End of training

README.md

@@ -1,14 +1,14 @@
 ---
 library_name: peft
-license: mit
-base_model: fxmarty/tiny-dummy-qwen2
+license: apache-2.0
+base_model: unsloth/Qwen2-0.5B-Instruct
 tags:
 - axolotl
 - generated_from_trainer
 datasets:
-- Aivesa/dataset_354d40c7-91f2-4ebd-87a1-e6e2ca96f021
+- Aivesa/dataset_7c40032f-e667-40ad-9658-3748512bf15b
 model-index:
-- name: a3f90d10-5451-49eb-b19d-e4df5e870acd
+- name: 3b45a5fe-37d5-4baa-91e1-1c813f38b31a
   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: fxmarty/tiny-dummy-qwen2
+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_354d40c7-91f2-4ebd-87a1-e6e2ca96f021
+  path: Aivesa/dataset_7c40032f-e667-40ad-9658-3748512bf15b
   type:
-    field_instruction: tokens
-    field_output: text
+    field_instruction: sentence1
+    field_output: sentence2
     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/a3f90d10-5451-49eb-b19d-e4df5e870acd
+hub_model_id: Aivesa/3b45a5fe-37d5-4baa-91e1-1c813f38b31a
 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: 354d40c7-91f2-4ebd-87a1-e6e2ca96f021
+wandb_name: 7c40032f-e667-40ad-9658-3748512bf15b
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
-wandb_runid: 354d40c7-91f2-4ebd-87a1-e6e2ca96f021
+wandb_runid: 7c40032f-e667-40ad-9658-3748512bf15b
 warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
@@ -99,11 +99,11 @@ xformers_attention: null
 
 </details><br>
 
-# a3f90d10-5451-49eb-b19d-e4df5e870acd
+# 3b45a5fe-37d5-4baa-91e1-1c813f38b31a
 
-This model is a fine-tuned version of [fxmarty/tiny-dummy-qwen2](https://huggingface.co/fxmarty/tiny-dummy-qwen2) on the Aivesa/dataset_354d40c7-91f2-4ebd-87a1-e6e2ca96f021 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_7c40032f-e667-40ad-9658-3748512bf15b dataset.
 It achieves the following results on the evaluation set:
-- Loss: 11.9316
+- Loss: 3.1446
 
 ## Model description
 
@@ -137,9 +137,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 11.9331       | 0.0046 | 3    | 11.9318         |
-| 11.9245       | 0.0092 | 6    | 11.9317         |
-| 11.9364       | 0.0138 | 9    | 11.9316         |
+| 3.7803        | 0.0030 | 3    | 3.5993          |
+| 2.9619        | 0.0060 | 6    | 3.4711          |
+| 3.3801        | 0.0090 | 9    | 3.1446          |
 
 
 ### Framework versions