Training complete

README.md

@@ -18,9 +18,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [google/mt5-base](https://huggingface.co/google/mt5-base) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 4.9746
-- Bleu: 4.6434
-- Gen Len: 16.6341
+- Loss: 7.2943
+- Bleu: 0.5766
+- Gen Len: 9.6098
 
 ## Model description
 
@@ -40,19 +40,21 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 5.6e-05
-- train_batch_size: 2
-- eval_batch_size: 2
+- train_batch_size: 8
+- eval_batch_size: 8
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 2
+- num_epochs: 4
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Bleu   | Gen Len |
 |:-------------:|:-----:|:----:|:---------------:|:------:|:-------:|
-| No log        | 1.0   | 61   | 5.8517          | 4.6627 | 17.5854 |
-| No log        | 2.0   | 122  | 4.9746          | 4.6434 | 16.6341 |
+| No log        | 1.0   | 16   | 10.5602         | 0.076  | 3.8049  |
+| No log        | 2.0   | 32   | 8.3458          | 0.1439 | 5.1951  |
+| No log        | 3.0   | 48   | 7.5921          | 0.4483 | 9.2683  |
+| No log        | 4.0   | 64   | 7.2943          | 0.5766 | 9.6098  |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69c43b5c6bc9d61bb61d05e68acbfd87f70ec9903fd404121003b1529089d2ba
+oid sha256:b0f4173980d3de2eec1b43c9d6ef5c50aafe30499e2268e53ac63e89872e3641
 size 2329638768

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:599ca58558683298ee873ff88b9a83abba0e9fb2f4b049c3cb2e399e975ee1c4
+oid sha256:852ab5934ebf62194288c520669a4ee89a1ef83cad6ec8185d903b70e02620b3
 size 4984