Training complete

README.md

@@ -0,0 +1,93 @@
+---
+license: apache-2.0
+base_model: DmitryPogrebnoy/MedRuRobertaLarge
+tags:
+- generated_from_trainer
+metrics:
+- precision
+- recall
+- f1
+- accuracy
+model-index:
+- name: MedRuRobertaLarge_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. -->
+
+# MedRuRobertaLarge_neg
+
+This model is a fine-tuned version of [DmitryPogrebnoy/MedRuRobertaLarge](https://huggingface.co/DmitryPogrebnoy/MedRuRobertaLarge) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.4946
+- Precision: 0.5932
+- Recall: 0.5804
+- F1: 0.5868
+- Accuracy: 0.9015
+
+## 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   | 0.6600          | 0.0       | 0.0    | 0.0    | 0.7759   |
+| No log        | 2.0   | 100  | 0.5893          | 0.0       | 0.0    | 0.0    | 0.7826   |
+| No log        | 3.0   | 150  | 0.4690          | 0.0265    | 0.0173 | 0.0210 | 0.8164   |
+| No log        | 4.0   | 200  | 0.4564          | 0.0979    | 0.1252 | 0.1099 | 0.8204   |
+| No log        | 5.0   | 250  | 0.3628          | 0.1881    | 0.2852 | 0.2266 | 0.8538   |
+| No log        | 6.0   | 300  | 0.3105          | 0.3469    | 0.3622 | 0.3544 | 0.8901   |
+| No log        | 7.0   | 350  | 0.3382          | 0.4084    | 0.3738 | 0.3903 | 0.8909   |
+| No log        | 8.0   | 400  | 0.2926          | 0.4774    | 0.4682 | 0.4728 | 0.9020   |
+| No log        | 9.0   | 450  | 0.2955          | 0.4630    | 0.4817 | 0.4721 | 0.9046   |
+| 0.3854        | 10.0  | 500  | 0.3161          | 0.5367    | 0.4933 | 0.5141 | 0.9080   |
+| 0.3854        | 11.0  | 550  | 0.3103          | 0.4612    | 0.6069 | 0.5241 | 0.9018   |
+| 0.3854        | 12.0  | 600  | 0.3020          | 0.5614    | 0.6166 | 0.5877 | 0.9136   |
+| 0.3854        | 13.0  | 650  | 0.3738          | 0.5625    | 0.5896 | 0.5757 | 0.9157   |
+| 0.3854        | 14.0  | 700  | 0.3322          | 0.4834    | 0.5877 | 0.5304 | 0.9031   |
+| 0.3854        | 15.0  | 750  | 0.3619          | 0.4855    | 0.5472 | 0.5145 | 0.9083   |
+| 0.3854        | 16.0  | 800  | 0.3597          | 0.4815    | 0.6763 | 0.5625 | 0.9018   |
+| 0.3854        | 17.0  | 850  | 0.4065          | 0.5488    | 0.6281 | 0.5858 | 0.9145   |
+| 0.3854        | 18.0  | 900  | 0.4491          | 0.6047    | 0.6513 | 0.6271 | 0.9184   |
+| 0.3854        | 19.0  | 950  | 0.4184          | 0.4972    | 0.6898 | 0.5779 | 0.8986   |
+| 0.0771        | 20.0  | 1000 | 0.3366          | 0.5929    | 0.6089 | 0.6008 | 0.9238   |
+| 0.0771        | 21.0  | 1050 | 0.6161          | 0.6834    | 0.5241 | 0.5932 | 0.9009   |
+| 0.0771        | 22.0  | 1100 | 0.6387          | 0.3497    | 0.6859 | 0.4632 | 0.8377   |
+| 0.0771        | 23.0  | 1150 | 0.3559          | 0.6004    | 0.6224 | 0.6112 | 0.9198   |
+| 0.0771        | 24.0  | 1200 | 0.4161          | 0.5926    | 0.6166 | 0.6043 | 0.9203   |
+| 0.0771        | 25.0  | 1250 | 0.4341          | 0.6365    | 0.6108 | 0.6234 | 0.9199   |
+| 0.0771        | 26.0  | 1300 | 0.3910          | 0.6184    | 0.5838 | 0.6006 | 0.9153   |
+| 0.0771        | 27.0  | 1350 | 0.3706          | 0.5396    | 0.6435 | 0.5870 | 0.9209   |
+| 0.0771        | 28.0  | 1400 | 0.5059          | 0.5833    | 0.6069 | 0.5949 | 0.9157   |
+
+
+### 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": "DmitryPogrebnoy/MedRuRobertaLarge",
+  "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": 50257
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9dbf3f714f0460c72961c72193ee665e8751d5eb600994bc54c14e0979081e91
+size 1417268116

runs/May06_23-03-53_4537e44771aa/events.out.tfevents.1715036634.4537e44771aa.34.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca14e83ecdb064c16766e2b198124e494ded5c3a93396d66b3b5d121c6fa86d5
+size 18789

runs/May06_23-03-53_4537e44771aa/events.out.tfevents.1715037929.4537e44771aa.34.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ac94ca5aeb5f755075d25283ec7ff48c4f89709e92182cca2d52a1c89f17d4d
+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": true,
+    "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": true,
+      "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:fea49175dffcf300beefc984322a438e08adb22620536bf75dfd078f2f546cc8
+size 4920