Gergoe
/

mt5-small-finetuned-amazon-en-es

text2text-generation

Generated from Trainer

Inference Endpoints

Model card Files Files and versions Metrics Training metrics Community

Gergoe commited on May 16, 2022

Commit

b21a021

·

1 Parent(s): fa53324

update model card README.md

Files changed (1) hide show

README.md +12 -12

README.md CHANGED Viewed

@@ -18,10 +18,10 @@ should probably proofread and complete it, then remove this comment. -->
 This model is a fine-tuned version of [google/mt5-small](https://huggingface.co/google/mt5-small) on the None dataset.
 It achieves the following results on the evaluation set:
 - Loss: 3.2891
-- Rouge1: 15.3337
-- Rouge2: 6.5868
-- Rougel: 14.7498
-- Rougelsum: 14.7933
 ## Model description
@@ -52,14 +52,14 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch | Step  | Validation Loss | Rouge1  | Rouge2 | Rougel  | Rougelsum |
 |:-------------:|:-----:|:-----:|:---------------:|:-------:|:------:|:-------:|:---------:|
-| 7.0622        | 1.0   | 1276  | 3.5617          | 13.2058 | 4.865  | 12.842  | 12.8295   |
-| 4.0768        | 2.0   | 2552  | 3.4329          | 14.4762 | 6.5303 | 14.1011 | 14.0786   |
-| 3.7736        | 3.0   | 3828  | 3.3393          | 15.2657 | 6.5763 | 14.6912 | 14.6868   |
-| 3.5951        | 4.0   | 5104  | 3.3122          | 14.8748 | 6.2937 | 14.3369 | 14.4209   |
-| 3.477         | 5.0   | 6380  | 3.2991          | 15.0897 | 6.475  | 14.7468 | 14.7971   |
-| 3.4084        | 6.0   | 7656  | 3.3035          | 15.1618 | 6.331  | 14.5715 | 14.6335   |
-| 3.3661        | 7.0   | 8932  | 3.2959          | 15.3575 | 6.7167 | 14.7582 | 14.8562   |
-| 3.3457        | 8.0   | 10208 | 3.2891          | 15.3337 | 6.5868 | 14.7498 | 14.7933   |
 ### Framework versions

 This model is a fine-tuned version of [google/mt5-small](https://huggingface.co/google/mt5-small) on the None dataset.
 It achieves the following results on the evaluation set:
 - Loss: 3.2891
+- Rouge1: 15.35
+- Rouge2: 6.4925
+- Rougel: 14.8921
+- Rougelsum: 14.6312
 ## Model description
 | Training Loss | Epoch | Step  | Validation Loss | Rouge1  | Rouge2 | Rougel  | Rougelsum |
 |:-------------:|:-----:|:-----:|:---------------:|:-------:|:------:|:-------:|:---------:|
+| 7.0622        | 1.0   | 1276  | 3.5617          | 13.2417 | 4.8928 | 12.8258 | 12.8078   |
+| 4.0768        | 2.0   | 2552  | 3.4329          | 14.5681 | 6.4922 | 14.0621 | 13.9709   |
+| 3.7736        | 3.0   | 3828  | 3.3393          | 15.1942 | 6.5262 | 14.7138 | 14.6049   |
+| 3.5951        | 4.0   | 5104  | 3.3122          | 14.8813 | 6.2962 | 14.507  | 14.3477   |
+| 3.477         | 5.0   | 6380  | 3.2991          | 15.0992 | 6.3888 | 14.8397 | 14.5606   |
+| 3.4084        | 6.0   | 7656  | 3.3035          | 15.1897 | 6.2292 | 14.6686 | 14.4488   |
+| 3.3661        | 7.0   | 8932  | 3.2959          | 15.3489 | 6.5702 | 14.9211 | 14.701    |
+| 3.3457        | 8.0   | 10208 | 3.2891          | 15.35   | 6.4925 | 14.8921 | 14.6312   |
 ### Framework versions