93 lines
2.3 KiB
JSON
93 lines
2.3 KiB
JSON
|
{
|
||
|
|
"best_global_step": 1902,
|
||
|
|
"best_metric": 73.47770313406798,
|
||
|
|
"best_model_checkpoint": "mbert-loraxs-qa-vanilla/run-11/checkpoint-1902",
|
||
|
|
"epoch": 3.0,
|
||
|
|
"eval_steps": 500,
|
||
|
|
"global_step": 1902,
|
||
|
|
"is_hyper_param_search": true,
|
||
|
|
"is_local_process_zero": true,
|
||
|
|
"is_world_process_zero": true,
|
||
|
|
"log_history": [
|
||
|
|
{
|
||
|
|
"epoch": 1.0,
|
||
|
|
"grad_norm": 5.858374118804932,
|
||
|
|
"learning_rate": 0.0001323620801649496,
|
||
|
|
"loss": 3.488962456254929,
|
||
|
|
"step": 634
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 1.0,
|
||
|
|
"eval_exact_match": 51.92,
|
||
|
|
"eval_f1": 65.66949504508666,
|
||
|
|
"eval_loss": 1.6104148626327515,
|
||
|
|
"eval_runtime": 7.857,
|
||
|
|
"eval_samples_per_second": 161.002,
|
||
|
|
"eval_steps_per_second": 10.182,
|
||
|
|
"step": 634
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 2.0,
|
||
|
|
"grad_norm": 5.785969257354736,
|
||
|
|
"learning_rate": 9.928460329282582e-05,
|
||
|
|
"loss": 1.61112075950069,
|
||
|
|
"step": 1268
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 2.0,
|
||
|
|
"eval_exact_match": 56.96,
|
||
|
|
"eval_f1": 71.61806679989618,
|
||
|
|
"eval_loss": 1.4072195291519165,
|
||
|
|
"eval_runtime": 7.8319,
|
||
|
|
"eval_samples_per_second": 161.519,
|
||
|
|
"eval_steps_per_second": 10.215,
|
||
|
|
"step": 1268
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 3.0,
|
||
|
|
"grad_norm": 3.854477882385254,
|
||
|
|
"learning_rate": 6.620712642070203e-05,
|
||
|
|
"loss": 1.356120882726242,
|
||
|
|
"step": 1902
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 3.0,
|
||
|
|
"eval_exact_match": 58.48,
|
||
|
|
"eval_f1": 73.47770313406798,
|
||
|
|
"eval_loss": 1.3114500045776367,
|
||
|
|
"eval_runtime": 7.8421,
|
||
|
|
"eval_samples_per_second": 161.309,
|
||
|
|
"eval_steps_per_second": 10.201,
|
||
|
|
"step": 1902
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"logging_steps": 500,
|
||
|
|
"max_steps": 3170,
|
||
|
|
"num_input_tokens_seen": 0,
|
||
|
|
"num_train_epochs": 5,
|
||
|
|
"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": 9271487193486336.0,
|
||
|
|
"train_batch_size": 16,
|
||
|
|
"trial_name": null,
|
||
|
|
"trial_params": {
|
||
|
|
"learning_rate": 0.00014884864592455704,
|
||
|
|
"lora_alpha": 64,
|
||
|
|
"lora_dropout": 0.1388229048767175,
|
||
|
|
"lora_r": 256,
|
||
|
|
"num_train_epochs": 5,
|
||
|
|
"weight_decay": 0.09101302692639024
|
||
|
|
}
|
||
|
|
}
|