上传 README.md

README.md

@@ -0,0 +1,74 @@
+---
+base_model: Sunshine279/gammaPO-mistral-7b-instruct-v0.2
+tags:
+- alignment-handbook
+- generated_from_trainer
+datasets:
+- princeton-nlp/mistral-instruct-ultrafeedback
+model-index:
+- name: Sunshine279/gammaPO-mistral-7b-instruct-v0.2
+  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. -->
+
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](None)
+# mistral-7b-it-gmsimpo-beta2.5-gm0.15-tau10-lr6e-7
+
+This model is a fine-tuned version of [Sunshine279/gammaPO-mistral-7b-instruct-v0.2](https://huggingface.co/Sunshine279/gammaPO-mistral-7b-instruct-v0.2) on the princeton-nlp/mistral-instruct-ultrafeedback dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.8477
+- Rewards/chosen: -2.2162
+- Rewards/rejected: -2.4466
+- Rewards/accuracies: 0.6197
+- Rewards/margins: 0.2304
+- Logps/rejected: -0.9786
+- Logps/chosen: -0.8865
+- Logits/rejected: -2.7504
+- Logits/chosen: -2.7538
+
+## 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: 6e-07
+- train_batch_size: 2
+- eval_batch_size: 4
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- gradient_accumulation_steps: 16
+- 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
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
+|:-------------:|:------:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
+| 0.7922        | 0.8573 | 400  | 0.8477          | -2.2162        | -2.4466          | 0.6197             | 0.2304          | -0.9786        | -0.8865      | -2.7504         | -2.7538       |
+
+
+### Framework versions
+
+- Transformers 4.42.4
+- Pytorch 2.3.0+cu121
+- Datasets 2.20.0
+- Tokenizers 0.19.1