59 lines
1.4 KiB
JSON
59 lines
1.4 KiB
JSON
|
{
|
||
|
|
"best_global_step": 634,
|
||
|
|
"best_metric": 66.45284613864096,
|
||
|
|
"best_model_checkpoint": "mbert-loraxs-qa-vanilla/run-7/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": 56.062278747558594,
|
||
|
|
"learning_rate": 5.730149137854825e-05,
|
||
|
|
"loss": 3.2366831686218456,
|
||
|
|
"step": 634
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 1.0,
|
||
|
|
"eval_exact_match": 52.72,
|
||
|
|
"eval_f1": 66.45284613864096,
|
||
|
|
"eval_loss": 1.5741198062896729,
|
||
|
|
"eval_runtime": 7.702,
|
||
|
|
"eval_samples_per_second": 164.243,
|
||
|
|
"eval_steps_per_second": 10.387,
|
||
|
|
"step": 634
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"logging_steps": 500,
|
||
|
|
"max_steps": 2536,
|
||
|
|
"num_input_tokens_seen": 0,
|
||
|
|
"num_train_epochs": 4,
|
||
|
|
"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": 6.871361183701897e-05,
|
||
|
|
"lora_alpha": 512,
|
||
|
|
"lora_dropout": 0.2970595529882041,
|
||
|
|
"lora_r": 128,
|
||
|
|
"num_train_epochs": 4,
|
||
|
|
"weight_decay": 0.0640462328905566
|
||
|
|
}
|
||
|
|
}
|