{ "epoch": 2.9904761904761905, "num_input_tokens_seen": 8039616, "total_flos": 3.746411207808123e+17, "train_loss": 0.05875852833955716, "train_runtime": 3746.4527, "train_samples_per_second": 0.841, "train_steps_per_second": 0.052 }