distilbert-emotion

README.md

@@ -1,13 +1,28 @@
 ---
 license: apache-2.0
-base_model: lilyray/results
+base_model: distilbert-base-uncased
 tags:
 - generated_from_trainer
+datasets:
+- emotion
 metrics:
 - accuracy
 model-index:
 - name: results
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: emotion
+      type: emotion
+      config: split
+      split: validation
+      args: split
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.944
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -15,10 +30,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # results
 
-This model is a fine-tuned version of [lilyray/results](https://huggingface.co/lilyray/results) on an unknown dataset.
+This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the emotion dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6652
-- Accuracy: 0.6314
+- Loss: 0.1774
+- Accuracy: 0.944
 
 ## Model description
 
@@ -37,23 +52,21 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 1.8306204953054156e-05
-- train_batch_size: 16
-- eval_batch_size: 16
-- seed: 21
+- learning_rate: 2e-05
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 5
+- num_epochs: 3
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| No log        | 1.0   | 179  | 0.5900          | 0.6866   |
-| No log        | 2.0   | 358  | 0.6840          | 0.6725   |
-| 0.4042        | 3.0   | 537  | 0.8741          | 0.6788   |
-| 0.4042        | 4.0   | 716  | 0.9795          | 0.6830   |
-| 0.4042        | 5.0   | 895  | 1.1036          | 0.6892   |
+| 0.2605        | 1.0   | 2000 | 0.2376          | 0.93     |
+| 0.1559        | 2.0   | 4000 | 0.1909          | 0.936    |
+| 0.1022        | 3.0   | 6000 | 0.1774          | 0.944    |
 
 
 ### Framework versions

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "lilyray/results",
+  "_name_or_path": "distilbert-base-uncased",
   "activation": "gelu",
   "architectures": [
     "DistilBertForSequenceClassification"
@@ -8,7 +8,23 @@
   "dim": 768,
   "dropout": 0.1,
   "hidden_dim": 3072,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5"
+  },
   "initializer_range": 0.02,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5
+  },
   "max_position_embeddings": 512,
   "model_type": "distilbert",
   "n_heads": 12,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bdecafe472d4c4ce35dc53f58e376c636f15f633933783ea912472ebd6bd7d80
-size 267832560
+oid sha256:92ae041864a7bce41a596cfef38707c5d3c31f362722cdd30190b65b86e33842
+size 267844872

runs/Mar10_13-43-34_cca651d8c56b/events.out.tfevents.1710078215.cca651d8c56b.1415.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a18c32855197aa4b52dcef37b4bd6b04697705a2f1e16a08d41b1bcd1db8e5d
+size 8546

runs/Mar10_13-43-34_cca651d8c56b/events.out.tfevents.1710078876.cca651d8c56b.1415.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fcad1fd398d90967a4b9baff86232beb3bc871c093aa8bcd39ed0354929cc584
+size 734

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c259b10a6cf51b228bad6e247bd6912729b2624957a2f8e300ab949f7922a7a
+oid sha256:cd3544d414a9fb66fa75771352d564d19e7fdfd9d0bca2c1724c31ecb4c3e3ba
 size 4920