diff --git "a/analysis_optimized.log" "b/analysis_optimized.log"
new file mode 100644--- /dev/null
+++ "b/analysis_optimized.log"
@@ -0,0 +1,446 @@
+nohup: ignoring input
+Retriggering analysis for video 6faca277-99bc-4a28-9a3d-15ca6b871730...
+
+WARNING ⚠️ imgsz=[1080] must be multiple of max stride 32, updating to [1088]
+0: 640x1088 1 basketball, 1 hoop, 6 players, 1 referee, 3 shot-clocks, 646.4ms
+1: 640x1088 1 basketball, 1 hoop, 6 players, 1 referee, 3 shot-clocks, 646.4ms
+2: 640x1088 1 basketball, 1 hoop, 5 players, 1 referee, 3 shot-clocks, 646.4ms
+3: 640x1088 1 basketball, 1 hoop, 8 players, 1 referee, 3 shot-clocks, 646.4ms
+4: 640x1088 1 basketball, 1 hoop, 6 players, 1 shot-clock, 646.4ms
+5: 640x1088 1 basketball, 1 hoop, 6 players, 646.4ms
+6: 640x1088 1 basketball, 1 hoop, 5 players, 646.4ms
+7: 640x1088 1 hoop, 5 players, 646.4ms
+8: 640x1088 1 basketball, 1 hoop, 4 players, 646.4ms
+9: 640x1088 1 basketball, 1 hoop, 5 players, 646.4ms
+Speed: 49.2ms preprocess, 646.4ms inference, 12.4ms postprocess per image at shape (1, 3, 640, 1088)
+
+WARNING ⚠️ imgsz=[1080] must be multiple of max stride 32, updating to [1088]
+0: 640x1088 1 basketball, 1 hoop, 7 players, 217.9ms
+1: 640x1088 1 basketball, 1 hoop, 6 players, 217.9ms
+2: 640x1088 1 basketball, 1 hoop, 7 players, 217.9ms
+3: 640x1088 1 basketball, 1 hoop, 5 players, 217.9ms
+4: 640x1088 1 basketball, 1 hoop, 6 players, 217.9ms
+5: 640x1088 1 basketball, 1 hoop, 8 players, 217.9ms
+6: 640x1088 1 basketball, 1 hoop, 8 players, 1 referee, 217.9ms
+7: 640x1088 2 basketballs, 1 hoop, 5 players, 217.9ms
+8: 640x1088 2 basketballs, 1 hoop, 5 players, 1 referee, 217.9ms
+9: 640x1088 2 basketballs, 1 hoop, 4 players, 2 referees, 217.9ms
+Speed: 34.5ms preprocess, 217.9ms inference, 0.8ms postprocess per image at shape (1, 3, 640, 1088)
+
+WARNING ⚠️ imgsz=[1080] must be multiple of max stride 32, updating to [1088]
+0: 640x1088 1 hoop, 6 players, 178.4ms
+1: 640x1088 1 hoop, 6 players, 178.4ms
+2: 640x1088 1 hoop, 7 players, 178.4ms
+3: 640x1088 2 basketballs, 1 hoop, 8 players, 178.4ms
+4: 640x1088 1 hoop, 7 players, 178.4ms
+5: 640x1088 1 basketball, 1 hoop, 7 players, 178.4ms
+6: 640x1088 1 basketball, 1 hoop, 7 players, 178.4ms
+7: 640x1088 1 basketball, 1 hoop, 6 players, 178.4ms
+8: 640x1088 2 basketballs, 1 hoop, 8 players, 178.4ms
+9: 640x1088 1 basketball, 1 hoop, 5 players, 178.4ms
+Speed: 41.2ms preprocess, 178.4ms inference, 0.6ms postprocess per image at shape (1, 3, 640, 1088)
+
+WARNING ⚠️ imgsz=[1080] must be multiple of max stride 32, updating to [1088]
+0: 640x1088 1 basketball, 1 hoop, 6 players, 340.7ms
+1: 640x1088 1 basketball, 1 hoop, 12 players, 340.7ms
+2: 640x1088 1 basketball, 1 hoop, 8 players, 340.7ms
+3: 640x1088 1 basketball, 1 hoop, 10 players, 340.7ms
+4: 640x1088 1 basketball, 1 hoop, 9 players, 340.7ms
+5: 640x1088 1 basketball, 1 hoop, 6 players, 340.7ms
+6: 640x1088 2 basketballs, 1 hoop, 6 players, 340.7ms
+7: 640x1088 1 basketball, 1 hoop, 6 players, 340.7ms
+8: 640x1088 1 basketball, 2 hoops, 6 players, 340.7ms
+9: 640x1088 2 basketballs, 1 hoop, 7 players, 340.7ms
+Speed: 65.1ms preprocess, 340.7ms inference, 0.6ms postprocess per image at shape (1, 3, 640, 1088)
+
+WARNING ⚠️ imgsz=[1080] must be multiple of max stride 32, updating to [1088]
+0: 640x1088 1 basketball, 1 hoop, 11 players, 227.3ms
+1: 640x1088 2 basketballs, 1 hoop, 9 players, 227.3ms
+2: 640x1088 2 basketballs, 1 hoop, 8 players, 227.3ms
+3: 640x1088 1 basketball, 1 hoop, 9 players, 227.3ms
+4: 640x1088 1 basketball, 1 hoop, 10 players, 227.3ms
+5: 640x1088 1 basketball, 1 hoop, 10 players, 227.3ms
+6: 640x1088 1 basketball, 1 hoop, 10 players, 1 referee, 227.3ms
+7: 640x1088 1 basketball, 1 hoop, 6 players, 227.3ms
+8: 640x1088 1 basketball, 1 hoop, 7 players, 227.3ms
+9: 640x1088 1 basketball, 1 hoop, 4 players, 227.3ms
+Speed: 52.8ms preprocess, 227.3ms inference, 1.7ms postprocess per image at shape (1, 3, 640, 1088)
+
+WARNING ⚠️ imgsz=[1080] must be multiple of max stride 32, updating to [1088]
+0: 640x1088 1 basketball, 1 hoop, 5 players, 194.5ms
+1: 640x1088 1 hoop, 7 players, 194.5ms
+2: 640x1088 1 hoop, 7 players, 194.5ms
+3: 640x1088 1 basketball, 1 hoop, 8 players, 194.5ms
+4: 640x1088 1 basketball, 1 hoop, 6 players, 194.5ms
+5: 640x1088 1 basketball, 1 hoop, 9 players, 194.5ms
+6: 640x1088 1 basketball, 1 hoop, 7 players, 194.5ms
+7: 640x1088 1 basketball, 1 hoop, 6 players, 194.5ms
+8: 640x1088 1 basketball, 1 hoop, 6 players, 194.5ms
+9: 640x1088 1 basketball, 1 hoop, 5 players, 194.5ms
+Speed: 68.5ms preprocess, 194.5ms inference, 1.2ms postprocess per image at shape (1, 3, 640, 1088)
+
+WARNING ⚠️ imgsz=[1080] must be multiple of max stride 32, updating to [1088]
+0: 640x1088 1 basketball, 1 hoop, 8 players, 279.7ms
+1: 640x1088 2 basketballs, 1 hoop, 8 players, 279.7ms
+2: 640x1088 1 basketball, 1 hoop, 5 players, 1 referee, 279.7ms
+3: 640x1088 2 basketballs, 1 hoop, 5 players, 1 referee, 279.7ms
+4: 640x1088 2 basketballs, 1 hoop, 5 players, 279.7ms
+5: 640x1088 1 basketball, 1 hoop, 6 players, 279.7ms
+6: 640x1088 1 basketball, 1 hoop, 6 players, 279.7ms
+7: 640x1088 1 basketball, 1 hoop, 5 players, 1 referee, 279.7ms
+8: 640x1088 1 basketball, 5 players, 1 referee, 279.7ms
+9: 640x1088 1 basketball, 1 hoop, 4 players, 1 referee, 279.7ms
+Speed: 65.6ms preprocess, 279.7ms inference, 1.4ms postprocess per image at shape (1, 3, 640, 1088)
+
+WARNING ⚠️ imgsz=[1080] must be multiple of max stride 32, updating to [1088]
+0: 640x1088 1 basketball, 6 players, 1 referee, 364.0ms
+1: 640x1088 1 basketball, 6 players, 1 referee, 364.0ms
+2: 640x1088 1 basketball, 4 players, 364.0ms
+3: 640x1088 1 basketball, 5 players, 364.0ms
+4: 640x1088 2 basketballs, 6 players, 364.0ms
+5: 640x1088 1 basketball, 8 players, 364.0ms
+6: 640x1088 1 basketball, 7 players, 364.0ms
+7: 640x1088 2 basketballs, 8 players, 364.0ms
+8: 640x1088 1 basketball, 6 players, 364.0ms
+9: 640x1088 1 basketball, 1 hoop, 6 players, 364.0ms
+Speed: 44.6ms preprocess, 364.0ms inference, 6.4ms postprocess per image at shape (1, 3, 640, 1088)
+
+WARNING ⚠️ imgsz=[1080] must be multiple of max stride 32, updating to [1088]
+0: 640x1088 1 basketball, 1 hoop, 5 players, 179.4ms
+1: 640x1088 1 basketball, 6 players, 179.4ms
+2: 640x1088 1 basketball, 1 hoop, 6 players, 179.4ms
+3: 640x1088 1 basketball, 1 hoop, 8 players, 179.4ms
+4: 640x1088 1 basketball, 9 players, 179.4ms
+5: 640x1088 2 basketballs, 7 players, 179.4ms
+6: 640x1088 1 basketball, 7 players, 179.4ms
+7: 640x1088 8 players, 179.4ms
+8: 640x1088 1 basketball, 1 hoop, 5 players, 179.4ms
+9: 640x1088 1 basketball, 6 players, 179.4ms
+Speed: 56.5ms preprocess, 179.4ms inference, 1.3ms postprocess per image at shape (1, 3, 640, 1088)
+
+WARNING ⚠️ imgsz=[1080] must be multiple of max stride 32, updating to [1088]
+0: 640x1088 1 basketball, 8 players, 191.1ms
+1: 640x1088 2 basketballs, 8 players, 191.1ms
+2: 640x1088 1 basketball, 7 players, 191.1ms
+3: 640x1088 2 basketballs, 1 hoop, 11 players, 191.1ms
+4: 640x1088 1 basketball, 1 hoop, 12 players, 191.1ms
+5: 640x1088 1 basketball, 1 hoop, 11 players, 191.1ms
+6: 640x1088 1 hoop, 8 players, 191.1ms
+7: 640x1088 3 basketballs, 1 hoop, 8 players, 191.1ms
+8: 640x1088 1 basketball, 1 hoop, 8 players, 191.1ms
+9: 640x1088 1 basketball, 1 hoop, 7 players, 191.1ms
+Speed: 74.7ms preprocess, 191.1ms inference, 1.0ms postprocess per image at shape (1, 3, 640, 1088)
+
+WARNING ⚠️ imgsz=[1080] must be multiple of max stride 32, updating to [1088]
+0: 640x1088 2 basketballs, 9 players, 193.4ms
+1: 640x1088 1 basketball, 6 players, 193.4ms
+2: 640x1088 1 basketball, 1 hoop, 5 players, 193.4ms
+3: 640x1088 1 basketball, 2 hoops, 5 players, 193.4ms
+4: 640x1088 3 basketballs, 2 hoops, 4 players, 193.4ms
+5: 640x1088 1 basketball, 1 hoop, 4 players, 193.4ms
+6: 640x1088 3 basketballs, 3 hoops, 10 players, 193.4ms
+7: 640x1088 1 basketball, 2 hoops, 11 players, 193.4ms
+8: 640x1088 1 basketball, 1 hoop, 10 players, 193.4ms
+9: 640x1088 1 basketball, 2 hoops, 10 players, 193.4ms
+Speed: 114.1ms preprocess, 193.4ms inference, 0.7ms postprocess per image at shape (1, 3, 640, 1088)
+
+WARNING ⚠️ imgsz=[1080] must be multiple of max stride 32, updating to [1088]
+0: 640x1088 1 basketball, 8 players, 224.4ms
+1: 640x1088 1 basketball, 5 players, 224.4ms
+2: 640x1088 1 basketball, 2 hoops, 5 players, 224.4ms
+3: 640x1088 2 hoops, 10 players, 224.4ms
+4: 640x1088 1 basketball, 1 hoop, 7 players, 224.4ms
+5: 640x1088 1 basketball, 6 players, 224.4ms
+6: 640x1088 1 basketball, 1 hoop, 7 players, 224.4ms
+7: 640x1088 1 basketball, 1 hoop, 5 players, 224.4ms
+8: 640x1088 1 basketball, 2 hoops, 8 players, 224.4ms
+9: 640x1088 1 basketball, 1 hoop, 5 players, 224.4ms
+Speed: 78.7ms preprocess, 224.4ms inference, 1.3ms postprocess per image at shape (1, 3, 640, 1088)
+
+WARNING ⚠️ imgsz=[1080] must be multiple of max stride 32, updating to [1088]
+0: 640x1088 2 basketballs, 2 hoops, 8 players, 201.3ms
+1: 640x1088 2 basketballs, 2 hoops, 8 players, 201.3ms
+2: 640x1088 2 basketballs, 1 hoop, 6 players, 201.3ms
+3: 640x1088 3 basketballs, 2 hoops, 5 players, 201.3ms
+4: 640x1088 2 basketballs, 1 hoop, 5 players, 201.3ms
+5: 640x1088 1 basketball, 2 hoops, 5 players, 201.3ms
+6: 640x1088 2 basketballs, 1 hoop, 4 players, 201.3ms
+7: 640x1088 1 basketball, 1 hoop, 5 players, 201.3ms
+8: 640x1088 1 basketball, 1 hoop, 5 players, 201.3ms
+9: 640x1088 2 basketballs, 1 hoop, 5 players, 201.3ms
+Speed: 83.5ms preprocess, 201.3ms inference, 0.6ms postprocess per image at shape (1, 3, 640, 1088)
+
+WARNING ⚠️ imgsz=[1080] must be multiple of max stride 32, updating to [1088]
+0: 640x1088 2 basketballs, 3 hoops, 3 players, 219.2ms
+1: 640x1088 1 basketball, 1 hoop, 3 players, 219.2ms
+2: 640x1088 1 basketball, 7 players, 219.2ms
+3: 640x1088 1 basketball, 1 hoop, 4 players, 219.2ms
+4: 640x1088 1 basketball, 4 hoops, 3 players, 219.2ms
+5: 640x1088 1 basketball, 1 hoop, 6 players, 219.2ms
+6: 640x1088 1 basketball, 1 hoop, 6 players, 219.2ms
+7: 640x1088 1 hoop, 6 players, 219.2ms
+8: 640x1088 2 basketballs, 2 hoops, 6 players, 219.2ms
+9: 640x1088 1 basketball, 5 players, 219.2ms
+Speed: 62.0ms preprocess, 219.2ms inference, 1.9ms postprocess per image at shape (1, 3, 640, 1088)
+
+WARNING ⚠️ imgsz=[1080] must be multiple of max stride 32, updating to [1088]
+0: 640x1088 1 basketball, 1 hoop, 6 players, 356.3ms
+1: 640x1088 1 basketball, 5 players, 356.3ms
+2: 640x1088 1 basketball, 5 players, 356.3ms
+3: 640x1088 1 basketball, 4 players, 356.3ms
+4: 640x1088 2 basketballs, 5 players, 356.3ms
+5: 640x1088 1 basketball, 3 players, 356.3ms
+6: 640x1088 1 basketball, 3 players, 356.3ms
+7: 640x1088 1 basketball, 5 players, 356.3ms
+8: 640x1088 1 basketball, 6 players, 356.3ms
+9: 640x1088 1 basketball, 7 players, 356.3ms
+Speed: 62.1ms preprocess, 356.3ms inference, 3.0ms postprocess per image at shape (1, 3, 640, 1088)
+
+WARNING ⚠️ imgsz=[1080] must be multiple of max stride 32, updating to [1088]
+0: 640x1088 1 basketball, 9 players, 227.4ms
+1: 640x1088 1 basketball, 9 players, 227.4ms
+2: 640x1088 1 basketball, 1 hoop, 8 players, 227.4ms
+3: 640x1088 2 basketballs, 4 players, 227.4ms
+4: 640x1088 1 basketball, 1 hoop, 5 players, 227.4ms
+5: 640x1088 1 basketball, 2 hoops, 5 players, 227.4ms
+6: 640x1088 6 players, 227.4ms
+7: 640x1088 1 basketball, 6 players, 227.4ms
+8: 640x1088 1 basketball, 8 players, 227.4ms
+9: 640x1088 1 basketball, 9 players, 227.4ms
+Speed: 77.5ms preprocess, 227.4ms inference, 0.8ms postprocess per image at shape (1, 3, 640, 1088)
+
+WARNING ⚠️ imgsz=[1080] must be multiple of max stride 32, updating to [1088]
+0: 640x1088 8 players, 243.5ms
+1: 640x1088 8 players, 243.5ms
+2: 640x1088 10 players, 243.5ms
+3: 640x1088 8 players, 243.5ms
+4: 640x1088 10 players, 243.5ms
+5: 640x1088 1 basketball, 9 players, 243.5ms
+6: 640x1088 5 players, 1 referee, 243.5ms
+7: 640x1088 1 basketball, 8 players, 243.5ms
+8: 640x1088 9 players, 243.5ms
+9: 640x1088 7 players, 243.5ms
+Speed: 60.9ms preprocess, 243.5ms inference, 1.5ms postprocess per image at shape (1, 3, 640, 1088)
+
+WARNING ⚠️ imgsz=[1080] must be multiple of max stride 32, updating to [1088]
+0: 640x1088 7 players, 294.1ms
+1: 640x1088 1 hoop, 7 players, 294.1ms
+2: 640x1088 6 players, 294.1ms
+3: 640x1088 2 basketballs, 6 players, 294.1ms
+4: 640x1088 1 basketball, 7 players, 294.1ms
+5: 640x1088 8 players, 294.1ms
+6: 640x1088 7 players, 294.1ms
+7: 640x1088 9 players, 294.1ms
+8: 640x1088 10 players, 294.1ms
+9: 640x1088 10 players, 294.1ms
+Speed: 64.1ms preprocess, 294.1ms inference, 3.6ms postprocess per image at shape (1, 3, 640, 1088)
+
+WARNING ⚠️ imgsz=[1080] must be multiple of max stride 32, updating to [1088]
+0: 640x1088 7 players, 155.6ms
+1: 640x1088 1 basketball, 8 players, 155.6ms
+2: 640x1088 2 basketballs, 7 players, 155.6ms
+3: 640x1088 4 basketballs, 1 hoop, 6 players, 155.6ms
+4: 640x1088 1 basketball, 5 players, 155.6ms
+5: 640x1088 2 basketballs, 5 players, 155.6ms
+6: 640x1088 4 basketballs, 8 players, 155.6ms
+7: 640x1088 2 basketballs, 6 players, 155.6ms
+8: 640x1088 2 basketballs, 6 players, 1 referee, 155.6ms
+9: 640x1088 3 basketballs, 5 players, 1 referee, 155.6ms
+Speed: 58.3ms preprocess, 155.6ms inference, 0.6ms postprocess per image at shape (1, 3, 640, 1088)
+
+WARNING ⚠️ imgsz=[1080] must be multiple of max stride 32, updating to [1088]
+0: 640x1088 2 basketballs, 5 players, 1 referee, 175.5ms
+1: 640x1088 4 basketballs, 6 players, 1 referee, 175.5ms
+2: 640x1088 1 basketball, 7 players, 175.5ms
+3: 640x1088 1 basketball, 7 players, 1 referee, 175.5ms
+4: 640x1088 3 basketballs, 8 players, 1 referee, 175.5ms
+5: 640x1088 1 basketball, 6 players, 1 referee, 175.5ms
+6: 640x1088 1 basketball, 2 hoops, 6 players, 1 referee, 175.5ms
+7: 640x1088 5 basketballs, 1 hoop, 5 players, 175.5ms
+8: 640x1088 1 basketball, 6 players, 175.5ms
+9: 640x1088 3 basketballs, 1 hoop, 9 players, 1 referee, 175.5ms
+Speed: 88.6ms preprocess, 175.5ms inference, 0.6ms postprocess per image at shape (1, 3, 640, 1088)
+
+WARNING ⚠️ imgsz=[1080] must be multiple of max stride 32, updating to [1088]
+0: 640x1088 3 basketballs, 1 hoop, 8 players, 1 referee, 174.0ms
+1: 640x1088 5 basketballs, 2 hoops, 7 players, 2 referees, 174.0ms
+2: 640x1088 5 basketballs, 1 hoop, 12 players, 1 referee, 174.0ms
+3: 640x1088 1 basketball, 1 hoop, 12 players, 1 referee, 174.0ms
+4: 640x1088 1 basketball, 1 hoop, 11 players, 2 referees, 174.0ms
+5: 640x1088 1 basketball, 1 hoop, 8 players, 2 referees, 174.0ms
+6: 640x1088 1 basketball, 1 hoop, 10 players, 3 referees, 174.0ms
+7: 640x1088 1 basketball, 1 hoop, 9 players, 2 referees, 174.0ms
+8: 640x1088 3 basketballs, 1 hoop, 8 players, 2 referees, 1 shot-clock, 174.0ms
+9: 640x1088 1 basketball, 1 hoop, 10 players, 1 referee, 2 shot-clocks, 174.0ms
+Speed: 62.4ms preprocess, 174.0ms inference, 1.5ms postprocess per image at shape (1, 3, 640, 1088)
+
+WARNING ⚠️ imgsz=[1080] must be multiple of max stride 32, updating to [1088]
+0: 640x1088 1 basketball, 1 hoop, 8 players, 1 referee, 1 shot-clock, 161.3ms
+1: 640x1088 1 basketball, 1 hoop, 7 players, 1 referee, 1 shot-clock, 161.3ms
