Model save

README.md

@@ -1,3 +1,85 @@
 ---
-license: apache-2.0
+license: mit
+base_model: roberta-base
+tags:
+- generated_from_trainer
+metrics:
+- f1
+- accuracy
+- recall
+model-index:
+- name: study-dictionary-roberta-base
+  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. -->
+
+# study-dictionary-roberta-base
+
+This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0011
+- F1: 1.0
+- Roc Auc: 1.0
+- Accuracy: 1.0
+- Recall: 1.0
+
+## 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: 10
+- eval_batch_size: 10
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 20
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss | F1     | Roc Auc | Accuracy | Recall |
+|:-------------:|:-----:|:-----:|:---------------:|:------:|:-------:|:--------:|:------:|
+| 0.3342        | 1.0   | 778   | 0.1192          | 0.0    | 0.5     | 0.0      | 0.0    |
+| 0.1099        | 2.0   | 1556  | 0.1040          | 0.0    | 0.5     | 0.0      | 0.0    |
+| 0.0892        | 3.0   | 2334  | 0.0465          | 0.6835 | 0.7644  | 0.5479   | 0.5293 |
+| 0.0345        | 4.0   | 3112  | 0.0240          | 0.9147 | 0.9241  | 0.8817   | 0.8485 |
+| 0.025         | 5.0   | 3890  | 0.0152          | 0.9594 | 0.9650  | 0.9493   | 0.9303 |
+| 0.0144        | 6.0   | 4668  | 0.0114          | 0.9735 | 0.9811  | 0.9671   | 0.9625 |
+| 0.0118        | 7.0   | 5446  | 0.0082          | 0.9779 | 0.9848  | 0.9717   | 0.9700 |
+| 0.0081        | 8.0   | 6224  | 0.0057          | 0.9873 | 0.9887  | 0.9839   | 0.9774 |
+| 0.0065        | 9.0   | 7002  | 0.0052          | 0.9839 | 0.9860  | 0.9848   | 0.9720 |
+| 0.0054        | 10.0  | 7780  | 0.0039          | 0.9895 | 0.9904  | 0.9888   | 0.9809 |
+| 0.0041        | 11.0  | 8558  | 0.0030          | 0.9942 | 0.9949  | 0.9925   | 0.9899 |
+| 0.0036        | 12.0  | 9336  | 0.0026          | 0.9936 | 0.9940  | 0.9942   | 0.9881 |
+| 0.0027        | 13.0  | 10114 | 0.0023          | 0.9956 | 0.9964  | 0.9958   | 0.9927 |
+| 0.0023        | 14.0  | 10892 | 0.0018          | 0.9985 | 0.9986  | 0.9972   | 0.9972 |
+| 0.0021        | 15.0  | 11670 | 0.0017          | 0.9985 | 0.9994  | 0.9974   | 0.9988 |
+| 0.0018        | 16.0  | 12448 | 0.0015          | 0.9985 | 0.9992  | 0.9979   | 0.9985 |
+| 0.0014        | 17.0  | 13226 | 0.0012          | 0.9997 | 0.9998  | 0.9994   | 0.9995 |
+| 0.0013        | 18.0  | 14004 | 0.0011          | 1.0    | 1.0     | 1.0      | 1.0    |
+| 0.0012        | 19.0  | 14782 | 0.0010          | 1.0    | 1.0     | 1.0      | 1.0    |
+| 0.0012        | 20.0  | 15560 | 0.0010          | 1.0    | 1.0     | 1.0      | 1.0    |
+
+
+### Framework versions
+
+- Transformers 4.33.2
+- Pytorch 2.0.1+cu118
+- Datasets 2.14.5
+- Tokenizers 0.13.3

config.json

@@ -0,0 +1,122 @@
+{
+  "_name_or_path": "roberta-base",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "NCT02136134",
+    "1": "NCT04181827",
+    "2": "NCT03399799",
+    "3": "NCT04557098",
+    "4": "NCT02252172",
+    "5": "NCT03275285",
+    "6": "NCT04162210",
+    "7": "NCT01554852",
+    "8": "NCT01712789",
+    "9": "NCT02541383",
+    "10": "NCT00551928",
+    "11": "NCT02336815",
+    "12": "NCT03110562",
+    "13": "NCT03548207",
+    "14": "NCT02076009",
+    "15": "NCT02412878",
+    "16": "NCT03180736",
+    "17": "NCT03361748",
+    "18": "NCT03651128",
+    "19": "NCT01660633",
+    "20": "NCT03158688",
+    "21": "NCT01080391",
+    "22": "NCT03525678",
+    "23": "NCT02654132",
+    "24": "NCT02990338",
+    "25": "NCT01564537",
+    "26": "NCT05066646",
+    "27": "NCT01985126",
+    "28": "NCT01734928",
+    "29": "NCT01998971",
+    "30": "NCT02195479",
+    "31": "NCT03151811",
+    "32": "NCT01311687",
+    "33": "NCT02874742",
+    "34": "NCT05083169",
+    "35": "NCT01239797",
+    "36": "NCT01023308",
+    "37": "NCT02963493",
+    "38": "NCT00114101",
+    "39": "NCT03412565",
+    "40": "NCT00430365",
+    "41": "NCT03277105",
+    "42": "NCT00103662",
+    "43": "ISRCTN17354232",
+    "44": "NCT01568866"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "ISRCTN17354232": 43,
+    "NCT00103662": 42,
+    "NCT00114101": 38,
+    "NCT00430365": 40,
+    "NCT00551928": 10,
+    "NCT01023308": 36,
+    "NCT01080391": 21,
+    "NCT01239797": 35,
+    "NCT01311687": 32,
+    "NCT01554852": 7,
+    "NCT01564537": 25,
+    "NCT01568866": 44,
+    "NCT01660633": 19,
+    "NCT01712789": 8,
+    "NCT01734928": 28,
+    "NCT01985126": 27,
+    "NCT01998971": 29,
+    "NCT02076009": 14,
+    "NCT02136134": 0,
+    "NCT02195479": 30,
+    "NCT02252172": 4,
+    "NCT02336815": 11,
+    "NCT02412878": 15,
+    "NCT02541383": 9,
+    "NCT02654132": 23,
+    "NCT02874742": 33,
+    "NCT02963493": 37,
+    "NCT02990338": 24,
+    "NCT03110562": 12,
+    "NCT03151811": 31,
+    "NCT03158688": 20,
+    "NCT03180736": 16,
+    "NCT03275285": 5,
+    "NCT03277105": 41,
+    "NCT03361748": 17,
+    "NCT03399799": 2,
+    "NCT03412565": 39,
+    "NCT03525678": 22,
+    "NCT03548207": 13,
+    "NCT03651128": 18,
+    "NCT04162210": 6,
+    "NCT04181827": 1,
+    "NCT04557098": 3,
+    "NCT05066646": 26,
+    "NCT05083169": 34
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "multi_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.33.2",
+  "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 sha256:3928fbbd9e0ec09587758292d8188fe3e1ea57057790ced14e93446deeb2d5e4
+size 498789297

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,15 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f040529a80aa19814879431b231153b18d44a3714ed291c0dacd8b6bb19d5295
+size 4091