loha_fine_tuned_rte_XLMroberta

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,71 @@
+---
+license: mit
+library_name: peft
+tags:
+- generated_from_trainer
+base_model: xlm-roberta-base
+metrics:
+- accuracy
+- f1
+model-index:
+- name: loha_fine_tuned_rte_XLMroberta
+  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. -->
+
+# loha_fine_tuned_rte_XLMroberta
+
+This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.6906
+- Accuracy: 0.6207
+- F1: 0.5466
+
+## 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: 8
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- training_steps: 400
+
+### Training results
+
+| Training Loss | Epoch   | Step | Validation Loss | Accuracy | F1     |
+|:-------------:|:-------:|:----:|:---------------:|:--------:|:------:|
+| 0.7061        | 1.7241  | 50   | 0.7021          | 0.4138   | 0.2422 |
+| 0.7012        | 3.4483  | 100  | 0.6955          | 0.4138   | 0.2422 |
+| 0.6902        | 5.1724  | 150  | 0.6970          | 0.4138   | 0.2422 |
+| 0.6922        | 6.8966  | 200  | 0.6917          | 0.5172   | 0.5087 |
+| 0.694         | 8.6207  | 250  | 0.6897          | 0.5862   | 0.4333 |
+| 0.6945        | 10.3448 | 300  | 0.6906          | 0.5517   | 0.4169 |
+| 0.6926        | 12.0690 | 350  | 0.6903          | 0.5862   | 0.4854 |
+| 0.6883        | 13.7931 | 400  | 0.6906          | 0.6207   | 0.5466 |
+
+
+### Framework versions
+
+- PEFT 0.11.1
+- Transformers 4.40.2
+- Pytorch 2.1.1+cu121
+- Datasets 2.19.1
+- Tokenizers 0.19.1

adapter_config.json

@@ -0,0 +1,26 @@
+{
+  "alpha": 32,
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "xlm-roberta-base",
+  "inference_mode": true,
+  "init_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "module_dropout": 0.0,
+  "modules_to_save": [
+    "classifier",
+    "score"
+  ],
+  "peft_type": "LOHA",
+  "r": 16,
+  "rank_dropout": 0.0,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "query",
+    "value"
+  ],
+  "task_type": "SEQ_CLS",
+  "use_effective_conv2d": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb86ea275dbb968fe8496431bc64c5f28173aa74fae3266177b73d6f269ee753
+size 7101032

runs/May22_22-01-47_DESKTOP-22QTFDR/events.out.tfevents.1716408108.DESKTOP-22QTFDR.32492.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aded248fd9eb9b539718d9e598a61cb1363afb619135a3dc2a7833f19d36432a
+size 9863

runs/May22_22-01-47_DESKTOP-22QTFDR/events.out.tfevents.1716408175.DESKTOP-22QTFDR.32492.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6747246bb751dd5db851c5fa85dc8e8b1fc5b517e1a90b78c0fdadd9f23e8fc8
+size 457

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a56def25aa40facc030ea8b0b87f3688e4b3c39eb8b45d5702b3a1300fe2a20
+size 17082734

tokenizer_config.json

@@ -0,0 +1,54 @@
+{
+  "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
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9d295a462db035de06e7c0a254223062e58eca203f16bbb8810380963d26e86
+size 5048