3 contributors

History: 16 commits

elishowk

Automatic correction of README.md metadata. Contact [email protected] for any question

fea8231 over 3 years ago

configs
Dump 187k steps, acc 0.6574 over 3 years ago
mc4
Dump 187k steps, acc 0.6574 over 3 years ago
outputs
Step... (249001/250000 | Loss: 1.678702473640442, Acc: 0.660828173160553): 76%|██████████████████▏ | 189999/250000 [97:45:10<29:36:08, 1.78s/it] over 3 years ago
.gitattributes

875 Bytes

Step... (200001/250000 | Loss: 1.6965291500091553, Acc: 0.6575480699539185): 56%|████████████▎ | 140093/250000 [71:33:45<52:41:15, 1.73s/it] over 3 years ago
.gitignore

39 Bytes

Step... (200001/250000 | Loss: 1.6965291500091553, Acc: 0.6575480699539185): 56%|████████████▎ | 140093/250000 [71:33:45<52:41:15, 1.73s/it] over 3 years ago
README.md

1.36 kB

Automatic correction of README.md metadata. Contact [email protected] for any question over 3 years ago
config.json

618 Bytes

Dump 187k steps, acc 0.6574 over 3 years ago
convert.py

876 Bytes

Dump 187k steps, acc 0.6574 over 3 years ago
flax_model.msgpack

250 MB
LFS

Step... (249001/250000 | Loss: 1.678702473640442, Acc: 0.660828173160553): 76%|██████████████████▏ | 189999/250000 [97:45:10<29:36:08, 1.78s/it] over 3 years ago
mc4-es-train-50M-gaussian-stats.csv.tar.gz

546 MB
LFS

Model at 191k steps, acc 0.6562. Dataset stats over 3 years ago
merges.txt

514 kB

Dump 187k steps, acc 0.6574 over 3 years ago
pytorch_model.bin
Detected Pickle imports (4)
- "torch.FloatStorage",
- "torch.LongStorage",
- "collections.OrderedDict",
- "torch._utils._rebuild_tensor_v2"
What is a pickle import?
499 MB
LFS

Step... (249001/250000 | Loss: 1.678702473640442, Acc: 0.660828173160553): 76%|██████████████████▏ | 189999/250000 [97:45:10<29:36:08, 1.78s/it] over 3 years ago
run_mlm_flax_stream.py

32.9 kB

Dump 187k steps, acc 0.6574 over 3 years ago
run_mlm_flax_stream.py.orig

30.8 kB

Dump 187k steps, acc 0.6574 over 3 years ago
run_stream.log

33 MB
LFS

Step... (249001/250000 | Loss: 1.678702473640442, Acc: 0.660828173160553): 76%|██████████████████▏ | 189999/250000 [97:45:10<29:36:08, 1.78s/it] over 3 years ago
run_stream.sh

1.03 kB

Dump 187k steps, acc 0.6574 over 3 years ago
special_tokens_map.json

239 Bytes

Dump 187k steps, acc 0.6574 over 3 years ago
tokenizer.json

1.47 MB

Dump 187k steps, acc 0.6574 over 3 years ago
tokenizer_config.json

292 Bytes

Dump 187k steps, acc 0.6574 over 3 years ago
vocab.json

855 kB

Dump 187k steps, acc 0.6574 over 3 years ago

Detected Pickle imports (4)