Tippawan/name_vs_common

README.md

@@ -0,0 +1,53 @@
+---
+library_name: transformers
+base_model: airesearch/wangchanberta-base-att-spm-uncased
+tags:
+- generated_from_trainer
+model-index:
+- name: wisesight_sentiment
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# wisesight_sentiment
+
+This model is a fine-tuned version of [airesearch/wangchanberta-base-att-spm-uncased](https://huggingface.co/airesearch/wangchanberta-base-att-spm-uncased) on the None dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 3e-05
+- train_batch_size: 4
+- eval_batch_size: 4
+- 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
+- num_epochs: 10
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 5.4.0
+- Pytorch 2.11.0+cu130
+- Datasets 4.0.0
+- Tokenizers 0.22.2

config.json

@@ -0,0 +1,31 @@
+{
+  "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",
+  "hidden_dropout_prob": 0.1,
+  "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",
+  "num_attention_head": 12,
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "problem_type": "single_label_classification",
+  "tie_word_embeddings": true,
+  "transformers_version": "5.4.0",
+  "type_vocab_size": 1,
+  "use_cache": false,
+  "vocab_size": 25005
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9621dd6bf74bb5851755cc7c21a2919f89193ba6e02a0b61d49c0dda5aa39f9
+size 421007904

tokenizer_config.json

@@ -0,0 +1,20 @@
+{
+  "add_prefix_space": true,
+  "backend": "tokenizers",
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "extra_special_tokens": [
+    "<s>NOTUSED",
+    "</s>NOTUSED",
+    "<_>"
+  ],
+  "is_local": false,
+  "mask_token": "<mask>",
+  "model_max_length": 510,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "CamembertTokenizer",
+  "unk_id": 0,
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0b06f1e78c1fef8f7175805b15a0f39c76343252ea750288bccea0e733efb9e
+size 5201