OPO Mistral-7B
Collection
8 items
•
Updated
mistral-7b-base-dpo-list_mle-listsize_8-beta_0.05-batchsize_128
This model is a fine-tuned version of alignment-handbook/zephyr-7b-sft-full on the yangzhao02/ListUltraFeedback dataset. It achieves the following results on the evaluation set:
- Loss: 6.7425
- Logps: -316.4365
- Logits: -2.1289
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-07
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- distributed_type: multi-GPU
- num_devices: 16
- gradient_accumulation_steps: 8
- total_train_batch_size: 128
- total_eval_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 1
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Logits | Logps | Validation Loss |
|---|---|---|---|---|---|
| 6.8406 | 0.5343 | 250 | -2.2186 | -311.0428 | 6.9513 |
Framework versions
- Transformers 4.42.0
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1
- Downloads last month
- 4
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API:
The model has no library tag.
Model tree for yangzhao02/mistral-7b-listmle
Base model
mistralai/Mistral-7B-v0.1
Finetuned
alignment-handbook/zephyr-7b-sft-full