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: tamil-sentiment-distilbert
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: tamilmixsentiment
+      type: tamilmixsentiment
+      args: default
+    metric:
+      name: Accuracy
+      type: accuracy
+      value: 0.653
+---
+
+<!-- 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. -->
+
+# tamil-sentiment-distilbert
+
+This model is a fine-tuned version of [distilbert-base-cased](https://huggingface.co/distilbert-base-cased) on the tamilmixsentiment dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.0230
+- Accuracy: 0.653
+
+## 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 |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 1.0442        | 1.0   | 250  | 0.9883          | 0.674    |
+| 0.9227        | 2.0   | 500  | 0.9782          | 0.673    |
+| 0.7591        | 3.0   | 750  | 1.0230          | 0.653    |
+
+
+### 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": "distilbert-base-cased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "output_past": true,
+  "pad_token_id": 0,
+  "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": "4.9.2",
+  "vocab_size": 28996
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ebfdbb6e28cfd3782bdbfd25bb6db62900544dfbcca9bba7ddeb9b6df2ac218c
+size 263181425

runs/Aug23_06-28-04_514fc84c5b16/1629700088.1643567/events.out.tfevents.1629700088.514fc84c5b16.1599.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e051dd4321ff2c5cf52a4f1f58ba9349ac1734ce0dee6626b61eaa38d272dc4
+size 4250

runs/Aug23_06-28-04_514fc84c5b16/events.out.tfevents.1629700088.514fc84c5b16.1599.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba55db019b3239cb1c14ce24998b234de1c3050aa3c8445194351e8998788d14
+size 4891

runs/Aug23_06-28-04_514fc84c5b16/events.out.tfevents.1629700776.514fc84c5b16.1599.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52f00567038c78444f49d32231d057ebca794ce923216312886c78777ea6676f
+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": false, "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": "distilbert-base-cased", "tokenizer_class": "DistilBertTokenizer"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:495a039cf02ebfd7143e74b105961a10df8cbd2041e895362d0961b7670733c7
+size 2671