Training in progress, epoch 1

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,75 @@
+---
+library_name: peft
+license: gemma
+base_model: google/gemma-3-1b-pt
+tags:
+- generated_from_trainer
+model-index:
+- name: gpt_1_causual_finetune
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# gpt_1_causual_finetune
+
+This model is a fine-tuned version of [google/gemma-3-1b-pt](https://huggingface.co/google/gemma-3-1b-pt) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.9766
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.00025
+- train_batch_size: 16
+- eval_batch_size: 16
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 64
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- num_epochs: 15
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 3.2323        | 1.0   | 12   | 2.9389          |
+| 2.6433        | 2.0   | 24   | 2.2669          |
+| 1.9319        | 3.0   | 36   | 1.5997          |
+| 1.4135        | 4.0   | 48   | 1.2555          |
+| 1.193         | 5.0   | 60   | 1.1551          |
+| 1.1195        | 6.0   | 72   | 1.1047          |
+| 1.0782        | 7.0   | 84   | 1.0753          |
+| 1.0507        | 8.0   | 96   | 1.0515          |
+| 1.0263        | 9.0   | 108  | 1.0319          |
+| 1.0072        | 10.0  | 120  | 1.0154          |
+| 0.9911        | 11.0  | 132  | 1.0053          |
+| 0.9781        | 12.0  | 144  | 0.9918          |
+| 0.9675        | 13.0  | 156  | 0.9833          |
+| 0.9597        | 14.0  | 168  | 0.9789          |
+| 0.9552        | 15.0  | 180  | 0.9766          |
+
+
+### Framework versions
+
+- PEFT 0.15.2.dev0
+- Transformers 4.51.0.dev0
+- Pytorch 2.6.0
+- Datasets 3.4.0
+- Tokenizers 0.21.1

adapter_config.json

@@ -24,8 +24,8 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "v_proj"
+    "v_proj",
+    "q_proj"
   ],
   "task_type": "CAUSAL_LM",
   "trainable_token_indices": null,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f76b4cb12d916cefa9130a39af60a021ec9a9c4e6410e2bbc041d3bbad2b77c
+oid sha256:9515d0f5031920eb8de18c313f99244a947cf77337262455e1a0b587deed70b9
 size 2995512

special_tokens_map.json

@@ -0,0 +1,33 @@
+{
+  "boi_token": "<start_of_image>",
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eoi_token": "<end_of_image>",
+  "eos_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "image_token": "<image_soft_token>",
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4667f2089529e8e7657cfb6d1c19910ae71ff5f28aa7ab2ff2763330affad795
+size 33384568

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d656bdb3cb6e6c27365fde64efcbea4dd20faf64355be88ac4c60e906aea7fa
-size 5432
+oid sha256:17096d50b7b262cc6ce5b9546e6bed94fc28e6da2b40cd25abf56577f2160707
+size 5368