Fine tune model

README.md

@@ -0,0 +1,72 @@
+---
+license: mit
+library_name: peft
+tags:
+- generated_from_trainer
+metrics:
+- precision
+- recall
+- accuracy
+base_model: roberta-large
+model-index:
+- name: roberta-large-lora-token-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. -->
+
+# roberta-large-lora-token-classification
+
+This model is a fine-tuned version of [roberta-large](https://huggingface.co/roberta-large) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.4877
+- Precision: 0.8557
+- Recall: 0.6375
+- F1-score: 0.7306
+- Accuracy: 0.7991
+
+## 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: 0.0001
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: constant
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 5
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1-score | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:--------:|:--------:|
+| 0.656         | 1.0   | 762  | 0.6091          | 0.5121    | 0.9432 | 0.6638   | 0.5916   |
+| 0.5514        | 2.0   | 1524 | 0.6414          | 0.5205    | 0.9370 | 0.6692   | 0.6041   |
+| 0.5584        | 3.0   | 2286 | 0.4862          | 0.7271    | 0.7696 | 0.7478   | 0.7781   |
+| 0.5467        | 4.0   | 3048 | 0.4781          | 0.8197    | 0.6912 | 0.7500   | 0.8030   |
+| 0.5519        | 5.0   | 3810 | 0.4877          | 0.8557    | 0.6375 | 0.7306   | 0.7991   |
+
+
+### Framework versions
+
+- PEFT 0.9.0
+- Transformers 4.38.1
+- Pytorch 2.1.0+cu121
+- Datasets 2.18.0
+- Tokenizers 0.15.2

adapter_config.json

@@ -0,0 +1,28 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "roberta-large",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 2,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "query",
+    "value"
+  ],
+  "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 sha256:492cf4c6725cb49116650cb01f492f513110779e9750e2686a8b3b42da27f004
+size 5007376

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:020fd968fe109b3a1ee63920e0eec556dd49d6bb59a91019108205abbb13044e
+size 4984