End of training

README.md

@@ -0,0 +1,164 @@
+---
+library_name: peft
+license: llama3
+base_model: MLP-KTLim/llama-3-Korean-Bllossom-8B
+tags:
+- axolotl
+- generated_from_trainer
+model-index:
+- name: fbc6976a-2c63-4b02-ac57-9d6485244dc4
+  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. -->
+
+[<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl)
+<details><summary>See axolotl config</summary>
+
+axolotl version: `0.4.1`
+```yaml
+adapter: qlora
+auto_resume_from_checkpoints: true
+base_model: MLP-KTLim/llama-3-Korean-Bllossom-8B
+bf16: auto
+chat_template: llama3
+dataset_prepared_path: null
+dataset_processes: 6
+datasets:
+- data_files:
+  - 11a00e660a24742e_train_data.json
+  ds_type: json
+  format: custom
+  path: /workspace/input_data/11a00e660a24742e_train_data.json
+  type:
+    field_input: schema
+    field_instruction: question
+    field_output: cypher
+    format: '{instruction} {input}'
+    no_input_format: '{instruction}'
+    system_format: '{system}'
+    system_prompt: ''
+debug: null
+deepspeed: null
+early_stopping_patience: 3
+eval_max_new_tokens: 128
+eval_steps: 200
+eval_table_size: null
+evals_per_epoch: null
+flash_attention: true
+fp16: false
+fsdp: null
+fsdp_config: null
+gradient_accumulation_steps: 4
+gradient_checkpointing: true
+group_by_length: false
+hub_model_id: error577/fbc6976a-2c63-4b02-ac57-9d6485244dc4
+hub_repo: null
+hub_strategy: checkpoint
+hub_token: null
+learning_rate: 0.0002
+load_in_4bit: true
+load_in_8bit: false
+local_rank: null
+logging_steps: 1
+lora_alpha: 64
+lora_dropout: 0.1
+lora_fan_in_fan_out: null
+lora_model_dir: null
+lora_r: 32
+lora_target_linear: true
+lr_scheduler: cosine
+max_grad_norm: 1.0
+max_steps: null
+micro_batch_size: 2
+mlflow_experiment_name: /tmp/11a00e660a24742e_train_data.json
+model_type: AutoModelForCausalLM
+num_epochs: 3
+optimizer: adamw_bnb_8bit
+output_dir: miner_id_24
+pad_to_sequence_len: true
+resume_from_checkpoint: null
+s2_attention: null
+sample_packing: false
+save_steps: 200
+sequence_len: 128
+strict: false
+tf32: false
+tokenizer_type: AutoTokenizer
+train_on_inputs: false
+trust_remote_code: true
+val_set_size: 0.005
+wandb_entity: null
+wandb_mode: online
+wandb_name: c91f038a-3ced-453a-a510-5f8b367aab16
+wandb_project: Gradients-On-Demand
+wandb_run: your_name
+wandb_runid: c91f038a-3ced-453a-a510-5f8b367aab16
+warmup_steps: 30
+weight_decay: 0.0
+xformers_attention: null
+
+```
+
+</details><br>
+
+# fbc6976a-2c63-4b02-ac57-9d6485244dc4
+
+This model is a fine-tuned version of [MLP-KTLim/llama-3-Korean-Bllossom-8B](https://huggingface.co/MLP-KTLim/llama-3-Korean-Bllossom-8B) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1236
+
+## 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: 0.0002
+- train_batch_size: 2
+- eval_batch_size: 2
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 8
+- optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 30
+- num_epochs: 3
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 1.9934        | 0.0012 | 1    | 2.0208          |
+| 0.2588        | 0.2309 | 200  | 0.2275          |
+| 0.233         | 0.4619 | 400  | 0.1927          |
+| 0.2045        | 0.6928 | 600  | 0.1782          |
+| 0.2046        | 0.9238 | 800  | 0.1550          |
+| 0.123         | 1.1547 | 1000 | 0.1590          |
+| 0.0634        | 1.3857 | 1200 | 0.1254          |
+| 0.1132        | 1.6166 | 1400 | 0.1299          |
+| 0.0871        | 1.8476 | 1600 | 0.1193          |
+| 0.0306        | 2.0785 | 1800 | 0.1250          |
+| 0.0199        | 2.3095 | 2000 | 0.1275          |
+| 0.028         | 2.5404 | 2200 | 0.1236          |
+
+
+### Framework versions
+
+- PEFT 0.13.2
+- Transformers 4.46.0
+- Pytorch 2.5.0+cu124
+- Datasets 3.0.1
+- Tokenizers 0.20.1

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b2b1568a285868cdf2275549fab8143ae6e7bc25895d955db15aa359febd8c8
+size 335706186

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b74ba6f9e29db97fc90e486f0c1783a62ecc7d2714333c2aaeb33374411e6fd
+oid sha256:3f2a639c61ea17158b23b298bf4ab07ca6709c4daaa55769cec45534bd6b471b
 size 335604696