Initial checkin

config.json

@@ -0,0 +1,110 @@
+{
+  "_name_or_path": "microsoft/deberta-base",
+  "architectures": [
+    "DebertaForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "O",
+    "1": "B-PERSON",
+    "2": "I-PERSON",
+    "3": "B-NORP",
+    "4": "I-NORP",
+    "5": "B-FAC",
+    "6": "I-FAC",
+    "7": "B-ORG",
+    "8": "I-ORG",
+    "9": "B-GPE",
+    "10": "I-GPE",
+    "11": "B-LOC",
+    "12": "I-LOC",
+    "13": "B-PRODUCT",
+    "14": "I-PRODUCT",
+    "15": "B-DATE",
+    "16": "I-DATE",
+    "17": "B-TIME",
+    "18": "I-TIME",
+    "19": "B-PERCENT",
+    "20": "I-PERCENT",
+    "21": "B-MONEY",
+    "22": "I-MONEY",
+    "23": "B-QUANTITY",
+    "24": "I-QUANTITY",
+    "25": "B-ORDINAL",
+    "26": "I-ORDINAL",
+    "27": "B-CARDINAL",
+    "28": "I-CARDINAL",
+    "29": "B-EVENT",
+    "30": "I-EVENT",
+    "31": "B-WORK_OF_ART",
+    "32": "I-WORK_OF_ART",
+    "33": "B-LAW",
+    "34": "I-LAW",
+    "35": "B-LANGUAGE",
+    "36": "I-LANGUAGE"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-CARDINAL": 27,
+    "B-DATE": 15,
+    "B-EVENT": 29,
+    "B-FAC": 5,
+    "B-GPE": 9,
+    "B-LANGUAGE": 35,
+    "B-LAW": 33,
+    "B-LOC": 11,
+    "B-MONEY": 21,
+    "B-NORP": 3,
+    "B-ORDINAL": 25,
+    "B-ORG": 7,
+    "B-PERCENT": 19,
+    "B-PERSON": 1,
+    "B-PRODUCT": 13,
+    "B-QUANTITY": 23,
+    "B-TIME": 17,
+    "B-WORK_OF_ART": 31,
+    "I-CARDINAL": 28,
+    "I-DATE": 16,
+    "I-EVENT": 30,
+    "I-FAC": 6,
+    "I-GPE": 10,
+    "I-LANGUAGE": 36,
+    "I-LAW": 34,
+    "I-LOC": 12,
+    "I-MONEY": 22,
+    "I-NORP": 4,
+    "I-ORDINAL": 26,
+    "I-ORG": 8,
+    "I-PERCENT": 20,
+    "I-PERSON": 2,
+    "I-PRODUCT": 14,
+    "I-QUANTITY": 24,
+    "I-TIME": 18,
+    "I-WORK_OF_ART": 32,
+    "O": 0
+  },
+  "layer_norm_eps": 1e-07,
+  "max_position_embeddings": 512,
+  "max_relative_positions": -1,
+  "model_type": "deberta",
+  "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": [
+    "c2p",
+    "p2c"
+  ],
+  "position_biased_input": false,
+  "relative_attention": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.23.0",
+  "type_vocab_size": 0,
+  "vocab_size": 50265
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ab235be6d875536f6ea6ae372fba48ce781e67a30607363bd1501128f17dbb8
+size 554591539

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6de13a5bb5071790a9af50795884d2fba4140bf5f6c5b1bcb0dc7e0b2c0347f4
+size 14503

run.log

@@ -0,0 +1,512 @@
+2022-11-16 17:06:48,577 - __main__ - INFO - Label List:['O', 'B-PERSON', 'I-PERSON', 'B-NORP', 'I-NORP', 'B-FAC', 'I-FAC', 'B-ORG', 'I-ORG', 'B-GPE', 'I-GPE', 'B-LOC', 'I-LOC', 'B-PRODUCT', 'I-PRODUCT', 'B-DATE', 'I-DATE', 'B-TIME', 'I-TIME', 'B-PERCENT', 'I-PERCENT', 'B-MONEY', 'I-MONEY', 'B-QUANTITY', 'I-QUANTITY', 'B-ORDINAL', 'I-ORDINAL', 'B-CARDINAL', 'I-CARDINAL', 'B-EVENT', 'I-EVENT', 'B-WORK_OF_ART', 'I-WORK_OF_ART', 'B-LAW', 'I-LAW', 'B-LANGUAGE', 'I-LANGUAGE']
+2022-11-16 17:06:55,367 - __main__ - INFO - Dataset({
+    features: ['id', 'words', 'ner_tags'],
+    num_rows: 75187
+})
+2022-11-16 17:06:56,175 - __main__ - INFO - Dataset({
+    features: ['id', 'words', 'ner_tags'],
+    num_rows: 9479
+})
+2022-11-16 17:06:56,185 - transformers.tokenization_utils_base - INFO - loading file vocab.json
+2022-11-16 17:06:56,185 - transformers.tokenization_utils_base - INFO - loading file merges.txt
+2022-11-16 17:06:56,185 - transformers.tokenization_utils_base - INFO - loading file tokenizer.json
+2022-11-16 17:06:56,185 - transformers.tokenization_utils_base - INFO - loading file added_tokens.json
+2022-11-16 17:06:56,185 - transformers.tokenization_utils_base - INFO - loading file special_tokens_map.json
+2022-11-16 17:06:56,185 - transformers.tokenization_utils_base - INFO - loading file tokenizer_config.json
+2022-11-16 17:06:56,250 - __main__ - INFO - {'input_ids': [[1, 653, 761, 9, 3783, 17487, 2, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0], [1, 166, 32928, 9603, 47, 7, 1183, 10, 780, 5403, 9, 15581, 436, 479, 2, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0], [1, 15584, 3082, 3192, 23959, 15, 5, 2860, 3875, 9, 436, 4832, 41876, 38628, 9, 15643, 24610, 4743, 2, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0], [1, 15125, 6764, 15, 15643, 24610, 4743, 16, 5, 23001, 7, 5, 41184, 6304, 25132, 23909, 479, 2, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0], [1, 85, 16, 14092, 9, 10, 2270, 11235, 459, 2156, 5929, 1690, 523, 293, 2156, 10, 1307, 1062, 18185, 8, 30943, 9368, 2156, 8, 5, 2860, 2298, 2156, 566, 97, 383, 479, 2]], 'token_type_ids': [[0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0], [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0], [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0], [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0], [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]], 'attention_mask': [[1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0], [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0], [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0], [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0], [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]]}
