OctavianB/BERT_emotion_entailment

README.md

@@ -1,10 +1,13 @@
 ---
 license: apache-2.0
-base_model: bert-base-uncased
+base_model: distilbert-base-uncased
 tags:
 - generated_from_trainer
 metrics:
 - accuracy
+- f1
+- precision
+- recall
 model-index:
 - name: test_trainer
   results: []
@@ -15,10 +18,13 @@ should probably proofread and complete it, then remove this comment. -->
 
 # test_trainer
 
-This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the None dataset.
+This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.4441
-- Accuracy: 0.4533
+- Loss: 0.5486
+- Accuracy: 0.9374
+- F1: 0.5984
+- Precision: 0.7067
+- Recall: 0.5189
 
 ## Model description
 
@@ -43,20 +49,20 @@ 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: 3.0
+- num_epochs: 3
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Accuracy |
-|:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 1.1863        | 1.0   | 1281 | 1.9083          | 0.4524   |
-| 0.8655        | 2.0   | 2562 | 2.0523          | 0.4483   |
-| 0.5372        | 3.0   | 3843 | 2.4441          | 0.4533   |
+| Training Loss | Epoch | Step  | Validation Loss | Accuracy | F1     | Precision | Recall |
+|:-------------:|:-----:|:-----:|:---------------:|:--------:|:------:|:---------:|:------:|
+| 0.6604        | 1.0   | 9009  | 0.6454          | 0.9258   | 0.3847 | 0.7537    | 0.2583 |
+| 0.5947        | 2.0   | 18018 | 0.4696          | 0.9356   | 0.6004 | 0.6779    | 0.5387 |
+| 0.5444        | 3.0   | 27027 | 0.5486          | 0.9374   | 0.5984 | 0.7067    | 0.5189 |
 
 
 ### Framework versions
 
-- Transformers 4.36.2
+- Transformers 4.37.1
 - Pytorch 2.1.0+cu121
 - Datasets 2.16.1
-- Tokenizers 0.15.0
+- Tokenizers 0.15.1

config.json

@@ -1,45 +1,25 @@
 {
-  "_name_or_path": "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,
-  "id2label": {
-    "0": "LABEL_0",
-    "1": "LABEL_1",
-    "2": "LABEL_2",
-    "3": "LABEL_3",
-    "4": "LABEL_4",
-    "5": "LABEL_5",
-    "6": "LABEL_6"
-  },
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
-  "label2id": {
-    "LABEL_0": 0,
-    "LABEL_1": 1,
-    "LABEL_2": 2,
-    "LABEL_3": 3,
-    "LABEL_4": 4,
-    "LABEL_5": 5,
-    "LABEL_6": 6
-  },
-  "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": "4.36.2",
-  "type_vocab_size": 2,
-  "use_cache": true,
+  "transformers_version": "4.37.1",
   "vocab_size": 30522
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2177581fad7136ac8d8b5bb287c5b983ba139181119a0b730bbc7f48a63597f
-size 437974028
+oid sha256:8d14dca093553a7648b5c03b492dd3b93551f1a068ddaca4b0986338817dce82
+size 267832560

runs/Jan25_07-41-14_155994e85fd6/events.out.tfevents.1706168477.155994e85fd6.2012.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6847c17b912871c73d5a507b0083d6e7f1e60c4b3a55d1fd43aa44dcf9322800
+size 14556

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0b559c482c5637add2412cc8c1a7523fd9e788325e4b24a2a8986581b0a7f76
+oid sha256:378e0e36c069bc242e0e3be19ce262d4bb1595e70a2056ec87a90793312e3f88
 size 4664