Model save

README.md

@@ -15,8 +15,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [microsoft/git-base](https://huggingface.co/microsoft/git-base) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0646
-- Bleu Score: 0.0501
+- Loss: 6.4422
+- Bleu Score: 0.0
 
 ## Model description
 
@@ -43,18 +43,14 @@ The following hyperparameters were used during training:
 - total_train_batch_size: 16
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 10
+- num_epochs: 2
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Bleu Score |
 |:-------------:|:------:|:----:|:---------------:|:----------:|
-| 7.4395 | 1.7544 | 50 | 4.7486 | 0.0011 |
-| 2.8193 | 3.5088 | 100 | 0.9704 | 0.0094 |
-| 0.4044 | 5.2632 | 150 | 0.1138 | 0.0588 |
-| 0.0733 | 7.0175 | 200 | 0.0661 | 0.0438 |
-| 0.0434 | 8.7719 | 250 | 0.0646 | 0.0501 |
+| 7.925 | 1.7544 | 50 | 6.4422 | 0.0 |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:214ca2f8048582112373059e9c9ba3adfad8c3018ce4f73bf0935f6388fbf049
+oid sha256:ba737e068683a8028c0c428421b4711a7e84b0a86a8be5716a7397e0f3926bd6
 size 706516040

runs/Aug02_04-42-18_fe738dc76da4/events.out.tfevents.1722573748.fe738dc76da4.285.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb094f25227cec3cee27fd287a36c69a0b5a8cccb7af4c70e670df2c82d5e9be
-size 5582
+oid sha256:b2ac60344eaa2ac393f49d31ea2e8aca79ea533efa38f3f032baea61c0e62f89
+size 5930

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c20b03e87e180d45dbe58ba6cbd37fa2f329ef8e51ef46dc7d1f3ba7bfc77b4
+oid sha256:ad04a4fcfbec15dd0ab0e1b44991913d62474ec34b3dfd075b0ca43a06d6ed78
 size 5112