+2: 640x1088 1 basketball, 1 hoop, 10 players, 1 referee, 1 shot-clock, 161.3ms
+3: 640x1088 1 basketball, 1 hoop, 7 players, 1 referee, 1 shot-clock, 161.3ms
+4: 640x1088 1 basketball, 1 hoop, 7 players, 1 referee, 1 shot-clock, 161.3ms
+5: 640x1088 1 basketball, 1 hoop, 9 players, 1 referee, 1 shot-clock, 161.3ms
+6: 640x1088 1 basketball, 1 hoop, 8 players, 2 referees, 1 shot-clock, 161.3ms
+7: 640x1088 2 basketballs, 1 hoop, 8 players, 1 referee, 1 shot-clock, 161.3ms
+8: 640x1088 1 basketball, 1 hoop, 8 players, 2 referees, 1 shot-clock, 161.3ms
+9: 640x1088 1 basketball, 1 hoop, 8 players, 1 referee, 1 shot-clock, 161.3ms
+Speed: 66.1ms preprocess, 161.3ms inference, 0.6ms postprocess per image at shape (1, 3, 640, 1088)
+
+WARNING ⚠️ imgsz=[1080] must be multiple of max stride 32, updating to [1088]
+0: 640x1088 1 basketball, 1 hoop, 7 players, 1 referee, 1 shot-clock, 233.6ms
+1: 640x1088 1 basketball, 2 hoops, 8 players, 1 referee, 1 shot-clock, 233.6ms
+2: 640x1088 1 basketball, 1 hoop, 9 players, 1 referee, 1 shot-clock, 233.6ms
+3: 640x1088 1 basketball, 1 hoop, 8 players, 1 referee, 1 shot-clock, 233.6ms
+4: 640x1088 1 basketball, 1 hoop, 9 players, 1 referee, 1 shot-clock, 233.6ms
+5: 640x1088 1 basketball, 1 hoop, 10 players, 1 referee, 1 shot-clock, 233.6ms
+6: 640x1088 1 basketball, 1 hoop, 8 players, 1 referee, 1 shot-clock, 233.6ms
+7: 640x1088 1 basketball, 1 hoop, 11 players, 1 referee, 1 shot-clock, 233.6ms
+8: 640x1088 1 basketball, 1 hoop, 7 players, 1 referee, 1 shot-clock, 233.6ms
+9: 640x1088 1 basketball, 1 hoop, 8 players, 1 referee, 1 shot-clock, 233.6ms
+Speed: 68.6ms preprocess, 233.6ms inference, 0.7ms postprocess per image at shape (1, 3, 640, 1088)
+
+WARNING ⚠️ imgsz=[1080] must be multiple of max stride 32, updating to [1088]
+0: 640x1088 1 basketball, 1 hoop, 5 players, 1 shot-clock, 152.8ms
+1: 640x1088 1 basketball, 1 hoop, 7 players, 1 shot-clock, 152.8ms
+2: 640x1088 1 basketball, 1 hoop, 6 players, 1 shot-clock, 152.8ms
+3: 640x1088 1 basketball, 1 hoop, 6 players, 1 shot-clock, 152.8ms
+4: 640x1088 1 basketball, 1 hoop, 7 players, 1 shot-clock, 152.8ms
+5: 640x1088 1 basketball, 1 hoop, 5 players, 1 shot-clock, 152.8ms
+6: 640x1088 1 basketball, 1 hoop, 5 players, 1 shot-clock, 152.8ms
+7: 640x1088 1 basketball, 1 hoop, 5 players, 1 shot-clock, 152.8ms
+8: 640x1088 2 basketballs, 1 hoop, 7 players, 1 shot-clock, 152.8ms
+9: 640x1088 2 basketballs, 1 hoop, 8 players, 1 referee, 1 shot-clock, 152.8ms
+Speed: 77.2ms preprocess, 152.8ms inference, 0.6ms postprocess per image at shape (1, 3, 640, 1088)
+
+WARNING ⚠️ imgsz=[1080] must be multiple of max stride 32, updating to [1088]
+0: 640x1088 1 basketball, 1 hoop, 10 players, 1 referee, 1 shot-clock, 179.5ms
+1: 640x1088 1 basketball, 1 hoop, 12 players, 1 referee, 1 shot-clock, 179.5ms
+2: 640x1088 1 basketball, 1 hoop, 9 players, 1 referee, 1 shot-clock, 179.5ms
+3: 640x1088 1 basketball, 1 hoop, 14 players, 1 referee, 1 shot-clock, 179.5ms
+4: 640x1088 2 basketballs, 1 hoop, 11 players, 1 referee, 1 shot-clock, 179.5ms
+5: 640x1088 1 basketball, 1 hoop, 10 players, 1 referee, 1 shot-clock, 179.5ms
+6: 640x1088 1 basketball, 1 hoop, 10 players, 1 referee, 1 shot-clock, 179.5ms
+7: 640x1088 1 basketball, 1 hoop, 10 players, 1 referee, 1 shot-clock, 179.5ms
+8: 640x1088 1 basketball, 1 hoop, 8 players, 1 referee, 1 shot-clock, 179.5ms
+9: 640x1088 1 basketball, 1 hoop, 9 players, 1 referee, 1 shot-clock, 179.5ms
+Speed: 64.7ms preprocess, 179.5ms inference, 0.6ms postprocess per image at shape (1, 3, 640, 1088)
+
+WARNING ⚠️ imgsz=[1080] must be multiple of max stride 32, updating to [1088]
+0: 640x1088 1 basketball, 1 hoop, 8 players, 1 referee, 1 shot-clock, 166.5ms
+1: 640x1088 1 basketball, 1 hoop, 9 players, 2 referees, 1 shot-clock, 166.5ms
+2: 640x1088 1 basketball, 1 hoop, 10 players, 2 referees, 1 shot-clock, 166.5ms
+3: 640x1088 1 basketball, 1 hoop, 10 players, 2 referees, 1 shot-clock, 166.5ms
+4: 640x1088 1 basketball, 1 hoop, 9 players, 1 referee, 1 shot-clock, 166.5ms
+5: 640x1088 1 basketball, 1 hoop, 7 players, 1 referee, 1 shot-clock, 166.5ms
+6: 640x1088 1 basketball, 1 hoop, 7 players, 1 referee, 1 shot-clock, 166.5ms
+7: 640x1088 1 basketball, 1 hoop, 4 players, 1 referee, 1 shot-clock, 166.5ms
+8: 640x1088 1 basketball, 1 hoop, 5 players, 1 referee, 1 shot-clock, 166.5ms
+9: 640x1088 1 basketball, 1 hoop, 6 players, 1 referee, 1 shot-clock, 166.5ms
+Speed: 55.3ms preprocess, 166.5ms inference, 1.4ms postprocess per image at shape (1, 3, 640, 1088)
+
+WARNING ⚠️ imgsz=[1080] must be multiple of max stride 32, updating to [1088]
+0: 640x1088 2 basketballs, 1 hoop, 8 players, 1 referee, 1 shot-clock, 220.8ms
+1: 640x1088 1 basketball, 1 hoop, 6 players, 1 referee, 1 shot-clock, 220.8ms
+2: 640x1088 1 basketball, 1 hoop, 7 players, 1 shot-clock, 220.8ms
+3: 640x1088 1 basketball, 1 hoop, 7 players, 1 shot-clock, 220.8ms
+4: 640x1088 1 basketball, 1 hoop, 6 players, 1 shot-clock, 220.8ms
+5: 640x1088 1 basketball, 1 hoop, 8 players, 1 referee, 1 shot-clock, 220.8ms
+6: 640x1088 1 hoop, 6 players, 1 referee, 1 shot-clock, 220.8ms
+7: 640x1088 1 hoop, 8 players, 1 referee, 1 shot-clock, 220.8ms
+8: 640x1088 1 basketball, 1 hoop, 8 players, 1 referee, 1 shot-clock, 220.8ms
+9: 640x1088 1 hoop, 7 players, 1 referee, 1 shot-clock, 220.8ms
+Speed: 78.1ms preprocess, 220.8ms inference, 3.6ms postprocess per image at shape (1, 3, 640, 1088)
+
+WARNING ⚠️ imgsz=[1080] must be multiple of max stride 32, updating to [1088]
+0: 640x1088 2 basketballs, 1 hoop, 8 players, 1 referee, 1 shot-clock, 171.5ms
+1: 640x1088 2 basketballs, 1 hoop, 7 players, 1 referee, 1 shot-clock, 171.5ms
+2: 640x1088 2 basketballs, 1 hoop, 5 players, 1 referee, 1 shot-clock, 171.5ms
+3: 640x1088 1 basketball, 1 hoop, 5 players, 1 referee, 1 shot-clock, 171.5ms
+4: 640x1088 2 basketballs, 1 hoop, 5 players, 1 referee, 1 shot-clock, 171.5ms
+5: 640x1088 1 hoop, 6 players, 1 referee, 1 shot-clock, 171.5ms
+6: 640x1088 1 hoop, 6 players, 1 referee, 1 shot-clock, 171.5ms
+7: 640x1088 1 hoop, 4 players, 1 referee, 1 shot-clock, 171.5ms
+8: 640x1088 1 hoop, 5 players, 1 referee, 1 shot-clock, 171.5ms
+9: 640x1088 1 hoop, 6 players, 2 referees, 1 shot-clock, 171.5ms
+Speed: 81.2ms preprocess, 171.5ms inference, 0.6ms postprocess per image at shape (1, 3, 640, 1088)
+
+WARNING ⚠️ imgsz=[1080] must be multiple of max stride 32, updating to [1088]
+0: 640x1088 1 hoop, 6 players, 1 referee, 1 shot-clock, 175.8ms
+1: 640x1088 2 basketballs, 1 hoop, 6 players, 1 referee, 1 shot-clock, 175.8ms
+2: 640x1088 1 basketball, 1 hoop, 7 players, 2 referees, 1 shot-clock, 175.8ms
+3: 640x1088 2 basketballs, 1 hoop, 11 players, 2 referees, 1 shot-clock, 175.8ms
+4: 640x1088 1 basketball, 1 hoop, 9 players, 1 referee, 1 shot-clock, 175.8ms
+5: 640x1088 1 basketball, 1 hoop, 9 players, 2 referees, 1 shot-clock, 175.8ms
+6: 640x1088 1 basketball, 1 hoop, 7 players, 1 referee, 1 shot-clock, 175.8ms
+7: 640x1088 1 basketball, 1 hoop, 8 players, 1 referee, 1 shot-clock, 175.8ms
+8: 640x1088 1 basketball, 1 hoop, 8 players, 1 referee, 1 shot-clock, 175.8ms
+9: 640x1088 1 basketball, 1 hoop, 8 players, 1 referee, 1 shot-clock, 175.8ms
+Speed: 74.0ms preprocess, 175.8ms inference, 0.5ms postprocess per image at shape (1, 3, 640, 1088)
+
+WARNING ⚠️ imgsz=[1080] must be multiple of max stride 32, updating to [1088]
+0: 640x1088 1 basketball, 1 hoop, 8 players, 1 referee, 1 shot-clock, 163.7ms
+1: 640x1088 2 basketballs, 1 hoop, 7 players, 1 referee, 1 shot-clock, 163.7ms
+2: 640x1088 1 basketball, 1 hoop, 6 players, 1 referee, 1 shot-clock, 163.7ms
+3: 640x1088 1 basketball, 1 hoop, 6 players, 1 referee, 1 shot-clock, 163.7ms
+4: 640x1088 1 basketball, 1 hoop, 7 players, 1 referee, 1 shot-clock, 163.7ms
+5: 640x1088 1 basketball, 1 hoop, 8 players, 1 referee, 1 shot-clock, 163.7ms
+6: 640x1088 1 basketball, 1 hoop, 8 players, 1 referee, 1 shot-clock, 163.7ms
+7: 640x1088 1 basketball, 1 hoop, 8 players, 1 referee, 1 shot-clock, 163.7ms
+8: 640x1088 1 basketball, 1 hoop, 7 players, 1 referee, 1 shot-clock, 163.7ms
+9: 640x1088 1 basketball, 1 hoop, 9 players, 1 referee, 1 shot-clock, 163.7ms
+Speed: 58.0ms preprocess, 163.7ms inference, 0.7ms postprocess per image at shape (1, 3, 640, 1088)
+
+WARNING ⚠️ imgsz=[1080] must be multiple of max stride 32, updating to [1088]
+0: 640x1088 1 basketball, 1 hoop, 8 players, 1 referee, 1 shot-clock, 250.7ms
+1: 640x1088 1 basketball, 1 hoop, 7 players, 1 referee, 1 shot-clock, 250.7ms
+Speed: 43.9ms preprocess, 250.7ms inference, 1.2ms postprocess per image at shape (1, 3, 640, 1088)
+
+0: 384x640 1 basketball, 1519.6ms
+1: 384x640 1 basketball, 1519.6ms
+2: 384x640 (no detections), 1519.6ms
+3: 384x640 (no detections), 1519.6ms
+4: 384x640 (no detections), 1519.6ms
+5: 384x640 (no detections), 1519.6ms
+6: 384x640 (no detections), 1519.6ms
+7: 384x640 (no detections), 1519.6ms
+8: 384x640 (no detections), 1519.6ms
+9: 384x640 1 basketball, 1519.6ms
+10: 384x640 1 basketball, 1519.6ms
+11: 384x640 1 basketball, 1519.6ms
+12: 384x640 1 basketball, 1519.6ms
+13: 384x640 1 basketball, 1519.6ms
+14: 384x640 (no detections), 1519.6ms
+15: 384x640 1 basketball, 1519.6ms
+16: 384x640 1 basketball, 1519.6ms
+17: 384x640 1 basketball, 1519.6ms
+18: 384x640 1 basketball, 1519.6ms
+19: 384x640 (no detections), 1519.6ms
+Speed: 9.0ms preprocess, 1519.6ms inference, 1.8ms postprocess per image at shape (1, 3, 384, 640)
+
+0: 384x640 (no detections), 1299.9ms
+1: 384x640 2 basketballs, 1299.9ms
+2: 384x640 (no detections), 1299.9ms
+3: 384x640 (no detections), 1299.9ms
+4: 384x640 (no detections), 1299.9ms
+5: 384x640 (no detections), 1299.9ms
+6: 384x640 1 basketball, 1299.9ms
+7: 384x640 (no detections), 1299.9ms
+8: 384x640 (no detections), 1299.9ms
+9: 384x640 (no detections), 1299.9ms
+10: 384x640 (no detections), 1299.9ms
+Speed: 9.3ms preprocess, 1299.9ms inference, 0.3ms postprocess per image at shape (1, 3, 384, 640)
+Loading Team Assignment Model (Fashion-CLIP)...
+
Loading weights:   0%|          | 0/398 [00:00<?, ?it/s]
Loading weights:   0%|          | 1/398 [00:00<00:05, 74.31it/s, Materializing param=logit_scale]
Loading weights:   0%|          | 1/398 [00:00<00:05, 73.08it/s, Materializing param=logit_scale]
Loading weights:   1%|          | 2/398 [00:00<00:02, 139.99it/s, Materializing param=text_model.embeddings.position_embedding.weight]
Loading weights:   1%|          | 2/398 [00:00<00:02, 139.31it/s, Materializing param=text_model.embeddings.position_embedding.weight]
Loading weights:   1%|          | 3/398 [00:00<00:02, 184.44it/s, Materializing param=text_model.embeddings.token_embedding.weight]   
Loading weights:   1%|          | 3/398 [00:00<00:02, 183.30it/s, Materializing param=text_model.embeddings.token_embedding.weight]
Loading weights:   1%|          | 4/398 [00:00<00:01, 238.55it/s, Materializing param=text_model.encoder.layers.0.layer_norm1.bias]
Loading weights:   1%|          | 4/398 [00:00<00:01, 236.50it/s, Materializing param=text_model.encoder.layers.0.layer_norm1.bias]
Loading weights:   1%|▏         | 5/398 [00:00<00:01, 251.41it/s, Materializing param=text_model.encoder.layers.0.layer_norm1.weight]
Loading weights:   1%|▏         | 5/398 [00:00<00:01, 249.82it/s, Materializing param=text_model.encoder.layers.0.layer_norm1.weight]
Loading weights:   2%|▏         | 6/398 [00:00<00:01, 297.23it/s, Materializing param=text_model.encoder.layers.0.layer_norm2.bias]  
Loading weights:   2%|▏         | 6/398 [00:00<00:01, 295.70it/s, Materializing param=text_model.encoder.layers.0.layer_norm2.bias]
Loading weights:   2%|▏         | 7/398 [00:00<00:01, 336.87it/s, Materializing param=text_model.encoder.layers.0.layer_norm2.weight]
Loading weights:   2%|▏         | 7/398 [00:00<00:01, 335.00it/s, Materializing param=text_model.encoder.layers.0.layer_norm2.weight]
Loading weights:   2%|▏         | 8/398 [00:00<00:01, 353.54it/s, Materializing param=text_model.encoder.layers.0.mlp.fc1.bias]      
Loading weights:   2%|▏         | 8/398 [00:00<00:01, 311.73it/s, Materializing param=text_model.encoder.layers.0.mlp.fc1.bias]
Loading weights:   2%|▏         | 9/398 [00:00<00:01, 346.30it/s, Materializing param=text_model.encoder.layers.0.mlp.fc1.weight]
Loading weights:   2%|▏         | 9/398 [00:00<00:01, 327.53it/s, Materializing param=text_model.encoder.layers.0.mlp.fc1.weight]
Loading weights:   3%|▎         | 10/398 [00:00<00:01, 326.45it/s, Materializing param=text_model.encoder.layers.0.mlp.fc2.bias] 
Loading weights:   3%|▎         | 10/398 [00:00<00:01, 324.48it/s, Materializing param=text_model.encoder.layers.0.mlp.fc2.bias]
Loading weights:   3%|▎         | 11/398 [00:00<00:01, 353.84it/s, Materializing param=text_model.encoder.layers.0.mlp.fc2.weight]
Loading weights:   3%|▎         | 11/398 [00:00<00:01, 338.71it/s, Materializing param=text_model.encoder.layers.0.mlp.fc2.weight]
Loading weights:   3%|▎         | 12/398 [00:00<00:01, 350.36it/s, Materializing param=text_model.encoder.layers.0.self_attn.k_proj.bias]
Loading weights:   3%|▎         | 12/398 [00:00<00:01, 336.43it/s, Materializing param=text_model.encoder.layers.0.self_attn.k_proj.bias]
Loading weights:   3%|▎         | 13/398 [00:00<00:01, 362.78it/s, Materializing param=text_model.encoder.layers.0.self_attn.k_proj.weight]
Loading weights:   3%|▎         | 13/398 [00:00<00:01, 362.08it/s, Materializing param=text_model.encoder.layers.0.self_attn.k_proj.weight]
Loading weights:   4%|▎         | 14/398 [00:00<00:01, 374.34it/s, Materializing param=text_model.encoder.layers.0.self_attn.out_proj.bias]
Loading weights:   4%|▎         | 14/398 [00:00<00:01, 373.53it/s, Materializing param=text_model.encoder.layers.0.self_attn.out_proj.bias]
Loading weights:   4%|▍         | 15/398 [00:00<00:00, 398.42it/s, Materializing param=text_model.encoder.layers.0.self_attn.out_proj.weight]
Loading weights:   4%|▍         | 15/398 [00:00<00:00, 384.70it/s, Materializing param=text_model.encoder.layers.0.self_attn.out_proj.weight]
Loading weights:   4%|▍         | 16/398 [00:00<00:00, 391.35it/s, Materializing param=text_model.encoder.layers.0.self_attn.q_proj.bias]    
Loading weights:   4%|▍         | 16/398 [00:00<00:00, 390.21it/s, Materializing param=text_model.encoder.layers.0.self_attn.q_proj.bias]
Loading weights:   4%|▍         | 17/398 [00:00<00:00, 397.89it/s, Materializing param=text_model.encoder.layers.0.self_attn.q_proj.weight]
Loading weights:   4%|▍         | 17/398 [00:00<00:00, 385.57it/s, Materializing param=text_model.encoder.layers.0.self_attn.q_proj.weight]
Loading weights:   5%|▍         | 18/398 [00:00<00:00, 404.94it/s, Materializing param=text_model.encoder.layers.0.self_attn.v_proj.bias]  
Loading weights:   5%|▍         | 18/398 [00:00<00:00, 393.48it/s, Materializing param=text_model.encoder.layers.0.self_attn.v_proj.bias]
Loading weights:   5%|▍         | 19/398 [00:00<00:00, 413.06it/s, Materializing param=text_model.encoder.layers.0.self_attn.v_proj.weight]
Loading weights:   5%|▍         | 19/398 [00:00<00:00, 412.08it/s, Materializing param=text_model.encoder.layers.0.self_attn.v_proj.weight]
Loading weights:   5%|▌         | 20/398 [00:00<00:00, 418.21it/s, Materializing param=text_model.encoder.layers.1.layer_norm1.bias]       
