End of training

README.md

@@ -0,0 +1,71 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: zera09/dpo_t5_2
+tags:
+- trl
+- dpo
+- generated_from_trainer
+model-index:
+- name: dpo_t5_3
+  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. -->
+
+# dpo_t5_3
+
+This model is a fine-tuned version of [zera09/dpo_t5_2](https://huggingface.co/zera09/dpo_t5_2) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.5278
+- Rewards/chosen: 0.0347
+- Rewards/rejected: -0.3816
+- Rewards/accuracies: 0.8494
+- Rewards/margins: 0.4163
+- Logps/rejected: -6.9733
+- Logps/chosen: -25.5442
+- Logits/rejected: -18.4809
+- Logits/chosen: -18.2253
+
+## 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: 16
+- eval_batch_size: 16
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 64
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- training_steps: 200
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
+|:-------------:|:-----:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
+| 0.7475        | 1.0   | 100  | 0.5503          | 0.0318         | -0.3144          | 0.8494             | 0.3461          | -6.8613        | -25.5491     | -18.5139        | -18.2528      |
+| 0.6693        | 2.0   | 200  | 0.5278          | 0.0347         | -0.3816          | 0.8494             | 0.4163          | -6.9733        | -25.5442     | -18.4809        | -18.2253      |
+
+
+### Framework versions
+
+- Transformers 4.45.2
+- Pytorch 2.2.1
+- Datasets 3.0.1
+- Tokenizers 0.20.1

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "decoder_start_token_id": 0,
+  "eos_token_id": 1,
+  "max_length": 100,
+  "pad_token_id": 0,
+  "transformers_version": "4.45.2"
+}