End of training

README.md

@@ -0,0 +1,77 @@
+---
+license: mit
+base_model: microsoft/deberta-v3-base
+tags:
+- generated_from_trainer
+datasets:
+- generator
+metrics:
+- accuracy
+model-index:
+- name: deberta-v3-base-finetuned-mnli
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: generator
+      type: generator
+      config: default
+      split: train
+      args: default
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.9165876777251185
+---
+
+<!-- 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-base-finetuned-mnli
+
+This model is a fine-tuned version of [microsoft/deberta-v3-base](https://huggingface.co/microsoft/deberta-v3-base) on the generator dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.4279
+- Accuracy: 0.9166
+
+## 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: 3
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 0.0003        | 1.0   | 374  | 0.6553          | 0.9137   |
+| 0.1791        | 2.0   | 748  | 0.4279          | 0.9166   |
+| 0.1101        | 3.0   | 1122 | 0.5088          | 0.9081   |
+
+
+### Framework versions
+
+- Transformers 4.40.2
+- Pytorch 2.2.1+cu121
+- Datasets 2.19.1
+- Tokenizers 0.19.1

added_tokens.json

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

config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "microsoft/deberta-v3-base",
+  "architectures": [
+    "DebertaV2ForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "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": 12,
+  "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": "4.40.2",
+  "type_vocab_size": 0,
+  "vocab_size": 128100
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc2505233d776e40ef1e1e52e3439f36bafcd1daaa92cea417c4452c34977bfc
+size 737719272

runs/May19_20-57-27_6046ebdb2d40/events.out.tfevents.1716152254.6046ebdb2d40.431.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14fa9c655bfa22bea23d213ed6b3d405baac8a848f2b208e2326cb1200c37ef0
+size 6046

runs/May19_21-40-39_6046ebdb2d40/events.out.tfevents.1716156950.6046ebdb2d40.7443.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:364dd8db8588bf012d53a30c654da194c51ce629e3c321cb9dab59c06ce3b1ec
+size 8631

runs/May19_22-19-45_6046ebdb2d40/events.out.tfevents.1716157192.6046ebdb2d40.7443.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1045a4a2abe4ce322817bda96f339c5adb4a8bcb4014bbb69bfc1615efb629b5
+size 8631

runs/May19_22-19-45_6046ebdb2d40/events.out.tfevents.1716158757.6046ebdb2d40.7443.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4f1122d85fe12a4efed2db1566e5fa5427d2e23728f8b01eec7bc2300ad19c9
+size 8631

runs/May19_22-49-49_6046ebdb2d40/events.out.tfevents.1716159009.6046ebdb2d40.7443.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:814471f1f7331bb368dd63863460467a8e6bcb196e3771d21d0b7376cc934434
+size 8631

runs/May19_22-49-49_6046ebdb2d40/events.out.tfevents.1716159240.6046ebdb2d40.7443.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:acebc8a1520bb768773565c19b0c847e66648e1c582a4903f45a286241d85299
+size 13640

runs/May19_22-49-49_6046ebdb2d40/events.out.tfevents.1716159459.6046ebdb2d40.7443.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e40da6f11ad58295acad1081a014571a3fcbe1ff1956f4b3830a28b88fad1b7
+size 411

runs/May19_23-15-23_6046ebdb2d40/events.out.tfevents.1716160542.6046ebdb2d40.7443.6

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:114ce5eeea6f5a482f8e9609bfc626b5d5ccf3dee56b345ef375657e1c37577a
+size 18067

runs/May19_23-15-23_6046ebdb2d40/events.out.tfevents.1716160924.6046ebdb2d40.7443.7

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fb8a4b720495f91fde7fdbd8edf052bb517395891fca5a6e5f2c7ef653122d4
+size 411

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 sha256:44a6dcbe55e107f9f90b33f0b703c2c601868f4027ac9e7b3674dfdf152b6295
+size 5048