End of training

README.md

@@ -1,13 +1,14 @@
 ---
 library_name: peft
-base_model: katuni4ka/tiny-random-olmo-hf
+license: apache-2.0
+base_model: Qwen/Qwen2.5-0.5B
 tags:
 - axolotl
 - generated_from_trainer
 datasets:
-- Aivesa/dataset_b612b32f-2e8a-4d95-ac6f-83bff6bbaa8a
+- Aivesa/dataset_e5909454-6ee7-43b0-bc21-d6fa723e34ec
 model-index:
-- name: 01fd184e-358d-4205-bb98-a4b572b0ef4b
+- name: 14faec3b-678a-4b3e-a3e7-95067cb131aa
   results: []
 ---
 
@@ -20,18 +21,17 @@ should probably proofread and complete it, then remove this comment. -->
 axolotl version: `0.6.0`
 ```yaml
 adapter: lora
-base_model: katuni4ka/tiny-random-olmo-hf
+base_model: Qwen/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_b612b32f-2e8a-4d95-ac6f-83bff6bbaa8a
+  path: Aivesa/dataset_e5909454-6ee7-43b0-bc21-d6fa723e34ec
   type:
-    field_input: input
     field_instruction: instruction
-    field_output: output
+    field_output: response
     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/01fd184e-358d-4205-bb98-a4b572b0ef4b
+hub_model_id: Aivesa/14faec3b-678a-4b3e-a3e7-95067cb131aa
 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: b612b32f-2e8a-4d95-ac6f-83bff6bbaa8a
+wandb_name: e5909454-6ee7-43b0-bc21-d6fa723e34ec
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
-wandb_runid: b612b32f-2e8a-4d95-ac6f-83bff6bbaa8a
+wandb_runid: e5909454-6ee7-43b0-bc21-d6fa723e34ec
 warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
@@ -99,11 +99,11 @@ xformers_attention: null
 
 </details><br>
 
-# 01fd184e-358d-4205-bb98-a4b572b0ef4b
+# 14faec3b-678a-4b3e-a3e7-95067cb131aa
 
-This model is a fine-tuned version of [katuni4ka/tiny-random-olmo-hf](https://huggingface.co/katuni4ka/tiny-random-olmo-hf) on the Aivesa/dataset_b612b32f-2e8a-4d95-ac6f-83bff6bbaa8a dataset.
+This model is a fine-tuned version of [Qwen/Qwen2.5-0.5B](https://huggingface.co/Qwen/Qwen2.5-0.5B) on the Aivesa/dataset_e5909454-6ee7-43b0-bc21-d6fa723e34ec dataset.
 It achieves the following results on the evaluation set:
-- Loss: 10.8309
+- Loss: 1.5795
 
 ## Model description
 
@@ -137,9 +137,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 10.8353       | 0.0000 | 3    | 10.8337         |
-| 10.8399       | 0.0001 | 6    | 10.8327         |
-| 10.8241       | 0.0001 | 9    | 10.8309         |
+| 1.6945        | 0.0036 | 3    | 1.6561          |
+| 1.2122        | 0.0071 | 6    | 1.6313          |
+| 1.7996        | 0.0107 | 9    | 1.5795          |
 
 
 ### Framework versions