End of training

README.md

@@ -1,6 +1,6 @@
 ---
-license: mit
-base_model: ai4bharat/indic-bert
+license: apache-2.0
+base_model: google/muril-base-cased
 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 [ai4bharat/indic-bert](https://huggingface.co/ai4bharat/indic-bert) on an unknown dataset.
+This model is a fine-tuned version of [google/muril-base-cased](https://huggingface.co/google/muril-base-cased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6152
-- Precision: 0.0391
-- Recall: 0.0131
-- F1: 0.0196
-- Accuracy: 0.8261
+- Loss: 1.5286
+- Precision: 0.0
+- Recall: 0.0
+- F1: 0.0
+- Accuracy: 0.8266
 
 ## Model description
 
@@ -53,18 +53,18 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| 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   |
+| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1  | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:---:|:--------:|
+| No log        | 1.0   | 144  | 1.8004          | 0.0       | 0.0    | 0.0 | 0.8266   |
+| No log        | 2.0   | 288  | 1.6949          | 0.0       | 0.0    | 0.0 | 0.8266   |
+| No log        | 3.0   | 432  | 1.6041          | 0.0       | 0.0    | 0.0 | 0.8266   |
+| 1.7388        | 4.0   | 576  | 1.5476          | 0.0       | 0.0    | 0.0 | 0.8266   |
+| 1.7388        | 5.0   | 720  | 1.5286          | 0.0       | 0.0    | 0.0 | 0.8266   |
 
 
 ### Framework versions
 
-- Transformers 4.34.0
-- Pytorch 2.0.1+cu118
+- Transformers 4.33.0
+- Pytorch 2.0.0
 - Datasets 2.14.5
-- Tokenizers 0.14.0
+- Tokenizers 0.13.3

config.json

@@ -1,17 +1,13 @@
 {
-  "_name_or_path": "ai4bharat/indic-bert",
+  "_name_or_path": "google/muril-base-cased",
   "architectures": [
-    "AlbertForTokenClassification"
+    "BertForTokenClassification"
   ],
-  "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,
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "embedding_size": 768,
   "hidden_act": "gelu",
-  "hidden_dropout_prob": 0,
+  "hidden_dropout_prob": 0.1,
   "hidden_size": 768,
   "id2label": {
     "0": "DATE",
@@ -24,7 +20,6 @@
     "7": "TIME"
   },
   "initializer_range": 0.02,
-  "inner_group_num": 1,
   "intermediate_size": 3072,
   "label2id": {
     "DATE": 0,
@@ -38,16 +33,14 @@
   },
   "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
-  "model_type": "albert",
-  "net_structure_type": 0,
+  "model_type": "bert",
   "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",
+  "transformers_version": "4.33.0",
   "type_vocab_size": 2,
-  "vocab_size": 200000
+  "use_cache": true,
+  "vocab_size": 197285
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17c21061a32b3ca91d1bcfcbb0933ca1142582ed41d86f8575f3830aeeaf7dc3
-size 131445244
+oid sha256:37f661f90c1de34705f140daf5561f34f30a18f0d87b645c2206f00fc53db1aa
+size 947954857

special_tokens_map.json

@@ -1,9 +1,7 @@
 {
-  "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]"
 }

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1380ca9cde3e5552469ae7f5c6b897faa4e96bfd39bd8a64ac5b4d05c5add12f
-size 15285634
+oid sha256:4cb5ee143f24f08e5fe598915cbcddb36d298e8532097433837bfa51087e77f1
+size 6408480

tokenizer_config.json

@@ -1,59 +1,16 @@
 {
-  "added_tokens_decoder": {
-    "0": {
-      "content": "<pad>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "1": {
-      "content": "<unk>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "2": {
-      "content": "[CLS]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "3": {
-      "content": "[SEP]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "4": {
-      "content": "[MASK]",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    }
-  },
-  "additional_special_tokens": [],
-  "bos_token": "[CLS]",
   "clean_up_tokenization_spaces": true,
   "cls_token": "[CLS]",
-  "do_lower_case": true,
-  "eos_token": "[SEP]",
-  "keep_accents": false,
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "lowercase": false,
   "mask_token": "[MASK]",
-  "model_max_length": 1000000000000000019884624838656,
-  "pad_token": "<pad>",
-  "remove_space": true,
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
   "sep_token": "[SEP]",
-  "sp_model_kwargs": {},
-  "tokenizer_class": "AlbertTokenizer",
-  "unk_token": "<unk>"
+  "strip_accents": false,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:226af777b432ce66c1fbf8c67f0134691b7aeb4d6a07914804bdef07e8d59bdf
-size 4091
+oid sha256:ca602948a696822b8ab70fee198e9d0c5bc3d0380e01e6601a915c5337e47745
+size 4027