End of training

README.md

@@ -0,0 +1,67 @@
+---
+library_name: transformers
+license: mit
+base_model: microsoft/BiomedNLP-BiomedBERT-base-uncased-abstract
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: arxiv_model
+  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. -->
+
+# arxiv_model
+
+This model is a fine-tuned version of [microsoft/BiomedNLP-BiomedBERT-base-uncased-abstract](https://huggingface.co/microsoft/BiomedNLP-BiomedBERT-base-uncased-abstract) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.3191
+- Accuracy: 0.4606
+
+## 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: 0.0003
+- train_batch_size: 16
+- eval_batch_size: 16
+- seed: 42
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 128
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- num_epochs: 5
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | Accuracy |
+|:-------------:|:------:|:----:|:---------------:|:--------:|
+| 2.2414        | 1.0    | 1468 | 2.5282          | 0.3647   |
+| 1.8278        | 2.0    | 2936 | 2.1141          | 0.4429   |
+| 1.45          | 3.0    | 4404 | 2.1294          | 0.4538   |
+| 1.0671        | 4.0    | 5872 | 2.2140          | 0.4576   |
+| 0.7401        | 4.9968 | 7335 | 2.3191          | 0.4606   |
+
+
+### Framework versions
+
+- Transformers 4.50.3
+- Pytorch 2.6.0+cu124
+- Datasets 3.5.0
+- Tokenizers 0.21.1