Loading weights:   5%|▌         | 20/398 [00:00<00:00, 387.83it/s, Materializing param=text_model.encoder.layers.1.layer_norm1.bias]
Loading weights:   5%|▌         | 21/398 [00:00<00:00, 383.62it/s, Materializing param=text_model.encoder.layers.1.layer_norm1.weight]
Loading weights:   5%|▌         | 21/398 [00:00<00:00, 382.59it/s, Materializing param=text_model.encoder.layers.1.layer_norm1.weight]
Loading weights:   6%|▌         | 22/398 [00:00<00:00, 387.81it/s, Materializing param=text_model.encoder.layers.1.layer_norm2.bias]  
Loading weights:   6%|▌         | 22/398 [00:00<00:00, 386.83it/s, Materializing param=text_model.encoder.layers.1.layer_norm2.bias]
Loading weights:   6%|▌         | 23/398 [00:00<00:00, 376.08it/s, Materializing param=text_model.encoder.layers.1.layer_norm2.weight]
Loading weights:   6%|▌         | 23/398 [00:00<00:01, 374.94it/s, Materializing param=text_model.encoder.layers.1.layer_norm2.weight]
Loading weights:   6%|▌         | 24/398 [00:00<00:00, 390.17it/s, Materializing param=text_model.encoder.layers.1.mlp.fc1.bias]      
Loading weights:   6%|▌         | 24/398 [00:00<00:00, 389.49it/s, Materializing param=text_model.encoder.layers.1.mlp.fc1.bias]
Loading weights:   6%|▋         | 25/398 [00:00<00:00, 385.18it/s, Materializing param=text_model.encoder.layers.1.mlp.fc1.weight]
Loading weights:   6%|▋         | 25/398 [00:00<00:01, 353.26it/s, Materializing param=text_model.encoder.layers.1.mlp.fc1.weight]
Loading weights:   7%|▋         | 26/398 [00:00<00:01, 363.59it/s, Materializing param=text_model.encoder.layers.1.mlp.fc2.bias]  
Loading weights:   7%|▋         | 26/398 [00:00<00:01, 356.27it/s, Materializing param=text_model.encoder.layers.1.mlp.fc2.bias]
Loading weights:   7%|▋         | 27/398 [00:00<00:01, 354.07it/s, Materializing param=text_model.encoder.layers.1.mlp.fc2.weight]
Loading weights:   7%|▋         | 27/398 [00:00<00:01, 353.55it/s, Materializing param=text_model.encoder.layers.1.mlp.fc2.weight]
Loading weights:   7%|▋         | 28/398 [00:00<00:01, 365.89it/s, Materializing param=text_model.encoder.layers.1.self_attn.k_proj.bias]
Loading weights:   7%|▋         | 28/398 [00:00<00:01, 365.54it/s, Materializing param=text_model.encoder.layers.1.self_attn.k_proj.bias]
Loading weights:   7%|▋         | 29/398 [00:00<00:01, 356.49it/s, Materializing param=text_model.encoder.layers.1.self_attn.k_proj.weight]
Loading weights:   7%|▋         | 29/398 [00:00<00:01, 356.07it/s, Materializing param=text_model.encoder.layers.1.self_attn.k_proj.weight]
Loading weights:   8%|▊         | 30/398 [00:00<00:01, 366.66it/s, Materializing param=text_model.encoder.layers.1.self_attn.out_proj.bias]
Loading weights:   8%|▊         | 30/398 [00:00<00:01, 365.98it/s, Materializing param=text_model.encoder.layers.1.self_attn.out_proj.bias]
Loading weights:   8%|▊         | 31/398 [00:00<00:00, 370.75it/s, Materializing param=text_model.encoder.layers.1.self_attn.out_proj.weight]
Loading weights:   8%|▊         | 31/398 [00:00<00:00, 370.16it/s, Materializing param=text_model.encoder.layers.1.self_attn.out_proj.weight]
Loading weights:   8%|▊         | 32/398 [00:00<00:00, 380.91it/s, Materializing param=text_model.encoder.layers.1.self_attn.q_proj.bias]    
Loading weights:   8%|▊         | 32/398 [00:00<00:00, 369.90it/s, Materializing param=text_model.encoder.layers.1.self_attn.q_proj.bias]
Loading weights:   8%|▊         | 33/398 [00:00<00:00, 378.49it/s, Materializing param=text_model.encoder.layers.1.self_attn.q_proj.weight]
Loading weights:   8%|▊         | 33/398 [00:00<00:00, 377.53it/s, Materializing param=text_model.encoder.layers.1.self_attn.q_proj.weight]
Loading weights:   9%|▊         | 34/398 [00:00<00:00, 376.57it/s, Materializing param=text_model.encoder.layers.1.self_attn.v_proj.bias]  
Loading weights:   9%|▊         | 34/398 [00:00<00:01, 355.31it/s, Materializing param=text_model.encoder.layers.1.self_attn.v_proj.bias]
Loading weights:   9%|▉         | 35/398 [00:00<00:00, 364.80it/s, Materializing param=text_model.encoder.layers.1.self_attn.v_proj.weight]
Loading weights:   9%|▉         | 35/398 [00:00<00:00, 364.50it/s, Materializing param=text_model.encoder.layers.1.self_attn.v_proj.weight]
Loading weights:   9%|▉         | 36/398 [00:00<00:00, 372.54it/s, Materializing param=text_model.encoder.layers.2.layer_norm1.bias]       
Loading weights:   9%|▉         | 36/398 [00:00<00:01, 360.79it/s, Materializing param=text_model.encoder.layers.2.layer_norm1.bias]
Loading weights:   9%|▉         | 37/398 [00:00<00:00, 370.00it/s, Materializing param=text_model.encoder.layers.2.layer_norm1.bias]
Loading weights:   9%|▉         | 37/398 [00:00<00:00, 370.00it/s, Materializing param=text_model.encoder.layers.2.layer_norm1.weight]
Loading weights:   9%|▉         | 37/398 [00:00<00:00, 370.00it/s, Materializing param=text_model.encoder.layers.2.layer_norm1.weight]
Loading weights:  10%|▉         | 38/398 [00:00<00:00, 370.00it/s, Materializing param=text_model.encoder.layers.2.layer_norm2.bias]  
Loading weights:  10%|▉         | 38/398 [00:00<00:00, 370.00it/s, Materializing param=text_model.encoder.layers.2.layer_norm2.bias]
Loading weights:  10%|▉         | 39/398 [00:00<00:00, 370.00it/s, Materializing param=text_model.encoder.layers.2.layer_norm2.weight]
Loading weights:  10%|▉         | 39/398 [00:00<00:00, 370.00it/s, Materializing param=text_model.encoder.layers.2.layer_norm2.weight]
Loading weights:  10%|█         | 40/398 [00:00<00:00, 370.00it/s, Materializing param=text_model.encoder.layers.2.mlp.fc1.bias]      
Loading weights:  10%|█         | 40/398 [00:00<00:00, 370.00it/s, Materializing param=text_model.encoder.layers.2.mlp.fc1.bias]
Loading weights:  10%|█         | 41/398 [00:00<00:00, 370.00it/s, Materializing param=text_model.encoder.layers.2.mlp.fc1.weight]
Loading weights:  10%|█         | 41/398 [00:00<00:00, 370.00it/s, Materializing param=text_model.encoder.layers.2.mlp.fc1.weight]
Loading weights:  11%|█         | 42/398 [00:00<00:00, 370.00it/s, Materializing param=text_model.encoder.layers.2.mlp.fc2.bias]  
Loading weights:  11%|█         | 42/398 [00:00<00:00, 370.00it/s, Materializing param=text_model.encoder.layers.2.mlp.fc2.bias]
Loading weights:  11%|█         | 43/398 [00:00<00:00, 370.00it/s, Materializing param=text_model.encoder.layers.2.mlp.fc2.weight]
Loading weights:  11%|█         | 43/398 [00:00<00:00, 370.00it/s, Materializing param=text_model.encoder.layers.2.mlp.fc2.weight]
Loading weights:  11%|█         | 44/398 [00:00<00:00, 370.00it/s, Materializing param=text_model.encoder.layers.2.self_attn.k_proj.bias]
Loading weights:  11%|█         | 44/398 [00:00<00:00, 370.00it/s, Materializing param=text_model.encoder.layers.2.self_attn.k_proj.bias]
Loading weights:  11%|█▏        | 45/398 [00:00<00:00, 370.00it/s, Materializing param=text_model.encoder.layers.2.self_attn.k_proj.weight]
Loading weights:  11%|█▏        | 45/398 [00:00<00:00, 370.00it/s, Materializing param=text_model.encoder.layers.2.self_attn.k_proj.weight]
Loading weights:  12%|█▏        | 46/398 [00:00<00:00, 370.00it/s, Materializing param=text_model.encoder.layers.2.self_attn.out_proj.bias]
Loading weights:  12%|█▏        | 46/398 [00:00<00:00, 370.00it/s, Materializing param=text_model.encoder.layers.2.self_attn.out_proj.bias]
Loading weights:  12%|█▏        | 47/398 [00:00<00:00, 370.00it/s, Materializing param=text_model.encoder.layers.2.self_attn.out_proj.weight]
Loading weights:  12%|█▏        | 47/398 [00:00<00:00, 370.00it/s, Materializing param=text_model.encoder.layers.2.self_attn.out_proj.weight]
Loading weights:  12%|█▏        | 48/398 [00:00<00:00, 370.00it/s, Materializing param=text_model.encoder.layers.2.self_attn.q_proj.bias]    
Loading weights:  12%|█▏        | 48/398 [00:00<00:00, 370.00it/s, Materializing param=text_model.encoder.layers.2.self_attn.q_proj.bias]
Loading weights:  12%|█▏        | 49/398 [00:00<00:00, 370.00it/s, Materializing param=text_model.encoder.layers.2.self_attn.q_proj.weight]
Loading weights:  12%|█▏        | 49/398 [00:00<00:00, 370.00it/s, Materializing param=text_model.encoder.layers.2.self_attn.q_proj.weight]
Loading weights:  13%|█▎        | 50/398 [00:00<00:00, 370.00it/s, Materializing param=text_model.encoder.layers.2.self_attn.v_proj.bias]  
Loading weights:  13%|█▎        | 50/398 [00:00<00:00, 370.00it/s, Materializing param=text_model.encoder.layers.2.self_attn.v_proj.bias]
Loading weights:  13%|█▎        | 51/398 [00:00<00:00, 370.00it/s, Materializing param=text_model.encoder.layers.2.self_attn.v_proj.weight]
Loading weights:  13%|█▎        | 51/398 [00:00<00:00, 370.00it/s, Materializing param=text_model.encoder.layers.2.self_attn.v_proj.weight]
Loading weights:  13%|█▎        | 52/398 [00:00<00:00, 370.00it/s, Materializing param=text_model.encoder.layers.3.layer_norm1.bias]       
Loading weights:  13%|█▎        | 52/398 [00:00<00:00, 370.00it/s, Materializing param=text_model.encoder.layers.3.layer_norm1.bias]
Loading weights:  13%|█▎        | 53/398 [00:00<00:00, 370.00it/s, Materializing param=text_model.encoder.layers.3.layer_norm1.weight]
Loading weights:  13%|█▎        | 53/398 [00:00<00:00, 370.00it/s, Materializing param=text_model.encoder.layers.3.layer_norm1.weight]
Loading weights:  14%|█▎        | 54/398 [00:00<00:00, 370.00it/s, Materializing param=text_model.encoder.layers.3.layer_norm2.bias]  
Loading weights:  14%|█▎        | 54/398 [00:00<00:00, 370.00it/s, Materializing param=text_model.encoder.layers.3.layer_norm2.bias]
Loading weights:  14%|█▍        | 55/398 [00:00<00:00, 370.00it/s, Materializing param=text_model.encoder.layers.3.layer_norm2.weight]
Loading weights:  14%|█▍        | 55/398 [00:00<00:00, 370.00it/s, Materializing param=text_model.encoder.layers.3.layer_norm2.weight]
Loading weights:  14%|█▍        | 56/398 [00:00<00:00, 370.00it/s, Materializing param=text_model.encoder.layers.3.mlp.fc1.bias]      
Loading weights:  14%|█▍        | 56/398 [00:00<00:00, 370.00it/s, Materializing param=text_model.encoder.layers.3.mlp.fc1.bias]
Loading weights:  14%|█▍        | 57/398 [00:00<00:00, 370.00it/s, Materializing param=text_model.encoder.layers.3.mlp.fc1.weight]
Loading weights:  14%|█▍        | 57/398 [00:00<00:00, 370.00it/s, Materializing param=text_model.encoder.layers.3.mlp.fc1.weight]
Loading weights:  15%|█▍        | 58/398 [00:00<00:00, 370.00it/s, Materializing param=text_model.encoder.layers.3.mlp.fc2.bias]  
Loading weights:  15%|█▍        | 58/398 [00:00<00:00, 370.00it/s, Materializing param=text_model.encoder.layers.3.mlp.fc2.bias]
Loading weights:  15%|█▍        | 59/398 [00:00<00:00, 370.00it/s, Materializing param=text_model.encoder.layers.3.mlp.fc2.weight]
Loading weights:  15%|█▍        | 59/398 [00:00<00:00, 370.00it/s, Materializing param=text_model.encoder.layers.3.mlp.fc2.weight]
Loading weights:  15%|█▌        | 60/398 [00:00<00:00, 370.00it/s, Materializing param=text_model.encoder.layers.3.self_attn.k_proj.bias]
Loading weights:  15%|█▌        | 60/398 [00:00<00:00, 370.00it/s, Materializing param=text_model.encoder.layers.3.self_attn.k_proj.bias]
Loading weights:  15%|█▌        | 61/398 [00:00<00:00, 370.00it/s, Materializing param=text_model.encoder.layers.3.self_attn.k_proj.weight]
Loading weights:  15%|█▌        | 61/398 [00:00<00:00, 370.00it/s, Materializing param=text_model.encoder.layers.3.self_attn.k_proj.weight]
Loading weights:  16%|█▌        | 62/398 [00:00<00:00, 370.00it/s, Materializing param=text_model.encoder.layers.3.self_attn.out_proj.bias]
Loading weights:  16%|█▌        | 62/398 [00:00<00:00, 370.00it/s, Materializing param=text_model.encoder.layers.3.self_attn.out_proj.bias]
Loading weights:  16%|█▌        | 63/398 [00:00<00:00, 370.00it/s, Materializing param=text_model.encoder.layers.3.self_attn.out_proj.weight]
Loading weights:  16%|█▌        | 63/398 [00:00<00:00, 370.00it/s, Materializing param=text_model.encoder.layers.3.self_attn.out_proj.weight]
Loading weights:  16%|█▌        | 64/398 [00:00<00:00, 370.00it/s, Materializing param=text_model.encoder.layers.3.self_attn.q_proj.bias]    
Loading weights:  16%|█▌        | 64/398 [00:00<00:00, 370.00it/s, Materializing param=text_model.encoder.layers.3.self_attn.q_proj.bias]
Loading weights:  16%|█▋        | 65/398 [00:00<00:00, 370.00it/s, Materializing param=text_model.encoder.layers.3.self_attn.q_proj.weight]
Loading weights:  16%|█▋        | 65/398 [00:00<00:00, 370.00it/s, Materializing param=text_model.encoder.layers.3.self_attn.q_proj.weight]
Loading weights:  17%|█▋        | 66/398 [00:00<00:00, 370.00it/s, Materializing param=text_model.encoder.layers.3.self_attn.v_proj.bias]  
Loading weights:  17%|█▋        | 66/398 [00:00<00:00, 370.00it/s, Materializing param=text_model.encoder.layers.3.self_attn.v_proj.bias]
Loading weights:  17%|█▋        | 67/398 [00:00<00:00, 370.00it/s, Materializing param=text_model.encoder.layers.3.self_attn.v_proj.weight]
Loading weights:  17%|█▋        | 67/398 [00:00<00:00, 370.00it/s, Materializing param=text_model.encoder.layers.3.self_attn.v_proj.weight]
Loading weights:  17%|█▋        | 68/398 [00:00<00:00, 370.00it/s, Materializing param=text_model.encoder.layers.4.layer_norm1.bias]       
Loading weights:  17%|█▋        | 68/398 [00:00<00:00, 370.00it/s, Materializing param=text_model.encoder.layers.4.layer_norm1.bias]
Loading weights:  17%|█▋        | 69/398 [00:00<00:00, 370.00it/s, Materializing param=text_model.encoder.layers.4.layer_norm1.weight]
Loading weights:  17%|█▋        | 69/398 [00:00<00:00, 370.00it/s, Materializing param=text_model.encoder.layers.4.layer_norm1.weight]
Loading weights:  18%|█▊        | 70/398 [00:00<00:00, 370.00it/s, Materializing param=text_model.encoder.layers.4.layer_norm2.bias]  
Loading weights:  18%|█▊        | 70/398 [00:00<00:00, 370.00it/s, Materializing param=text_model.encoder.layers.4.layer_norm2.bias]
Loading weights:  18%|█▊        | 71/398 [00:00<00:00, 370.00it/s, Materializing param=text_model.encoder.layers.4.layer_norm2.weight]
Loading weights:  18%|█▊        | 71/398 [00:00<00:00, 370.00it/s, Materializing param=text_model.encoder.layers.4.layer_norm2.weight]
Loading weights:  18%|█▊        | 72/398 [00:00<00:00, 370.00it/s, Materializing param=text_model.encoder.layers.4.mlp.fc1.bias]      
Loading weights:  18%|█▊        | 72/398 [00:00<00:00, 370.00it/s, Materializing param=text_model.encoder.layers.4.mlp.fc1.bias]
Loading weights:  18%|█▊        | 73/398 [00:00<00:00, 370.00it/s, Materializing param=text_model.encoder.layers.4.mlp.fc1.weight]
Loading weights:  18%|█▊        | 73/398 [00:00<00:00, 370.00it/s, Materializing param=text_model.encoder.layers.4.mlp.fc1.weight]
Loading weights:  19%|█▊        | 74/398 [00:00<00:00, 370.00it/s, Materializing param=text_model.encoder.layers.4.mlp.fc2.bias]  
Loading weights:  19%|█▊        | 74/398 [00:00<00:00, 370.00it/s, Materializing param=text_model.encoder.layers.4.mlp.fc2.bias]
Loading weights:  19%|█▉        | 75/398 [00:00<00:00, 370.00it/s, Materializing param=text_model.encoder.layers.4.mlp.fc2.weight]
Loading weights:  19%|█▉        | 75/398 [00:00<00:00, 370.00it/s, Materializing param=text_model.encoder.layers.4.mlp.fc2.weight]
