ashuc27/Bert_tweetEval

README.md

@@ -1,6 +1,6 @@
 ---
 license: apache-2.0
-base_model: distilbert-base-uncased
+base_model: bert-base-uncased
 tags:
 - generated_from_trainer
 metrics:
@@ -15,10 +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 an unknown dataset.
+This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.4324
-- Accuracy: 0.6735
+- Loss: 1.5357
+- Accuracy: 0.7130
 
 ## Model description
 
@@ -39,7 +39,7 @@ More information needed
 The following hyperparameters were used during training:
 - learning_rate: 2.8e-05
 - train_batch_size: 4
-- eval_batch_size: 64
+- eval_batch_size: 32
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
@@ -49,9 +49,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 0.7114        | 1.0   | 716  | 0.6388          | 0.6283   |
-| 0.556         | 2.0   | 1432 | 0.7971          | 0.6890   |
-| 0.3142        | 3.0   | 2148 | 1.4232          | 0.6775   |
+| 0.7088        | 1.0   | 716  | 0.6241          | 0.6545   |
+| 0.5523        | 2.0   | 1432 | 0.8595          | 0.7225   |
+| 0.2348        | 3.0   | 2148 | 1.5133          | 0.7089   |
 
 
 ### Framework versions

config.json

@@ -1,13 +1,14 @@
 {
-  "_name_or_path": "distilbert-base-uncased",
-  "activation": "gelu",
+  "_name_or_path": "bert-base-uncased",
   "architectures": [
-    "DistilBertForSequenceClassification"
+    "BertForSequenceClassification"
   ],
-  "attention_dropout": 0.1,
-  "dim": 768,
-  "dropout": 0.1,
-  "hidden_dim": 3072,
+  "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",
@@ -17,6 +18,7 @@
     "5": "LABEL_5"
   },
   "initializer_range": 0.02,
+  "intermediate_size": 3072,
   "label2id": {
     "LABEL_0": 0,
     "LABEL_1": 1,
@@ -25,17 +27,17 @@
     "LABEL_4": 4,
     "LABEL_5": 5
   },
+  "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
-  "model_type": "distilbert",
-  "n_heads": 12,
-  "n_layers": 6,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
   "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:ecd68f30f498a582b8e800bc016ab1bc93f1232839fd44baac1d0e36a14d1596
-size 267844872
+oid sha256:69376644e7495ef9a6cb6fa30af4f5828cac9b7776c5cae01bb6fa24ccde4471
+size 437970952

runs/Mar15_00-11-46_7e523dcb7947/events.out.tfevents.1710461515.7e523dcb7947.5607.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68bc00d364cebca1212ee50e16c70877bbab0232538d66264bd311b97321f730
+size 7278

runs/Mar15_00-11-46_7e523dcb7947/events.out.tfevents.1710462008.7e523dcb7947.5607.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5dc9af05be7a5854dcb5408c74a605e9e6f87e8109012c3ff77fa4754047f342
+size 1057

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9ddc761cab49090c0cfb69ea5e413ba8c5856cfcb9935b2221bbf8b511e6837
+oid sha256:c36d6939fda7f2aad5f2894a3a9379c1eb360571421ed4530ca03c3d34ceec45
 size 4856