Model save

README.md

@@ -1,6 +1,5 @@
 ---
 base_model: Qwen/Qwen2.5-0.5B
-datasets: reply_likes.json
 library_name: transformers
 model_name: Qwen2.5-0.5B-replies
 tags:
@@ -12,7 +11,7 @@ licence: license
 
 # Model Card for Qwen2.5-0.5B-replies
 
-This model is a fine-tuned version of [Qwen/Qwen2.5-0.5B](https://huggingface.co/Qwen/Qwen2.5-0.5B) on the [reply_likes.json](https://huggingface.co/datasets/reply_likes.json) dataset.
+This model is a fine-tuned version of [Qwen/Qwen2.5-0.5B](https://huggingface.co/Qwen/Qwen2.5-0.5B).
 It has been trained using [TRL](https://github.com/huggingface/trl).
 
 ## Quick start
@@ -28,7 +27,7 @@ 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/awentzonline/huggingface/runs/t99wvz8x) 
+[<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/awentzonline/huggingface/runs/oas4fr8a) 
 
 
 This model was trained with SFT.

config.json

@@ -21,7 +21,7 @@
   "rope_theta": 1000000.0,
   "sliding_window": null,
   "tie_word_embeddings": true,
-  "torch_dtype": "float32",
+  "torch_dtype": "bfloat16",
   "transformers_version": "4.48.2",
   "use_cache": true,
   "use_mrope": false,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:304a8fa6054442a3e7af424c91613a1c73b08a65f82caafda99d472c7f0d5c05
-size 1976163472
+oid sha256:6ba052fc542e0236b976425272937bb3f1a6d50937e67e3da14792f75935fee7
+size 988097824

runs/Feb07_13-07-22_deeplarry/events.out.tfevents.1738962445.deeplarry.8316.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35fab35a617801eca4d2ded644e2a4ea3e7cade2a6c151fa2724f69a95f44931
+size 8727

runs/Feb07_13-08-49_deeplarry/events.out.tfevents.1738962531.deeplarry.8432.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a25b63eb5c3f469cf087cd162798ef069f0bd55b930b080df308967d57d9a6f
+size 562525

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae8c64f391d64d155eea0907ab4478978a55f5a75f19a0df41a5625018177840
+oid sha256:af35b601c0d929cfd3fb964efbf5f814ffefe1c8e666982f6a5186f9c8ebd7f0
 size 5752