Loading weights:  19%|█▉        | 76/398 [00:00<00:00, 370.00it/s, Materializing param=text_model.encoder.layers.4.self_attn.k_proj.bias]
Loading weights:  19%|█▉        | 76/398 [00:00<00:00, 370.00it/s, Materializing param=text_model.encoder.layers.4.self_attn.k_proj.bias]
Loading weights:  19%|█▉        | 77/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.4.self_attn.k_proj.bias]
Loading weights:  19%|█▉        | 77/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.4.self_attn.k_proj.weight]
Loading weights:  19%|█▉        | 77/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.4.self_attn.k_proj.weight]
Loading weights:  20%|█▉        | 78/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.4.self_attn.out_proj.bias]
Loading weights:  20%|█▉        | 78/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.4.self_attn.out_proj.bias]
Loading weights:  20%|█▉        | 79/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.4.self_attn.out_proj.weight]
Loading weights:  20%|█▉        | 79/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.4.self_attn.out_proj.weight]
Loading weights:  20%|██        | 80/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.4.self_attn.q_proj.bias]    
Loading weights:  20%|██        | 80/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.4.self_attn.q_proj.bias]
Loading weights:  20%|██        | 81/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.4.self_attn.q_proj.weight]
Loading weights:  20%|██        | 81/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.4.self_attn.q_proj.weight]
Loading weights:  21%|██        | 82/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.4.self_attn.v_proj.bias]  
Loading weights:  21%|██        | 82/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.4.self_attn.v_proj.bias]
Loading weights:  21%|██        | 83/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.4.self_attn.v_proj.weight]
Loading weights:  21%|██        | 83/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.4.self_attn.v_proj.weight]
Loading weights:  21%|██        | 84/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.5.layer_norm1.bias]       
Loading weights:  21%|██        | 84/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.5.layer_norm1.bias]
Loading weights:  21%|██▏       | 85/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.5.layer_norm1.weight]
Loading weights:  21%|██▏       | 85/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.5.layer_norm1.weight]
Loading weights:  22%|██▏       | 86/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.5.layer_norm2.bias]  
Loading weights:  22%|██▏       | 86/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.5.layer_norm2.bias]
Loading weights:  22%|██▏       | 87/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.5.layer_norm2.weight]
Loading weights:  22%|██▏       | 87/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.5.layer_norm2.weight]
Loading weights:  22%|██▏       | 88/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.5.mlp.fc1.bias]      
Loading weights:  22%|██▏       | 88/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.5.mlp.fc1.bias]
Loading weights:  22%|██▏       | 89/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.5.mlp.fc1.weight]
Loading weights:  22%|██▏       | 89/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.5.mlp.fc1.weight]
Loading weights:  23%|██▎       | 90/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.5.mlp.fc2.bias]  
Loading weights:  23%|██▎       | 90/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.5.mlp.fc2.bias]
Loading weights:  23%|██▎       | 91/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.5.mlp.fc2.weight]
Loading weights:  23%|██▎       | 91/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.5.mlp.fc2.weight]
Loading weights:  23%|██▎       | 92/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.5.self_attn.k_proj.bias]
Loading weights:  23%|██▎       | 92/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.5.self_attn.k_proj.bias]
Loading weights:  23%|██▎       | 93/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.5.self_attn.k_proj.weight]
Loading weights:  23%|██▎       | 93/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.5.self_attn.k_proj.weight]
Loading weights:  24%|██▎       | 94/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.5.self_attn.out_proj.bias]
Loading weights:  24%|██▎       | 94/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.5.self_attn.out_proj.bias]
Loading weights:  24%|██▍       | 95/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.5.self_attn.out_proj.weight]
Loading weights:  24%|██▍       | 95/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.5.self_attn.out_proj.weight]
Loading weights:  24%|██▍       | 96/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.5.self_attn.q_proj.bias]    
Loading weights:  24%|██▍       | 96/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.5.self_attn.q_proj.bias]
Loading weights:  24%|██▍       | 97/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.5.self_attn.q_proj.weight]
Loading weights:  24%|██▍       | 97/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.5.self_attn.q_proj.weight]
Loading weights:  25%|██▍       | 98/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.5.self_attn.v_proj.bias]  
Loading weights:  25%|██▍       | 98/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.5.self_attn.v_proj.bias]
Loading weights:  25%|██▍       | 99/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.5.self_attn.v_proj.weight]
Loading weights:  25%|██▍       | 99/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.5.self_attn.v_proj.weight]
Loading weights:  25%|██▌       | 100/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.6.layer_norm1.bias]      
Loading weights:  25%|██▌       | 100/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.6.layer_norm1.bias]
Loading weights:  25%|██▌       | 101/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.6.layer_norm1.weight]
Loading weights:  25%|██▌       | 101/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.6.layer_norm1.weight]
Loading weights:  26%|██▌       | 102/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.6.layer_norm2.bias]  
Loading weights:  26%|██▌       | 102/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.6.layer_norm2.bias]
Loading weights:  26%|██▌       | 103/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.6.layer_norm2.weight]
Loading weights:  26%|██▌       | 103/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.6.layer_norm2.weight]
Loading weights:  26%|██▌       | 104/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.6.mlp.fc1.bias]      
Loading weights:  26%|██▌       | 104/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.6.mlp.fc1.bias]
Loading weights:  26%|██▋       | 105/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.6.mlp.fc1.weight]
Loading weights:  26%|██▋       | 105/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.6.mlp.fc1.weight]
Loading weights:  27%|██▋       | 106/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.6.mlp.fc2.bias]  
Loading weights:  27%|██▋       | 106/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.6.mlp.fc2.bias]
Loading weights:  27%|██▋       | 107/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.6.mlp.fc2.weight]
Loading weights:  27%|██▋       | 107/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.6.mlp.fc2.weight]
Loading weights:  27%|██▋       | 108/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.6.self_attn.k_proj.bias]
Loading weights:  27%|██▋       | 108/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.6.self_attn.k_proj.bias]
Loading weights:  27%|██▋       | 109/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.6.self_attn.k_proj.weight]
Loading weights:  27%|██▋       | 109/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.6.self_attn.k_proj.weight]
Loading weights:  28%|██▊       | 110/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.6.self_attn.out_proj.bias]
Loading weights:  28%|██▊       | 110/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.6.self_attn.out_proj.bias]
Loading weights:  28%|██▊       | 111/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.6.self_attn.out_proj.weight]
Loading weights:  28%|██▊       | 111/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.6.self_attn.out_proj.weight]
Loading weights:  28%|██▊       | 112/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.6.self_attn.q_proj.bias]    
Loading weights:  28%|██▊       | 112/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.6.self_attn.q_proj.bias]
Loading weights:  28%|██▊       | 113/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.6.self_attn.q_proj.weight]
Loading weights:  28%|██▊       | 113/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.6.self_attn.q_proj.weight]
Loading weights:  29%|██▊       | 114/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.6.self_attn.v_proj.bias]  
Loading weights:  29%|██▊       | 114/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.6.self_attn.v_proj.bias]
Loading weights:  29%|██▉       | 115/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.6.self_attn.v_proj.weight]
Loading weights:  29%|██▉       | 115/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.6.self_attn.v_proj.weight]
Loading weights:  29%|██▉       | 116/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.7.layer_norm1.bias]       
Loading weights:  29%|██▉       | 116/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.7.layer_norm1.bias]
Loading weights:  29%|██▉       | 117/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.7.layer_norm1.weight]
Loading weights:  29%|██▉       | 117/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.7.layer_norm1.weight]
Loading weights:  30%|██▉       | 118/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.7.layer_norm2.bias]  
Loading weights:  30%|██▉       | 118/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.7.layer_norm2.bias]
Loading weights:  30%|██▉       | 119/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.7.layer_norm2.weight]
Loading weights:  30%|██▉       | 119/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.7.layer_norm2.weight]
Loading weights:  30%|███       | 120/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.7.mlp.fc1.bias]      
Loading weights:  30%|███       | 120/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.7.mlp.fc1.bias]
Loading weights:  30%|███       | 121/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.7.mlp.fc1.weight]
Loading weights:  30%|███       | 121/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.7.mlp.fc1.weight]
Loading weights:  31%|███       | 122/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.7.mlp.fc2.bias]  
Loading weights:  31%|███       | 122/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.7.mlp.fc2.bias]
Loading weights:  31%|███       | 123/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.7.mlp.fc2.weight]
Loading weights:  31%|███       | 123/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.7.mlp.fc2.weight]
Loading weights:  31%|███       | 124/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.7.self_attn.k_proj.bias]
Loading weights:  31%|███       | 124/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.7.self_attn.k_proj.bias]
Loading weights:  31%|███▏      | 125/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.7.self_attn.k_proj.weight]
Loading weights:  31%|███▏      | 125/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.7.self_attn.k_proj.weight]
Loading weights:  32%|███▏      | 126/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.7.self_attn.out_proj.bias]
Loading weights:  32%|███▏      | 126/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.7.self_attn.out_proj.bias]
Loading weights:  32%|███▏      | 127/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.7.self_attn.out_proj.weight]
Loading weights:  32%|███▏      | 127/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.7.self_attn.out_proj.weight]
Loading weights:  32%|███▏      | 128/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.7.self_attn.q_proj.bias]    
Loading weights:  32%|███▏      | 128/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.7.self_attn.q_proj.bias]
Loading weights:  32%|███▏      | 129/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.7.self_attn.q_proj.weight]
Loading weights:  32%|███▏      | 129/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.7.self_attn.q_proj.weight]
Loading weights:  33%|███▎      | 130/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.7.self_attn.v_proj.bias]  
Loading weights:  33%|███▎      | 130/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.7.self_attn.v_proj.bias]
Loading weights:  33%|███▎      | 131/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.7.self_attn.v_proj.weight]
Loading weights:  33%|███▎      | 131/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.7.self_attn.v_proj.weight]
Loading weights:  33%|███▎      | 132/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.8.layer_norm1.bias]       
Loading weights:  33%|███▎      | 132/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.8.layer_norm1.bias]
Loading weights:  33%|███▎      | 133/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.8.layer_norm1.weight]
Loading weights:  33%|███▎      | 133/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.8.layer_norm1.weight]
Loading weights:  34%|███▎      | 134/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.8.layer_norm2.bias]  
Loading weights:  34%|███▎      | 134/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.8.layer_norm2.bias]
Loading weights:  34%|███▍      | 135/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.8.layer_norm2.weight]
Loading weights:  34%|███▍      | 135/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.8.layer_norm2.weight]
Loading weights:  34%|███▍      | 136/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.8.mlp.fc1.bias]      
Loading weights:  34%|███▍      | 136/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.8.mlp.fc1.bias]
Loading weights:  34%|███▍      | 137/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.8.mlp.fc1.weight]
Loading weights:  34%|███▍      | 137/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.8.mlp.fc1.weight]
Loading weights:  35%|███▍      | 138/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.8.mlp.fc2.bias]  
Loading weights:  35%|███▍      | 138/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.8.mlp.fc2.bias]
Loading weights:  35%|███▍      | 139/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.8.mlp.fc2.weight]
Loading weights:  35%|███▍      | 139/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.8.mlp.fc2.weight]
Loading weights:  35%|███▌      | 140/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.8.self_attn.k_proj.bias]
Loading weights:  35%|███▌      | 140/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.8.self_attn.k_proj.bias]
Loading weights:  35%|███▌      | 141/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.8.self_attn.k_proj.weight]
