End of training

README.md

@@ -13,7 +13,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # idefics2-8b-docvqa-finetuned-tutorial
 
-This model is a fine-tuned version of [HuggingFaceM4/idefics2-8b](https://huggingface.co/HuggingFaceM4/idefics2-8b) on an unknown dataset.
+This model is a fine-tuned version of [HuggingFaceM4/idefics2-8b](https://huggingface.co/HuggingFaceM4/idefics2-8b) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0340
 
 ## Model description
 
@@ -33,19 +35,23 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 0.0001
-- train_batch_size: 2
+- train_batch_size: 8
 - eval_batch_size: 8
 - seed: 42
 - gradient_accumulation_steps: 8
-- total_train_batch_size: 16
+- total_train_batch_size: 64
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- lr_scheduler_warmup_steps: 50
+- lr_scheduler_warmup_steps: 10
 - num_epochs: 2
 - mixed_precision_training: Native AMP
 
 ### Training results
 
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 0.044         | 0.9984 | 156  | 0.0368          |
+| 0.0361        | 1.9968 | 312  | 0.0340          |
 
 
 ### Framework versions

adapter_config.json

@@ -19,7 +19,7 @@
   "r": 8,
   "rank_pattern": {},
   "revision": null,
-  "target_modules": ".*(text_model|modality_projection|perceiver_resampler).*(down_proj|gate_proj|up_proj|k_proj|q_proj|v_proj|o_proj).*$",
+  "target_modules": ".*(down_proj|gate_proj|up_proj|k_proj|q_proj|v_proj|o_proj).*$",
   "task_type": null,
   "use_dora": false,
   "use_rslora": false

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1cac69b2fd6888ae4529f9befa8aa1aa568e4889d291a1b0972970fc60068e2
-size 93378688
+oid sha256:335fcd6fbf5e1b1d4f8d97f85af5d911abb665728c15765f2dcad2279b59703e
+size 99375704

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e79c07f9e8249f828c3f157677ea6dfa18628549245db09feefcbfbeb7d8646e
+oid sha256:3724fec2d7e56d43a85516594667a5540289274a9fea040ae3f8b3d3093d9b8b
 size 5112