Upload TFRobertaForMaskedLM

README.md

@@ -1,8 +1,8 @@
 ---
 license: apache-2.0
+base_model: distilbert/distilroberta-base
 tags:
 - generated_from_keras_callback
-base_model: distilbert/distilroberta-base
 model-index:
 - name: distilroberta_trainedOnCACatalogue
   results: []
@@ -15,7 +15,9 @@ probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [distilbert/distilroberta-base](https://huggingface.co/distilbert/distilroberta-base) on an unknown dataset.
 It achieves the following results on the evaluation set:
-
+- Train Loss: 2.0395
+- Validation Loss: 2.0452
+- Epoch: 2
 
 ## Model description
 
@@ -34,16 +36,21 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- optimizer: None
+- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': 2e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay_rate': 0.01}
 - training_precision: float32
 
 ### Training results
 
+| Train Loss | Validation Loss | Epoch |
+|:----------:|:---------------:|:-----:|
+| 2.2110     | 2.0461          | 0     |
+| 2.1291     | 2.0448          | 1     |
+| 2.0395     | 2.0452          | 2     |
 
 
 ### Framework versions
 
-- Transformers 4.40.0
-- TensorFlow 2.15.1
-- Datasets 2.19.0
-- Tokenizers 0.19.1
+- Transformers 4.34.0
+- TensorFlow 2.12.1
+- Datasets 2.14.5
+- Tokenizers 0.14.1

config.json

@@ -19,7 +19,7 @@
   "num_hidden_layers": 6,
   "pad_token_id": 1,
   "position_embedding_type": "absolute",
-  "transformers_version": "4.40.0",
+  "transformers_version": "4.34.0",
   "type_vocab_size": 1,
   "use_cache": true,
   "vocab_size": 50265

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0af6b28e466a5ed2867470f9e1e8770b02ca3870f229c1d8a0a2b1909cd065da
+oid sha256:1cbc19b2af20f5e4c57e3170aff8b7bafc7efdc52220f9539218375890aa4f8c
 size 484838604