loha_fine_tuned_rte_sloberta

README.md

@@ -0,0 +1,71 @@
+---
+license: cc-by-sa-4.0
+library_name: peft
+tags:
+- generated_from_trainer
+base_model: EMBEDDIA/sloberta
+metrics:
+- accuracy
+- f1
+model-index:
+- name: loha_fine_tuned_rte_sloberta
+  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_sloberta
+
+This model is a fine-tuned version of [EMBEDDIA/sloberta](https://huggingface.co/EMBEDDIA/sloberta) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.6925
+- Accuracy: 0.5172
+- F1: 0.5207
+
+## 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: 1e-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     |
+|:-------------:|:-------:|:----:|:---------------:|:--------:|:------:|
+| 0.6991        | 1.7241  | 50   | 0.6870          | 0.5862   | 0.4333 |
+| 0.6913        | 3.4483  | 100  | 0.6865          | 0.5862   | 0.4333 |
+| 0.6957        | 5.1724  | 150  | 0.6913          | 0.6897   | 0.6687 |
+| 0.6913        | 6.8966  | 200  | 0.6937          | 0.4483   | 0.4145 |
+| 0.6909        | 8.6207  | 250  | 0.6931          | 0.4483   | 0.4443 |
+| 0.6946        | 10.3448 | 300  | 0.6929          | 0.4138   | 0.4138 |
+| 0.6925        | 12.0690 | 350  | 0.6924          | 0.5517   | 0.5539 |
+| 0.6891        | 13.7931 | 400  | 0.6925          | 0.5172   | 0.5207 |
+
+
+### Framework versions
+
+- PEFT 0.11.1
+- Transformers 4.41.0
+- Pytorch 2.3.0+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": "EMBEDDIA/sloberta",
+  "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 sha256:87c71aecddb998c258394f1a9fd84534f85d6ba5bb2d01955c45144fcf2fb1c4
+size 7101032

runs/May23_20-25-23_a58e1acdfa49/events.out.tfevents.1716495924.a58e1acdfa49.459.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:081bfbdb563168fc5b9ae756b8102c0e4dea06c7ea2e6294faccdb247444819e
+size 9999

runs/May23_20-25-23_a58e1acdfa49/events.out.tfevents.1716495966.a58e1acdfa49.459.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1198970b4a1caee5f08e680b0d298bcd033fcabf7dc297ccc87e0f22d59b526
+size 457

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34b589385a2320549143ab23b0ccf82cc99a82685701cdabe0fad847bd0479ff
+size 800013

special_tokens_map.json

@@ -0,0 +1,55 @@
+{
+  "additional_special_tokens": [
+    "<s>NOTUSED",
+    "</s>NOTUSED"
+  ],
+  "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
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "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 +1,76 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>NOTUSED",
+      "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>NOTUSED",
+      "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
+    },
+    "5": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32004": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<s>NOTUSED",
+    "</s>NOTUSED"
+  ],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "CamembertTokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d8ec947340bebabef0fe7f9da7797e7150877c5c8e66b3125ea5542037ff328
+size 5112