HuggingFaceTB/SmolLM2-135M-Instruct
4241.7m
1{2 "epoch": 1.9973828840617638,3 "total_flos": 0.0,4 "train_loss": 0.675485389037702,5 "train_runtime": 5897.7907,6 "train_samples": 61134,7 "train_samples_per_second": 20.731,8 "train_steps_per_second": 0.1629}