End of training

README.md

@@ -1,14 +1,13 @@
 ---
 library_name: peft
-license: apache-2.0
-base_model: beomi/polyglot-ko-12.8b-safetensors
+base_model: katuni4ka/tiny-random-qwen1.5-moe
 tags:
 - axolotl
 - generated_from_trainer
 datasets:
-- Aivesa/dataset_4f03d256-fb4b-43bb-b945-88a8c88f6053
+- Aivesa/dataset_5e3967ba-d17c-4d93-91ec-a23620abb5dc
 model-index:
-- name: c3bfce47-44b2-4c1d-8e66-2dd2057825e1
+- name: 7aaa2460-6f85-4864-89e1-417e92d9df67
   results: []
 ---
 
@@ -21,16 +20,15 @@ should probably proofread and complete it, then remove this comment. -->
 axolotl version: `0.6.0`
 ```yaml
 adapter: lora
-base_model: beomi/polyglot-ko-12.8b-safetensors
+base_model: katuni4ka/tiny-random-qwen1.5-moe
 bf16: auto
 chat_template: llama3
 dataset_prepared_path: /workspace/axolotl/data/prepared
 datasets:
 - ds_type: json
   format: custom
-  path: Aivesa/dataset_4f03d256-fb4b-43bb-b945-88a8c88f6053
+  path: Aivesa/dataset_5e3967ba-d17c-4d93-91ec-a23620abb5dc
   type:
-    field_input: ''
     field_instruction: instruction
     field_output: output
     system_format: '{system}'
@@ -48,7 +46,7 @@ fsdp_config: null
 gradient_accumulation_steps: 4
 gradient_checkpointing: false
 group_by_length: false
-hub_model_id: Aivesa/c3bfce47-44b2-4c1d-8e66-2dd2057825e1
+hub_model_id: Aivesa/7aaa2460-6f85-4864-89e1-417e92d9df67
 hub_private_repo: true
 hub_repo: null
 hub_strategy: checkpoint
@@ -88,10 +86,10 @@ use_accelerate: true
 val_set_size: 0.05
 wandb_entity: null
 wandb_mode: online
-wandb_name: 4f03d256-fb4b-43bb-b945-88a8c88f6053
+wandb_name: 5e3967ba-d17c-4d93-91ec-a23620abb5dc
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
-wandb_runid: 4f03d256-fb4b-43bb-b945-88a8c88f6053
+wandb_runid: 5e3967ba-d17c-4d93-91ec-a23620abb5dc
 warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
@@ -100,11 +98,11 @@ xformers_attention: null
 
 </details><br>
 
-# c3bfce47-44b2-4c1d-8e66-2dd2057825e1
+# 7aaa2460-6f85-4864-89e1-417e92d9df67
 
-This model is a fine-tuned version of [beomi/polyglot-ko-12.8b-safetensors](https://huggingface.co/beomi/polyglot-ko-12.8b-safetensors) on the Aivesa/dataset_4f03d256-fb4b-43bb-b945-88a8c88f6053 dataset.
+This model is a fine-tuned version of [katuni4ka/tiny-random-qwen1.5-moe](https://huggingface.co/katuni4ka/tiny-random-qwen1.5-moe) on the Aivesa/dataset_5e3967ba-d17c-4d93-91ec-a23620abb5dc dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.1381
+- Loss: 11.9365
 
 ## Model description
 
@@ -138,9 +136,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 8.6748        | 0.0005 | 3    | 2.1950          |
-| 8.7484        | 0.0010 | 6    | 2.1873          |
-| 7.6001        | 0.0015 | 9    | 2.1381          |
+| 11.9333       | 0.0002 | 3    | 11.9376         |
+| 11.9358       | 0.0004 | 6    | 11.9372         |
+| 11.9334       | 0.0007 | 9    | 11.9365         |
 
 
 ### Framework versions