Upload folder using huggingface_hub

README.md

@@ -0,0 +1,6 @@
+## TextAttack Model Card
+
+            This `lstm` model was fine-tuned using TextAttackand the *yelp_polarity* dataset loaded using the huggingface library. The model was fine-tuned for 50 epochs with a batch size of 8, a maximum sequence length of 128, and an initial learning rate of 1e-05.
+            Since this was a classification task, the model was trained with a cross-entropy loss function. The best score the model achieved on this task was 0.9174473684210527, as measured by the eval set accuracy, found after 28 epochs.
+
+            For more information on the source repo, check out [TextAttack on Github](https://github.com/QData/TextAttack).

config copy.json

@@ -0,0 +1,22 @@
+{
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "model_name": "my_model",
+  "attention_probs_dropout_prob": 0.1,
+  "finetuning_task": "yelp_polarity",
+  "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,
+  "type_vocab_size": 2,
+  "vocab_size": 30522
+}

config.json

@@ -0,0 +1,21 @@
+{
+    "architectures": [
+      "BertForSequenceClassification"
+    ],
+    "attention_probs_dropout_prob": 0.1,
+    "finetuning_task": "yelp_polarity",
+    "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,
+    "type_vocab_size": 2,
+    "vocab_size": 30522
+  }

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c70002c363b84cb50fc02d63e9ebbc2bca966638b2958446c5a51094c7348c2e
+size 320670479

