zorbahouse/roberta-base-klue-ynat-classification

README.md

@@ -0,0 +1,60 @@
+---
+library_name: transformers
+base_model: klue/roberta-base
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: results
+  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. -->
+
+# results
+
+This model is a fine-tuned version of [klue/roberta-base](https://huggingface.co/klue/roberta-base) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1184
+- Accuracy: 0.966
+
+## 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: 5e-05
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 1
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 0.5397        | 1.0   | 1250 | 0.1594          | 0.951    |
+
+
+### Framework versions
+
+- Transformers 4.44.1
+- Pytorch 2.3.1+cu121
+- Datasets 2.19.0
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,48 @@
+{
+  "_name_or_path": "klue/roberta-base",
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "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,
+  "id2label": {
+    "0": "IT\uacfc\ud559",
+    "1": "\uacbd\uc81c",
+    "2": "\uc0ac\ud68c",
+    "3": "\uc0dd\ud65c\ubb38\ud654",
+    "4": "\uc138\uacc4",
+    "5": "\uc2a4\ud3ec\uce20",
+    "6": "\uc815\uce58"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "IT\uacfc\ud559": 0,
+    "\uacbd\uc81c": 1,
+    "\uc0ac\ud68c": 2,
+    "\uc0dd\ud65c\ubb38\ud654": 3,
+    "\uc138\uacc4": 4,
+    "\uc2a4\ud3ec\uce20": 5,
+    "\uc815\uce58": 6
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "tokenizer_class": "BertTokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 32000
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f41454d07dff5a65dcaab607bd23d707ff0a296db06de27abcff17a950b95e56
+size 442518124

runs/Aug22_13-50-45_367745fa8281/events.out.tfevents.1724334657.367745fa8281.1732.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6473399e6e0f580b2995edb33b1a64cb76b0de97dfa9c1d3a4e4fe9b84e41376
+size 6131

runs/Aug22_13-50-45_367745fa8281/events.out.tfevents.1724335612.367745fa8281.1732.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ef035e9e89b980036bd5f3cef07da6a63102111244c45bfc00b42a2461f3a20
+size 411

runs/Aug22_15-27-36_367745fa8281/events.out.tfevents.1724340464.367745fa8281.27996.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:351cfd414b61560802f547e49ee15bbbee51b07018eba0dfd67a3b46c713165e
+size 6365

runs/Aug22_15-27-36_367745fa8281/events.out.tfevents.1724341438.367745fa8281.27996.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39ae492c998af49052c6c2b1522e392a1053d204cd7d96f146bb86166574cf43
+size 411

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0a6c2a941761bea19de99accc6d8a079a17402a6cda238d9965b44aa230820a
+size 5176