6.44 GB

Ctrl+K

1 contributor

History: 2 commits

iamPi

Add trained checkpoint: step 1358, loss ~0.09, token_acc ~97%

d9ff036 verified 12 days ago

.gitattributes

1.57 kB
Add trained checkpoint: step 1358, loss ~0.09, token_acc ~97% 12 days ago
chat_template.jinja

3.83 kB
Add trained checkpoint: step 1358, loss ~0.09, token_acc ~97% 12 days ago
config.json

885 Bytes
Add trained checkpoint: step 1358, loss ~0.09, token_acc ~97% 12 days ago
generation_config.json

234 Bytes
Add trained checkpoint: step 1358, loss ~0.09, token_acc ~97% 12 days ago
loss.txt

12 Bytes
Add trained checkpoint: step 1358, loss ~0.09, token_acc ~97% 12 days ago
model-00001-of-00002.safetensors

4.97 GB
xet

Add trained checkpoint: step 1358, loss ~0.09, token_acc ~97% 12 days ago
model-00002-of-00002.safetensors

1.46 GB
xet

Add trained checkpoint: step 1358, loss ~0.09, token_acc ~97% 12 days ago
model.safetensors.index.json

21 kB
Add trained checkpoint: step 1358, loss ~0.09, token_acc ~97% 12 days ago
special_tokens_map.json

454 Bytes
Add trained checkpoint: step 1358, loss ~0.09, token_acc ~97% 12 days ago
tokenizer.json

17.2 MB
xet

Add trained checkpoint: step 1358, loss ~0.09, token_acc ~97% 12 days ago
tokenizer_config.json

50.6 kB
Add trained checkpoint: step 1358, loss ~0.09, token_acc ~97% 12 days ago
trainer_state.json

67.1 kB
Add trained checkpoint: step 1358, loss ~0.09, token_acc ~97% 12 days ago
training_args.bin
Detected Pickle imports (9)
- "transformers.trainer_utils.IntervalStrategy",
- "torch.device",
- "transformers.trainer_utils.SaveStrategy",
- "__main__.SFTEnvTrainingArgs",
- "accelerate.state.PartialState",
- "transformers.trainer_utils.HubStrategy",
- "accelerate.utils.dataclasses.DistributedType",
- "transformers.training_args.OptimizerNames",
- "transformers.trainer_pt_utils.AcceleratorConfig"
How to fix it?
6.35 kB
xet

Add trained checkpoint: step 1358, loss ~0.09, token_acc ~97% 12 days ago

Detected Pickle imports (9)