+2022-11-16 17:06:56,251 - __main__ - INFO - ['[CLS]', 'ĠWhat', 'Ġkind', 'Ġof', 'Ġmemory', 'Ġ?', '[SEP]', '[PAD]', '[PAD]', '[PAD]', '[PAD]', '[PAD]', '[PAD]', '[PAD]', '[PAD]', '[PAD]', '[PAD]', '[PAD]', '[PAD]', '[PAD]', '[PAD]', '[PAD]', '[PAD]', '[PAD]', '[PAD]', '[PAD]', '[PAD]', '[PAD]', '[PAD]', '[PAD]', '[PAD]', '[PAD]', '[PAD]']
+2022-11-16 17:06:56,251 - __main__ - INFO - ['[CLS]', 'ĠWe', 'Ġrespectfully', 'Ġinvite', 'Ġyou', 'Ġto', 'Ġwatch', 'Ġa', 'Ġspecial', 'Ġedition', 'Ġof', 'ĠAcross', 'ĠChina', 'Ġ.', '[SEP]', '[PAD]', '[PAD]', '[PAD]', '[PAD]', '[PAD]', '[PAD]', '[PAD]', '[PAD]', '[PAD]', '[PAD]', '[PAD]', '[PAD]', '[PAD]', '[PAD]', '[PAD]', '[PAD]', '[PAD]', '[PAD]']
+2022-11-16 17:06:56,251 - __main__ - INFO - ['[CLS]', 'ĠWW', 'ĠII', 'ĠLand', 'marks', 'Ġon', 'Ġthe', 'ĠGreat', 'ĠEarth', 'Ġof', 'ĠChina', 'Ġ:', 'ĠEternal', 'ĠMemories', 'Ġof', 'ĠTai', 'hang', 'ĠMountain', '[SEP]', '[PAD]', '[PAD]', '[PAD]', '[PAD]', '[PAD]', '[PAD]', '[PAD]', '[PAD]', '[PAD]', '[PAD]', '[PAD]', '[PAD]', '[PAD]', '[PAD]']
+2022-11-16 17:06:56,251 - __main__ - INFO - ['[CLS]', 'ĠStanding', 'Ġtall', 'Ġon', 'ĠTai', 'hang', 'ĠMountain', 'Ġis', 'Ġthe', 'ĠMonument', 'Ġto', 'Ġthe', 'ĠHundred', 'ĠReg', 'iments', 'ĠOffensive', 'Ġ.', '[SEP]', '[PAD]', '[PAD]', '[PAD]', '[PAD]', '[PAD]', '[PAD]', '[PAD]', '[PAD]', '[PAD]', '[PAD]', '[PAD]', '[PAD]', '[PAD]', '[PAD]', '[PAD]']
+2022-11-16 17:06:56,252 - __main__ - INFO - ['[CLS]', 'ĠIt', 'Ġis', 'Ġcomposed', 'Ġof', 'Ġa', 'Ġprimary', 'Ġste', 'le', 'Ġ,', 'Ġsecondary', 'Ġst', 'el', 'es', 'Ġ,', 'Ġa', 'Ġhuge', 'Ġround', 'Ġsculpture', 'Ġand', 'Ġbeacon', 'Ġtower', 'Ġ,', 'Ġand', 'Ġthe', 'ĠGreat', 'ĠWall', 'Ġ,', 'Ġamong', 'Ġother', 'Ġthings', 'Ġ.', '[SEP]']
+2022-11-16 17:06:56,252 - __main__ - INFO - -------------
+2022-11-16 17:06:56,252 - __main__ - INFO - ['[CLS]', 'ĠWe', 'Ġrespectfully', 'Ġinvite', 'Ġyou', 'Ġto', 'Ġwatch', 'Ġa', 'Ġspecial', 'Ġedition', 'Ġof', 'ĠAcross', 'ĠChina', 'Ġ.', '[SEP]', '[PAD]', '[PAD]', '[PAD]', '[PAD]', '[PAD]', '[PAD]', '[PAD]', '[PAD]', '[PAD]', '[PAD]', '[PAD]', '[PAD]', '[PAD]', '[PAD]', '[PAD]', '[PAD]', '[PAD]', '[PAD]']
+2022-11-16 17:06:56,252 - __main__ - INFO - [None, 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None]
+2022-11-16 17:07:05,682 - __main__ - INFO - {'id': [0, 1, 2, 3, 4], 'words': [['What', 'kind', 'of', 'memory', '?'], ['We', 'respectfully', 'invite', 'you', 'to', 'watch', 'a', 'special', 'edition', 'of', 'Across', 'China', '.'], ['WW', 'II', 'Landmarks', 'on', 'the', 'Great', 'Earth', 'of', 'China', ':', 'Eternal', 'Memories', 'of', 'Taihang', 'Mountain'], ['Standing', 'tall', 'on', 'Taihang', 'Mountain', 'is', 'the', 'Monument', 'to', 'the', 'Hundred', 'Regiments', 'Offensive', '.'], ['It', 'is', 'composed', 'of', 'a', 'primary', 'stele', ',', 'secondary', 'steles', ',', 'a', 'huge', 'round', 'sculpture', 'and', 'beacon', 'tower', ',', 'and', 'the', 'Great', 'Wall', ',', 'among', 'other', 'things', '.']], 'ner_tags': [[0, 0, 0, 0, 0], [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 7, 8, 0], [31, 32, 32, 32, 32, 32, 32, 32, 32, 32, 32, 32, 32, 32, 32], [0, 0, 0, 11, 12, 0, 31, 32, 32, 32, 32, 32, 32, 0], [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 31, 32, 32, 0, 0, 0, 0, 0]], 'input_ids': [[1, 653, 761, 9, 3783, 17487, 2], [1, 166, 32928, 9603, 47, 7, 1183, 10, 780, 5403, 9, 15581, 436, 479, 2], [1, 15584, 3082, 3192, 23959, 15, 5, 2860, 3875, 9, 436, 4832, 41876, 38628, 9, 15643, 24610, 4743, 2], [1, 15125, 6764, 15, 15643, 24610, 4743, 16, 5, 23001, 7, 5, 41184, 6304, 25132, 23909, 479, 2], [1, 85, 16, 14092, 9, 10, 2270, 11235, 459, 2156, 5929, 1690, 523, 293, 2156, 10, 1307, 1062, 18185, 8, 30943, 9368, 2156, 8, 5, 2860, 2298, 2156, 566, 97, 383, 479, 2]], 'token_type_ids': [[0, 0, 0, 0, 0, 0, 0], [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0], [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0], [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0], [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]], 'attention_mask': [[1, 1, 1, 1, 1, 1, 1], [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1], [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1], [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1], [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]], 'labels': [[-100, 0, 0, 0, 0, 0, -100], [-100, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 7, 8, 0, -100], [-100, 31, 32, 32, -100, 32, 32, 32, 32, 32, 32, 32, 32, 32, 32, 32, -100, 32, -100], [-100, 0, 0, 0, 11, -100, 12, 0, 31, 32, 32, 32, 32, 32, -100, 32, 0, -100], [-100, 0, 0, 0, 0, 0, 0, 0, -100, 0, 0, 0, -100, -100, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 31, 32, 32, 0, 0, 0, 0, 0, -100]]}
