Training in progress epoch 0

README.md

@@ -3,22 +3,22 @@ license: apache-2.0
 tags:
 - generated_from_keras_callback
 model-index:
-- name: andreiliphdpr/distilbert-base-uncased-finetuned-cola
+- name: andreiliphdpr/bert-base-multilingual-uncased-finetuned-cola
   results: []
 ---
 
 <!-- This model card has been generated automatically according to the information Keras had access to. You should
 probably proofread and complete it, then remove this comment. -->
 
-# andreiliphdpr/distilbert-base-uncased-finetuned-cola
+# andreiliphdpr/bert-base-multilingual-uncased-finetuned-cola
 
-This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
+This model is a fine-tuned version of [bert-base-multilingual-uncased](https://huggingface.co/bert-base-multilingual-uncased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 0.0015
-- Train Accuracy: 0.9995
-- Validation Loss: 0.0570
-- Validation Accuracy: 0.9915
-- Epoch: 4
+- Train Loss: 0.0423
+- Train Accuracy: 0.9869
+- Validation Loss: 0.0303
+- Validation Accuracy: 0.9913
+- Epoch: 0
 
 ## Model description
 
@@ -44,11 +44,7 @@ The following hyperparameters were used during training:
 
 | Train Loss | Train Accuracy | Validation Loss | Validation Accuracy | Epoch |
 |:----------:|:--------------:|:---------------:|:-------------------:|:-----:|
-| 0.0399     | 0.9870         | 0.0281          | 0.9908              | 0     |
-| 0.0182     | 0.9944         | 0.0326          | 0.9901              | 1     |
-| 0.0089     | 0.9971         | 0.0396          | 0.9912              | 2     |
-| 0.0040     | 0.9987         | 0.0486          | 0.9918              | 3     |
-| 0.0015     | 0.9995         | 0.0570          | 0.9915              | 4     |
+| 0.0423     | 0.9869         | 0.0303          | 0.9913              | 0     |
 
 
 ### Framework versions

config.json

@@ -1,23 +1,30 @@
 {
-  "_name_or_path": "distilbert-base-uncased",
-  "activation": "gelu",
+  "_name_or_path": "bert-base-multilingual-uncased",
   "architectures": [
-    "DistilBertForSequenceClassification"
+    "BertForSequenceClassification"
   ],
-  "attention_dropout": 0.1,
-  "dim": 768,
-  "dropout": 0.1,
-  "hidden_dim": 3072,
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
   "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
-  "model_type": "distilbert",
-  "n_heads": 12,
-  "n_layers": 6,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
   "pad_token_id": 0,
-  "qa_dropout": 0.1,
-  "seq_classif_dropout": 0.2,
-  "sinusoidal_pos_embds": false,
-  "tie_weights_": true,
+  "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",
   "transformers_version": "4.15.0.dev0",
-  "vocab_size": 30522
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 105879
 }

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50238a8c3615621f82a6cc7fad2f0ea42b08d82a60982ef06469fdec588f0c5c
-size 267951896
+oid sha256:d4e2b6127d711d248ce2b32db3936ebe522130127426935e5b40d7c2d8f5bbe6
+size 669719896

tokenizer_config.json

@@ -1 +1 @@
-{"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "distilbert-base-uncased", "tokenizer_class": "DistilBertTokenizer"}
+{"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "bert-base-multilingual-uncased", "tokenizer_class": "BertTokenizer"}