reevan/bert_base_kan_rom

README.md

@@ -4,6 +4,9 @@ base_model: bert-base-uncased
 tags:
 - generated_from_trainer
 metrics:
+- precision
+- recall
+- f1
 - accuracy
 model-index:
 - name: model
@@ -17,8 +20,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6832
-- Accuracy: 0.7827
+- Loss: 0.7107
+- Precision: 0.7026
+- Recall: 0.6852
+- F1: 0.6885
+- Accuracy: 0.6858
 
 ## Model description
 
@@ -47,13 +53,13 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Accuracy |
-|:-------------:|:-----:|:----:|:---------------:|:--------:|
-| No log        | 1.0   | 327  | 0.9373          | 0.6278   |
-| 0.971         | 2.0   | 654  | 0.7674          | 0.7218   |
-| 0.971         | 3.0   | 981  | 0.6970          | 0.7559   |
-| 0.6976        | 4.0   | 1308 | 0.6832          | 0.7740   |
-| 0.4782        | 5.0   | 1635 | 0.6832          | 0.7827   |
+| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| No log        | 1.0   | 171  | 0.9182          | 0.5766    | 0.5701 | 0.5725 | 0.5709   |
+| No log        | 2.0   | 342  | 0.8927          | 0.5607    | 0.5567 | 0.5492 | 0.5594   |
+| 0.8332        | 3.0   | 513  | 0.7695          | 0.6618    | 0.6318 | 0.6375 | 0.6322   |
+| 0.8332        | 4.0   | 684  | 0.7402          | 0.6859    | 0.6658 | 0.6684 | 0.6667   |
+| 0.8332        | 5.0   | 855  | 0.7107          | 0.7026    | 0.6852 | 0.6885 | 0.6858   |
 
 
 ### Framework versions

config.json

@@ -12,16 +12,14 @@
   "id2label": {
     "0": "Negative",
     "1": "Positive",
-    "2": "Mixed feelings",
-    "3": "unknown state"
+    "2": "Neutral"
   },
   "initializer_range": 0.02,
   "intermediate_size": 3072,
   "label2id": {
-    "Mixed feelings": 2,
     "Negative": 0,
-    "Positive": 1,
-    "unknown state": 3
+    "Neutral": 2,
+    "Positive": 1
   },
   "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65fe32950e21b00f92561a2a9277806adfab5508de48c2f3d37b7d71dc7cd826
-size 437964800
+oid sha256:c75946e2b8057700bd0c91bc357ded4407d4f8d83501a6302ac1d3d7dc72783f
+size 437961724

runs/Apr18_17-51-33_2406a229272e/events.out.tfevents.1713462694.2406a229272e.200.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf9334d72e6eca36c49695f793cbfbe90384daa4a7cdfb59971b45d5240c95ac
+size 7607

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d325e3cba7182be21d1693a544ae59c1c57425fd9b9fcee023c9182c18552a8e
+oid sha256:1a8e97ac4c5001ee9ab1a03567ee47fc24943d8217b7a6572fefad864861c3b5
 size 4856