+2022-11-16 17:07:06,902 - transformers.configuration_utils - INFO - loading configuration file /content/NER-System/models/microsoft/deberta-base_1668615764.565312/checkpoint-14100/config.json
+2022-11-16 17:07:06,904 - transformers.configuration_utils - INFO - Model config DebertaConfig {
+  "_name_or_path": "/content/NER-System/models/microsoft/deberta-base_1668615764.565312/checkpoint-14100",
+  "architectures": [
+    "DebertaForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "O",
+    "1": "B-PERSON",
+    "2": "I-PERSON",
+    "3": "B-NORP",
+    "4": "I-NORP",
+    "5": "B-FAC",
+    "6": "I-FAC",
+    "7": "B-ORG",
+    "8": "I-ORG",
+    "9": "B-GPE",
+    "10": "I-GPE",
+    "11": "B-LOC",
+    "12": "I-LOC",
+    "13": "B-PRODUCT",
+    "14": "I-PRODUCT",
+    "15": "B-DATE",
+    "16": "I-DATE",
+    "17": "B-TIME",
+    "18": "I-TIME",
+    "19": "B-PERCENT",
+    "20": "I-PERCENT",
+    "21": "B-MONEY",
+    "22": "I-MONEY",
+    "23": "B-QUANTITY",
+    "24": "I-QUANTITY",
+    "25": "B-ORDINAL",
+    "26": "I-ORDINAL",
+    "27": "B-CARDINAL",
+    "28": "I-CARDINAL",
+    "29": "B-EVENT",
+    "30": "I-EVENT",
+    "31": "B-WORK_OF_ART",
+    "32": "I-WORK_OF_ART",
+    "33": "B-LAW",
+    "34": "I-LAW",
+    "35": "B-LANGUAGE",
+    "36": "I-LANGUAGE"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-CARDINAL": 27,
+    "B-DATE": 15,
+    "B-EVENT": 29,
+    "B-FAC": 5,
+    "B-GPE": 9,
+    "B-LANGUAGE": 35,
+    "B-LAW": 33,
+    "B-LOC": 11,
+    "B-MONEY": 21,
+    "B-NORP": 3,
+    "B-ORDINAL": 25,
+    "B-ORG": 7,
+    "B-PERCENT": 19,
+    "B-PERSON": 1,
+    "B-PRODUCT": 13,
+    "B-QUANTITY": 23,
+    "B-TIME": 17,
+    "B-WORK_OF_ART": 31,
+    "I-CARDINAL": 28,
+    "I-DATE": 16,
+    "I-EVENT": 30,
+    "I-FAC": 6,
+    "I-GPE": 10,
+    "I-LANGUAGE": 36,
+    "I-LAW": 34,
+    "I-LOC": 12,
+    "I-MONEY": 22,
+    "I-NORP": 4,
+    "I-ORDINAL": 26,
+    "I-ORG": 8,
+    "I-PERCENT": 20,
+    "I-PERSON": 2,
+    "I-PRODUCT": 14,
+    "I-QUANTITY": 24,
+    "I-TIME": 18,
+    "I-WORK_OF_ART": 32,
+    "O": 0
+  },
+  "layer_norm_eps": 1e-07,
+  "max_position_embeddings": 512,
+  "max_relative_positions": -1,
+  "model_type": "deberta",
+  "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": [
+    "c2p",
+    "p2c"
+  ],
+  "position_biased_input": false,
+  "relative_attention": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.23.0",
+  "type_vocab_size": 0,
+  "vocab_size": 50265
+}
+
+2022-11-16 17:07:06,933 - transformers.modeling_utils - INFO - loading weights file /content/NER-System/models/microsoft/deberta-base_1668615764.565312/checkpoint-14100/pytorch_model.bin
+2022-11-16 17:07:08,422 - transformers.modeling_utils - INFO - All model checkpoint weights were used when initializing DebertaForTokenClassification.
+
+2022-11-16 17:07:08,422 - transformers.modeling_utils - INFO - All the weights of DebertaForTokenClassification were initialized from the model checkpoint at /content/NER-System/models/microsoft/deberta-base_1668615764.565312/checkpoint-14100.
+If your task is similar to the task the model of the checkpoint was trained on, you can already use DebertaForTokenClassification for predictions without further training.
+2022-11-16 17:07:08,500 - __main__ - INFO - DebertaForTokenClassification(
+  (deberta): DebertaModel(
+    (embeddings): DebertaEmbeddings(
+      (word_embeddings): Embedding(50265, 768, padding_idx=0)
+      (LayerNorm): DebertaLayerNorm()
+      (dropout): StableDropout()
+    )
+    (encoder): DebertaEncoder(
+      (layer): ModuleList(
+        (0): DebertaLayer(
+          (attention): DebertaAttention(
+            (self): DisentangledSelfAttention(
+              (in_proj): Linear(in_features=768, out_features=2304, bias=False)
+              (pos_dropout): StableDropout()
+              (pos_proj): Linear(in_features=768, out_features=768, bias=False)
+              (pos_q_proj): Linear(in_features=768, out_features=768, bias=True)
+              (dropout): StableDropout()
+            )
