Initial commit from mrm8488

README.md

@@ -0,0 +1,76 @@
+---
+license: mit
+tags:
+- generated_from_trainer
+datasets:
+- hate_speech18
+metrics:
+- accuracy
+model-index:
+- name: deberta-v3-small-hate-speech
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: hate_speech18
+      type: hate_speech18
+      args: default
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.916058394160584
+---
+
+<!-- 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. -->
+
+# deberta-v3-small-hate-speech
+
+This model is a fine-tuned version of [microsoft/deberta-v3-small](https://huggingface.co/microsoft/deberta-v3-small) on the hate_speech18 dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.2922
+- Accuracy: 0.9161
+
+## 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 |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 0.4147        | 1.0   | 650  | 0.3910          | 0.8832   |
+| 0.2975        | 2.0   | 1300 | 0.2922          | 0.9161   |
+| 0.2575        | 3.0   | 1950 | 0.3555          | 0.9051   |
+| 0.1553        | 4.0   | 2600 | 0.4263          | 0.9124   |
+| 0.1267        | 5.0   | 3250 | 0.4238          | 0.9161   |
+
+
+### Framework versions
+
+- Transformers 4.12.5
+- Pytorch 1.10.0+cu111
+- Datasets 1.16.1
+- Tokenizers 0.10.3

added_tokens.json

@@ -0,0 +1 @@
+{"[MASK]": 128000}

config.json

@@ -0,0 +1,47 @@
+{
+  "_name_or_path": "microsoft/deberta-v3-small",
+  "architectures": [
+    "DebertaV2ForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3
+  },
+  "layer_norm_eps": 1e-07,
+  "max_position_embeddings": 512,
+  "max_relative_positions": -1,
+  "model_type": "deberta-v2",
+  "norm_rel_ebd": "layer_norm",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 6,
+  "pad_token_id": 0,
+  "pooler_dropout": 0,
+  "pooler_hidden_act": "gelu",
+  "pooler_hidden_size": 768,
+  "pos_att_type": [
+    "p2c",
+    "c2p"
+  ],
+  "position_biased_input": false,
+  "position_buckets": 256,
+  "relative_attention": true,
+  "share_att_key": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.12.5",
+  "type_vocab_size": 0,
+  "vocab_size": 128100
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7bba1d425fa321ea03dcefc70da5b922d4bfdce43a60b056f52d8b8ac8deed4a
+size 567639019

runs/Dec01_17-09-18_c9404fbf682f/1638378572.6315808/events.out.tfevents.1638378572.c9404fbf682f.608.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2426294740adf0d06b368cf24915974ae66bde4a118df2fa54ef7cb2b138296
+size 4577

runs/Dec01_17-09-18_c9404fbf682f/events.out.tfevents.1638378572.c9404fbf682f.608.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8fd22104c5bbaaa8c62c46bf59980a265b5a17d34ef1c6e101d4e9f78ac895fa
+size 6464

runs/Dec01_17-09-18_c9404fbf682f/events.out.tfevents.1638379118.c9404fbf682f.608.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80b411e4c0d2064e49ce80345b2230bdf7be46dd0f483fabb839355184de4945
+size 363

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "[CLS]", "eos_token": "[SEP]", "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}

spm.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
+size 2464616

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": false, "bos_token": "[CLS]", "eos_token": "[SEP]", "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "split_by_punct": false, "sp_model_kwargs": {}, "vocab_type": "spm", "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "microsoft/deberta-v3-small", "tokenizer_class": "DebertaV2Tokenizer"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6d1f6c71235107b4e94a472fb0d5f2dfc3ee48ce7c4d109b3799116c2637ce8
+size 2863