Training complete

README.md

@@ -0,0 +1,105 @@
+---
+base_model: ai-forever/ruRoberta-large
+tags:
+- generated_from_trainer
+metrics:
+- precision
+- recall
+- f1
+- accuracy
+model-index:
+- name: ruRoberta-large_neg
+ 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. -->
+
+# ruRoberta-large_neg
+
+This model is a fine-tuned version of [ai-forever/ruRoberta-large](https://huggingface.co/ai-forever/ruRoberta-large) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.6173
+- Precision: 0.5980
+- Recall: 0.5920
+- F1: 0.5950
+- Accuracy: 0.9001
+
+## 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: 5e-05
+- train_batch_size: 4
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 100
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| No log | 1.0 | 50 | 0.6748 | 0.0 | 0.0 | 0.0 | 0.7758 |
+| No log | 2.0 | 100 | 0.6015 | 0.0054 | 0.0019 | 0.0028 | 0.7853 |
+| No log | 3.0 | 150 | 0.4397 | 0.0699 | 0.0867 | 0.0774 | 0.8296 |
+| No log | 4.0 | 200 | 0.3701 | 0.1805 | 0.2351 | 0.2042 | 0.8555 |
+| No log | 5.0 | 250 | 0.3134 | 0.3189 | 0.3680 | 0.3417 | 0.8823 |
+| No log | 6.0 | 300 | 0.2931 | 0.3305 | 0.4528 | 0.3821 | 0.8921 |
+| No log | 7.0 | 350 | 0.2891 | 0.4114 | 0.4297 | 0.4204 | 0.9017 |
+| No log | 8.0 | 400 | 0.2799 | 0.4714 | 0.5087 | 0.4893 | 0.9033 |
+| No log | 9.0 | 450 | 0.2671 | 0.5045 | 0.5453 | 0.5241 | 0.9118 |
+| 0.3651 | 10.0 | 500 | 0.2917 | 0.5287 | 0.5145 | 0.5215 | 0.9149 |
+| 0.3651 | 11.0 | 550 | 0.2900 | 0.4768 | 0.6127 | 0.5363 | 0.9105 |
+| 0.3651 | 12.0 | 600 | 0.3307 | 0.4873 | 0.5896 | 0.5336 | 0.9135 |
+| 0.3651 | 13.0 | 650 | 0.2883 | 0.5490 | 0.6050 | 0.5756 | 0.9163 |
+| 0.3651 | 14.0 | 700 | 0.3514 | 0.5308 | 0.5819 | 0.5551 | 0.9170 |
+| 0.3651 | 15.0 | 750 | 0.3858 | 0.5120 | 0.6590 | 0.5762 | 0.9055 |
+| 0.3651 | 16.0 | 800 | 0.3655 | 0.5008 | 0.6262 | 0.5565 | 0.9204 |
+| 0.3651 | 17.0 | 850 | 0.3605 | 0.5952 | 0.6628 | 0.6272 | 0.9206 |
+| 0.3651 | 18.0 | 900 | 0.5156 | 0.5822 | 0.6416 | 0.6104 | 0.9148 |
+| 0.3651 | 19.0 | 950 | 0.4462 | 0.4873 | 0.6628 | 0.5616 | 0.8964 |
+| 0.0734 | 20.0 | 1000 | 0.3837 | 0.5817 | 0.5626 | 0.5720 | 0.9147 |
+| 0.0734 | 21.0 | 1050 | 0.5484 | 0.6283 | 0.5472 | 0.5850 | 0.9122 |
+| 0.0734 | 22.0 | 1100 | 0.4612 | 0.4459 | 0.6358 | 0.5242 | 0.8869 |
+| 0.0734 | 23.0 | 1150 | 0.5106 | 0.588 | 0.5665 | 0.5770 | 0.9146 |
+| 0.0734 | 24.0 | 1200 | 0.4511 | 0.6526 | 0.5973 | 0.6237 | 0.9187 |
+| 0.0734 | 25.0 | 1250 | 0.4511 | 0.6152 | 0.6069 | 0.6111 | 0.9183 |
+| 0.0734 | 26.0 | 1300 | 0.4642 | 0.6141 | 0.5703 | 0.5914 | 0.9141 |
+| 0.0734 | 27.0 | 1350 | 0.4177 | 0.5191 | 0.6802 | 0.5888 | 0.9057 |
+| 0.0734 | 28.0 | 1400 | 0.4025 | 0.6011 | 0.6532 | 0.6260 | 0.9210 |
+| 0.0734 | 29.0 | 1450 | 0.4620 | 0.5519 | 0.6455 | 0.5950 | 0.9068 |
+| 0.0435 | 30.0 | 1500 | 0.4229 | 0.6029 | 0.6320 | 0.6171 | 0.9205 |
+| 0.0435 | 31.0 | 1550 | 0.3752 | 0.5565 | 0.6647 | 0.6058 | 0.9139 |
+| 0.0435 | 32.0 | 1600 | 0.5814 | 0.6146 | 0.5684 | 0.5906 | 0.9131 |
+| 0.0435 | 33.0 | 1650 | 0.4216 | 0.6155 | 0.5800 | 0.5972 | 0.9128 |
+| 0.0435 | 34.0 | 1700 | 0.5093 | 0.5853 | 0.5819 | 0.5836 | 0.9147 |
+| 0.0435 | 35.0 | 1750 | 0.4221 | 0.5968 | 0.6532 | 0.6237 | 0.9153 |
+| 0.0435 | 36.0 | 1800 | 0.4700 | 0.6404 | 0.6416 | 0.6410 | 0.9179 |
+| 0.0435 | 37.0 | 1850 | 0.3946 | 0.5651 | 0.5684 | 0.5668 | 0.9167 |
+| 0.0435 | 38.0 | 1900 | 0.4196 | 0.6013 | 0.5549 | 0.5772 | 0.9062 |
+| 0.0435 | 39.0 | 1950 | 0.4054 | 0.6282 | 0.5761 | 0.6010 | 0.9194 |
+| 0.0447 | 40.0 | 2000 | 0.3649 | 0.6075 | 0.5934 | 0.6004 | 0.9133 |
+| 0.0447 | 41.0 | 2050 | 0.4154 | 0.5907 | 0.6089 | 0.5996 | 0.9145 |
+
+
+### Framework versions
+
+- Transformers 4.38.2
+- Pytorch 2.1.2
+- Datasets 2.1.0
+- Tokenizers 0.15.2

