vaani-lora-lata / trainer_state.json
rahul7star's picture
LoRA checkpoint step 10
d81cfb9 verified
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0,
"eval_steps": 500,
"global_step": 10,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.1,
"grad_norm": 14.800739288330078,
"learning_rate": 0.0001,
"loss": 15.3207,
"step": 1
},
{
"epoch": 0.2,
"grad_norm": 14.96125602722168,
"learning_rate": 9e-05,
"loss": 16.127,
"step": 2
},
{
"epoch": 0.3,
"grad_norm": 13.516273498535156,
"learning_rate": 8e-05,
"loss": 15.5743,
"step": 3
},
{
"epoch": 0.4,
"grad_norm": 15.074135780334473,
"learning_rate": 7e-05,
"loss": 15.1249,
"step": 4
},
{
"epoch": 0.5,
"grad_norm": 12.500387191772461,
"learning_rate": 6e-05,
"loss": 15.3016,
"step": 5
},
{
"epoch": 0.6,
"grad_norm": 12.868051528930664,
"learning_rate": 5e-05,
"loss": 13.8441,
"step": 6
},
{
"epoch": 0.7,
"grad_norm": 12.014676094055176,
"learning_rate": 4e-05,
"loss": 14.4305,
"step": 7
},
{
"epoch": 0.8,
"grad_norm": 12.44831657409668,
"learning_rate": 3e-05,
"loss": 13.5286,
"step": 8
},
{
"epoch": 0.9,
"grad_norm": 11.084362030029297,
"learning_rate": 2e-05,
"loss": 15.0303,
"step": 9
},
{
"epoch": 1.0,
"grad_norm": 14.512312889099121,
"learning_rate": 1e-05,
"loss": 12.5946,
"step": 10
}
],
"logging_steps": 1,
"max_steps": 10,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 10,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 867328484966400.0,
"train_batch_size": 10,
"trial_name": null,
"trial_params": null
}