End of training

README.md

@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [HuggingFaceM4/idefics2-8b](https://huggingface.co/HuggingFaceM4/idefics2-8b) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6739
+- Loss: 0.6872
 
 ## Model description
 
@@ -35,36 +35,31 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 0.0001
-- train_batch_size: 2
-- eval_batch_size: 2
+- train_batch_size: 3
+- eval_batch_size: 3
 - seed: 42
 - gradient_accumulation_steps: 10
-- total_train_batch_size: 20
+- total_train_batch_size: 30
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 50
 - num_epochs: 2
-- mixed_precision_training: Native AMP
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss |
-|:-------------:|:-----:|:----:|:---------------:|
-| 1.5316        | 0.2   | 38   | 0.7854          |
-| 0.7931        | 0.4   | 76   | 0.7384          |
-| 0.8019        | 0.6   | 114  | 0.7167          |
-| 0.7487        | 0.8   | 152  | 0.6992          |
-| 0.7416        | 1.0   | 190  | 0.6887          |
-| 0.5919        | 1.2   | 228  | 0.6977          |
-| 0.5819        | 1.4   | 266  | 0.6903          |
-| 0.5948        | 1.6   | 304  | 0.6849          |
-| 0.5858        | 1.8   | 342  | 0.6780          |
-| 0.5539        | 2.0   | 380  | 0.6739          |
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 1.4399        | 0.2999 | 38   | 0.7745          |
+| 0.8072        | 0.5998 | 76   | 0.7329          |
+| 0.7577        | 0.8998 | 114  | 0.7067          |
+| 0.6603        | 1.1997 | 152  | 0.7081          |
+| 0.6099        | 1.4996 | 190  | 0.6960          |
+| 0.6045        | 1.7995 | 228  | 0.6872          |
 
 
 ### Framework versions
 
 - Transformers 4.41.0.dev0
-- Pytorch 1.13.1+cu117
+- Pytorch 2.0.1
 - Datasets 2.19.1
 - Tokenizers 0.19.1

adapter_config.json

@@ -21,6 +21,6 @@
   "revision": null,
   "target_modules": ".*(text_model|modality_projection|perceiver_resampler).*(down_proj|gate_proj|up_proj|k_proj|q_proj|v_proj|o_proj).*$",
   "task_type": null,
-  "use_dora": false,
+  "use_dora": true,
   "use_rslora": false
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c4430b955fd1bcca51748433e8bd18ac08a1a0b1a446165741e1c9b3e91b671
-size 93378688
+oid sha256:7da3396b30bb4afe2e4eb2206a34b4bebdde289c521757d8f98d916f74b527eb
+size 49840864

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1920691e93e1b989f360a2f842bdbbf92dc0386365f49826cf716a94f45d7f64
+oid sha256:b65e69b9f16929f9153aeb81074223e10d976406a3610f8b175bcc5c85163483
 size 4731