Upload TFBertForMaskedLM

README.md

@@ -14,9 +14,9 @@ probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [justinian336/chupeto](https://huggingface.co/justinian336/chupeto) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 0.9468
-- Validation Loss: 0.8882
-- Epoch: 3
+- Train Loss: 0.9364
+- Validation Loss: 0.8661
+- Epoch: 1
 
 ## Model description
 
@@ -42,15 +42,13 @@ The following hyperparameters were used during training:
 
 | Train Loss | Validation Loss | Epoch |
 |:----------:|:---------------:|:-----:|
-| 0.9745     | 0.8988          | 0     |
-| 0.9645     | 0.8890          | 1     |
-| 0.9574     | 0.8913          | 2     |
-| 0.9468     | 0.8882          | 3     |
+| 0.9454     | 0.8668          | 0     |
+| 0.9364     | 0.8661          | 1     |
 
 
 ### Framework versions
 
-- Transformers 4.26.1
+- Transformers 4.27.2
 - TensorFlow 2.11.0
 - Datasets 2.10.1
 - Tokenizers 0.13.2

config.json

@@ -24,7 +24,7 @@
   "pooler_type": "first_token_transform",
   "position_embedding_type": "absolute",
   "torch_dtype": "float32",
-  "transformers_version": "4.26.1",
+  "transformers_version": "4.27.2",
   "type_vocab_size": 2,
   "use_cache": true,
   "vocab_size": 119547

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6df78185e7b2c5f41aa4dcfe31361a1b9ba067c785727019ce9d96923a0eb7fb
-size 1081013380
+oid sha256:1368c731690d6e12bcf8ec5e9b6966c56a9b58996484c33053b45eadce7b6590
+size 1081013316