76 lines
1.9 KiB
JSON
76 lines
1.9 KiB
JSON
|
{
|
||
|
|
"best_global_step": 1268,
|
||
|
|
"best_metric": 58.06834889049466,
|
||
|
|
"best_model_checkpoint": "mbert-loraxs-qa-vanilla/run-4/checkpoint-1268",
|
||
|
|
"epoch": 2.0,
|
||
|
|
"eval_steps": 500,
|
||
|
|
"global_step": 1268,
|
||
|
|
"is_hyper_param_search": true,
|
||
|
|
"is_local_process_zero": true,
|
||
|
|
"is_world_process_zero": true,
|
||
|
|
"log_history": [
|
||
|
|
{
|
||
|
|
"epoch": 1.0,
|
||
|
|
"grad_norm": 10.389764785766602,
|
||
|
|
"learning_rate": 2.203344436447427e-05,
|
||
|
|
"loss": 4.208139894888604,
|
||
|
|
"step": 634
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 1.0,
|
||
|
|
"eval_exact_match": 31.68,
|
||
|
|
"eval_f1": 45.273247698850945,
|
||
|
|
"eval_loss": 2.3350870609283447,
|
||
|
|
"eval_runtime": 7.7987,
|
||
|
|
"eval_samples_per_second": 162.207,
|
||
|
|
"eval_steps_per_second": 10.258,
|
||
|
|
"step": 634
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 2.0,
|
||
|
|
"grad_norm": 9.32017707824707,
|
||
|
|
"learning_rate": 1.1025403602396503e-05,
|
||
|
|
"loss": 2.3320699505249407,
|
||
|
|
"step": 1268
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 2.0,
|
||
|
|
"eval_exact_match": 45.52,
|
||
|
|
"eval_f1": 58.06834889049466,
|
||
|
|
"eval_loss": 1.9215565919876099,
|
||
|
|
"eval_runtime": 7.8078,
|
||
|
|
"eval_samples_per_second": 162.017,
|
||
|
|
"eval_steps_per_second": 10.246,
|
||
|
|
"step": 1268
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"logging_steps": 500,
|
||
|
|
"max_steps": 1902,
|
||
|
|
"num_input_tokens_seen": 0,
|
||
|
|
"num_train_epochs": 3,
|
||
|
|
"save_steps": 500,
|
||
|
|
"stateful_callbacks": {
|
||
|
|
"TrainerControl": {
|
||
|
|
"args": {
|
||
|
|
"should_epoch_stop": false,
|
||
|
|
"should_evaluate": false,
|
||
|
|
"should_log": false,
|
||
|
|
"should_save": true,
|
||
|
|
"should_training_stop": false
|
||
|
|
},
|
||
|
|
"attributes": {}
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"total_flos": 6180991462324224.0,
|
||
|
|
"train_batch_size": 16,
|
||
|
|
"trial_name": null,
|
||
|
|
"trial_params": {
|
||
|
|
"learning_rate": 2.9707819785354985e-05,
|
||
|
|
"lora_alpha": 128,
|
||
|
|
"lora_dropout": 0.12668659169460122,
|
||
|
|
"lora_r": 256,
|
||
|
|
"num_train_epochs": 3,
|
||
|
|
"weight_decay": 0.05519317165246046
|
||
|
|
}
|
||
|
|
}
|