End of training

README.md

@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [HuggingFaceM4/idefics-9b](https://huggingface.co/HuggingFaceM4/idefics-9b) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.6324
+- Loss: 2.6189
 
 ## Model description
 
@@ -36,25 +36,30 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 0.0002
-- train_batch_size: 2
-- eval_batch_size: 2
+- train_batch_size: 1
+- eval_batch_size: 1
 - seed: 42
 - gradient_accumulation_steps: 8
-- total_train_batch_size: 16
+- total_train_batch_size: 8
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- training_steps: 50
+- training_steps: 100
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 2.1526        | 5.71  | 10   | 2.0213          |
-| 1.4147        | 11.43 | 20   | 1.6357          |
-| 1.1461        | 17.14 | 30   | 1.5834          |
-| 1.002         | 22.86 | 40   | 1.6000          |
-| 0.897         | 28.57 | 50   | 1.6324          |
+| 2.1253        | 2.76  | 10   | 1.8248          |
+| 1.3929        | 5.52  | 20   | 1.6206          |
+| 1.1155        | 8.28  | 30   | 1.6422          |
+| 0.8392        | 11.03 | 40   | 1.6946          |
+| 0.5928        | 13.79 | 50   | 1.8916          |
+| 0.4053        | 16.55 | 60   | 2.0038          |
+| 0.2454        | 19.31 | 70   | 2.2366          |
+| 0.1412        | 22.07 | 80   | 2.3802          |
+| 0.0798        | 24.83 | 90   | 2.5553          |
+| 0.0667        | 27.59 | 100  | 2.6189          |
 
 
 ### Framework versions

adapter_config.json

@@ -1,10 +1,10 @@
 {
   "alpha_pattern": {},
   "auto_mapping": {
-    "base_model_class": "IdeficsForVisionText2Text",
-    "parent_library": "transformers.models.idefics.modeling_idefics"
+    "base_model_class": "PeftModel",
+    "parent_library": "peft.peft_model"
   },
-  "base_model_name_or_path": "HuggingFaceM4/idefics-9b",
+  "base_model_name_or_path": null,
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
@@ -22,8 +22,8 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
     "k_proj",
+    "q_proj",
     "v_proj"
   ],
   "task_type": null,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ec74ae6a0539b42fd85c80698e976d10a1f3d3bc1319922b3901fd78bfb31d3
-size 79071880
+oid sha256:fe616c8491deb0cdf6fd5b3ff9a99486ef268706b98e5165368325a435d4e847
+size 79079832

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8bfe0735da98a266a70faca4de03b0a93f1cfb50e5a25035f8268ece25078c91
+oid sha256:cef17a836f55cf409b325d56fb8d39d2211c0f2bb273039da8778d321ead7395
 size 4856