harrisr-smu's picture
Training in progress, epoch 2
7960612 verified
raw
history blame
1.33 kB
{
"best_metric": 0.49598738599258474,
"best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-0/checkpoint-536",
"epoch": 2.0,
"eval_steps": 500,
"global_step": 536,
"is_hyper_param_search": true,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.0,
"eval_loss": 0.4704936742782593,
"eval_matthews_correlation": 0.45744157534977586,
"eval_runtime": 30.3484,
"eval_samples_per_second": 34.367,
"eval_steps_per_second": 2.175,
"step": 268
},
{
"epoch": 1.87,
"grad_norm": 4.522963523864746,
"learning_rate": 6.0537366159391475e-06,
"loss": 0.4213,
"step": 500
},
{
"epoch": 2.0,
"eval_loss": 0.5014804601669312,
"eval_matthews_correlation": 0.49598738599258474,
"eval_runtime": 31.4302,
"eval_samples_per_second": 33.185,
"eval_steps_per_second": 2.1,
"step": 536
}
],
"logging_steps": 500,
"max_steps": 536,
"num_input_tokens_seen": 0,
"num_train_epochs": 2,
"save_steps": 500,
"total_flos": 95271225799404.0,
"train_batch_size": 32,
"trial_name": null,
"trial_params": {
"learning_rate": 9.01334118373162e-05,
"num_train_epochs": 2,
"per_device_train_batch_size": 32,
"seed": 1
}
}