Model save

README.md

@@ -0,0 +1,76 @@
+---
+license: mit
+library_name: peft
+tags:
+- trl
+- dpo
+- generated_from_trainer
+base_model: HuggingFaceH4/zephyr-7b-beta
+model-index:
+- name: WeniGPT-2.4.1-Zephyr-7B-5-epochs-LLM_Base_2.0.3_DPO
+  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. -->
+
+# WeniGPT-2.4.1-Zephyr-7B-5-epochs-LLM_Base_2.0.3_DPO
+
+This model is a fine-tuned version of [HuggingFaceH4/zephyr-7b-beta](https://huggingface.co/HuggingFaceH4/zephyr-7b-beta) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.6387
+- Rewards/chosen: -0.7462
+- Rewards/rejected: -2.9362
+- Rewards/accuracies: 0.0792
+- Rewards/margins: 2.1901
+- Logps/rejected: -44.1444
+- Logps/chosen: -15.8185
+- Logits/rejected: -1.9454
+- Logits/chosen: -1.9472
+
+## 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-05
+- 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: 445
+- 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 |
+|:-------------:|:-----:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
+| 0.6643        | 1.12  | 100  | 0.6418          | -0.8916        | -3.0433          | 0.0760             | 2.1516          | -45.2145       | -17.2732     | -1.8856         | -1.8882       |
+| 0.6792        | 2.23  | 200  | 0.6388          | -0.7493        | -2.9465          | 0.0792             | 2.1972          | -44.2469       | -15.8498     | -1.9453         | -1.9472       |
+| 0.6859        | 3.35  | 300  | 0.6387          | -0.7462        | -2.9362          | 0.0792             | 2.1901          | -44.1444       | -15.8185     | -1.9454         | -1.9472       |
+| 0.6487        | 4.47  | 400  | 0.6393          | -0.5904        | -2.5253          | 0.0792             | 1.9349          | -40.0352       | -14.2607     | -1.9706         | -1.9719       |
+
+
+### Framework versions
+
+- PEFT 0.8.2
+- Transformers 4.38.2
+- Pytorch 2.1.0+cu118
+- Datasets 2.17.1
+- Tokenizers 0.15.2

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:463731410d1620bfe68b5b7e089437b720c2145626d81b8107cd0817abe92a77
+oid sha256:fdd9a5e0c6396c289cef2ab73888ab4a18f2e010c0d215d1ac81194ffebadd90
 size 27297032