+            (output): DebertaSelfOutput(
+              (dense): Linear(in_features=768, out_features=768, bias=True)
+              (LayerNorm): DebertaLayerNorm()
+              (dropout): StableDropout()
+            )
+          )
+          (intermediate): DebertaIntermediate(
+            (dense): Linear(in_features=768, out_features=3072, bias=True)
+            (intermediate_act_fn): GELUActivation()
+          )
+          (output): DebertaOutput(
+            (dense): Linear(in_features=3072, out_features=768, bias=True)
+            (LayerNorm): DebertaLayerNorm()
+            (dropout): StableDropout()
+          )
+        )
+        (1): DebertaLayer(
+          (attention): DebertaAttention(
+            (self): DisentangledSelfAttention(
+              (in_proj): Linear(in_features=768, out_features=2304, bias=False)
+              (pos_dropout): StableDropout()
+              (pos_proj): Linear(in_features=768, out_features=768, bias=False)
+              (pos_q_proj): Linear(in_features=768, out_features=768, bias=True)
+              (dropout): StableDropout()
+            )
+            (output): DebertaSelfOutput(
+              (dense): Linear(in_features=768, out_features=768, bias=True)
+              (LayerNorm): DebertaLayerNorm()
+              (dropout): StableDropout()
+            )
+          )
+          (intermediate): DebertaIntermediate(
+            (dense): Linear(in_features=768, out_features=3072, bias=True)
+            (intermediate_act_fn): GELUActivation()
+          )
+          (output): DebertaOutput(
+            (dense): Linear(in_features=3072, out_features=768, bias=True)
+            (LayerNorm): DebertaLayerNorm()
+            (dropout): StableDropout()
+          )
+        )
+        (2): DebertaLayer(
+          (attention): DebertaAttention(
+            (self): DisentangledSelfAttention(
+              (in_proj): Linear(in_features=768, out_features=2304, bias=False)
+              (pos_dropout): StableDropout()
+              (pos_proj): Linear(in_features=768, out_features=768, bias=False)
+              (pos_q_proj): Linear(in_features=768, out_features=768, bias=True)
+              (dropout): StableDropout()
+            )
+            (output): DebertaSelfOutput(
+              (dense): Linear(in_features=768, out_features=768, bias=True)
+              (LayerNorm): DebertaLayerNorm()
+              (dropout): StableDropout()
+            )
+          )
+          (intermediate): DebertaIntermediate(
+            (dense): Linear(in_features=768, out_features=3072, bias=True)
+            (intermediate_act_fn): GELUActivation()
+          )
+          (output): DebertaOutput(
+            (dense): Linear(in_features=3072, out_features=768, bias=True)
+            (LayerNorm): DebertaLayerNorm()
+            (dropout): StableDropout()
+          )
+        )
+        (3): DebertaLayer(
+          (attention): DebertaAttention(
+            (self): DisentangledSelfAttention(
+              (in_proj): Linear(in_features=768, out_features=2304, bias=False)
+              (pos_dropout): StableDropout()
+              (pos_proj): Linear(in_features=768, out_features=768, bias=False)
+              (pos_q_proj): Linear(in_features=768, out_features=768, bias=True)
+              (dropout): StableDropout()
+            )
+            (output): DebertaSelfOutput(
+              (dense): Linear(in_features=768, out_features=768, bias=True)
+              (LayerNorm): DebertaLayerNorm()
+              (dropout): StableDropout()
+            )
+          )
+          (intermediate): DebertaIntermediate(
+            (dense): Linear(in_features=768, out_features=3072, bias=True)
+            (intermediate_act_fn): GELUActivation()
+          )
+          (output): DebertaOutput(
+            (dense): Linear(in_features=3072, out_features=768, bias=True)
+            (LayerNorm): DebertaLayerNorm()
+            (dropout): StableDropout()
+          )
+        )
+        (4): DebertaLayer(
+          (attention): DebertaAttention(
+            (self): DisentangledSelfAttention(
+              (in_proj): Linear(in_features=768, out_features=2304, bias=False)
+              (pos_dropout): StableDropout()
+              (pos_proj): Linear(in_features=768, out_features=768, bias=False)
+              (pos_q_proj): Linear(in_features=768, out_features=768, bias=True)
+              (dropout): StableDropout()
+            )
+            (output): DebertaSelfOutput(
+              (dense): Linear(in_features=768, out_features=768, bias=True)
+              (LayerNorm): DebertaLayerNorm()
+              (dropout): StableDropout()
