End of training

README.md

@@ -15,16 +15,16 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [ai-forever/ruBert-base](https://huggingface.co/ai-forever/ruBert-base) on the None dataset.
 It achieves the following results on the evaluation set:
-- eval_loss: 0.0021
-- eval_precision: 0.9995
-- eval_recall: 0.9994
-- eval_f1: 0.9995
-- eval_accuracy: 0.9996
-- eval_runtime: 39.8442
-- eval_samples_per_second: 161.705
-- eval_steps_per_second: 2.535
-- epoch: 3.0
-- step: 1059
+- eval_loss: 0.0007
+- eval_precision: 1.0
+- eval_recall: 1.0
+- eval_f1: 1.0
+- eval_accuracy: 1.0
+- eval_runtime: 0.2167
+- eval_samples_per_second: 96.897
+- eval_steps_per_second: 4.614
+- epoch: 2.0
+- step: 738
 
 ## Model description
 
@@ -49,7 +49,7 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 10
+- num_epochs: 5
 
 ### Framework versions
 

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f27c9d39236051dca997c77239ecc8d101cbc3e696637d6fa8421f36f9cf45c
+oid sha256:c9c450c9aa31d86523540290951ad34da0494ca6efccc18e32fcd396930a0719
 size 711062560

runs/Mar15_14-25-12_af6d53f073f1/events.out.tfevents.1710512714.af6d53f073f1.1790.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a64b1c0b5137322eb11a22230bd944e2fdafd5e8cac82668331b888fbb5cec9
+size 7502

runs/Mar15_14-34-51_af6d53f073f1/events.out.tfevents.1710513511.af6d53f073f1.1790.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f11cbf3d2302b95624aa96ad4fbf682510eb786c33c048a37e130ca3d41981f
+size 8657

tmp-checkpoint-738/config.json

@@ -0,0 +1,147 @@
+{
+  "_name_or_path": "ai-forever/ruBert-base",
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "O",
+    "1": "Not",
+    "2": "Abbr",
+    "3": "Adj",
+    "4": "Adv",
+    "5": "Adv/action_des\u0441",
+    "6": "Adv/action_time",
+    "7": "Adv/measure",
+    "8": "Adv/place",
+    "9": "Adv/emph",
+    "10": "Advt",
+    "11": "Advt1",
+    "12": "Aux",
+    "13": "Bracket",
+    "14": "Colon",
+    "15": "Comma",
+    "16": "Conj.comp",
+    "17": "Coord",
+    "18": "Dash",
+    "19": "Dot",
+    "20": "Ellipsis",
+    "21": "Fw",
+    "22": "Interj.",
+    "23": "Interrog.word",
+    "24": "Introduct",
+    "25": "Mark/excl",
+    "26": "Mark/quest",
+    "27": "Measure",
+    "28": "N",
+    "29": "Num",
+    "30": "Num/ordinal",
+    "31": "Part/dem",
+    "32": "Part/excl",
+    "33": "Part/limit",
+    "34": "Part/imp",
+    "35": "Part/intens",
+    "36": "Part/neg",
+    "37": "Part/quest",
+    "38": "Part/soft",
+    "39": "Prep",
+    "40": "Pron",
+    "41": "Pron/attr",
+    "42": "Pron/dem",
+    "43": "Pron/neg",
+    "44": "Pron/pos",
+    "45": "Pron/rel",
+    "46": "Particip/adj",
+    "47": "Particip/v",
+    "48": "Punct",
+    "49": "Quote",
+    "50": "Semicolon",
+    "51": "State",
+    "52": "Sub",
+    "53": "Vf",
+    "54": "Vinf",
+    "55": "Vm"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "Abbr": 2,
+    "Adj": 3,
+    "Adv": 4,
+    "Adv/action_des\u0441": 5,
+    "Adv/action_time": 6,
+    "Adv/emph": 9,
+    "Adv/measure": 7,
+    "Adv/place": 8,
+    "Advt": 10,
+    "Advt1": 11,
+    "Aux": 12,
+    "Bracket": 13,
+    "Colon": 14,
+    "Comma": 15,
+    "Conj.comp": 16,
+    "Coord": 17,
+    "Dash": 18,
+    "Dot": 19,
+    "Ellipsis": 20,
+    "Fw": 21,
+    "Interj.": 22,
+    "Interrog.word": 23,
+    "Introduct": 24,
+    "Mark/excl": 25,
+    "Mark/quest": 26,
+    "Measure": 27,
+    "N": 28,
+    "Not": 1,
+    "Num": 29,
+    "Num/ordinal": 30,
+    "O": 0,
+    "Part/dem": 31,
+    "Part/excl": 32,
+    "Part/imp": 34,
+    "Part/intens": 35,
+    "Part/limit": 33,
+    "Part/neg": 36,
+    "Part/quest": 37,
+    "Part/soft": 38,
+    "Particip/adj": 46,
+    "Particip/v": 47,
+    "Prep": 39,
+    "Pron": 40,
+    "Pron/attr": 41,
+    "Pron/dem": 42,
+    "Pron/neg": 43,
+    "Pron/pos": 44,
+    "Pron/rel": 45,
+    "Punct": 48,
+    "Quote": 49,
+    "Semicolon": 50,
+    "State": 51,
+    "Sub": 52,
+    "Vf": 53,
+    "Vinf": 54,
+    "Vm": 55
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 120138
+}

tmp-checkpoint-738/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9c450c9aa31d86523540290951ad34da0494ca6efccc18e32fcd396930a0719
+size 711062560

tmp-checkpoint-738/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:113130f74a9659058a82b6e87b313f67e7f35ffb68fb1aff48f3e30fdc068938
+size 491807520

tmp-checkpoint-738/special_tokens_map.json

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

tmp-checkpoint-738/tokenizer_config.json

@@ -0,0 +1,60 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "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]",
+  "max_length": 100,
+  "model_max_length": 1000000000000000019884624838656,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "padding": true,
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "truncation": true,
+  "unk_token": "[UNK]"
+}

tmp-checkpoint-738/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba023a3342832acbecdae7796454869353f46a0acfd7e3d4bc0d5103123dfc7f
+size 4920

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91e133dc65cfa7de7b6309e9d4ffa61691d54a4222c584940217dddb4b3f6a40
+oid sha256:ba023a3342832acbecdae7796454869353f46a0acfd7e3d4bc0d5103123dfc7f
 size 4920