Abhi964/L3_Cube_Task_0_trial

README.md

@@ -0,0 +1,53 @@
+---
+license: mit
+base_model: ai4bharat/indic-bert
+tags:
+- generated_from_trainer
+model-index:
+- name: Trial1
+  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. -->
+
+# Trial1
+
+This model is a fine-tuned version of [ai4bharat/indic-bert](https://huggingface.co/ai4bharat/indic-bert) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.7663
+
+## 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: 10
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.42.3
+- Pytorch 2.3.0+cu121
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,44 @@
+{
+  "_name_or_path": "ai4bharat/indic-bert",
+  "architectures": [
+    "AlbertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0,
+  "bos_token_id": 2,
+  "classifier_dropout_prob": 0.1,
+  "down_scale_factor": 1,
+  "embedding_size": 128,
+  "eos_token_id": 3,
+  "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": "albert",
+  "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": "4.42.3",
+  "type_vocab_size": 2,
+  "vocab_size": 200000
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:beb3bd848bd4c2fb9e28fdcd5f011e96efa2de5310bbdfea389b8a272b37b3e1
+size 133787028

runs/Jul02_06-30-04_7977c367d0d7/events.out.tfevents.1719901807.7977c367d0d7.218.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:417c05734725edf07ce487c1755cad59a55fad8efb1ec24bde0f44ba20643192
+size 5481

runs/Jul02_06-34-00_7977c367d0d7/events.out.tfevents.1719902042.7977c367d0d7.218.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0edcf54c1514ddfd82b81e52f0c187bc0bacc0a1362c4d41f84fab8ee2a5c2a0
+size 5201

runs/Jul02_06-34-11_7977c367d0d7/events.out.tfevents.1719902051.7977c367d0d7.218.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d1c4fca1f0f0c4bb917e52028169e858f8584af65d1d5dc38cd99aeeaf87b2b
+size 11252

runs/Jul02_06-34-11_7977c367d0d7/events.out.tfevents.1719904906.7977c367d0d7.218.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef2412d95ca3a4a99b4cfb0d9143f4731d6cbf9999d20932523662799685cb49
+size 359

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e272eda491fd6749752820cd46b30c64169a443370b66c6fd3e9107d831af701
+size 5112