End of training

README.md

@@ -0,0 +1,74 @@
+---
+base_model: allenai/scibert_scivocab_uncased
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- f1
+- precision
+- recall
+model-index:
+- name: uniBERT.SciBERT.3
+ 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. -->
+
+# uniBERT.SciBERT.3
+
+This model is a fine-tuned version of [allenai/scibert_scivocab_uncased](https://huggingface.co/allenai/scibert_scivocab_uncased) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.4561
+- Accuracy: (0.6702412868632708,)
+- F1: (0.6657502111957233,)
+- Precision: (0.6734478583674295,)
+- Recall: 0.6702
+
+## 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: 64
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 10
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
+|:-------------:|:-----:|:----:|:---------------:|:---------------------:|:---------------------:|:---------------------:|:------:|
+| 2.3677 | 1.0 | 210 | 1.9707 | (0.4075067024128686,) | (0.4090192400845535,) | (0.547509709321153,) | 0.4075 |
+| 1.5004 | 2.0 | 420 | 1.5800 | (0.5040214477211796,) | (0.5054715276021063,) | (0.5609302049861328,) | 0.5040 |
+| 1.1293 | 3.0 | 630 | 1.4399 | (0.5978552278820375,) | (0.5952450222746305,) | (0.626189358268289,) | 0.5979 |
+| 0.7653 | 4.0 | 840 | 1.3531 | (0.613941018766756,) | (0.6131261450333483,) | (0.6327420067968214,) | 0.6139 |
+| 0.5953 | 5.0 | 1050 | 1.3496 | (0.6273458445040214,) | (0.6242006045463042,) | (0.6387356344263772,) | 0.6273 |
+| 0.4295 | 6.0 | 1260 | 1.4336 | (0.6407506702412868,) | (0.6336787424282196,) | (0.6518816492980041,) | 0.6408 |
+| 0.28 | 7.0 | 1470 | 1.4272 | (0.6407506702412868,) | (0.63679869732329,) | (0.6493551584566409,) | 0.6408 |
+| 0.2789 | 8.0 | 1680 | 1.4619 | (0.6514745308310992,) | (0.6469674646912128,) | (0.6567012350489139,) | 0.6515 |
+| 0.1723 | 9.0 | 1890 | 1.4713 | (0.6514745308310992,) | (0.6473277862770819,) | (0.6561545316552414,) | 0.6515 |
+| 0.1383 | 10.0 | 2100 | 1.4561 | (0.6702412868632708,) | (0.6657502111957233,) | (0.6734478583674295,) | 0.6702 |
+
+
+### Framework versions
+
+- Transformers 4.39.3
+- Pytorch 2.2.1+cu121
+- Datasets 2.18.0
+- Tokenizers 0.15.2

