llama8_on_korean_conv-base-ltm

README.md

@@ -0,0 +1,81 @@
+---
+license: other
+library_name: peft
+tags:
+- generated_from_trainer
+base_model: beomi/Llama-3-Open-Ko-8B-Instruct-preview
+model-index:
+- name: llama8_on_korean_conv-base-ltm
+  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. -->
+
+# llama8_on_korean_conv-base-ltm
+
+This model is a fine-tuned version of [beomi/Llama-3-Open-Ko-8B-Instruct-preview](https://huggingface.co/beomi/Llama-3-Open-Ko-8B-Instruct-preview) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.1665
+
+## 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: 20
+- total_train_batch_size: 20
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 100
+- training_steps: 2000
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 1.156         | 0.2563 | 100  | 1.1623          |
+| 1.0573        | 0.5126 | 200  | 1.0621          |
+| 0.9766        | 0.7688 | 300  | 1.0136          |
+| 0.8888        | 1.0251 | 400  | 0.9799          |
+| 0.7699        | 1.2814 | 500  | 0.9696          |
+| 0.7575        | 1.5377 | 600  | 0.9534          |
+| 0.7641        | 1.7940 | 700  | 0.9405          |
+| 0.588         | 2.0502 | 800  | 0.9882          |
+| 0.542         | 2.3065 | 900  | 0.9862          |
+| 0.5494        | 2.5628 | 1000 | 0.9776          |
+| 0.5314        | 2.8191 | 1100 | 0.9726          |
+| 0.3521        | 3.0753 | 1200 | 1.0522          |
+| 0.3379        | 3.3316 | 1300 | 1.0573          |
+| 0.3875        | 3.5879 | 1400 | 1.0439          |
+| 0.346         | 3.8442 | 1500 | 1.0578          |
+| 0.2252        | 4.1005 | 1600 | 1.1292          |
+| 0.2271        | 4.3567 | 1700 | 1.1488          |
+| 0.2237        | 4.6130 | 1800 | 1.1526          |
+| 0.2199        | 4.8693 | 1900 | 1.1563          |
+| 0.1614        | 5.1256 | 2000 | 1.1665          |
+
+
+### 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/Llama-3-Open-Ko-8B-Instruct-preview",
+  "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": [
+    "gate_proj",
+    "o_proj",
+    "q_proj",
+    "v_proj",
+    "k_proj",
+    "down_proj",
+    "up_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:e6b86c4b24b96ce02c9d73099da443b1131cd4183ee42d217e498e94ab7b535a
+size 167832240

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce1430b14798b304275cfbd9868491942c1300a8b5a495c35627fac4c7b2ec1f
+size 5176