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, "model_max_length": 512}

train_log.txt

@@ -0,0 +1,281 @@
+Writing logs to ./outputs/2024-03-22-01-16-17-693140/train_log.txt.
+Wrote original training args to ./outputs/2024-03-22-01-16-17-693140/training_args.json.
+***** Running training *****
+  Num examples = 560000
+  Num epochs = 50
+  Num clean epochs = 50
+  Instantaneous batch size per device = 8
+  Total train batch size (w. parallel, distributed & accumulation) = 8
+  Gradient accumulation steps = 1
+  Total optimization steps = 3500000
+==========================================================
+Epoch 1
+Running clean epoch 1/50
+Train accuracy: 81.85%
+Eval accuracy: 88.42%
+Best score found. Saved model to ./outputs/2024-03-22-01-16-17-693140/best_model/
+==========================================================
+Epoch 2
+Running clean epoch 2/50
+Train accuracy: 88.95%
+Eval accuracy: 88.87%
+Best score found. Saved model to ./outputs/2024-03-22-01-16-17-693140/best_model/
+==========================================================
+Epoch 3
+Running clean epoch 3/50
+Train accuracy: 89.65%
+Eval accuracy: 89.58%
+Best score found. Saved model to ./outputs/2024-03-22-01-16-17-693140/best_model/
+==========================================================
+Epoch 4
+Running clean epoch 4/50
+Train accuracy: 90.02%
+Eval accuracy: 89.53%
+==========================================================
+Epoch 5
+Running clean epoch 5/50
+Train accuracy: 90.22%
+Eval accuracy: 89.73%
+Best score found. Saved model to ./outputs/2024-03-22-01-16-17-693140/best_model/
+==========================================================
+Epoch 6
+Running clean epoch 6/50
+Train accuracy: 90.43%
+Eval accuracy: 89.60%
+==========================================================
+Epoch 7
+Running clean epoch 7/50
+Train accuracy: 90.64%
+Eval accuracy: 89.83%
+Best score found. Saved model to ./outputs/2024-03-22-01-16-17-693140/best_model/
+==========================================================
+Epoch 8
+Running clean epoch 8/50
+Train accuracy: 90.79%
+Eval accuracy: 90.04%
+Best score found. Saved model to ./outputs/2024-03-22-01-16-17-693140/best_model/
+==========================================================
+Epoch 9
+Running clean epoch 9/50
+Train accuracy: 90.97%
+Eval accuracy: 90.22%
+Best score found. Saved model to ./outputs/2024-03-22-01-16-17-693140/best_model/
+==========================================================
+Epoch 10
+Running clean epoch 10/50
+Train accuracy: 91.16%
+Eval accuracy: 90.33%
+Best score found. Saved model to ./outputs/2024-03-22-01-16-17-693140/best_model/
+==========================================================
+Epoch 11
+Running clean epoch 11/50
+Train accuracy: 91.37%
+Eval accuracy: 90.50%
+Best score found. Saved model to ./outputs/2024-03-22-01-16-17-693140/best_model/
+==========================================================
+Epoch 12
+Running clean epoch 12/50
+Train accuracy: 91.58%
+Eval accuracy: 90.42%
+==========================================================
+Epoch 13
+Running clean epoch 13/50
+Train accuracy: 91.81%
+Eval accuracy: 90.64%
+Best score found. Saved model to ./outputs/2024-03-22-01-16-17-693140/best_model/
+==========================================================
+Epoch 14
+Running clean epoch 14/50
+Train accuracy: 92.01%
+Eval accuracy: 90.71%
+Best score found. Saved model to ./outputs/2024-03-22-01-16-17-693140/best_model/
+==========================================================
+Epoch 15
+Running clean epoch 15/50
+Train accuracy: 92.23%
+Eval accuracy: 90.88%
+Best score found. Saved model to ./outputs/2024-03-22-01-16-17-693140/best_model/
+==========================================================
+Epoch 16
+Running clean epoch 16/50
+Train accuracy: 92.41%
+Eval accuracy: 90.95%
+Best score found. Saved model to ./outputs/2024-03-22-01-16-17-693140/best_model/
+==========================================================
+Epoch 17
+Running clean epoch 17/50
+Train accuracy: 92.59%
+Eval accuracy: 90.72%
+==========================================================
+Epoch 18
+Running clean epoch 18/50
+Train accuracy: 92.78%
+Eval accuracy: 91.12%
+Best score found. Saved model to ./outputs/2024-03-22-01-16-17-693140/best_model/
+==========================================================
+Epoch 19
+Running clean epoch 19/50
+Train accuracy: 92.97%
+Eval accuracy: 91.19%
+Best score found. Saved model to ./outputs/2024-03-22-01-16-17-693140/best_model/
+==========================================================
+Epoch 20
+Running clean epoch 20/50
+Train accuracy: 93.12%
+Eval accuracy: 91.43%
+Best score found. Saved model to ./outputs/2024-03-22-01-16-17-693140/best_model/
