# NLP chapter 3 question **URL:** \ **Category:** Beginners\ **Created:** [April 1, 2025, 2:28pm UTC](https://discuss.huggingface.co/t/nlp-chapter-3-question/148420 "2025-04-01T14:28:15Z")\ **Posts on this page:** 6\ **Page:** 1
**Author:** ![Rtdon8363737](https://avatars.discourse-cdn.com/v4/letter/r/6f9a4e/32.png) [@Rtdon8363737](https://discuss.huggingface.co/u/Rtdon8363737)\ **Post date:** [April 1, 2025, 2:28pm UTC](https://discuss.huggingface.co/t/nlp-chapter-3-question/148420/1 "2025-04-01T14:28:16Z")
![Screenshot 2025-04-01 195443](https://us1.discourse-cdn.com/hellohellohello/original/3X/a/1/a1418bed003690b4964efd7a9eedd3174cb299ff.png) i tried import adam\_v2, as well as just opt object but getting error ValueError: Could not interpret optimizer identifier: \ ---
**Author:** ![John6666](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/john6666/32/27664_2.png) [@John6666](https://discuss.huggingface.co/u/John6666)\ **Post date:** [April 1, 2025, 3:19pm UTC](https://discuss.huggingface.co/t/nlp-chapter-3-question/148420/2 "2025-04-01T15:19:41Z")
Apparently, there is a version incompatibility issue between Keras and TensorFlow that has been around for a long time. The solution differs for each version… For more information, search for the version you want to use… > > > \`\`\`python > import tensorflow as tf > from datasets import load\_dataset > from tran…sformers import AutoTokenizer, TFAutoModelForSequenceClassification, DataCollatorWithPadding > from tensorflow.keras.optimizers import Adam > from tensorflow.keras.optimizers.schedules import PolynomialDecay > from tensorflow.keras.losses import SparseCategoricalCrossentropy > > def prepare\_imdb\_dataset(tokenizer): > """ > Prepares the IMDB dataset for training and validation. > > Args: > tokenizer: The tokenizer to use for text tokenization. > > Returns: > A tuple containing the tokenized training and validation datasets. > """ > imdb = load\_dataset("imdb") > train\_set = imdb\['train'\].map(lambda x: tokenizer(x\['text'\], truncation=True), batched=True) > test\_set = imdb\['test'\].map(lambda x: tokenizer(x\['text'\], truncation=True), batched=True) > return train\_set, test\_set > > tokenizer = AutoTokenizer.from\_pretrained("distilbert-base-uncased") > model = TFAutoModelForSequenceClassification.from\_pretrained("distilbert-base-uncased", num\_labels=2) > > train\_set, test\_set = prepare\_imdb\_dataset(tokenizer) > > data\_collator = DataCollatorWithPadding(tokenizer=tokenizer, return\_tensors="tf") > > tf\_train\_dataset = train\_set.to\_tf\_dataset( > columns=\["attention\_mask", "input\_ids"\], > label\_cols=\["label"\], > shuffle=True, > collate\_fn=data\_collator, > batch\_size=8, > ) > > tf\_validation\_dataset = test\_set.to\_tf\_dataset( > columns=\["attention\_mask", "input\_ids"\], > label\_cols=\["label"\], > shuffle=False, > collate\_fn=data\_collator, > batch\_size=8, > ) > > batch\_size = 16 > num\_epochs = 1 > num\_train\_steps = len(tf\_train\_dataset) \* num\_epochs > lr\_scheduler = PolynomialDecay( > initial\_learning\_rate=5e-5, end\_learning\_rate=0.0, decay\_steps=num\_train\_steps > ) > > optimizer = Adam(learning\_rate=lr\_scheduler) > loss = SparseCategoricalCrossentropy(from\_logits=True) > model.compile(optimizer=optimizer, loss=loss, metrics=\["accuracy"\]) > > model.fit(tf\_train\_dataset, validation\_data=tf\_validation\_dataset, epochs=5) > > \`\`\` > > \`\`\` > Some weights of the PyTorch model were not used when initializing the TF 2.0 model TFDistilBertForSequenceClassification: \['vocab\_layer\_norm.weight', 'vocab\_transform.weight', 'vocab\_projector.bias', 'vocab\_transform.bias', 'vocab\_layer\_norm.bias'\] > \- This IS expected if you are initializing TFDistilBertForSequenceClassification from a PyTorch model trained on another task or with another architecture (e.g. initializing a TFBertForSequenceClassification model from a BertForPreTraining model). > \- This IS NOT expected if you are initializing TFDistilBertForSequenceClassification from a PyTorch model that you expect to be exactly identical (e.g. initializing a TFBertForSequenceClassification model from a BertForSequenceClassification model). > Some weights or buffers of the TF 2.0 model TFDistilBertForSequenceClassification were not initialized from the PyTorch model and are newly initialized: \['pre\_classifier.weight', 'pre\_classifier.bias', 'classifier.weight', 'classifier.bias'\] > You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference. > Map: 100% >  25000/25000 \[00:23\<00:00, 1086.84 examples/s\] > Map: 100% >  25000/25000 \[00:20\<00:00, 1304.86 examples/s\] > \--------------------------------------------------------------------------- > ValueError Traceback (most recent call last) > \[\\](https://localhost:8080/#) in \() > 53 optimizer = Adam(learning\_rate=lr\_scheduler) > 54 loss = SparseCategoricalCrossentropy(from\_logits=True) > \---\> 55 model.compile(optimizer=optimizer, loss=loss, metrics=\["accuracy"\]) > 