videomae-base-SOCAL1-finetune / trainer_state.json
RRHF's picture
End of training
6fe9756
raw
history blame
2.09 kB
{
"best_metric": 0.71875,
"best_model_checkpoint": "videomae-base-SOCAL1-finetune/checkpoint-23",
"epoch": 3.25,
"eval_steps": 500,
"global_step": 92,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.25,
"eval_f1": 0.71875,
"eval_loss": 0.8954424262046814,
"eval_runtime": 53.0216,
"eval_samples_per_second": 0.773,
"eval_steps_per_second": 0.207,
"step": 23
},
{
"epoch": 1.25,
"eval_f1": 0.71875,
"eval_loss": 0.8061372637748718,
"eval_runtime": 52.0068,
"eval_samples_per_second": 0.788,
"eval_steps_per_second": 0.212,
"step": 46
},
{
"epoch": 2.25,
"eval_f1": 0.71875,
"eval_loss": 0.7606935501098633,
"eval_runtime": 54.0005,
"eval_samples_per_second": 0.759,
"eval_steps_per_second": 0.204,
"step": 69
},
{
"epoch": 3.25,
"eval_f1": 0.71875,
"eval_loss": 0.747420072555542,
"eval_runtime": 53.1634,
"eval_samples_per_second": 0.771,
"eval_steps_per_second": 0.207,
"step": 92
},
{
"epoch": 3.25,
"step": 92,
"total_flos": 4.585517689256018e+17,
"train_loss": 0.6411792506342349,
"train_runtime": 856.0732,
"train_samples_per_second": 0.43,
"train_steps_per_second": 0.107
},
{
"epoch": 3.25,
"eval_f1": 0.6229508196721312,
"eval_loss": 0.9376347661018372,
"eval_runtime": 63.8246,
"eval_samples_per_second": 0.658,
"eval_steps_per_second": 0.172,
"step": 92
},
{
"epoch": 3.25,
"eval_f1": 0.6229508196721312,
"eval_loss": 0.9376347661018372,
"eval_runtime": 62.197,
"eval_samples_per_second": 0.675,
"eval_steps_per_second": 0.177,
"step": 92
}
],
"logging_steps": 100,
"max_steps": 92,
"num_train_epochs": 9223372036854775807,
"save_steps": 500,
"total_flos": 4.585517689256018e+17,
"trial_name": null,
"trial_params": null
}