kwang123/deberta-large-ReqORNot

README.md

@@ -0,0 +1,68 @@
+---
+license: mit
+base_model: microsoft/deberta-v3-large
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: deberta-large-ReqORNot
+  results: []
+---
+
+<!-- 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-large-ReqORNot
+
+This model is a fine-tuned version of [microsoft/deberta-v3-large](https://huggingface.co/microsoft/deberta-v3-large) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.5297
+- Accuracy: 0.9135
+- Weighted precision: 0.9135
+- Weighted recall: 0.9135
+- Weighted f1: 0.9134
+- Macro precision: 0.9135
+- Macro recall: 0.9128
+- Macro f1: 0.9131
+
+## 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: 3
+- eval_batch_size: 3
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 3
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | Weighted precision | Weighted recall | Weighted f1 | Macro precision | Macro recall | Macro f1 |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:------------------:|:---------------:|:-----------:|:---------------:|:------------:|:--------:|
+| 0.4826        | 1.0   | 1896 | 0.4286          | 0.9020   | 0.9020             | 0.9020          | 0.9019      | 0.9018          | 0.9014       | 0.9016   |
+| 0.3429        | 2.0   | 3792 | 0.4274          | 0.9077   | 0.9091             | 0.9077          | 0.9078      | 0.9076          | 0.9089       | 0.9076   |
+| 0.1299        | 3.0   | 5688 | 0.5297          | 0.9135   | 0.9135             | 0.9135          | 0.9134      | 0.9135          | 0.9128       | 0.9131   |
+
+
+### Framework versions
+
+- Transformers 4.38.2
+- Pytorch 2.1.0+cu121
+- Datasets 2.18.0
+- Tokenizers 0.15.2

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[MASK]": 128000
+}

config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "microsoft/deberta-v3-large",
+  "architectures": [
+    "DebertaV2ForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "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": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "pooler_dropout": 0,
+  "pooler_hidden_act": "gelu",
+  "pooler_hidden_size": 1024,
+  "pos_att_type": [
+    "p2c",
+    "c2p"
+  ],
+  "position_biased_input": false,
+  "position_buckets": 256,
+  "relative_attention": true,
+  "share_att_key": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.2",
+  "type_vocab_size": 0,
+  "vocab_size": 128100
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71af1d5118c887cc4c96588e14da3df9f02b0ee2d30dd5565a269b2bd675ddb4
+size 1740304440

runs/Mar05_02-49-57_a9253d894a9f/events.out.tfevents.1709606998.a9253d894a9f.695.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2d33e60c7cf7cb874acab1e4a4b455961dad51e1f6666f2372f49409d480542
+size 9045

runs/Mar05_03-10-27_a9253d894a9f/events.out.tfevents.1709608228.a9253d894a9f.6510.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10eb4155dfaedeaf6dc69fc0feace6da5c1b41c24c4db2850c254e8bd6b5312c
+size 9399

runs/Mar05_03-31-17_a9253d894a9f/events.out.tfevents.1709609478.a9253d894a9f.11767.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:465a0f408c40c5a8db7868510e9d2b1928a67abdcf0c8179dea356aa5bc9b7ae
+size 12208

runs/Mar05_04-06-14_a9253d894a9f/events.out.tfevents.1709611575.a9253d894a9f.20454.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4da20244c7fe04a2f32a6c279748eec22fc2899ccc7d3300313747d9f62a421e
+size 17915

runs/Mar05_05-08-59_a9253d894a9f/events.out.tfevents.1709615340.a9253d894a9f.36168.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d88a7cdb30751b236a33b196d95112eaff757700053ed48ac75ed2b11f20a3e
+size 9399

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

spm.model

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

tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128000": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "[CLS]",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "sp_model_kwargs": {},
+  "split_by_punct": false,
+  "tokenizer_class": "DebertaV2Tokenizer",
+  "unk_token": "[UNK]",
+  "vocab_type": "spm"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb776d62c12a76067ffa7d0a1c158f788c4b429a9c3f61132dfafc341ebce3ff
+size 4920