Model save

README.md

@@ -1,7 +1,7 @@
 ---
-base_model: RyanYr/reflect_ministral8Bit_om2_sft-t2_lr.5-6
+base_model: RyanYr/reflect_mini8Bit_om2-460k_sft-t1
 library_name: transformers
-model_name: reflect_mini8B_Om2SftT2_Om2G8kOm2AgIpsdpIter1T02_b0.1
+model_name: reflect_mini8B_Om2SftT1-Om2G8kOm2AgIpsdpIter1T1_b0.1
 tags:
 - generated_from_trainer
 - trl
@@ -9,9 +9,9 @@ tags:
 licence: license
 ---
 
-# Model Card for reflect_mini8B_Om2SftT2_Om2G8kOm2AgIpsdpIter1T02_b0.1
+# Model Card for reflect_mini8B_Om2SftT1-Om2G8kOm2AgIpsdpIter1T1_b0.1
 
-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).
+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).
 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_Om2SftT2_Om2G8kOm2AgIpsdpIter1T02_b0.1", device="cuda")
+generator = pipeline("text-generation", model="RyanYr/reflect_mini8B_Om2SftT1-Om2G8kOm2AgIpsdpIter1T1_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/cmge7g4l)
+[<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/s117w777)
 
 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_ministral8Bit_om2_sft-t2_lr.5-6",
+  "_name_or_path": "RyanYr/reflect_mini8Bit_om2-460k_sft-t1",
   "architectures": [
     "MistralForCausalLM"
   ],

last_checkpoint/model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ef8322f4f3a1de4f29b3096fb79dba37cfa99af358c32a5d879abc2fa375eb7
+oid sha256:f2902945e237497a6ece2745ac39d19daca2e7ecc3dad3edd2c6e286cc6cc7bd
 size 4983016096

last_checkpoint/model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:14b4951a3ed90807c4271c66e8be328e84ed2be17c48f90e4ca66c29c86987e3
+oid sha256:6b87d9a0c3564f9fb039baeecf7452704394c53becbe45e22a5227a5c06b6ae6
 size 4999836776

last_checkpoint/model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2046cf96de5be3b86692a59122c601cbeaf5a5c9a06219283fe2b6f42f4d34b6
+oid sha256:46575a667e28da5f01ee9b08becca09244e71ceaa92aafa9c0e780ec18a5af79
 size 4983067960

last_checkpoint/model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:faa39fdbcbb8f4342383282122fd7447fa036a98ab0824fb7699ab285d27547a
+oid sha256:573eed494696e512ef82a8f3bc14388e93042bde87f13af3d127fb4c17d5910e
 size 1073750144

last_checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e0bc5c3650912528f0e262bd62680923a8f609bd8d410f5a23dcdb85a832a0ba
+oid sha256:58b4a9f0574106c50050ff3a1b2764b0559d0a226fa17e18bf954a0bebca5d47
 size 8056