148 lines
3.8 KiB
JSON
148 lines
3.8 KiB
JSON
{
|
|
"best_metric": 0.9578313253012049,
|
|
"best_model_checkpoint": "UL_bedroom_classification/checkpoint-63",
|
|
"epoch": 6.8108108108108105,
|
|
"eval_steps": 500,
|
|
"global_step": 63,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"epoch": 0.972972972972973,
|
|
"eval_accuracy": 0.8463855421686747,
|
|
"eval_loss": 0.4275299310684204,
|
|
"eval_runtime": 8.4557,
|
|
"eval_samples_per_second": 39.264,
|
|
"eval_steps_per_second": 1.301,
|
|
"step": 9
|
|
},
|
|
{
|
|
"epoch": 1.0810810810810811,
|
|
"grad_norm": 2.2527873516082764,
|
|
"learning_rate": 4.732142857142857e-05,
|
|
"loss": 0.7101,
|
|
"step": 10
|
|
},
|
|
{
|
|
"epoch": 1.945945945945946,
|
|
"eval_accuracy": 0.9518072289156626,
|
|
"eval_loss": 0.19900576770305634,
|
|
"eval_runtime": 9.1611,
|
|
"eval_samples_per_second": 36.24,
|
|
"eval_steps_per_second": 1.201,
|
|
"step": 18
|
|
},
|
|
{
|
|
"epoch": 2.1621621621621623,
|
|
"grad_norm": 1.2397936582565308,
|
|
"learning_rate": 3.839285714285715e-05,
|
|
"loss": 0.3133,
|
|
"step": 20
|
|
},
|
|
{
|
|
"epoch": 2.918918918918919,
|
|
"eval_accuracy": 0.9548192771084337,
|
|
"eval_loss": 0.13989512622356415,
|
|
"eval_runtime": 9.427,
|
|
"eval_samples_per_second": 35.218,
|
|
"eval_steps_per_second": 1.167,
|
|
"step": 27
|
|
},
|
|
{
|
|
"epoch": 3.2432432432432434,
|
|
"grad_norm": 1.1667276620864868,
|
|
"learning_rate": 2.9464285714285718e-05,
|
|
"loss": 0.2012,
|
|
"step": 30
|
|
},
|
|
{
|
|
"epoch": 4.0,
|
|
"eval_accuracy": 0.9548192771084337,
|
|
"eval_loss": 0.12292628735303879,
|
|
"eval_runtime": 9.5891,
|
|
"eval_samples_per_second": 34.623,
|
|
"eval_steps_per_second": 1.147,
|
|
"step": 37
|
|
},
|
|
{
|
|
"epoch": 4.324324324324325,
|
|
"grad_norm": 1.3547431230545044,
|
|
"learning_rate": 2.0535714285714285e-05,
|
|
"loss": 0.1724,
|
|
"step": 40
|
|
},
|
|
{
|
|
"epoch": 4.972972972972973,
|
|
"eval_accuracy": 0.9487951807228916,
|
|
"eval_loss": 0.13844643533229828,
|
|
"eval_runtime": 9.5401,
|
|
"eval_samples_per_second": 34.801,
|
|
"eval_steps_per_second": 1.153,
|
|
"step": 46
|
|
},
|
|
{
|
|
"epoch": 5.405405405405405,
|
|
"grad_norm": 1.610047459602356,
|
|
"learning_rate": 1.1607142857142857e-05,
|
|
"loss": 0.1458,
|
|
"step": 50
|
|
},
|
|
{
|
|
"epoch": 5.945945945945946,
|
|
"eval_accuracy": 0.9518072289156626,
|
|
"eval_loss": 0.12401360273361206,
|
|
"eval_runtime": 9.3935,
|
|
"eval_samples_per_second": 35.344,
|
|
"eval_steps_per_second": 1.171,
|
|
"step": 55
|
|
},
|
|
{
|
|
"epoch": 6.486486486486487,
|
|
"grad_norm": 1.9438917636871338,
|
|
"learning_rate": 2.6785714285714285e-06,
|
|
"loss": 0.1476,
|
|
"step": 60
|
|
},
|
|
{
|
|
"epoch": 6.8108108108108105,
|
|
"eval_accuracy": 0.9578313253012049,
|
|
"eval_loss": 0.1282922625541687,
|
|
"eval_runtime": 9.5037,
|
|
"eval_samples_per_second": 34.934,
|
|
"eval_steps_per_second": 1.157,
|
|
"step": 63
|
|
},
|
|
{
|
|
"epoch": 6.8108108108108105,
|
|
"step": 63,
|
|
"total_flos": 6.169967512085422e+17,
|
|
"train_loss": 0.27290829495778157,
|
|
"train_runtime": 723.3592,
|
|
"train_samples_per_second": 11.293,
|
|
"train_steps_per_second": 0.087
|
|
}
|
|
],
|
|
"logging_steps": 10,
|
|
"max_steps": 63,
|
|
"num_input_tokens_seen": 0,
|
|
"num_train_epochs": 7,
|
|
"save_steps": 500,
|
|
"stateful_callbacks": {
|
|
"TrainerControl": {
|
|
"args": {
|
|
"should_epoch_stop": false,
|
|
"should_evaluate": false,
|
|
"should_log": false,
|
|
"should_save": true,
|
|
"should_training_stop": true
|
|
},
|
|
"attributes": {}
|
|
}
|
|
},
|
|
"total_flos": 6.169967512085422e+17,
|
|
"train_batch_size": 32,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|