End of training

README.md

@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [bigscience/mt0-large](https://huggingface.co/bigscience/mt0-large) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0043
+- Loss: 0.0015
 
 ## Model description
 
@@ -48,11 +48,11 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 0.576         | 1.0   | 157  | 0.2631          |
-| 0.1453        | 2.0   | 314  | 0.0342          |
-| 0.0622        | 3.0   | 471  | 0.0198          |
-| 0.0294        | 4.0   | 628  | 0.0061          |
-| 0.0302        | 5.0   | 785  | 0.0043          |
+| 0.5765        | 1.0   | 157  | 0.2644          |
+| 0.1485        | 2.0   | 314  | 0.0381          |
+| 0.0619        | 3.0   | 471  | 0.0112          |
+| 0.0287        | 4.0   | 628  | 0.0017          |
+| 0.0297        | 5.0   | 785  | 0.0015          |
 
 
 ### Framework versions

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f3935bbc314af0ad407bca12a511be02c4de3f458b92911e9e6f6b232948e1db
+oid sha256:4b9090ff20f305ceb5de7c98cf9e1a57ad45b43002ec8b1b3ac9a9c081adf030
 size 9477544

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de1d2064b2338cc0d56939cf3ecdc8c45bab141956725533ec4ba9c10871a089
-size 4283
+oid sha256:d8abca0c522e63b92d28a3ab7f2a42f5803b836c91918119e076d6472f1333be
+size 4219