config.json

@@ -0,0 +1,333 @@
+{
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "nlin.PS",
+    "1": "stat.OT",
+    "2": "physics.ins-det",
+    "3": "gr-qc",
+    "4": "hep-ex",
+    "5": "math.KT",
+    "6": "q-fin.MF",
+    "7": "math.HO",
+    "8": "astro-ph.HE",
+    "9": "q-bio.BM",
+    "10": "cs.OH",
+    "11": "math.RT",
+    "12": "math.RA",
+    "13": "physics.bio-ph",
+    "14": "econ.TH",
+    "15": "math.DS",
+    "16": "math.GM",
+    "17": "econ.GN",
+    "18": "cs.CR",
+    "19": "math.AC",
+    "20": "cs.HC",
+    "21": "physics.plasm-ph",
+    "22": "q-bio.QM",
+    "23": "math.QA",
+    "24": "physics.flu-dyn",
+    "25": "astro-ph.SR",
+    "26": "math.NA",
+    "27": "cs.CL",
+    "28": "cs.IT",
+    "29": "cs.CC",
+    "30": "cs.DM",
+    "31": "quant-ph",
+    "32": "cs.SC",
+    "33": "cs.SI",
+    "34": "cs.GR",
+    "35": "cs.RO",
+    "36": "cond-mat.str-el",
+    "37": "cs.CE",
+    "38": "math.LO",
+    "39": "cs.GL",
+    "40": "math.GT",
+    "41": "astro-ph.GA",
+    "42": "math.GN",
+    "43": "q-fin.CP",
+    "44": "math.AG",
+    "45": "q-fin.ST",
+    "46": "physics.chem-ph",
+    "47": "cs.NI",
+    "48": "physics.geo-ph",
+    "49": "eess.SP",
+    "50": "math.CV",
+    "51": "math.DG",
+    "52": "cs.OS",
+    "53": "cs.PL",
+    "54": "hep-ph",
+    "55": "physics.ed-ph",
+    "56": "cond-mat.stat-mech",
+    "57": "q-bio.PE",
+    "58": "cond-mat.mtrl-sci",
+    "59": "math.FA",
+    "60": "physics.app-ph",
+    "61": "q-bio.GN",
+    "62": "cs.SD",
+    "63": "q-fin.PR",
+    "64": "stat.AP",
+    "65": "math.SP",
+    "66": "cond-mat.soft",
+    "67": "physics.data-an",
+    "68": "nlin.SI",
+    "69": "physics.comp-ph",
+    "70": "cs.DS",
+    "71": "physics.ao-ph",
+    "72": "math.OA",
+    "73": "nlin.CD",
+    "74": "cs.AR",
+    "75": "physics.gen-ph",
+    "76": "math.CO",
+    "77": "nlin.AO",
+    "78": "cs.CG",
+    "79": "cs.PF",
+    "80": "math.AP",
+    "81": "q-fin.TR",
+    "82": "cs.LO",
+    "83": "hep-th",
+    "84": "cs.MM",
+    "85": "cond-mat.quant-gas",
+    "86": "physics.atm-clus",
+    "87": "stat.ME",
+    "88": "astro-ph.CO",
+    "89": "math-ph",
+    "90": "physics.pop-ph",
+    "91": "eess.SY",
+    "92": "cs.MA",
+    "93": "nucl-th",
+    "94": "math.OC",
+    "95": "cs.SY",
+    "96": "math.MG",
+    "97": "physics.med-ph",
+    "98": "q-fin.GN",
+    "99": "cs.CY",
+    "100": "cs.IR",
+    "101": "physics.acc-ph",
+    "102": "cs.NE",
+    "103": "physics.hist-ph",
+    "104": "astro-ph.EP",
+    "105": "stat.ML",
+    "106": "math.AT",
+    "107": "econ.EM",
+    "108": "math.NT",
+    "109": "q-bio.CB",
+    "110": "q-bio.TO",
+    "111": "q-bio.MN",
+    "112": "math.SG",
+    "113": "nlin.CG",
+    "114": "cond-mat.dis-nn",
+    "115": "stat.CO",
+    "116": "nucl-ex",
+    "117": "math.GR",
+    "118": "cs.NA",
+    "119": "cond-mat.supr-con",
+    "120": "physics.soc-ph",
+    "121": "q-fin.EC",
+    "122": "q-bio.SC",
+    "123": "cs.DL",
+    "124": "q-bio.OT",
+    "125": "q-fin.RM",
+    "126": "hep-lat",
+    "127": "cs.LG",
+    "128": "cs.DC",
+    "129": "cs.AI",
+    "130": "cs.GT",
+    "131": "physics.class-ph",
+    "132": "physics.space-ph",
+    "133": "q-fin.PM",
+    "134": "math.CA",
+    "135": "math.CT",
+    "136": "eess.AS",
+    "137": "cs.MS",
+    "138": "math.PR",
+    "139": "astro-ph.IM",
+    "140": "q-bio.NC",
+    "141": "cs.ET",
+    "142": "cond-mat.other",
+    "143": "math.ST",
+    "144": "cs.SE",
+    "145": "cond-mat.mes-hall",
+    "146": "physics.optics",
+    "147": "cs.DB",
+    "148": "cs.FL",
+    "149": "eess.IV",
+    "150": "physics.atom-ph",
+    "151": "cs.CV"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "astro-ph.CO": 88,
+    "astro-ph.EP": 104,
+    "astro-ph.GA": 41,
