Hello! I am trying to initialize the encoder in the EncoderDecoderModel with AraBERT (a BERT model trained on Arabic data), and the decoder with GPT-2 for Arabic to English Machine Translation. Here’s the model config after some changes I’ve done on it:
EncoderDecoderConfig {
"decoder": {
"_name_or_path": "gpt2",
"activation_function": "gelu_new",
"add_cross_attention": true,
"architectures": [
"GPT2LMHeadModel"
],
"attn_pdrop": 0.1,
"bad_words_ids": null,
"bos_token_id": 50256,
"chunk_size_feed_forward": 0,
"cross_attention_hidden_size": null,
"decoder_start_token_id": null,
"diversity_penalty": 0.0,
"do_sample": false,
"early_stopping": false,
"embd_pdrop": 0.1,
"encoder_no_repeat_ngram_size": 0,
"eos_token_id": 50256,
"exponential_decay_length_penalty": null,
"finetuning_task": null,
"forced_bos_token_id": null,
"forced_eos_token_id": null,
"id2label": {
"0": "LABEL_0",
"1": "LABEL_1"
},
"initializer_range": 0.02,
"is_decoder": true,
"is_encoder_decoder": false,
"label2id": {
"LABEL_0": 0,
"LABEL_1": 1
},
"layer_norm_epsilon": 1e-05,
"length_penalty": 1.0,
"max_length": 20,
"min_length": 0,
"model_type": "gpt2",
"n_ctx": 1024,
"n_embd": 512,
"n_head": 12,
"n_inner": null,
"n_layer": 12,
"n_positions": 1024,
"no_repeat_ngram_size": 0,
"num_beam_groups": 1,
"num_beams": 1,
"num_return_sequences": 1,
"output_attentions": false,
"output_hidden_states": false,
"output_scores": false,
"pad_token_id": null,
"prefix": null,
"problem_type": null,
"pruned_heads": {},
"remove_invalid_values": false,
"reorder_and_upcast_attn": false,
"repetition_penalty": 1.0,
"resid_pdrop": 0.1,
"return_dict": true,
"return_dict_in_generate": false,
"scale_attn_by_inverse_layer_idx": false,
"scale_attn_weights": true,
"sep_token_id": null,
"summary_activation": null,
"summary_first_dropout": 0.1,
"summary_proj_to_labels": true,
"summary_type": "cls_index",
"summary_use_proj": true,
"task_specific_params": {
"text-generation": {
"do_sample": true,
"max_length": 50
}
},
"temperature": 1.0,
"tie_encoder_decoder": false,
"tie_word_embeddings": true,
"tokenizer_class": null,
"top_k": 50,
"top_p": 1.0,
"torch_dtype": null,
"torchscript": false,
"transformers_version": "4.19.2",
"typical_p": 1.0,
"use_bfloat16": false,
"use_cache": true,
"vocab_size": 64000
},
"decoder_start_token_id": 2,
"encoder": {
"_name_or_path": "aubmindlab/bert-base-arabertv02",
"add_cross_attention": false,
"architectures": [
"BertForMaskedLM"
],
"attention_probs_dropout_prob": 0.1,
"bad_words_ids": null,
"bos_token_id": null,
"chunk_size_feed_forward": 0,
"classifier_dropout": null,
"cross_attention_hidden_size": null,
"decoder_start_token_id": null,
"diversity_penalty": 0.0,
"do_sample": false,
"early_stopping": false,
"encoder_no_repeat_ngram_size": 0,
"eos_token_id": 50256,
"exponential_decay_length_penalty": null,
"finetuning_task": null,
"forced_bos_token_id": null,
"forced_eos_token_id": null,
"hidden_act": "gelu",
"hidden_dropout_prob": 0.1,
"hidden_size": 768,
"id2label": {
"0": "LABEL_0",
"1": "LABEL_1"
},
"initializer_range": 0.02,
"intermediate_size": 3072,
"is_decoder": false,
"is_encoder_decoder": false,
"label2id": {
"LABEL_0": 0,
"LABEL_1": 1
},
"layer_norm_eps": 1e-12,
"length_penalty": 1.0,
"max_length": 20,
"max_position_embeddings": 512,
"min_length": 0,
"model_type": "bert",
"no_repeat_ngram_size": 0,
"num_attention_heads": 12,
"num_beam_groups": 1,
"num_beams": 1,
"num_hidden_layers": 12,
"num_return_sequences": 1,
"output_attentions": false,
"output_hidden_states": false,
"output_scores": false,
"pad_token_id": null,
"position_embedding_type": "absolute",
"prefix": null,
"problem_type": null,
"pruned_heads": {},
"remove_invalid_values": false,
"repetition_penalty": 1.0,
"return_dict": true,
"return_dict_in_generate": false,
"sep_token_id": null,
"task_specific_params": null,
"temperature": 1.0,
"tie_encoder_decoder": false,
"tie_word_embeddings": true,
"tokenizer_class": null,
"top_k": 50,
"top_p": 1.0,
"torch_dtype": null,
"torchscript": false,
"transformers_version": "4.19.2",
"type_vocab_size": 2,
"typical_p": 1.0,
"use_bfloat16": false,
"use_cache": true,
"vocab_size": 64000
},
"eos_token_id": 50256,
"is_encoder_decoder": true,
"max_length": 512,
"model_type": "encoder-decoder",
"pad_token_id": 0,
"transformers_version": null,
"vocab_size": 64000
}
The configurations I’ve changed are as follows:
model.config.decoder_start_token_id = ar_tokenizer.cls_token_id
model.config.vocab_size = model.config.decoder.vocab_size
model.config.eos_token_id = model.config.decoder.eos_token_id
model.config.encoder.pad_token_id = model.config.pad_token_id
model.config.encoder.eos_token_id = model.config.eos_token_id
model.config.decoder.n_embd = 512
model.config.decoder.vocab_size = 64000
model.config.pad_token_id = 0
My pre-processing function:
max_input_length = 128
max_target_length = 128
source_lang = "ar"
target_lang = "en"
def preprocess_function(examples):
inputs = [ex[source_lang] for ex in examples["translation"]]
targets = [ex[target_lang] for ex in examples["translation"]]
model_inputs = ar_tokenizer(inputs, max_length=max_input_length, truncation=True, padding=True)
# Setup the tokenizer for targets
with ar_tokenizer.as_target_tokenizer():
labels = en_tokenizer(targets, max_length=max_target_length, truncation=True, padding=True)
model_inputs["labels"] = labels["input_ids"]
return model_inputs
tokenized_dataset = train_test.map(preprocess_function, batched=True)
However, when I start training, I get this error message:
ValueError: expected sequence of length 128 at dim 1 (got 118)
What should I change in my code for it to work?