updating

.gitattributes

@@ -1,35 +1,12 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin.* filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
 *.bin filter=lfs diff=lfs merge=lfs -text
-*.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
-*.ftz filter=lfs diff=lfs merge=lfs -text
-*.gz filter=lfs diff=lfs merge=lfs -text
 *.h5 filter=lfs diff=lfs merge=lfs -text
-*.joblib filter=lfs diff=lfs merge=lfs -text
-*.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
-*.model filter=lfs diff=lfs merge=lfs -text
-*.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
-*.onnx filter=lfs diff=lfs merge=lfs -text
-*.ot filter=lfs diff=lfs merge=lfs -text
-*.parquet filter=lfs diff=lfs merge=lfs -text
-*.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
-*.pt filter=lfs diff=lfs merge=lfs -text
-*.pth filter=lfs diff=lfs merge=lfs -text
-*.rar filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text
-*.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
 *.tflite filter=lfs diff=lfs merge=lfs -text
-*.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
-*.xz filter=lfs diff=lfs merge=lfs -text
-*.zip filter=lfs diff=lfs merge=lfs -text
-*.zst filter=lfs diff=lfs merge=lfs -text
-*tfevents* filter=lfs diff=lfs merge=lfs -text
+*.tar.gz filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+runs/Mar22_01-22-16_dsmtyh100xx0153/events.out.tfevents.1711070537.dsmtyh100xx0153.4107907.0 filter=lfs diff=lfs merge=lfs -text
+runs/Mar22_01-58-04_dsmtyh100xx0153/events.out.tfevents.1711072685.dsmtyh100xx0153.4141967.0 filter=lfs diff=lfs merge=lfs -text
+runs/Mar22_06-16-00_dsmtyh100xx0153/events.out.tfevents.1711088160.dsmtyh100xx0153.156772.0 filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,10 @@
+## TextAttack Model Card
+This `bert-base-uncased` model was fine-tuned for sequence classification using TextAttack 
+and the yelp_polarity dataset loaded using the `nlp` library. The model was fine-tuned 
+for 5 epochs with a batch size of 16, a learning 
+rate of 5e-05, and a maximum sequence length of 256. 
+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 0.9699473684210527, as measured by the 
+eval set accuracy, found after 4 epochs.
+
+For more information, check out [TextAttack on Github](https://github.com/QData/TextAttack).

config.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
+}

flax_model.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80c93148809240ce872694c420e0b28a6d5048518edd50f91b9ac4f2825be5d5
+size 437942328

log.txt

@@ -0,0 +1,34 @@
+Writing logs to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/bert-base-uncased-yelp_polarity-2020-07-08-10:42/log.txt.
+Loading nlp dataset yelp_polarity, split train.
+Loading nlp dataset yelp_polarity, split test.
+Loaded dataset. Found: 2 labels: ([0, 1])
+Loading transformers AutoModelForSequenceClassification: bert-base-uncased
+Tokenizing training data. (len: 560000)
+Tokenizing eval data (len: 38000)
+Loaded data and tokenized in 720.6436557769775s
+Using torch.nn.DataParallel.
+Training model across 4 GPUs
+Wrote original training args to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/bert-base-uncased-yelp_polarity-2020-07-08-10:42/train_args.json.
+***** Running training *****
+	Num examples = 560000
+	Batch size = 16
+	Max sequence length = 256
+	Num steps = 175000
+	Num epochs = 5
+	Learning rate = 5e-05
+Eval accuracy: 95.95263157894736%
+Best acc found. Saved model to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/bert-base-uncased-yelp_polarity-2020-07-08-10:42/.
+Eval accuracy: 96.59473684210526%
+Best acc found. Saved model to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/bert-base-uncased-yelp_polarity-2020-07-08-10:42/.
+Eval accuracy: 96.69473684210527%
+Best acc found. Saved model to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/bert-base-uncased-yelp_polarity-2020-07-08-10:42/.
+Eval accuracy: 96.91052631578947%
+Best acc found. Saved model to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/bert-base-uncased-yelp_polarity-2020-07-08-10:42/.
+Eval accuracy: 96.99473684210527%
+Best acc found. Saved model to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/bert-base-uncased-yelp_polarity-2020-07-08-10:42/.
+Finished training. Re-loading and evaluating model from disk.
+Loading transformers AutoModelForSequenceClassification: bert-base-uncased
+Eval of saved model accuracy: 96.99473684210527%
+Saved tokenizer <textattack.models.tokenizers.auto_tokenizer.AutoTokenizer object at 0x7fcc548eb730> to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/bert-base-uncased-yelp_polarity-2020-07-08-10:42/.
+Wrote README to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/bert-base-uncased-yelp_polarity-2020-07-08-10:42/README.md.
+Wrote final training args to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/bert-base-uncased-yelp_polarity-2020-07-08-10:42/train_args.json.

outputs/last_model/config.json

@@ -0,0 +1,10 @@
+{
+    "architectures": "LSTMForClassification",
+    "hidden_size": 150,
+    "depth": 1,
+    "dropout": 0.3,
+    "num_labels": 2,
+    "max_seq_length": 128,
+    "model_path": null,
+    "emb_layer_trainable": true
+}

outputs/last_model/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b2b5d5ee6a89c8983119c70a2533f4c564266cac9e75d6c4063a6c124237529
+size 320670479

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:934989a6c6465c39311acbb466e8e27e4a715539c3baa95c7c66b424a6c27a66
+size 437985387

runs/Mar22_01-22-16_dsmtyh100xx0153/events.out.tfevents.1711070537.dsmtyh100xx0153.4107907.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6111d8c294b444df3fd36c3b6f89f3bb94f171378739f9c3319685205dbb688c
+size 4611

runs/Mar22_01-58-04_dsmtyh100xx0153/events.out.tfevents.1711072685.dsmtyh100xx0153.4141967.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65ec1882ef54182df948fc55b077c1772881802c93b895f6e6f2a357a336a290
+size 4611

runs/Mar22_06-16-00_dsmtyh100xx0153/events.out.tfevents.1711088160.dsmtyh100xx0153.156772.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9281542ad5ddc27cbb571b8e31bd287a3defe268d4258f16c0f1c3be34f821d
+size 4611

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_args.json

@@ -0,0 +1,25 @@
+{
+  "model": "bert-base-uncased",
+  "dataset": "yelp_polarity",
+  "dataset_train_split": "train",
+  "dataset_dev_split": "test",
+  "tb_writer_step": 1000,
+  "checkpoint_steps": -1,
+  "checkpoint_every_epoch": false,
+  "num_train_epochs": 5,
+  "early_stopping_epochs": -1,
+  "batch_size": 16,
+  "max_length": 256,
+  "learning_rate": 5e-05,
+  "grad_accum_steps": 1,
+  "warmup_proportion": 0.1,
+  "config_name": "config.json",
+  "weights_name": "pytorch_model.bin",
+  "enable_wandb": false,
+  "output_dir": "/p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/bert-base-uncased-yelp_polarity-2020-07-08-10:42/",
+  "num_labels": 2,
+  "do_regression": false,
+  "best_eval_score": 0.9699473684210527,
+  "best_eval_score_epoch": 4,
+  "epochs_since_best_eval_score": 0
+}

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 +1,132 @@
+{
+  "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
+}