hebert_parashoot / trainer_state.json
imvladikon's picture
End of training
55fd6e5
raw
history blame
2.33 kB
{
"best_metric": 36.8601893452485,
"best_model_checkpoint": "./hebert_parashoot/checkpoint-1407",
"epoch": 5.0,
"global_step": 2345,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.0,
"eval_exact_match": 12.217194570135746,
"eval_f1": 30.9937324652663,
"eval_runtime": 6.4609,
"eval_samples_per_second": 38.539,
"eval_steps_per_second": 4.953,
"step": 469
},
{
"epoch": 1.07,
"learning_rate": 2.3603411513859275e-05,
"loss": 4.3712,
"step": 500
},
{
"epoch": 2.0,
"eval_exact_match": 17.647058823529413,
"eval_f1": 35.4171725736381,
"eval_runtime": 6.8735,
"eval_samples_per_second": 36.226,
"eval_steps_per_second": 4.656,
"step": 938
},
{
"epoch": 2.13,
"learning_rate": 1.7206823027718552e-05,
"loss": 2.926,
"step": 1000
},
{
"epoch": 3.0,
"eval_exact_match": 18.099547511312217,
"eval_f1": 36.8601893452485,
"eval_runtime": 6.9389,
"eval_samples_per_second": 35.884,
"eval_steps_per_second": 4.612,
"step": 1407
},
{
"epoch": 3.2,
"learning_rate": 1.0810234541577825e-05,
"loss": 1.9172,
"step": 1500
},
{
"epoch": 4.0,
"eval_exact_match": 18.552036199095024,
"eval_f1": 35.27425497728763,
"eval_runtime": 6.9353,
"eval_samples_per_second": 35.903,
"eval_steps_per_second": 4.614,
"step": 1876
},
{
"epoch": 4.26,
"learning_rate": 4.4136460554371e-06,
"loss": 1.1751,
"step": 2000
},
{
"epoch": 5.0,
"eval_exact_match": 17.194570135746606,
"eval_f1": 35.41593343704486,
"eval_runtime": 6.9293,
"eval_samples_per_second": 35.934,
"eval_steps_per_second": 4.618,
"step": 2345
},
{
"epoch": 5.0,
"step": 2345,
"total_flos": 1836262957962240.0,
"train_loss": 2.3373700692963753,
"train_runtime": 923.5379,
"train_samples_per_second": 10.146,
"train_steps_per_second": 2.539
}
],
"max_steps": 2345,
"num_train_epochs": 5,
"total_flos": 1836262957962240.0,
"trial_name": null,
"trial_params": null
}