End of training

README.md

@@ -1,14 +1,14 @@
 ---
 library_name: peft
-license: llama3
-base_model: aisingapore/llama3-8b-cpt-sea-lionv2.1-instruct
+license: apache-2.0
+base_model: unsloth/Qwen2-0.5B-Instruct
 tags:
 - axolotl
 - generated_from_trainer
 datasets:
-- Aivesa/dataset_f46a633e-74e3-4ffd-b2da-ea6aceb33f22
+- Aivesa/dataset_fdd2902e-b68a-478a-8c73-81802471323d
 model-index:
-- name: bf77e967-7d63-4cd2-a62f-a46597c3c55c
+- name: 38f5cfa4-d2db-44cd-9dae-55988102a590
   results: []
 ---
 
@@ -21,17 +21,17 @@ should probably proofread and complete it, then remove this comment. -->
 axolotl version: `0.6.0`
 ```yaml
 adapter: lora
-base_model: aisingapore/llama3-8b-cpt-sea-lionv2.1-instruct
+base_model: unsloth/Qwen2-0.5B-Instruct
 bf16: auto
 chat_template: llama3
 dataset_prepared_path: /workspace/axolotl/data/prepared
 datasets:
 - ds_type: json
   format: custom
-  path: Aivesa/dataset_f46a633e-74e3-4ffd-b2da-ea6aceb33f22
+  path: Aivesa/dataset_fdd2902e-b68a-478a-8c73-81802471323d
   type:
-    field_instruction: question
-    field_output: reference_answer
+    field_instruction: prompt
+    field_output: chosen
     system_format: '{system}'
     system_prompt: ''
 debug: null
@@ -47,7 +47,7 @@ fsdp_config: null
 gradient_accumulation_steps: 4
 gradient_checkpointing: false
 group_by_length: false
-hub_model_id: Aivesa/bf77e967-7d63-4cd2-a62f-a46597c3c55c
+hub_model_id: Aivesa/38f5cfa4-d2db-44cd-9dae-55988102a590
 hub_private_repo: true
 hub_repo: null
 hub_strategy: checkpoint
@@ -87,10 +87,10 @@ use_accelerate: true
 val_set_size: 0.05
 wandb_entity: null
 wandb_mode: online
-wandb_name: f46a633e-74e3-4ffd-b2da-ea6aceb33f22
+wandb_name: fdd2902e-b68a-478a-8c73-81802471323d
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
-wandb_runid: f46a633e-74e3-4ffd-b2da-ea6aceb33f22
+wandb_runid: fdd2902e-b68a-478a-8c73-81802471323d
 warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
@@ -99,11 +99,11 @@ xformers_attention: null
 
 </details><br>
 
-# bf77e967-7d63-4cd2-a62f-a46597c3c55c
+# 38f5cfa4-d2db-44cd-9dae-55988102a590
 
-This model is a fine-tuned version of [aisingapore/llama3-8b-cpt-sea-lionv2.1-instruct](https://huggingface.co/aisingapore/llama3-8b-cpt-sea-lionv2.1-instruct) on the Aivesa/dataset_f46a633e-74e3-4ffd-b2da-ea6aceb33f22 dataset.
+This model is a fine-tuned version of [unsloth/Qwen2-0.5B-Instruct](https://huggingface.co/unsloth/Qwen2-0.5B-Instruct) on the Aivesa/dataset_fdd2902e-b68a-478a-8c73-81802471323d dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.5762
+- Loss: 2.6926
 
 ## Model description
 
@@ -137,9 +137,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 4.9581        | 0.0051 | 3    | 4.6766          |
-| 3.7444        | 0.0101 | 6    | 4.1615          |
-| 2.7246        | 0.0152 | 9    | 2.5762          |
+| 2.7649        | 0.0042 | 3    | 3.1153          |
+| 3.1474        | 0.0083 | 6    | 2.9960          |
+| 2.6516        | 0.0125 | 9    | 2.6926          |
 
 
 ### Framework versions