Model save

README.md

@@ -1,7 +1,7 @@
 ---
-base_model: RyanYr/self-correct_Ministral-8B-Instruct-2410_metaMathQA_dpo_iter1
+base_model: RyanYr/self-correct_Ministral-8B-Instruct-2410_metaMathQA_dpo_iter2
 library_name: transformers
-model_name: self-correct_Ministral-8B-Instruct-2410_metaMathQA_dpo_iter2
+model_name: self-correct_Ministral-8B-Instruct-2410_metaMathQA_dpo_iter3
 tags:
 - generated_from_trainer
 - trl
@@ -9,9 +9,9 @@ tags:
 licence: license
 ---
 
-# Model Card for self-correct_Ministral-8B-Instruct-2410_metaMathQA_dpo_iter2
+# Model Card for self-correct_Ministral-8B-Instruct-2410_metaMathQA_dpo_iter3
 
-This model is a fine-tuned version of [RyanYr/self-correct_Ministral-8B-Instruct-2410_metaMathQA_dpo_iter1](https://huggingface.co/RyanYr/self-correct_Ministral-8B-Instruct-2410_metaMathQA_dpo_iter1).
+This model is a fine-tuned version of [RyanYr/self-correct_Ministral-8B-Instruct-2410_metaMathQA_dpo_iter2](https://huggingface.co/RyanYr/self-correct_Ministral-8B-Instruct-2410_metaMathQA_dpo_iter2).
 It has been trained using [TRL](https://github.com/huggingface/trl).
 
 ## Quick start
@@ -20,14 +20,14 @@ It has been trained using [TRL](https://github.com/huggingface/trl).
 from transformers import pipeline
 
 question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
-generator = pipeline("text-generation", model="RyanYr/self-correct_Ministral-8B-Instruct-2410_metaMathQA_dpo_iter2", device="cuda")
+generator = pipeline("text-generation", model="RyanYr/self-correct_Ministral-8B-Instruct-2410_metaMathQA_dpo_iter3", device="cuda")
 output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
 print(output["generated_text"])
 ```
 
 ## Training procedure
 
-[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/yyr/huggingface/runs/86tsr409)
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/yyr/huggingface/runs/bvrqxizo)
 
 This model was trained with DPO, a method introduced in [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://huggingface.co/papers/2305.18290).
 

last_checkpoint/config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "RyanYr/self-correct_Ministral-8B-Instruct-2410_metaMathQA_dpo_iter1",
+  "_name_or_path": "RyanYr/self-correct_Ministral-8B-Instruct-2410_metaMathQA_dpo_iter2",
   "architectures": [
     "MistralForCausalLM"
   ],

last_checkpoint/model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a7e25e0e8b98bd1df63a82f58bd9e61ab3b501422c368a649b070f1864bb50c3
+oid sha256:330301beced0ece141453b78b3f8ec33f90e2edf1107cde3f53dff43cc8b38c0
 size 4983016096

last_checkpoint/model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:122737c96d3caf8730dad2ea5fd0ee1d421ef9b5a6dcefb9d0956a9f6284396b
+oid sha256:399b9b42d89cb802d1948f220621fc7dbed3e088ab31beeb95177e6ea399e31b
 size 4999836776

last_checkpoint/model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4449c3cb2765620b81fc6c7d1412a02ac6c12829fb7e1421c13a87d01b75ea77
+oid sha256:3f50a3d712ecb29ca1f172b1227232a7d0c3b19490f819e1aad3f0fafa9a42ba
 size 4983067960

last_checkpoint/model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17d168646a4f26c15a85b7a683191c10da704ea3bef0a8ec50be3ca855f05a2c
+oid sha256:ab4ce2369549b393d1faad24acfe6ac2f8cf6f4144350c484296c0189bf6dc5f
 size 1073750144

last_checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77e1fea400142556e131e8b3682da44fd98d05f36bb9aa76ce3fc17c28674a26
+oid sha256:99fd16565ffa839b90ec31bb8a11a5e4de2938ef3bf110c0bdc36ad4e316ab20
 size 8056