+            )
+          )
+          (intermediate): DebertaIntermediate(
+            (dense): Linear(in_features=768, out_features=3072, bias=True)
+            (intermediate_act_fn): GELUActivation()
+          )
+          (output): DebertaOutput(
+            (dense): Linear(in_features=3072, out_features=768, bias=True)
+            (LayerNorm): DebertaLayerNorm()
+            (dropout): StableDropout()
+          )
+        )
+        (5): DebertaLayer(
+          (attention): DebertaAttention(
+            (self): DisentangledSelfAttention(
+              (in_proj): Linear(in_features=768, out_features=2304, bias=False)
+              (pos_dropout): StableDropout()
+              (pos_proj): Linear(in_features=768, out_features=768, bias=False)
+              (pos_q_proj): Linear(in_features=768, out_features=768, bias=True)
+              (dropout): StableDropout()
+            )
+            (output): DebertaSelfOutput(
+              (dense): Linear(in_features=768, out_features=768, bias=True)
+              (LayerNorm): DebertaLayerNorm()
+              (dropout): StableDropout()
+            )
+          )
+          (intermediate): DebertaIntermediate(
+            (dense): Linear(in_features=768, out_features=3072, bias=True)
+            (intermediate_act_fn): GELUActivation()
+          )
+          (output): DebertaOutput(
+            (dense): Linear(in_features=3072, out_features=768, bias=True)
+            (LayerNorm): DebertaLayerNorm()
+            (dropout): StableDropout()
+          )
+        )
+        (6): DebertaLayer(
+          (attention): DebertaAttention(
+            (self): DisentangledSelfAttention(
+              (in_proj): Linear(in_features=768, out_features=2304, bias=False)
+              (pos_dropout): StableDropout()
+              (pos_proj): Linear(in_features=768, out_features=768, bias=False)
+              (pos_q_proj): Linear(in_features=768, out_features=768, bias=True)
+              (dropout): StableDropout()
+            )
+            (output): DebertaSelfOutput(
+              (dense): Linear(in_features=768, out_features=768, bias=True)
+              (LayerNorm): DebertaLayerNorm()
+              (dropout): StableDropout()
+            )
+          )
+          (intermediate): DebertaIntermediate(
+            (dense): Linear(in_features=768, out_features=3072, bias=True)
+            (intermediate_act_fn): GELUActivation()
+          )
+          (output): DebertaOutput(
+            (dense): Linear(in_features=3072, out_features=768, bias=True)
+            (LayerNorm): DebertaLayerNorm()
+            (dropout): StableDropout()
+          )
+        )
+        (7): DebertaLayer(
+          (attention): DebertaAttention(
+            (self): DisentangledSelfAttention(
+              (in_proj): Linear(in_features=768, out_features=2304, bias=False)
+              (pos_dropout): StableDropout()
+              (pos_proj): Linear(in_features=768, out_features=768, bias=False)
+              (pos_q_proj): Linear(in_features=768, out_features=768, bias=True)
+              (dropout): StableDropout()
+            )
+            (output): DebertaSelfOutput(
+              (dense): Linear(in_features=768, out_features=768, bias=True)
+              (LayerNorm): DebertaLayerNorm()
+              (dropout): StableDropout()
+            )
+          )
+          (intermediate): DebertaIntermediate(
+            (dense): Linear(in_features=768, out_features=3072, bias=True)
+            (intermediate_act_fn): GELUActivation()
+          )
+          (output): DebertaOutput(
+            (dense): Linear(in_features=3072, out_features=768, bias=True)
+            (LayerNorm): DebertaLayerNorm()
+            (dropout): StableDropout()
+          )
+        )
+        (8): DebertaLayer(
+          (attention): DebertaAttention(
+            (self): DisentangledSelfAttention(
+              (in_proj): Linear(in_features=768, out_features=2304, bias=False)
+              (pos_dropout): StableDropout()
+              (pos_proj): Linear(in_features=768, out_features=768, bias=False)
+              (pos_q_proj): Linear(in_features=768, out_features=768, bias=True)
+              (dropout): StableDropout()
+            )
+            (output): DebertaSelfOutput(
+              (dense): Linear(in_features=768, out_features=768, bias=True)
+              (LayerNorm): DebertaLayerNorm()
+              (dropout): StableDropout()
+            )
+          )
+          (intermediate): DebertaIntermediate(
+            (dense): Linear(in_features=768, out_features=3072, bias=True)
+            (intermediate_act_fn): GELUActivation()
