add model

README.md

@@ -11,16 +11,16 @@ probably proofread and complete it, then remove this comment. -->
 
 # t5-small-finetuned-tf-xsum
 
-This model was trained from scratch on xsum dataset.
+This model was trained from scratch on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 2.4711
-- Validation Loss: 2.2703
-- Train Rouge1: 32.2768
-- Train Rouge2: 11.0460
-- Train Rougel: 26.2472
-- Train Rougelsum: 26.1540
-- Train Gen Len: 18.825
-- Epoch: 1
+- Train Loss: 2.4305
+- Validation Loss: 2.2432
+- Train Rouge1: 29.3935
+- Train Rouge2: 8.3337
+- Train Rougel: 22.2859
+- Train Rougelsum: 22.3557
+- Train Gen Len: 18.65
+- Epoch: 0
 
 ## Model description
 
@@ -46,13 +46,12 @@ The following hyperparameters were used during training:
 
 | Train Loss | Validation Loss | Train Rouge1 | Train Rouge2 | Train Rougel | Train Rougelsum | Train Gen Len | Epoch |
 |:----------:|:---------------:|:------------:|:------------:|:------------:|:---------------:|:-------------:|:-----:|
-| 2.5174     | 2.2979          | 32.3706      | 11.5463      | 26.4253      | 26.3525         | 18.75         | 0     |
-| 2.4711     | 2.2703          | 32.2768      | 11.0460      | 26.2472      | 26.1540         | 18.825        | 1     |
+| 2.4305     | 2.2432          | 29.3935      | 8.3337       | 22.2859      | 22.3557         | 18.65         | 0     |
 
 
 ### Framework versions
 
-- Transformers 4.20.1
+- Transformers 4.21.1
 - TensorFlow 2.8.2
-- Datasets 2.3.2
+- Datasets 2.4.0
 - Tokenizers 0.12.1

config.json

@@ -53,7 +53,7 @@
       "prefix": "translate English to Romanian: "
     }
   },
-  "transformers_version": "4.20.1",
+  "transformers_version": "4.21.1",
   "use_cache": true,
   "vocab_size": 32128
 }

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad6c00e7942c2d5abd021d1e22aa29ad02de7b5bf20a980f56ea9e4f7c030195
+oid sha256:5f19e6aeea75c641f0b1100d1e1cdef784c4c616b9776e2aab0042e27a0365b9
 size 242301848