jonatatyska/DeepSeek-R1-Distill-Qwen-1.5B-Embodied-SFT-GRPO

Model save

Training in progress, step 240

Training in progress, step 230

Training in progress, step 220

Training in progress, step 210

Training in progress, step 200

Training in progress, step 190

Training in progress, step 180

Training in progress, step 170

Training in progress, step 160

Training in progress, step 150

Training in progress, step 140

Training in progress, step 130

Training in progress, step 120

Training in progress, step 110

Training in progress, step 100

Training in progress, step 90

Training in progress, step 80

Training in progress, step 70

Training in progress, step 60

Training in progress, step 50

Training in progress, step 40

Training in progress, step 30

Training in progress, step 20

Training in progress, step 10

initial commit