Training in progress, step 50

README.md

@@ -4,11 +4,10 @@ library_name: transformers
 model_name: OmniCoder-9B-Zero-Phase2
 tags:
 - generated_from_trainer
-- trl
-- grpo
-- trackio:https://wheattoast11-trackio.hf.space?project=zero-rl&runs=phase2-vlm-grpo-carl&sidebar=collapsed
 - hf_jobs
-- trackio
+- trackio:https://wheattoast11-trackio.hf.space?project=zero-rl&runs=phase2-vlm-grpo-carl-v2&sidebar=collapsed
+- grpo
+- trl
 licence: license
 ---
 
@@ -31,7 +30,7 @@ print(output["generated_text"])
 ## Training procedure
 
  
-[<img src="https://raw.githubusercontent.com/gradio-app/trackio/refs/heads/main/trackio/assets/badge.png" alt="Visualize in Trackio" title="Visualize in Trackio" width="150" height="24"/>](https://wheattoast11-trackio.hf.space?project=zero-rl&runs=phase2-vlm-grpo-carl&sidebar=collapsed)
+[<img src="https://raw.githubusercontent.com/gradio-app/trackio/refs/heads/main/trackio/assets/badge.png" alt="Visualize in Trackio" title="Visualize in Trackio" width="150" height="24"/>](https://wheattoast11-trackio.hf.space?project=zero-rl&runs=phase2-vlm-grpo-carl-v2&sidebar=collapsed)
 
 
 This model was trained with GRPO, a method introduced in [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://huggingface.co/papers/2402.03300).
@@ -39,8 +38,8 @@ This model was trained with GRPO, a method introduced in [DeepSeekMath: Pushing
 ### Framework versions
 
 - TRL: 1.0.0
-- Transformers: 5.4.0
-- Pytorch: 2.11.0
+- Transformers: 5.5.0
+- Pytorch: 2.6.0
 - Datasets: 4.8.4
 - Tokenizers: 0.22.2
 

adapter_config.json

@@ -29,13 +29,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
-    "q_proj",
-    "up_proj",
     "v_proj",
-    "o_proj",
     "down_proj",
-    "gate_proj"
+    "q_proj",
+    "k_proj",
+    "gate_proj",
+    "up_proj",
+    "o_proj"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7646df83e1efe2e482c6981fac6087cdd3c9cb9fc1c824f3ccb76f9d947cbae8
-size 232818320
+oid sha256:33f5eff5f769d20354bddfd57a6fc3de820b7503147aecdc2b8d01256ce98697
+size 465602056

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16e71421c5d4e5b01c8be19a0ed8c9b91f9fd257ed0b17b39182561f48376ca9
-size 19989441
+oid sha256:87a7830d63fcf43bf241c3c5242e96e62dd3fdc29224ca26fed8ea333db72de4
+size 19989343

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c1812a19d9d40df9d7dbf1be808a6660c4110138b77f3296aaadddc82f33eb5b
-size 7249
+oid sha256:751d4f9e6ed7152c38cfc2dd82e1b7212694c0a84f4fa167e942a23f6a708ffb
+size 6904