bert-cased

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,80 @@
+---
+license: mit
+base_model: timpal0l/mdeberta-v3-base-squad2
+tags:
+- generated_from_trainer
+datasets:
+- covid_qa_deepset
+model-index:
+- name: bert-covidqa-5
+  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. -->
+
+# bert-covidqa-5
+
+This model is a fine-tuned version of [timpal0l/mdeberta-v3-base-squad2](https://huggingface.co/timpal0l/mdeberta-v3-base-squad2) on the covid_qa_deepset dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.4190
+
+## 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: 3e-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: 1
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 0.5956        | 0.04  | 5    | 0.4016          |
+| 0.3741        | 0.09  | 10   | 0.3879          |
+| 0.3405        | 0.13  | 15   | 0.4240          |
+| 0.4372        | 0.18  | 20   | 0.4102          |
+| 0.2592        | 0.22  | 25   | 0.4534          |
+| 0.3534        | 0.26  | 30   | 0.4571          |
+| 0.4268        | 0.31  | 35   | 0.4107          |
+| 0.2663        | 0.35  | 40   | 0.4166          |
+| 0.143         | 0.39  | 45   | 0.4345          |
+| 0.2494        | 0.44  | 50   | 0.5575          |
+| 0.8953        | 0.48  | 55   | 0.6172          |
+| 0.5504        | 0.53  | 60   | 0.4879          |
+| 0.6411        | 0.57  | 65   | 0.3718          |
+| 0.5454        | 0.61  | 70   | 0.3929          |
+| 0.4441        | 0.66  | 75   | 0.3641          |
+| 0.2922        | 0.7   | 80   | 0.3638          |
+| 0.491         | 0.75  | 85   | 0.3785          |
+| 0.4362        | 0.79  | 90   | 0.3938          |
+| 0.1633        | 0.83  | 95   | 0.4162          |
+| 0.6762        | 0.88  | 100  | 0.4321          |
+| 0.3111        | 0.92  | 105  | 0.4241          |
+| 0.3453        | 0.96  | 110  | 0.4190          |
+
+
+### Framework versions
+
+- Transformers 4.34.1
+- Pytorch 2.1.0+cu118
+- Datasets 2.14.5
+- Tokenizers 0.14.1

config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "timpal0l/mdeberta-v3-base-squad2",
+  "architectures": [
+    "DebertaV2ForQuestionAnswering"
+  ],
+  "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": "4.34.1",
+  "type_vocab_size": 0,
+  "vocab_size": 251000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:216e6d7211caf13ed3c4d54199a735fc9fa3c4136ae180c76b1e950ab00b01d9
+size 1112950570

special_tokens_map.json

@@ -0,0 +1,9 @@
+{
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:338f230099c23cd536b4eb1823cfa31ea6108bf4fe506afbc3ee075b7e998dee
+size 16316344

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": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250101": {
+      "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:c0171f032b4fc763d7dbfd3facfaaf7e48fd930bf34dea4464685104d8c18d27
+size 4536