marcus2000/HSE_PRAVO_complexity_classifier_large

README.md

@@ -0,0 +1,53 @@
+---
+base_model: ai-forever/ruBert-large
+tags:
+- generated_from_trainer
+model-index:
+- name: HSE_PRAVO_complexity_classifier_large_nolora
+  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. -->
+
+# HSE_PRAVO_complexity_classifier_large_nolora
+
+This model is a fine-tuned version of [ai-forever/ruBert-large](https://huggingface.co/ai-forever/ruBert-large) on an unknown dataset.
+
+## 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-06
+- train_batch_size: 3
+- eval_batch_size: 3
+- seed: 42
+- gradient_accumulation_steps: 10
+- total_train_batch_size: 30
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- training_steps: 200
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.36.2
+- Pytorch 2.2.1+cu121
+- Datasets 2.19.0
+- Tokenizers 0.15.2

config.json

@@ -0,0 +1,42 @@
+{
+  "_name_or_path": "ai-forever/ruBert-large",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "\u043b\u0435\u0433\u043a\u0438\u0439",
+    "1": "\u0441\u043b\u043e\u0436\u043d\u044b\u0439",
+    "2": "\u043e\u0447\u0435\u043d\u044c \u0441\u043b\u043e\u0436\u043d\u044b\u0439"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "\u043b\u0435\u0433\u043a\u0438\u0439": 0,
+    "\u043e\u0447\u0435\u043d\u044c \u0441\u043b\u043e\u0436\u043d\u044b\u0439": 2,
+    "\u0441\u043b\u043e\u0436\u043d\u044b\u0439": 1
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "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",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.36.2",
+  "type_vocab_size": 2,
+  "use_cache": false,
+  "vocab_size": 120138
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6c7ad39b572cbff5246857e63f6ac47cb3f15c36c8b6893a3f3b8923967295b
+size 1707694236

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
+    },
+    "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]",
+  "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 sha256:9ded2d38dee1dcdc0aaaef5eafe887a9debbe64619879c52712e510a2823aff1
+size 4664