End of training

README.md

@@ -13,8 +13,8 @@ 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: 4.6877
-- Exact Match: 0.0
+- Loss: 0.6800
+- Exact Match: 0.165
 
 ## Model description
 
@@ -39,13 +39,22 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 1
+- num_epochs: 10
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Exact Match |
 |:-------------:|:-----:|:----:|:---------------:|:-----------:|
-| 5.0517        | 1.0   | 4    | 4.6877          | 0.0         |
+| 2.1419        | 1.0   | 313  | 1.3197          | 0.01        |
+| 1.1804        | 2.0   | 626  | 1.0833          | 0.023       |
+| 0.8888        | 3.0   | 939  | 0.9529          | 0.062       |
+| 0.7167        | 4.0   | 1252 | 0.9488          | 0.052       |
+| 0.5985        | 5.0   | 1565 | 0.8626          | 0.09        |
+| 0.514         | 6.0   | 1878 | 0.7982          | 0.115       |
+| 0.439         | 7.0   | 2191 | 0.7420          | 0.144       |
+| 0.3851        | 8.0   | 2504 | 0.6876          | 0.15        |
+| 0.3434        | 9.0   | 2817 | 0.6794          | 0.178       |
+| 0.3174        | 10.0  | 3130 | 0.6800          | 0.165       |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73c440bc49e923a988cf435451bf1ec699a0bb14cea490470d9f7d9b2680bb18
+oid sha256:bd89516243a31537d2ae1963e01df839e9aee338734648f5ee1b1f38f19304fb
 size 2699200