Training in progress epoch 0

README.md

@@ -1,6 +1,6 @@
 ---
 license: mit
-base_model: xlm-roberta-base
+base_model: ai4bharat/indic-bert
 tags:
 - generated_from_keras_callback
 model-index:
@@ -13,11 +13,11 @@ probably proofread and complete it, then remove this comment. -->
 
 # imtiaz114/mbert-ner-baseline-1
 
-This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) 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:
-- Train Loss: 0.0470
-- Validation Loss: 0.2044
-- Epoch: 7
+- Train Loss: 0.4884
+- Validation Loss: 0.3742
+- Epoch: 0
 
 ## Model description
 
@@ -36,21 +36,14 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 12736, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.1}
+- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 3184, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.1}
 - training_precision: mixed_float16
 
 ### Training results
 
 | Train Loss | Validation Loss | Epoch |
 |:----------:|:---------------:|:-----:|
-| 0.2960     | 0.1926          | 0     |
-| 0.1732     | 0.1713          | 1     |
-| 0.1326     | 0.1692          | 2     |
-| 0.1070     | 0.1702          | 3     |
-| 0.0849     | 0.1813          | 4     |
-| 0.0686     | 0.1918          | 5     |
-| 0.0564     | 0.1961          | 6     |
-| 0.0470     | 0.2044          | 7     |
+| 0.4884     | 0.3742          | 0     |
 
 
 ### Framework versions

config.json

@@ -1,45 +1,50 @@
 {
-  "_name_or_path": "xlm-roberta-base",
+  "_name_or_path": "ai4bharat/indic-bert",
   "architectures": [
-    "XLMRobertaForTokenClassification"
+    "AlbertForTokenClassification"
   ],
-  "attention_probs_dropout_prob": 0.1,
-  "bos_token_id": 0,
-  "classifier_dropout": null,
-  "eos_token_id": 2,
+  "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": "I-PER",
-    "1": "O",
-    "2": "I-ORG",
-    "3": "I-LOC",
-    "4": "B-LOC",
-    "5": "B-PER",
-    "6": "B-ORG"
+    "0": "B-PER",
+    "1": "I-LOC",
+    "2": "I-PER",
+    "3": "O",
+    "4": "I-ORG",
+    "5": "B-ORG",
+    "6": "B-LOC"
   },
   "initializer_range": 0.02,
+  "inner_group_num": 1,
   "intermediate_size": 3072,
   "label2id": {
-    "B-LOC": 4,
-    "B-ORG": 6,
-    "B-PER": 5,
-    "I-LOC": 3,
-    "I-ORG": 2,
-    "I-PER": 0,
-    "O": 1
+    "B-LOC": 6,
+    "B-ORG": 5,
+    "B-PER": 0,
+    "I-LOC": 1,
+    "I-ORG": 4,
+    "I-PER": 2,
+    "O": 3
   },
-  "layer_norm_eps": 1e-05,
-  "max_position_embeddings": 514,
-  "model_type": "xlm-roberta",
+  "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,
-  "output_past": true,
-  "pad_token_id": 1,
+  "num_memory_blocks": 0,
+  "pad_token_id": 0,
   "position_embedding_type": "absolute",
   "transformers_version": "4.31.0.dev0",
-  "type_vocab_size": 1,
-  "use_cache": true,
-  "vocab_size": 250002
+  "type_vocab_size": 2,
+  "vocab_size": 200000
 }

special_tokens_map.json

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

spiece.model

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

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e2ec9c4ad944351229ad58b4ee10aae1b310347826bc2cf30c61f55b3564e7d
-size 1110121552
+oid sha256:7fbd569667e98157f97a2a7669a9886aec87224e068f93ab24102fb369d3fa3c
+size 131473068

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2c509a525eb51aebb33fb59c24ee923c1d4c1db23c3ae81fe05ccf354084f7b
-size 17082758
+oid sha256:431ec72a485a382d7e3a6063af5f54249b36e4870e0c8d079918e79cd0a4f8f1
+size 15285606

tokenizer_config.json

@@ -1,19 +1,23 @@
 {
-  "bos_token": "<s>",
+  "bos_token": "[CLS]",
   "clean_up_tokenization_spaces": true,
-  "cls_token": "<s>",
-  "eos_token": "</s>",
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "eos_token": "[SEP]",
+  "keep_accents": false,
   "mask_token": {
     "__type": "AddedToken",
-    "content": "<mask>",
+    "content": "[MASK]",
     "lstrip": true,
-    "normalized": true,
+    "normalized": false,
     "rstrip": false,
     "single_word": false
   },
-  "model_max_length": 512,
+  "model_max_length": 1000000000000000019884624838656,
   "pad_token": "<pad>",
-  "sep_token": "</s>",
-  "tokenizer_class": "XLMRobertaTokenizer",
+  "remove_space": true,
+  "sep_token": "[SEP]",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "AlbertTokenizer",
   "unk_token": "<unk>"
 }