distilbert-irony

README.md

@@ -3,26 +3,11 @@ license: apache-2.0
 base_model: distilbert-base-uncased
 tags:
 - generated_from_trainer
-datasets:
-- emotion
 metrics:
 - accuracy
 model-index:
 - name: 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: 0.9385
+  results: []
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -30,10 +15,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # results
 
-This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/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 an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.1706
-- Accuracy: 0.9385
+- Loss: 0.5392
+- Accuracy: 0.7362
 
 ## Model description
 
@@ -64,16 +49,16 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 0.257         | 1.0   | 1000 | 0.1801          | 0.934    |
-| 0.1568        | 2.0   | 2000 | 0.1773          | 0.9325   |
-| 0.1095        | 3.0   | 3000 | 0.1706          | 0.9385   |
-| 0.0803        | 4.0   | 4000 | 0.1866          | 0.939    |
-| 0.0565        | 5.0   | 5000 | 0.2082          | 0.9345   |
+| No log        | 1.0   | 179  | 0.6078          | 0.6534   |
+| No log        | 2.0   | 358  | 0.6082          | 0.6681   |
+| 0.5295        | 3.0   | 537  | 0.6529          | 0.6796   |
+| 0.5295        | 4.0   | 716  | 0.7743          | 0.6859   |
+| 0.5295        | 5.0   | 895  | 0.8280          | 0.6827   |
 
 
 ### Framework versions
 
-- Transformers 4.38.1
+- Transformers 4.38.2
 - Pytorch 2.1.0+cu121
 - Datasets 2.18.0
 - Tokenizers 0.15.2

config.json

@@ -1,27 +1,25 @@
 {
-  "_name_or_path": "google-bert/bert-base-uncased",
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
   "architectures": [
-    "BertForSequenceClassification"
+    "DistilBertForSequenceClassification"
   ],
-  "attention_probs_dropout_prob": 0.1,
-  "classifier_dropout": null,
-  "gradient_checkpointing": false,
-  "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.1,
-  "hidden_size": 768,
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
-  "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
-  "model_type": "bert",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 12,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
   "pad_token_id": 0,
-  "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
   "torch_dtype": "float32",
   "transformers_version": "4.38.2",
-  "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 sha256:5e6b7192ac023b99453abae6426209233d1e86113b4ae39a3cd7fc4c6e67469c
-size 437958648
+oid sha256:26f66a305c7749bdf45977de4fb6af47d6647ff1bbebdff8eb539c9f97a173be
+size 267832560

runs/Mar10_00-13-37_9e66d5520874/events.out.tfevents.1710029623.9e66d5520874.3219.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12fb3e690fef62266dd2ce39e06bf0f95dea1b8f9856a7b2dae85f42851e626d
+size 862

runs/Mar10_00-14-03_9e66d5520874/events.out.tfevents.1710029644.9e66d5520874.3219.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:439c86645932fa855e641ee94f120866003719877764330468331f6660217a4c
+size 6605

runs/Mar10_00-14-03_9e66d5520874/events.out.tfevents.1710029902.9e66d5520874.3219.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1114079dc49b59ec19c7917402c968fee92eb9863030b9c558b71257e8417d0
+size 734

tokenizer_config.json

@@ -52,6 +52,6 @@
   "sep_token": "[SEP]",
   "strip_accents": null,
   "tokenize_chinese_chars": true,
-  "tokenizer_class": "BertTokenizer",
+  "tokenizer_class": "DistilBertTokenizer",
   "unk_token": "[UNK]"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2bf4adf8eb808dd644c69cea85cfe008935e4f450bf19284dd29f846fa0895b7
+oid sha256:053eafb695e31e083430bae8494f4ba1f8bc65d8882f3d8df0e1a3d692ff2eb4
 size 4920