Training complete

README.md

@@ -0,0 +1,88 @@
+---
+license: apache-2.0
+base_model: DmitryPogrebnoy/MedRuRobertaLarge
+tags:
+- generated_from_trainer
+metrics:
+- precision
+- recall
+- f1
+- accuracy
+model-index:
+- name: MedRuRobertaLarge_pos
+  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_pos
+
+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: 0.4823
+- Precision: 0.4746
+- Recall: 0.5274
+- F1: 0.4996
+- Accuracy: 0.9031
+
+## 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   | 0.6491          | 0.0       | 0.0    | 0.0    | 0.7598   |
+| No log        | 2.0   | 100  | 0.6401          | 0.0       | 0.0    | 0.0    | 0.7664   |
+| No log        | 3.0   | 150  | 0.4835          | 0.0195    | 0.0193 | 0.0194 | 0.8187   |
+| No log        | 4.0   | 200  | 0.4325          | 0.0790    | 0.1368 | 0.1001 | 0.8181   |
+| No log        | 5.0   | 250  | 0.3456          | 0.1653    | 0.2370 | 0.1948 | 0.8675   |
+| No log        | 6.0   | 300  | 0.3438          | 0.2128    | 0.2697 | 0.2379 | 0.8744   |
+| No log        | 7.0   | 350  | 0.3814          | 0.3415    | 0.2948 | 0.3164 | 0.8832   |
+| No log        | 8.0   | 400  | 0.3005          | 0.3026    | 0.3854 | 0.3390 | 0.8877   |
+| No log        | 9.0   | 450  | 0.2641          | 0.3718    | 0.5279 | 0.4363 | 0.8997   |
+| 0.4044        | 10.0  | 500  | 0.2754          | 0.4036    | 0.5164 | 0.4531 | 0.9057   |
+| 0.4044        | 11.0  | 550  | 0.3153          | 0.4041    | 0.6416 | 0.4959 | 0.8949   |
+| 0.4044        | 12.0  | 600  | 0.3362          | 0.4428    | 0.5222 | 0.4792 | 0.9094   |
+| 0.4044        | 13.0  | 650  | 0.3325          | 0.4433    | 0.5645 | 0.4966 | 0.9109   |
+| 0.4044        | 14.0  | 700  | 0.2921          | 0.4320    | 0.5568 | 0.4865 | 0.9064   |
+| 0.4044        | 15.0  | 750  | 0.3871          | 0.4630    | 0.5780 | 0.5141 | 0.9080   |
+| 0.4044        | 16.0  | 800  | 0.3479          | 0.4218    | 0.6339 | 0.5065 | 0.8946   |
+| 0.4044        | 17.0  | 850  | 0.3886          | 0.4914    | 0.6031 | 0.5415 | 0.9096   |
+| 0.4044        | 18.0  | 900  | 0.5079          | 0.5108    | 0.5491 | 0.5292 | 0.9076   |
+| 0.4044        | 19.0  | 950  | 0.3963          | 0.4344    | 0.6763 | 0.5290 | 0.8999   |
+| 0.0912        | 20.0  | 1000 | 0.3845          | 0.5033    | 0.5915 | 0.5438 | 0.9145   |
+| 0.0912        | 21.0  | 1050 | 0.5141          | 0.3986    | 0.4239 | 0.4108 | 0.8925   |
+| 0.0912        | 22.0  | 1100 | 0.4587          | 0.4706    | 0.5395 | 0.5027 | 0.9028   |
+| 0.0912        | 23.0  | 1150 | 0.4360          | 0.5017    | 0.5800 | 0.5380 | 0.9075   |
+
+
+### 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:ed9f08356fd9aaf7dad36e296be9b75c573d69830fee50cc8be61906140b10ed
+size 1417268116

runs/May06_21-18-12_634985d315af/events.out.tfevents.1715030294.634985d315af.34.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76986d83f30d9438ee2fe6813acd273709e88bdb1f0c4cb4de0dddfcd16c40a4
+size 4815

runs/May06_21-21-30_634985d315af/events.out.tfevents.1715030492.634985d315af.34.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e652885cd5879253757e34bff6025062902bc986df3cd11c79c76bde66c27b5
+size 16429

runs/May06_21-21-30_634985d315af/events.out.tfevents.1715031573.634985d315af.34.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e12948b7a573bfe8efb7e37b8217b2b870e4bd6461f5b63d0381cee55ea76bc6
+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 sha256:9c1fc6a97c14019c974f9fcc8e7a166f22f0b0234fd80d770e26cfbd82631799
+size 4920