Text Generation
Transformers
Safetensors
llama
mergekit
Merge
text-generation-inference
blackthinking / trainer_state.json
42hgyn26hz-cpu
update
f6ceb9b
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0,
"eval_steps": 50,
"global_step": 3,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.0,
"step": 3,
"total_flos": 40311604543488.0,
"train_loss": 7.614580790201823,
"train_runtime": 173.9636,
"train_samples_per_second": 0.115,
"train_steps_per_second": 0.017
}
],
"logging_steps": 25,
"max_steps": 3,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"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": 40311604543488.0,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}