imelnyk
/

slm-2-dpo-full

Text Generation

alignment-handbook

Generated from Trainer

Model card Files Files and versions Metrics Training metrics Community

1 contributor

History: 7 commits

imelnyk's picture

Training in progress, step 700

2957baf verified 5 months ago

runs
Training in progress, step 700 5 months ago
.gitattributes

1.52 kB

initial commit 5 months ago
arcade100k.tiktoken

1.68 MB

Training in progress, step 100 5 months ago
config.json

908 Bytes

Training in progress, step 100 5 months ago
model.safetensors

3.29 GB
LFS

Training in progress, step 700 5 months ago
special_tokens_map.json

99 Bytes

Training in progress, step 100 5 months ago
tokenizer_config.json

861 Bytes

Training in progress, step 100 5 months ago
training_args.bin
Detected Pickle imports (12)
- "torch.device",
- "accelerate.utils.dataclasses.DeepSpeedPlugin",
- "transformers.trainer_utils.HubStrategy",
- "transformers.integrations.deepspeed.HfDeepSpeedConfig",
- "transformers.trainer_utils.IntervalStrategy",
- "transformers.trainer_utils.SchedulerType",
- "accelerate.state.PartialState",
- "alignment.configs.DPOConfig",
- "torch.bfloat16",
- "accelerate.utils.dataclasses.DistributedType",
- "transformers.training_args.OptimizerNames",
- "transformers.integrations.deepspeed.HfTrainerDeepSpeedConfig"
How to fix it?
5.94 kB
LFS

Training in progress, step 100 5 months ago