sil-ai/madlad400-finetuned-engNASB-swhONEN

README.md

@@ -16,8 +16,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [jbochi/madlad400-3b-mt](https://huggingface.co/jbochi/madlad400-3b-mt) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 7.6123
-- Chrf: 21.2726
+- Loss: 7.4433
+- Chrf: 37.7656
 
 ## Model description
 
@@ -49,13 +49,13 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Chrf    |
-|:-------------:|:-----:|:----:|:---------------:|:-------:|
-| 8.3321        | 1.0   | 447  | 7.9944          | 16.8707 |
-| 8.2447        | 2.0   | 894  | 7.9054          | 16.7970 |
-| 7.8946        | 3.0   | 1341 | 7.7068          | 19.7205 |
-| 7.8613        | 4.0   | 1788 | 7.6445          | 20.4812 |
-| 7.5683        | 5.0   | 2235 | 7.6123          | 21.2726 |
+| Training Loss | Epoch  | Step | Validation Loss | Chrf    |
+|:-------------:|:------:|:----:|:---------------:|:-------:|
+| 7.5714        | 0.9997 | 1748 | 7.4837          | 36.0379 |
+| 7.5863        | 2.0    | 3497 | 7.4686          | 36.6073 |
+| 7.5366        | 2.9997 | 5245 | 7.4529          | 37.1613 |
+| 7.5282        | 4.0    | 6994 | 7.4461          | 37.4309 |
+| 7.6738        | 4.9986 | 8740 | 7.4433          | 37.7656 |
 
 
 ### Framework versions

adapter_config.json

@@ -20,8 +20,8 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q",
-    "v"
+    "v",
+    "q"
   ],
   "task_type": "SEQ_2_SEQ_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d71a0f601f08e49f17141ad2096cfe015022c17d64db12b595d0eeab3b1dad17
+oid sha256:f278fc9d96027d2b1edebfbedf8ea59657ed1e66a30543d9f26aeec16edb2879
 size 18928616