Initial commit from mrm8488

README.md

@@ -0,0 +1,70 @@
+---
+license: apache-2.0
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: distilRoberta-stereotype
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.989151002901476
+---
+
+<!-- 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. -->
+
+# distilRoberta-stereotype
+
+This model is a fine-tuned version of [distilroberta-base](https://huggingface.co/distilroberta-base) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0651
+- Accuracy: 0.9892
+
+## 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: 2e-05
+- train_batch_size: 16
+- eval_batch_size: 16
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 5
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss | Accuracy |
+|:-------------:|:-----:|:-----:|:---------------:|:--------:|
+| 0.0783        | 1.0   | 5615  | 0.0703          | 0.9847   |
+| 0.0468        | 2.0   | 11230 | 0.0573          | 0.9863   |
+| 0.0316        | 3.0   | 16845 | 0.0580          | 0.9882   |
+| 0.0172        | 4.0   | 22460 | 0.0591          | 0.9885   |
+| 0.0098        | 5.0   | 28075 | 0.0651          | 0.9892   |
+
+
+### Framework versions
+
+- Transformers 4.10.2
+- Pytorch 1.9.0+cu102
+- Datasets 1.11.0
+- Tokenizers 0.10.3

config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "distilroberta-base",
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "neutral",
+    "1": "stereotype",
+    "2": " anti-stereotype"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "neutral": 0,
+    "stereotype": 1,
+    "anti-stereotype": 2
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 6,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.10.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62e944dd48696d30dc554a6614f37b1e6b740c62e786c7df504d4e550190a6ab
+size 328529005

runs/Sep13_11-26-56_59fd62c7c141/1631532507.0280204/events.out.tfevents.1631532507.59fd62c7c141.75.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66a2c0d06ce033173b6d3923f27b15809eec6803c6aeb2ca7dab9fed8dc079f7
+size 4267

runs/Sep13_11-26-56_59fd62c7c141/events.out.tfevents.1631532507.59fd62c7c141.75.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ad80ede416b4bacbe63158ded3af2ef5cb0ce3508afd468550a4724be977cb8
+size 3229

runs/Sep13_11-30-08_59fd62c7c141/1631532608.5955467/events.out.tfevents.1631532608.59fd62c7c141.75.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa067d72acc9c37cdc6841e565c5af81794addd29a8a0d2020b22764a747411d
+size 4267

runs/Sep13_11-30-08_59fd62c7c141/events.out.tfevents.1631532608.59fd62c7c141.75.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2784500947b7aa889e8430db81590611560e9f5d708f7a07933c5e479ed078d5
+size 14086

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}

tokenizer_config.json

@@ -0,0 +1 @@
+{"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "add_prefix_space": false, "errors": "replace", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": "<mask>", "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "distilroberta-base", "tokenizer_class": "RobertaTokenizer"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a739c01e4e5801ab9884040af6f480c6395e2cbf1f6c2ad065dcdaef0ded38e1
+size 2735