Model save

README.md

@@ -1,7 +1,7 @@
 ---
-base_model: RyanYr/reflect_llm8B_om2-mstlrg-300k460k-t12_llm33-130k-t12_SFTt1-lr1e-6_DPOt1
+base_model: RyanYr/reflect_llama8B_llama-mstlrg-om2-80k_sft-t2_lr1e-6
 library_name: transformers
-model_name: reflect_llm8B_om2-mstlrg300k460kLlm33130k_SftDpo0to20kIpsdp20to40kT1_b1.0
+model_name: reflect_llm8B_llmMstlrg-om2-80k-SftT2_iPSDP20to40kT02_b1.0
 tags:
 - generated_from_trainer
 - trl
@@ -9,9 +9,9 @@ tags:
 licence: license
 ---
 
-# Model Card for reflect_llm8B_om2-mstlrg300k460kLlm33130k_SftDpo0to20kIpsdp20to40kT1_b1.0
+# Model Card for reflect_llm8B_llmMstlrg-om2-80k-SftT2_iPSDP20to40kT02_b1.0
 
-This model is a fine-tuned version of [RyanYr/reflect_llm8B_om2-mstlrg-300k460k-t12_llm33-130k-t12_SFTt1-lr1e-6_DPOt1](https://huggingface.co/RyanYr/reflect_llm8B_om2-mstlrg-300k460k-t12_llm33-130k-t12_SFTt1-lr1e-6_DPOt1).
+This model is a fine-tuned version of [RyanYr/reflect_llama8B_llama-mstlrg-om2-80k_sft-t2_lr1e-6](https://huggingface.co/RyanYr/reflect_llama8B_llama-mstlrg-om2-80k_sft-t2_lr1e-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_llm8B_om2-mstlrg300k460kLlm33130k_SftDpo0to20kIpsdp20to40kT1_b1.0", device="cuda")
+generator = pipeline("text-generation", model="RyanYr/reflect_llm8B_llmMstlrg-om2-80k-SftT2_iPSDP20to40kT02_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/2b9ghurm)
+[<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/94qisaiy)
 
 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_om2-mstlrg-300k460k-t12_llm33-130k-t12_SFTt1-lr1e-6_DPOt1",
+  "_name_or_path": "RyanYr/reflect_llama8B_llama-mstlrg-om2-80k_sft-t2_lr1e-6",
   "architectures": [
     "LlamaForCausalLM"
   ],

last_checkpoint/model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8bc344ad32b0ef9acff18dcf449ff608ac7e5fce3d2df26dca172168e48b454e
+oid sha256:845ff239ccd18bd6524461455c06f70f5cbfca83f2ba56c04d2ab994f31a5113
 size 4976706864

last_checkpoint/model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc91aa5fac4eb1c660fc89ef8214e4698cb122958d881f78a77c64081c72c0ca
+oid sha256:99dd5b99c5e5f3963f94f6b53388812ab11a08c818d2751514eba38138c7f2e3
 size 4999802720

last_checkpoint/model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a2bb26977a19c35d8c55b4fab2fdb1e86f8ed69925b2d042e16c29c45ef674a
+oid sha256:7ef6d005c43a45c123761c12d910c7c7f6ca3518e68c097252e2e79d748a8e5f
 size 4915916176

last_checkpoint/model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90299a912a5886a43e4dbd8e3cae64f8a7b6bc7a8e81038631b3acbe9e8e1269
+oid sha256:cf3b1bbf430af742e3982977b3a13ad0c1e2675978eae0d642fda77fc571b362
 size 1168147000

last_checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:57ead2b7c44f919bc7a218dd9f3f2456beaa1a8d65b2f67eda029fb48a48d4dc
-size 8120
+oid sha256:0475bf6d1b44ba1fb38add49f4f7efe38e1af4ae63c0dbd5a255bb0c9a450bea
+size 8056