PATs_upload_test_model_3 / trainer_state.json
Dongkkka's picture
Upload folder using huggingface_hub
06b2458 verified
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0,
"eval_steps": 500,
"global_step": 100,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"grad_norm": 0.22046448290348053,
"learning_rate": 9.956320346634876e-05,
"loss": 1.3194,
"step": 10
},
{
"grad_norm": 0.17060352861881256,
"learning_rate": 9.473646649103818e-05,
"loss": 1.2678,
"step": 20
},
{
"grad_norm": 0.4370490610599518,
"learning_rate": 8.506183921362443e-05,
"loss": 1.2517,
"step": 30
},
{
"grad_norm": 0.29495033621788025,
"learning_rate": 7.158771761692464e-05,
"loss": 1.1563,
"step": 40
},
{
"grad_norm": 0.323966383934021,
"learning_rate": 5.577423184847932e-05,
"loss": 1.0987,
"step": 50
},
{
"grad_norm": 0.35949671268463135,
"learning_rate": 3.933501846281267e-05,
"loss": 1.081,
"step": 60
},
{
"grad_norm": 0.33241820335388184,
"learning_rate": 2.405152131093926e-05,
"loss": 1.068,
"step": 70
},
{
"grad_norm": 0.3555103540420532,
"learning_rate": 1.157994445715706e-05,
"loss": 1.0564,
"step": 80
},
{
"grad_norm": 0.31199315190315247,
"learning_rate": 3.271776770026963e-06,
"loss": 1.0606,
"step": 90
},
{
"grad_norm": 0.30680856108665466,
"learning_rate": 2.7337132953697554e-08,
"loss": 1.0678,
"step": 100
}
],
"logging_steps": 10,
"max_steps": 100,
"num_input_tokens_seen": 0,
"num_train_epochs": 9223372036854775807,
"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": 0.0,
"train_batch_size": 48,
"trial_name": null,
"trial_params": null
}