Saving best model of DeBERT_50K_steps to hub

README.md

@@ -0,0 +1,87 @@
+---
+license: mit
+base_model: microsoft/deberta-v3-base
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- precision
+- recall
+- f1
+model-index:
+- name: DeBERT_50K_steps
+  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. -->
+
+# DeBERT_50K_steps
+
+This model is a fine-tuned version of [microsoft/deberta-v3-base](https://huggingface.co/microsoft/deberta-v3-base) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0169
+- Accuracy: 0.9941
+- Precision: 0.7649
+- Recall: 0.5670
+- F1: 0.6512
+- Hamming: 0.0059
+
+## 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
+- lr_scheduler_warmup_ratio: 0.1
+- training_steps: 50000
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss | Accuracy | Precision | Recall | F1     | Hamming |
+|:-------------:|:-----:|:-----:|:---------------:|:--------:|:---------:|:------:|:------:|:-------:|
+| 0.2014        | 0.02  | 2500  | 0.0451          | 0.9902   | 0.0       | 0.0    | 0.0    | 0.0098  |
+| 0.0373        | 0.04  | 5000  | 0.0297          | 0.9913   | 0.6879    | 0.2003 | 0.3102 | 0.0087  |
+| 0.0286        | 0.06  | 7500  | 0.0250          | 0.9921   | 0.6965    | 0.3329 | 0.4505 | 0.0079  |
+| 0.0253        | 0.08  | 10000 | 0.0233          | 0.9925   | 0.7038    | 0.4010 | 0.5109 | 0.0075  |
+| 0.0234        | 0.1   | 12500 | 0.0217          | 0.9928   | 0.7085    | 0.4382 | 0.5415 | 0.0072  |
+| 0.0223        | 0.12  | 15000 | 0.0208          | 0.9930   | 0.7229    | 0.4559 | 0.5591 | 0.0070  |
+| 0.0213        | 0.14  | 17500 | 0.0205          | 0.9931   | 0.7255    | 0.4696 | 0.5701 | 0.0069  |
+| 0.0206        | 0.16  | 20000 | 0.0196          | 0.9933   | 0.7325    | 0.4990 | 0.5936 | 0.0067  |
+| 0.0203        | 0.18  | 22500 | 0.0191          | 0.9935   | 0.7368    | 0.5125 | 0.6045 | 0.0065  |
+| 0.0196        | 0.2   | 25000 | 0.0188          | 0.9935   | 0.7354    | 0.5209 | 0.6098 | 0.0065  |
+| 0.0195        | 0.22  | 27500 | 0.0185          | 0.9936   | 0.7415    | 0.5335 | 0.6205 | 0.0064  |
+| 0.019         | 0.24  | 30000 | 0.0183          | 0.9936   | 0.7437    | 0.5296 | 0.6186 | 0.0064  |
+| 0.0189        | 0.26  | 32500 | 0.0180          | 0.9938   | 0.7585    | 0.5304 | 0.6243 | 0.0062  |
+| 0.0187        | 0.28  | 35000 | 0.0178          | 0.9938   | 0.7630    | 0.5342 | 0.6284 | 0.0062  |
+| 0.0184        | 0.3   | 37500 | 0.0175          | 0.9939   | 0.7626    | 0.5457 | 0.6362 | 0.0061  |
+| 0.0182        | 0.32  | 40000 | 0.0174          | 0.9939   | 0.7621    | 0.5451 | 0.6356 | 0.0061  |
+| 0.0179        | 0.34  | 42500 | 0.0172          | 0.9940   | 0.7594    | 0.5563 | 0.6422 | 0.0060  |
+| 0.0178        | 0.36  | 45000 | 0.0171          | 0.9940   | 0.7553    | 0.5633 | 0.6453 | 0.0060  |
+| 0.0177        | 0.38  | 47500 | 0.0170          | 0.9941   | 0.7623    | 0.5680 | 0.6510 | 0.0059  |
+| 0.0175        | 0.4   | 50000 | 0.0169          | 0.9941   | 0.7649    | 0.5670 | 0.6512 | 0.0059  |
+
+
+### Framework versions
+
+- Transformers 4.35.0.dev0
+- Pytorch 2.0.1+cu118
+- Datasets 2.7.1
+- Tokenizers 0.14.1

