Training in progress, step 500

README.md

@@ -1,6 +1,6 @@
 ---
 license: apache-2.0
-base_model: distilbert/distilbert-base-uncased
+base_model: distilbert-base-uncased
 tags:
 - generated_from_trainer
 datasets:
@@ -23,23 +23,22 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.9285
+      value: 0.9215
     - name: F1
       type: f1
-      value: 0.9286327520264782
+      value: 0.9214718883562769
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 should probably proofread and complete it, then remove this comment. -->
 
-[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/wzy_study/huggingface/runs/0l0zgyh5)
 # distilbert-base-uncased-finetuned-emotion
 
-This model is a fine-tuned version of [distilbert/distilbert-base-uncased](https://huggingface.co/distilbert/distilbert-base-uncased) on the emotion 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: 0.2044
-- Accuracy: 0.9285
-- F1: 0.9286
+- Loss: 0.2186
+- Accuracy: 0.9215
+- F1: 0.9215
 
 ## Model description
 
@@ -70,13 +69,13 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
-| 0.8044        | 1.0   | 250  | 0.2926          | 0.912    | 0.9117 |
-| 0.2398        | 2.0   | 500  | 0.2044          | 0.9285   | 0.9286 |
+| 0.8382        | 1.0   | 250  | 0.3176          | 0.905    | 0.9037 |
+| 0.2522        | 2.0   | 500  | 0.2186          | 0.9215   | 0.9215 |
 
 
 ### Framework versions
 
-- Transformers 4.42.3
-- Pytorch 2.2.2+cu118
-- Datasets 2.20.0
+- Transformers 4.40.2
+- Pytorch 2.2.2+cu121
+- Datasets 2.19.1
 - Tokenizers 0.19.1

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "distilbert/distilbert-base-uncased",
+  "_name_or_path": "distilbert-base-uncased",
   "activation": "gelu",
   "architectures": [
     "DistilBertForSequenceClassification"
@@ -36,6 +36,6 @@
   "sinusoidal_pos_embds": false,
   "tie_weights_": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.42.3",
+  "transformers_version": "4.44.2",
   "vocab_size": 30522
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2ce212226e175f577d261a6d64354acde68201e254704c885539aeb6e400d1d
+oid sha256:dfa70f88e8133ae54f1b9ae7615b9d1efedee76678c7ba135312a94bc134d79a
 size 267844872

tokenizer.json

@@ -1,19 +1,7 @@
 {
   "version": "1.0",
-  "truncation": {
-    "direction": "Right",
-    "max_length": 512,
-    "strategy": "LongestFirst",
-    "stride": 0
-  },
-  "padding": {
-    "strategy": "BatchLongest",
-    "direction": "Right",
-    "pad_to_multiple_of": null,
-    "pad_id": 0,
-    "pad_type_id": 0,
-    "pad_token": "[PAD]"
-  },
+  "truncation": null,
+  "padding": null,
   "added_tokens": [
     {
       "id": 0,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a785c926e694c579e1399c9aa3102ddda6c6996f86c0a87ba5ff809669cb6e08
+oid sha256:0c48e82856ef5b9765636f9d515fd70f4ceb58316aa2f32aab657cad83f98504
 size 5240