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: 1.4155
-- Accuracy: 0.6747
+- Loss: 1.6234
+- Accuracy: 0.7054
 
 ## Model description
 
@@ -49,9 +49,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 0.7101        | 1.0   | 716  | 0.6199          | 0.6597   |
-| 0.5864        | 2.0   | 1432 | 0.7953          | 0.6901   |
-| 0.3081        | 3.0   | 2148 | 1.3766          | 0.6869   |
+| 0.7149        | 1.0   | 716  | 0.6495          | 0.6346   |
+| 0.561         | 2.0   | 1432 | 0.9508          | 0.7089   |
+| 0.2295        | 3.0   | 2148 | 1.5088          | 0.7173   |
 
 
 ### 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 sha256:4bf76ecd6b0935debd1bba3f143d14dcba411a433f18ea01098aa34044e752fc
-size 267844872
+oid sha256:28d5fda8bdbfb4833b67583bf5d4297ff2ebfd86b2f1033660bb3bd6ba15de41
+size 437970952

runs/Mar15_01-02-10_7e523dcb7947/events.out.tfevents.1710464539.7e523dcb7947.18634.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e87d667f65529782ff57b7b148e9d8bd522c683447dcf02d7a4c64fa7d2a7a0
+size 346

runs/Mar15_01-02-46_7e523dcb7947/events.out.tfevents.1710464598.7e523dcb7947.18634.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fe58cf7221b914fe00d07ac6520ff31a51dde6127f67eba2e1aadb0aa3cf3db
+size 346

runs/Mar15_01-03-41_7e523dcb7947/events.out.tfevents.1710464632.7e523dcb7947.18634.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0d0854097819a9ede81f4cf449aa3da3ce2d2f69dcae8b03803970f2e3943d4
+size 7278

runs/Mar15_01-03-41_7e523dcb7947/events.out.tfevents.1710465038.7e523dcb7947.18634.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12a52665ece2b4949fcdf8f5104c2230bf6315898230e97fd3b5f8f9e9701042
+size 1057

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86787c3d97e3ab8123245daf20bd0ec8da9b700b0ae985858f082b0d92ee93b8
+oid sha256:b9eb3e141ef2273dd9a8db7310724a881b781800037a627082affdc731af360f
 size 4856