End of training

README.md

@@ -1,14 +1,14 @@
 ---
 library_name: peft
-license: cc-by-nc-4.0
-base_model: upstage/SOLAR-10.7B-Instruct-v1.0
+license: apache-2.0
+base_model: unsloth/Qwen2.5-0.5B
 tags:
 - axolotl
 - generated_from_trainer
 datasets:
-- Aivesa/dataset_e175057f-603d-4237-a78c-89fd13066a97
+- Aivesa/dataset_e393b615-2f4d-4521-8903-a1ed65df68c0
 model-index:
-- name: 358b7f6c-7cec-4ddc-9434-a0f91b26dc24
+- name: 266e0867-e9ae-4112-8a0e-1740587fcd13
   results: []
 ---
 
@@ -21,18 +21,17 @@ should probably proofread and complete it, then remove this comment. -->
 axolotl version: `0.6.0`
 ```yaml
 adapter: lora
-base_model: upstage/SOLAR-10.7B-Instruct-v1.0
+base_model: unsloth/Qwen2.5-0.5B
 bf16: auto
 chat_template: llama3
 dataset_prepared_path: /workspace/axolotl/data/prepared
 datasets:
 - ds_type: json
   format: custom
-  path: Aivesa/dataset_e175057f-603d-4237-a78c-89fd13066a97
+  path: Aivesa/dataset_e393b615-2f4d-4521-8903-a1ed65df68c0
   type:
-    field_input: platform
-    field_instruction: source
-    field_output: prompt
+    field_instruction: context
+    field_output: question
     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: Aivesa/358b7f6c-7cec-4ddc-9434-a0f91b26dc24
+hub_model_id: Aivesa/266e0867-e9ae-4112-8a0e-1740587fcd13
 hub_private_repo: true
 hub_repo: null
 hub_strategy: checkpoint
@@ -88,10 +87,10 @@ use_accelerate: true
 val_set_size: 0.05
 wandb_entity: null
 wandb_mode: online
-wandb_name: e175057f-603d-4237-a78c-89fd13066a97
+wandb_name: e393b615-2f4d-4521-8903-a1ed65df68c0
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
-wandb_runid: e175057f-603d-4237-a78c-89fd13066a97
+wandb_runid: e393b615-2f4d-4521-8903-a1ed65df68c0
 warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
@@ -100,11 +99,11 @@ xformers_attention: null
 
 </details><br>
 
-# 358b7f6c-7cec-4ddc-9434-a0f91b26dc24
+# 266e0867-e9ae-4112-8a0e-1740587fcd13
 
-This model is a fine-tuned version of [upstage/SOLAR-10.7B-Instruct-v1.0](https://huggingface.co/upstage/SOLAR-10.7B-Instruct-v1.0) on the Aivesa/dataset_e175057f-603d-4237-a78c-89fd13066a97 dataset.
+This model is a fine-tuned version of [unsloth/Qwen2.5-0.5B](https://huggingface.co/unsloth/Qwen2.5-0.5B) on the Aivesa/dataset_e393b615-2f4d-4521-8903-a1ed65df68c0 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.2440
+- Loss: 2.5342
 
 ## Model description
 
@@ -138,9 +137,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 2.6185        | 0.0504 | 3    | 2.6540          |
-| 2.4712        | 0.1008 | 6    | 2.3696          |
-| 2.2846        | 0.1513 | 9    | 2.2440          |
+| 2.7753        | 0.0131 | 3    | 3.0765          |
+| 2.9505        | 0.0262 | 6    | 2.8979          |
+| 2.6498        | 0.0393 | 9    | 2.5342          |
 
 
 ### Framework versions