Upload TFBartForConditionalGeneration

README.md

@@ -15,9 +15,9 @@ probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [facebook/bart-large](https://huggingface.co/facebook/bart-large) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 0.5390
-- Validation Loss: 0.8504
-- Epoch: 6
+- Train Loss: 0.4108
+- Validation Loss: 0.6862
+- Epoch: 7
 
 ## Model description
 
@@ -43,18 +43,19 @@ The following hyperparameters were used during training:
 
 | Train Loss | Validation Loss | Epoch |
 |:----------:|:---------------:|:-----:|
-| 1.5397     | 1.0943          | 0     |
-| 1.0308     | 0.9304          | 1     |
-| 0.9037     | 0.8744          | 2     |
-| 0.7231     | 0.8223          | 3     |
-| 0.6445     | 0.8153          | 4     |
-| 0.5842     | 0.7929          | 5     |
-| 0.5390     | 0.8504          | 6     |
+| 1.4774     | 1.0330          | 0     |
+| 0.9993     | 0.8665          | 1     |
+| 0.7898     | 0.8213          | 2     |
+| 0.6723     | 0.7351          | 3     |
+| 0.5816     | 0.7387          | 4     |
+| 0.5306     | 0.6879          | 5     |
+| 0.4547     | 0.6966          | 6     |
+| 0.4108     | 0.6862          | 7     |
 
 
 ### Framework versions
 
-- Transformers 4.33.0
+- Transformers 4.33.1
 - TensorFlow 2.12.0
-- Datasets 2.14.4
+- Datasets 2.14.5
 - Tokenizers 0.13.3

config.json

@@ -67,7 +67,7 @@
       "num_beams": 6
     }
   },
-  "transformers_version": "4.33.0",
+  "transformers_version": "4.33.1",
   "use_cache": true,
   "vocab_size": 50265
 }

generation_config.json

@@ -9,5 +9,5 @@
   "no_repeat_ngram_size": 3,
   "num_beams": 4,
   "pad_token_id": 1,
-  "transformers_version": "4.33.0"
+  "transformers_version": "4.33.1"
 }

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c7aaed66589fbe62d4978d68ef63f31300a7bcb823aa7ae2357502a5a1cbed9
+oid sha256:d4ad4b80352ff701b9a8b2e9c243bb956f79f7346e65ede91216d4140578f4a4
 size 1625925412