gemma7_on_korean_conv

README.md

@@ -0,0 +1,97 @@
+---
+license: other
+library_name: peft
+tags:
+- generated_from_trainer
+base_model: beomi/gemma-ko-7b
+model-index:
+- name: gemma7_on_korean_conv
+  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. -->
+
+# gemma7_on_korean_conv
+
+This model is a fine-tuned version of [beomi/gemma-ko-7b](https://huggingface.co/beomi/gemma-ko-7b) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.7037
+
+## 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: 1
+- eval_batch_size: 1
+- seed: 42
+- gradient_accumulation_steps: 5
+- total_train_batch_size: 5
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 100
+- training_steps: 7200
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 0.8472        | 0.1281 | 200  | 0.8849          |
+| 0.7799        | 0.2563 | 400  | 0.8185          |
+| 0.7791        | 0.3844 | 600  | 0.7945          |
+| 0.7505        | 0.5126 | 800  | 0.7877          |
+| 0.7891        | 0.6407 | 1000 | 0.7616          |
+| 0.689         | 0.7688 | 1200 | 0.7437          |
+| 0.7612        | 0.8970 | 1400 | 0.7520          |
+| 0.5183        | 1.0251 | 1600 | 0.8028          |
+| 0.4562        | 1.1533 | 1800 | 0.7811          |
+| 0.4584        | 1.2814 | 2000 | 0.7920          |
+| 0.4535        | 1.4095 | 2200 | 0.7887          |
+| 0.4268        | 1.5377 | 2400 | 0.8048          |
+| 0.4368        | 1.6658 | 2600 | 0.7640          |
+| 0.4435        | 1.7940 | 2800 | 0.7844          |
+| 0.4327        | 1.9221 | 3000 | 0.7977          |
+| 0.1711        | 2.0502 | 3200 | 1.0313          |
+| 0.1856        | 2.1784 | 3400 | 0.9997          |
+| 0.1812        | 2.3065 | 3600 | 0.9870          |
+| 0.1876        | 2.4346 | 3800 | 0.9731          |
+| 0.1927        | 2.5628 | 4000 | 0.9857          |
+| 0.1964        | 2.6909 | 4200 | 1.0148          |
+| 0.1948        | 2.8191 | 4400 | 1.0025          |
+| 0.1865        | 2.9472 | 4600 | 1.0556          |
+| 0.059         | 3.0753 | 4800 | 1.3127          |
+| 0.0523        | 3.2035 | 5000 | 1.3947          |
+| 0.0658        | 3.3316 | 5200 | 1.3980          |
+| 0.0596        | 3.4598 | 5400 | 1.3785          |
+| 0.0556        | 3.5879 | 5600 | 1.3936          |
+| 0.0709        | 3.7160 | 5800 | 1.3858          |
+| 0.0544        | 3.8442 | 6000 | 1.3943          |
+| 0.0503        | 3.9723 | 6200 | 1.4319          |
+| 0.0133        | 4.1005 | 6400 | 1.6485          |
+| 0.0144        | 4.2286 | 6600 | 1.6932          |
+| 0.0126        | 4.3567 | 6800 | 1.6980          |
+| 0.0189        | 4.4849 | 7000 | 1.6962          |
+| 0.0128        | 4.6130 | 7200 | 1.7037          |
+
+
+### Framework versions
+
+- PEFT 0.11.1
+- Transformers 4.41.1
+- 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": "beomi/gemma-ko-7b",
+  "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": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "down_proj",
+    "k_proj",
+    "up_proj",
+    "o_proj",
+    "gate_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3857797b2536702a6014db58dc6d222f8ce8be78073ce75e9f3ba73e7b447b9b
+size 200068512

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f1d514cb77f9d72dc7d06ace00f1213ad91dae11eaa61e728651a4b60655b24
+size 5112