dsmanomano/image-consolidation-models

README.md

@@ -17,6 +17,9 @@ should probably proofread and complete it, then remove this comment. -->
 # image-consolidation-models
 
 This model is a fine-tuned version of [HuggingFaceTB/SmolVLM-Instruct](https://huggingface.co/HuggingFaceTB/SmolVLM-Instruct) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.3098
+- Num Input Tokens Seen: 566737
 
 ## Model description
 
@@ -48,6 +51,11 @@ The following hyperparameters were used during training:
 
 ### Training results
 
+| Training Loss | Epoch  | Step | Validation Loss | Input Tokens Seen |
+|:-------------:|:------:|:----:|:---------------:|:-----------------:|
+| 0.3372        | 0.3226 | 20   | 0.3406          | 192201            |
+| 0.2361        | 0.6452 | 40   | 0.3172          | 381365            |
+| 0.2272        | 0.9677 | 60   | 0.3098          | 566737            |
 
 
 ### Framework versions

adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "up_proj",
+    "k_proj",
+    "gate_proj",
     "o_proj",
     "q_proj",
-    "gate_proj",
     "down_proj",
-    "k_proj",
-    "v_proj",
-    "up_proj"
+    "v_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": true,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c00f95fe4383611a047e137c1e04d2e74e7743a53e31f56b529a648b311ad31
+oid sha256:94283faeaa172b14c165eabc05b7555ef16a7e4c184332d29b729206a93921d9
 size 45187904

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52574df72b68da1981341545aac637d6f8ced79eba27dd97889e852454e76368
+oid sha256:f67b5c2c5ec2625ab93307fab0641dd2ae8427b4c1d7462f0249501ff0e49e2f
 size 5688