Model save

README.md

@@ -1,7 +1,7 @@
 ---
-base_model: RyanYr/reflect_llm8B_llmMstlrg-om2-80k-SftT2_MgSpsdpT02_b1.0
+base_model: RyanYr/reflect_llm8B_om2-mstlrg300k460kLlm33130k_SftDpo-MgSpsdpT1_b1.0
 library_name: transformers
-model_name: reflect_llm8B_llmMstlrg-om2-80k-SftT2_MgSpsdpIter2T02_b1.0
+model_name: reflect_llm8B_om2-mstlrg300k460kLlm33130k_SftDpo-MgSpsdpIter2T1_b0.5
 tags:
 - generated_from_trainer
 - trl
@@ -9,9 +9,9 @@ tags:
 licence: license
 ---
 
-# Model Card for reflect_llm8B_llmMstlrg-om2-80k-SftT2_MgSpsdpIter2T02_b1.0
+# Model Card for reflect_llm8B_om2-mstlrg300k460kLlm33130k_SftDpo-MgSpsdpIter2T1_b0.5
 
-This model is a fine-tuned version of [RyanYr/reflect_llm8B_llmMstlrg-om2-80k-SftT2_MgSpsdpT02_b1.0](https://huggingface.co/RyanYr/reflect_llm8B_llmMstlrg-om2-80k-SftT2_MgSpsdpT02_b1.0).
+This model is a fine-tuned version of [RyanYr/reflect_llm8B_om2-mstlrg300k460kLlm33130k_SftDpo-MgSpsdpT1_b1.0](https://huggingface.co/RyanYr/reflect_llm8B_om2-mstlrg300k460kLlm33130k_SftDpo-MgSpsdpT1_b1.0).
 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_llm8B_llmMstlrg-om2-80k-SftT2_MgSpsdpIter2T02_b1.0", device="cuda")
+generator = pipeline("text-generation", model="RyanYr/reflect_llm8B_om2-mstlrg300k460kLlm33130k_SftDpo-MgSpsdpIter2T1_b0.5", 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/y8nevzte)
+[<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/wu84xu9d)
 
 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_llm8B_llmMstlrg-om2-80k-SftT2_MgSpsdpT02_b1.0",
+  "_name_or_path": "RyanYr/reflect_llm8B_om2-mstlrg300k460kLlm33130k_SftDpo-MgSpsdpT1_b1.0",
   "architectures": [
     "LlamaForCausalLM"
   ],

last_checkpoint/model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ac24b736b91c5c2840669bd5173072f4aadd3c7d4a57eb06d55ffbb37167205
+oid sha256:c560f01f0508a9f88871069d4ef53257580778edbebce3b311f9bdff2d2818fe
 size 4976706864

last_checkpoint/model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a445918589e8f19c6fd89aca70f2666a31dbd0f2517f99008c7fe1ff934da389
+oid sha256:b25c27d2cbd3721c9f9d243da83b106a0354decfd77610008b5bb0ec0da28c13
 size 4999802720

last_checkpoint/model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f6a9f1c0d69f93c1b81bb4584651cf41fe3e4345c70102819668be0c14bfe6f3
+oid sha256:3aa7b51636989630450ed25f48d0b3c7da984407aff40a99deafa34bfd2ecf4b
 size 4915916176

last_checkpoint/model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9797ec99608e9514d64c60868d51bfce817fbba660f37cb7afe13f9b90c1b2aa
+oid sha256:fd6575d0a1c1780bd12de30a7bea285ba8a067bbf6fb026816245b1d726da249
 size 1168147000

last_checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f5a330b5f57bafa5690ca464f2e5d94ffdabe07e2bbeeff79114ac324cfb57d
+oid sha256:76ed97b79eede608b10af40280f0195802aa5496472bb7d087bded932dfe95e0
 size 8056