Training in progress, epoch 1

README.md

@@ -27,7 +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/qwen3-battleship/huggingface/runs/44znbdhx) 
+[<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/qwen3-battleship/huggingface/runs/cjdw4xfg) 
 
 
 This model was trained with SFT.
@@ -35,7 +35,7 @@ This model was trained with SFT.
 ### Framework versions
 
 - TRL: 0.21.0
-- Transformers: 4.55.3
+- Transformers: 4.55.4
 - Pytorch: 2.7.1
 - Datasets: 4.0.0
 - Tokenizers: 0.21.4

config.json

@@ -61,7 +61,7 @@
   "sliding_window": null,
   "tie_word_embeddings": true,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.55.3",
+  "transformers_version": "4.55.4",
   "use_cache": false,
   "use_sliding_window": false,
   "vocab_size": 151936

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b381ba685c6e97b524a7933e93b419252cb07d92260bb64ca40acd89641dfa4
+oid sha256:d38328c06a67a563cfd3969025a5ceeed5c79eec72ad29ad11e7c74ff9baa3a2
 size 4967215360

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aaaa4a6c054b92c8c7104c7753f6c91a9b07359b353f04e751c7cb26aa143150
+oid sha256:e9c59f1055ad93cd8cb1c0a3354c185ac041161897bcd2d62eec6da286939608
 size 3077766632

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:62f8d3b004938828ca5379f886e8ee188bd195556e606892d9a67301e5ed41af
-size 7505
+oid sha256:e6e209d30f6903a2079ec8543dbc9a565d7aebcc8cc9dcbde240c057c1f04769
+size 7441