offering-generator-qwen / trainer_state.json
anuroopkeshav's picture
Upload 16 files
700c684 verified
raw
history blame contribute delete
943 Bytes
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 20.0,
"eval_steps": 50,
"global_step": 40,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 12.666666666666666,
"grad_norm": 0.17876079678535461,
"learning_rate": 9.600000000000001e-07,
"loss": 1.5688,
"step": 25
}
],
"logging_steps": 25,
"max_steps": 40,
"num_input_tokens_seen": 0,
"num_train_epochs": 20,
"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": 1.310172257452032e+17,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}