initial upload

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "bert-base-uncased",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "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",
+  "transformers_version": "4.3.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

eval_results.txt

@@ -0,0 +1,8 @@
+Output: {
+  "acc": 0.6205404499115925,
+  "r2": 0.6205404499115925
+}
+Output: {
+  "acc": 0.7122379620175763,
+  "r2": 0.7122379620175763
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b68b77c0167485d3787760384021224d7091c268816e7cf39e87bb70cea8cdd
+size 438018958

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, "do_basic_tokenize": true, "never_split": null, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "name_or_path": "bert-base-uncased"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89bd9b4daef8af7f5bf354cac866ee2a8299e2f0e987198a6190c69f73251ec0
+size 943

training_args.json

@@ -0,0 +1 @@
+{"model_path": "bert-base-uncased", "output_dir": "finetuned_women_clothing_review/", "data_dir": "./datasets/auto_mm/women_clothing_review", "max_seq_length": 128, "epoch": 5, "local_rank": -1, "task_name": "cloth", "overwrite_cache": false, "learning_rate": 5e-05, "adam_epsilon": 1e-08, "train_batch_size": 16, "eval_batch_size": 64, "weight_decay": 0.1, "num_labels": 1, "train": true, "eval": true, "n_gpu": 1, "device": "cuda"}