End of training

README.md

@@ -3,9 +3,9 @@ library_name: peft
 tags:
 - axolotl
 - generated_from_trainer
-base_model: oopsung/llama2-7b-n-ox-test-v1
+base_model: oopsung/llama2-7b-koNqa-test-v1
 model-index:
-- name: 695b6d76-a4f0-4d1e-b337-f6d87e10453d
+- name: 7cf75911-52d7-4b9f-b49f-422caa1e3165
   results: []
 ---
 
@@ -18,19 +18,19 @@ should probably proofread and complete it, then remove this comment. -->
 axolotl version: `0.4.1`
 ```yaml
 adapter: lora
-base_model: oopsung/llama2-7b-n-ox-test-v1
+base_model: oopsung/llama2-7b-koNqa-test-v1
 bf16: auto
 datasets:
 - data_files:
-  - 35ca5ef06350813d_train_data.json
+  - b1db72b837c3bf33_train_data.json
   ds_type: json
   format: custom
-  path: 35ca5ef06350813d_train_data.json
+  path: b1db72b837c3bf33_train_data.json
   type:
     field: null
     field_input: null
-    field_instruction: instruction
-    field_output: output
+    field_instruction: question
+    field_output: query
     field_system: null
     format: null
     no_input_format: null
@@ -50,7 +50,7 @@ fsdp_config: null
 gradient_accumulation_steps: 4
 gradient_checkpointing: true
 group_by_length: false
-hub_model_id: FatCat87/695b6d76-a4f0-4d1e-b337-f6d87e10453d
+hub_model_id: FatCat87/7cf75911-52d7-4b9f-b49f-422caa1e3165
 learning_rate: 0.0002
 load_in_4bit: false
 load_in_8bit: true
@@ -81,9 +81,9 @@ val_set_size: 0.1
 wandb_entity: fatcat87-taopanda
 wandb_log_model: null
 wandb_mode: online
-wandb_name: 695b6d76-a4f0-4d1e-b337-f6d87e10453d
+wandb_name: 7cf75911-52d7-4b9f-b49f-422caa1e3165
 wandb_project: subnet56
-wandb_runid: 695b6d76-a4f0-4d1e-b337-f6d87e10453d
+wandb_runid: 7cf75911-52d7-4b9f-b49f-422caa1e3165
 wandb_watch: null
 warmup_ratio: 0.05
 weight_decay: 0.0
@@ -93,12 +93,12 @@ xformers_attention: null
 
 </details><br>
 
-[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/fatcat87-taopanda/subnet56/runs/euufo96d)
-# 695b6d76-a4f0-4d1e-b337-f6d87e10453d
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/fatcat87-taopanda/subnet56/runs/ni7922kd)
+# 7cf75911-52d7-4b9f-b49f-422caa1e3165
 
-This model is a fine-tuned version of [oopsung/llama2-7b-n-ox-test-v1](https://huggingface.co/oopsung/llama2-7b-n-ox-test-v1) on the None dataset.
+This model is a fine-tuned version of [oopsung/llama2-7b-koNqa-test-v1](https://huggingface.co/oopsung/llama2-7b-koNqa-test-v1) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.0870
+- Loss: 2.3653
 
 ## Model description
 
@@ -128,17 +128,15 @@ The following hyperparameters were used during training:
 - total_eval_batch_size: 4
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine
-- lr_scheduler_warmup_steps: 2
 - num_epochs: 1
 
 ### Training results
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 2.8009        | 0.0331 | 1    | 2.9392          |
-| 2.309         | 0.2645 | 8    | 2.3503          |
-| 2.2402        | 0.5289 | 16   | 2.1435          |
-| 2.1873        | 0.7934 | 24   | 2.0870          |
+| 2.6121        | 0.1739 | 1    | 3.0362          |
+| 2.6016        | 0.3478 | 2    | 2.7754          |
+| 2.088         | 0.6957 | 4    | 2.3653          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab4f52457a073d6ac822788e123aea2637035d6f1e06680bd9c795f3e5da993d
+oid sha256:9de5d782948a6513fedc80c0d95e8fe0a085689c42d8b95dbcbb6db0a57e9c55
 size 319977674