90 lines
2.2 KiB
JSON
90 lines
2.2 KiB
JSON
|
{
|
||
|
|
"best_global_step": 1902,
|
||
|
|
"best_metric": 78.458442399707,
|
||
|
|
"best_model_checkpoint": "mbert-loraxs-qa-vanilla/run-3/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": 0.7886435331230284,
|
||
|
|
"grad_norm": 31.252710342407227,
|
||
|
|
"learning_rate": 2.5915663787327118e-05,
|
||
|
|
"loss": 2.36512060546875,
|
||
|
|
"step": 500
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 1.0,
|
||
|
|
"eval_exact_match": 61.76,
|
||
|
|
"eval_f1": 76.08343679857553,
|
||
|
|
"eval_loss": 1.205523133277893,
|
||
|
|
"eval_runtime": 5.7547,
|
||
|
|
"eval_samples_per_second": 219.822,
|
||
|
|
"eval_steps_per_second": 13.902,
|
||
|
|
"step": 634
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 1.5772870662460567,
|
||
|
|
"grad_norm": 29.112215042114258,
|
||
|
|
"learning_rate": 1.6679860584430782e-05,
|
||
|
|
"loss": 1.0828076171875,
|
||
|
|
"step": 1000
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 2.0,
|
||
|
|
"eval_exact_match": 64.4,
|
||
|
|
"eval_f1": 77.92568009442539,
|
||
|
|
"eval_loss": 1.2169331312179565,
|
||
|
|
"eval_runtime": 5.8111,
|
||
|
|
"eval_samples_per_second": 217.687,
|
||
|
|
"eval_steps_per_second": 13.767,
|
||
|
|
"step": 1268
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 2.365930599369085,
|
||
|
|
"grad_norm": 7.044902324676514,
|
||
|
|
"learning_rate": 7.444057381534446e-06,
|
||
|
|
"loss": 0.7706432495117187,
|
||
|
|
"step": 1500
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 3.0,
|
||
|
|
"eval_exact_match": 64.24,
|
||
|
|
"eval_f1": 78.458442399707,
|
||
|
|
"eval_loss": 1.3074095249176025,
|
||
|
|
"eval_runtime": 6.3974,
|
||
|
|
"eval_samples_per_second": 197.738,
|
||
|
|
"eval_steps_per_second": 12.505,
|
||
|
|
"step": 1902
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"logging_steps": 500,
|
||
|
|
"max_steps": 1902,
|
||
|
|
"num_input_tokens_seen": 0,
|
||
|
|
"num_train_epochs": 3,
|
||
|
|
"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": 4702949676112896.0,
|
||
|
|
"train_batch_size": 16,
|
||
|
|
"trial_name": null,
|
||
|
|
"trial_params": {
|
||
|
|
"learning_rate": 3.160491856031126e-05,
|
||
|
|
"num_train_epochs": 3,
|
||
|
|
"weight_decay": 0.022722580353297495
|
||
|
|
}
|
||
|
|
}
|