sql-ocr / checkpoint-30 /trainer_state.json
JohnnyZeppelin's picture
Upload checkpoint-30/trainer_state.json with huggingface_hub
ddf9b1b verified
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.9375,
"eval_steps": 500,
"global_step": 30,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.15625,
"grad_norm": 0.21668776869773865,
"learning_rate": 0.00017333333333333334,
"loss": 5.2044,
"step": 5
},
{
"epoch": 0.3125,
"grad_norm": 0.24632510542869568,
"learning_rate": 0.00014,
"loss": 5.2178,
"step": 10
},
{
"epoch": 0.46875,
"grad_norm": 0.26152700185775757,
"learning_rate": 0.00010666666666666667,
"loss": 5.2657,
"step": 15
},
{
"epoch": 0.625,
"grad_norm": 0.24584853649139404,
"learning_rate": 7.333333333333333e-05,
"loss": 5.2687,
"step": 20
},
{
"epoch": 0.78125,
"grad_norm": 0.25921785831451416,
"learning_rate": 4e-05,
"loss": 5.1945,
"step": 25
},
{
"epoch": 0.9375,
"grad_norm": 0.25720950961112976,
"learning_rate": 6.666666666666667e-06,
"loss": 5.207,
"step": 30
}
],
"logging_steps": 5,
"max_steps": 30,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 50,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 11620030464.0,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}