Training in progress epoch 0

README.md

@@ -15,8 +15,8 @@ probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [distilroberta-base](https://huggingface.co/distilroberta-base) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 2.1299
-- Validation Loss: 1.7090
+- Train Loss: 2.0840
+- Validation Loss: 1.8650
 - Epoch: 0
 
 ## Model description
@@ -43,12 +43,12 @@ The following hyperparameters were used during training:
 
 | Train Loss | Validation Loss | Epoch |
 |:----------:|:---------------:|:-----:|
-| 2.1299     | 1.7090          | 0     |
+| 2.0840     | 1.8650          | 0     |
 
 
 ### Framework versions
 
 - Transformers 4.35.2
 - TensorFlow 2.15.0
-- Datasets 2.17.0
+- Datasets 2.17.1
 - Tokenizers 0.15.2

special_tokens_map.json

@@ -9,7 +9,7 @@
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": "</s>",
+  "pad_token": "<pad>",
   "sep_token": "</s>",
   "unk_token": "<unk>"
 }

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e0d49405c1babe2a821cdaabba8e14a6680a10119edd6b97151b68fede29be24
+oid sha256:f53cf78cfba4a8d92207284c1179eb9f68534ebbb0baadeacac6e1fa3d1aed73
 size 484838604

tokenizer_config.json

@@ -49,7 +49,7 @@
   "errors": "replace",
   "mask_token": "<mask>",
   "model_max_length": 512,
-  "pad_token": "</s>",
+  "pad_token": "<pad>",
   "sep_token": "</s>",
   "tokenizer_class": "RobertaTokenizer",
   "trim_offsets": true,