Training in progress epoch 0

README.md

@@ -1,6 +1,6 @@
 ---
 license: apache-2.0
-base_model: google/mobilebert-uncased
+base_model: distilbert-base-multilingual-cased
 tags:
 - generated_from_keras_callback
 model-index:
@@ -13,11 +13,11 @@ probably proofread and complete it, then remove this comment. -->
 
 # dot-ammar/dotless_mask_model-small
 
-This model is a fine-tuned version of [google/mobilebert-uncased](https://huggingface.co/google/mobilebert-uncased) on an unknown dataset.
+This model is a fine-tuned version of [distilbert-base-multilingual-cased](https://huggingface.co/distilbert-base-multilingual-cased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 6.8440
-- Validation Loss: 6.6637
-- Epoch: 2
+- Train Loss: 6.9175
+- Validation Loss: 6.2919
+- Epoch: 0
 
 ## Model description
 
@@ -43,9 +43,7 @@ The following hyperparameters were used during training:
 
 | Train Loss | Validation Loss | Epoch |
 |:----------:|:---------------:|:-----:|
-| 8.0775     | 7.6064          | 0     |
-| 7.2023     | 7.0024          | 1     |
-| 6.8440     | 6.6637          | 2     |
+| 6.9175     | 6.2919          | 0     |
 
 
 ### Framework versions

config.json

@@ -1,32 +1,24 @@
 {
-  "_name_or_path": "google/mobilebert-uncased",
+  "_name_or_path": "distilbert-base-multilingual-cased",
+  "activation": "gelu",
   "architectures": [
-    "MobileBertForMaskedLM"
+    "DistilBertForMaskedLM"
   ],
-  "attention_probs_dropout_prob": 0.1,
-  "classifier_activation": false,
-  "classifier_dropout": null,
-  "embedding_size": 128,
-  "hidden_act": "relu",
-  "hidden_dropout_prob": 0.0,
-  "hidden_size": 512,
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
   "initializer_range": 0.02,
-  "intermediate_size": 512,
-  "intra_bottleneck_size": 128,
-  "key_query_shared_bottleneck": true,
-  "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
-  "model_type": "mobilebert",
-  "normalization_type": "no_norm",
-  "num_attention_heads": 4,
-  "num_feedforward_networks": 4,
-  "num_hidden_layers": 24,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "output_past": true,
   "pad_token_id": 0,
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
   "transformers_version": "4.33.0",
-  "trigram_input": true,
-  "true_hidden_size": 128,
-  "type_vocab_size": 2,
-  "use_bottleneck": true,
-  "use_bottleneck_attention": false,
-  "vocab_size": 30522
+  "vocab_size": 119547
 }

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16271ac70ec58eda60e1936b1d12eb4678e6aa472738a8f614043827ebf86110
-size 163499912
+oid sha256:97375cacad274b9c3658bc37bb4a7b679ab9aadc40065a2fa13e7975a3eeaede
+size 910749348

tokenizer_config.json

@@ -43,13 +43,13 @@
   },
   "clean_up_tokenization_spaces": true,
   "cls_token": "[CLS]",
-  "do_lower_case": true,
+  "do_lower_case": false,
   "mask_token": "[MASK]",
-  "model_max_length": 1000000000000000019884624838656,
+  "model_max_length": 512,
   "pad_token": "[PAD]",
   "sep_token": "[SEP]",
   "strip_accents": null,
   "tokenize_chinese_chars": true,
-  "tokenizer_class": "MobileBertTokenizer",
+  "tokenizer_class": "DistilBertTokenizer",
   "unk_token": "[UNK]"
 }