initial commit

README.md

@@ -1,3 +1,35 @@
 ---
 license: apache-2.0
 ---
+
+## Overview
+
+This model was trained with data from https://registry.opendata.aws/helpful-sentences-from-reviews/ to predict how "helpful" a review is.
+
+The model was fine-tuned from the `distilbert-base-uncased` model
+
+### Labels
+LABEL_0 - Not helpful  
+LABEL_1 - Helpful  
+
+### How to use
+
+The following code shows how to make a prediction with this model
+
+```python
+tokenizer = AutoTokenizer.from_pretrained("banjtheman/distilbert-base-uncased-helpful-amazon")
+
+model = AutoModelForSequenceClassification.from_pretrained(
+    "banjtheman/distilbert-base-uncased-helpful-amazon"
+)
+
+pipe = TextClassificationPipeline(model=model, tokenizer=tokenizer)
+
+result = pipe("This was a Christmas gift for my grandson.")
+
+print(result)
+
+#[{'label': 'LABEL_0', 'score': 0.998775064945221}]
+# This is NOT A HELPFUL comment
+
+```

config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "initializer_range": 0.02,
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.16.2",
+  "vocab_size": 30522
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8080440c31bff658bc43e21bb670280f53e2ff99a8d02104d056acf234e9a853
+size 535697121

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:240f3b4382ebc4b725cb8feabf56490d2331580deec62d7a538645022397ee92
+size 267858673

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d472be743e81e2c44df6fef58280983b27985a661ff1a0ea5e46b7c6ecf48c4
+size 13547

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70f3b6898b3736c88c4753f24553626a755034f7c39b91298e6bf1d0b4c4372f
+size 623

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, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "distilbert-base-uncased", "tokenizer_class": "DistilBertTokenizer"}

trainer_state.json

@@ -0,0 +1,88 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.8,
+  "global_step": 6000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.8400000000000003e-05,
+      "loss": 0.4452,
+      "step": 500
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 1.6800000000000002e-05,
+      "loss": 0.4168,
+      "step": 1000
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 1.5200000000000002e-05,
+      "loss": 0.3512,
+      "step": 1500
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 1.3600000000000002e-05,
+      "loss": 0.306,
+      "step": 2000
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 1.2e-05,
+      "loss": 0.3201,
+      "step": 2500
+    },
+    {
+      "epoch": 2.4,
+      "learning_rate": 1.04e-05,
+      "loss": 0.2128,
+      "step": 3000
+    },
+    {
+      "epoch": 2.8,
+      "learning_rate": 8.8e-06,
+      "loss": 0.2058,
+      "step": 3500
+    },
+    {
+      "epoch": 3.2,
+      "learning_rate": 7.2000000000000005e-06,
+      "loss": 0.1738,
+      "step": 4000
+    },
+    {
+      "epoch": 3.6,
+      "learning_rate": 5.600000000000001e-06,
+      "loss": 0.1371,
+      "step": 4500
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 0.1345,
+      "step": 5000
+    },
+    {
+      "epoch": 4.4,
+      "learning_rate": 2.4000000000000003e-06,
+      "loss": 0.0901,
+      "step": 5500
+    },
+    {
+      "epoch": 4.8,
+      "learning_rate": 8.000000000000001e-07,
+      "loss": 0.087,
+      "step": 6000
+    }
+  ],
+  "max_steps": 6250,
+  "num_train_epochs": 5,
+  "total_flos": 1047523211328192.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d664d1289c9fcdb7f8329debbb07e51e629d0317f6fa2a09b795b08e3429449
+size 2991