Loading weights:  35%|███▌      | 141/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.8.self_attn.k_proj.weight]
Loading weights:  36%|███▌      | 142/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.8.self_attn.out_proj.bias]
Loading weights:  36%|███▌      | 142/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.8.self_attn.out_proj.bias]
Loading weights:  36%|███▌      | 143/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.8.self_attn.out_proj.weight]
Loading weights:  36%|███▌      | 143/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.8.self_attn.out_proj.weight]
Loading weights:  36%|███▌      | 144/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.8.self_attn.q_proj.bias]    
Loading weights:  36%|███▌      | 144/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.8.self_attn.q_proj.bias]
Loading weights:  36%|███▋      | 145/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.8.self_attn.q_proj.weight]
Loading weights:  36%|███▋      | 145/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.8.self_attn.q_proj.weight]
Loading weights:  37%|███▋      | 146/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.8.self_attn.v_proj.bias]  
Loading weights:  37%|███▋      | 146/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.8.self_attn.v_proj.bias]
Loading weights:  37%|███▋      | 147/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.8.self_attn.v_proj.weight]
Loading weights:  37%|███▋      | 147/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.8.self_attn.v_proj.weight]
Loading weights:  37%|███▋      | 148/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.9.layer_norm1.bias]       
Loading weights:  37%|███▋      | 148/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.9.layer_norm1.bias]
Loading weights:  37%|███▋      | 149/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.9.layer_norm1.weight]
Loading weights:  37%|███▋      | 149/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.9.layer_norm1.weight]
Loading weights:  38%|███▊      | 150/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.9.layer_norm2.bias]  
Loading weights:  38%|███▊      | 150/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.9.layer_norm2.bias]
Loading weights:  38%|███▊      | 151/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.9.layer_norm2.weight]
Loading weights:  38%|███▊      | 151/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.9.layer_norm2.weight]
Loading weights:  38%|███▊      | 152/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.9.mlp.fc1.bias]      
Loading weights:  38%|███▊      | 152/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.9.mlp.fc1.bias]
Loading weights:  38%|███▊      | 153/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.9.mlp.fc1.weight]
Loading weights:  38%|███▊      | 153/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.9.mlp.fc1.weight]
Loading weights:  39%|███▊      | 154/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.9.mlp.fc2.bias]  
Loading weights:  39%|███▊      | 154/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.9.mlp.fc2.bias]
Loading weights:  39%|███▉      | 155/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.9.mlp.fc2.weight]
Loading weights:  39%|███▉      | 155/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.9.mlp.fc2.weight]
Loading weights:  39%|███▉      | 156/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.9.self_attn.k_proj.bias]
Loading weights:  39%|███▉      | 156/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.9.self_attn.k_proj.bias]
Loading weights:  39%|███▉      | 157/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.9.self_attn.k_proj.weight]
Loading weights:  39%|███▉      | 157/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.9.self_attn.k_proj.weight]
Loading weights:  40%|███▉      | 158/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.9.self_attn.out_proj.bias]
Loading weights:  40%|███▉      | 158/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.9.self_attn.out_proj.bias]
Loading weights:  40%|███▉      | 159/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.9.self_attn.out_proj.weight]
Loading weights:  40%|███▉      | 159/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.9.self_attn.out_proj.weight]
Loading weights:  40%|████      | 160/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.9.self_attn.q_proj.bias]    
Loading weights:  40%|████      | 160/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.9.self_attn.q_proj.bias]
Loading weights:  40%|████      | 161/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.9.self_attn.q_proj.weight]
Loading weights:  40%|████      | 161/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.9.self_attn.q_proj.weight]
Loading weights:  41%|████      | 162/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.9.self_attn.v_proj.bias]  
Loading weights:  41%|████      | 162/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.9.self_attn.v_proj.bias]
Loading weights:  41%|████      | 163/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.9.self_attn.v_proj.weight]
Loading weights:  41%|████      | 163/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.9.self_attn.v_proj.weight]
Loading weights:  41%|████      | 164/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.10.layer_norm1.bias]      
Loading weights:  41%|████      | 164/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.10.layer_norm1.bias]
Loading weights:  41%|████▏     | 165/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.10.layer_norm1.weight]
Loading weights:  41%|████▏     | 165/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.10.layer_norm1.weight]
Loading weights:  42%|████▏     | 166/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.10.layer_norm2.bias]  
Loading weights:  42%|████▏     | 166/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.10.layer_norm2.bias]
Loading weights:  42%|████▏     | 167/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.10.layer_norm2.weight]
Loading weights:  42%|████▏     | 167/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.10.layer_norm2.weight]
Loading weights:  42%|████▏     | 168/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.10.mlp.fc1.bias]      
Loading weights:  42%|████▏     | 168/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.10.mlp.fc1.bias]
Loading weights:  42%|████▏     | 169/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.10.mlp.fc1.weight]
Loading weights:  42%|████▏     | 169/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.10.mlp.fc1.weight]
Loading weights:  43%|████▎     | 170/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.10.mlp.fc2.bias]  
Loading weights:  43%|████▎     | 170/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.10.mlp.fc2.bias]
Loading weights:  43%|████▎     | 171/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.10.mlp.fc2.weight]
Loading weights:  43%|████▎     | 171/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.10.mlp.fc2.weight]
Loading weights:  43%|████▎     | 172/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.10.self_attn.k_proj.bias]
Loading weights:  43%|████▎     | 172/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.10.self_attn.k_proj.bias]
Loading weights:  43%|████▎     | 173/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.10.self_attn.k_proj.weight]
Loading weights:  43%|████▎     | 173/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.10.self_attn.k_proj.weight]
Loading weights:  44%|████▎     | 174/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.10.self_attn.out_proj.bias]
Loading weights:  44%|████▎     | 174/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.10.self_attn.out_proj.bias]
Loading weights:  44%|████▍     | 175/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.10.self_attn.out_proj.weight]
Loading weights:  44%|████▍     | 175/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.10.self_attn.out_proj.weight]
Loading weights:  44%|████▍     | 176/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.10.self_attn.q_proj.bias]    
Loading weights:  44%|████▍     | 176/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.10.self_attn.q_proj.bias]
Loading weights:  44%|████▍     | 177/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.10.self_attn.q_proj.weight]
Loading weights:  44%|████▍     | 177/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.10.self_attn.q_proj.weight]
Loading weights:  45%|████▍     | 178/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.10.self_attn.v_proj.bias]  
Loading weights:  45%|████▍     | 178/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.10.self_attn.v_proj.bias]
Loading weights:  45%|████▍     | 179/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.10.self_attn.v_proj.weight]
Loading weights:  45%|████▍     | 179/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.10.self_attn.v_proj.weight]
Loading weights:  45%|████▌     | 180/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.11.layer_norm1.bias]       
Loading weights:  45%|████▌     | 180/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.11.layer_norm1.bias]
Loading weights:  45%|████▌     | 181/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.11.layer_norm1.weight]
Loading weights:  45%|████▌     | 181/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.11.layer_norm1.weight]
Loading weights:  46%|████▌     | 182/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.11.layer_norm2.bias]  
Loading weights:  46%|████▌     | 182/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.11.layer_norm2.bias]
Loading weights:  46%|████▌     | 183/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.11.layer_norm2.weight]
Loading weights:  46%|████▌     | 183/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.11.layer_norm2.weight]
Loading weights:  46%|████▌     | 184/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.11.mlp.fc1.bias]      
Loading weights:  46%|████▌     | 184/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.11.mlp.fc1.bias]
Loading weights:  46%|████▋     | 185/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.11.mlp.fc1.weight]
Loading weights:  46%|████▋     | 185/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.11.mlp.fc1.weight]
Loading weights:  47%|████▋     | 186/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.11.mlp.fc2.bias]  
Loading weights:  47%|████▋     | 186/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.11.mlp.fc2.bias]
Loading weights:  47%|████▋     | 187/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.11.mlp.fc2.weight]
Loading weights:  47%|████▋     | 187/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.11.mlp.fc2.weight]
Loading weights:  47%|████▋     | 188/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.11.self_attn.k_proj.bias]
Loading weights:  47%|████▋     | 188/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.11.self_attn.k_proj.bias]
Loading weights:  47%|████▋     | 189/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.11.self_attn.k_proj.weight]
Loading weights:  47%|████▋     | 189/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.11.self_attn.k_proj.weight]
Loading weights:  48%|████▊     | 190/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.11.self_attn.out_proj.bias]
Loading weights:  48%|████▊     | 190/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.11.self_attn.out_proj.bias]
Loading weights:  48%|████▊     | 191/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.11.self_attn.out_proj.weight]
Loading weights:  48%|████▊     | 191/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.11.self_attn.out_proj.weight]
Loading weights:  48%|████▊     | 192/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.11.self_attn.q_proj.bias]    
Loading weights:  48%|████▊     | 192/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.11.self_attn.q_proj.bias]
Loading weights:  48%|████▊     | 193/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.11.self_attn.q_proj.weight]
Loading weights:  48%|████▊     | 193/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.11.self_attn.q_proj.weight]
Loading weights:  49%|████▊     | 194/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.11.self_attn.v_proj.bias]  
Loading weights:  49%|████▊     | 194/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.11.self_attn.v_proj.bias]
Loading weights:  49%|████▉     | 195/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.11.self_attn.v_proj.weight]
Loading weights:  49%|████▉     | 195/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.encoder.layers.11.self_attn.v_proj.weight]
Loading weights:  49%|████▉     | 196/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.final_layer_norm.bias]                    
Loading weights:  49%|████▉     | 196/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.final_layer_norm.bias]
Loading weights:  49%|████▉     | 197/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.final_layer_norm.weight]
Loading weights:  49%|████▉     | 197/398 [00:00<00:00, 381.71it/s, Materializing param=text_model.final_layer_norm.weight]
Loading weights:  50%|████▉     | 198/398 [00:00<00:00, 381.71it/s, Materializing param=text_projection.weight]            
Loading weights:  50%|████▉     | 198/398 [00:00<00:00, 381.71it/s, Materializing param=text_projection.weight]
Loading weights:  50%|█████     | 199/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.embeddings.class_embedding]
Loading weights:  50%|█████     | 199/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.embeddings.class_embedding]
Loading weights:  50%|█████     | 200/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.embeddings.patch_embedding.weight]
Loading weights:  50%|█████     | 200/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.embeddings.patch_embedding.weight]
Loading weights:  51%|█████     | 201/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.embeddings.position_embedding.weight]
Loading weights:  51%|█████     | 201/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.embeddings.position_embedding.weight]
Loading weights:  51%|█████     | 202/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.0.layer_norm1.bias]   
Loading weights:  51%|█████     | 202/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.0.layer_norm1.bias]
Loading weights:  51%|█████     | 203/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.0.layer_norm1.weight]
Loading weights:  51%|█████     | 203/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.0.layer_norm1.weight]
Loading weights:  51%|█████▏    | 204/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.0.layer_norm2.bias]  
Loading weights:  51%|█████▏    | 204/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.0.layer_norm2.bias]
Loading weights:  52%|█████▏    | 205/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.0.layer_norm2.weight]
Loading weights:  52%|█████▏    | 205/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.0.layer_norm2.weight]
Loading weights:  52%|█████▏    | 206/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.0.mlp.fc1.bias]      
