Training step 20000

Update model card (step 19399)

Step 19399: loss=0.1888

Update model card (step 18774)

Step 18774: loss=0.1893

Update model card (step 18149)

Step 18149: loss=0.1898

Training step 18000

Update model card (step 17524)

Step 17524: loss=0.1904

Update model card (step 16899)

Step 16899: loss=0.1911

Update model card (step 16274)

Step 16274: loss=0.1918

Training step 16000

Update model card (step 15649)

Step 15649: loss=0.1926

Update model card (step 15024)

Step 15024: loss=0.1935

Update model card (step 14399)

Step 14399: loss=0.1945

Training step 14000

Update model card (step 13774)

Step 13774: loss=0.1956

Update model card (step 13149)

Step 13149: loss=0.1968

Update model card (step 12524)

Step 12524: loss=0.1982

Training step 12000

Update model card (step 11899)

Step 11899: loss=0.1997

Update model card (step 11274)

Step 11274: loss=0.2015

Update model card (step 10649)

Step 10649: loss=0.2034

Update model card (step 10024)

Step 10024: loss=0.2056

Training step 10000

Training step 8774

Update model card (step 8750)

Step 8750: loss=0.2074

Update model card (step 8125)

Step 8125: loss=0.2097

Training step 8000

Update model card (step 7500)

Step 7500: loss=0.2120

Update model card (step 6875)

Step 6875: loss=0.2130

Update model card (step 6250)

Step 6250: loss=0.2141