End of training

README.md

@@ -17,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.5649
-- Accuracy: 0.8008
+- Loss: 0.7541
+- Accuracy: 0.7980
 
 ## Model description
 
@@ -43,16 +43,18 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 2
+- num_epochs: 3
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| No log        | 1.0   | 204  | 0.5372          | 0.8274   |
-| No log        | 1.0   | 204  | 0.6288          | 0.7847   |
-| No log        | 2.0   | 408  | 0.4156          | 0.8704   |
-| No log        | 2.0   | 408  | 0.5649          | 0.8008   |
+| No log        | 1.0   | 204  | 0.1647          | 0.9579   |
+| No log        | 1.0   | 204  | 0.6233          | 0.8001   |
+| No log        | 2.0   | 408  | 0.1083          | 0.9699   |
+| No log        | 2.0   | 408  | 0.7254          | 0.7910   |
+| 0.2523        | 3.0   | 612  | 0.0809          | 0.9797   |
+| 0.2523        | 3.0   | 612  | 0.7541          | 0.7980   |
 
 
 ### Framework versions

config.json

@@ -10,16 +10,16 @@
   "hidden_dim": 3072,
   "id2label": {
     "0": "anger",
-    "1": "sadness",
-    "2": "joy",
-    "3": "optimism"
+    "1": "joy",
+    "2": "optimism",
+    "3": "sadness"
   },
   "initializer_range": 0.02,
   "label2id": {
     "anger": 0,
-    "joy": 2,
-    "optimism": 3,
-    "sadness": 1
+    "joy": 1,
+    "optimism": 2,
+    "sadness": 3
   },
   "max_position_embeddings": 512,
   "model_type": "distilbert",

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb29fd7a8f240820a21595796abfe7f90dfcb49ee9b86d3d9c803fbf9fbe1182
+oid sha256:a37bc7d36b4a672b960ad93e7c754b03f122a019fdf6540b74a568dd876b4054
 size 267838720

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:985906296400bfba8b0f496195499d54c82756bca4c3c0d1793f592499e0dfe4
+oid sha256:3a8e31921469b2145505ad445520f1a54c40d0a7faf19ace3abe170786d1b17c
 size 4856