gemma2_on_korean_events

README.md

@@ -0,0 +1,100 @@
+---
+license: other
+library_name: peft
+tags:
+- generated_from_trainer
+base_model: beomi/gemma-ko-2b
+model-index:
+- name: gemma2_on_korean_events
+  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. -->
+
+# gemma2_on_korean_events
+
+This model is a fine-tuned version of [beomi/gemma-ko-2b](https://huggingface.co/beomi/gemma-ko-2b) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.7952
+
+## 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: 5e-05
+- train_batch_size: 2
+- eval_batch_size: 2
+- seed: 42
+- gradient_accumulation_steps: 5
+- total_train_batch_size: 10
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 50
+- training_steps: 760
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 1.7756        | 0.26  | 20   | 1.6485          |
+| 1.4697        | 0.53  | 40   | 1.2639          |
+| 1.1143        | 0.79  | 60   | 1.0257          |
+| 0.9885        | 1.05  | 80   | 0.9638          |
+| 0.9346        | 1.32  | 100  | 0.9163          |
+| 0.8965        | 1.58  | 120  | 0.8794          |
+| 0.8711        | 1.84  | 140  | 0.8540          |
+| 0.8126        | 2.11  | 160  | 0.8339          |
+| 0.7741        | 2.37  | 180  | 0.8167          |
+| 0.757         | 2.63  | 200  | 0.8028          |
+| 0.7416        | 2.89  | 220  | 0.7868          |
+| 0.7128        | 3.16  | 240  | 0.7838          |
+| 0.666         | 3.42  | 260  | 0.7757          |
+| 0.6636        | 3.68  | 280  | 0.7636          |
+| 0.6571        | 3.95  | 300  | 0.7579          |
+| 0.6156        | 4.21  | 320  | 0.7577          |
+| 0.5964        | 4.47  | 340  | 0.7557          |
+| 0.5999        | 4.74  | 360  | 0.7516          |
+| 0.5843        | 5.0   | 380  | 0.7426          |
+| 0.5388        | 5.26  | 400  | 0.7633          |
+| 0.5362        | 5.53  | 420  | 0.7619          |
+| 0.5332        | 5.79  | 440  | 0.7530          |
+| 0.5287        | 6.05  | 460  | 0.7537          |
+| 0.4931        | 6.32  | 480  | 0.7695          |
+| 0.5074        | 6.58  | 500  | 0.7611          |
+| 0.4913        | 6.84  | 520  | 0.7573          |
+| 0.4686        | 7.11  | 540  | 0.7703          |
+| 0.4594        | 7.37  | 560  | 0.7714          |
+| 0.4562        | 7.63  | 580  | 0.7790          |
+| 0.4648        | 7.89  | 600  | 0.7691          |
+| 0.4353        | 8.16  | 620  | 0.7895          |
+| 0.4387        | 8.42  | 640  | 0.7876          |
+| 0.4184        | 8.68  | 660  | 0.7875          |
+| 0.4301        | 8.95  | 680  | 0.7881          |
+| 0.4239        | 9.21  | 700  | 0.7952          |
+| 0.4116        | 9.47  | 720  | 0.7953          |
+| 0.4018        | 9.74  | 740  | 0.7948          |
+| 0.4063        | 10.0  | 760  | 0.7952          |
+
+
+### Framework versions
+
+- PEFT 0.8.2
+- Transformers 4.38.2
+- Pytorch 2.1.2+cu121
+- Datasets 2.17.0
+- Tokenizers 0.15.0

adapter_config.json

@@ -0,0 +1,32 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "beomi/gemma-ko-2b",
+  "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": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "o_proj",
+    "k_proj",
+    "gate_proj",
+    "down_proj",
+    "up_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec5e47741ba2a68c2ae2dd68b9c87bd11f671c31f223abf3bcdaab45be025d90
+size 78480072

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90bc184d5a05142346f40469aaefe1ed504f50c16c38b1616315d56d4992b333
+size 4920