added_tokens.json

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

all_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 0.4,
+    "train_loss": 0.030178942489624022,
+    "train_runtime": 76019.1937,
+    "train_samples_per_second": 10.524,
+    "train_steps_per_second": 0.658
+}

config.json

@@ -0,0 +1,370 @@
+{
+  "_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,
+  "id2label": {
+    "0": "adap-org",
+    "1": "alg-geom",
+    "2": "astro-ph",
+    "3": "astro-ph.CO",
+    "4": "astro-ph.EP",
+    "5": "astro-ph.GA",
+    "6": "astro-ph.HE",
+    "7": "astro-ph.IM",
+    "8": "astro-ph.SR",
+    "9": "atom-ph",
+    "10": "chao-dyn",
+    "11": "chem-ph",
+    "12": "cmp-lg",
+    "13": "comp-gas",
+    "14": "cond-mat",
+    "15": "cond-mat.dis-nn",
+    "16": "cond-mat.mes-hall",
+    "17": "cond-mat.mtrl-sci",
+    "18": "cond-mat.other",
+    "19": "cond-mat.quant-gas",
+    "20": "cond-mat.soft",
+    "21": "cond-mat.stat-mech",
+    "22": "cond-mat.str-el",
+    "23": "cond-mat.supr-con",
+    "24": "cs.AI",
+    "25": "cs.AR",
+    "26": "cs.CC",
+    "27": "cs.CE",
+    "28": "cs.CG",
+    "29": "cs.CL",
+    "30": "cs.CR",
+    "31": "cs.CV",
+    "32": "cs.CY",
+    "33": "cs.DB",
+    "34": "cs.DC",
+    "35": "cs.DL",
+    "36": "cs.DM",
+    "37": "cs.DS",
+    "38": "cs.ET",
+    "39": "cs.FL",
+    "40": "cs.GL",
+    "41": "cs.GR",
+    "42": "cs.GT",
+    "43": "cs.HC",
+    "44": "cs.IR",
+    "45": "cs.LG",
+    "46": "cs.LO",
+    "47": "cs.MA",
+    "48": "cs.MM",
+    "49": "cs.MS",
+    "50": "cs.NA",
+    "51": "cs.NE",
+    "52": "cs.NI",
+    "53": "cs.OH",
+    "54": "cs.OS",
+    "55": "cs.PF",
+    "56": "cs.PL",
+    "57": "cs.RO",
+    "58": "cs.SC",
+    "59": "cs.SD",
+    "60": "cs.SE",
+    "61": "cs.SI",
+    "62": "cs.SY",
+    "63": "dg-ga",
+    "64": "econ.EM",
+    "65": "econ.GN",
+    "66": "econ.TH",
+    "67": "eess.AS",
+    "68": "eess.IV",
+    "69": "eess.SP",
+    "70": "eess.SY",
+    "71": "funct-an",
+    "72": "gr-qc",
+    "73": "hep-ex",
+    "74": "hep-lat",
+    "75": "hep-ph",
+    "76": "hep-th",
+    "77": "math.AC",
+    "78": "math.AG",
+    "79": "math.AP",
+    "80": "math.AT",
+    "81": "math.CA",
+    "82": "math.CO",
+    "83": "math.CT",
+    "84": "math.CV",
+    "85": "math.DG",
+    "86": "math.DS",
+    "87": "math.FA",
+    "88": "math.GM",
+    "89": "math.GN",
+    "90": "math.GR",
+    "91": "math.GT",
+    "92": "math.HO",
+    "93": "math.KT",
+    "94": "math.LO",
+    "95": "math.MG",
+    "96": "math.NA",
+    "97": "math.NT",
+    "98": "math.OA",
+    "99": "math.OC",
+    "100": "math.PR",
+    "101": "math.QA",
+    "102": "math.RA",
+    "103": "math.RT",
+    "104": "math.SG",
+    "105": "math.SP",
+    "106": "mtrl-th",
+    "107": "nlin.AO",
+    "108": "nlin.CD",
+    "109": "nlin.CG",
+    "110": "nlin.PS",
+    "111": "nlin.SI",
+    "112": "nucl-ex",
