End of training

README.md

@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [bigscience/mt0-small](https://huggingface.co/bigscience/mt0-small) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 21.6926
+- Loss: 10.3401
 
 ## Model description
 
@@ -44,10 +44,10 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss |
-|:-------------:|:-----:|:----:|:---------------:|
-| No log        | 1.0   | 339  | 22.3324         |
-| 23.3367       | 2.0   | 678  | 21.6926         |
+| Training Loss | Epoch | Step  | Validation Loss |
+|:-------------:|:-----:|:-----:|:---------------:|
+| 12.8444       | 1.0   | 16917 | 10.3394         |
+| 12.8649       | 2.0   | 33834 | 10.3401         |
 
 
 ### Framework versions

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ebeb3cb655bf34e5c0b7b1f1362d835278fcbd68128ba294d0073b3bbb8df67
+oid sha256:5b095f2a38b2c6b80549584edda865d315598c6554c93ef083ad6030bd9ca34c
 size 600419077

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b07064c05eb1dc2bec6d86ced100b22c73ac65bf376effb721a46a67d919323b
+oid sha256:c3f8ae86b11df14551f6a47632ee6d5c12743feb31bb012c189d2b4eba32c1c7
 size 4027