elephantmipt
/

dpo-llama-1b

Model card Files Files and versions

4.96 GB

Ctrl+K

Ctrl+K

1 contributor

History: 2 commits

elephantmipt's picture

Training in progress, step 58

007aaea verified over 1 year ago

.gitattributes

1.57 kB
Training in progress, step 58 over 1 year ago
config.json

885 Bytes
Training in progress, step 58 over 1 year ago
model.safetensors

4.94 GB
xet

Training in progress, step 58 over 1 year ago
special_tokens_map.json

449 Bytes
Training in progress, step 58 over 1 year ago
tokenizer.json

17.2 MB
xet

Training in progress, step 58 over 1 year ago
tokenizer_config.json

50.9 kB
Training in progress, step 58 over 1 year ago
training_args.bin
Detected Pickle imports (10)
- "torch.device",
- "transformers.trainer_utils.IntervalStrategy",
- "transformers.trainer_utils.HubStrategy",
- "trl.trainer.dpo_config.FDivergenceType",
- "transformers.trainer_pt_utils.AcceleratorConfig",
- "accelerate.state.PartialState",
- "accelerate.utils.dataclasses.DistributedType",
- "trl.trainer.dpo_config.DPOConfig",
- "transformers.training_args.OptimizerNames",
- "transformers.trainer_utils.SchedulerType"
How to fix it?
6.07 kB
xet

Training in progress, step 58 over 1 year ago