TajBERTo / checkpoint-20000 /trainer_state.json
muhtasham's picture
Initial commit
4684a3a
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.8112602928649657,
"global_step": 20000,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.02,
"learning_rate": 4.8985924633918794e-05,
"loss": 8.3189,
"step": 500
},
{
"epoch": 0.04,
"learning_rate": 4.7971849267837586e-05,
"loss": 7.6649,
"step": 1000
},
{
"epoch": 0.06,
"learning_rate": 4.695777390175638e-05,
"loss": 7.424,
"step": 1500
},
{
"epoch": 0.08,
"learning_rate": 4.5943698535675176e-05,
"loss": 7.2422,
"step": 2000
},
{
"epoch": 0.1,
"learning_rate": 4.492962316959397e-05,
"loss": 7.0602,
"step": 2500
},
{
"epoch": 0.12,
"learning_rate": 4.391554780351276e-05,
"loss": 6.8806,
"step": 3000
},
{
"epoch": 0.14,
"learning_rate": 4.290147243743155e-05,
"loss": 6.7319,
"step": 3500
},
{
"epoch": 0.16,
"learning_rate": 4.188739707135034e-05,
"loss": 6.6085,
"step": 4000
},
{
"epoch": 0.18,
"learning_rate": 4.0873321705269134e-05,
"loss": 6.4786,
"step": 4500
},
{
"epoch": 0.2,
"learning_rate": 3.9859246339187925e-05,
"loss": 6.3686,
"step": 5000
},
{
"epoch": 0.22,
"learning_rate": 3.8845170973106724e-05,
"loss": 6.2653,
"step": 5500
},
{
"epoch": 0.24,
"learning_rate": 3.7831095607025515e-05,
"loss": 6.1734,
"step": 6000
},
{
"epoch": 0.26,
"learning_rate": 3.6817020240944314e-05,
"loss": 6.0843,
"step": 6500
},
{
"epoch": 0.28,
"learning_rate": 3.5802944874863105e-05,
"loss": 6.0259,
"step": 7000
},
{
"epoch": 0.3,
"learning_rate": 3.47888695087819e-05,
"loss": 5.9236,
"step": 7500
},
{
"epoch": 0.32,
"learning_rate": 3.377479414270069e-05,
"loss": 5.8589,
"step": 8000
},
{
"epoch": 0.34,
"learning_rate": 3.276071877661948e-05,
"loss": 5.8056,
"step": 8500
},
{
"epoch": 0.37,
"learning_rate": 3.174664341053827e-05,
"loss": 5.7384,
"step": 9000
},
{
"epoch": 0.39,
"learning_rate": 3.073256804445706e-05,
"loss": 5.7061,
"step": 9500
},
{
"epoch": 0.41,
"learning_rate": 2.9718492678375858e-05,
"loss": 5.6454,
"step": 10000
},
{
"epoch": 0.43,
"learning_rate": 2.870441731229465e-05,
"loss": 5.6005,
"step": 10500
},
{
"epoch": 0.45,
"learning_rate": 2.7690341946213445e-05,
"loss": 5.5741,
"step": 11000
},
{
"epoch": 0.47,
"learning_rate": 2.6676266580132236e-05,
"loss": 5.5323,
"step": 11500
},
{
"epoch": 0.49,
"learning_rate": 2.5662191214051028e-05,
"loss": 5.4985,
"step": 12000
},
{
"epoch": 0.51,
"learning_rate": 2.4648115847969823e-05,
"loss": 5.4576,
"step": 12500
},
{
"epoch": 0.53,
"learning_rate": 2.3634040481888615e-05,
"loss": 5.4265,
"step": 13000
},
{
"epoch": 0.55,
"learning_rate": 2.2619965115807406e-05,
"loss": 5.3953,
"step": 13500
},
{
"epoch": 0.57,
"learning_rate": 2.16058897497262e-05,
"loss": 5.3739,
"step": 14000
},
{
"epoch": 0.59,
"learning_rate": 2.0591814383644993e-05,
"loss": 5.3361,
"step": 14500
},
{
"epoch": 0.61,
"learning_rate": 1.9577739017563788e-05,
"loss": 5.3105,
"step": 15000
},
{
"epoch": 0.63,
"learning_rate": 1.856366365148258e-05,
"loss": 5.2979,
"step": 15500
},
{
"epoch": 0.65,
"learning_rate": 1.754958828540137e-05,
"loss": 5.278,
"step": 16000
},
{
"epoch": 0.67,
"learning_rate": 1.6535512919320166e-05,
"loss": 5.2304,
"step": 16500
},
{
"epoch": 0.69,
"learning_rate": 1.5521437553238958e-05,
"loss": 5.2239,
"step": 17000
},
{
"epoch": 0.71,
"learning_rate": 1.450736218715775e-05,
"loss": 5.2037,
"step": 17500
},
{
"epoch": 0.73,
"learning_rate": 1.3493286821076543e-05,
"loss": 5.2013,
"step": 18000
},
{
"epoch": 0.75,
"learning_rate": 1.2479211454995336e-05,
"loss": 5.1625,
"step": 18500
},
{
"epoch": 0.77,
"learning_rate": 1.1465136088914129e-05,
"loss": 5.1583,
"step": 19000
},
{
"epoch": 0.79,
"learning_rate": 1.045106072283292e-05,
"loss": 5.1328,
"step": 19500
},
{
"epoch": 0.81,
"learning_rate": 9.436985356751714e-06,
"loss": 5.144,
"step": 20000
}
],
"max_steps": 24653,
"num_train_epochs": 1,
"total_flos": 3.19689423366144e+16,
"trial_name": null,
"trial_params": null
}