End of training

README.md

@@ -5,23 +5,23 @@ tags:
 metrics:
 - rouge
 model-index:
-- name: flan-t5-small-taboo-for-llms
+- name: flan-t5-small-taboo-for-llms-repo
   results: []
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 should probably proofread and complete it, then remove this comment. -->
 
-# flan-t5-small-taboo-for-llms
+# flan-t5-small-taboo-for-llms-repo
 
-This model is a fine-tuned version of [google/flan-t5-small](https://huggingface.co/google/flan-t5-small) on the None dataset.
+This model is a fine-tuned version of [vlkn/flan-t5-small-taboo-for-llms](https://huggingface.co/vlkn/flan-t5-small-taboo-for-llms) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.9537
-- Rouge1: 21.6856
-- Rouge2: 6.9727
-- Rougel: 20.6587
-- Rougelsum: 20.5292
-- Gen Len: 15.5
+- Loss: 2.4246
+- Rouge1: 31.1045
+- Rouge2: 13.9259
+- Rougel: 30.6689
+- Rougelsum: 31.0064
+- Gen Len: 19.0
 
 ## Model description
 
@@ -46,13 +46,22 @@ 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: 1
+- num_epochs: 10
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Rouge1  | Rouge2 | Rougel  | Rougelsum | Gen Len |
-|:-------------:|:-----:|:----:|:---------------:|:-------:|:------:|:-------:|:---------:|:-------:|
-| No log        | 1.0   | 6    | 2.9537          | 21.6856 | 6.9727 | 20.6587 | 20.5292   | 15.5    |
+| Training Loss | Epoch | Step | Validation Loss | Rouge1  | Rouge2  | Rougel  | Rougelsum | Gen Len |
+|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:-------:|
+| No log        | 1.0   | 6    | 2.7272          | 29.2133 | 12.3393 | 27.335  | 27.1699   | 16.6667 |
+| No log        | 2.0   | 12   | 2.6153          | 29.2351 | 10.0862 | 27.3832 | 27.3832   | 17.0    |
+| No log        | 3.0   | 18   | 2.5546          | 31.4176 | 11.5699 | 29.5658 | 29.5658   | 17.0    |
+| No log        | 4.0   | 24   | 2.5072          | 31.2198 | 12.9464 | 30.3189 | 30.4981   | 19.0    |
+| No log        | 5.0   | 30   | 2.4758          | 31.6534 | 14.1563 | 30.3831 | 30.5725   | 19.0    |
+| No log        | 6.0   | 36   | 2.4548          | 31.5148 | 14.1563 | 31.0945 | 31.4799   | 19.0    |
+| No log        | 7.0   | 42   | 2.4410          | 31.1045 | 13.9259 | 30.6689 | 31.0064   | 19.0    |
+| No log        | 8.0   | 48   | 2.4319          | 31.1045 | 13.9259 | 30.6689 | 31.0064   | 19.0    |
+| No log        | 9.0   | 54   | 2.4265          | 31.1045 | 13.9259 | 30.6689 | 31.0064   | 19.0    |
+| No log        | 10.0  | 60   | 2.4246          | 31.1045 | 13.9259 | 30.6689 | 31.0064   | 19.0    |
 
 
 ### Framework versions

logs/events.out.tfevents.1685801092.85a114cc9afe.156.5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8af35769847c3406f9487768ed094193a299aa9a22184ce3b17c02ae10541983
-size 10286
+oid sha256:28c533bba136e76fd880e25ddd8a188942038da49113d5143fec60b3657f3de5
+size 10634

logs/events.out.tfevents.1685801279.85a114cc9afe.156.7

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac7691f8ee9f65b5afa837c6794d150ed98e6b46cde76e06a44dfaa5e003061e
+size 603