roberta-base-ca-cased-sts / trainer_state.json
ccasimiro's picture
upload model
206d483
raw
history blame
4.16 kB
{
"best_metric": 0.7437504611247936,
"best_model_checkpoint": "/home/ccasimiro/ccasimiro/berta/src/finetuning/sts/roberta-base-ca-cased-sts/checkpoint-455",
"epoch": 10.0,
"global_step": 650,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.0,
"eval_combined_score": 0.6805577619623024,
"eval_loss": 0.4414205849170685,
"eval_pearson": 0.6667563227309266,
"eval_runtime": 10.4961,
"eval_samples_per_second": 47.637,
"eval_spearmanr": 0.6943592011936784,
"eval_steps_per_second": 1.524,
"step": 65
},
{
"epoch": 2.0,
"eval_combined_score": 0.7152235717947664,
"eval_loss": 0.3806273341178894,
"eval_pearson": 0.718255308294224,
"eval_runtime": 10.3114,
"eval_samples_per_second": 48.49,
"eval_spearmanr": 0.7121918352953086,
"eval_steps_per_second": 1.552,
"step": 130
},
{
"epoch": 3.0,
"eval_combined_score": 0.7127492106541832,
"eval_loss": 0.3876854479312897,
"eval_pearson": 0.7141017567917686,
"eval_runtime": 10.3161,
"eval_samples_per_second": 48.468,
"eval_spearmanr": 0.7113966645165978,
"eval_steps_per_second": 1.551,
"step": 195
},
{
"epoch": 4.0,
"eval_combined_score": 0.7300156062557066,
"eval_loss": 0.380470871925354,
"eval_pearson": 0.731967198769625,
"eval_runtime": 10.2905,
"eval_samples_per_second": 48.589,
"eval_spearmanr": 0.7280640137417881,
"eval_steps_per_second": 1.555,
"step": 260
},
{
"epoch": 5.0,
"eval_combined_score": 0.7302656118713525,
"eval_loss": 0.33833837509155273,
"eval_pearson": 0.7366071674449775,
"eval_runtime": 10.3827,
"eval_samples_per_second": 48.157,
"eval_spearmanr": 0.7239240562977276,
"eval_steps_per_second": 1.541,
"step": 325
},
{
"epoch": 6.0,
"eval_combined_score": 0.7325772109724351,
"eval_loss": 0.36641925573349,
"eval_pearson": 0.7349002365451928,
"eval_runtime": 10.2668,
"eval_samples_per_second": 48.701,
"eval_spearmanr": 0.7302541853996775,
"eval_steps_per_second": 1.558,
"step": 390
},
{
"epoch": 7.0,
"eval_combined_score": 0.7437504611247936,
"eval_loss": 0.33539897203445435,
"eval_pearson": 0.7484496954159015,
"eval_runtime": 10.2857,
"eval_samples_per_second": 48.611,
"eval_spearmanr": 0.7390512268336858,
"eval_steps_per_second": 1.556,
"step": 455
},
{
"epoch": 7.69,
"learning_rate": 1.153846153846154e-05,
"loss": 0.2244,
"step": 500
},
{
"epoch": 8.0,
"eval_combined_score": 0.7370831462161629,
"eval_loss": 0.3497055172920227,
"eval_pearson": 0.7429713239243328,
"eval_runtime": 10.3129,
"eval_samples_per_second": 48.483,
"eval_spearmanr": 0.731194968507993,
"eval_steps_per_second": 1.551,
"step": 520
},
{
"epoch": 9.0,
"eval_combined_score": 0.7429305671131216,
"eval_loss": 0.3452938497066498,
"eval_pearson": 0.7476867678468953,
"eval_runtime": 10.2732,
"eval_samples_per_second": 48.67,
"eval_spearmanr": 0.7381743663793479,
"eval_steps_per_second": 1.557,
"step": 585
},
{
"epoch": 10.0,
"eval_combined_score": 0.7410151955266198,
"eval_loss": 0.3426874279975891,
"eval_pearson": 0.7469684882191953,
"eval_runtime": 10.2706,
"eval_samples_per_second": 48.683,
"eval_spearmanr": 0.7350619028340443,
"eval_steps_per_second": 1.558,
"step": 650
},
{
"epoch": 10.0,
"step": 650,
"total_flos": 5454243205724160.0,
"train_loss": 0.17999618823711688,
"train_runtime": 1715.2897,
"train_samples_per_second": 12.085,
"train_steps_per_second": 0.379
}
],
"max_steps": 650,
"num_train_epochs": 10,
"total_flos": 5454243205724160.0,
"trial_name": null,
"trial_params": null
}