+    "astro-ph.HE": 8,
+    "astro-ph.IM": 139,
+    "astro-ph.SR": 25,
+    "cond-mat.dis-nn": 114,
+    "cond-mat.mes-hall": 145,
+    "cond-mat.mtrl-sci": 58,
+    "cond-mat.other": 142,
+    "cond-mat.quant-gas": 85,
+    "cond-mat.soft": 66,
+    "cond-mat.stat-mech": 56,
+    "cond-mat.str-el": 36,
+    "cond-mat.supr-con": 119,
+    "cs.AI": 129,
+    "cs.AR": 74,
+    "cs.CC": 29,
+    "cs.CE": 37,
+    "cs.CG": 78,
+    "cs.CL": 27,
+    "cs.CR": 18,
+    "cs.CV": 151,
+    "cs.CY": 99,
+    "cs.DB": 147,
+    "cs.DC": 128,
+    "cs.DL": 123,
+    "cs.DM": 30,
+    "cs.DS": 70,
+    "cs.ET": 141,
+    "cs.FL": 148,
+    "cs.GL": 39,
+    "cs.GR": 34,
+    "cs.GT": 130,
+    "cs.HC": 20,
+    "cs.IR": 100,
+    "cs.IT": 28,
+    "cs.LG": 127,
+    "cs.LO": 82,
+    "cs.MA": 92,
+    "cs.MM": 84,
+    "cs.MS": 137,
+    "cs.NA": 118,
+    "cs.NE": 102,
+    "cs.NI": 47,
+    "cs.OH": 10,
+    "cs.OS": 52,
+    "cs.PF": 79,
+    "cs.PL": 53,
+    "cs.RO": 35,
+    "cs.SC": 32,
+    "cs.SD": 62,
+    "cs.SE": 144,
+    "cs.SI": 33,
+    "cs.SY": 95,
+    "econ.EM": 107,
+    "econ.GN": 17,
+    "econ.TH": 14,
+    "eess.AS": 136,
+    "eess.IV": 149,
+    "eess.SP": 49,
+    "eess.SY": 91,
+    "gr-qc": 3,
+    "hep-ex": 4,
+    "hep-lat": 126,
+    "hep-ph": 54,
+    "hep-th": 83,
+    "math-ph": 89,
+    "math.AC": 19,
+    "math.AG": 44,
+    "math.AP": 80,
+    "math.AT": 106,
+    "math.CA": 134,
+    "math.CO": 76,
+    "math.CT": 135,
+    "math.CV": 50,
+    "math.DG": 51,
+    "math.DS": 15,
+    "math.FA": 59,
+    "math.GM": 16,
+    "math.GN": 42,
+    "math.GR": 117,
+    "math.GT": 40,
+    "math.HO": 7,
+    "math.KT": 5,
+    "math.LO": 38,
+    "math.MG": 96,
+    "math.NA": 26,
+    "math.NT": 108,
+    "math.OA": 72,
+    "math.OC": 94,
+    "math.PR": 138,
+    "math.QA": 23,
+    "math.RA": 12,
+    "math.RT": 11,
+    "math.SG": 112,
+    "math.SP": 65,
+    "math.ST": 143,
+    "nlin.AO": 77,
+    "nlin.CD": 73,
+    "nlin.CG": 113,
+    "nlin.PS": 0,
+    "nlin.SI": 68,
+    "nucl-ex": 116,
+    "nucl-th": 93,
+    "physics.acc-ph": 101,
+    "physics.ao-ph": 71,
+    "physics.app-ph": 60,
+    "physics.atm-clus": 86,
+    "physics.atom-ph": 150,
+    "physics.bio-ph": 13,
+    "physics.chem-ph": 46,
+    "physics.class-ph": 131,
+    "physics.comp-ph": 69,
+    "physics.data-an": 67,
+    "physics.ed-ph": 55,
+    "physics.flu-dyn": 24,
+    "physics.gen-ph": 75,
+    "physics.geo-ph": 48,
+    "physics.hist-ph": 103,
+    "physics.ins-det": 2,
+    "physics.med-ph": 97,
+    "physics.optics": 146,
+    "physics.plasm-ph": 21,
+    "physics.pop-ph": 90,
+    "physics.soc-ph": 120,
+    "physics.space-ph": 132,
+    "q-bio.BM": 9,
+    "q-bio.CB": 109,
+    "q-bio.GN": 61,
+    "q-bio.MN": 111,
+    "q-bio.NC": 140,
+    "q-bio.OT": 124,
+    "q-bio.PE": 57,
+    "q-bio.QM": 22,
+    "q-bio.SC": 122,
+    "q-bio.TO": 110,
+    "q-fin.CP": 43,
+    "q-fin.EC": 121,
+    "q-fin.GN": 98,
+    "q-fin.MF": 6,
+    "q-fin.PM": 133,
+    "q-fin.PR": 63,
+    "q-fin.RM": 125,
+    "q-fin.ST": 45,
+    "q-fin.TR": 81,
+    "quant-ph": 31,
+    "stat.AP": 64,
+    "stat.CO": 115,
+    "stat.ME": 87,
+    "stat.ML": 105,
+    "stat.OT": 1
+  },
+  "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",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.50.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd8f578371299d7cc8d1fd0734e7b380ab6035ad0bcd9462a3f11e95973fa611
+size 438420048

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 +1,58 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "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,
+  "extra_special_tokens": {},
+  "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 sha256:1e918705eab3dc4a2921f13abd96299207fd37ba7bb5590528e7ca4755dd0b85
+size 5304