End of training

README.md

@@ -14,6 +14,8 @@ should probably proofread and complete it, then remove this comment. -->
 # gm-lora-bfloat16-idefics2-8b-finetuned-mimic-report
 
 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: 0.0959
 
 ## Model description
 
@@ -40,11 +42,19 @@ The following hyperparameters were used during training:
 - total_train_batch_size: 80
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 3
+- num_epochs: 2
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 0.2177        | 0.8945 | 100  | 0.0992          |
+| 0.1001        | 1.7889 | 200  | 0.0959          |
+
 
 ### Framework versions
 
 - Transformers 4.41.0.dev0
-- Pytorch 1.13.1+cu117
-- Datasets 2.19.0
+- Pytorch 2.2.1+cu121
+- Datasets 2.19.1
 - Tokenizers 0.19.1

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d34a1a53e28bbd6e34df59a1b6194c37c22b67615821b7a8b61c63151651959b
+oid sha256:f18d8f7df2ee144fac07b8ca8cfc97f2143135a6a49118e55588692d96c38223
 size 49840864

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c09e22a4eb0268423de5c078739f8680190685b79e08923e6772816f85cc911
-size 4731
+oid sha256:db9b141594ad2df95ea94258d2c83aa29a8b6a4e2a13b2ebe1d4fff133596d35
+size 5240