bert-base-case-financial-news-twitter-sentiment

README.md

@@ -4,6 +4,9 @@ license: apache-2.0
 base_model: bert-base-cased
 tags:
 - generated_from_trainer
+metrics:
+- accuracy
+- f1
 model-index:
 - name: twitter_trainer
   results: []
@@ -15,6 +18,12 @@ should probably proofread and complete it, then remove this comment. -->
 # twitter_trainer
 
 This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.6231
+- Accuracy: 79.1
+- P: 97.2874
+- R: 107.8862
+- F1: 102.3130
 
 ## Model description
 
@@ -42,13 +51,19 @@ The following hyperparameters were used during training:
 - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.1
-- num_epochs: 1
+- num_epochs: 7
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy | P       | R        | F1       |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:-------:|:--------:|:--------:|
-| No log        | 0.992 | 62   | 0.9867          | 66.5     | 90.1379 | 132.1537 | 107.1751 |
+| No log        | 1.0   | 63   | 1.0913          | 64.3     | 89.9301 | 138.4284 | 109.0292 |
+| No log        | 2.0   | 126  | 0.8107          | 67.3     | 90.5817 | 128.2353 | 106.1688 |
+| No log        | 3.0   | 189  | 0.6766          | 74.6     | 92.8424 | 112.6984 | 101.8113 |
+| No log        | 4.0   | 252  | 0.6369          | 76.4     | 95.0107 | 108.6390 | 101.3688 |
+| No log        | 5.0   | 315  | 0.6300          | 78.3     | 97.6935 | 106.8348 | 102.0599 |
+| No log        | 6.0   | 378  | 0.6253          | 79.3     | 97.4302 | 107.4494 | 102.1948 |
+| No log        | 6.896 | 434  | 0.6231          | 79.1     | 97.2874 | 107.8862 | 102.3130 |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3da953ba079b14638c11b1aa95e4a1bba20744c7cc75dc13e2a09a8997c24d70
+oid sha256:310eddb0465f9774bcfeb5e877d8cdf8b68c0309b5678a61284e5e0b993ac60c
 size 433279996

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44962e8da4e7626306f98cdf9639ba3704847d2af1070260ff650b9f6504ad1e
+oid sha256:8d9c2891c8e61f86ed749859cfbf3997b8f566b91234a2ddf00e4cd04386c2b2
 size 5304