videomae-base-SOCAL1-finetune / trainer_state.json
RRHF's picture
End of training
f94d54f
raw
history blame
2.15 kB
{
"best_metric": 0.7108433734939759,
"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": 0.7108433734939759,
"eval_loss": 0.8709341883659363,
"eval_runtime": 100.0415,
"eval_samples_per_second": 1.07,
"eval_steps_per_second": 0.27,
"step": 23
},
{
"epoch": 1.25,
"eval_f1": 0.7108433734939759,
"eval_loss": 0.8158706426620483,
"eval_runtime": 99.7202,
"eval_samples_per_second": 1.073,
"eval_steps_per_second": 0.271,
"step": 46
},
{
"epoch": 2.25,
"eval_f1": 0.7108433734939759,
"eval_loss": 0.7319411635398865,
"eval_runtime": 101.0863,
"eval_samples_per_second": 1.059,
"eval_steps_per_second": 0.267,
"step": 69
},
{
"epoch": 3.25,
"eval_f1": 0.7108433734939759,
"eval_loss": 0.7353231310844421,
"eval_runtime": 103.0401,
"eval_samples_per_second": 1.038,
"eval_steps_per_second": 0.262,
"step": 92
},
{
"epoch": 3.25,
"step": 92,
"total_flos": 4.585517689256018e+17,
"train_loss": 0.6584867809129797,
"train_runtime": 903.9039,
"train_samples_per_second": 0.407,
"train_steps_per_second": 0.102
},
{
"epoch": 3.25,
"eval_f1": 0.6470588235294118,
"eval_loss": 0.879997193813324,
"eval_runtime": 129.7812,
"eval_samples_per_second": 0.886,
"eval_steps_per_second": 0.223,
"step": 92
},
{
"epoch": 3.25,
"eval_f1": 0.6470588235294118,
"eval_loss": 0.8799970746040344,
"eval_runtime": 126.6292,
"eval_samples_per_second": 0.908,
"eval_steps_per_second": 0.229,
"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
}