I will appreciate if someone can help me with UNQ_C6.

I’m getting the error

```
Output must be a tuple of size 2 containing a integer and a float number
Expected output: [7283, -9.929085731506348]
0 Tests passed
2 Tests failed
```

I checked the thread with others having the same issues. I followed to steps, but I must be missing something, as I’m still getting the error.

I read the following, from what I understand let’s assume we use output[0,3,:] we will get the log probability of length vocab size for batch 0 and 3rd word.

```
The log probabilities output will have the shape: (batch size, decoder length, vocab size). It will contain log probabilities for each token in the cur_output_tokens plus 1 for the start symbol introduced by the ShiftRight in the preattention decoder. For example, if cur_output_tokens is [1, 2, 5], the model will output an array of log probabilities each for tokens 0 (start symbol), 1, 2, and 5. To generate the next symbol, you just want to get the log probabilities associated with the last token (i.e. token 5 at index 3). You can slice the model output at [0, 3, :] to get this. It will be up to you to generalize this for any length of cur_output_tokens
```

Any help will be appreciated.

My id is : nkaxkxugvues