Update model weights and readme

README.md

@@ -7,13 +7,34 @@ tags:
 datasets:
 - financial_phrasebank
 widget:
-- text: "FTSE100 fell sharply today."
-- text: "Oil near one-month high."
+- text: "INDEX100 fell sharply today."
+- text: "ImaginaryJetCo bookings hit by Omicron variant as losses total £1bn."
+- text: "Q1 ImaginaryGame's earnings beat expectations."
+- text: "Should we buy IMAGINARYSTOCK today?"
 ---
 
 # FINPerceiver
 FINPerceiver is a fine-tuned Perceiver IO language model for financial sentiment analysis.
 More details on the training process of this model are available on the [GitHub repository](https://github.com/warwickai/fin-perceiver).
 
+We achieved the following results with 10-fold cross validation.
+
+```
+eval/accuracy  0.8624 (stdev 0.01922)
+eval/f1        0.8416 (stdev 0.03738)
+eval/loss      0.4314 (stdev 0.05295)
+eval/precision 0.8438 (stdev 0.02938)
+eval/recall    0.8415 (stdev 0.04458)
+```
+
+The hyperparameters used are as follows.
+
+```
+per_device_train_batch_size  16
+per_device_eval_batch_size   16
+num_train_epochs             4
+learning_rate                2e-5
+```
+
 ## Datasets
 This model was trained on the Financial PhraseBank (>= 50% agreement)

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1afcdf5aa5ad0e792f01f13fa80fb30626b5a8f3a501a30cadaefe6b9c0b5e5e
-size 824589613
+oid sha256:a215a79a89c02c5821329e584c6de405e44dda87d1ebd7e4923fc46f927cf878
+size 824551789