Tippawan/name_vs_common_v2

README.md

@@ -38,7 +38,7 @@ The following hyperparameters were used during training:
 - seed: 1412
 - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
-- lr_scheduler_warmup_steps: 803
+- lr_scheduler_warmup_steps: 3594
 - num_epochs: 10
 
 ### Training results
@@ -47,7 +47,7 @@ The following hyperparameters were used during training:
 
 ### Framework versions
 
-- Transformers 5.4.0
-- Pytorch 2.11.0+cu130
-- Datasets 4.0.0
-- Tokenizers 0.22.2
+- Transformers 4.56.0.dev0
+- Pytorch 2.8.0+cu128
+- Datasets 3.6.0
+- Tokenizers 0.21.2

config.json

@@ -1,12 +1,10 @@
 {
-  "add_cross_attention": false,
   "architectures": [
     "CamembertForSequenceClassification"
   ],
   "attention_probs_dropout_prob": 0.1,
   "bos_token_id": 0,
   "classifier_dropout": null,
-  "dtype": "float32",
   "eos_token_id": 2,
   "gradient_checkpointing": false,
   "hidden_act": "gelu",
@@ -14,7 +12,6 @@
   "hidden_size": 768,
   "initializer_range": 0.02,
   "intermediate_size": 3072,
-  "is_decoder": false,
   "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
   "model_type": "camembert",
@@ -22,10 +19,11 @@
   "num_attention_heads": 12,
   "num_hidden_layers": 12,
   "pad_token_id": 1,
+  "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",
-  "tie_word_embeddings": true,
-  "transformers_version": "5.4.0",
+  "torch_dtype": "float32",
+  "transformers_version": "4.56.0.dev0",
   "type_vocab_size": 1,
-  "use_cache": false,
+  "use_cache": true,
   "vocab_size": 25005
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9621dd6bf74bb5851755cc7c21a2919f89193ba6e02a0b61d49c0dda5aa39f9
-size 421007904
+oid sha256:2457ea1472c12d505c8ca3858449f8a2e14fff0e81d547a75a68f05d5bd4f850
+size 421007928

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49c4ba4e495ddf31eb2fdba7fc6aef3c233091d25d35bc9d24694ccf48ae114c
+size 904693

special_tokens_map.json

@@ -0,0 +1,20 @@
+{
+  "additional_special_tokens": [
+    "<s>NOTUSED",
+    "</s>NOTUSED",
+    "<_>"
+  ],
+  "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>"
+}

tokenizer_config.json

@@ -1,20 +1,85 @@
 {
-  "add_prefix_space": true,
-  "backend": "tokenizers",
-  "bos_token": "<s>",
-  "cls_token": "<s>",
-  "eos_token": "</s>",
-  "extra_special_tokens": [
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>NOTUSED",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>NOTUSED",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "8": {
+      "content": "<_>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "25004": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
     "<s>NOTUSED",
     "</s>NOTUSED",
     "<_>"
   ],
-  "is_local": false,
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
   "mask_token": "<mask>",
   "model_max_length": 510,
   "pad_token": "<pad>",
   "sep_token": "</s>",
+  "sp_model_kwargs": {},
   "tokenizer_class": "CamembertTokenizer",
-  "unk_id": 0,
   "unk_token": "<unk>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0b06f1e78c1fef8f7175805b15a0f39c76343252ea750288bccea0e733efb9e
-size 5201
+oid sha256:09b0a279a64ccdc1cca282a1770fe80c3bb371cb1273722693827c9da80e8bb3
+size 5777