rasdani
/

qwen2-math-1_5b-step-dpo

Text Generation

alignment-handbook

Generated from Trainer

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

qwen2-math-1_5b-step-dpo

1 contributor

History: 4 commits

rasdani's picture

Training in progress, step 1200

9085790 verified 4 months ago

.gitattributes

1.52 kB

initial commit 4 months ago
added_tokens.json

80 Bytes

Training in progress, step 400 4 months ago
config.json

731 Bytes

Training in progress, step 400 4 months ago
merges.txt

1.67 MB

Training in progress, step 400 4 months ago
model.safetensors

3.09 GB
LFS

Training in progress, step 1200 4 months ago
special_tokens_map.json

367 Bytes

Training in progress, step 400 4 months ago
tokenizer.json

7.03 MB

Training in progress, step 400 4 months ago
tokenizer_config.json

1.3 kB

Training in progress, step 400 4 months ago
training_args.bin
Detected Pickle imports (13)
- "transformers.trainer_utils.HubStrategy",
- "transformers.integrations.deepspeed.HfTrainerDeepSpeedConfig",
- "transformers.training_args.OptimizerNames",
- "torch.device",
- "transformers.trainer_pt_utils.AcceleratorConfig",
- "accelerate.utils.dataclasses.DistributedType",
- "transformers.integrations.deepspeed.HfDeepSpeedConfig",
- "accelerate.utils.dataclasses.DeepSpeedPlugin",
- "__main__.StepDPOConfig",
- "transformers.trainer_utils.IntervalStrategy",
- "torch.bfloat16",
- "transformers.trainer_utils.SchedulerType",
- "accelerate.state.PartialState"
How to fix it?
6.65 kB
LFS

Training in progress, step 400 4 months ago
vocab.json

2.78 MB

Training in progress, step 400 4 months ago