Training in progress, epoch 1

README.md

@@ -0,0 +1,74 @@
+---
+library_name: peft
+base_model: DeepPavlov/rubert-base-cased
+tags:
+- generated_from_trainer
+metrics:
+- precision
+- recall
+- f1
+model-index:
+- name: pollen-ner-500
+  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. -->
+
+# pollen-ner-500
+
+This model is a fine-tuned version of [DeepPavlov/rubert-base-cased](https://huggingface.co/DeepPavlov/rubert-base-cased) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.3313
+- Precision: 0.6161
+- Recall: 0.7992
+- F1: 0.6958
+
+## 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: 8
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Use OptimizerNames.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: 10
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|
+| No log        | 1.0   | 63   | 0.3821          | 0.5504    | 0.7450 | 0.6331 |
+| No log        | 2.0   | 126  | 0.3790          | 0.5526    | 0.7590 | 0.6396 |
+| No log        | 3.0   | 189  | 0.3655          | 0.5687    | 0.7651 | 0.6524 |
+| No log        | 4.0   | 252  | 0.3649          | 0.5714    | 0.7791 | 0.6593 |
+| No log        | 5.0   | 315  | 0.3379          | 0.6071    | 0.7851 | 0.6848 |
+| No log        | 6.0   | 378  | 0.3412          | 0.6015    | 0.7912 | 0.6834 |
+| No log        | 7.0   | 441  | 0.3354          | 0.6071    | 0.7912 | 0.6870 |
+| 0.6175        | 8.0   | 504  | 0.3355          | 0.6070    | 0.7972 | 0.6892 |
+| 0.6175        | 9.0   | 567  | 0.3321          | 0.6142    | 0.7992 | 0.6946 |
+| 0.6175        | 10.0  | 630  | 0.3313          | 0.6161    | 0.7992 | 0.6958 |
+
+
+### Framework versions
+
+- PEFT 0.15.2
+- Transformers 4.51.3
+- Pytorch 2.7.0+cu128
+- Datasets 3.5.0
+- Tokenizers 0.21.1

adapter_config.json

@@ -0,0 +1,37 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "DeepPavlov/bert-base-bg-cs-pl-ru-cased",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "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_bias": false,
+  "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": [
+    "value",
+    "query"
+  ],
+  "task_type": "TOKEN_CLS",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ff9cd7f78956b986ea0f6c16de991ff75a8c1c0718041bb4d776a6c9a3fc549
+size 2400100

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00a8d7a9c2c305f14120535b9ac8a8f53d9a2c303401d608b8c676b758b90d93
+size 5841