Training in progress epoch 0

README.md

@@ -14,10 +14,10 @@ probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 0.2014
-- Validation Loss: 0.1349
-- Train Accuracy: 0.95
-- Epoch: 13
+- Train Loss: 0.6634
+- Validation Loss: 0.6379
+- Train Accuracy: 0.625
+- Epoch: 0
 
 ## Model description
 
@@ -43,20 +43,7 @@ The following hyperparameters were used during training:
 
 | Train Loss | Validation Loss | Train Accuracy | Epoch |
 |:----------:|:---------------:|:--------------:|:-----:|
-| 0.0019     | 0.4504          | 0.85           | 0     |
-| 0.0017     | 0.4712          | 0.85           | 1     |
-| 0.0016     | 0.4817          | 0.85           | 2     |
-| 0.0016     | 0.4854          | 0.85           | 3     |
-| 0.0015     | 0.4889          | 0.85           | 4     |
-| 0.0014     | 0.4960          | 0.85           | 5     |
-| 0.0014     | 0.4971          | 0.85           | 6     |
-| 0.0013     | 0.4970          | 0.85           | 7     |
-| 0.0013     | 0.4994          | 0.85           | 8     |
-| 0.0012     | 0.5083          | 0.85           | 9     |
-| 0.0011     | 0.5147          | 0.85           | 10    |
-| 0.0722     | 0.6652          | 0.825          | 11    |
-| 0.0971     | 0.8475          | 0.8            | 12    |
-| 0.2014     | 0.1349          | 0.95           | 13    |
+| 0.6634     | 0.6379          | 0.625          | 0     |
 
 
 ### Framework versions

special_tokens_map.json

@@ -1,20 +1,7 @@
 {
-  "additional_special_tokens": [
-    "<s>NOTUSED",
-    "</s>NOTUSED",
-    "<_>"
-  ],
-  "bos_token": "<s>",
-  "cls_token": "<s>",
-  "eos_token": "</s>",
-  "mask_token": {
-    "content": "<mask>",
-    "lstrip": true,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "pad_token": "<pad>",
-  "sep_token": "</s>",
-  "unk_token": "<unk>"
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
 }

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97089274e4ff858a78d1b9173e574dd68f2be5b77e8be019d6174fe64564e220
+oid sha256:e0a3679a3067180ebecfcb831ef6bbb4e7133ebe06f63125657bb02f254d6908
 size 267955144

tokenizer_config.json

@@ -1,25 +1,13 @@
 {
-  "additional_special_tokens": [
-    "<s>NOTUSED",
-    "</s>NOTUSED",
-    "<_>"
-  ],
-  "bos_token": "<s>",
   "clean_up_tokenization_spaces": true,
-  "cls_token": "<s>",
-  "eos_token": "</s>",
-  "mask_token": {
-    "__type": "AddedToken",
-    "content": "<mask>",
-    "lstrip": true,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "model_max_length": 416,
-  "pad_token": "<pad>",
-  "sep_token": "</s>",
-  "sp_model_kwargs": {},
-  "tokenizer_class": "CamembertTokenizer",
-  "unk_token": "<unk>"
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
 }