Training in progress, epoch 1

README.md

@@ -0,0 +1,62 @@
+---
+license: apache-2.0
+base_model: google/bert_uncased_L-2_H-128_A-2
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: berttiny-hateXplain-parentpretrained
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# berttiny-hateXplain-parentpretrained
+
+This model is a fine-tuned version of [google/bert_uncased_L-2_H-128_A-2](https://huggingface.co/google/bert_uncased_L-2_H-128_A-2) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.2286
+- Accuracy: 0.7601
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0001286744242350192
+- train_batch_size: 128
+- eval_batch_size: 128
+- seed: 33
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 7
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 0.236         | 1.0   | 121  | 0.2296          | 0.7581   |
+| 0.2239        | 2.0   | 242  | 0.2274          | 0.7591   |
+| 0.2174        | 3.0   | 363  | 0.2286          | 0.7601   |
+
+
+### Framework versions
+
+- Transformers 4.36.0.dev0
+- Pytorch 2.1.1
+- Datasets 2.15.0
+- Tokenizers 0.15.0

config.json

@@ -2,12 +2,17 @@
   "_name_or_path": "agvidit1/DistilledBert_HateSpeech_pretrain",
   "activation": "gelu",
   "architectures": [
-    "DistilBertForSequenceClassification"
+    "BertForSequenceClassification"
   ],
   "attention_dropout": 0.1,
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
   "dim": 768,
   "dropout": 0.1,
+  "hidden_act": "gelu",
   "hidden_dim": 3072,
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
   "id2label": {
     "0": 0,
     "1": 1,
@@ -15,17 +20,22 @@
     "3": 3
   },
   "initializer_range": 0.02,
+  "intermediate_size": 3072,
   "label2id": {
     "0": 0,
     "1": 1,
     "2": 2,
     "3": 3
   },
+  "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
-  "model_type": "distilbert",
+  "model_type": "bert",
   "n_heads": 12,
   "n_layers": 6,
+  "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,
@@ -33,5 +43,7 @@
   "tie_weights_": true,
   "torch_dtype": "float32",
   "transformers_version": "4.36.0.dev0",
+  "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:aa2ee73f8ef5e2aba8dc8552e2c60d53e640beb1de82bde1dd2ef5494cffb85b
-size 267838720
+oid sha256:a5f2b07901305af79e865683b356eb4ab715f6de4a310edcafd9a9f4f108274c
+size 437964800

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d867fd6fc4a219ef921faa090af65c09ea1d32483558946d8c240940c28b9f0
+oid sha256:bd291d568e2c39552c50319c78392acde4dc20f897814064a3491ade1c9c0893
 size 4792