Loading weights:  52%|█████▏    | 206/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.0.mlp.fc1.bias]
Loading weights:  52%|█████▏    | 207/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.0.mlp.fc1.weight]
Loading weights:  52%|█████▏    | 207/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.0.mlp.fc1.weight]
Loading weights:  52%|█████▏    | 208/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.0.mlp.fc2.bias]  
Loading weights:  52%|█████▏    | 208/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.0.mlp.fc2.bias]
Loading weights:  53%|█████▎    | 209/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.0.mlp.fc2.weight]
Loading weights:  53%|█████▎    | 209/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.0.mlp.fc2.weight]
Loading weights:  53%|█████▎    | 210/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.0.self_attn.k_proj.bias]
Loading weights:  53%|█████▎    | 210/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.0.self_attn.k_proj.bias]
Loading weights:  53%|█████▎    | 211/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.0.self_attn.k_proj.weight]
Loading weights:  53%|█████▎    | 211/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.0.self_attn.k_proj.weight]
Loading weights:  53%|█████▎    | 212/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.0.self_attn.out_proj.bias]
Loading weights:  53%|█████▎    | 212/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.0.self_attn.out_proj.bias]
Loading weights:  54%|█████▎    | 213/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.0.self_attn.out_proj.weight]
Loading weights:  54%|█████▎    | 213/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.0.self_attn.out_proj.weight]
Loading weights:  54%|█████▍    | 214/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.0.self_attn.q_proj.bias]    
Loading weights:  54%|█████▍    | 214/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.0.self_attn.q_proj.bias]
Loading weights:  54%|█████▍    | 215/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.0.self_attn.q_proj.weight]
Loading weights:  54%|█████▍    | 215/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.0.self_attn.q_proj.weight]
Loading weights:  54%|█████▍    | 216/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.0.self_attn.v_proj.bias]  
Loading weights:  54%|█████▍    | 216/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.0.self_attn.v_proj.bias]
Loading weights:  55%|█████▍    | 217/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.0.self_attn.v_proj.weight]
Loading weights:  55%|█████▍    | 217/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.0.self_attn.v_proj.weight]
Loading weights:  55%|█████▍    | 218/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.1.layer_norm1.bias]       
Loading weights:  55%|█████▍    | 218/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.1.layer_norm1.bias]
Loading weights:  55%|█████▌    | 219/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.1.layer_norm1.weight]
Loading weights:  55%|█████▌    | 219/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.1.layer_norm1.weight]
Loading weights:  55%|█████▌    | 220/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.1.layer_norm2.bias]  
Loading weights:  55%|█████▌    | 220/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.1.layer_norm2.bias]
Loading weights:  56%|█████▌    | 221/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.1.layer_norm2.weight]
Loading weights:  56%|█████▌    | 221/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.1.layer_norm2.weight]
Loading weights:  56%|█████▌    | 222/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.1.mlp.fc1.bias]      
Loading weights:  56%|█████▌    | 222/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.1.mlp.fc1.bias]
Loading weights:  56%|█████▌    | 223/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.1.mlp.fc1.weight]
Loading weights:  56%|█████▌    | 223/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.1.mlp.fc1.weight]
Loading weights:  56%|█████▋    | 224/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.1.mlp.fc2.bias]  
Loading weights:  56%|█████▋    | 224/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.1.mlp.fc2.bias]
Loading weights:  57%|█████▋    | 225/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.1.mlp.fc2.weight]
Loading weights:  57%|█████▋    | 225/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.1.mlp.fc2.weight]
Loading weights:  57%|█████▋    | 226/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.1.self_attn.k_proj.bias]
Loading weights:  57%|█████▋    | 226/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.1.self_attn.k_proj.bias]
Loading weights:  57%|█████▋    | 227/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.1.self_attn.k_proj.weight]
Loading weights:  57%|█████▋    | 227/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.1.self_attn.k_proj.weight]
Loading weights:  57%|█████▋    | 228/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.1.self_attn.out_proj.bias]
Loading weights:  57%|█████▋    | 228/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.1.self_attn.out_proj.bias]
Loading weights:  58%|█████▊    | 229/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.1.self_attn.out_proj.weight]
Loading weights:  58%|█████▊    | 229/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.1.self_attn.out_proj.weight]
Loading weights:  58%|█████▊    | 230/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.1.self_attn.q_proj.bias]    
Loading weights:  58%|█████▊    | 230/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.1.self_attn.q_proj.bias]
Loading weights:  58%|█████▊    | 231/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.1.self_attn.q_proj.weight]
Loading weights:  58%|█████▊    | 231/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.1.self_attn.q_proj.weight]
Loading weights:  58%|█████▊    | 232/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.1.self_attn.v_proj.bias]  
Loading weights:  58%|█████▊    | 232/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.1.self_attn.v_proj.bias]
Loading weights:  59%|█████▊    | 233/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.1.self_attn.v_proj.weight]
Loading weights:  59%|█████▊    | 233/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.1.self_attn.v_proj.weight]
Loading weights:  59%|█████▉    | 234/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.2.layer_norm1.bias]       
Loading weights:  59%|█████▉    | 234/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.2.layer_norm1.bias]
Loading weights:  59%|█████▉    | 235/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.2.layer_norm1.weight]
Loading weights:  59%|█████▉    | 235/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.2.layer_norm1.weight]
Loading weights:  59%|█████▉    | 236/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.2.layer_norm2.bias]  
Loading weights:  59%|█████▉    | 236/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.2.layer_norm2.bias]
Loading weights:  60%|█████▉    | 237/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.2.layer_norm2.weight]
Loading weights:  60%|█████▉    | 237/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.2.layer_norm2.weight]
Loading weights:  60%|█████▉    | 238/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.2.mlp.fc1.bias]      
Loading weights:  60%|█████▉    | 238/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.2.mlp.fc1.bias]
Loading weights:  60%|██████    | 239/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.2.mlp.fc1.weight]
Loading weights:  60%|██████    | 239/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.2.mlp.fc1.weight]
Loading weights:  60%|██████    | 240/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.2.mlp.fc2.bias]  
Loading weights:  60%|██████    | 240/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.2.mlp.fc2.bias]
Loading weights:  61%|██████    | 241/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.2.mlp.fc2.weight]
Loading weights:  61%|██████    | 241/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.2.mlp.fc2.weight]
Loading weights:  61%|██████    | 242/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.2.self_attn.k_proj.bias]
Loading weights:  61%|██████    | 242/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.2.self_attn.k_proj.bias]
Loading weights:  61%|██████    | 243/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.2.self_attn.k_proj.weight]
Loading weights:  61%|██████    | 243/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.2.self_attn.k_proj.weight]
Loading weights:  61%|██████▏   | 244/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.2.self_attn.out_proj.bias]
Loading weights:  61%|██████▏   | 244/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.2.self_attn.out_proj.bias]
Loading weights:  62%|██████▏   | 245/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.2.self_attn.out_proj.weight]
Loading weights:  62%|██████▏   | 245/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.2.self_attn.out_proj.weight]
Loading weights:  62%|██████▏   | 246/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.2.self_attn.q_proj.bias]    
Loading weights:  62%|██████▏   | 246/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.2.self_attn.q_proj.bias]
Loading weights:  62%|██████▏   | 247/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.2.self_attn.q_proj.weight]
Loading weights:  62%|██████▏   | 247/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.2.self_attn.q_proj.weight]
Loading weights:  62%|██████▏   | 248/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.2.self_attn.v_proj.bias]  
Loading weights:  62%|██████▏   | 248/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.2.self_attn.v_proj.bias]
Loading weights:  63%|██████▎   | 249/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.2.self_attn.v_proj.weight]
Loading weights:  63%|██████▎   | 249/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.2.self_attn.v_proj.weight]
Loading weights:  63%|██████▎   | 250/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.3.layer_norm1.bias]       
Loading weights:  63%|██████▎   | 250/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.3.layer_norm1.bias]
Loading weights:  63%|██████▎   | 251/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.3.layer_norm1.weight]
Loading weights:  63%|██████▎   | 251/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.3.layer_norm1.weight]
Loading weights:  63%|██████▎   | 252/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.3.layer_norm2.bias]  
Loading weights:  63%|██████▎   | 252/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.3.layer_norm2.bias]
Loading weights:  64%|██████▎   | 253/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.3.layer_norm2.weight]
Loading weights:  64%|██████▎   | 253/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.3.layer_norm2.weight]
Loading weights:  64%|██████▍   | 254/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.3.mlp.fc1.bias]      
Loading weights:  64%|██████▍   | 254/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.3.mlp.fc1.bias]
Loading weights:  64%|██████▍   | 255/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.3.mlp.fc1.weight]
Loading weights:  64%|██████▍   | 255/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.3.mlp.fc1.weight]
Loading weights:  64%|██████▍   | 256/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.3.mlp.fc2.bias]  
Loading weights:  64%|██████▍   | 256/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.3.mlp.fc2.bias]
Loading weights:  65%|██████▍   | 257/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.3.mlp.fc2.weight]
Loading weights:  65%|██████▍   | 257/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.3.mlp.fc2.weight]
Loading weights:  65%|██████▍   | 258/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.3.self_attn.k_proj.bias]
Loading weights:  65%|██████▍   | 258/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.3.self_attn.k_proj.bias]
Loading weights:  65%|██████▌   | 259/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.3.self_attn.k_proj.weight]
Loading weights:  65%|██████▌   | 259/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.3.self_attn.k_proj.weight]
Loading weights:  65%|██████▌   | 260/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.3.self_attn.out_proj.bias]
Loading weights:  65%|██████▌   | 260/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.3.self_attn.out_proj.bias]
Loading weights:  66%|██████▌   | 261/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.3.self_attn.out_proj.weight]
Loading weights:  66%|██████▌   | 261/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.3.self_attn.out_proj.weight]
Loading weights:  66%|██████▌   | 262/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.3.self_attn.q_proj.bias]    
Loading weights:  66%|██████▌   | 262/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.3.self_attn.q_proj.bias]
Loading weights:  66%|██████▌   | 263/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.3.self_attn.q_proj.weight]
Loading weights:  66%|██████▌   | 263/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.3.self_attn.q_proj.weight]
Loading weights:  66%|██████▋   | 264/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.3.self_attn.v_proj.bias]  
Loading weights:  66%|██████▋   | 264/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.3.self_attn.v_proj.bias]
Loading weights:  67%|██████▋   | 265/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.3.self_attn.v_proj.weight]
Loading weights:  67%|██████▋   | 265/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.3.self_attn.v_proj.weight]
Loading weights:  67%|██████▋   | 266/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.4.layer_norm1.bias]       
Loading weights:  67%|██████▋   | 266/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.4.layer_norm1.bias]
Loading weights:  67%|██████▋   | 267/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.4.layer_norm1.weight]
Loading weights:  67%|██████▋   | 267/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.4.layer_norm1.weight]
Loading weights:  67%|██████▋   | 268/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.4.layer_norm2.bias]  
Loading weights:  67%|██████▋   | 268/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.4.layer_norm2.bias]
Loading weights:  68%|██████▊   | 269/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.4.layer_norm2.weight]
Loading weights:  68%|██████▊   | 269/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.4.layer_norm2.weight]
Loading weights:  68%|██████▊   | 270/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.4.mlp.fc1.bias]      
Loading weights:  68%|██████▊   | 270/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.4.mlp.fc1.bias]
Loading weights:  68%|██████▊   | 271/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.4.mlp.fc1.weight]
Loading weights:  68%|██████▊   | 271/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.4.mlp.fc1.weight]
Loading weights:  68%|██████▊   | 272/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.4.mlp.fc2.bias]  
