Training in progress epoch 0

README.md

@@ -15,10 +15,10 @@ probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [ayshi/basic_distil](https://huggingface.co/ayshi/basic_distil) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 0.0347
-- Validation Loss: 0.9729
-- Train Accuracy: 0.7867
-- Epoch: 9
+- Train Loss: 0.0683
+- Validation Loss: 1.0267
+- Train Accuracy: 0.7422
+- Epoch: 0
 
 ## Model description
 
@@ -44,16 +44,7 @@ The following hyperparameters were used during training:
 
 | Train Loss | Validation Loss | Train Accuracy | Epoch |
 |:----------:|:---------------:|:--------------:|:-----:|
-| 0.3419     | 0.9411          | 0.7556         | 0     |
-| 0.2309     | 0.9458          | 0.7156         | 1     |
-| 0.1663     | 0.9184          | 0.7556         | 2     |
-| 0.1142     | 0.8916          | 0.7511         | 3     |
-| 0.0864     | 0.9570          | 0.7733         | 4     |
-| 0.0658     | 0.9529          | 0.7778         | 5     |
-| 0.0522     | 0.9422          | 0.7822         | 6     |
-| 0.0423     | 0.9622          | 0.7867         | 7     |
-| 0.0376     | 0.9713          | 0.7867         | 8     |
-| 0.0347     | 0.9729          | 0.7867         | 9     |
+| 0.0683     | 1.0267          | 0.7422         | 0     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:911531d7ff974f5ad817513920560180406e408a7732aca392052c8665aee5f0
-size 541448896
+oid sha256:37ca84008368ee2cc876eb5b2db720cd242a413332e3bee39ee68075665b0859
+size 541452232

tokenizer_config.json

@@ -52,11 +52,15 @@
   "cls_token": "[CLS]",
   "do_lower_case": false,
   "mask_token": "[MASK]",
+  "max_length": 512,
   "model_max_length": 512,
   "pad_token": "[PAD]",
   "sep_token": "[SEP]",
+  "stride": 0,
   "strip_accents": null,
   "tokenize_chinese_chars": true,
   "tokenizer_class": "DistilBertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
   "unk_token": "[UNK]"
 }