Wing Lian 24146733db E2e device cuda (#575) ...

* use torch.cuda.current_device() instead of local_rank

* ignore NVML errors for gpu stats

* llama lora packing e2e tests

2023-09-14 22:49:27 -04:00

..

e2e

E2e device cuda (#575)

2023-09-14 22:49:27 -04:00

fixtures

fix test fixture b/c hf trainer tokenization changed (#464)

2023-08-23 04:04:49 -04:00

monkeypatch

Attention mask and position id fixes for packing (#285)

2023-08-12 15:14:56 -04:00

test_data.py

Fix pretraining with iterable/streaming Dataset (#556)

2023-09-13 00:16:40 -04:00

test_dict.py

fix DefaultDict.__or__

2023-08-13 01:15:50 +00:00

test_expand_mask.py

Attention mask and position id fixes for packing (#285)

2023-08-12 15:14:56 -04:00

test_packed_dataset.py

Attention mask and position id fixes for packing (#285)

2023-08-12 15:14:56 -04:00

test_prompt_tokenizers.py

Attention mask and position id fixes for packing (#285)

2023-08-12 15:14:56 -04:00

test_prompters.py

Attention mask and position id fixes for packing (#285)

2023-08-12 15:14:56 -04:00

test_tokenizers.py

simplify load_tokenizer

2023-08-12 18:55:06 -07:00

test_validation.py

recommend padding when using sample packing (#531)

2023-09-06 17:00:21 -04:00