+          )
+          (output): DebertaOutput(
+            (dense): Linear(in_features=3072, out_features=768, bias=True)
+            (LayerNorm): DebertaLayerNorm()
+            (dropout): StableDropout()
+          )
+        )
+        (9): DebertaLayer(
+          (attention): DebertaAttention(
+            (self): DisentangledSelfAttention(
+              (in_proj): Linear(in_features=768, out_features=2304, bias=False)
+              (pos_dropout): StableDropout()
+              (pos_proj): Linear(in_features=768, out_features=768, bias=False)
+              (pos_q_proj): Linear(in_features=768, out_features=768, bias=True)
+              (dropout): StableDropout()
+            )
+            (output): DebertaSelfOutput(
+              (dense): Linear(in_features=768, out_features=768, bias=True)
+              (LayerNorm): DebertaLayerNorm()
+              (dropout): StableDropout()
+            )
+          )
+          (intermediate): DebertaIntermediate(
+            (dense): Linear(in_features=768, out_features=3072, bias=True)
+            (intermediate_act_fn): GELUActivation()
+          )
+          (output): DebertaOutput(
+            (dense): Linear(in_features=3072, out_features=768, bias=True)
+            (LayerNorm): DebertaLayerNorm()
+            (dropout): StableDropout()
+          )
+        )
+        (10): DebertaLayer(
+          (attention): DebertaAttention(
+            (self): DisentangledSelfAttention(
+              (in_proj): Linear(in_features=768, out_features=2304, bias=False)
+              (pos_dropout): StableDropout()
+              (pos_proj): Linear(in_features=768, out_features=768, bias=False)
+              (pos_q_proj): Linear(in_features=768, out_features=768, bias=True)
+              (dropout): StableDropout()
+            )
+            (output): DebertaSelfOutput(
+              (dense): Linear(in_features=768, out_features=768, bias=True)
+              (LayerNorm): DebertaLayerNorm()
+              (dropout): StableDropout()
+            )
+          )
+          (intermediate): DebertaIntermediate(
+            (dense): Linear(in_features=768, out_features=3072, bias=True)
+            (intermediate_act_fn): GELUActivation()
+          )
+          (output): DebertaOutput(
+            (dense): Linear(in_features=3072, out_features=768, bias=True)
+            (LayerNorm): DebertaLayerNorm()
+            (dropout): StableDropout()
+          )
+        )
+        (11): DebertaLayer(
+          (attention): DebertaAttention(
+            (self): DisentangledSelfAttention(
+              (in_proj): Linear(in_features=768, out_features=2304, bias=False)
+              (pos_dropout): StableDropout()
+              (pos_proj): Linear(in_features=768, out_features=768, bias=False)
+              (pos_q_proj): Linear(in_features=768, out_features=768, bias=True)
+              (dropout): StableDropout()
+            )
+            (output): DebertaSelfOutput(
+              (dense): Linear(in_features=768, out_features=768, bias=True)
+              (LayerNorm): DebertaLayerNorm()
+              (dropout): StableDropout()
+            )
+          )
+          (intermediate): DebertaIntermediate(
+            (dense): Linear(in_features=768, out_features=3072, bias=True)
+            (intermediate_act_fn): GELUActivation()
+          )
+          (output): DebertaOutput(
+            (dense): Linear(in_features=3072, out_features=768, bias=True)
+            (LayerNorm): DebertaLayerNorm()
+            (dropout): StableDropout()
+          )
+        )
+      )
+      (rel_embeddings): Embedding(1024, 768)
+    )
+  )
+  (dropout): Dropout(p=0.1, inplace=False)
+  (classifier): Linear(in_features=768, out_features=37, bias=True)
+)
+2022-11-16 17:07:08,521 - __main__ - INFO - CONFIGS:{
+    "output_dir": "./eval_test1",
+    "per_device_train_batch_size": 16,
+    "per_device_eval_batch_size": 16,
+    "save_total_limit": 2,
+    "num_train_epochs": 3,
+    "seed": 1,
+    "load_best_model_at_end": true,
+    "evaluation_strategy": "epoch",
+    "save_strategy": "epoch",
+    "learning_rate": 2e-05,
+    "weight_decay": 0.01,
+    "fp16": true,
+    "logging_steps": 469.0
+}
+2022-11-16 17:07:08,522 - transformers.training_args - INFO - PyTorch: setting up devices
+2022-11-16 17:07:08,557 - transformers.training_args - INFO - The default value for the training argument `--report_to` will change in v5 (from all installed integrations to none). In v5, you will need to use `--report_to all` to get the same behavior as now. You should start updating your code and make this info disappear :-).
