Model save

README.md

@@ -0,0 +1,70 @@
+---
+library_name: peft
+license: cc-by-4.0
+base_model: pczarnik/herbert-base-ner
+tags:
+- generated_from_trainer
+metrics:
+- precision
+- recall
+- f1
+model-index:
+- name: herbert-ner-lora-sensitive
+  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-ner-lora-sensitive
+
+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: 0.0070
+- Precision: 0.8622
+- Recall: 0.8596
+- F1: 0.8609
+
+## 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: 0.0002
+- 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: 5
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|
+| No log        | 1.0   | 315  | 0.0148          | 0.8076    | 0.7253 | 0.7642 |
+| 0.1305        | 2.0   | 630  | 0.0096          | 0.8339    | 0.8133 | 0.8234 |
+| 0.1305        | 3.0   | 945  | 0.0079          | 0.8538    | 0.8472 | 0.8505 |
+| 0.0112        | 4.0   | 1260 | 0.0072          | 0.8556    | 0.8596 | 0.8576 |
+| 0.0092        | 5.0   | 1575 | 0.0070          | 0.8622    | 0.8596 | 0.8609 |
+
+
+### Framework versions
+
+- PEFT 0.12.0
+- Transformers 4.50.3
+- Pytorch 2.4.1
+- Datasets 2.21.0
+- Tokenizers 0.21.1

adapter_config.json

@@ -0,0 +1,31 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "pczarnik/herbert-base-ner",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [
+    "classifier",
+    "score"
+  ],
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "classifier"
+  ],
+  "task_type": "TOKEN_CLS",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e6f2a46a1a1633688fff5db6c54fc4a9e05cf6cb48772883f3b8c57a206de75
+size 236652

runs/Apr24_14-32-14_laptop-Micha.local/events.out.tfevents.1745497939.laptop-Micha.local.13856.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b72612bf2ff67ebf6189c693eb4b8b5952862026c03cbd9bc8bf4a81a9751e3
+size 9366

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 sha256:57a6da018d996fa15bb0de16bd1cb5a65df37df682a633093606fddd0beba5c1
+size 5368