Training in progress epoch 0

README.md

@@ -13,10 +13,10 @@ probably proofread and complete it, then remove this comment. -->
 
 This model was trained from scratch on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 0.1314
-- Validation Loss: 0.1705
+- Train Loss: 0.1343
+- Validation Loss: 0.1610
 - Train Accuracy: 0.945
-- Epoch: 2
+- Epoch: 0
 
 ## Model description
 
@@ -42,9 +42,7 @@ The following hyperparameters were used during training:
 
 | Train Loss | Validation Loss | Train Accuracy | Epoch |
 |:----------:|:---------------:|:--------------:|:-----:|
-| 0.4879     | 0.2200          | 0.9355         | 0     |
-| 0.1768     | 0.1752          | 0.937          | 1     |
-| 0.1314     | 0.1705          | 0.945          | 2     |
+| 0.1343     | 0.1610          | 0.945          | 0     |
 
 
 ### Framework versions

special_tokens_map.json

@@ -1,7 +1,25 @@
 {
-  "bos_token": "<s>",
-  "cls_token": "<s>",
-  "eos_token": "</s>",
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
   "mask_token": {
     "content": "<mask>",
     "lstrip": true,
@@ -9,7 +27,25 @@
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": "<pad>",
-  "sep_token": "</s>",
-  "unk_token": "<unk>"
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
 }

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61be112871d87e3ee066bea5135dffbf83db67b9859e86ace43f67261db7da93
+oid sha256:6a971d4a546bc9f70abd3d28ae119141a9dc155c961b1ec22d678e17529c58e9
 size 328641624

tokenizer_config.json

@@ -48,10 +48,14 @@
   "eos_token": "</s>",
   "errors": "replace",
   "mask_token": "<mask>",
+  "max_length": 512,
   "model_max_length": 512,
   "pad_token": "<pad>",
   "sep_token": "</s>",
+  "stride": 0,
   "tokenizer_class": "RobertaTokenizer",
   "trim_offsets": true,
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
   "unk_token": "<unk>"
 }