+2022-11-16 17:07:11,000 - transformers.trainer - INFO - Using cuda_amp half precision backend
+2022-11-16 17:07:11,001 - __main__ - INFO - [[ MODEL EVALUATION ]]
+2022-11-16 17:07:11,001 - transformers.trainer - INFO - The following columns in the evaluation set don't have a corresponding argument in `DebertaForTokenClassification.forward` and have been ignored: words, ner_tags, id. If words, ner_tags, id are not expected by `DebertaForTokenClassification.forward`,  you can safely ignore this message.
+2022-11-16 17:07:11,004 - transformers.trainer - INFO - ***** Running Evaluation *****
+2022-11-16 17:07:11,004 - transformers.trainer - INFO -   Num examples = 9479
+2022-11-16 17:07:11,004 - transformers.trainer - INFO -   Batch size = 16
+2022-11-16 17:07:11,007 - transformers.tokenization_utils_base - WARNING - You're using a DebertaTokenizerFast tokenizer. Please note that with a fast tokenizer, using the `__call__` method is faster than using a method to encode the text followed by a call to the `pad` method to get a padded encoding.
+2022-11-16 17:07:33,916 - __main__ - INFO - {'eval_loss': 0.06115942820906639, 'eval_precision': 0.8953762782973517, 'eval_recall': 0.9100115483699032, 'eval_f1': 0.902634593356243, 'eval_accuracy': 0.9848035428915137, 'eval_runtime': 22.906, 'eval_samples_per_second': 413.822, 'eval_steps_per_second': 25.888, 'step': 0}
+2022-11-16 17:07:33,916 - transformers.trainer - INFO - The following columns in the test set don't have a corresponding argument in `DebertaForTokenClassification.forward` and have been ignored: words, ner_tags, id. If words, ner_tags, id are not expected by `DebertaForTokenClassification.forward`,  you can safely ignore this message.
+2022-11-16 17:07:33,918 - transformers.trainer - INFO - ***** Running Prediction *****
+2022-11-16 17:07:33,918 - transformers.trainer - INFO -   Num examples = 9479
+2022-11-16 17:07:33,918 - transformers.trainer - INFO -   Batch size = 16
+2022-11-16 17:07:59,630 - __main__ - INFO -               precision    recall  f1-score   support
+
+    CARDINAL       0.86      0.87      0.86       935
+        DATE       0.85      0.89      0.87      1602
+       EVENT       0.65      0.78      0.71        63
+         FAC       0.74      0.80      0.77       135
+         GPE       0.97      0.96      0.96      2240
+    LANGUAGE       0.83      0.68      0.75        22
+         LAW       0.71      0.68      0.69        40
+         LOC       0.74      0.77      0.76       179
+       MONEY       0.88      0.90      0.89       314
+        NORP       0.94      0.97      0.95       841
+     ORDINAL       0.79      0.87      0.83       195
+         ORG       0.92      0.92      0.92      1795
+     PERCENT       0.92      0.92      0.92       349
+      PERSON       0.95      0.95      0.95      1988
+     PRODUCT       0.65      0.76      0.70        76
+    QUANTITY       0.77      0.82      0.80       105
+        TIME       0.62      0.65      0.63       212
+ WORK_OF_ART       0.64      0.69      0.66       166
+
+   micro avg       0.90      0.91      0.90     11257
+   macro avg       0.80      0.83      0.81     11257
+weighted avg       0.90      0.91      0.90     11257
+

scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1de1151bb371c7a9fcf0cdf747ea19c1e78511e69dbbc399a1e42e08562f77d2
+size 559

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31f8c1b6927b129b6987f9b4f5bfb276f770a427eb2d042836118c5cfe4e18a9
+size 623

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,67 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": true,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "__type": "AddedToken",
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "do_lower_case": false,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "errors": "replace",
+  "mask_token": {
+    "__type": "AddedToken",
+    "content": "[MASK]",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 512,
+  "name_or_path": "microsoft/deberta-base",
+  "pad_token": {
+    "__type": "AddedToken",
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "__type": "AddedToken",
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "special_tokens_map_file": null,
+  "tokenizer_class": "DebertaTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "vocab_type": "gpt2"
+}

trainer_state.json

@@ -0,0 +1,232 @@
+{
+  "best_metric": 0.05693262815475464,
+  "best_model_checkpoint": "./models/microsoft/deberta-base_1668615764.565312/checkpoint-9400",
+  "epoch": 3.0,
+  "global_step": 14100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.9341843971631205e-05,
+      "loss": 0.2396,
+      "step": 469
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.8676595744680853e-05,
+      "loss": 0.0934,
+      "step": 938
