alayaran/bodo-t5-base-news-headline-ft

.gitignore

@@ -0,0 +1,2 @@
+checkpoint-*
+runs

README.md

@@ -7,12 +7,6 @@ metrics:
 model-index:
 - name: bodo-t5-base-news-headline-ft
   results: []
-license: mit
-datasets:
-- alayaran/bodo-news-headline
-language:
-- brx
-library_name: transformers
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -22,12 +16,12 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [alayaran/bodo-t5-base](https://huggingface.co/alayaran/bodo-t5-base) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 3.2921
-- Rouge1: 0.0107
+- Loss: 3.7051
+- Rouge1: 0.0
 - Rouge2: 0.0
-- Rougel: 0.0107
-- Rougelsum: 0.0107
-- Gen Len: 18.39
+- Rougel: 0.0
+- Rougelsum: 0.0
+- Gen Len: 18.51
 
 ## Model description
 
@@ -52,16 +46,32 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 4
+- num_epochs: 20
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
 |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
-| No log        | 1.0   | 215  | 3.3718          | 0.0067 | 0.0    | 0.0067 | 0.0067    | 18.79   |
-| No log        | 2.0   | 430  | 3.3196          | 0.004  | 0.0    | 0.004  | 0.004     | 18.83   |
-| 3.2677        | 3.0   | 645  | 3.3023          | 0.0107 | 0.0    | 0.0107 | 0.0107    | 18.47   |
-| 3.2677        | 4.0   | 860  | 3.2921          | 0.0107 | 0.0    | 0.0107 | 0.0107    | 18.39   |
+| No log        | 1.0   | 215  | 3.4320          | 0.005  | 0.0    | 0.005  | 0.005     | 18.54   |
+| No log        | 2.0   | 430  | 3.4632          | 0.004  | 0.0    | 0.004  | 0.004     | 18.61   |
+| 1.7652        | 3.0   | 645  | 3.5416          | 0.004  | 0.0    | 0.004  | 0.004     | 18.72   |
+| 1.7652        | 4.0   | 860  | 3.4878          | 0.004  | 0.0    | 0.004  | 0.004     | 18.42   |
+| 1.7484        | 5.0   | 1075 | 3.4530          | 0.004  | 0.0    | 0.004  | 0.004     | 18.39   |
+| 1.7484        | 6.0   | 1290 | 3.4678          | 0.004  | 0.0    | 0.004  | 0.004     | 18.25   |
+| 1.7311        | 7.0   | 1505 | 3.5064          | 0.005  | 0.0    | 0.005  | 0.005     | 18.29   |
+| 1.7311        | 8.0   | 1720 | 3.5868          | 0.008  | 0.0    | 0.008  | 0.008     | 18.46   |
+| 1.7311        | 9.0   | 1935 | 3.5522          | 0.0    | 0.0    | 0.0    | 0.0       | 18.39   |
+| 1.6771        | 10.0  | 2150 | 3.5595          | 0.0    | 0.0    | 0.0    | 0.0       | 18.57   |
+| 1.6771        | 11.0  | 2365 | 3.5799          | 0.0    | 0.0    | 0.0    | 0.0       | 18.64   |
+| 1.6422        | 12.0  | 2580 | 3.6062          | 0.0    | 0.0    | 0.0    | 0.0       | 18.62   |
+| 1.6422        | 13.0  | 2795 | 3.6093          | 0.0    | 0.0    | 0.0    | 0.0       | 18.62   |
+| 1.5939        | 14.0  | 3010 | 3.6359          | 0.0    | 0.0    | 0.0    | 0.0       | 18.49   |
+| 1.5939        | 15.0  | 3225 | 3.6230          | 0.0    | 0.0    | 0.0    | 0.0       | 18.62   |
+| 1.5939        | 16.0  | 3440 | 3.6537          | 0.0    | 0.0    | 0.0    | 0.0       | 18.51   |
+| 1.5636        | 17.0  | 3655 | 3.6624          | 0.0    | 0.0    | 0.0    | 0.0       | 18.55   |
+| 1.5636        | 18.0  | 3870 | 3.7012          | 0.0    | 0.0    | 0.0    | 0.0       | 18.45   |
+| 1.5324        | 19.0  | 4085 | 3.7114          | 0.0    | 0.0    | 0.0    | 0.0       | 18.45   |
+| 1.5324        | 20.0  | 4300 | 3.7051          | 0.0    | 0.0    | 0.0    | 0.0       | 18.51   |
 
 
 ### Framework versions
@@ -69,4 +79,4 @@ The following hyperparameters were used during training:
 - Transformers 4.34.0.dev0
 - Pytorch 2.0.1+cu117
 - Datasets 2.14.5
-- Tokenizers 0.13.3
+- Tokenizers 0.13.3

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4644caafae6ce7022ad8598ece01593b41023faf667d7377954129e424e37076
+oid sha256:0b897f1266e25035550c58e7633b8a389b28457e907c3fbe9e4c9e44ab727617
 size 802611381

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e550a599659cc21b83768b23c57682b7323b506522f3de2c7858202ff9266a41
+oid sha256:ba3e9d48972d6f123343d5d5c7ee8ba10119b8d26c621f06c18841fc6aaf4a4a
 size 4219