|
Trainer.evaluate()
|
|
3
|
6878
|
May 11, 2021
|
|
How to set early stopping when running run_summarization.py
|
|
3
|
731
|
May 11, 2021
|
|
Wav2vec2-large-xlsr-53 for non-listed low resource language
|
|
1
|
492
|
May 11, 2021
|
|
Generate text on multiple GPU
|
|
2
|
1306
|
May 10, 2021
|
|
BERT model trained on small corpus (English)?
|
|
0
|
334
|
May 8, 2021
|
|
Trainer.train() padding error but it was working before
|
|
0
|
480
|
May 7, 2021
|
|
Text wrangling before classification
|
|
0
|
236
|
May 7, 2021
|
|
Tensorflow TPUStrategy and model.generate: Does it work?
|
|
0
|
224
|
May 7, 2021
|
|
Using BERT for labels categorization
|
|
0
|
993
|
May 6, 2021
|
|
Trainer class and compute_metrics
|
|
0
|
336
|
May 6, 2021
|
|
GPT-GPT encoder decoder
|
|
0
|
290
|
May 4, 2021
|
|
Trainer Question Answering evaluation metrics
|
|
4
|
3396
|
May 3, 2021
|
|
Training of new ELECTRA or ConvBERT language model possible?
|
|
0
|
262
|
May 3, 2021
|
|
How to run transformer model like t5-small, facebook/bart-large-cnn without loading pretrained weights?
|
|
0
|
426
|
May 3, 2021
|
|
Fine Tuning GPT2 for machine translation
|
|
1
|
4795
|
May 2, 2021
|
|
DataCollator vs. Tokenizers
|
|
1
|
3818
|
May 1, 2021
|
|
Dataset for training BlenderBot
|
|
1
|
2504
|
May 1, 2021
|
|
Could I inference the Encoder-Decoder model without specify "decoder_input_ids"?
|
|
4
|
2467
|
May 1, 2021
|
|
How to only finetune the last layer of ALBERT?
|
|
4
|
4083
|
April 30, 2021
|
|
TFTrainer.train() stucks into infinite loop
|
|
0
|
407
|
April 29, 2021
|
|
Marian MT half precision inference
|
|
0
|
413
|
April 29, 2021
|
|
Adding more information on Trainer state
|
|
2
|
310
|
April 29, 2021
|
|
How to specify sequence length when using "feature-extraction"
|
|
3
|
1305
|
April 28, 2021
|
|
Eval freezes on local multi GPU Deepspeed run
|
|
4
|
2916
|
April 28, 2021
|
|
RuntimeError: CUDA error: device-side assert triggered
|
|
1
|
2508
|
April 28, 2021
|
|
[Deepspeed] ZeRO-Infinity integration released and config changes
|
|
2
|
2304
|
April 28, 2021
|
|
Append a linear layer on top of the vanilla Electra model
|
|
1
|
376
|
April 27, 2021
|
|
Getting random results with BERT
|
|
3
|
917
|
April 27, 2021
|
|
[Deepspeed ZeRO-Infinity] looking for NVMe device benchmarks
|
|
0
|
1190
|
April 26, 2021
|
|
Large max differences between single input processing and batching with Bert and T5
|
|
0
|
556
|
April 26, 2021
|