lora_fine_tuned_cb_sloroberta

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: lora_fine_tuned_cb_sloroberta
+  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. -->
+
+# lora_fine_tuned_cb_sloroberta
+
+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: 1.4857
+- Accuracy: 0.3182
+- F1: 0.1536
+
+## 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     |
+|:-------------:|:-------:|:----:|:---------------:|:--------:|:------:|
+| 0.8917        | 3.5714  | 50   | 1.2659          | 0.3182   | 0.1536 |
+| 0.7167        | 7.1429  | 100  | 1.4722          | 0.3182   | 0.1536 |
+| 0.7436        | 10.7143 | 150  | 1.4516          | 0.3182   | 0.1536 |
+| 0.6926        | 14.2857 | 200  | 1.4899          | 0.3182   | 0.1536 |
+| 0.7165        | 17.8571 | 250  | 1.4917          | 0.3182   | 0.1536 |
+| 0.7161        | 21.4286 | 300  | 1.4901          | 0.3182   | 0.1536 |
+| 0.6938        | 25.0    | 350  | 1.4871          | 0.3182   | 0.1536 |
+| 0.7145        | 28.5714 | 400  | 1.4857          | 0.3182   | 0.1536 |
+
+
+### 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 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": null,
+  "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": 32,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [
+    "classifier",
+    "score"
+  ],
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "dense",
+    "value",
+    "query",
+    "key"
+  ],
+  "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 sha256:53ae479e454082191acea8d5bb170ecd0c08f2e4ee145ccc13bad783af52f4fa
+size 13310452

runs/May23_07-53-57_36eb943dc605/events.out.tfevents.1716450841.36eb943dc605.395.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:494fdb559385cd7e5322dfc316ded141055f2df91130a1a8676b4601b9832f66
+size 10038

runs/May23_07-53-57_36eb943dc605/events.out.tfevents.1716450867.36eb943dc605.395.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5c5901d6e20165885e8b94c3d19630c425f6f1599f8b8339d5af634d747dd11
+size 457

runs/May23_07-54-47_36eb943dc605/events.out.tfevents.1716450890.36eb943dc605.395.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80ed5d300cdff33c286269bdb9dd97a2bcd9ad69ba03d4eee4263c9f91e7b984
+size 10087

runs/May23_07-55-45_36eb943dc605/events.out.tfevents.1716450946.36eb943dc605.395.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07c374534b28af6c6a1fbd1462a3de6a39380c2508133563d443b3a73fa7813d
+size 10087

runs/May23_07-57-49_36eb943dc605/events.out.tfevents.1716451069.36eb943dc605.395.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65609bf5003c7f01bbf2212320a12520c1b376eb36e6c4e8a717da9845629df1
+size 10087

runs/May23_07-57-49_36eb943dc605/events.out.tfevents.1716451130.36eb943dc605.395.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f78eb03c59ac3604be2e0066d2ee5363d46e35a2631efe1e77a3bba39f21281
+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 sha256:9ba2372433a0728824e10b7144a0afa09bf2befc62b31d2e2c36c6a6d74f373f
+size 5112