hfdsajkfd's picture
Training in progress, epoch 1
6b69b87 verified
raw
history blame
1.27 kB
{
"best_metric": 0.4507129896372791,
"best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-4/checkpoint-1069",
"epoch": 1.0,
"eval_steps": 500,
"global_step": 1069,
"is_hyper_param_search": true,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.4677268475210477,
"grad_norm": 10.02040958404541,
"learning_rate": 9.850120145255282e-06,
"loss": 0.5436,
"step": 500
},
{
"epoch": 0.9354536950420954,
"grad_norm": 12.507477760314941,
"learning_rate": 1.1944785413402715e-06,
"loss": 0.4997,
"step": 1000
},
{
"epoch": 1.0,
"eval_loss": 0.4817218780517578,
"eval_matthews_correlation": 0.4507129896372791,
"eval_runtime": 0.3399,
"eval_samples_per_second": 3068.93,
"eval_steps_per_second": 194.199,
"step": 1069
}
],
"logging_steps": 500,
"max_steps": 1069,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 500,
"total_flos": 37629020430720.0,
"train_batch_size": 8,
"trial_name": null,
"trial_params": {
"learning_rate": 1.8505761749170293e-05,
"num_train_epochs": 1,
"per_device_train_batch_size": 8,
"seed": 28
}
}