Files
capsd-Qwen3-1.7B-Base-math_…/checkpoint-63/trainer_state.json

42 lines
934 B
JSON
Raw Normal View History

{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0,
"eval_steps": 500,
"global_step": 63,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.8,
"grad_norm": 0.8426390559384174,
"learning_rate": 1.2443403456474017e-06,
"loss": 0.7008683776855469,
"step": 50
}
],
"logging_steps": 50,
"max_steps": 63,
"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": 2763503304704.0,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}