After finetuning my dataset using keras, I tried to fit the model to lora and this was the error I encountered:
TypeError Traceback (most recent call last) Cell In[12], line 1 ----> 1 gemma_lm.fit(data, epochs=10, batch_size=32)
File :240, in sentencepiece_tokenize_op(sp_handle, input, nbest_size, alpha, add_bos, add_eos, reverse, out_type, Tsplits, return_nbest, name)
TypeError: Exception encountered when calling GemmaTokenizer.call().
Input 'input' of 'SentencepieceTokenizeOp' Op has type float32 that does not match expected type of string.
Arguments received by GemmaTokenizer.call():
• inputs=tf.Tensor(shape=(None,), dtype=float32)
• args=<class 'inspect._empty'>
• training=None
• kwargs=<class 'inspect._empty'>`your text`
Please help.
I tried adjusting the epochs to 10, and batch_size to 32.