56 > 57 model.fit(tf\_train\_dataset, validation\_data=tf\_validation\_dataset, epochs=5) > > 2 frames > \[/usr/local/lib/python3.10/dist-packages/tf\_keras/src/optimizers/\_\_init\_\_.py\](https://localhost:8080/#) in get(identifier, \*\*kwargs) > 332 ) > 333 else: > \--\> 334 raise ValueError( > 335 f"Could not interpret optimizer identifier: {identifier}" > 336 ) > > ValueError: Could not interpret optimizer identifier: \ > \`\`\` > [@Pretrain model not accepting optimizer](https://discuss.huggingface.co/t/pretrain-model-not-accepting-optimizer/76209): > > For this code, model = TFAutoModelForSequenceClassification.from\_pretrained(“bert-base-cased”, num\_labels=3) model.compile( optimizer = tf.keras.optimizers.Adam(learning\_rate=5e-5) ) This gives me this error ValueError: Could not interpret optimizer identifier: \ what to do? I am using google colab > ---
**Author:** ![Rtdon8363737](https://avatars.discourse-cdn.com/v4/letter/r/6f9a4e/32.png) [@Rtdon8363737](https://discuss.huggingface.co/u/Rtdon8363737)\ **Post date:** [April 4, 2025, 6:10pm UTC](https://discuss.huggingface.co/t/nlp-chapter-3-question/148420/3 "2025-04-04T18:10:56Z")
it works for me now after “”" setting these to tackle: ValueError: Could not interpret optimizer identifier: \ “”" !pip install --upgrade transformers !pip install tf-keras import os os.environ[‘TF\_USE\_LEGACY\_KERAS’] = ‘1’ ---
**Author:** ![bhuvnn](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/bhuvnn/32/44844_2.png) [@bhuvnn](https://discuss.huggingface.co/u/bhuvnn)\ **Post date:** [April 5, 2025, 10:22am UTC](https://discuss.huggingface.co/t/nlp-chapter-3-question/148420/4 "2025-04-05T10:22:57Z")
ValueError Traceback (most recent call last) in \() 1 optimizer = Adam(learning\_rate=2e-5) ----\> 2 model.compile(loss=tf.keras.losses.SparseCategoricalCrossentropy(from\_logits=True), 3 optimizer=opt, 4 metrics=[“accuracy”]) 5 tf.keras.backend.set\_value(model.optimizer.learning\_rate, 2e-5) /usr/local/lib/python3.10/dist-packages/transformers/modeling\_tf\_utils.py in compile(self, optimizer, loss, metrics, loss\_weights, weighted\_metrics, run\_eagerly, steps\_per\_execution, \*\*kwargs) 1561 # This argument got renamed, we need to support both versions 1562 if “steps\_per\_execution” in parent\_args: → 1563 super().compile( 1564 optimizer=optimizer, 1565 loss=loss, /usr/local/lib/python3.10/dist-packages/tf\_keras/src/utils/traceback\_utils.py in error\_handler(\*args, \*\*kwargs) 68 # To get the full stack trace, call: 69 # `tf.debugging.disable_traceback_filtering()` —\> 70 raise e.with\_traceback(filtered\_tb) from None 71 finally: 72 del filtered\_tb /usr/local/lib/python3.10/dist-packages/tf\_keras/src/optimizers/ **init**.py in get(identifier, \*\*kwargs) 333 ) 334 else: → 335 raise ValueError( 336 f"Could not interpret optimizer identifier: {identifier}" 337 ) ValueError: Could not interpret optimizer identifier: \ i am also facing a similiar kind of error ---
**Author:** ![John6666](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/john6666/32/27664_2.png) [@John6666](https://discuss.huggingface.co/u/John6666)\ **Post date:** [April 5, 2025, 11:11am UTC](https://discuss.huggingface.co/t/nlp-chapter-3-question/148420/5 "2025-04-05T11:11:13Z")
It seems that there are different errors for each version… > [@Pretrain model not accepting optimizer](https://discuss.huggingface.co/t/pretrain-model-not-accepting-optimizer/76209/19?page=2): > > I have the same problem and still getting same error. I tried everything, but it doesn’t work. I am working on a project and I am short on time. Please help. > > > I followed Tutorial A3: \[Text Classification with Hugging Face Transformers\]. I …tried to implement the 'bert-base-multilingual-uncased' model from HuggingFace. When using the code, model = t\_mod.get\_classifier(), it generates an error message. This code was working perfectly some days ago. However, now it produces the following error: > > \*\*Error\*\* > \--------------------------------------------------------------------------- > > ValueError Traceback (most recent call last) > > \[\\](https://localhost:8080/#) in \() > \----\> 1 model = t\_mod.get\_classifier() > > 3 frames > > \[/usr/local/lib/python3.10/dist-packages/tf\_keras/src/optimizers/\_\_init\_\_.py\](https://localhost:8080/#) in get(identifier, \*\*kwargs) > 332 ) > 333 else: > \--\> 334 raise ValueError( > 335 f"Could not interpret optimizer identifier: {identifier}" > 336 ) > > ValueError: Could not interpret optimizer identifier: \ ---
**Author:** ![system](https://us1.discourse-cdn.com/hellohellohello/original/2X/d/de4155eb4aa4108ecb32a1389d7cc37ae69f88b7.png) [@system](https://discuss.huggingface.co/u/system)\ **Post date:** [April 5, 2025, 11:11pm UTC](https://discuss.huggingface.co/t/nlp-chapter-3-question/148420/6 "2025-04-05T23:11:54Z")
This topic was automatically closed 12 hours after the last reply. New replies are no longer allowed.