|
How to generate a sequence using inputs_embeds instead of input_ids?
|
|
2
|
210
|
October 18, 2021
|
|
Why save_steps should be a round multiple of eval_steps when load_best_model_at_end=True?
|
|
3
|
75
|
October 18, 2021
|
|
Why do we set input_ids = decoder_input_ids in beam search?
|
|
0
|
39
|
October 18, 2021
|
|
Error when trying Deberta for tensorflow version, Can't import the model
|
|
1
|
40
|
October 18, 2021
|
|
Masking specific token in each input sentence during Masked language modelling
|
|
0
|
40
|
October 18, 2021
|
|
How to suppress HuggingFace logging warning: "Setting `pad_token_id` to `eos_token_id`:{eos_token_id} for open-end generation."
|
|
0
|
33
|
October 18, 2021
|
|
How to check or manually control the learning rate used in training?
|
|
0
|
49
|
October 17, 2021
|
|
Bug in BartForConditionalGeneration's intialisation of lm_head
|
|
0
|
34
|
October 16, 2021
|
|
Limit predictions computing to single CPU core?
|
|
0
|
38
|
October 16, 2021
|
|
New pipeline for zero-shot text classification
|
|
94
|
26343
|
October 15, 2021
|
|
Only one SageMaker TFEvent?
|
|
0
|
25
|
October 15, 2021
|
|
Trainer using Checkpoint makes TPU crash
|
|
4
|
40
|
October 15, 2021
|
|
How hard is it to finetune an ELECTRA model for multihead regression & classification?
|
|
0
|
30
|
October 15, 2021
|
|
Some weights of BertModel were not initialized from the model checkpoint
|
|
2
|
792
|
October 15, 2021
|
|
How to convert model output logits into string sentences during training to check what the model is outputting?
|
|
3
|
59
|
October 14, 2021
|
|
No loss being logged, when running MLM script (Colab)
|
|
11
|
205
|
October 14, 2021
|
|
Encoder Decoder Loss
|
|
6
|
458
|
October 14, 2021
|
|
Ways to reduce memory consumption in Q&A tasks without damage (or at least, not that much) the accuracy?
|
|
0
|
27
|
October 13, 2021
|
|
Logging & Experiment tracking with W&B
|
|
55
|
4563
|
October 13, 2021
|
|
How DeepSpeed interacts with Trainer optimizer
|
|
1
|
47
|
October 13, 2021
|
|
Gradient_checkpointing = True results in error
|
|
0
|
35
|
October 13, 2021
|
|
Next sentence prediction on custom model
|
|
2
|
296
|
October 12, 2021
|
|
Good word list in generate function
|
|
0
|
26
|
October 12, 2021
|
|
How do I change the classification head of a model?
|
|
18
|
3623
|
October 12, 2021
|
|
Decoding the predicted output array in distilbertbase uncased model for NER
|
|
1
|
76
|
October 11, 2021
|
|
Text format for language modeling
|
|
5
|
89
|
October 10, 2021
|
|
Log Perplexity using Trainer
|
|
2
|
162
|
October 9, 2021
|
|
Overlapping data between pre-training and fine-tuning stages
|
|
0
|
32
|
October 8, 2021
|
|
Stop sequence for few-shot learning with GPT-J on HF API
|
|
0
|
30
|
October 8, 2021
|
|
Train T5 from scratch
|
|
3
|
749
|
October 8, 2021
|
