Training in progress epoch 0

.gitattributes

@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+vocab.txt filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,6 +1,6 @@
 ---
 license: apache-2.0
-base_model: distilroberta-base
+base_model: KoichiYasuoka/roberta-classical-chinese-base-char
 tags:
 - generated_from_keras_callback
 model-index:
@@ -13,10 +13,10 @@ probably proofread and complete it, then remove this comment. -->
 
 # MooBai/distilroberta-base-finetuned-wikitext2
 
-This model is a fine-tuned version of [distilroberta-base](https://huggingface.co/distilroberta-base) on an unknown dataset.
+This model is a fine-tuned version of [KoichiYasuoka/roberta-classical-chinese-base-char](https://huggingface.co/KoichiYasuoka/roberta-classical-chinese-base-char) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 2.1517
-- Validation Loss: 1.9132
+- Train Loss: 1.4938
+- Validation Loss: 0.9427
 - Epoch: 0
 
 ## Model description
@@ -43,7 +43,7 @@ The following hyperparameters were used during training:
 
 | Train Loss | Validation Loss | Epoch |
 |:----------:|:---------------:|:-----:|
-| 2.1517     | 1.9132          | 0     |
+| 1.4938     | 0.9427          | 0     |
 
 
 ### Framework versions

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "distilroberta-base",
+  "_name_or_path": "KoichiYasuoka/roberta-classical-chinese-base-char",
   "architectures": [
     "RobertaForMaskedLM"
   ],
@@ -7,6 +7,7 @@
   "bos_token_id": 0,
   "classifier_dropout": null,
   "eos_token_id": 2,
+  "gradient_checkpointing": false,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
   "hidden_size": 768,
@@ -16,11 +17,12 @@
   "max_position_embeddings": 514,
   "model_type": "roberta",
   "num_attention_heads": 12,
-  "num_hidden_layers": 6,
+  "num_hidden_layers": 12,
   "pad_token_id": 1,
   "position_embedding_type": "absolute",
+  "tokenizer_class": "BertTokenizer",
   "transformers_version": "4.38.2",
   "type_vocab_size": 1,
   "use_cache": true,
-  "vocab_size": 50265
+  "vocab_size": 26318
 }

special_tokens_map.json

@@ -1,15 +1,7 @@
 {
-  "bos_token": "<s>",
-  "cls_token": "<s>",
-  "eos_token": "</s>",
-  "mask_token": {
-    "content": "<mask>",
-    "lstrip": true,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "pad_token": "<pad>",
-  "sep_token": "</s>",
-  "unk_token": "<unk>"
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
 }

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f5a8a8bf734c31de9397f390048d7612c31af08425cbd02621cd2f7308929f03
-size 484838604
+oid sha256:3fb9c962dd8c23f8fd0f57e9abad2ab31411d8e874565d18e5f63186fb70cc1f
+size 507845000

tokenizer_config.json

@@ -1,57 +1,57 @@
 {
-  "add_prefix_space": false,
   "added_tokens_decoder": {
     "0": {
-      "content": "<s>",
+      "content": "[CLS]",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
     "1": {
-      "content": "<pad>",
+      "content": "[PAD]",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
     "2": {
-      "content": "</s>",
+      "content": "[SEP]",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
     "3": {
-      "content": "<unk>",
+      "content": "[UNK]",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "50264": {
-      "content": "<mask>",
-      "lstrip": true,
+    "23291": {
+      "content": "[MASK]",
+      "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     }
   },
-  "bos_token": "<s>",
   "clean_up_tokenization_spaces": true,
-  "cls_token": "<s>",
-  "eos_token": "</s>",
-  "errors": "replace",
-  "mask_token": "<mask>",
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
   "model_max_length": 512,
-  "pad_token": "<pad>",
-  "sep_token": "</s>",
-  "tokenizer_class": "RobertaTokenizer",
-  "trim_offsets": true,
-  "unk_token": "<unk>"
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
 }

vocab.txt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6d19121379d1d258ff28c2ae25e264d70a66ff3926fe3490e2f8977a4d3111e
+size 105602