Qwen2.5-1.5B-Open-R1-Distill / trainer_state.json
T1anyu's picture
Model save
d6e8d71 verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0,
"eval_steps": 500,
"global_step": 19,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.2631578947368421,
"grad_norm": 4.513563155702256,
"learning_rate": 4.473599997017701e-05,
"loss": 0.869,
"step": 5
},
{
"epoch": 0.5263157894736842,
"grad_norm": 3.3623716219856,
"learning_rate": 2.7500000000000004e-05,
"loss": 0.8519,
"step": 10
},
{
"epoch": 0.7894736842105263,
"grad_norm": 3.2657311833778047,
"learning_rate": 1.0264000029822999e-05,
"loss": 0.8395,
"step": 15
},
{
"epoch": 1.0,
"step": 19,
"total_flos": 103624402944.0,
"train_loss": 0.0,
"train_runtime": 1.3161,
"train_samples_per_second": 28.873,
"train_steps_per_second": 14.436
}
],
"logging_steps": 5,
"max_steps": 19,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 100,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 103624402944.0,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}