Training in progress, epoch 2

README.md

@@ -0,0 +1,72 @@
+---
+base_model: ai-forever/ruRoberta-large
+library_name: peft
+metrics:
+- accuracy
+tags:
+- generated_from_trainer
+model-index:
+- name: ruRoberta-large-brand-text-classification
+  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. -->
+
+# ruRoberta-large-brand-text-classification
+
+This model was trained from scratch on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.4496
+- Accuracy: {'accuracy': 0.9166666666666666}
+- F1 Score: {'f1': 0.8095238095238095}
+
+## 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: 0.001
+- 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
+- lr_scheduler_warmup_steps: 500
+- num_epochs: 10
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy                         | F1 Score                    |
+|:-------------:|:-----:|:----:|:---------------:|:--------------------------------:|:---------------------------:|
+| 0.0864        | 1.0   | 7    | 0.4496          | {'accuracy': 0.9166666666666666} | {'f1': 0.8095238095238095}  |
+| 0.5172        | 2.0   | 14   | 0.4940          | {'accuracy': 0.9166666666666666} | {'f1': 0.8095238095238095}  |
+| 0.2577        | 3.0   | 21   | 0.6420          | {'accuracy': 0.5833333333333334} | {'f1': 0.3686274509803922}  |
+| 0.5231        | 4.0   | 28   | 0.7110          | {'accuracy': 0.5833333333333334} | {'f1': 0.3686274509803922}  |
+| 0.4421        | 5.0   | 35   | 0.5916          | {'accuracy': 0.75}               | {'f1': 0.5029239766081871}  |
+| 0.138         | 6.0   | 42   | 0.6586          | {'accuracy': 0.75}               | {'f1': 0.5029239766081871}  |
+| 0.1561        | 7.0   | 49   | 0.6274          | {'accuracy': 0.6666666666666666} | {'f1': 0.4259259259259259}  |
+| 0.0271        | 8.0   | 56   | 0.6291          | {'accuracy': 0.6666666666666666} | {'f1': 0.48148148148148145} |
+| 0.4528        | 9.0   | 63   | 0.5169          | {'accuracy': 0.9166666666666666} | {'f1': 0.8095238095238095}  |
+| 0.5633        | 10.0  | 70   | 0.4749          | {'accuracy': 0.75}               | {'f1': 0.6210526315789473}  |
+
+
+### Framework versions
+
+- PEFT 0.13.2
+- Transformers 4.46.1
+- Pytorch 2.5.0+cu121
+- Datasets 3.1.0
+- Tokenizers 0.20.1

adapter_config.json

@@ -0,0 +1,32 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "ai-forever/ruRoberta-large",
+  "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": 16,
+  "lora_dropout": 0.01,
+  "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": "SEQ_CLS",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa7b6952a582561a444f8f2e959e507038c07a89e590b8e770da00d0b8b826ac
+size 10516612

runs/Nov03_21-38-24_1351ccee4e40/events.out.tfevents.1730669906.1351ccee4e40.23132.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e346f52ec0497f9f90451e8039745a3785d657f04c19000abf959cca5b5faef
+size 22878

runs/Nov03_21-38-24_1351ccee4e40/events.out.tfevents.1730670128.1351ccee4e40.23132.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c86d88452a4fb0829d7e47d9eb1fa18c1fd16099371c15feb88c179082cf538a
+size 354

runs/Nov03_21-51-33_1351ccee4e40/events.out.tfevents.1730670695.1351ccee4e40.23132.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa919ff24f162cf807f7ed32383050a9a9e0c9513c8261a60cfce30e08c02ee5
+size 22875

runs/Nov03_21-51-33_1351ccee4e40/events.out.tfevents.1730670840.1351ccee4e40.23132.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55d5dd47b1fa8750bc415602b896acd65e3c0ec31e1b3fad50ac37e6e977017a
+size 620

runs/Nov03_22-21-39_1351ccee4e40/events.out.tfevents.1730672504.1351ccee4e40.23132.6

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b8a35d11587beecfa8bb0882ec0e2f67945cc5d7fa43e44633e0a46a08d7ed3
+size 8846

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": false,
+    "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 +1,58 @@
+{
+  "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": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "max_length": 512,
+  "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 sha256:8545919633221c036848ea42e0f2b78d041138bdfafad4bacbfd5238cd4485e9
+size 5432