+==========================================================
+Epoch 21
+Running clean epoch 21/50
+Train accuracy: 93.28%
+Eval accuracy: 91.47%
+Best score found. Saved model to ./outputs/2024-03-22-01-16-17-693140/best_model/
+==========================================================
+Epoch 22
+Running clean epoch 22/50
+Train accuracy: 93.42%
+Eval accuracy: 91.52%
+Best score found. Saved model to ./outputs/2024-03-22-01-16-17-693140/best_model/
+==========================================================
+Epoch 23
+Running clean epoch 23/50
+Train accuracy: 93.54%
+Eval accuracy: 91.71%
+Best score found. Saved model to ./outputs/2024-03-22-01-16-17-693140/best_model/
+==========================================================
+Epoch 24
+Running clean epoch 24/50
+Train accuracy: 93.69%
+Eval accuracy: 91.61%
+==========================================================
+Epoch 25
+Running clean epoch 25/50
+Train accuracy: 93.86%
+Eval accuracy: 91.69%
+==========================================================
+Epoch 26
+Running clean epoch 26/50
+Train accuracy: 93.98%
+Eval accuracy: 91.63%
+==========================================================
+Epoch 27
+Running clean epoch 27/50
+Train accuracy: 94.12%
+Eval accuracy: 91.57%
+==========================================================
+Epoch 28
+Running clean epoch 28/50
+Train accuracy: 94.24%
+Eval accuracy: 91.74%
+Best score found. Saved model to ./outputs/2024-03-22-01-16-17-693140/best_model/
+==========================================================
+Epoch 29
+Running clean epoch 29/50
+Train accuracy: 94.37%
+Eval accuracy: 91.73%
+==========================================================
+Epoch 30
+Running clean epoch 30/50
+Train accuracy: 94.47%
+Eval accuracy: 91.45%
+==========================================================
+Epoch 31
+Running clean epoch 31/50
+Train accuracy: 94.62%
+Eval accuracy: 91.34%
+==========================================================
+Epoch 32
+Running clean epoch 32/50
+Train accuracy: 94.72%
+Eval accuracy: 91.58%
+==========================================================
+Epoch 33
+Running clean epoch 33/50
+Train accuracy: 94.86%
+Eval accuracy: 91.61%
+==========================================================
+Epoch 34
+Running clean epoch 34/50
+Train accuracy: 94.96%
+Eval accuracy: 91.70%
+==========================================================
+Epoch 35
+Running clean epoch 35/50
+Train accuracy: 95.06%
+Eval accuracy: 91.65%
+==========================================================
+Epoch 36
+Running clean epoch 36/50
+Train accuracy: 95.17%
+Eval accuracy: 91.71%
+==========================================================
+Epoch 37
+Running clean epoch 37/50
+Train accuracy: 95.28%
+Eval accuracy: 91.58%
+==========================================================
+Epoch 38
+Running clean epoch 38/50
+Train accuracy: 95.37%
+Eval accuracy: 91.52%
+==========================================================
+Epoch 39
+Running clean epoch 39/50
+Train accuracy: 95.49%
+Eval accuracy: 91.10%
+==========================================================
+Epoch 40
+Running clean epoch 40/50
+Train accuracy: 95.58%
+Eval accuracy: 91.54%
+==========================================================
+Epoch 41
+Running clean epoch 41/50
+Train accuracy: 95.68%
+Eval accuracy: 91.37%
+==========================================================
+Epoch 42
+Running clean epoch 42/50
+Train accuracy: 95.76%
+Eval accuracy: 91.34%
+==========================================================
+Epoch 43
+Running clean epoch 43/50
+Train accuracy: 95.85%
+Eval accuracy: 91.01%
+==========================================================
+Epoch 44
+Running clean epoch 44/50
+Train accuracy: 95.95%
+Eval accuracy: 91.35%
+==========================================================
+Epoch 45
+Running clean epoch 45/50
+Train accuracy: 96.03%
+Eval accuracy: 91.23%
+==========================================================
+Epoch 46
+Running clean epoch 46/50
+Train accuracy: 96.10%
+Eval accuracy: 91.19%
+==========================================================
+Epoch 47
+Running clean epoch 47/50
+Train accuracy: 96.18%
+Eval accuracy: 91.14%
+==========================================================
+Epoch 48
+Running clean epoch 48/50
+Train accuracy: 96.29%
+Eval accuracy: 91.27%
+==========================================================
+Epoch 49
+Running clean epoch 49/50
+Train accuracy: 96.39%
+Eval accuracy: 91.14%
+==========================================================
+Epoch 50
+Running clean epoch 50/50
+Train accuracy: 96.46%
+Eval accuracy: 91.11%
+Wrote README to ./outputs/2024-03-22-01-16-17-693140/README.md.

