eformConsult / run-7 /checkpoint-1340 /trainer_state.json
RavingRabbit's picture
Training in progress, epoch 1
05076c5
{
"best_metric": 0.5221688848649157,
"best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-7/checkpoint-1072",
"epoch": 5.0,
"eval_steps": 500,
"global_step": 1340,
"is_hyper_param_search": true,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.0,
"eval_loss": 0.481789767742157,
"eval_matthews_correlation": 0.4368717152763518,
"eval_runtime": 0.7166,
"eval_samples_per_second": 1455.425,
"eval_steps_per_second": 92.098,
"step": 268
},
{
"epoch": 1.87,
"learning_rate": 3.509309760035438e-05,
"loss": 0.4167,
"step": 500
},
{
"epoch": 2.0,
"eval_loss": 0.5229902267456055,
"eval_matthews_correlation": 0.4746837140719997,
"eval_runtime": 0.7929,
"eval_samples_per_second": 1315.363,
"eval_steps_per_second": 83.235,
"step": 536
},
{
"epoch": 3.0,
"eval_loss": 0.6462266445159912,
"eval_matthews_correlation": 0.5120519207329847,
"eval_runtime": 0.7953,
"eval_samples_per_second": 1311.521,
"eval_steps_per_second": 82.992,
"step": 804
},
{
"epoch": 3.73,
"learning_rate": 1.4204349028714865e-05,
"loss": 0.1554,
"step": 1000
},
{
"epoch": 4.0,
"eval_loss": 0.7052999138832092,
"eval_matthews_correlation": 0.5221688848649157,
"eval_runtime": 0.8041,
"eval_samples_per_second": 1297.093,
"eval_steps_per_second": 82.079,
"step": 1072
},
{
"epoch": 5.0,
"eval_loss": 0.9151925444602966,
"eval_matthews_correlation": 0.5100838064555473,
"eval_runtime": 1.0618,
"eval_samples_per_second": 982.329,
"eval_steps_per_second": 62.161,
"step": 1340
}
],
"logging_steps": 500,
"max_steps": 1340,
"num_input_tokens_seen": 0,
"num_train_epochs": 5,
"save_steps": 500,
"total_flos": 191053175514720.0,
"train_batch_size": 32,
"trial_name": null,
"trial_params": {
"learning_rate": 5.598184617199388e-05,
"num_train_epochs": 5,
"per_device_train_batch_size": 32,
"seed": 17
}
}