ashuc27/DistiliBert_tweetEval

README.md

@@ -1,6 +1,6 @@
 ---
 license: apache-2.0
-base_model: bert-base-uncased
+base_model: distilbert-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 [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown 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: 1.5357
-- Accuracy: 0.7130
+- Loss: 1.4155
+- Accuracy: 0.6747
 
 ## 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: 32
+- eval_batch_size: 64
 - 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 |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 0.7088        | 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   |
+| 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   |
 
 
 ### Framework versions

config.json

@@ -1,14 +1,13 @@
 {
-  "_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,
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
   "id2label": {
     "0": "LABEL_0",
     "1": "LABEL_1",
@@ -18,7 +17,6 @@
     "5": "LABEL_5"
   },
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
   "label2id": {
     "LABEL_0": 0,
     "LABEL_1": 1,
@@ -27,17 +25,17 @@
     "LABEL_4": 4,
     "LABEL_5": 5
   },
-  "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 sha256:69376644e7495ef9a6cb6fa30af4f5828cac9b7776c5cae01bb6fa24ccde4471
-size 437970952
+oid sha256:4bf76ecd6b0935debd1bba3f143d14dcba411a433f18ea01098aa34044e752fc
+size 267844872

runs/Mar15_00-51-26_7e523dcb7947/events.out.tfevents.1710463892.7e523dcb7947.15672.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b28cf91193fd7b919ee1f74444945039b8f5431d02d9e00369925eccae17c1c
+size 346

runs/Mar15_00-52-32_7e523dcb7947/events.out.tfevents.1710463956.7e523dcb7947.15672.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2213000cc63d434ebb7355172ea7176cc8758a0232561cc98be02608b6d0ec97
+size 346

runs/Mar15_00-53-21_7e523dcb7947/events.out.tfevents.1710464020.7e523dcb7947.15672.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8625a474f88f8e82fe960f4307a723793b0b7dbcb19fbad543791aa01088d7a4
+size 346

runs/Mar15_00-53-57_7e523dcb7947/events.out.tfevents.1710464043.7e523dcb7947.15672.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd393d85ad972f2a724d2ea24a26873e3fa23080b230659496adf748954ef624
+size 346

runs/Mar15_00-54-26_7e523dcb7947/events.out.tfevents.1710464071.7e523dcb7947.15672.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba5cb19e06139ae4912ae3ca6f27530f2c15b5fca606ec22c1d0f6c55540f857
+size 7166

runs/Mar15_00-54-26_7e523dcb7947/events.out.tfevents.1710464307.7e523dcb7947.15672.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5fad0b55e812481423596046b1c148aedc737fbe2ffaa51d5fe2f5eb5538ba6b
+size 1057

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c36d6939fda7f2aad5f2894a3a9379c1eb360571421ed4530ca03c3d34ceec45
+oid sha256:86787c3d97e3ab8123245daf20bd0ec8da9b700b0ae985858f082b0d92ee93b8
 size 4856