Training in progress, step 5

README.md

@@ -1,7 +1,7 @@
 ---
-base_model: Qwen/Qwen3-1.7B
+base_model: Qwen/Qwen3-0.6B
 library_name: transformers
-model_name: sft_full_1.7_pre
+model_name: sft_full_0.6_pre
 tags:
 - generated_from_trainer
 - trl
@@ -9,9 +9,9 @@ tags:
 licence: license
 ---
 
-# Model Card for sft_full_1.7_pre
+# Model Card for sft_full_0.6_pre
 
-This model is a fine-tuned version of [Qwen/Qwen3-1.7B](https://huggingface.co/Qwen/Qwen3-1.7B).
+This model is a fine-tuned version of [Qwen/Qwen3-0.6B](https://huggingface.co/Qwen/Qwen3-0.6B).
 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="SaminSkyfall/sft_full_1.7_pre", device="cuda")
+generator = pipeline("text-generation", model="SaminSkyfall/sft_full_0.6_pre", 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/samin-skyfall-ai/huggingface/runs/pctoxsql) 
+[<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/samin-skyfall-ai/huggingface/runs/aez1f97o) 
 
 
 This model was trained with SFT.

config.json

@@ -23,7 +23,7 @@
   "rope_theta": 1000000,
   "sliding_window": null,
   "tie_word_embeddings": true,
-  "torch_dtype": "float32",
+  "torch_dtype": "float16",
   "transformers_version": "4.51.3",
   "use_cache": true,
   "use_sliding_window": false,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83936892210c3f2bb5d1c76118aa98f6c70c255f9c72f434924b1450a905a558
-size 2384234968
+oid sha256:7822ad66d626e7c74433ec69603290f055af1f2b92123c89ee31946ce229aebd
+size 3441185296

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:57448f1170bca92e6f95f3e713a59c797a449a62d5217fc94b044e42a3e49c8d
+oid sha256:dad462a1733b11479eb1ddbf9e924f649d1de3c01844bc5c162aa0c9e78b479f
 size 6033