Training in progress, step 30

README.md

@@ -1,20 +1,18 @@
 ---
 base_model: ibm-granite/granite-4.0-micro
-datasets: HuggingFaceH4/cai-conversation-harmless
 library_name: transformers
 model_name: granite-4.0-micro-cai
 tags:
 - generated_from_trainer
-- trl
+- trackio:https://yiling24-granite-4.0-micro-cai.hf.space?project=huggingface&runs=yiling24-1773112443&sidebar=collapsed
 - sft
-- trackio
-- trackio:https://yiling24-granite-4.0-micro-cai.hf.space?project=huggingface&runs=yiling24-1773068822&sidebar=collapsed
+- trl
 licence: license
 ---
 
 # Model Card for granite-4.0-micro-cai
 
-This model is a fine-tuned version of [ibm-granite/granite-4.0-micro](https://huggingface.co/ibm-granite/granite-4.0-micro) on the [HuggingFaceH4/cai-conversation-harmless](https://huggingface.co/datasets/HuggingFaceH4/cai-conversation-harmless) dataset.
+This model is a fine-tuned version of [ibm-granite/granite-4.0-micro](https://huggingface.co/ibm-granite/granite-4.0-micro).
 It has been trained using [TRL](https://github.com/huggingface/trl).
 
 ## Quick start
@@ -31,7 +29,7 @@ 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://yiling24-granite-4.0-micro-cai.hf.space?project=huggingface&runs=yiling24-1773068822&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://yiling24-granite-4.0-micro-cai.hf.space?project=huggingface&runs=yiling24-1773112443&sidebar=collapsed)
 
 
 This model was trained with SFT.
@@ -39,7 +37,7 @@ This model was trained with SFT.
 ### Framework versions
 
 - TRL: 0.29.0
-- Transformers: 4.57.6
+- Transformers: 5.0.0
 - Pytorch: 2.10.0+cu128
 - Datasets: 4.0.0
 - Tokenizers: 0.22.2

adapter_config.json

@@ -33,11 +33,11 @@
   "revision": null,
   "target_modules": [
     "k_proj",
-    "gate_proj",
     "down_proj",
+    "o_proj",
+    "gate_proj",
     "up_proj",
     "q_proj",
-    "o_proj",
     "v_proj"
   ],
   "target_parameters": null,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f3bf6a641844cd096fd8ad77fa52d6db76da726569604dcf1b5bf61d8664166
+oid sha256:e3ca64522938a98b65d3c0a74cc8e3609b69973fa30102640b6211e88b7dc657
 size 41986272