Training in progress epoch 0

README.md

@@ -1,6 +1,5 @@
 ---
-license: mit
-base_model: ai4bharat/indic-bert
+base_model: Aleksandar/electra-srb-ner
 tags:
 - generated_from_keras_callback
 model-index:
@@ -13,11 +12,11 @@ probably proofread and complete it, then remove this comment. -->
 
 # imtiaz114/mbert-ner-baseline-1
 
-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 [Aleksandar/electra-srb-ner](https://huggingface.co/Aleksandar/electra-srb-ner) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 0.0636
-- Validation Loss: 0.0832
-- Epoch: 3
+- Train Loss: 0.1767
+- Validation Loss: 0.1226
+- Epoch: 0
 
 ## Model description
 
@@ -36,17 +35,14 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- optimizer: {'inner_optimizer': {'class_name': 'AdamWeightDecay', 'config': {'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': 0.01}}, 'dynamic': True, 'initial_scale': 32768.0, 'dynamic_growth_steps': 2000}
+- optimizer: {'inner_optimizer': {'class_name': 'AdamWeightDecay', 'config': {'name': 'AdamWeightDecay', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 1592, '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': 0.01}}, 'dynamic': True, 'initial_scale': 32768.0, 'dynamic_growth_steps': 2000}
 - training_precision: mixed_float16
 
 ### Training results
 
 | Train Loss | Validation Loss | Epoch |
 |:----------:|:---------------:|:-----:|
-| 0.2187     | 0.1320          | 0     |
-| 0.1144     | 0.0944          | 1     |
-| 0.0817     | 0.0866          | 2     |
-| 0.0636     | 0.0832          | 3     |
+| 0.1767     | 0.1226          | 0     |
 
 
 ### Framework versions

config.json

@@ -1,17 +1,13 @@
 {
-  "_name_or_path": "ai4bharat/indic-bert",
+  "_name_or_path": "Aleksandar/electra-srb-ner",
   "architectures": [
-    "AlbertForTokenClassification"
+    "ElectraForTokenClassification"
   ],
-  "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": "O",
@@ -23,7 +19,6 @@
     "6": "I-LOC"
   },
   "initializer_range": 0.02,
-  "inner_group_num": 1,
   "intermediate_size": 3072,
   "label2id": {
     "B-LOC": 5,
@@ -36,15 +31,18 @@
   },
   "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
-  "model_type": "albert",
-  "net_structure_type": 0,
+  "model_type": "electra",
   "num_attention_heads": 12,
-  "num_hidden_groups": 1,
   "num_hidden_layers": 12,
-  "num_memory_blocks": 0,
   "pad_token_id": 0,
   "position_embedding_type": "absolute",
+  "summary_activation": "gelu",
+  "summary_last_dropout": 0.1,
+  "summary_type": "first",
+  "summary_use_proj": true,
+  "torch_dtype": "float32",
   "transformers_version": "4.31.0.dev0",
   "type_vocab_size": 2,
-  "vocab_size": 200000
+  "use_cache": true,
+  "vocab_size": 30522
 }

special_tokens_map.json

@@ -1,15 +1,7 @@
 {
-  "bos_token": "[CLS]",
   "cls_token": "[CLS]",
-  "eos_token": "[SEP]",
-  "mask_token": {
-    "content": "[MASK]",
-    "lstrip": true,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "pad_token": "<pad>",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
   "sep_token": "[SEP]",
-  "unk_token": "<unk>"
+  "unk_token": "[UNK]"
 }

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:efa595d50fd8161039fc600e5d410925f970223195f98d7b0ee20d164cdd1b5e
-size 131473068
+oid sha256:f43194a5239c23b38310828324013de45ce38bbf2df00287b74ea6ab69d94903
+size 435876320

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:431ec72a485a382d7e3a6063af5f54249b36e4870e0c8d079918e79cd0a4f8f1
-size 15285606
+oid sha256:e4a3974847fda36dc728132432b910a0f67598ca1cc7f0686901cf3ef82d4f03
+size 772540

tokenizer_config.json

@@ -1,23 +1,13 @@
 {
-  "bos_token": "[CLS]",
   "clean_up_tokenization_spaces": true,
   "cls_token": "[CLS]",
   "do_lower_case": true,
-  "eos_token": "[SEP]",
-  "keep_accents": false,
-  "mask_token": {
-    "__type": "AddedToken",
-    "content": "[MASK]",
-    "lstrip": true,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "model_max_length": 1000000000000000019884624838656,
-  "pad_token": "<pad>",
-  "remove_space": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
   "sep_token": "[SEP]",
-  "sp_model_kwargs": {},
-  "tokenizer_class": "AlbertTokenizer",
-  "unk_token": "<unk>"
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "ElectraTokenizer",
+  "unk_token": "[UNK]"
 }