checkpoint-100_test / trainer_state.json
Dongkkka's picture
Upload folder using huggingface_hub
3440fa1 verified
Raw
History Blame Contribute Delete
2.15 kB
{
"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": 0.33240026235580444,
"learning_rate": 9.956320346634876e-05,
"loss": 1.2615,
"step": 10
},
{
"grad_norm": 0.4248397648334503,
"learning_rate": 9.473646649103818e-05,
"loss": 1.1359,
"step": 20
},
{
"grad_norm": 0.34815770387649536,
"learning_rate": 8.506183921362443e-05,
"loss": 1.0759,
"step": 30
},
{
"grad_norm": 0.30539968609809875,
"learning_rate": 7.158771761692464e-05,
"loss": 1.0638,
"step": 40
},
{
"grad_norm": 0.30587705969810486,
"learning_rate": 5.577423184847932e-05,
"loss": 1.0507,
"step": 50
},
{
"grad_norm": 0.3342309594154358,
"learning_rate": 3.933501846281267e-05,
"loss": 1.0315,
"step": 60
},
{
"grad_norm": 0.5034079551696777,
"learning_rate": 2.405152131093926e-05,
"loss": 1.0001,
"step": 70
},
{
"grad_norm": 0.38376083970069885,
"learning_rate": 1.157994445715706e-05,
"loss": 0.9808,
"step": 80
},
{
"grad_norm": 0.36459216475486755,
"learning_rate": 3.271776770026963e-06,
"loss": 0.9679,
"step": 90
},
{
"grad_norm": 0.39225029945373535,
"learning_rate": 2.7337132953697554e-08,
"loss": 0.9775,
"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
}