Training in progress epoch 0

README.md

@@ -1,6 +1,6 @@
 ---
 license: apache-2.0
-base_model: google/electra-base-generator
+base_model: google/electra-base-discriminator
 tags:
 - generated_from_keras_callback
 model-index:
@@ -13,11 +13,11 @@ probably proofread and complete it, then remove this comment. -->
 
 # syabusyabu0141/test2
 
-This model is a fine-tuned version of [google/electra-base-generator](https://huggingface.co/google/electra-base-generator) on an unknown dataset.
+This model is a fine-tuned version of [google/electra-base-discriminator](https://huggingface.co/google/electra-base-discriminator) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 1.9064
-- Validation Loss: 1.9879
-- Epoch: 1
+- Train Loss: 0.0691
+- Validation Loss: 0.0361
+- Epoch: 0
 
 ## Model description
 
@@ -43,13 +43,12 @@ The following hyperparameters were used during training:
 
 | Train Loss | Validation Loss | Epoch |
 |:----------:|:---------------:|:-----:|
-| 2.1386     | 2.0232          | 0     |
-| 1.9064     | 1.9879          | 1     |
+| 0.0691     | 0.0361          | 0     |
 
 
 ### Framework versions
 
-- Transformers 4.34.0
-- TensorFlow 2.13.0
-- Datasets 2.14.5
+- Transformers 4.35.0
+- TensorFlow 2.14.0
+- Datasets 2.14.6
 - Tokenizers 0.14.1

config.json

@@ -1,20 +1,32 @@
 {
-  "_name_or_path": "google/electra-base-generator",
+  "_name_or_path": "google/electra-base-discriminator",
   "architectures": [
-    "ElectraForMaskedLM"
+    "ElectraForTokenClassification"
   ],
   "attention_probs_dropout_prob": 0.1,
   "classifier_dropout": null,
   "embedding_size": 768,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
-  "hidden_size": 256,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "other_pos",
+    "1": "cha_miss",
+    "2": "ins_miss",
+    "3": "true_prep"
+  },
   "initializer_range": 0.02,
-  "intermediate_size": 1024,
+  "intermediate_size": 3072,
+  "label2id": {
+    "cha_miss": 1,
+    "ins_miss": 2,
+    "other_pos": 0,
+    "true_prep": 3
+  },
   "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
   "model_type": "electra",
-  "num_attention_heads": 4,
+  "num_attention_heads": 12,
   "num_hidden_layers": 12,
   "pad_token_id": 0,
   "position_embedding_type": "absolute",
@@ -22,7 +34,7 @@
   "summary_last_dropout": 0.1,
   "summary_type": "first",
   "summary_use_proj": true,
-  "transformers_version": "4.34.0",
+  "transformers_version": "4.35.0",
   "type_vocab_size": 2,
   "use_cache": true,
   "vocab_size": 30522

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47dc58f6e4c88f6c1051512b5a5e9f1cb05a764357b029fa45db150392e0aada
-size 230595504
+oid sha256:48f32660b6212551e9e72e8c82c454a6d33dc737294bb6359842737895dcbe85
+size 435867104

tokenizer_config.json

@@ -6,7 +6,7 @@
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
     "100": {
       "content": "[UNK]",
@@ -14,7 +14,7 @@
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
     "101": {
       "content": "[CLS]",
@@ -22,7 +22,7 @@
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
     "102": {
       "content": "[SEP]",
@@ -30,7 +30,7 @@
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
     "103": {
       "content": "[MASK]",
@@ -38,10 +38,9 @@
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     }
   },
-  "additional_special_tokens": [],
   "clean_up_tokenization_spaces": true,
   "cls_token": "[CLS]",
   "do_basic_tokenize": true,
@@ -54,6 +53,5 @@
   "strip_accents": null,
   "tokenize_chinese_chars": true,
   "tokenizer_class": "ElectraTokenizer",
-  "tokenizer_file": "/root/.cache/huggingface/hub/models--google--electra-base-generator/snapshots/1c65e3f5f4597679b87620707df5774c08c6606d/tokenizer.json",
   "unk_token": "[UNK]"
 }