Training in progress epoch 0

README.md

@@ -12,12 +12,12 @@ probably proofread and complete it, then remove this comment. -->
 
 # xb0129/my_awesome_model
 
-This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-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: 0.0714
-- Validation Loss: 1.4912
-- Train Accuracy: 0.5761
-- Epoch: 4
+- Train Loss: 1.0772
+- Validation Loss: 1.3395
+- Train Accuracy: 0.5802
+- Epoch: 0
 
 ## Model description
 
@@ -43,11 +43,7 @@ The following hyperparameters were used during training:
 
 | Train Loss | Validation Loss | Train Accuracy | Epoch |
 |:----------:|:---------------:|:--------------:|:-----:|
-| 1.2501     | 1.6023          | 0.4712         | 0     |
-| 0.3192     | 1.5776          | 0.5062         | 1     |
-| 0.1608     | 1.4756          | 0.5864         | 2     |
-| 0.0960     | 1.5070          | 0.5370         | 3     |
-| 0.0714     | 1.4912          | 0.5761         | 4     |
+| 1.0772     | 1.3395          | 0.5802         | 0     |
 
 
 ### Framework versions

config.json

@@ -1,14 +1,13 @@
 {
-  "_name_or_path": "bert-base-cased",
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
   "architectures": [
-    "BertForSequenceClassification"
+    "DistilBertForSequenceClassification"
   ],
-  "attention_probs_dropout_prob": 0.1,
-  "classifier_dropout": null,
-  "gradient_checkpointing": false,
-  "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.1,
-  "hidden_size": 768,
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
   "id2label": {
     "0": "uncategorized",
     "1": "Housing",
@@ -23,7 +22,6 @@
     "10": "Credit/Loan"
   },
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
   "label2id": {
     "Bank transfer": 9,
     "Clothing": 6,
@@ -37,15 +35,15 @@
     "Utilities": 4,
     "uncategorized": 0
   },
-  "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
-  "model_type": "bert",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 12,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
   "pad_token_id": 0,
-  "position_embedding_type": "absolute",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
   "transformers_version": "4.27.4",
-  "type_vocab_size": 2,
-  "use_cache": true,
-  "vocab_size": 28996
+  "vocab_size": 30522
 }

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5426f6ea603a07fe0ff863bf87376f58bb11c6fc6482fdc7450a4aa6cb3fb96e
-size 433562940
+oid sha256:5c23a7df88ca3f7f0d2251b1c8af5efa05a1f03f4f71e7d6a6c02513cc6957fc
+size 267979456

tokenizer_config.json

@@ -1,6 +1,6 @@
 {
   "cls_token": "[CLS]",
-  "do_lower_case": false,
+  "do_lower_case": true,
   "mask_token": "[MASK]",
   "model_max_length": 512,
   "pad_token": "[PAD]",
@@ -8,6 +8,6 @@
   "special_tokens_map_file": null,
   "strip_accents": null,
   "tokenize_chinese_chars": true,
-  "tokenizer_class": "BertTokenizer",
+  "tokenizer_class": "DistilBertTokenizer",
   "unk_token": "[UNK]"
 }