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.8011347517730498e-05,
+      "loss": 0.076,
+      "step": 1407
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.7346099290780143e-05,
+      "loss": 0.0742,
+      "step": 1876
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.6680851063829788e-05,
+      "loss": 0.0697,
+      "step": 2345
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 1.6015602836879433e-05,
+      "loss": 0.0612,
+      "step": 2814
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 1.5350354609929078e-05,
+      "loss": 0.0645,
+      "step": 3283
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 1.4685106382978724e-05,
+      "loss": 0.0558,
+      "step": 3752
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 1.401985815602837e-05,
+      "loss": 0.0559,
+      "step": 4221
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 1.3354609929078016e-05,
+      "loss": 0.0533,
+      "step": 4690
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9835180063569192,
+      "eval_f1": 0.8845294916144851,
+      "eval_loss": 0.05832871422171593,
+      "eval_precision": 0.8721934369602763,
+      "eval_recall": 0.8972195078617748,
+      "eval_runtime": 22.9422,
+      "eval_samples_per_second": 413.168,
+      "eval_steps_per_second": 25.848,
+      "step": 4700
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 1.268936170212766e-05,
+      "loss": 0.0432,
+      "step": 5159
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 1.2024113475177306e-05,
+      "loss": 0.0426,
+      "step": 5628
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 1.135886524822695e-05,
+      "loss": 0.0416,
+      "step": 6097
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 1.0693617021276597e-05,
+      "loss": 0.042,
+      "step": 6566
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 1.0028368794326242e-05,
+      "loss": 0.0413,
+      "step": 7035
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 9.363120567375887e-06,
+      "loss": 0.0388,
+      "step": 7504
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 8.697872340425533e-06,
+      "loss": 0.0369,
+      "step": 7973
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 8.032624113475178e-06,
+      "loss": 0.039,
+      "step": 8442
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 7.367375886524823e-06,
+      "loss": 0.036,
+      "step": 8911
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 6.702127659574469e-06,
+      "loss": 0.0397,
+      "step": 9380
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9839366902741495,
+      "eval_f1": 0.8953622417309568,
+      "eval_loss": 0.05693262815475464,
+      "eval_precision": 0.8937771089669824,
+      "eval_recall": 0.8969530070178555,
+      "eval_runtime": 22.8104,
+      "eval_samples_per_second": 415.555,
+      "eval_steps_per_second": 25.997,
+      "step": 9400
+    },
+    {
+      "epoch": 2.1,
+      "learning_rate": 6.036879432624114e-06,
+      "loss": 0.0263,
+      "step": 9849
+    },
+    {
+      "epoch": 2.2,
+      "learning_rate": 5.37163120567376e-06,
+      "loss": 0.0252,
+      "step": 10318
+    },
+    {
+      "epoch": 2.3,
+      "learning_rate": 4.707801418439717e-06,
+      "loss": 0.0254,
+      "step": 10787
+    },
+    {
+      "epoch": 2.39,
+      "learning_rate": 4.042553191489362e-06,
+      "loss": 0.028,
+      "step": 11256
+    },
+    {
+      "epoch": 2.49,
+      "learning_rate": 3.377304964539007e-06,
+      "loss": 0.0256,
+      "step": 11725
+    },
+    {
+      "epoch": 2.59,
+      "learning_rate": 2.7120567375886527e-06,
+      "loss": 0.0242,
+      "step": 12194
+    },
+    {
+      "epoch": 2.69,
+      "learning_rate": 2.046808510638298e-06,
+      "loss": 0.0287,
+      "step": 12663
+    },
+    {
+      "epoch": 2.79,
+      "learning_rate": 1.3815602836879433e-06,
+      "loss": 0.0242,
+      "step": 13132
+    },
+    {
+      "epoch": 2.89,
+      "learning_rate": 7.177304964539007e-07,
+      "loss": 0.025,
+      "step": 13601
+    },
+    {
+      "epoch": 2.99,
+      "learning_rate": 5.248226950354611e-08,
+      "loss": 0.0266,
+      "step": 14070
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9848035428915137,
+      "eval_f1": 0.902634593356243,
+      "eval_loss": 0.06115942820906639,
+      "eval_precision": 0.8953762782973517,
+      "eval_recall": 0.9100115483699032,
+      "eval_runtime": 22.4809,
+      "eval_samples_per_second": 421.647,
+      "eval_steps_per_second": 26.378,
+      "step": 14100
+    }
+  ],
+  "max_steps": 14100,
+  "num_train_epochs": 3,
+  "total_flos": 7109576555415114.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d368503b0706bb556b9151f13917aa8e5a85e45f4a65d7150cd257a0d68c42a
+size 3439