Model save

README.md

@@ -0,0 +1,71 @@
+---
+library_name: transformers
+license: cc-by-4.0
+base_model: pczarnik/herbert-base-ner
+tags:
+- generated_from_trainer
+metrics:
+- precision
+- recall
+- f1
+model-index:
+- name: herbert-finetuned-core
+  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. -->
+
+# herbert-finetuned-core
+
+This model is a fine-tuned version of [pczarnik/herbert-base-ner](https://huggingface.co/pczarnik/herbert-base-ner) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0001
+- Precision: 1.0000
+- Recall: 1.0000
+- F1: 1.0000
+
+## 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-05
+- train_batch_size: 16
+- eval_batch_size: 16
+- seed: 42
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- num_epochs: 7
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|
+| 0.0346        | 1.0   | 434  | 0.0005          | 0.9999    | 0.9999 | 0.9999 |
+| 0.0009        | 2.0   | 868  | 0.0001          | 1.0000    | 1.0000 | 1.0000 |
+| 0.0002        | 3.0   | 1302 | 0.0001          | 1.0000    | 1.0000 | 1.0000 |
+| 0.0002        | 4.0   | 1736 | 0.0001          | 1.0000    | 1.0000 | 1.0000 |
+| 0.0002        | 5.0   | 2170 | 0.0001          | 1.0000    | 1.0000 | 1.0000 |
+| 0.0001        | 6.0   | 2604 | 0.0001          | 1.0000    | 1.0000 | 1.0000 |
+| 0.0001        | 7.0   | 3038 | 0.0001          | 1.0000    | 1.0000 | 1.0000 |
+
+
+### Framework versions
+
+- Transformers 4.50.3
+- Pytorch 2.4.1
+- Datasets 2.21.0
+- Tokenizers 0.21.1

config.json

@@ -0,0 +1,47 @@
+{
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "B-ADDRESS",
+    "1": "B-LOC",
+    "2": "B-ORG",
+    "3": "B-PER",
+    "4": "I-ADDRESS",
+    "5": "I-LOC",
+    "6": "I-ORG",
+    "7": "I-PER",
+    "8": "O"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-ADDRESS": 0,
+    "B-LOC": 1,
+    "B-ORG": 2,
+    "B-PER": 3,
+    "I-ADDRESS": 4,
+    "I-LOC": 5,
+    "I-ORG": 6,
+    "I-PER": 7,
+    "O": 8
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 514,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "tokenizer_class": "HerbertTokenizerFast",
+  "torch_dtype": "float32",
+  "transformers_version": "4.50.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 50000
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e06620c8568b08b01bbc76f00e4c154c824c06f44be174616641d19392a83afb
+size 495460188

runs/Apr25_01-02-46_laptop-Micha.local/events.out.tfevents.1745535767.laptop-Micha.local.23249.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01d8629714cb26e1d7aec95fa2b5d3ecb7368f94bfd7ea8e06aa9a27de97d6ee
+size 10842

special_tokens_map.json

@@ -0,0 +1,44 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,62 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<mask>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "do_lowercase_and_remove_accent": false,
+  "extra_special_tokens": {},
+  "id2lang": null,
+  "lang2id": null,
+  "mask_token": "<mask>",
+  "max_length": 512,
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "stride": 0,
+  "tokenizer_class": "HerbertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0bbde373341fd4086775fe39341fbd067f69396dd9e136bdc357f94c1d1dd10f
+size 5368