tona3738/model1-1

README.md

@@ -0,0 +1,63 @@
+---
+library_name: transformers
+base_model: Blue7Bird/chungli_ao_bert_model
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- f1
+- precision
+- recall
+model-index:
+- name: training_output
+  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. -->
+
+# training_output
+
+This model is a fine-tuned version of [Blue7Bird/chungli_ao_bert_model](https://huggingface.co/Blue7Bird/chungli_ao_bert_model) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1731
+- Accuracy: 0.9559
+- F1: 0.9559
+- Precision: 0.9570
+- Recall: 0.9565
+
+## 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: 7.009534549707257e-05
+- train_batch_size: 16
+- eval_batch_size: 16
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 1
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.45.2
+- Pytorch 2.5.1+cu121
+- Datasets 3.1.0
+- Tokenizers 0.20.3

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "Blue7Bird/chungli_ao_bert_model",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.45.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 21455
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e0b93ad523139a511d12c1d6c0d3eb7513d73822394d4803a947d34d0dfaf5a
+size 410104792

runs/Nov25_19-19-11_9369a326af02/events.out.tfevents.1732562352.9369a326af02.1492.11

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f455e66c18ea36dede8b30272f49ef5dab3ee7def47b62ff32010e6a8df845f
+size 5834

runs/Nov25_19-19-11_9369a326af02/events.out.tfevents.1732562382.9369a326af02.1492.12

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26ade35988e66e9786ac5a66dfc00b68f83715b427b3fca0cd7a457baa188d8e
+size 1032

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0279f880cef9ec7a87a7e0bd69b55ed58e2744f95365b6957e9843306ceb0187
+size 5240