Files
Qwen2.5-3B-Distillation-Dee…/last-checkpoint/trainer_state.json

42 lines
961 B
JSON
Raw Normal View History

{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.003509695533912433,
"eval_steps": 500,
"global_step": 10,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.003509695533912433,
"grad_norm": 10.8125,
"learning_rate": 2.105263157894737e-07,
"loss": 9.61218719482422,
"step": 10
}
],
"logging_steps": 10,
"max_steps": 8550,
"num_input_tokens_seen": 0,
"num_train_epochs": 3,
"save_steps": 10,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 2.18217087762432e+16,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}