Qwen2.5-1.5B-Open-R1-Distill / trainer_state.json
shuheikurita's picture
Model save
75eec35 verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.9974102848686645,
"eval_steps": 500,
"global_step": 337,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.9974102848686645,
"step": 337,
"total_flos": 76774385909760.0,
"train_loss": 0.0,
"train_runtime": 1.3263,
"train_samples_per_second": 16303.078,
"train_steps_per_second": 254.088
}
],
"logging_steps": 500,
"max_steps": 337,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"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": 76774385909760.0,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}