Training in progress, epoch 1

.ipynb_checkpoints/README-checkpoint.md

@@ -0,0 +1,58 @@
+---
+base_model: google/gemma-3-4b-it
+library_name: transformers
+model_name: gemma-text-image-finetune
+tags:
+- generated_from_trainer
+- trl
+- sft
+licence: license
+---
+
+# Model Card for gemma-text-image-finetune
+
+This model is a fine-tuned version of [google/gemma-3-4b-it](https://huggingface.co/google/gemma-3-4b-it).
+It has been trained using [TRL](https://github.com/huggingface/trl).
+
+## Quick start
+
+```python
+from transformers import pipeline
+
+question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
+generator = pipeline("text-generation", model="rishirath/gemma-text-image-finetune", device="cuda")
+output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
+print(output["generated_text"])
+```
+
+## Training procedure
+
+ 
+
+
+This model was trained with SFT.
+
+### Framework versions
+
+- TRL: 0.22.1
+- Transformers: 4.56.0
+- Pytorch: 2.8.0.dev20250319+cu128
+- Datasets: 4.0.0
+- Tokenizers: 0.22.0
+
+## Citations
+
+
+
+Cite TRL as:
+    
+```bibtex
+@misc{vonwerra2022trl,
+	title        = {{TRL: Transformer Reinforcement Learning}},
+	author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
+	year         = 2020,
+	journal      = {GitHub repository},
+	publisher    = {GitHub},
+	howpublished = {\url{https://github.com/huggingface/trl}}
+}
+```

adapter_config.json

@@ -28,16 +28,16 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "down_proj",
+    "fc1",
+    "k_proj",
     "v_proj",
-    "up_proj",
     "fc2",
-    "fc1",
-    "down_proj",
-    "o_proj",
-    "out_proj",
+    "up_proj",
     "gate_proj",
-    "k_proj",
-    "q_proj"
+    "q_proj",
+    "o_proj",
+    "out_proj"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b7f060dded3d174be943da15bf53be935a5ecba22c53181692103c01cd23b89
+oid sha256:5f2f51f76d1a80dccc9c318964e1abce4dc51a28388243c264b194b8c508992c
 size 5524138880

runs/Sep01_11-22-26_f80229a91f19/events.out.tfevents.1756725753.f80229a91f19.2175.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:032c968384ca55879d7f8c1f6c29d7631e96bf526d2bdb897436b3839fa91bb2
-size 7323
+oid sha256:658af015716d7b0d8f746e2727c1d2647aba4ddf92575bfed39ffaf74a685003
+size 8073

runs/Sep01_11-34-41_8960e6502684/events.out.tfevents.1756726488.8960e6502684.282.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d16b764a61f7acda412d431db993c93e886f2951d189ec4219c84c4caafad7b9
+size 7322

runs/Sep01_11-37-38_8960e6502684/events.out.tfevents.1756726668.8960e6502684.282.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4f231b884d0dc223129fe76b77b5db98ed149841d79b350ee844e5a1e781ab8
+size 7274

runs/Sep01_11-39-03_8960e6502684/events.out.tfevents.1756726749.8960e6502684.675.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1846e7b590b8324bbeb84ef0ed8b998db2b7fe40ec584f4709aaeeb9f9056fd1
+size 7322

runs/Sep01_11-41-47_8960e6502684/events.out.tfevents.1756726913.8960e6502684.675.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48188a5763471f0cb71ca2c7547973b55d68392f3a902aa6210541e9552eab0c
+size 7322

runs/Sep01_11-45-49_8960e6502684/events.out.tfevents.1756727155.8960e6502684.938.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fcf23a553653ce50c77786ab06a538138508d98b764816e2ba188983977702c9
+size 7322

runs/Sep01_11-48-54_8960e6502684/events.out.tfevents.1756727341.8960e6502684.1191.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1971bdcf9214c600bb5bc07b694a216eb6d63ab56130df25bd0673cde5c44a2
+size 7839

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:71b6c71604c784cfaef8032e4c47e1758029330970bdb8d507259312501a79f6
+oid sha256:7fd9009f301d2e964deb6b17a27dc66ed1f6b0b1d364ed0aeced9c1af1cfc9b2
 size 6161