End of training

README.md

@@ -1,14 +1,13 @@
 ---
 library_name: peft
-license: apache-2.0
-base_model: openlm-research/open_llama_3b
+base_model: Korabbit/llama-2-ko-7b
 tags:
 - axolotl
 - generated_from_trainer
 datasets:
-- Paladiso/dataset_b98c9df0-5280-40e9-9125-37aafc6279e9
+- Paladiso/dataset_6f876187-6d0a-4410-b9c7-16623cec1fad
 model-index:
-- name: 369db93c-b0b2-4862-895e-e55b2f44da91
+- name: 30353663-cac7-44d6-a6f6-fbfa5b116bba
   results: []
 ---
 
@@ -21,18 +20,18 @@ should probably proofread and complete it, then remove this comment. -->
 axolotl version: `0.6.0`
 ```yaml
 adapter: lora
-base_model: openlm-research/open_llama_3b
+base_model: Korabbit/llama-2-ko-7b
 bf16: auto
 chat_template: llama3
 dataset_prepared_path: /workspace/axolotl/data/prepared
 datasets:
 - ds_type: json
   format: custom
-  path: Paladiso/dataset_b98c9df0-5280-40e9-9125-37aafc6279e9
+  path: Paladiso/dataset_6f876187-6d0a-4410-b9c7-16623cec1fad
   type:
-    field_input: sentence1
-    field_instruction: genre
-    field_output: sentence2
+    field_input: Description
+    field_instruction: Prompt
+    field_output: GT
     system_format: '{system}'
     system_prompt: ''
 debug: null
@@ -48,7 +47,7 @@ fsdp_config: null
 gradient_accumulation_steps: 4
 gradient_checkpointing: false
 group_by_length: false
-hub_model_id: Paladiso/369db93c-b0b2-4862-895e-e55b2f44da91
+hub_model_id: Paladiso/30353663-cac7-44d6-a6f6-fbfa5b116bba
 hub_private_repo: true
 hub_repo: null
 hub_strategy: checkpoint
@@ -90,10 +89,10 @@ use_accelerate: true
 val_set_size: 0.05
 wandb_entity: null
 wandb_mode: online
-wandb_name: b98c9df0-5280-40e9-9125-37aafc6279e9
+wandb_name: 6f876187-6d0a-4410-b9c7-16623cec1fad
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
-wandb_runid: b98c9df0-5280-40e9-9125-37aafc6279e9
+wandb_runid: 6f876187-6d0a-4410-b9c7-16623cec1fad
 warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
@@ -102,11 +101,11 @@ xformers_attention: null
 
 </details><br>
 
-# 369db93c-b0b2-4862-895e-e55b2f44da91
+# 30353663-cac7-44d6-a6f6-fbfa5b116bba
 
-This model is a fine-tuned version of [openlm-research/open_llama_3b](https://huggingface.co/openlm-research/open_llama_3b) on the Paladiso/dataset_b98c9df0-5280-40e9-9125-37aafc6279e9 dataset.
+This model is a fine-tuned version of [Korabbit/llama-2-ko-7b](https://huggingface.co/Korabbit/llama-2-ko-7b) on the Paladiso/dataset_6f876187-6d0a-4410-b9c7-16623cec1fad dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.9400
+- Loss: 0.7657
 
 ## Model description
 
@@ -140,9 +139,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 0.9502        | 0.0030 | 3    | 1.0558          |
-| 1.1032        | 0.0060 | 6    | 1.0392          |
-| 0.9992        | 0.0090 | 9    | 0.9400          |
+| 6.9731        | 0.0110 | 3    | 6.6195          |
+| 4.871         | 0.0220 | 6    | 3.0740          |
+| 1.0696        | 0.0329 | 9    | 0.7657          |
 
 
 ### Framework versions