indobert-lite-squadx / trainer_state.json
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 2.0,
"global_step": 7250,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.14,
"learning_rate": 2.793103448275862e-05,
"loss": 1.3311,
"step": 500
},
{
"epoch": 0.28,
"learning_rate": 2.586206896551724e-05,
"loss": 1.3174,
"step": 1000
},
{
"epoch": 0.41,
"learning_rate": 2.3793103448275862e-05,
"loss": 1.2975,
"step": 1500
},
{
"epoch": 0.55,
"learning_rate": 2.1724137931034484e-05,
"loss": 1.2811,
"step": 2000
},
{
"epoch": 0.69,
"learning_rate": 1.9655172413793102e-05,
"loss": 1.2528,
"step": 2500
},
{
"epoch": 0.83,
"learning_rate": 1.7586206896551724e-05,
"loss": 1.2374,
"step": 3000
},
{
"epoch": 0.97,
"learning_rate": 1.5517241379310346e-05,
"loss": 1.2414,
"step": 3500
},
{
"epoch": 1.1,
"learning_rate": 1.3448275862068966e-05,
"loss": 0.9927,
"step": 4000
},
{
"epoch": 1.24,
"learning_rate": 1.1379310344827586e-05,
"loss": 0.9257,
"step": 4500
},
{
"epoch": 1.38,
"learning_rate": 9.310344827586207e-06,
"loss": 0.9237,
"step": 5000
},
{
"epoch": 1.52,
"learning_rate": 7.241379310344828e-06,
"loss": 0.9171,
"step": 5500
},
{
"epoch": 1.66,
"learning_rate": 5.172413793103449e-06,
"loss": 0.9109,
"step": 6000
},
{
"epoch": 1.79,
"learning_rate": 3.103448275862069e-06,
"loss": 0.8931,
"step": 6500
},
{
"epoch": 1.93,
"learning_rate": 1.0344827586206896e-06,
"loss": 0.878,
"step": 7000
},
{
"epoch": 2.0,
"step": 7250,
"total_flos": 8894687420252160.0,
"train_runtime": 3251.9473,
"train_samples_per_second": 2.229
}
],
"max_steps": 7250,
"num_train_epochs": 2,
"total_flos": 8894687420252160.0,
"trial_name": null,
"trial_params": null
}