Model save

README.md

@@ -1,7 +1,7 @@
 ---
-base_model: RyanYr/self-correct_mistral-small-it_mMQA_dpo_iter1
+base_model: RyanYr/self-correct_mistral-small-it_mMQA_dpo_iter2
 library_name: transformers
-model_name: self-correct_mistral-small-it_mMQA_dpo_iter2_beta.05
+model_name: self-correct_mistral-small-it_mMQA_dpo_iter3_beta.05
 tags:
 - generated_from_trainer
 - trl
@@ -9,9 +9,9 @@ tags:
 licence: license
 ---
 
-# Model Card for self-correct_mistral-small-it_mMQA_dpo_iter2_beta.05
+# Model Card for self-correct_mistral-small-it_mMQA_dpo_iter3_beta.05
 
-This model is a fine-tuned version of [RyanYr/self-correct_mistral-small-it_mMQA_dpo_iter1](https://huggingface.co/RyanYr/self-correct_mistral-small-it_mMQA_dpo_iter1).
+This model is a fine-tuned version of [RyanYr/self-correct_mistral-small-it_mMQA_dpo_iter2](https://huggingface.co/RyanYr/self-correct_mistral-small-it_mMQA_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_mistral-small-it_mMQA_dpo_iter2_beta.05", device="cuda")
+generator = pipeline("text-generation", model="RyanYr/self-correct_mistral-small-it_mMQA_dpo_iter3_beta.05", 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/9ec28lm9)
+[<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/3xxkncbf)
 
 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_mistral-small-it_mMQA_dpo_iter1",
+  "_name_or_path": "RyanYr/self-correct_mistral-small-it_mMQA_dpo_iter2",
   "architectures": [
     "MistralForCausalLM"
   ],

last_checkpoint/model-00001-of-00009.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:464ac8437e48d586d41a333ed6a7e4b2b39b5dcd8bbd73abba2faefd3517cf26
+oid sha256:b18e0294beb3fd7eab6e621c9a474788cb17fcf4cccf2949942d10fe6fd69b47
 size 4882311064

last_checkpoint/model-00002-of-00009.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:080fb99eefb3790b94cfec04ca25e9e75c7f003424b2d01e674d1f9cf616aef9
+oid sha256:f499e6c04610db0cdaf2f92d2543456e03caaf75c3a53b7c8c89ef8981a84fff
 size 4983012160

last_checkpoint/model-00003-of-00009.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2aa87c471c78ed5711ccaf3c4e7f3a83b3fc2e1c92c66a22ea2d5829c8ac45c
+oid sha256:0ed19bd32ef693b21e31de2104ea0d48fb564f8034832f05c7930005b77378fa
 size 4957821336

last_checkpoint/model-00004-of-00009.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a1232d5d34f02adf3065664ad362051e6165a73a96b374a2d390a328a620d5ff
+oid sha256:df1f6895c60c307417c6f44b362dca81b5cdaace29cd4cbbd0fff0e57fab80b7
 size 4882323744

last_checkpoint/model-00005-of-00009.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c6978e76c9f29ab95f800bb3eff65b8e9a19381ab3cc9ed6f11e19dff6c4796
+oid sha256:87f1f68e41a7f451383b3f667b35b402ed81c376a398cec7c2838e56f5cdf4b5
 size 4983012192

last_checkpoint/model-00006-of-00009.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8463efa2f7cf5a8d03e3604e9eb1e2008acdd8c9ae67abc9f33dab27b97aceb0
+oid sha256:afc0f083f0052aeb28f508597edd20f9c449895bb2d520fe7cde2455a79d7acb
 size 4957821336

last_checkpoint/model-00007-of-00009.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa981da7eca667a0d10e694a87da0b71f02182796b003c52441600b23523ebce
+oid sha256:373f76dfcedf249caece3211dbef9b3de0c22cf0856bf6f56dc8200734dcf439
 size 4882323744

last_checkpoint/model-00008-of-00009.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6abe9dae918d6a2eeda8a07dc6fa2ca525391d5128b5c0bcdde2e21d12760905
+oid sha256:d88aa96687bd642de6d294f6a21266c2248a53516752ad4308771949c9070c8b
 size 4983012192

last_checkpoint/model-00009-of-00009.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43589738ab4d826e22d2de7d8e7a803e7e6fe6bda0dfb64ff3b3c89c205ef863
+oid sha256:edf1471c0e95ae9ce2d4ce49b73b3005678e09da5e13f88aba301d78573fbaff
 size 4983011344

last_checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:182dbfc5cfadd9e156149dd754da5a26bb1016076a06193570698711c2a26a26
+oid sha256:bc3e3abd0433f8b904eb5a7a7b013326e3da729383ec2da00ba3c2520baec6bc
 size 8056