training_args copy.json

@@ -0,0 +1,132 @@
+{
+  "output_dir": "my_model",
+  "overwrite_output_dir": false,
+  "do_train": false,
+  "do_eval": false,
+  "do_predict": false,
+  "evaluation_strategy": "no",
+  "prediction_loss_only": false,
+  "per_device_train_batch_size": 8,
+  "per_device_eval_batch_size": 8,
+  "per_gpu_train_batch_size": null,
+  "per_gpu_eval_batch_size": null,
+  "gradient_accumulation_steps": 1,
+  "eval_accumulation_steps": null,
+  "eval_delay": 0,
+  "learning_rate": 5e-05,
+  "weight_decay": 0.0,
+  "adam_beta1": 0.9,
+  "adam_beta2": 0.999,
+  "adam_epsilon": 1e-08,
+  "max_grad_norm": 1.0,
+  "num_train_epochs": 3.0,
+  "max_steps": -1,
+  "lr_scheduler_type": "linear",
+  "lr_scheduler_kwargs": {},
+  "warmup_ratio": 0.0,
+  "warmup_steps": 0,
+  "log_level": "passive",
+  "log_level_replica": "warning",
+  "log_on_each_node": true,
+  "logging_dir": "my_model/training_args.json/runs/Mar22_01-08-45_dsmtyh100xx0153",
+  "logging_strategy": "steps",
+  "logging_first_step": false,
+  "logging_steps": 500,
+  "logging_nan_inf_filter": true,
+  "save_strategy": "steps",
+  "save_steps": 500,
+  "save_total_limit": null,
+  "save_safetensors": true,
+  "save_on_each_node": false,
+  "save_only_model": false,
+  "no_cuda": false,
+  "use_cpu": false,
+  "use_mps_device": false,
+  "seed": 42,
+  "data_seed": null,
+  "jit_mode_eval": false,
+  "use_ipex": false,
+  "bf16": false,
+  "fp16": false,
+  "fp16_opt_level": "O1",
+  "half_precision_backend": "auto",
+  "bf16_full_eval": false,
+  "fp16_full_eval": false,
+  "tf32": null,
+  "local_rank": 0,
+  "ddp_backend": null,
+  "tpu_num_cores": null,
+  "tpu_metrics_debug": false,
+  "debug": [],
+  "dataloader_drop_last": false,
+  "eval_steps": null,
+  "dataloader_num_workers": 0,
+  "dataloader_prefetch_factor": null,
+  "past_index": -1,
+  "run_name": "my_model",
+  "disable_tqdm": false,
+  "remove_unused_columns": true,
+  "label_names": null,
+  "load_best_model_at_end": false,
+  "metric_for_best_model": null,
+  "greater_is_better": null,
+  "ignore_data_skip": false,
+  "fsdp": [],
+  "fsdp_min_num_params": 0,
+  "fsdp_config": {
+    "min_num_params": 0,
+    "xla": false,
+    "xla_fsdp_v2": false,
+    "xla_fsdp_grad_ckpt": false
+  },
+  "fsdp_transformer_layer_cls_to_wrap": null,
+  "accelerator_config": {
+    "split_batches": false,
+    "dispatch_batches": null,
+    "even_batches": true,
+    "use_seedable_sampler": true
+  },
+  "deepspeed": null,
+  "label_smoothing_factor": 0.0,
+  "optim": "adamw_torch",
+  "optim_args": null,
+  "adafactor": false,
+  "group_by_length": false,
+  "length_column_name": "length",
+  "report_to": [],
+  "ddp_find_unused_parameters": null,
+  "ddp_bucket_cap_mb": null,
+  "ddp_broadcast_buffers": null,
+  "dataloader_pin_memory": true,
+  "dataloader_persistent_workers": false,
+  "skip_memory_metrics": true,
+  "use_legacy_prediction_loop": false,
+  "push_to_hub": false,
+  "resume_from_checkpoint": null,
+  "hub_model_id": null,
+  "hub_strategy": "every_save",
+  "hub_token": "<HUB_TOKEN>",
+  "hub_private_repo": false,
+  "hub_always_push": false,
+  "gradient_checkpointing": false,
+  "gradient_checkpointing_kwargs": null,
+  "include_inputs_for_metrics": false,
+  "fp16_backend": "auto",
+  "push_to_hub_model_id": null,
+  "push_to_hub_organization": null,
+  "push_to_hub_token": "<PUSH_TO_HUB_TOKEN>",
+  "mp_parameters": "",
+  "auto_find_batch_size": false,
+  "full_determinism": false,
+  "torchdynamo": null,
+  "ray_scope": "last",
+  "ddp_timeout": 1800,
+  "torch_compile": false,
+  "torch_compile_backend": null,
+  "torch_compile_mode": null,
+  "dispatch_batches": null,
+  "split_batches": null,
+  "include_tokens_per_second": false,
+  "include_num_input_tokens_seen": false,
+  "neftune_noise_alpha": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d353037f945468aa95fe1a5029d9a81e6ddc9e0c380a50912a7731a06f54c0ee
+size 203

training_args.json

@@ -0,0 +1,38 @@
+{
+    "model_name_or_path": "lstm",
+    "attack": null,
+    "dataset": "yelp_polarity",
+    "task_type": "classification",
+    "model_max_length": null,
+    "model_num_labels": null,
+    "dataset_train_split": "train",
+    "dataset_eval_split": "test",
+    "filter_train_by_labels": null,
+    "filter_eval_by_labels": null,
+    "num_epochs": 50,
+    "num_clean_epochs": 1,
+    "attack_epoch_interval": 1,
+    "early_stopping_epochs": null,
+    "learning_rate": 1e-05,
+    "num_warmup_steps": 500,
+    "weight_decay": 0.01,
+    "per_device_train_batch_size": 8,
+    "per_device_eval_batch_size": 32,
+    "gradient_accumulation_steps": 1,
+    "random_seed": 786,
+    "parallel": false,
+    "load_best_model_at_end": false,
+    "alpha": 1.0,
+    "num_train_adv_examples": -1,
+    "query_budget_train": null,
+    "attack_num_workers_per_device": 1,
+    "output_dir": "./outputs/2024-03-22-01-16-17-693140",
+    "checkpoint_interval_steps": null,
+    "checkpoint_interval_epochs": null,
+    "save_last": true,
+    "log_to_tb": false,
+    "tb_log_dir": null,
+    "log_to_wandb": false,
+    "wandb_project": "textattack",
+    "logging_interval_step": 1
+}