Model save

README.md

@@ -1,7 +1,7 @@
 ---
-base_model: RyanYr/reflect_llama8B_llama-mstlrg-om2-80k_sft-t2_lr1e-6
+base_model: RyanYr/reflect_llm8B_om2-mstlrg-300k460k-t12_llm33-130k-t12_SFTt1-lr1e-6_DPOt1
 library_name: transformers
-model_name: reflect_llm8B_llmMstlrg-om2-80k-SftT2Spsdp0to20kT02_b1.0
+model_name: reflect_llm8B_om2-mstlrg300k460kLlm33130k_SftDpo-MgSpsdpT1_b0.1
 tags:
 - generated_from_trainer
 - trl
@@ -9,9 +9,9 @@ tags:
 licence: license
 ---
 
-# Model Card for reflect_llm8B_llmMstlrg-om2-80k-SftT2Spsdp0to20kT02_b1.0
+# Model Card for reflect_llm8B_om2-mstlrg300k460kLlm33130k_SftDpo-MgSpsdpT1_b0.1
 
-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).
+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).
 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-SftT2Spsdp0to20kT02_b1.0", device="cuda")
+generator = pipeline("text-generation", model="RyanYr/reflect_llm8B_om2-mstlrg300k460kLlm33130k_SftDpo-MgSpsdpT1_b0.1", 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/agrn59vv)
+[<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/6wi6rmp6)
 
 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_llama8B_llama-mstlrg-om2-80k_sft-t2_lr1e-6",
+  "_name_or_path": "RyanYr/reflect_llm8B_om2-mstlrg-300k460k-t12_llm33-130k-t12_SFTt1-lr1e-6_DPOt1",
   "architectures": [
     "LlamaForCausalLM"
   ],

last_checkpoint/model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:54082993138518dcbd2df172e57f16a1fc90b5d3de73894e05ba334102200100
+oid sha256:e3b66dfdb5c16b09d7603757c03ac3107e96de9c8f2bb66ff0369b3cb5d039a0
 size 4976706864

last_checkpoint/model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f0c08a34beefb8b507cc997700c533b80d0baa7829bd8c3e865aea2c5727623
+oid sha256:4f6509c94aa84e67d3038a6c8eb82174c30b511493cf1af0fb929de99d9457cc
 size 4999802720

last_checkpoint/model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7910d4f405f95202052a4cd9d48f36fa08f8989cf1bf98ab8798e0252fd80b84
+oid sha256:7f8f057acc7cba4b9e633c283196dfd4d715e93896f99b1d6f255b9eba3748fb
 size 4915916176

last_checkpoint/model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f066fb7da617469f49ca365bb9bf3fbcc8c30bb6b9d2b7c608a85a5f7381540
+oid sha256:12e691c1564837cd65afca3d275858ddb2b65352f903f513b149a97c211cd7d1
 size 1168147000

last_checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da61ce58627e264908468aa0fb4bf1bd7e305bbba34058c49399bdc105072242
+oid sha256:5606f156e21af77aef1bc054d2396be4c8d76fd96441b071e84d4fe3084b5310
 size 8056