Loading weights:  68%|██████▊   | 272/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.4.mlp.fc2.bias]
Loading weights:  69%|██████▊   | 273/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.4.mlp.fc2.weight]
Loading weights:  69%|██████▊   | 273/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.4.mlp.fc2.weight]
Loading weights:  69%|██████▉   | 274/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.4.self_attn.k_proj.bias]
Loading weights:  69%|██████▉   | 274/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.4.self_attn.k_proj.bias]
Loading weights:  69%|██████▉   | 275/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.4.self_attn.k_proj.weight]
Loading weights:  69%|██████▉   | 275/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.4.self_attn.k_proj.weight]
Loading weights:  69%|██████▉   | 276/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.4.self_attn.out_proj.bias]
Loading weights:  69%|██████▉   | 276/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.4.self_attn.out_proj.bias]
Loading weights:  70%|██████▉   | 277/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.4.self_attn.out_proj.weight]
Loading weights:  70%|██████▉   | 277/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.4.self_attn.out_proj.weight]
Loading weights:  70%|██████▉   | 278/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.4.self_attn.q_proj.bias]    
Loading weights:  70%|██████▉   | 278/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.4.self_attn.q_proj.bias]
Loading weights:  70%|███████   | 279/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.4.self_attn.q_proj.weight]
Loading weights:  70%|███████   | 279/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.4.self_attn.q_proj.weight]
Loading weights:  70%|███████   | 280/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.4.self_attn.v_proj.bias]  
Loading weights:  70%|███████   | 280/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.4.self_attn.v_proj.bias]
Loading weights:  71%|███████   | 281/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.4.self_attn.v_proj.weight]
Loading weights:  71%|███████   | 281/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.4.self_attn.v_proj.weight]
Loading weights:  71%|███████   | 282/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.5.layer_norm1.bias]       
Loading weights:  71%|███████   | 282/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.5.layer_norm1.bias]
Loading weights:  71%|███████   | 283/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.5.layer_norm1.weight]
Loading weights:  71%|███████   | 283/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.5.layer_norm1.weight]
Loading weights:  71%|███████▏  | 284/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.5.layer_norm2.bias]  
Loading weights:  71%|███████▏  | 284/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.5.layer_norm2.bias]
Loading weights:  72%|███████▏  | 285/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.5.layer_norm2.weight]
Loading weights:  72%|███████▏  | 285/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.5.layer_norm2.weight]
Loading weights:  72%|███████▏  | 286/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.5.mlp.fc1.bias]      
Loading weights:  72%|███████▏  | 286/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.5.mlp.fc1.bias]
Loading weights:  72%|███████▏  | 287/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.5.mlp.fc1.weight]
Loading weights:  72%|███████▏  | 287/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.5.mlp.fc1.weight]
Loading weights:  72%|███████▏  | 288/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.5.mlp.fc2.bias]  
Loading weights:  72%|███████▏  | 288/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.5.mlp.fc2.bias]
Loading weights:  73%|███████▎  | 289/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.5.mlp.fc2.weight]
Loading weights:  73%|███████▎  | 289/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.5.mlp.fc2.weight]
Loading weights:  73%|███████▎  | 290/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.5.self_attn.k_proj.bias]
Loading weights:  73%|███████▎  | 290/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.5.self_attn.k_proj.bias]
Loading weights:  73%|███████▎  | 291/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.5.self_attn.k_proj.weight]
Loading weights:  73%|███████▎  | 291/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.5.self_attn.k_proj.weight]
Loading weights:  73%|███████▎  | 292/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.5.self_attn.out_proj.bias]
Loading weights:  73%|███████▎  | 292/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.5.self_attn.out_proj.bias]
Loading weights:  74%|███████▎  | 293/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.5.self_attn.out_proj.weight]
Loading weights:  74%|███████▎  | 293/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.5.self_attn.out_proj.weight]
Loading weights:  74%|███████▍  | 294/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.5.self_attn.q_proj.bias]    
Loading weights:  74%|███████▍  | 294/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.5.self_attn.q_proj.bias]
Loading weights:  74%|███████▍  | 295/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.5.self_attn.q_proj.weight]
Loading weights:  74%|███████▍  | 295/398 [00:00<00:00, 381.71it/s, Materializing param=vision_model.encoder.layers.5.self_attn.q_proj.weight]
Loading weights:  74%|███████▍  | 296/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.5.self_attn.q_proj.weight]
Loading weights:  74%|███████▍  | 296/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.5.self_attn.v_proj.bias]  
Loading weights:  74%|███████▍  | 296/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.5.self_attn.v_proj.bias]
Loading weights:  75%|███████▍  | 297/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.5.self_attn.v_proj.weight]
Loading weights:  75%|███████▍  | 297/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.5.self_attn.v_proj.weight]
Loading weights:  75%|███████▍  | 298/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.6.layer_norm1.bias]       
Loading weights:  75%|███████▍  | 298/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.6.layer_norm1.bias]
Loading weights:  75%|███████▌  | 299/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.6.layer_norm1.weight]
Loading weights:  75%|███████▌  | 299/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.6.layer_norm1.weight]
Loading weights:  75%|███████▌  | 300/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.6.layer_norm2.bias]  
Loading weights:  75%|███████▌  | 300/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.6.layer_norm2.bias]
Loading weights:  76%|███████▌  | 301/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.6.layer_norm2.weight]
Loading weights:  76%|███████▌  | 301/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.6.layer_norm2.weight]
Loading weights:  76%|███████▌  | 302/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.6.mlp.fc1.bias]      
Loading weights:  76%|███████▌  | 302/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.6.mlp.fc1.bias]
Loading weights:  76%|███████▌  | 303/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.6.mlp.fc1.weight]
Loading weights:  76%|███████▌  | 303/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.6.mlp.fc1.weight]
Loading weights:  76%|███████▋  | 304/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.6.mlp.fc2.bias]  
Loading weights:  76%|███████▋  | 304/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.6.mlp.fc2.bias]
Loading weights:  77%|███████▋  | 305/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.6.mlp.fc2.weight]
Loading weights:  77%|███████▋  | 305/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.6.mlp.fc2.weight]
Loading weights:  77%|███████▋  | 306/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.6.self_attn.k_proj.bias]
Loading weights:  77%|███████▋  | 306/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.6.self_attn.k_proj.bias]
Loading weights:  77%|███████▋  | 307/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.6.self_attn.k_proj.weight]
Loading weights:  77%|███████▋  | 307/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.6.self_attn.k_proj.weight]
Loading weights:  77%|███████▋  | 308/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.6.self_attn.out_proj.bias]
Loading weights:  77%|███████▋  | 308/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.6.self_attn.out_proj.bias]
Loading weights:  78%|███████▊  | 309/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.6.self_attn.out_proj.weight]
Loading weights:  78%|███████▊  | 309/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.6.self_attn.out_proj.weight]
Loading weights:  78%|███████▊  | 310/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.6.self_attn.q_proj.bias]    
Loading weights:  78%|███████▊  | 310/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.6.self_attn.q_proj.bias]
Loading weights:  78%|███████▊  | 311/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.6.self_attn.q_proj.weight]
Loading weights:  78%|███████▊  | 311/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.6.self_attn.q_proj.weight]
Loading weights:  78%|███████▊  | 312/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.6.self_attn.v_proj.bias]  
Loading weights:  78%|███████▊  | 312/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.6.self_attn.v_proj.bias]
Loading weights:  79%|███████▊  | 313/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.6.self_attn.v_proj.weight]
Loading weights:  79%|███████▊  | 313/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.6.self_attn.v_proj.weight]
Loading weights:  79%|███████▉  | 314/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.7.layer_norm1.bias]       
Loading weights:  79%|███████▉  | 314/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.7.layer_norm1.bias]
Loading weights:  79%|███████▉  | 315/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.7.layer_norm1.weight]
Loading weights:  79%|███████▉  | 315/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.7.layer_norm1.weight]
Loading weights:  79%|███████▉  | 316/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.7.layer_norm2.bias]  
Loading weights:  79%|███████▉  | 316/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.7.layer_norm2.bias]
Loading weights:  80%|███████▉  | 317/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.7.layer_norm2.weight]
Loading weights:  80%|███████▉  | 317/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.7.layer_norm2.weight]
Loading weights:  80%|███████▉  | 318/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.7.mlp.fc1.bias]      
Loading weights:  80%|███████▉  | 318/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.7.mlp.fc1.bias]
Loading weights:  80%|████████  | 319/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.7.mlp.fc1.weight]
Loading weights:  80%|████████  | 319/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.7.mlp.fc1.weight]
Loading weights:  80%|████████  | 320/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.7.mlp.fc2.bias]  
Loading weights:  80%|████████  | 320/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.7.mlp.fc2.bias]
Loading weights:  81%|████████  | 321/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.7.mlp.fc2.weight]
Loading weights:  81%|████████  | 321/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.7.mlp.fc2.weight]
Loading weights:  81%|████████  | 322/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.7.self_attn.k_proj.bias]
Loading weights:  81%|████████  | 322/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.7.self_attn.k_proj.bias]
Loading weights:  81%|████████  | 323/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.7.self_attn.k_proj.weight]
Loading weights:  81%|████████  | 323/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.7.self_attn.k_proj.weight]
Loading weights:  81%|████████▏ | 324/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.7.self_attn.out_proj.bias]
Loading weights:  81%|████████▏ | 324/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.7.self_attn.out_proj.bias]
Loading weights:  82%|████████▏ | 325/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.7.self_attn.out_proj.weight]
Loading weights:  82%|████████▏ | 325/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.7.self_attn.out_proj.weight]
Loading weights:  82%|████████▏ | 326/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.7.self_attn.q_proj.bias]    
Loading weights:  82%|████████▏ | 326/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.7.self_attn.q_proj.bias]
Loading weights:  82%|████████▏ | 327/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.7.self_attn.q_proj.weight]
Loading weights:  82%|████████▏ | 327/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.7.self_attn.q_proj.weight]
Loading weights:  82%|████████▏ | 328/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.7.self_attn.v_proj.bias]  
Loading weights:  82%|████████▏ | 328/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.7.self_attn.v_proj.bias]
Loading weights:  83%|████████▎ | 329/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.7.self_attn.v_proj.weight]
Loading weights:  83%|████████▎ | 329/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.7.self_attn.v_proj.weight]
Loading weights:  83%|████████▎ | 330/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.8.layer_norm1.bias]       
Loading weights:  83%|████████▎ | 330/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.8.layer_norm1.bias]
Loading weights:  83%|████████▎ | 331/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.8.layer_norm1.weight]
Loading weights:  83%|��███████▎ | 331/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.8.layer_norm1.weight]
Loading weights:  83%|████████▎ | 332/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.8.layer_norm2.bias]  
Loading weights:  83%|████████▎ | 332/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.8.layer_norm2.bias]
Loading weights:  84%|████████▎ | 333/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.8.layer_norm2.weight]
Loading weights:  84%|████████▎ | 333/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.8.layer_norm2.weight]
Loading weights:  84%|████████▍ | 334/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.8.mlp.fc1.bias]      
Loading weights:  84%|████████▍ | 334/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.8.mlp.fc1.bias]
Loading weights:  84%|████████▍ | 335/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.8.mlp.fc1.weight]
Loading weights:  84%|████████▍ | 335/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.8.mlp.fc1.weight]
Loading weights:  84%|████████▍ | 336/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.8.mlp.fc2.bias]  
Loading weights:  84%|████████▍ | 336/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.8.mlp.fc2.bias]
Loading weights:  85%|████████▍ | 337/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.8.mlp.fc2.weight]
Loading weights:  85%|████████▍ | 337/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.8.mlp.fc2.weight]
