asahi417 / lmppl Goto Github PK

IndexError                                Traceback (most recent call last)
Cell In[58], line 5
      3 scorer = MaskedLM('/data/user/home/nchendri/LongRun/')
      4 text =  dsMap['test']['text']
----> 5 ppl = scorer.get_perplexity(text, batch=32)
      6 print(ppl)
      7 print(list(zip(text, ppl)))

Cell In[57], line 162, in MaskedLM.get_perplexity(self, input_texts, batch)
    159     return _e
    161 if self.max_length is not None:
--> 162     data.append([encode_mask(i) for i in range(min(self.max_length - len(self.sp_token_prefix), len(x)))])
    163 else:
    164     data.append([encode_mask(i) for i in range(len(x))])

Cell In[57], line 162, in <listcomp>(.0)
    159     return _e
    161 if self.max_length is not None:
--> 162     data.append([encode_mask(i) for i in range(min(self.max_length - len(self.sp_token_prefix), len(x)))])
    163 else:
    164     data.append([encode_mask(i) for i in range(len(x))])

Cell In[57], line 157, in MaskedLM.get_perplexity.<locals>.encode_mask(mask_position)
    155 # add the correct token id as the label
    156 label = [PAD_TOKEN_LABEL_ID] * _e['input_ids'].shape[1]
--> 157 label[mask_position + len(self.sp_token_prefix)] = masked_token_id
    158 _e['labels'] = torch.tensor([label], dtype=torch.long)
    159 return _e

IndexError: list assignment index out of range

import lmppl

scorer = lmppl.EncoderDecoderLM("/home/racball/models--flan-t5-xxl",device_map='auto',low_cpu_mem_usage=True)

inputs = [
    'sentiment classification: I dropped my laptop on my knee, and someone stole my coffee.',
    'sentiment classification: I dropped my laptop on my knee, and someone stole my coffee.'
]
outputs = [
    'I am happy.',
    'I am sad.'
]
ppl = scorer.get_perplexity(input_texts=inputs, output_texts=outputs)
print(list(zip(outputs, ppl)))

RuntimeError                              Traceback (most recent call last)
Cell In[6], line 14
      6 inputs = [
      7     'sentiment classification: I dropped my laptop on my knee, and someone stole my coffee.',
      8     'sentiment classification: I dropped my laptop on my knee, and someone stole my coffee.'
      9 ]
     10 outputs = [
     11     'I am happy.',
     12     'I am sad.'
     13 ]
---> 14 ppl = scorer.get_perplexity(input_texts=inputs, output_texts=outputs)
     15 print(list(zip(outputs, ppl)))
     16 # >>> [
     17 #   ('I am happy.', 4138.748977714201),
     18 #   ('I am sad.', 2991.629250051472)
     19 # ]
     20 # print(f"prediction: {outputs[ppl.index(min(ppl))]}")
     21 # >>> "prediction: I am sad."

File [/nobackup/racball/miniconda3/envs/bertviz/lib/python3.10/site-packages/lmppl/ppl_encoder_decoder_lm.py:157](https://vscode-remote+ssh-002dremote-002bash.vscode-resource.vscode-cdn.net/nobackup/racball/miniconda3/envs/bertviz/lib/python3.10/site-packages/lmppl/ppl_encoder_decoder_lm.py:157), in EncoderDecoderLM.get_perplexity(self, input_texts, output_texts, batch)
    155 # model run & loss conversion into likelihood
    156 valid_length = (model_inputs["labels"] != PAD_TOKEN_LABEL_ID).sum(dim=-1)
--> 157 output = self.model(**{k: v.to(self.device) for k, v in model_inputs.items()})
    158 loss = self.loss_fct(output['logits'].view(-1, self.config.vocab_size), model_inputs["labels"].view(-1))
    159 loss = loss.view(len(output['logits']), -1)

File [/nobackup/racball/miniconda3/envs/bertviz/lib/python3.10/site-packages/torch/nn/modules/module.py:1194](https://vscode-remote+ssh-002dremote-002bash.vscode-resource.vscode-cdn.net/nobackup/racball/miniconda3/envs/bertviz/lib/python3.10/site-packages/torch/nn/modules/module.py:1194), in Module._call_impl(self, *input, **kwargs)
   1190 # If we don't have any hooks, we want to skip the rest of the logic in
   1191 # this function, and just call forward.
   1192 if not (self._backward_hooks or self._forward_hooks or self._forward_pre_hooks or _global_backward_hooks
   1193         or _global_forward_hooks or _global_forward_pre_hooks):
-> 1194     return forward_call(*input, **kwargs)
   1195 # Do not call functions when jit is used
   1196 full_backward_hooks, non_full_backward_hooks = [], []

File [/nobackup/racball/miniconda3/envs/bertviz/lib/python3.10/site-packages/accelerate/hooks.py:158](https://vscode-remote+ssh-002dremote-002bash.vscode-resource.vscode-cdn.net/nobackup/racball/miniconda3/envs/bertviz/lib/python3.10/site-packages/accelerate/hooks.py:158), in add_hook_to_module..new_forward(*args, **kwargs)
    156         output = old_forward(*args, **kwargs)
    157 else:
--> 158     output = old_forward(*args, **kwargs)
    159 return module._hf_hook.post_forward(module, output)

File [/nobackup/racball/miniconda3/envs/bertviz/lib/python3.10/site-packages/transformers/models/t5/modeling_t5.py:1696](https://vscode-remote+ssh-002dremote-002bash.vscode-resource.vscode-cdn.net/nobackup/racball/miniconda3/envs/bertviz/lib/python3.10/site-packages/transformers/models/t5/modeling_t5.py:1696), in T5ForConditionalGeneration.forward(self, input_ids, attention_mask, decoder_input_ids, decoder_attention_mask, head_mask, decoder_head_mask, cross_attn_head_mask, encoder_outputs, past_key_values, inputs_embeds, decoder_inputs_embeds, labels, use_cache, output_attentions, output_hidden_states, return_dict)
   1694 if labels is not None:
   1695     loss_fct = CrossEntropyLoss(ignore_index=-100)
...
   3024 if size_average is not None or reduce is not None:
   3025     reduction = _Reduction.legacy_get_string(size_average, reduce)
-> 3026 return torch._C._nn.cross_entropy_loss(input, target, weight, _Reduction.get_enum(reduction), ignore_index, label_smoothing)

RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cuda:7 and cuda:0! (when checking argument for argument target in method wrapper_nll_loss_forward)

>>> import lmppl
>>> scorer = lmppl.LM('gpt2')
Using pad_token, but it is not set yet.
>>> text = [
    'sentiment classification: I dropped my laptop on my knee, and someone stole my coffee. I am happy.',
    'sentiment classification: I dropped my laptop on my knee, and someone stole my coffee. I am sad.'
]
>>> ppl = scorer.get_perplexity(text)
100%|██████████| 1/1 [00:00<00:00,  3.03it/s]
>>> ppl
[4.2328431180493815e+43, 4.732356477497072e+43] # <-- They are quite large, there seems to be something wrong.