Llama-3.1-8B-Instruct-reward-100 / trainer_state.json
chchen's picture
End of training
4c127fd verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 9.488888888888889,
"eval_steps": 50,
"global_step": 50,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.8444444444444446,
"grad_norm": 15.148612976074219,
"learning_rate": 9.698463103929542e-05,
"loss": 0.5463,
"step": 10
},
{
"epoch": 3.7555555555555555,
"grad_norm": 1.5098639726638794,
"learning_rate": 7.500000000000001e-05,
"loss": 0.1026,
"step": 20
},
{
"epoch": 5.666666666666667,
"grad_norm": 8.635929407319054e-05,
"learning_rate": 4.131759111665349e-05,
"loss": 0.0046,
"step": 30
},
{
"epoch": 7.5777777777777775,
"grad_norm": 0.0007328893407247961,
"learning_rate": 1.1697777844051105e-05,
"loss": 0.0,
"step": 40
},
{
"epoch": 9.488888888888889,
"grad_norm": 1.457463440601714e-05,
"learning_rate": 0.0,
"loss": 0.0,
"step": 50
},
{
"epoch": 9.488888888888889,
"eval_accuracy": 0.9,
"eval_loss": 0.3585858941078186,
"eval_runtime": 0.8163,
"eval_samples_per_second": 12.25,
"eval_steps_per_second": 6.125,
"step": 50
},
{
"epoch": 9.488888888888889,
"step": 50,
"total_flos": 0.0,
"train_loss": 0.13070689755084458,
"train_runtime": 217.2241,
"train_samples_per_second": 4.143,
"train_steps_per_second": 0.23
}
],
"logging_steps": 10,
"max_steps": 50,
"num_input_tokens_seen": 0,
"num_train_epochs": 10,
"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": 2,
"trial_name": null,
"trial_params": null
}