End of training

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,68 @@
+---
+license: mit
+base_model: xlm-roberta-base
+tags:
+- generated_from_trainer
+metrics:
+- precision
+- recall
+- f1
+- accuracy
+model-index:
+- name: hindi-roberta-ner
+  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. -->
+
+# hindi-roberta-ner
+
+This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0006
+- Precision: 0.9957
+- Recall: 0.9983
+- F1: 0.9970
+- Accuracy: 0.9997
+
+## 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: 2e-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
+
+### Training results
+
+| Training Loss | Epoch | Step   | Validation Loss | Precision | Recall | F1     | Accuracy |
+|:-------------:|:-----:|:------:|:---------------:|:---------:|:------:|:------:|:--------:|
+| 0.0074        | 1.0   | 47891  | 0.0052          | 0.9839    | 0.9850 | 0.9844 | 0.9985   |
+| 0.0027        | 2.0   | 95782  | 0.0016          | 0.9926    | 0.9969 | 0.9948 | 0.9994   |
+| 0.0014        | 3.0   | 143673 | 0.0006          | 0.9957    | 0.9983 | 0.9970 | 0.9997   |
+
+
+### Framework versions
+
+- Transformers 4.33.0
+- Pytorch 2.0.0
+- Datasets 2.14.5
+- Tokenizers 0.13.3

config.json

@@ -0,0 +1,58 @@
+{
+  "_name_or_path": "xlm-roberta-base",
+  "architectures": [
+    "XLMRobertaForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LOCATION",
+    "1": "BRAND",
+    "2": "TITLE_OBJECT",
+    "3": "TITLE_PERSON",
+    "4": "PERSON",
+    "5": "DESIGNATION",
+    "6": "ORGANIZATION",
+    "7": "ABBREVIATION",
+    "8": "TIME",
+    "9": "NUMBER",
+    "10": "MEASURE",
+    "11": "TERMS",
+    "12": "O"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "ABBREVIATION": 7,
+    "BRAND": 1,
+    "DESIGNATION": 5,
+    "LOCATION": 0,
+    "MEASURE": 10,
+    "NUMBER": 9,
+    "O": 12,
+    "ORGANIZATION": 6,
+    "PERSON": 4,
+    "TERMS": 11,
+    "TIME": 8,
+    "TITLE_OBJECT": 2,
+    "TITLE_PERSON": 3
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.33.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:545dba0d0534e5a7ad91b6aa470cdd1facabe1243783b81297bf0e9fd6dbb241
+size 1109920489

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2c509a525eb51aebb33fb59c24ee923c1d4c1db23c3ae81fe05ccf354084f7b
+size 17082758

tokenizer_config.json

@@ -0,0 +1,19 @@
+{
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "__type": "AddedToken",
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61e4bd76b06ba8bfd1bf6491e1490e2f656f3928165ac4485bf8f7b59840266f
+size 4027