Initial Commit

README.md

@@ -0,0 +1,69 @@
+---
+license: apache-2.0
+base_model: bert-base-uncased
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: scenario-KD-SCR-DIV2-data-glue-qnli-model-bert-base-uncased-run-1
+  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. -->
+
+# scenario-KD-SCR-DIV2-data-glue-qnli-model-bert-base-uncased-run-1
+
+This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.3184
+- Accuracy: 0.8656
+
+## 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: 32
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 32
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 6969
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss | Accuracy |
+|:-------------:|:-----:|:-----:|:---------------:|:--------:|
+| 2.0351        | 1.0   | 3273  | 1.4221          | 0.8567   |
+| 1.4555        | 2.0   | 6546  | 1.4660          | 0.8504   |
+| 0.9549        | 3.0   | 9819  | 1.4297          | 0.8678   |
+| 0.7553        | 4.0   | 13093 | 1.4296          | 0.8631   |
+| 0.66          | 5.0   | 16366 | 1.2841          | 0.8653   |
+| 0.5769        | 6.0   | 19639 | 1.3951          | 0.8609   |
+| 0.5347        | 7.0   | 22912 | 1.3986          | 0.8607   |
+| 0.4957        | 8.0   | 26186 | 1.3184          | 0.8656   |
+
+
+### Framework versions
+
+- Transformers 4.36.2
+- Pytorch 2.1.2
+- Datasets 2.16.0
+- Tokenizers 0.15.0

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "bert-base-uncased",
+  "architectures": [
+    "BertForSequenceClassificationKD"
+  ],
+  "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": 6,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.36.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2bc14f7184d8ed4a8516ce671e6e888c732a7b6d4cc4f203df2bd32c0ce61f9e
+size 267838384

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbdbcb5d25734150b10979b7d7c3ae5538dce76be98d1eee95979976075d5035
+size 4920