add model

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

README.md

@@ -0,0 +1,75 @@
+---
+tags:
+- generated_from_trainer
+datasets:
+- glue
+metrics:
+- accuracy
+model_index:
+- name: hackMIT-finetuned-sst2
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: glue
+      type: glue
+      args: sst2
+    metric:
+      name: Accuracy
+      type: accuracy
+      value: 0.786697247706422
+---
+
+<!-- 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. -->
+
+# hackMIT-finetuned-sst2
+
+This model is a fine-tuned version of [HackMIT/double-agent](https://huggingface.co/HackMIT/double-agent) on the glue dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.3250
+- Accuracy: 0.7867
+
+## 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: 2e-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: 5
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss | Accuracy |
+|:-------------:|:-----:|:-----:|:---------------:|:--------:|
+| 0.0673        | 1.0   | 4210  | 1.3312          | 0.7787   |
+| 0.0804        | 2.0   | 8420  | 1.3250          | 0.7867   |
+| 0.0594        | 3.0   | 12630 | 1.3437          | 0.7867   |
+| 0.0602        | 4.0   | 16840 | 1.3437          | 0.7867   |
+| 0.0627        | 5.0   | 21050 | 1.3437          | 0.7867   |
+
+
+### Framework versions
+
+- Transformers 4.9.2
+- Pytorch 1.9.0+cu102
+- Datasets 1.11.0
+- Tokenizers 0.10.3

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "HackMIT/double-agent",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 128,
+  "initializer_range": 0.02,
+  "intermediate_size": 512,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 2,
+  "num_hidden_layers": 2,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.9.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fb3b39c9687b513dd7387ed5c0d5d37c8ba088a0e4cb2da8fbc8713eac22e57
+size 17564583

runs/Aug23_01-54-17_a81d125a81bf/1629684030.3332376/events.out.tfevents.1629684030.a81d125a81bf.75.11

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4e486e4cf4565d4d0674bbc8cd71c51d902a039ba1d52dd13f0c4b9bfb7b447
+size 4193

runs/Aug23_01-54-17_a81d125a81bf/1629684111.6883879/events.out.tfevents.1629684111.a81d125a81bf.75.13

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1c9733d2180a468e6df9abca2973c7112d7d97a4a21ef23d81a5f88a673333c
+size 4193

runs/Aug23_01-54-17_a81d125a81bf/1629684300.576347/events.out.tfevents.1629684300.a81d125a81bf.75.15

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e48f288a5f77ca507345bd032bc985ff2e798b8da6da4ca2c40ab6dda83948e7
+size 4193

runs/Aug23_01-54-17_a81d125a81bf/events.out.tfevents.1629684030.a81d125a81bf.75.10

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ff894a6086bd6facbf7a0e2ae4cf8efec56b0f537795ef173bd87f3123d009a
+size 4268

runs/Aug23_01-54-17_a81d125a81bf/events.out.tfevents.1629684111.a81d125a81bf.75.12

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01337671f749d738ec1359fbe6b7ee5306d3084ec9f2faac6f2ee11c1cae8b68
+size 4268

runs/Aug23_01-54-17_a81d125a81bf/events.out.tfevents.1629684300.a81d125a81bf.75.14

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c277ab25c5eec829c6ae488f5d68161d5cc9fe3fc31f424fdc5babcfccc916a3
+size 11623

runs/Aug23_01-54-17_a81d125a81bf/events.out.tfevents.1629684672.a81d125a81bf.75.16

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f82cdc49a946e931fb11edc46455772cce02215841bd5a6e9ad131b2cc95e199
+size 369

special_tokens_map.json

@@ -0,0 +1 @@
+{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "special_tokens_map_file": null, "name_or_path": "HackMIT/double-agent", "do_basic_tokenize": true, "never_split": null, "tokenizer_class": "BertTokenizer"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec69fef0beb204e2c8074d6b4172d00067b695337c24390e691e13cb77b03011
+size 2671