End of training

README.md

@@ -1,13 +1,14 @@
 ---
 library_name: peft
-base_model: jhflow/mistral7b-lora-multi-turn-v2
+license: apache-2.0
+base_model: unsloth/Qwen2-7B
 tags:
 - axolotl
 - generated_from_trainer
 datasets:
-- Aivesa/dataset_d971ef8e-ddfc-4982-8273-bc0a7fdf9c0b
+- Aivesa/dataset_984452ef-f0ae-4611-869e-6f45e5e33123
 model-index:
-- name: 0830c1be-3e13-4080-983f-4615af87dcf0
+- name: c1064ea8-7730-47b6-9dda-8e0841c9194d
   results: []
 ---
 
@@ -20,17 +21,18 @@ should probably proofread and complete it, then remove this comment. -->
 axolotl version: `0.6.0`
 ```yaml
 adapter: lora
-base_model: jhflow/mistral7b-lora-multi-turn-v2
+base_model: unsloth/Qwen2-7B
 bf16: auto
 chat_template: llama3
 dataset_prepared_path: /workspace/axolotl/data/prepared
 datasets:
 - ds_type: json
   format: custom
-  path: Aivesa/dataset_d971ef8e-ddfc-4982-8273-bc0a7fdf9c0b
+  path: Aivesa/dataset_984452ef-f0ae-4611-869e-6f45e5e33123
   type:
-    field_instruction: title
-    field_output: content
+    field_input: original_question
+    field_instruction: question
+    field_output: solution
     system_format: '{system}'
     system_prompt: ''
 debug: null
@@ -46,7 +48,7 @@ fsdp_config: null
 gradient_accumulation_steps: 4
 gradient_checkpointing: false
 group_by_length: false
-hub_model_id: Aivesa/0830c1be-3e13-4080-983f-4615af87dcf0
+hub_model_id: Aivesa/c1064ea8-7730-47b6-9dda-8e0841c9194d
 hub_private_repo: true
 hub_repo: null
 hub_strategy: checkpoint
@@ -86,10 +88,10 @@ use_accelerate: true
 val_set_size: 0.05
 wandb_entity: null
 wandb_mode: online
-wandb_name: d971ef8e-ddfc-4982-8273-bc0a7fdf9c0b
+wandb_name: 984452ef-f0ae-4611-869e-6f45e5e33123
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
-wandb_runid: d971ef8e-ddfc-4982-8273-bc0a7fdf9c0b
+wandb_runid: 984452ef-f0ae-4611-869e-6f45e5e33123
 warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
@@ -98,11 +100,11 @@ xformers_attention: null
 
 </details><br>
 
-# 0830c1be-3e13-4080-983f-4615af87dcf0
+# c1064ea8-7730-47b6-9dda-8e0841c9194d
 
-This model is a fine-tuned version of [jhflow/mistral7b-lora-multi-turn-v2](https://huggingface.co/jhflow/mistral7b-lora-multi-turn-v2) on the Aivesa/dataset_d971ef8e-ddfc-4982-8273-bc0a7fdf9c0b dataset.
+This model is a fine-tuned version of [unsloth/Qwen2-7B](https://huggingface.co/unsloth/Qwen2-7B) on the Aivesa/dataset_984452ef-f0ae-4611-869e-6f45e5e33123 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.2284
+- Loss: 0.2935
 
 ## Model description
 
@@ -136,9 +138,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 9.552         | 0.0013 | 3    | 2.2880          |
-| 8.5972        | 0.0026 | 6    | 2.2492          |
-| 9.1434        | 0.0038 | 9    | 2.2284          |
+| 0.2573        | 0.0066 | 3    | 0.3362          |
+| 0.3052        | 0.0133 | 6    | 0.3171          |
+| 0.2834        | 0.0199 | 9    | 0.2935          |
 
 
 ### Framework versions