8049af9
1
2
3
4
5
6
7
8
9
model_name_or_path = yahma/llama-13b-hf learning_rate = 1e-4 max_steps = 10000 epoch = 3.08 train_loss = 0.7169 train_runtime = 1 day, 7:23:32.67 train_samples_per_second = 1.416 train_steps_per_second = 0.088
