Model save

README.md

@@ -0,0 +1,73 @@
+---
+library_name: peft
+tags:
+- trl
+- dpo
+- generated_from_trainer
+base_model: Weni/ZeroShot-3.3.14-Mistral-7b-Multilanguage-3.2.0-merged
+model-index:
+- name: ZeroShot-3.4.6-Mistral-7b-DPO-1.0.0
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# ZeroShot-3.4.6-Mistral-7b-DPO-1.0.0
+
+This model is a fine-tuned version of [Weni/ZeroShot-3.3.14-Mistral-7b-Multilanguage-3.2.0-merged](https://huggingface.co/Weni/ZeroShot-3.3.14-Mistral-7b-Multilanguage-3.2.0-merged) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.4359
+- Rewards/chosen: 0.5672
+- Rewards/rejected: -0.1870
+- Rewards/accuracies: 0.8447
+- Rewards/margins: 0.7542
+- Logps/rejected: -17.4222
+- Logps/chosen: -12.1310
+- Logits/rejected: -1.2273
+- Logits/chosen: -1.2477
+
+## 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: 2e-06
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 32
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_ratio: 0.1
+- training_steps: 288
+- 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 |
+|:-------------:|:-----:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
+| 0.5697        | 2.04  | 100  | 0.5667          | 0.3017         | -0.0150          | 0.7652             | 0.3167          | -15.7020       | -14.7860     | -1.3079         | -1.3298       |
+| 0.4274        | 4.08  | 200  | 0.4359          | 0.5672         | -0.1870          | 0.8447             | 0.7542          | -17.4222       | -12.1310     | -1.2273         | -1.2477       |
+
+
+### Framework versions
+
+- PEFT 0.8.2
+- Transformers 4.38.2
+- Pytorch 2.1.0+cu118
+- Datasets 2.17.1
+- Tokenizers 0.15.2