|
I am getting bad performance when evaluating on Huggingface test dataset (GLUE dataset)
|
|
0
|
297
|
October 26, 2021
|
|
Hidden States of OpenAI GPT2 inconsistent
|
|
2
|
284
|
October 25, 2021
|
|
I could not able to use save_pretrained on my T5 Model
|
|
3
|
1061
|
October 25, 2021
|
|
How to save and load fine-tune model
|
|
4
|
24736
|
October 25, 2021
|
|
Issue in the Documentation of transformers for BiET
|
|
2
|
582
|
October 24, 2021
|
|
Multiple Perturbs on Same Trial but no more Checkpoints with PBT using RayTune
|
|
0
|
458
|
October 24, 2021
|
|
ValueError fp16 lm_head.weight
|
|
1
|
774
|
October 24, 2021
|
|
Importance of padding for tokens and same size inputs for transformers
|
|
1
|
690
|
October 22, 2021
|
|
List index out of range when saving
|
|
0
|
379
|
October 21, 2021
|
|
Convert_graph_to_onnx doesn't meet UnicodeDecodeError
|
|
0
|
258
|
October 21, 2021
|
|
Different Behaviors between Tokenizers for Question Answering
|
|
0
|
337
|
October 20, 2021
|
|
Why does ignore_mismatched_sizes increase the number of TfAlbertMainLayer parameters?
|
|
1
|
5728
|
October 20, 2021
|
|
Using sample weights in compute_metrics
|
|
1
|
1067
|
October 20, 2021
|
|
How to fine-tune BERT model for NER if forward method doesn't have "labels" argument
|
|
2
|
940
|
October 20, 2021
|
|
Unable to import model in colab
|
|
0
|
465
|
October 20, 2021
|
|
Running multiple pipelines concurrently
|
|
0
|
794
|
October 19, 2021
|
|
Why TFBlenderbot SmallModel and TFBlenderbot SmallForConditionalGeneration are the same trainable_variables?
|
|
4
|
277
|
October 19, 2021
|
|
Why save_steps should be a round multiple of eval_steps when load_best_model_at_end=True?
|
|
3
|
3789
|
October 18, 2021
|
|
Why do we set input_ids = decoder_input_ids in beam search?
|
|
0
|
317
|
October 18, 2021
|
|
Masking specific token in each input sentence during Masked language modelling
|
|
0
|
1050
|
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
|
1691
|
October 18, 2021
|
|
Bug in BartForConditionalGeneration's intialisation of lm_head
|
|
0
|
264
|
October 16, 2021
|
|
Only one SageMaker TFEvent?
|
|
0
|
456
|
October 15, 2021
|
|
Trainer using Checkpoint makes TPU crash
|
|
4
|
595
|
October 15, 2021
|
|
How hard is it to finetune an ELECTRA model for multihead regression & classification?
|
|
0
|
310
|
October 15, 2021
|
|
How to convert model output logits into string sentences during training to check what the model is outputting?
|
|
3
|
5260
|
October 14, 2021
|
|
No loss being logged, when running MLM script (Colab)
|
|
11
|
2618
|
October 14, 2021
|
|
Encoder Decoder Loss
|
|
6
|
9038
|
October 14, 2021
|
|
Ways to reduce memory consumption in Q&A tasks without damage (or at least, not that much) the accuracy?
|
|
0
|
438
|
October 13, 2021
|
|
How DeepSpeed interacts with Trainer optimizer
|
|
1
|
1202
|
October 13, 2021
|