config.json

@@ -0,0 +1,38 @@
+{
+ "_name_or_path": "ai-forever/ruRoberta-large",
+ "architectures": [
+ "RobertaForTokenClassification"
+ ],
+ "attention_probs_dropout_prob": 0.1,
+ "bos_token_id": 1,
+ "classifier_dropout": null,
+ "eos_token_id": 2,
+ "gradient_checkpointing": false,
+ "hidden_act": "gelu",
+ "hidden_dropout_prob": 0.1,
+ "hidden_size": 1024,
+ "id2label": {
+ "0": "O",
+ "1": "B-symp",
+ "2": "I-symp"
+ },
+ "initializer_range": 0.02,
+ "intermediate_size": 4096,
+ "label2id": {
+ "0": "O",
+ "1": "B-symp",
+ "2": "I-symp"
+ },
+ "layer_norm_eps": 1e-05,
+ "max_position_embeddings": 514,
+ "model_type": "roberta",
+ "num_attention_heads": 16,
+ "num_hidden_layers": 24,
+ "pad_token_id": 1,
+ "position_embedding_type": "absolute",
+ "torch_dtype": "float32",
+ "transformers_version": "4.38.2",
+ "type_vocab_size": 1,
+ "use_cache": true,
+ "vocab_size": 50265
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:906584c2738d52216c402ea4851fa070ddb2cf5b0a52d935e27898a84ce2f30d
+size 1417300884

runs/May07_13-37-17_8dd371958cdf/events.out.tfevents.1715089038.8dd371958cdf.34.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79fa34c81d930a8ed84eeab082152005baa76f7bdba77c44bf5350078b2bcbac
+size 4774

runs/May07_13-57-54_8dd371958cdf/events.out.tfevents.1715090275.8dd371958cdf.34.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5bacd7ae108e2b3820eb10757e5b85a17e8e6154c446f63286107050e8e89266
+size 25306

runs/May07_13-57-54_8dd371958cdf/events.out.tfevents.1715092184.8dd371958cdf.34.6

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9f47e3086b3a8550bc1297358688047be7d50c8af76e172e3e072f072085be8
+size 560

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+ "bos_token": {
+ "content": "<s>",
+ "lstrip": false,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false
+ },
+ "cls_token": {
+ "content": "<s>",
+ "lstrip": false,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false
+ },
+ "eos_token": {
+ "content": "</s>",
+ "lstrip": false,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false
+ },
+ "mask_token": {
+ "content": "<mask>",
+ "lstrip": true,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "pad_token": {
+ "content": "<pad>",
+ "lstrip": false,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false
+ },
+ "sep_token": {
+ "content": "</s>",
+ "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 +1,57 @@
+{
+ "add_prefix_space": true,
+ "added_tokens_decoder": {
+ "0": {
+ "content": "<pad>",
+ "lstrip": false,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "1": {
+ "content": "<s>",
+ "lstrip": false,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "2": {
+ "content": "</s>",
+ "lstrip": false,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "3": {
+ "content": "<unk>",
+ "lstrip": false,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "4": {
+ "content": "<mask>",
+ "lstrip": true,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ }
+ },
+ "bos_token": "<s>",
+ "clean_up_tokenization_spaces": true,
+ "cls_token": "<s>",
+ "eos_token": "</s>",
+ "errors": "replace",
+ "mask_token": "<mask>",
+ "model_max_length": 1000000000000000019884624838656,
+ "pad_token": "<pad>",
+ "sep_token": "</s>",
+ "tokenizer_class": "RobertaTokenizer",
+ "trim_offsets": true,
+ "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc12b2e9c235412b354b860712149041e14535fa9b66ca89221dd509c56cd35c
+size 4920