single-qa-ontonotes / trainer_state.json
jatinarora2702's picture
first model version
ad107d6
Raw History Blame
744 Bytes
{
"best_metric": 0.0,
"best_model_checkpoint": "../out/onto_final/ner-roberta-qa4-querytype4-char-pattern3-subtext-dim50-new/checkpoints/checkpoint-30000",
"epoch": 0.8659508139937652,
"global_step": 30000,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.8659508139937652,
"learning_rate": 9.971134972866875e-05,
"loss": 6.094925006230672e-05,
"step": 30000
},
{
"epoch": 0.8659508139937652,
"eval_loss": 0.0,
"eval_micro_f1": 0.0,
"step": 30000
}
],
"max_steps": 10393200,
"num_train_epochs": 300,
"total_flos": 156978982343677440,
"trial_name": null,
"trial_params": null
}