datht's picture
Training in progress, epoch 2
3b8893b verified
raw
history blame
1.31 kB
{
"best_metric": 0.7791095890410958,
"best_model_checkpoint": "distilbert-base-uncased-finetuned-SA/run-2/checkpoint-293",
"epoch": 2.0,
"eval_steps": 500,
"global_step": 586,
"is_hyper_param_search": true,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.0,
"eval_accuracy": 0.7791095890410958,
"eval_loss": 0.4647526144981384,
"eval_runtime": 3.3644,
"eval_samples_per_second": 173.581,
"eval_steps_per_second": 10.997,
"step": 293
},
{
"epoch": 1.71,
"grad_norm": 12.796131134033203,
"learning_rate": 1.0510539180585223e-05,
"loss": 0.5057,
"step": 500
},
{
"epoch": 2.0,
"eval_accuracy": 0.7773972602739726,
"eval_loss": 0.452179491519928,
"eval_runtime": 3.3787,
"eval_samples_per_second": 172.846,
"eval_steps_per_second": 10.951,
"step": 586
}
],
"logging_steps": 500,
"max_steps": 879,
"num_input_tokens_seen": 0,
"num_train_epochs": 3,
"save_steps": 500,
"total_flos": 632183474186820.0,
"train_batch_size": 16,
"trial_name": null,
"trial_params": {
"learning_rate": 2.4376685856819023e-05,
"num_train_epochs": 3,
"per_device_train_batch_size": 16,
"seed": 1
}
}