YAML Metadata
Warning:
The pipeline tag "conversational" is not in the official list: text-classification, token-classification, table-question-answering, question-answering, zero-shot-classification, translation, summarization, feature-extraction, text-generation, text2text-generation, fill-mask, sentence-similarity, text-to-speech, text-to-audio, automatic-speech-recognition, audio-to-audio, audio-classification, voice-activity-detection, depth-estimation, image-classification, object-detection, image-segmentation, text-to-image, image-to-text, image-to-image, image-to-video, unconditional-image-generation, video-classification, reinforcement-learning, robotics, tabular-classification, tabular-regression, tabular-to-text, table-to-text, multiple-choice, text-retrieval, time-series-forecasting, text-to-video, image-text-to-text, visual-question-answering, document-question-answering, zero-shot-image-classification, graph-ml, mask-generation, zero-shot-object-detection, text-to-3d, image-to-3d, image-feature-extraction, video-text-to-text, keypoint-detection, any-to-any, other
mistral-dpo
This model is a fine-tuned version of TheBloke/OpenHermes-2-Mistral-7B-GPTQ on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0559
- Rewards/chosen: -0.6622
- Rewards/rejected: -5.8356
- Rewards/accuracies: 1.0
- Rewards/margins: 5.1735
- Logps/rejected: -138.0126
- Logps/chosen: -105.3292
- Logits/rejected: -2.5356
- Logits/chosen: -2.7185
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: 0.0002
- train_batch_size: 1
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 2
- training_steps: 50
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
|---|---|---|---|---|---|---|---|---|---|---|---|
| 0.6666 | 0.01 | 10 | 0.5490 | 0.3763 | 0.0083 | 1.0 | 0.3680 | -79.5733 | -94.9446 | -2.6386 | -2.7333 |
| 0.439 | 0.01 | 20 | 0.2792 | 1.0686 | -0.2159 | 1.0 | 1.2845 | -81.8148 | -88.0209 | -2.6245 | -2.7868 |
| 0.1683 | 0.02 | 30 | 0.1116 | 1.0530 | -2.2150 | 1.0 | 3.2680 | -101.8059 | -88.1772 | -2.6157 | -2.7924 |
| 0.54 | 0.03 | 40 | 0.0719 | -0.1064 | -4.6952 | 1.0 | 4.5888 | -126.6084 | -99.7713 | -2.5649 | -2.7384 |
| 0.0965 | 0.03 | 50 | 0.0559 | -0.6622 | -5.8356 | 1.0 | 5.1735 | -138.0126 | -105.3292 | -2.5356 | -2.7185 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.0.1+cu117
- Datasets 2.16.1
- Tokenizers 0.15.0
Model tree for Ram07/mistral-dpo
Base model
mistralai/Mistral-7B-v0.1
Finetuned
teknium/OpenHermes-2-Mistral-7B
Quantized
TheBloke/OpenHermes-2-Mistral-7B-GPTQ