+    "113": "nucl-th",
+    "114": "patt-sol",
+    "115": "physics.acc-ph",
+    "116": "physics.ao-ph",
+    "117": "physics.app-ph",
+    "118": "physics.atm-clus",
+    "119": "physics.atom-ph",
+    "120": "physics.bio-ph",
+    "121": "physics.chem-ph",
+    "122": "physics.class-ph",
+    "123": "physics.comp-ph",
+    "124": "physics.data-an",
+    "125": "physics.ed-ph",
+    "126": "physics.flu-dyn",
+    "127": "physics.gen-ph",
+    "128": "physics.geo-ph",
+    "129": "physics.hist-ph",
+    "130": "physics.ins-det",
+    "131": "physics.med-ph",
+    "132": "physics.optics",
+    "133": "physics.plasm-ph",
+    "134": "physics.pop-ph",
+    "135": "physics.soc-ph",
+    "136": "physics.space-ph",
+    "137": "q-alg",
+    "138": "q-bio.BM",
+    "139": "q-bio.CB",
+    "140": "q-bio.GN",
+    "141": "q-bio.MN",
+    "142": "q-bio.NC",
+    "143": "q-bio.OT",
+    "144": "q-bio.PE",
+    "145": "q-bio.QM",
+    "146": "q-bio.SC",
+    "147": "q-bio.TO",
+    "148": "q-fin.CP",
+    "149": "q-fin.EC",
+    "150": "q-fin.GN",
+    "151": "q-fin.MF",
+    "152": "q-fin.PM",
+    "153": "q-fin.PR",
+    "154": "q-fin.RM",
+    "155": "q-fin.ST",
+    "156": "q-fin.TR",
+    "157": "quant-ph",
+    "158": "solv-int",
+    "159": "stat.AP",
+    "160": "stat.CO",
+    "161": "stat.ME",
+    "162": "stat.ML",
+    "163": "stat.OT",
+    "164": "supr-con"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "adap-org": 0,
+    "alg-geom": 1,
+    "astro-ph": 2,
+    "astro-ph.CO": 3,
+    "astro-ph.EP": 4,
+    "astro-ph.GA": 5,
+    "astro-ph.HE": 6,
+    "astro-ph.IM": 7,
+    "astro-ph.SR": 8,
+    "atom-ph": 9,
+    "chao-dyn": 10,
+    "chem-ph": 11,
+    "cmp-lg": 12,
+    "comp-gas": 13,
+    "cond-mat": 14,
+    "cond-mat.dis-nn": 15,
+    "cond-mat.mes-hall": 16,
+    "cond-mat.mtrl-sci": 17,
+    "cond-mat.other": 18,
+    "cond-mat.quant-gas": 19,
+    "cond-mat.soft": 20,
+    "cond-mat.stat-mech": 21,
+    "cond-mat.str-el": 22,
+    "cond-mat.supr-con": 23,
+    "cs.AI": 24,
+    "cs.AR": 25,
+    "cs.CC": 26,
+    "cs.CE": 27,
+    "cs.CG": 28,
+    "cs.CL": 29,
+    "cs.CR": 30,
+    "cs.CV": 31,
+    "cs.CY": 32,
+    "cs.DB": 33,
+    "cs.DC": 34,
+    "cs.DL": 35,
+    "cs.DM": 36,
+    "cs.DS": 37,
+    "cs.ET": 38,
+    "cs.FL": 39,
+    "cs.GL": 40,
+    "cs.GR": 41,
+    "cs.GT": 42,
+    "cs.HC": 43,
+    "cs.IR": 44,
+    "cs.LG": 45,
+    "cs.LO": 46,
+    "cs.MA": 47,
+    "cs.MM": 48,
+    "cs.MS": 49,
+    "cs.NA": 50,
+    "cs.NE": 51,
+    "cs.NI": 52,
+    "cs.OH": 53,
+    "cs.OS": 54,
+    "cs.PF": 55,
+    "cs.PL": 56,
+    "cs.RO": 57,
+    "cs.SC": 58,
+    "cs.SD": 59,
+    "cs.SE": 60,
+    "cs.SI": 61,
+    "cs.SY": 62,
+    "dg-ga": 63,
+    "econ.EM": 64,
+    "econ.GN": 65,
+    "econ.TH": 66,
+    "eess.AS": 67,
+    "eess.IV": 68,
+    "eess.SP": 69,
+    "eess.SY": 70,
+    "funct-an": 71,
+    "gr-qc": 72,
