L3Cube-Task0

README.md

@@ -0,0 +1,48 @@
+---
+license: mit
+base_model: ai4bharat/indic-bert
+tags:
+- generated_from_trainer
+model-index:
+- name: Best_Model_indic_bert
+  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. -->
+
+# Best_Model_indic_bert
+
+This model is a fine-tuned version of [ai4bharat/indic-bert](https://huggingface.co/ai4bharat/indic-bert) on an unknown dataset.
+
+## 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: 64
+- eval_batch_size: 16
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-07
+- lr_scheduler_type: linear
+- num_epochs: 2
+
+### Framework versions
+
+- Transformers 4.41.2
+- Pytorch 2.1.2
+- Datasets 2.19.2
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,43 @@
+{
+  "_name_or_path": "ai4bharat/indic-bert",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0,
+  "classifier_dropout": null,
+  "down_scale_factor": 1,
+  "embedding_size": 128,
+  "gap_size": 0,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "initializer_range": 0.02,
+  "inner_group_num": 1,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "net_structure_type": 0,
+  "num_attention_heads": 12,
+  "num_hidden_groups": 1,
+  "num_hidden_layers": 12,
+  "num_memory_blocks": 0,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 200000
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01507b57c07ae3a384338fcdfb3876f740d2dc88cddb43094733bf4d57aa9e76
+size 958598148

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:236f7d518b40f254348890013aa79d178e65fe32e07010afa78d3697146325d4
+size 5112