End of training

README.md

@@ -1,6 +1,6 @@
 ---
 license: apache-2.0
-base_model: poom-sci/WangchanBERTa-finetuned-sentiment
+base_model: distilbert/distilbert-base-uncased
 tags:
 - generated_from_trainer
 model-index:
@@ -13,14 +13,14 @@ should probably proofread and complete it, then remove this comment. -->
 
 # fined-tune-thai-sentiment
 
-This model is a fine-tuned version of [poom-sci/WangchanBERTa-finetuned-sentiment](https://huggingface.co/poom-sci/WangchanBERTa-finetuned-sentiment) on an unknown dataset.
+This model is a fine-tuned version of [distilbert/distilbert-base-uncased](https://huggingface.co/distilbert/distilbert-base-uncased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- eval_loss: 0.0001
+- eval_loss: 0.0003
 - eval_accuracy: {'accuracy': 1.0}
 - eval_f1score: {'f1': 1.0}
-- eval_runtime: 0.9777
-- eval_samples_per_second: 128.877
-- eval_steps_per_second: 16.365
+- eval_runtime: 2.7276
+- eval_samples_per_second: 46.194
+- eval_steps_per_second: 5.866
 - step: 0
 
 ## Model description

config.json

@@ -1,40 +1,35 @@
 {
-  "_name_or_path": "poom-sci/WangchanBERTa-finetuned-sentiment",
+  "_name_or_path": "distilbert/distilbert-base-uncased",
+  "activation": "gelu",
   "architectures": [
-    "CamembertForSequenceClassification"
+    "DistilBertForSequenceClassification"
   ],
-  "attention_probs_dropout_prob": 0.1,
-  "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,
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
   "id2label": {
-    "0": "pos",
-    "1": "neu",
-    "2": "neg"
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
   },
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
   "label2id": {
-    "neg": 2,
-    "neu": 1,
-    "pos": 0
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
   },
-  "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
-  "model_type": "camembert",
-  "num_attention_head": 12,
-  "num_attention_heads": 12,
-  "num_hidden_layers": 12,
-  "pad_token_id": 1,
-  "position_embedding_type": "absolute",
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
   "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
   "torch_dtype": "float32",
   "transformers_version": "4.41.2",
-  "type_vocab_size": 1,
-  "use_cache": true,
-  "vocab_size": 25005
+  "vocab_size": 30522
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:017c69a83a7d0ff4c31397045fed380027574765c67f079764201fe0142def65
-size 421011004
+oid sha256:2ba627409419ca4fd646d47071d55642712eb57214097d40b7b763a526295d3a
+size 267835644

runs/Jun06_06-04-11_27de48a3f45e/events.out.tfevents.1717653859.27de48a3f45e.445.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:730dfca8a57fcfa1a9f92516178392307b77e363bf20d74f6992e0838f16c579
+size 6681

runs/Jun06_06-04-11_27de48a3f45e/events.out.tfevents.1717654042.27de48a3f45e.445.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a35cb2b450e3e574bf79e1429bbf500d5ff6b9effa26746bb9168b3cc11f2ac7
+size 506

special_tokens_map.json

@@ -1,56 +1,7 @@
 {
-  "additional_special_tokens": [
-    "<s>NOTUSED",
-    "</s>NOTUSED",
-    "<_>"
-  ],
-  "bos_token": {
-    "content": "<s>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "cls_token": {
-    "content": "<s>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "eos_token": {
-    "content": "</s>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "mask_token": {
-    "content": "<mask>",
-    "lstrip": true,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "pad_token": {
-    "content": "<pad>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "sep_token": {
-    "content": "</s>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "unk_token": {
-    "content": "<unk>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  }
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
 }

tokenizer_config.json

@@ -1,88 +1,55 @@
 {
   "added_tokens_decoder": {
     "0": {
-      "content": "<s>NOTUSED",
+      "content": "[PAD]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "1": {
-      "content": "<pad>",
+    "100": {
+      "content": "[UNK]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "2": {
-      "content": "</s>NOTUSED",
+    "101": {
+      "content": "[CLS]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "3": {
-      "content": "<unk>",
+    "102": {
+      "content": "[SEP]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "5": {
-      "content": "<s>",
+    "103": {
+      "content": "[MASK]",
       "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": true
-    },
-    "25004": {
-      "content": "<mask>",
-      "lstrip": true,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
     }
   },
-  "additional_special_tokens": [
-    "<s>NOTUSED",
-    "</s>NOTUSED",
-    "<_>"
-  ],
-  "bos_token": "<s>",
   "clean_up_tokenization_spaces": true,
-  "cls_token": "<s>",
-  "eos_token": "</s>",
-  "mask_token": "<mask>",
-  "max_length": 510,
-  "model_max_length": 1000000000000000019884624838656,
-  "pad_token": "<pad>",
-  "sep_token": "</s>",
-  "sp_model_kwargs": {},
-  "stride": 0,
-  "tokenizer_class": "CamembertTokenizer",
-  "truncation_side": "right",
-  "truncation_strategy": "longest_first",
-  "unk_token": "<unk>"
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e5fe62a2682111407d2476010a3f54f3cf0feabefd0b4d8c476cda996fc8909f
+oid sha256:ebddb684d4e9a90f9d7b30c61006339c7c1441482bb13adfcc8e3694a4ef7d88
 size 5112