Training in progress epoch 0

README.md

@@ -1,5 +1,6 @@
 ---
 license: apache-2.0
+base_model: bert-base-uncased
 tags:
 - generated_from_keras_callback
 model-index:
@@ -14,9 +15,9 @@ probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 1.9628
-- Validation Loss: 1.8647
-- Epoch: 4
+- Train Loss: 2.0970
+- Validation Loss: 1.8569
+- Epoch: 0
 
 ## Model description
 
@@ -42,16 +43,12 @@ The following hyperparameters were used during training:
 
 | Train Loss | Validation Loss | Epoch |
 |:----------:|:---------------:|:-----:|
-| 2.0947     | 1.8478          | 0     |
-| 1.9615     | 1.8739          | 1     |
-| 1.9655     | 1.8581          | 2     |
-| 1.9618     | 1.8774          | 3     |
-| 1.9628     | 1.8647          | 4     |
+| 2.0970     | 1.8569          | 0     |
 
 
 ### Framework versions
 
-- Transformers 4.26.1
-- TensorFlow 2.11.0
-- Datasets 2.10.1
-- Tokenizers 0.13.2
+- Transformers 4.31.0
+- TensorFlow 2.12.0
+- Datasets 2.13.1
+- Tokenizers 0.13.3

checkpoint/extra_data.pickle

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0bbccb8cc419d4bb75ba4af607f786a3277c17a6426c01354508eb0dc66c1752
+oid sha256:dccceae5178f18725b48dadb8b4c414030fc7cdecfe3637b18b97ae374e9eeb6
 size 876130159

checkpoint/weights.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77fb5d659cf487d6217b95873c56af65a2785fc6b4949a640aa10aeb867b2662
-size 533687680
+oid sha256:9957f259e997077ee3d1d3120f80601c056e33603d2de7ee426f2dd6ec808d0e
+size 533687616

config.json

@@ -18,7 +18,7 @@
   "num_hidden_layers": 12,
   "pad_token_id": 0,
   "position_embedding_type": "absolute",
-  "transformers_version": "4.26.1",
+  "transformers_version": "4.31.0",
   "type_vocab_size": 2,
   "use_cache": true,
   "vocab_size": 30522

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f56618403cdf5727b87ba4b8a0d02f46d06c9a37f3ef107ebb5fa8a86f64d85b
-size 533687680
+oid sha256:9957f259e997077ee3d1d3120f80601c056e33603d2de7ee426f2dd6ec808d0e
+size 533687616

tokenizer_config.json

@@ -1,12 +1,11 @@
 {
+  "clean_up_tokenization_spaces": true,
   "cls_token": "[CLS]",
   "do_lower_case": true,
   "mask_token": "[MASK]",
   "model_max_length": 512,
-  "name_or_path": "bert-base-uncased",
   "pad_token": "[PAD]",
   "sep_token": "[SEP]",
-  "special_tokens_map_file": null,
   "strip_accents": null,
   "tokenize_chinese_chars": true,
   "tokenizer_class": "BertTokenizer",