Model save

README.md

@@ -1,7 +1,7 @@
 ---
-base_model: RyanYr/reflect_mini8Bit_om2-460k_sft-t1
+base_model: RyanYr/reflect_ministral8Bit_om2_sft-t2_lr.5-6
 library_name: transformers
-model_name: reflect_mini8B_Om2SftT1-Om2G8kIpsdpIter1T1_b0.5
+model_name: reflect_mini8B_Om2SftT2_Om2G8kIpsdpIter1T02_b1.0
 tags:
 - generated_from_trainer
 - trl
@@ -9,9 +9,9 @@ tags:
 licence: license
 ---
 
-# Model Card for reflect_mini8B_Om2SftT1-Om2G8kIpsdpIter1T1_b0.5
+# Model Card for reflect_mini8B_Om2SftT2_Om2G8kIpsdpIter1T02_b1.0
 
-This model is a fine-tuned version of [RyanYr/reflect_mini8Bit_om2-460k_sft-t1](https://huggingface.co/RyanYr/reflect_mini8Bit_om2-460k_sft-t1).
+This model is a fine-tuned version of [RyanYr/reflect_ministral8Bit_om2_sft-t2_lr.5-6](https://huggingface.co/RyanYr/reflect_ministral8Bit_om2_sft-t2_lr.5-6).
 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/reflect_mini8B_Om2SftT1-Om2G8kIpsdpIter1T1_b0.5", device="cuda")
+generator = pipeline("text-generation", model="RyanYr/reflect_mini8B_Om2SftT2_Om2G8kIpsdpIter1T02_b1.0", 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/s7qpejxw)
+[<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/e0pwbi40)
 
 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/reflect_mini8Bit_om2-460k_sft-t1",
+  "_name_or_path": "RyanYr/reflect_ministral8Bit_om2_sft-t2_lr.5-6",
   "architectures": [
     "MistralForCausalLM"
   ],

last_checkpoint/model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87a6984b3f24e942756124aded24eace23b40852bf0b347ed5dbdbeaa34eecb8
+oid sha256:be9e6c0f3bdaec31e82cefa64f01e4b4139e6fa7621e72124d655ece53d78e3d
 size 4983016096

last_checkpoint/model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d9b27c9d6314b9961bd27b3f5e899da8950777fe90ffd3f31c1e952e4a27c38
+oid sha256:0855deac9b4ef1968fac2302b67fbc7a085b26004f6a46359b1d0b37373bff87
 size 4999836776

last_checkpoint/model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df90c24a377f2b3a715bf3ba6c4c0fd1a1492201b2a7f63b938c138a818591a4
+oid sha256:26ab6f546c0b0a8982af7572e488573303ef70375e9f09db7198c7461b6f6fd2
 size 4983067960

last_checkpoint/model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69fd87cd7a1421ed15922b06cae3920fabadc6b724bf7dd4cc05ea0b3ed1fe56
+oid sha256:677021788a9886abdfea32db8c3c9a7e6f46fe32dd50ca43e38e1f01f202259e
 size 1073750144

last_checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2bc84dc3524f2207c43fe080346b8f00d9ae5d1e806cc96e5dac8726b54c4c08
+oid sha256:71799f1ac373b37acf0d0ae31efe3fc964950dc88d0cf53b5ec0fc3c611b6b92
 size 8056