Model save

README.md

@@ -14,7 +14,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 3.4163
+- Loss: 3.2544
 
 ## Model description
 
@@ -46,9 +46,21 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step  | Validation Loss |
 |:-------------:|:-----:|:-----:|:---------------:|
-| 3.7975        | 0.32  | 5000  | 3.8163          |
-| 3.5694        | 0.64  | 10000 | 3.5999          |
-| 3.3983        | 0.96  | 15000 | 3.4163          |
+| 3.8254        | 0.064 | 5000  | 3.8259          |
+| 3.5877        | 0.128 | 10000 | 3.6043          |
+| 3.4987        | 0.192 | 15000 | 3.5176          |
+| 3.4495        | 0.256 | 20000 | 3.4692          |
+| 3.4157        | 0.32  | 25000 | 3.4390          |
+| 3.4003        | 0.384 | 30000 | 3.4159          |
+| 3.382         | 0.448 | 35000 | 3.4012          |
+| 3.3649        | 0.512 | 40000 | 3.3881          |
+| 3.3592        | 0.576 | 45000 | 3.3781          |
+| 3.3518        | 0.64  | 50000 | 3.3702          |
+| 3.3447        | 0.704 | 55000 | 3.3609          |
+| 3.3348        | 0.768 | 60000 | 3.3474          |
+| 3.2925        | 0.832 | 65000 | 3.3085          |
+| 3.2576        | 0.896 | 70000 | 3.2757          |
+| 3.2402        | 0.96  | 75000 | 3.2544          |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:14a73049118eb00022b428d10b8c7d9713770f38ef65f86eda0129f09ad2156f
+oid sha256:f2b7df33ffc0fd82f9e293b00783d8193039e5d145609168535212fa6b4523ea
 size 245234560

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86d71a19a4e8e2ae7a224dd51e85a427e5436faac9e034d1764e85669441181e
+oid sha256:376e1ae04e84cca9a92e134ee9edbbd668e7aa2e9d98dfb5c05a99260bd967e6
 size 5585