upload model

.gitignore

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

README.md

@@ -0,0 +1,87 @@
+---
+tags:
+- generated_from_trainer
+datasets:
+- imdb
+metrics:
+- accuracy
+model-index:
+- name: baseline
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: imdb
+      type: imdb
+      config: plain_text
+      split: test
+      args: plain_text
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.92088
+---
+
+<!-- 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. -->
+
+# baseline
+
+This model is a fine-tuned version of [textattack/bert-base-uncased-imdb](https://huggingface.co/textattack/bert-base-uncased-imdb) on the imdb dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.5238
+- Accuracy: 0.9209
+
+## 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: 32
+- eval_batch_size: 32
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 3.0
+- mixed_precision_training: Native AMP
+
+### Training script
+
+```bash
+python run_glue.py \
+  --model_name_or_path textattack/bert-base-uncased-imdb \
+  --dataset_name imdb  \
+  --do_train \
+  --do_eval \
+  --max_seq_length 384 \
+  --pad_to_max_length False \
+  --per_device_train_batch_size 32 \
+  --per_device_eval_batch_size 32 \
+  --fp16 \
+  --learning_rate 5e-5 \
+  --optim adamw_torch \
+  --num_train_epochs 3 \
+  --overwrite_output_dir \
+  --output_dir /tmp/bert-base-uncased-imdb
+```
+
+### Framework versions
+
+- Transformers 4.27.4
+- Pytorch 1.13.1
+- Datasets 2.11.0
+- Tokenizers 0.13.3

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.92088,
+    "eval_loss": 0.5238260626792908,
+    "eval_runtime": 66.6946,
+    "eval_samples": 25000,
+    "eval_samples_per_second": 374.843,
+    "eval_steps_per_second": 11.725,
+    "train_loss": 0.057570336623163375,
+    "train_runtime": 650.909,
+    "train_samples": 25000,
+    "train_samples_per_second": 115.223,
+    "train_steps_per_second": 3.604
+}

config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "textattack/bert-base-uncased-imdb",
+  "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,
+  "id2label": {
+    "0": 0,
+    "1": 1
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "0": 0,
+    "1": 1
+  },
+  "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": "4.27.4",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.92088,
+    "eval_loss": 0.5238260626792908,
+    "eval_runtime": 66.6946,
+    "eval_samples": 25000,
+    "eval_samples_per_second": 374.843,
+    "eval_steps_per_second": 11.725
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad19993f9b2c0193715910d6717c55af0e6af95160b34e997f63240e71a0bac5
+size 438007925

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,15 @@
+{
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "special_tokens_map_file": "/home/yujiepan/.cache/huggingface/hub/models--textattack--bert-base-uncased-imdb/snapshots/c70b9f391af2067f7eff69a03940218bba9b8d39/special_tokens_map.json",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "train_loss": 0.057570336623163375,
+    "train_runtime": 650.909,
+    "train_samples": 25000,
+    "train_samples_per_second": 115.223,
+    "train_steps_per_second": 3.604
+}

trainer_state.json

@@ -0,0 +1,49 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "global_step": 2346,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.64,
+      "learning_rate": 3.94075021312873e-05,
+      "loss": 0.1202,
+      "step": 500
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 2.8751065643648767e-05,
+      "loss": 0.0785,
+      "step": 1000
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 1.8094629156010232e-05,
+      "loss": 0.0481,
+      "step": 1500
+    },
+    {
+      "epoch": 2.56,
+      "learning_rate": 7.438192668371696e-06,
+      "loss": 0.0162,
+      "step": 2000
+    },
+    {
+      "epoch": 3.0,
+      "step": 2346,
+      "total_flos": 1.4799996864e+16,
+      "train_loss": 0.057570336623163375,
+      "train_runtime": 650.909,
+      "train_samples_per_second": 115.223,
+      "train_steps_per_second": 3.604
+    }
+  ],
+  "max_steps": 2346,
+  "num_train_epochs": 3,
+  "total_flos": 1.4799996864e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ffaf73f3c1f4339de1c60e430185af7b3691e0961621089b06a41c7f71c07c4
+size 3771