Training in progress epoch 0

README.md

@@ -1,5 +1,5 @@
 ---
-license: mit
+license: apache-2.0
 tags:
 - generated_from_keras_callback
 model-index:
@@ -12,11 +12,11 @@ probably proofread and complete it, then remove this comment. -->
 
 # NAOKITY/bert-squad
 
-This model is a fine-tuned version of [neuralmind/bert-base-portuguese-cased](https://huggingface.co/neuralmind/bert-base-portuguese-cased) on an unknown dataset.
+This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 1.6405
+- Train Loss: 3.3672
 - Validation Loss: 0.0
-- Epoch: 1
+- Epoch: 0
 
 ## Model description
 
@@ -35,15 +35,14 @@ 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': 987, '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}
+- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 1149, '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}
 - training_precision: float32
 
 ### Training results
 
 | Train Loss | Validation Loss | Epoch |
 |:----------:|:---------------:|:-----:|
-| 2.7834     | 0.0             | 0     |
-| 1.6405     | 0.0             | 1     |
+| 3.3672     | 0.0             | 0     |
 
 
 ### Framework versions

config.json

@@ -1,31 +1,23 @@
 {
-  "_name_or_path": "neuralmind/bert-base-portuguese-cased",
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
   "architectures": [
-    "BertForQuestionAnswering"
+    "DistilBertForQuestionAnswering"
   ],
-  "attention_probs_dropout_prob": 0.1,
-  "classifier_dropout": null,
-  "directionality": "bidi",
-  "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.1,
-  "hidden_size": 768,
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
-  "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
-  "model_type": "bert",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 12,
-  "output_past": true,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
   "pad_token_id": 0,
-  "pooler_fc_size": 768,
-  "pooler_num_attention_heads": 12,
-  "pooler_num_fc_layers": 3,
-  "pooler_size_per_head": 128,
-  "pooler_type": "first_token_transform",
-  "position_embedding_type": "absolute",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
   "transformers_version": "4.20.0",
-  "type_vocab_size": 2,
-  "use_cache": true,
-  "vocab_size": 29794
+  "vocab_size": 30522
 }

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed08027123c9cd8b641946652ab7ac2552c731fc3a9bd46cd261ff71e57a91e2
-size 433605584
+oid sha256:afda53c876448e9b6b390d97836128ca8181ac89b14472db3e2ebd479530bf81
+size 265583592

tokenizer_config.json

@@ -1,15 +1,14 @@
 {
   "cls_token": "[CLS]",
-  "do_basic_tokenize": true,
-  "do_lower_case": false,
+  "do_lower_case": true,
   "mask_token": "[MASK]",
-  "name_or_path": "neuralmind/bert-base-portuguese-cased",
-  "never_split": null,
+  "model_max_length": 512,
+  "name_or_path": "distilbert-base-uncased",
   "pad_token": "[PAD]",
   "sep_token": "[SEP]",
-  "special_tokens_map_file": "/home/studio-lab-user/.cache/huggingface/transformers/eecc45187d085a1169eed91017d358cc0e9cbdd5dc236bcd710059dbf0a2f816.dd8bd9bfd3664b530ea4e645105f557769387b3da9f79bdb55ed556bdd80611d",
+  "special_tokens_map_file": null,
   "strip_accents": null,
   "tokenize_chinese_chars": true,
-  "tokenizer_class": "BertTokenizer",
+  "tokenizer_class": "DistilBertTokenizer",
   "unk_token": "[UNK]"
 }