chess-lora-adapter-llama-3.1-8b / trainer_state.json
mkopecki's picture
End of training
180390d verified
raw
history blame
980 Bytes
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 3.0,
"eval_steps": 500,
"global_step": 30,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 3.0,
"step": 30,
"total_flos": 388808857313280.0,
"train_loss": 1.1855101267496744,
"train_runtime": 71.2626,
"train_samples_per_second": 0.421,
"train_steps_per_second": 0.421
}
],
"logging_steps": 500,
"max_steps": 30,
"num_input_tokens_seen": 0,
"num_train_epochs": 3,
"save_steps": 500,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 388808857313280.0,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}