step": 35000
},
{
"epoch": 3.13,
"learning_rate": 1.8743944331894657e-05,
"loss": 1.5008,
"step": 35500
},
{
"epoch": 3.17,
"learning_rate": 1.8303532106051265e-05,
"loss": 1.5741,
"step": 36000
},
{
"epoch": 3.22,
"learning_rate": 1.7863119880207877e-05,
"loss": 1.4937,
"step": 36500
},
{
"epoch": 3.26,
"learning_rate": 1.7423588478816172e-05,
"loss": 1.5352,
"step": 37000
},
{
"epoch": 3.3,
"learning_rate": 1.698317625297278e-05,
"loss": 1.6432,
"step": 37500
},
{
"epoch": 3.35,
"learning_rate": 1.6542764027129393e-05,
"loss": 1.5811,
"step": 38000
},
{
"epoch": 3.39,
"learning_rate": 1.6102351801286005e-05,
"loss": 1.5633,
"step": 38500
},
{
"epoch": 3.44,
"learning_rate": 1.5661939575442617e-05,
"loss": 1.5949,
"step": 39000
},
{
"epoch": 3.48,
"learning_rate": 1.5222408174050912e-05,
"loss": 1.5309,
"step": 39500
},
{
"epoch": 3.52,
"learning_rate": 1.4781995948207522e-05,
"loss": 1.4779,
"step": 40000
},
{
"epoch": 3.57,
"learning_rate": 1.4341583722364133e-05,
"loss": 1.5713,
"step": 40500
},
{
"epoch": 3.61,
"learning_rate": 1.3901171496520743e-05,
"loss": 1.521,
"step": 41000
},
{
"epoch": 3.66,
"learning_rate": 1.3461640095129042e-05,
"loss": 1.558,
"step": 41500
},
{
"epoch": 3.7,
"learning_rate": 1.3021227869285652e-05,
"loss": 1.5095,
"step": 42000
},
{
"epoch": 3.74,
"learning_rate": 1.2580815643442262e-05,
"loss": 1.4322,
"step": 42500
},
{
"epoch": 3.79,
"learning_rate": 1.2140403417598874e-05,
"loss": 1.558,
"step": 43000
},
{
"epoch": 3.83,
"learning_rate": 1.1700872016207171e-05,
"loss": 1.5619,
"step": 43500
},
{
"epoch": 3.88,
"learning_rate": 1.1260459790363781e-05,
"loss": 1.4401,
"step": 44000
},
{
"epoch": 3.92,
"learning_rate": 1.0820047564520392e-05,
"loss": 1.5182,
"step": 44500
},
{
"epoch": 3.96,
"learning_rate": 1.0379635338677002e-05,
"loss": 1.5103,
"step": 45000
},
{
"epoch": 4.01,
"learning_rate": 9.939223112833612e-06,
"loss": 1.5342,
"step": 45500
},
{
"epoch": 4.05,
"learning_rate": 9.498810886990224e-06,
"loss": 1.4571,
"step": 46000
},
{
"epoch": 4.1,
"learning_rate": 9.059279485598521e-06,
"loss": 1.4884,
"step": 46500
},
{
"epoch": 4.14,
"learning_rate": 8.618867259755131e-06,
"loss": 1.5288,
"step": 47000
},
{
"epoch": 4.18,
"learning_rate": 8.178455033911742e-06,
"loss": 1.6157,
"step": 47500
},
{
"epoch": 4.23,
"learning_rate": 7.738042808068352e-06,
"loss": 1.5245,
"step": 48000
},
{
"epoch": 4.27,
"learning_rate": 7.29851140667665e-06,
"loss": 1.4058,
"step": 48500
},
{
"epoch": 4.32,
"learning_rate": 6.858099180833261e-06,
"loss": 1.617,
"step": 49000
},
{
"epoch": 4.36,
"learning_rate": 6.417686954989871e-06,
"loss": 1.4707,
"step": 49500
},
{
"epoch": 4.4,
"learning_rate": 5.977274729146481e-06,
"loss": 1.4786,
"step": 50000
},
{
"epoch": 4.45,
"learning_rate": 5.536862503303092e-06,
"loss": 1.4711,
"step": 50500
},
{
"epoch": 4.49,
"learning_rate": 5.097331101911389e-06,
"loss": 1.4751,
"step": 51000
},
{
"epoch": 4.54,
"learning_rate": 4.6569188760679995e-06,
"loss": 1.5495,
"step": 51500
},
{
"epoch": 4.58,
"learning_rate": 4.21650665022461e-06,
"loss": 1.4748,
"step": 52000
},
{
"epoch": 4.62,
"learning_rate": 3.7760944243812214e-06,
"loss": 1.4816,
"step": 52500
},
{
"epoch": 4.67,
"learning_rate": 3.3356821985378317e-06,
"loss": 1.5052,
"step": 53000
},
{
"epoch": 4.71,
"learning_rate": 2.896150797146129e-06,
"loss": 1.4555,
"step": 53500
},
{
"epoch": 4.76,
"learning_rate": 2.4557385713027396e-06,
"loss": 1.4899,
"step": 54000
},
{
"epoch": 4.8,
"learning_rate": 2.01532634545935e-06,
"loss": 1.4849,
"step": 54500
},
{
"epoch": 4.84,
"learning_rate": 1.5749141196159605e-06,
"loss": 1.5955,
"step": 55000
},
{
"epoch": 4.89,
"learning_rate": 1.1345018937725712e-06,
"loss": 1.4426,
"step": 55500
},
{
"epoch": 4.93,
"learning_rate": 6.940896679291817e-07,
"loss": 1.4316,
"step": 56000
},
{
"epoch": 4.98,
"learning_rate": 2.5367744208579233e-07,
"loss": 1.5447,
"step": 56500
},
{
"epoch": 5.0,
"step": 56765,
"total_flos": 4.366478177206272e+16,
"train_runtime": 14442.4553,
"train_samples_per_second": 3.93,
"train_steps_per_second": 3.93
}
],
"max_steps": 56765,
"num_train_epochs": 5,
"total_flos": 4.366478177206272e+16,
"trial_name": null,
"trial_params": null
}