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: 2.0343
-- Validation Loss: 1.8209
+- Train Loss: 2.0197
+- Validation Loss: 1.8531
 - Epoch: 0
 
 ## Model description
@@ -43,12 +43,12 @@ The following hyperparameters were used during training:
 
 | Train Loss | Validation Loss | Epoch |
 |:----------:|:---------------:|:-----:|
-| 2.0343     | 1.8209          | 0     |
+| 2.0197     | 1.8531          | 0     |
 
 
 ### Framework versions
 
-- Transformers 4.34.0
-- TensorFlow 2.13.0
-- Datasets 2.14.5
+- Transformers 4.35.1
+- TensorFlow 2.14.0
+- Datasets 2.14.7
 - Tokenizers 0.14.1

config.json

@@ -19,7 +19,7 @@
   "num_hidden_layers": 6,
   "pad_token_id": 1,
   "position_embedding_type": "absolute",
-  "transformers_version": "4.34.0",
+  "transformers_version": "4.35.1",
   "type_vocab_size": 1,
   "use_cache": true,
   "vocab_size": 50265

special_tokens_map.json

@@ -2,7 +2,13 @@
   "bos_token": "<s>",
   "cls_token": "<s>",
   "eos_token": "</s>",
-  "mask_token": "<mask>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
   "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 sha256:93e047120970464a0f40f18d69b5cc098c61d889e832659c5b83263d1aa64ee0
+oid sha256:b1792b1bcdc7d40468d6efd320855c1a363177b17222b73a8f72f51949f3e0ce
 size 484838604

tokenizer.json

@@ -9,7 +9,7 @@
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
-      "normalized": false,
+      "normalized": true,
       "special": true
     },
     {
@@ -18,7 +18,7 @@
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
-      "normalized": false,
+      "normalized": true,
       "special": true
     },
     {
@@ -27,7 +27,7 @@
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
-      "normalized": false,
+      "normalized": true,
       "special": true
     },
     {
@@ -36,7 +36,7 @@
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
-      "normalized": false,
+      "normalized": true,
       "special": true
     },
     {

tokenizer_config.json

@@ -4,7 +4,7 @@
     "0": {
       "content": "<s>",
       "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": true
@@ -12,7 +12,7 @@
     "1": {
       "content": "<pad>",
       "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": true
@@ -20,7 +20,7 @@
     "2": {
       "content": "</s>",
       "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": true
@@ -28,7 +28,7 @@
     "3": {
       "content": "<unk>",
       "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": true
@@ -42,7 +42,6 @@
       "special": true
     }
   },
-  "additional_special_tokens": [],
   "bos_token": "<s>",
   "clean_up_tokenization_spaces": true,
   "cls_token": "<s>",