javicorvi/pretoxtm-sentence-classifier

README.md

@@ -20,11 +20,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [microsoft/BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext](https://huggingface.co/microsoft/BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0802
-- Precision: 0.9778
-- Recall: 0.9801
+- Loss: 0.1181
+- Precision: 0.9788
+- Recall: 0.9800
 - Accuracy: 0.9795
-- F1: 0.9789
+- F1: 0.9794
 
 ## Model description
 
@@ -43,28 +43,26 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 7.755382954990098e-06
-- train_batch_size: 8
+- learning_rate: 1.1848183151867784e-05
+- train_batch_size: 4
 - eval_batch_size: 8
-- seed: 42
+- seed: 1
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 10
+- num_epochs: 3
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | Accuracy | F1     |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:--------:|:------:|
-| No log        | 1.0   | 257  | 0.1410          | 0.9593    | 0.9684 | 0.9636   | 0.9628 |
-| 0.1997        | 2.0   | 514  | 0.0802          | 0.9778    | 0.9801 | 0.9795   | 0.9789 |
-| 0.1997        | 3.0   | 771  | 0.1103          | 0.9824    | 0.9848 | 0.9841   | 0.9836 |
-| 0.0514        | 4.0   | 1028 | 0.1139          | 0.9798    | 0.9829 | 0.9818   | 0.9813 |
-| 0.0514        | 5.0   | 1285 | 0.1208          | 0.9804    | 0.9821 | 0.9818   | 0.9812 |
+| 0.2543        | 1.0   | 514  | 0.1181          | 0.9788    | 0.9800 | 0.9795   | 0.9794 |
+| 0.1344        | 2.0   | 1028 | 0.1488          | 0.9767    | 0.9775 | 0.9773   | 0.9771 |
+| 0.0419        | 3.0   | 1542 | 0.1520          | 0.9767    | 0.9775 | 0.9773   | 0.9771 |
 
 
 ### Framework versions
 
-- Transformers 4.39.2
+- Transformers 4.39.3
 - Pytorch 2.2.1+cu121
 - Datasets 2.18.0
 - Tokenizers 0.15.2

config.json

@@ -27,7 +27,7 @@
   "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",
   "torch_dtype": "float32",
-  "transformers_version": "4.39.2",
+  "transformers_version": "4.39.3",
   "type_vocab_size": 2,
   "use_cache": true,
   "vocab_size": 30522

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe9c64c65528f684f2f6150137c58978bb21575884774b713d2cbd36f112df19
+oid sha256:91cae5380f97a366947d372f003284672937aded4e3edee7b9cefcef68097e15
 size 437958648

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02921f0a11a038bbebe5d34b968c7edcf6b3947e1b627936a700e9055974e7a4
-size 4920
+oid sha256:632010ddb485dfc0f4589869cb50862f46a9be39e3bc575c098c8ba3319e7b34
+size 4856