ana-grassmann's picture
Training in progress, epoch 1
b87026d verified
{
"best_metric": 0.6513409961685823,
"best_model_checkpoint": "bert-finetuned-spam/run-4/checkpoint-39",
"epoch": 2.9433962264150946,
"eval_steps": 500,
"global_step": 39,
"is_hyper_param_search": true,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.9811320754716981,
"eval_accuracy": 0.6360153256704981,
"eval_loss": 0.6667433977127075,
"eval_runtime": 11.9551,
"eval_samples_per_second": 87.327,
"eval_steps_per_second": 5.521,
"step": 13
},
{
"epoch": 1.9622641509433962,
"eval_accuracy": 0.6369731800766284,
"eval_loss": 0.6545999646186829,
"eval_runtime": 11.9785,
"eval_samples_per_second": 87.156,
"eval_steps_per_second": 5.51,
"step": 26
},
{
"epoch": 2.9433962264150946,
"eval_accuracy": 0.6513409961685823,
"eval_loss": 0.646373987197876,
"eval_runtime": 11.9349,
"eval_samples_per_second": 87.475,
"eval_steps_per_second": 5.53,
"step": 39
}
],
"logging_steps": 500,
"max_steps": 39,
"num_input_tokens_seen": 0,
"num_train_epochs": 3,
"save_steps": 500,
"total_flos": 0,
"train_batch_size": 64,
"trial_name": null,
"trial_params": {
"learning_rate": 6.10788229546224e-05,
"num_train_epochs": 3,
"per_device_train_batch_size": 64,
"seed": 16
}
}