Training in progress, step 30

README.md

@@ -1,20 +1,18 @@
 ---
 base_model: ibm-granite/granite-4.0-micro
-datasets: HuggingFaceH4/cai-conversation-harmless-old
 library_name: transformers
 model_name: granite-4.0-micro
 tags:
 - generated_from_trainer
+- trackio:https://Nafifa-granite-4.0-micro.hf.space?project=huggingface&runs=Nafifa-1773292479&sidebar=collapsed
 - sft
 - trl
-- trackio:https://Nafifa-granite-4.0-micro.hf.space?project=huggingface&runs=Nafifa-1773132048&sidebar=collapsed
-- trackio
 licence: license
 ---
 
 # Model Card for granite-4.0-micro
 
-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-old](https://huggingface.co/datasets/HuggingFaceH4/cai-conversation-harmless-old) 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://Nafifa-granite-4.0-micro.hf.space?project=huggingface&runs=Nafifa-1773132048&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://Nafifa-granite-4.0-micro.hf.space?project=huggingface&runs=Nafifa-1773292479&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

@@ -32,12 +32,12 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "o_proj",
-    "q_proj",
-    "gate_proj",
     "k_proj",
     "up_proj",
+    "q_proj",
+    "o_proj",
+    "gate_proj",
+    "v_proj",
     "down_proj"
   ],
   "target_parameters": null,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5fdaf1349d13eb9ca2a779d5b45833b526836f6b779e3f76e16c6f4f07cb2220
+oid sha256:a4577af5526286dd7d276119e1e7ec3481b60c5875c7308c5709860c31a4a24e
 size 41986272

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0aa8148c54974d382da3eac654f363d6eb5641458c63578b2effdb3f56eb3486
+oid sha256:a4bc849338a7a1d1de79a5c661646f5df2dbd7f0f80697f877648902fe9ba25a
 size 5585