Oysiyl/colSmol-500M_ufo

README.md

@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [vidore/ColSmolVLM-Instruct-500M-base](https://huggingface.co/vidore/ColSmolVLM-Instruct-500M-base) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.5117
+- Loss: 0.0878
 
 ## Model description
 
@@ -48,12 +48,12 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 0.6352        | 0.1636 | 80   | 0.6687          |
-| 0.5504        | 0.3272 | 160  | 0.6134          |
-| 0.5282        | 0.4908 | 240  | 0.5780          |
-| 0.4699        | 0.6544 | 320  | 0.5423          |
-| 0.4442        | 0.8180 | 400  | 0.5228          |
-| 0.4276        | 0.9816 | 480  | 0.5117          |
+| 0.1306        | 0.1636 | 80   | 0.1418          |
+| 0.0751        | 0.3272 | 160  | 0.1086          |
+| 0.0823        | 0.4908 | 240  | 0.0912          |
+| 0.0513        | 0.6544 | 320  | 0.0887          |
+| 0.0475        | 0.8180 | 400  | 0.0865          |
+| 0.0572        | 0.9816 | 480  | 0.0878          |
 
 
 ### Framework versions

adapter_config.json

@@ -16,23 +16,17 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 8,
+  "lora_alpha": 2,
   "lora_bias": false,
   "lora_dropout": 0.1,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 8,
+  "r": 1,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "down_proj",
-    "gate_proj",
-    "v_proj",
-    "up_proj",
-    "k_proj",
-    "o_proj",
     "q_proj"
   ],
   "task_type": null,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7771c4ae83c4484668cafccb78cc484b0fb3bf745bb9f4524f7603b9b8c3b83
-size 19210776
+oid sha256:aa45fcf4234cfeb65cda19093f2a2027cb1fd6a2d6bdd531746c7ba5b4f909b4
+size 61991040

runs/May09_19-08-59_ip-10-192-12-65/events.out.tfevents.1746817770.ip-10-192-12-65.127240.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1a2da24fe1698584c35b2414a943dcb2c2dc6650e0919a9214395e08e9eb5fb
+size 11621

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:181707e6ad5be9399b0865e3e1654144b70064c0fb18d1f3f5020fbec2478f8a
+oid sha256:d6b2b35f01b6ba33eb69bfb93231e484df2b55ee6d850262cb4923129e142ac3
 size 5304