config.json

@@ -0,0 +1,147 @@
+{
+ "_name_or_path": "allenai/scibert_scivocab_uncased",
+ "architectures": [
+ "BertForTokenClassification"
+ ],
+ "attention_probs_dropout_prob": 0.1,
+ "classifier_dropout": null,
+ "hidden_act": "gelu",
+ "hidden_dropout_prob": 0.1,
+ "hidden_size": 768,
+ "id2label": {
+ "0": "O",
+ "1": "B-1",
+ "2": "I-1",
+ "3": "B-2",
+ "4": "I-2",
+ "5": "B-3",
+ "6": "I-3",
+ "7": "B-4",
+ "8": "I-4",
+ "9": "B-5",
+ "10": "I-5",
+ "11": "B-6",
+ "12": "I-6",
+ "13": "B-7",
+ "14": "I-7",
+ "15": "B-8",
+ "16": "I-8",
+ "17": "B-9",
+ "18": "I-9",
+ "19": "B-10",
+ "20": "I-10",
+ "21": "B-11",
+ "22": "I-11",
+ "23": "B-12",
+ "24": "I-12",
+ "25": "B-13",
+ "26": "I-13",
+ "27": "B-14",
+ "28": "I-14",
+ "29": "B-15",
+ "30": "I-15",
+ "31": "B-16",
+ "32": "I-16",
+ "33": "B-17",
+ "34": "I-17",
+ "35": "B-18",
+ "36": "I-18",
+ "37": "B-19",
+ "38": "I-19",
+ "39": "B-20",
+ "40": "I-20",
+ "41": "B-21",
+ "42": "I-21",
+ "43": "B-22",
+ "44": "I-22",
+ "45": "B-23",
+ "46": "I-23",
+ "47": "B-24",
+ "48": "I-24",
+ "49": "B-25",
+ "50": "I-25",
+ "51": "B-26",
+ "52": "I-26",
+ "53": "B-27",
+ "54": "I-27",
+ "55": "B-28",
+ "56": "I-28",
+ "57": "B-29",
+ "58": "I-29"
+ },
+ "initializer_range": 0.02,
+ "intermediate_size": 3072,
+ "label2id": {
+ "B-1": 1,
+ "B-10": 19,
+ "B-11": 21,
+ "B-12": 23,
+ "B-13": 25,
+ "B-14": 27,
+ "B-15": 29,
+ "B-16": 31,
+ "B-17": 33,
+ "B-18": 35,
+ "B-19": 37,
+ "B-2": 3,
+ "B-20": 39,
+ "B-21": 41,
+ "B-22": 43,
+ "B-23": 45,
+ "B-24": 47,
+ "B-25": 49,
+ "B-26": 51,
+ "B-27": 53,
+ "B-28": 55,
+ "B-29": 57,
+ "B-3": 5,
+ "B-4": 7,
+ "B-5": 9,
+ "B-6": 11,
+ "B-7": 13,
+ "B-8": 15,
+ "B-9": 17,
+ "I-1": 2,
+ "I-10": 20,
+ "I-11": 22,
+ "I-12": 24,
+ "I-13": 26,
+ "I-14": 28,
+ "I-15": 30,
+ "I-16": 32,
+ "I-17": 34,
+ "I-18": 36,
+ "I-19": 38,
+ "I-2": 4,
+ "I-20": 40,
+ "I-21": 42,
+ "I-22": 44,
+ "I-23": 46,
+ "I-24": 48,
+ "I-25": 50,
+ "I-26": 52,
+ "I-27": 54,
+ "I-28": 56,
+ "I-29": 58,
+ "I-3": 6,
+ "I-4": 8,
+ "I-5": 10,
+ "I-6": 12,
+ "I-7": 14,
+ "I-8": 16,
+ "I-9": 18,
+ "O": 0
+ },
+ "layer_norm_eps": 1e-12,
+ "max_position_embeddings": 512,
+ "model_type": "bert",
+ "num_attention_heads": 12,
+ "num_hidden_layers": 12,
+ "pad_token_id": 0,
+ "position_embedding_type": "absolute",
+ "torch_dtype": "float32",
+ "transformers_version": "4.39.3",
+ "type_vocab_size": 2,
+ "use_cache": true,
+ "vocab_size": 31090
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6bf02d5a88e06f54457423c3d4b535ab52d69f4f61e8743d8faecad0e405e29c
+size 437516316

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+ "cls_token": "[CLS]",
+ "mask_token": "[MASK]",
+ "pad_token": "[PAD]",
+ "sep_token": "[SEP]",
+ "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+ "added_tokens_decoder": {
+ "0": {
+ "content": "[PAD]",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "101": {
+ "content": "[UNK]",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "102": {
+ "content": "[CLS]",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "103": {
+ "content": "[SEP]",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "104": {
+ "content": "[MASK]",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ }
+ },
+ "clean_up_tokenization_spaces": true,
+ "cls_token": "[CLS]",
+ "do_basic_tokenize": true,
+ "do_lower_case": true,
+ "mask_token": "[MASK]",
+ "model_max_length": 1000000000000000019884624838656,
+ "never_split": null,
+ "pad_token": "[PAD]",
+ "sep_token": "[SEP]",
+ "strip_accents": null,
+ "tokenize_chinese_chars": true,
+ "tokenizer_class": "BertTokenizer",
+ "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fda96d955c6bb0281b04d5106a4e561ae31740e112f94d79605d4898d24f1c9f
+size 4856