End of training

README.md

@@ -1,14 +1,13 @@
 ---
 library_name: peft
-license: apache-2.0
-base_model: unsloth/Qwen2.5-0.5B
+base_model: katuni4ka/tiny-random-olmo-hf
 tags:
 - axolotl
 - generated_from_trainer
 datasets:
-- Aivesa/dataset_e393b615-2f4d-4521-8903-a1ed65df68c0
+- Aivesa/dataset_b612b32f-2e8a-4d95-ac6f-83bff6bbaa8a
 model-index:
-- name: 266e0867-e9ae-4112-8a0e-1740587fcd13
+- name: 56e71944-03bc-453e-9069-74558ea663d2
   results: []
 ---
 
@@ -21,17 +20,18 @@ should probably proofread and complete it, then remove this comment. -->
 axolotl version: `0.6.0`
 ```yaml
 adapter: lora
-base_model: unsloth/Qwen2.5-0.5B
+base_model: katuni4ka/tiny-random-olmo-hf
 bf16: auto
 chat_template: llama3
 dataset_prepared_path: /workspace/axolotl/data/prepared
 datasets:
 - ds_type: json
   format: custom
-  path: Aivesa/dataset_e393b615-2f4d-4521-8903-a1ed65df68c0
+  path: Aivesa/dataset_b612b32f-2e8a-4d95-ac6f-83bff6bbaa8a
   type:
-    field_instruction: context
-    field_output: question
+    field_input: input
+    field_instruction: instruction
+    field_output: output
     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/266e0867-e9ae-4112-8a0e-1740587fcd13
+hub_model_id: Aivesa/56e71944-03bc-453e-9069-74558ea663d2
 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: e393b615-2f4d-4521-8903-a1ed65df68c0
+wandb_name: b612b32f-2e8a-4d95-ac6f-83bff6bbaa8a
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
-wandb_runid: e393b615-2f4d-4521-8903-a1ed65df68c0
+wandb_runid: b612b32f-2e8a-4d95-ac6f-83bff6bbaa8a
 warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
@@ -99,11 +99,11 @@ xformers_attention: null
 
 </details><br>
 
-# 266e0867-e9ae-4112-8a0e-1740587fcd13
+# 56e71944-03bc-453e-9069-74558ea663d2
 
-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.
+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.
 It achieves the following results on the evaluation set:
-- Loss: 2.5342
+- Loss: 10.8313
 
 ## Model description
 
@@ -137,9 +137,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 2.7753        | 0.0131 | 3    | 3.0765          |
-| 2.9505        | 0.0262 | 6    | 2.8979          |
-| 2.6498        | 0.0393 | 9    | 2.5342          |
+| 10.8353       | 0.0000 | 3    | 10.8337         |
+| 10.84         | 0.0001 | 6    | 10.8328         |
+| 10.8244       | 0.0001 | 9    | 10.8313         |
 
 
 ### Framework versions