Training in progress, step 25

README.md

@@ -4,11 +4,10 @@ library_name: transformers
 model_name: OmniCoder-9B-Zero-Phase1
 tags:
 - generated_from_trainer
-- hf_jobs
-- trackio
-- trl
-- trackio:https://wheattoast11-trackio.hf.space?project=zero-rl&runs=phase1-grpo-tool-calling&sidebar=collapsed
 - grpo
+- trl
+- hf_jobs
+- trackio:https://wheattoast11-trackio.hf.space?project=zero-rl&runs=phase1-grpo-carl&sidebar=collapsed
 licence: license
 ---
 
@@ -31,14 +30,14 @@ 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=phase1-grpo-tool-calling&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=phase1-grpo-carl&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).
 
 ### Framework versions
 
-- TRL: 0.29.1
+- TRL: 1.0.0
 - Transformers: 5.4.0
 - Pytorch: 2.11.0
 - Datasets: 4.8.4
@@ -55,7 +54,6 @@ Cite GRPO as:
     year         = 2024,
     eprint       = {arXiv:2402.03300},
 }
-
 ```
 
 Cite TRL as:

adapter_config.json

@@ -29,13 +29,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
+    "v_proj",
     "down_proj",
-    "up_proj",
     "gate_proj",
+    "up_proj",
+    "q_proj",
     "k_proj",
-    "v_proj",
-    "q_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 sha256:0cb818e838ca7d176b8401520ebb127c63e56e3644e2b7a6a8abe548ce47be88
+oid sha256:b790a795e153f111ad7426c8e95268b1d57f091533a777007bcf634e91aaa4b2
 size 232818320

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2684b3deb1fb9e7a568591cf42459a21e00d8caeca8d7e424e8301cf1fd8828b
-size 7121
+oid sha256:c69cc6976b95d3503a0e7b3ef5fab8913834b8902f107b0affad90a5b67ead28
+size 7313