RyanYr
/

self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter2-only2nd-2e-7

Text Generation

Generated from Trainer

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter2-only2nd-2e-7

1 contributor

History: 4 commits

RyanYr's picture

Training in progress, step 77

d74a580 verified 21 days ago

last_checkpoint
Model save 21 days ago
.gitattributes

1.64 kB

Training in progress, step 77 21 days ago
README.md

2.86 kB

Model save 21 days ago
config.json

985 Bytes

Training in progress, step 77 21 days ago
generation_config.json

184 Bytes

Training in progress, step 77 21 days ago
model-00001-of-00002.safetensors

4.97 GB
LFS

Training in progress, step 77 21 days ago
model-00002-of-00002.safetensors

2.25 GB
LFS

Training in progress, step 77 21 days ago
model.safetensors.index.json

21 kB

Training in progress, step 77 21 days ago
special_tokens_map.json

434 Bytes

Training in progress, step 77 21 days ago
tokenizer.json

17.2 MB
LFS

Training in progress, step 77 21 days ago
tokenizer_config.json

54.7 kB

Training in progress, step 77 21 days ago
training_args.bin
Detected Pickle imports (14)
- "transformers.training_args.OptimizerNames",
- "transformers.trainer_utils.SchedulerType",
- "transformers.integrations.deepspeed.HfDeepSpeedConfig",
- "trl.trainer.dpo_config.FDivergenceType",
- "accelerate.state.PartialState",
- "accelerate.utils.dataclasses.DeepSpeedPlugin",
- "transformers.trainer_utils.IntervalStrategy",
- "trl.trainer.dpo_config.DPOConfig",
- "accelerate.utils.dataclasses.DistributedType",
- "transformers.integrations.deepspeed.HfTrainerDeepSpeedConfig",
- "torch.device",
- "transformers.trainer_pt_utils.AcceleratorConfig",
- "transformers.trainer_utils.HubStrategy",
- "torch.bfloat16"
How to fix it?
7.61 kB
LFS

Training in progress, step 77 21 days ago