Training in progress, step 50

README.md

@@ -5,8 +5,8 @@ model_name: HidatoQwenModel
 tags:
 - generated_from_trainer
 - unsloth
-- trl
 - grpo
+- trl
 licence: license
 ---
 
@@ -28,17 +28,17 @@ 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/michlea-hse-spb/huggingface/runs/avr83ay6) 
+[<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/michlea-hse-spb/huggingface/runs/x14d9l69) 
 
 
 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: 0.23.0
+- TRL: 0.22.2
 - Transformers: 4.55.4
-- Pytorch: 2.7.1
-- Datasets: 3.6.0
+- Pytorch: 2.7.0
+- Datasets: 4.1.1
 - Tokenizers: 0.21.4
 
 ## Citations

adapter_config.json

@@ -1,6 +1,10 @@
 {
   "alpha_pattern": {},
-  "auto_mapping": null,
+  "auto_mapping": {
+    "base_model_class": "Qwen2ForCausalLM",
+    "parent_library": "transformers.models.qwen2.modeling_qwen2",
+    "unsloth_fixed": true
+  },
   "base_model_name_or_path": "unsloth/qwen2.5-3b-instruct-unsloth-bnb-4bit",
   "bias": "none",
   "corda_config": null,
@@ -25,13 +29,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "gate_proj",
     "q_proj",
     "up_proj",
-    "v_proj",
-    "o_proj",
-    "gate_proj",
     "down_proj",
-    "k_proj"
+    "k_proj",
+    "v_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 sha256:50d2559f24ac7844cec1711ca17f640f666d3c760c36f89e0561ee58ec28145d
+oid sha256:61c18c6ba36083ce8a5de53d95c0e7446a13b91eb4df3497d405ad4c1786a0e4
 size 479005064

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a21f2a1ad66e8b0b577ebebf57ff15b23c38c74200ea2a2e8549e07d45ee9a03
-size 7249
+oid sha256:9f47ca104107db0990f56443d657e8d76852d3f24fa0efb2dba9b148ff6bf368
+size 7185