Model save

README.md

@@ -1,7 +1,7 @@
 ---
 base_model: RyanYr/self-correct_ministral8Bit_mMQA_dpo_iter1
 library_name: transformers
-model_name: self-correct_ministral8Bit_mMQA_dpo_iter1
+model_name: self-correct_ministral8Bit_mMQA_dpo_iter2
 tags:
 - generated_from_trainer
 - trl
@@ -9,7 +9,7 @@ tags:
 licence: license
 ---
 
-# Model Card for self-correct_ministral8Bit_mMQA_dpo_iter1
+# Model Card for self-correct_ministral8Bit_mMQA_dpo_iter2
 
 This model is a fine-tuned version of [RyanYr/self-correct_ministral8Bit_mMQA_dpo_iter1](https://huggingface.co/RyanYr/self-correct_ministral8Bit_mMQA_dpo_iter1).
 It has been trained using [TRL](https://github.com/huggingface/trl).
@@ -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_ministral8Bit_mMQA_dpo_iter1", device="cuda")
+generator = pipeline("text-generation", model="RyanYr/self-correct_ministral8Bit_mMQA_dpo_iter2", 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/jqoshhaq)
+[<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/3cwz4oet)
 
 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/model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37804c8e3ce5262e6071b0d26f8f0d0d6c3a062f4f7fcd70d6ed55cae89af594
+oid sha256:0b18134015e7ea9fadd9569949d7e2c4a2abb8ca4a68f00d2e62268deb510962
 size 4983016096

last_checkpoint/model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db14f02b0db7b4ca4164811b257a0a9760638b35d255f76b2d61f6373b0d1279
+oid sha256:c340e91ce5895431613cd67c15f5a28a62c1f1a08660271fcc571ba101cddaca
 size 4999836776

last_checkpoint/model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b5df87ca29b22d5ec519235f3143e1a0b0f31e04834ebec9c9544e61ce482fe
+oid sha256:aa54eb37eeafa58ffb38fda31ddc378722de8b261079e3f2a4c52672feab9ba7
 size 4983067960

last_checkpoint/model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f5efdf6c1cc2a111dfa66f46acd4db5f7b002fdb7e0b485242394c3ba7f48b19
+oid sha256:2b9c662799b7c6dcf810f015a348289591ae524ab2413930ab58f95febf5554d
 size 1073750144

last_checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c712538fff51db9b6b7893b2e0b057fdfc0779ffc27f61a04957e444df0ba87
+oid sha256:3d64e61c44c068190aa06a5d631de835e2782cb88b9584a20eed6067f71080cf
 size 8056