Loading weights:  85%|████████▍ | 338/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.8.self_attn.k_proj.bias]
Loading weights:  85%|████████▍ | 338/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.8.self_attn.k_proj.bias]
Loading weights:  85%|████████▌ | 339/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.8.self_attn.k_proj.weight]
Loading weights:  85%|████████▌ | 339/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.8.self_attn.k_proj.weight]
Loading weights:  85%|████████▌ | 340/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.8.self_attn.out_proj.bias]
Loading weights:  85%|████████▌ | 340/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.8.self_attn.out_proj.bias]
Loading weights:  86%|████████▌ | 341/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.8.self_attn.out_proj.weight]
Loading weights:  86%|████████▌ | 341/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.8.self_attn.out_proj.weight]
Loading weights:  86%|████████▌ | 342/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.8.self_attn.q_proj.bias]    
Loading weights:  86%|████████▌ | 342/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.8.self_attn.q_proj.bias]
Loading weights:  86%|████████▌ | 343/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.8.self_attn.q_proj.weight]
Loading weights:  86%|████████▌ | 343/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.8.self_attn.q_proj.weight]
Loading weights:  86%|████████▋ | 344/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.8.self_attn.v_proj.bias]  
Loading weights:  86%|████████▋ | 344/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.8.self_attn.v_proj.bias]
Loading weights:  87%|████████▋ | 345/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.8.self_attn.v_proj.weight]
Loading weights:  87%|████████▋ | 345/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.8.self_attn.v_proj.weight]
Loading weights:  87%|████████▋ | 346/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.9.layer_norm1.bias]       
Loading weights:  87%|████████▋ | 346/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.9.layer_norm1.bias]
Loading weights:  87%|████████▋ | 347/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.9.layer_norm1.weight]
Loading weights:  87%|████████▋ | 347/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.9.layer_norm1.weight]
Loading weights:  87%|████████▋ | 348/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.9.layer_norm2.bias]  
Loading weights:  87%|████████▋ | 348/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.9.layer_norm2.bias]
Loading weights:  88%|████████▊ | 349/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.9.layer_norm2.weight]
Loading weights:  88%|████████▊ | 349/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.9.layer_norm2.weight]
Loading weights:  88%|████████▊ | 350/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.9.mlp.fc1.bias]      
Loading weights:  88%|████████▊ | 350/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.9.mlp.fc1.bias]
Loading weights:  88%|████████▊ | 351/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.9.mlp.fc1.weight]
Loading weights:  88%|████████▊ | 351/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.9.mlp.fc1.weight]
Loading weights:  88%|████████▊ | 352/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.9.mlp.fc2.bias]  
Loading weights:  88%|████████▊ | 352/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.9.mlp.fc2.bias]
Loading weights:  89%|████████▊ | 353/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.9.mlp.fc2.weight]
Loading weights:  89%|████████▊ | 353/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.9.mlp.fc2.weight]
Loading weights:  89%|████████▉ | 354/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.9.self_attn.k_proj.bias]
Loading weights:  89%|████████▉ | 354/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.9.self_attn.k_proj.bias]
Loading weights:  89%|████████▉ | 355/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.9.self_attn.k_proj.weight]
Loading weights:  89%|████████▉ | 355/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.9.self_attn.k_proj.weight]
Loading weights:  89%|████████▉ | 356/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.9.self_attn.out_proj.bias]
Loading weights:  89%|████████▉ | 356/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.9.self_attn.out_proj.bias]
Loading weights:  90%|████████▉ | 357/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.9.self_attn.out_proj.weight]
Loading weights:  90%|████████▉ | 357/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.9.self_attn.out_proj.weight]
Loading weights:  90%|████████▉ | 358/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.9.self_attn.q_proj.bias]    
Loading weights:  90%|████████▉ | 358/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.9.self_attn.q_proj.bias]
Loading weights:  90%|█████████ | 359/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.9.self_attn.q_proj.weight]
Loading weights:  90%|█████████ | 359/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.9.self_attn.q_proj.weight]
Loading weights:  90%|█████████ | 360/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.9.self_attn.v_proj.bias]  
Loading weights:  90%|█████████ | 360/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.9.self_attn.v_proj.bias]
Loading weights:  91%|█████████ | 361/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.9.self_attn.v_proj.weight]
Loading weights:  91%|█████████ | 361/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.9.self_attn.v_proj.weight]
Loading weights:  91%|█████████ | 362/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.10.layer_norm1.bias]      
Loading weights:  91%|█████████ | 362/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.10.layer_norm1.bias]
Loading weights:  91%|█████████ | 363/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.10.layer_norm1.weight]
Loading weights:  91%|█████████ | 363/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.10.layer_norm1.weight]
Loading weights:  91%|█████████▏| 364/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.10.layer_norm2.bias]  
Loading weights:  91%|█████████▏| 364/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.10.layer_norm2.bias]
Loading weights:  92%|█████████▏| 365/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.10.layer_norm2.weight]
Loading weights:  92%|█████████▏| 365/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.10.layer_norm2.weight]
Loading weights:  92%|█████████▏| 366/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.10.mlp.fc1.bias]      
Loading weights:  92%|█████████▏| 366/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.10.mlp.fc1.bias]
Loading weights:  92%|█████████▏| 367/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.10.mlp.fc1.weight]
Loading weights:  92%|█████████▏| 367/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.10.mlp.fc1.weight]
Loading weights:  92%|█████████▏| 368/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.10.mlp.fc2.bias]  
Loading weights:  92%|█████████▏| 368/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.10.mlp.fc2.bias]
Loading weights:  93%|█████████▎| 369/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.10.mlp.fc2.weight]
Loading weights:  93%|█████████▎| 369/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.10.mlp.fc2.weight]
Loading weights:  93%|█████████▎| 370/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.10.self_attn.k_proj.bias]
Loading weights:  93%|█████████▎| 370/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.10.self_attn.k_proj.bias]
Loading weights:  93%|█████████▎| 371/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.10.self_attn.k_proj.weight]
Loading weights:  93%|█████████▎| 371/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.10.self_attn.k_proj.weight]
Loading weights:  93%|█████████▎| 372/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.10.self_attn.out_proj.bias]
Loading weights:  93%|█████████▎| 372/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.10.self_attn.out_proj.bias]
Loading weights:  94%|█████████▎| 373/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.10.self_attn.out_proj.weight]
Loading weights:  94%|█████████▎| 373/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.10.self_attn.out_proj.weight]
Loading weights:  94%|█████████▍| 374/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.10.self_attn.q_proj.bias]    
Loading weights:  94%|█████████▍| 374/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.10.self_attn.q_proj.bias]
Loading weights:  94%|█████████▍| 375/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.10.self_attn.q_proj.weight]
Loading weights:  94%|█████████▍| 375/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.10.self_attn.q_proj.weight]
Loading weights:  94%|█████████▍| 376/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.10.self_attn.v_proj.bias]  
Loading weights:  94%|█████████▍| 376/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.10.self_attn.v_proj.bias]
Loading weights:  95%|█████████▍| 377/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.10.self_attn.v_proj.weight]
Loading weights:  95%|█████████▍| 377/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.10.self_attn.v_proj.weight]
Loading weights:  95%|█████████▍| 378/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.11.layer_norm1.bias]       
Loading weights:  95%|█████████▍| 378/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.11.layer_norm1.bias]
Loading weights:  95%|█████████▌| 379/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.11.layer_norm1.weight]
Loading weights:  95%|█████████▌| 379/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.11.layer_norm1.weight]
Loading weights:  95%|█████████▌| 380/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.11.layer_norm2.bias]  
Loading weights:  95%|█████████▌| 380/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.11.layer_norm2.bias]
Loading weights:  96%|█████████▌| 381/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.11.layer_norm2.weight]
Loading weights:  96%|█████████▌| 381/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.11.layer_norm2.weight]
Loading weights:  96%|█████████▌| 382/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.11.mlp.fc1.bias]      
Loading weights:  96%|█████████▌| 382/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.11.mlp.fc1.bias]
Loading weights:  96%|█████████▌| 383/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.11.mlp.fc1.weight]
Loading weights:  96%|█████████▌| 383/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.11.mlp.fc1.weight]
Loading weights:  96%|█████████▋| 384/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.11.mlp.fc2.bias]  
Loading weights:  96%|█████████▋| 384/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.11.mlp.fc2.bias]
Loading weights:  97%|█████████▋| 385/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.11.mlp.fc2.weight]
Loading weights:  97%|█████████▋| 385/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.11.mlp.fc2.weight]
Loading weights:  97%|█████████▋| 386/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.11.self_attn.k_proj.bias]
Loading weights:  97%|█████████▋| 386/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.11.self_attn.k_proj.bias]
Loading weights:  97%|█████████▋| 387/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.11.self_attn.k_proj.weight]
Loading weights:  97%|█████████▋| 387/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.11.self_attn.k_proj.weight]
Loading weights:  97%|█████████▋| 388/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.11.self_attn.out_proj.bias]
Loading weights:  97%|█████████▋| 388/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.11.self_attn.out_proj.bias]
Loading weights:  98%|█████████▊| 389/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.11.self_attn.out_proj.weight]
Loading weights:  98%|█████████▊| 389/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.11.self_attn.out_proj.weight]
Loading weights:  98%|█████████▊| 390/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.11.self_attn.q_proj.bias]    
Loading weights:  98%|█████████▊| 390/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.11.self_attn.q_proj.bias]
Loading weights:  98%|█████████▊| 391/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.11.self_attn.q_proj.weight]
Loading weights:  98%|█████████▊| 391/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.11.self_attn.q_proj.weight]
Loading weights:  98%|█████████▊| 392/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.11.self_attn.v_proj.bias]  
Loading weights:  98%|█████████▊| 392/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.11.self_attn.v_proj.bias]
Loading weights:  99%|█████████▊| 393/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.11.self_attn.v_proj.weight]
Loading weights:  99%|█████████▊| 393/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.encoder.layers.11.self_attn.v_proj.weight]
Loading weights:  99%|█████████▉| 394/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.post_layernorm.bias]                      
Loading weights:  99%|█████████▉| 394/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.post_layernorm.bias]
Loading weights:  99%|█████████▉| 395/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.post_layernorm.weight]
Loading weights:  99%|█████████▉| 395/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.post_layernorm.weight]
Loading weights:  99%|█████████▉| 396/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.pre_layrnorm.bias]    
Loading weights:  99%|█████████▉| 396/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.pre_layrnorm.bias]
Loading weights: 100%|█████████▉| 397/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.pre_layrnorm.weight]
Loading weights: 100%|█████████▉| 397/398 [00:00<00:00, 1198.78it/s, Materializing param=vision_model.pre_layrnorm.weight]
Loading weights: 100%|██████████| 398/398 [00:00<00:00, 1198.78it/s, Materializing param=visual_projection.weight]        
Loading weights: 100%|██████████| 398/398 [00:00<00:00, 1198.78it/s, Materializing param=visual_projection.weight]
Loading weights: 100%|██████████| 398/398 [00:00<00:00, 1149.65it/s, Materializing param=visual_projection.weight]
+CLIPModel LOAD REPORT from: patrickjohncyh/fashion-clip
+Key                                  | Status     |  | 
+-------------------------------------+------------+--+-
+vision_model.embeddings.position_ids | UNEXPECTED |  | 
+text_model.embeddings.position_ids   | UNEXPECTED |  | 
+
+Notes:
+- UNEXPECTED	:can be ignored when loading from different task/architecture; not ok if you expect identical arch.
+Warning: You are sending unauthenticated requests to the HF Hub. Please set a HF_TOKEN to enable higher rate limits and faster downloads.
+The image processor of type `CLIPImageProcessor` is now loaded as a fast processor by default, even if the model checkpoint was saved with a slow processor. This is a breaking change and may produce slightly different outputs. To continue using the slow processor, instantiate this class with `use_fast=False`. 
+✅ Team Assignment Model loaded.
+Analysis background task finished.