Model save

README.md

@@ -1,5 +1,6 @@
 ---
 library_name: transformers
+base_model: indictrans-en-ne-checkpoint/checkpoint-732
 tags:
 - generated_from_trainer
 model-index:
@@ -12,9 +13,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # indictrans-en-ne-checkpoint
 
-This model was trained from scratch on an unknown dataset.
+This model is a fine-tuned version of [indictrans-en-ne-checkpoint/checkpoint-732](https://huggingface.co/indictrans-en-ne-checkpoint/checkpoint-732) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 11.1038
+- Loss: 10.7601
 
 ## Model description
 
@@ -41,16 +42,15 @@ The following hyperparameters were used during training:
 - total_train_batch_size: 2048
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 2
+- num_epochs: 3
 
 ### Training results
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 10.8035       | 0.4095 | 150  | 11.4138         |
-| 10.4287       | 0.8189 | 300  | 11.2105         |
-| 10.3006       | 1.2284 | 450  | 11.1235         |
-| 10.2617       | 1.6378 | 600  | 11.1038         |
+| 9.8002        | 0.8189 | 300  | 10.7568         |
+| 9.734         | 1.6378 | 600  | 10.7586         |
+| 9.7215        | 2.4567 | 900  | 10.7601         |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b40aa7edc394ce576587a78e70b414ebd9a0d87cf87542d261dd815ec8b096c8
+oid sha256:57ab9a212c34ac081c016977ec6a878b53636ae17a36dfd7aed8f52136c99d01
 size 549258952

runs/Aug23_18-51-30_ip-10-192-11-25/events.out.tfevents.1724439090.ip-10-192-11-25.1731.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba151ff754f417dc15f4fedf4c83a809a221b5c4a7c80f30cf9c46c023e99614
-size 44500
+oid sha256:63f86ff78a4f4e6d01ea2818587f096102b7952d0681a3e49210b2fc00a20c71
+size 53083