+    "hep-ex": 73,
+    "hep-lat": 74,
+    "hep-ph": 75,
+    "hep-th": 76,
+    "math.AC": 77,
+    "math.AG": 78,
+    "math.AP": 79,
+    "math.AT": 80,
+    "math.CA": 81,
+    "math.CO": 82,
+    "math.CT": 83,
+    "math.CV": 84,
+    "math.DG": 85,
+    "math.DS": 86,
+    "math.FA": 87,
+    "math.GM": 88,
+    "math.GN": 89,
+    "math.GR": 90,
+    "math.GT": 91,
+    "math.HO": 92,
+    "math.KT": 93,
+    "math.LO": 94,
+    "math.MG": 95,
+    "math.NA": 96,
+    "math.NT": 97,
+    "math.OA": 98,
+    "math.OC": 99,
+    "math.PR": 100,
+    "math.QA": 101,
+    "math.RA": 102,
+    "math.RT": 103,
+    "math.SG": 104,
+    "math.SP": 105,
+    "mtrl-th": 106,
+    "nlin.AO": 107,
+    "nlin.CD": 108,
+    "nlin.CG": 109,
+    "nlin.PS": 110,
+    "nlin.SI": 111,
+    "nucl-ex": 112,
+    "nucl-th": 113,
+    "patt-sol": 114,
+    "physics.acc-ph": 115,
+    "physics.ao-ph": 116,
+    "physics.app-ph": 117,
+    "physics.atm-clus": 118,
+    "physics.atom-ph": 119,
+    "physics.bio-ph": 120,
+    "physics.chem-ph": 121,
+    "physics.class-ph": 122,
+    "physics.comp-ph": 123,
+    "physics.data-an": 124,
+    "physics.ed-ph": 125,
+    "physics.flu-dyn": 126,
+    "physics.gen-ph": 127,
+    "physics.geo-ph": 128,
+    "physics.hist-ph": 129,
+    "physics.ins-det": 130,
+    "physics.med-ph": 131,
+    "physics.optics": 132,
+    "physics.plasm-ph": 133,
+    "physics.pop-ph": 134,
+    "physics.soc-ph": 135,
+    "physics.space-ph": 136,
+    "q-alg": 137,
+    "q-bio.BM": 138,
+    "q-bio.CB": 139,
+    "q-bio.GN": 140,
+    "q-bio.MN": 141,
+    "q-bio.NC": 142,
+    "q-bio.OT": 143,
+    "q-bio.PE": 144,
+    "q-bio.QM": 145,
+    "q-bio.SC": 146,
+    "q-bio.TO": 147,
+    "q-fin.CP": 148,
+    "q-fin.EC": 149,
+    "q-fin.GN": 150,
+    "q-fin.MF": 151,
+    "q-fin.PM": 152,
+    "q-fin.PR": 153,
+    "q-fin.RM": 154,
+    "q-fin.ST": 155,
+    "q-fin.TR": 156,
+    "quant-ph": 157,
+    "solv-int": 158,
+    "stat.AP": 159,
+    "stat.CO": 160,
+    "stat.ME": 161,
+    "stat.ML": 162,
+    "stat.OT": 163,
+    "supr-con": 164
+  },
+  "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,
+  "problem_type": "multi_label_classification",
+  "relative_attention": true,
+  "share_att_key": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.0.dev0",
+  "type_vocab_size": 0,
+  "vocab_size": 128100
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5093518ea902693cc4e13cb156b03813a9be733b1f60a099786aeaa490827c62
+size 738265717

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"
+}

train_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 0.4,
+    "train_loss": 0.030178942489624022,
+    "train_runtime": 76019.1937,
+    "train_samples_per_second": 10.524,
+    "train_steps_per_second": 0.658
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:097f22deb737cb0ef2d1d8a83ef78af6e067bb18f68cf867f30cb5c51f2007e6
+size 4091