59 lines
1.4 KiB
JSON
59 lines
1.4 KiB
JSON
|
{
|
||
|
|
"best_global_step": 634,
|
||
|
|
"best_metric": 63.941961174475914,
|
||
|
|
"best_model_checkpoint": "mbert-loraxs-qa-vanilla/run-3/checkpoint-634",
|
||
|
|
"epoch": 1.0,
|
||
|
|
"eval_steps": 500,
|
||
|
|
"global_step": 634,
|
||
|
|
"is_hyper_param_search": true,
|
||
|
|
"is_local_process_zero": true,
|
||
|
|
"is_world_process_zero": true,
|
||
|
|
"log_history": [
|
||
|
|
{
|
||
|
|
"epoch": 1.0,
|
||
|
|
"grad_norm": 25.72856330871582,
|
||
|
|
"learning_rate": 0.00036170225367171497,
|
||
|
|
"loss": 2.8233307558655363,
|
||
|
|
"step": 634
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 1.0,
|
||
|
|
"eval_exact_match": 50.32,
|
||
|
|
"eval_f1": 63.941961174475914,
|
||
|
|
"eval_loss": 1.6252752542495728,
|
||
|
|
"eval_runtime": 7.6169,
|
||
|
|
"eval_samples_per_second": 166.078,
|
||
|
|
"eval_steps_per_second": 10.503,
|
||
|
|
"step": 634
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"logging_steps": 500,
|
||
|
|
"max_steps": 3804,
|
||
|
|
"num_input_tokens_seen": 0,
|
||
|
|
"num_train_epochs": 6,
|
||
|
|
"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": 2511572962139136.0,
|
||
|
|
"train_batch_size": 16,
|
||
|
|
"trial_name": null,
|
||
|
|
"trial_params": {
|
||
|
|
"learning_rate": 0.0003904468036323811,
|
||
|
|
"lora_alpha": 256,
|
||
|
|
"lora_dropout": 0.22980730880873645,
|
||
|
|
"lora_r": 128,
|
||
|
|
"num_train_epochs": 6,
|
||
|
|
"weight_decay": 0.06293800360990247
|
||
|
|
}
|
||
|
|
}
|