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

@@ -1,6 +1,6 @@
 ---
-license: apache-2.0
-base_model: google/muril-base-cased
+license: mit
+base_model: ai4bharat/indic-bert
 tags:
 - generated_from_trainer
 metrics:
@@ -18,13 +18,13 @@ should probably proofread and complete it, then remove this comment. -->
 
 # uner-muril-ner
 
-This model is a fine-tuned version of [google/muril-base-cased](https://huggingface.co/google/muril-base-cased) on an unknown dataset.
+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: 1.5456
-- Precision: 0.0
-- Recall: 0.0
-- F1: 0.0
-- Accuracy: 0.8266
+- Loss: 0.6152
+- Precision: 0.0391
+- Recall: 0.0131
+- F1: 0.0196
+- Accuracy: 0.8261
 
 ## Model description
 
@@ -53,13 +53,13 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1  | Accuracy |
-|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:---:|:--------:|
-| No log        | 1.0   | 144  | 1.8170          | 0.0       | 0.0    | 0.0 | 0.8266   |
-| No log        | 2.0   | 288  | 1.7102          | 0.0       | 0.0    | 0.0 | 0.8266   |
-| No log        | 3.0   | 432  | 1.6219          | 0.0       | 0.0    | 0.0 | 0.8266   |
-| 1.7546        | 4.0   | 576  | 1.5650          | 0.0       | 0.0    | 0.0 | 0.8266   |
-| 1.7546        | 5.0   | 720  | 1.5456          | 0.0       | 0.0    | 0.0 | 0.8266   |
+| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| No log        | 1.0   | 144  | 0.7361          | 0.0       | 0.0    | 0.0    | 0.8181   |
+| No log        | 2.0   | 288  | 0.6689          | 0.0       | 0.0    | 0.0    | 0.8181   |
+| No log        | 3.0   | 432  | 0.6523          | 0.0154    | 0.0016 | 0.0030 | 0.8182   |
+| 0.6809        | 4.0   | 576  | 0.6231          | 0.0375    | 0.0123 | 0.0185 | 0.8246   |
+| 0.6809        | 5.0   | 720  | 0.6152          | 0.0391    | 0.0131 | 0.0196 | 0.8261   |
 
 
 ### Framework versions

added_tokens.json

@@ -1,7 +1,7 @@
 {
-  "[CLS]": 104,
-  "[MASK]": 103,
-  "[PAD]": 0,
-  "[SEP]": 105,
-  "[UNK]": 100
+  "<pad>": 0,
+  "<unk>": 1,
+  "[CLS]": 2,
+  "[MASK]": 4,
+  "[SEP]": 3
 }

config.json

@@ -1,13 +1,17 @@
 {
-  "_name_or_path": "google/muril-base-cased",
+  "_name_or_path": "ai4bharat/indic-bert",
   "architectures": [
-    "BertForTokenClassification"
+    "AlbertForTokenClassification"
   ],
-  "attention_probs_dropout_prob": 0.1,
-  "classifier_dropout": null,
-  "embedding_size": 768,
+  "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": 0.1,
+  "hidden_dropout_prob": 0,
   "hidden_size": 768,
   "id2label": {
     "0": "DATE",
@@ -20,6 +24,7 @@
     "7": "TIME"
   },
   "initializer_range": 0.02,
+  "inner_group_num": 1,
   "intermediate_size": 3072,
   "label2id": {
     "DATE": 0,
@@ -33,14 +38,16 @@
   },
   "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
-  "model_type": "bert",
+  "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",
   "torch_dtype": "float32",
   "transformers_version": "4.34.0",
   "type_vocab_size": 2,
-  "use_cache": true,
-  "vocab_size": 197285
+  "vocab_size": 200000
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:510d515083e20c27fab97aa5840244414eb7f4c702921befe072adacf3ac7d97
-size 947954857
+oid sha256:17c21061a32b3ca91d1bcfcbb0933ca1142582ed41d86f8575f3830aeeaf7dc3
+size 131445244

special_tokens_map.json

@@ -1,7 +1,9 @@
 {
+  "bos_token": "[CLS]",
   "cls_token": "[CLS]",
+  "eos_token": "[SEP]",
   "mask_token": "[MASK]",
-  "pad_token": "[PAD]",
+  "pad_token": "<pad>",
   "sep_token": "[SEP]",
-  "unk_token": "[UNK]"
+  "unk_token": "<unk>"
 }

spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a1173c2b6e144a02c001e289a05b5dbefddf247c50d4dcf42633158b2968fcb
+size 5646064

tokenizer_config.json

@@ -1,40 +1,40 @@
 {
   "added_tokens_decoder": {
     "0": {
-      "content": "[PAD]",
+      "content": "<pad>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "100": {
-      "content": "[UNK]",
+    "1": {
+      "content": "<unk>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "103": {
-      "content": "[MASK]",
+    "2": {
+      "content": "[CLS]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "104": {
-      "content": "[CLS]",
+    "3": {
+      "content": "[SEP]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "105": {
-      "content": "[SEP]",
-      "lstrip": false,
+    "4": {
+      "content": "[MASK]",
+      "lstrip": true,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
@@ -42,18 +42,18 @@
     }
   },
   "additional_special_tokens": [],
+  "bos_token": "[CLS]",
   "clean_up_tokenization_spaces": true,
   "cls_token": "[CLS]",
-  "do_basic_tokenize": true,
-  "do_lower_case": false,
-  "lowercase": false,
+  "do_lower_case": true,
+  "eos_token": "[SEP]",
+  "keep_accents": false,
   "mask_token": "[MASK]",
-  "model_max_length": 512,
-  "never_split": null,
-  "pad_token": "[PAD]",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "remove_space": true,
   "sep_token": "[SEP]",
-  "strip_accents": false,
-  "tokenize_chinese_chars": true,
-  "tokenizer_class": "BertTokenizer",
-  "unk_token": "[UNK]"
+  "sp_model_kwargs": {},
+  "tokenizer_class": "AlbertTokenizer",
+  "unk_token": "<unk>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f0b2bc1a382b17cfa5762bd14617e30ffd3769ee00bdd53cbe1ca628952859e4
+oid sha256:226af777b432ce66c1fbf8c67f0134691b7aeb4d6a07914804bdef07e8d59bdf
 size 4091