videomae-base-furtos / trainer_state.json
leandroZanatta27's picture
Training in progress, epoch 0
87bad1b verified
{
"best_metric": 0.95,
"best_model_checkpoint": "videomae-base-furtos/checkpoint-2",
"epoch": 3.25,
"eval_steps": 500,
"global_step": 8,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.25,
"eval_accuracy": 0.95,
"eval_loss": 0.5629596710205078,
"eval_runtime": 47.2295,
"eval_samples_per_second": 0.423,
"eval_steps_per_second": 0.106,
"step": 2
},
{
"epoch": 1.25,
"eval_accuracy": 0.9,
"eval_loss": 0.4741394519805908,
"eval_runtime": 48.2615,
"eval_samples_per_second": 0.414,
"eval_steps_per_second": 0.104,
"step": 4
},
{
"epoch": 2.25,
"eval_accuracy": 0.9,
"eval_loss": 0.43011197447776794,
"eval_runtime": 54.2665,
"eval_samples_per_second": 0.369,
"eval_steps_per_second": 0.092,
"step": 6
},
{
"epoch": 3.25,
"eval_accuracy": 0.9,
"eval_loss": 0.41513046622276306,
"eval_runtime": 52.0763,
"eval_samples_per_second": 0.384,
"eval_steps_per_second": 0.096,
"step": 8
},
{
"epoch": 3.25,
"step": 8,
"total_flos": 3.987406686309581e+16,
"train_loss": 0.6022815704345703,
"train_runtime": 495.3461,
"train_samples_per_second": 0.065,
"train_steps_per_second": 0.016
},
{
"epoch": 3.25,
"eval_accuracy": 0.95,
"eval_loss": 0.5629596710205078,
"eval_runtime": 54.9037,
"eval_samples_per_second": 0.364,
"eval_steps_per_second": 0.091,
"step": 8
}
],
"logging_steps": 10,
"max_steps": 8,
"num_input_tokens_seen": 0,
"num_train_epochs": 9223372036854775807,
"save_steps": 500,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 3.987406686309581e+16,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}