Upload TFRobertaForSequenceClassification

README.md

@@ -12,25 +12,25 @@ probably proofread and complete it, then remove this comment. -->
 
 # Roberta-base-financial-sentiment-analysis
 
-This model is a fine-tuned version of [cardiffnlp/twitter-roberta-base-sentiment-latest](https://huggingface.co/cardiffnlp/twitter-roberta-base-sentiment-latest) on the financial_phrasebank dataset.
+This model is a fine-tuned version of [cardiffnlp/twitter-roberta-base-sentiment-latest](https://huggingface.co/cardiffnlp/twitter-roberta-base-sentiment-latest) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 0.0030
-- Train Accuracy: 0.9988
-- Validation Loss: 0.3030
-- Validation Accuracy: 0.9421
+- Train Loss: 0.0013
+- Train Accuracy: 1.0
+- Validation Loss: 0.2910
+- Validation Accuracy: 0.9431
 - Epoch: 9
 
 ## Model description
 
-This is a RoBERTa-base model trained on ~124M tweets from January 2018 to December 2021, and finetuned for sentiment analysis (positive, neutral, negative) with the TweetEval benchmark.
+More information needed
 
 ## Intended uses & limitations
 
-Sentiment analysis for text describing financial markets
+More information needed
 
 ## Training and evaluation data
 
-"The financial_phrasebank dataset contains 4840 sentences describing financial markets in english, with an associated sentiment label as positive, neutral, or negative.
+More information needed
 
 ## Training procedure
 
@@ -44,21 +44,21 @@ The following hyperparameters were used during training:
 
 | Train Loss | Train Accuracy | Validation Loss | Validation Accuracy | Epoch |
 |:----------:|:--------------:|:---------------:|:-------------------:|:-----:|
-| 0.3811     | 0.8688         | 0.2107          | 0.9324              | 0     |
-| 0.1596     | 0.9561         | 0.2188          | 0.9295              | 1     |
-| 0.1074     | 0.9706         | 0.2296          | 0.9373              | 2     |
-| 0.0846     | 0.9743         | 0.2560          | 0.9315              | 3     |
-| 0.0277     | 0.9921         | 0.3173          | 0.9247              | 4     |
-| 0.0151     | 0.9959         | 0.2698          | 0.9488              | 5     |
-| 0.0071     | 0.9975         | 0.3498          | 0.9353              | 6     |
-| 0.0038     | 0.9992         | 0.3178          | 0.9479              | 7     |
-| 0.0054     | 0.9979         | 0.3035          | 0.9431              | 8     |
-| 0.0030     | 0.9988         | 0.3030          | 0.9421              | 9     |
+| 0.4682     | 0.8080         | 0.3497          | 0.8687              | 0     |
+| 0.1674     | 0.9504         | 0.2655          | 0.9064              | 1     |
+| 0.1139     | 0.9681         | 0.2639          | 0.9189              | 2     |
+| 0.0847     | 0.9723         | 0.2259          | 0.9334              | 3     |
+| 0.0454     | 0.9876         | 0.2156          | 0.9440              | 4     |
+| 0.0262     | 0.9897         | 0.2593          | 0.9344              | 5     |
+| 0.0136     | 0.9963         | 0.3786          | 0.9170              | 6     |
+| 0.0043     | 0.9988         | 0.2589          | 0.9488              | 7     |
+| 0.0042     | 0.9988         | 0.2866          | 0.9450              | 8     |
+| 0.0013     | 1.0            | 0.2910          | 0.9431              | 9     |
 
 
 ### Framework versions
 
-- Transformers 4.31.0
+- Transformers 4.32.0
 - TensorFlow 2.12.0
 - Datasets 2.14.4
 - Tokenizers 0.13.3

config.json

@@ -31,7 +31,7 @@
   "pad_token_id": 1,
   "position_embedding_type": "absolute",
   "torch_dtype": "float32",
-  "transformers_version": "4.31.0",
+  "transformers_version": "4.32.0",
   "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 sha256:647428040e09986e0d87a49cc32f6b6d630051b6bc37f4f9d91ec7c9a3a5a248
+oid sha256:3d4ae52a947f7b66bc9c6c101c9da36282615fd7638d7dc9b40afaa04edf9049
 size 498881344