This model has 1 file scanned as unsafe.
- copy_teacher_modules=_(_lm_head___False)_, dropout=0, learning_rate=4e-05, warmup_ratio=0, weight_decay=0
- copy_teacher_modules=_(_lm_head___False)_, dropout=0, learning_rate=4e-05, warmup_ratio=0.25, weight_decay=0
- copy_teacher_modules=_(_lm_head___True)_, dropout=0, learning_rate=4e-05, warmup_ratio=0, weight_decay=0.01
- copy_teacher_modules=_(_lm_head___True)_, dropout=0, learning_rate=4e-05, warmup_ratio=0, weight_decay=0
- copy_teacher_modules=_(_lm_head___True)_, dropout=0, learning_rate=4e-05, warmup_ratio=0.25, weight_decay=0
- copy_teacher_modules=_(_transformer.wte___True)__(_transformer.wpe____False_)__(_lm_head___True)_, dropout=0, learning_rate=0.0004, warmup_ratio=0, weight_decay=0
- copy_teacher_modules=_(_transformer.wte___True)__(_transformer.wpe____False_)__(_lm_head___True)_, dropout=0, learning_rate=0.0004, warmup_ratio=0.25, weight_decay=0
- copy_teacher_modules=_(_transformer.wte___True)__(_transformer.wpe____True_)__(_lm_head___True)_, dropout=0, learning_rate=4e-05, warmup_ratio=0, weight_decay=0.01
- copy_teacher_modules=_(_transformer.wte___True)__(_transformer.wpe____True_)__(_lm_head___True)_, dropout=0, learning_rate=4e-05, warmup_ratio=0, weight_decay=0
- copy_teacher_modules=_(_transformer.wte___True)__(_transformer.wpe____True_)__(_lm_head___True)_, dropout=0, learning_rate=4e-05, warmup_ratio=0.25, weight_decay=0
- copy_teacher_modules=__, dropout=0, learning_rate=0.0004, warmup_ratio=0, weight_decay=0.01
- copy_teacher_modules=__, dropout=0, learning_rate=0.0004, warmup_ratio=0, weight_decay=0
- copy_teacher_modules=__, dropout=0, learning_rate=0.0004, warmup_ratio=0.25, weight_decay=0
- copy_teacher_modules=__, dropout=0, learning_rate=0.004, warmup_ratio=0, weight_decay=0
- copy_teacher_modules=__, dropout=0, learning_rate=4e-05, warmup_ratio=0, weight_decay=0.01
- copy_teacher_modules=__, dropout=0, learning_rate=4e-05, warmup_ratio=0, weight_decay=0
- copy_teacher_modules=__, dropout=0, learning_rate=4e-05, warmup_ratio=0.25, weight_decay=0