add model

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

README.md

@@ -0,0 +1,74 @@
+---
+license: apache-2.0
+tags:
+- generated_from_trainer
+datasets:
+- tamilmixsentiment
+metrics:
+- accuracy
+model_index:
+- name: emoBERTTamil
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: tamilmixsentiment
+      type: tamilmixsentiment
+      args: default
+    metric:
+      name: Accuracy
+      type: accuracy
+      value: 0.671
+---
+
+<!-- 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. -->
+
+# emoBERTTamil
+
+This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the tamilmixsentiment dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.9666
+- Accuracy: 0.671
+
+## 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: 5e-05
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 3.0
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 1.1128        | 1.0   | 250  | 1.0290          | 0.672    |
+| 1.0226        | 2.0   | 500  | 1.0172          | 0.686    |
+| 0.9137        | 3.0   | 750  | 0.9666          | 0.671    |
+
+
+### Framework versions
+
+- Transformers 4.9.2
+- Pytorch 1.9.0+cu102
+- Datasets 1.11.0
+- Tokenizers 0.10.3

config.json

@@ -0,0 +1,40 @@
+{
+  "_name_or_path": "bert-base-uncased",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "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"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.9.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e0d1e5c1108b432d901cd8bf72e4eaf614845b816e56a1d9df42a1da51cbdee
+size 438028461

runs/Aug22_15-15-57_6e80acf7d2f8/1629645371.4616039/events.out.tfevents.1629645371.6e80acf7d2f8.73.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76229f400c7092f1e812899fc96e671d12e45870a3535a721822300b778602a7
+size 4194

runs/Aug22_15-15-57_6e80acf7d2f8/events.out.tfevents.1629645371.6e80acf7d2f8.73.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff4e88928e9a9811309c26b37c7ec68ebcf85d240bbbedb9b7a751187dc556c1
+size 4950

runs/Aug22_15-15-57_6e80acf7d2f8/events.out.tfevents.1629646164.6e80acf7d2f8.73.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5972ea526999989fa26dbf9a67a014b663fb99ced624a9fe3c390ae8e73b5ac
+size 363

special_tokens_map.json

@@ -0,0 +1 @@
+{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "bert-base-uncased", "tokenizer_class": "BertTokenizer"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2559222510cf55541ad89de11e950c68bb50ce056744ae7440200c1f681c070
+size 2671