End of training

README.md

@@ -1,14 +1,14 @@
 ---
 library_name: peft
-license: llama3.2
-base_model: NousResearch/Llama-3.2-1B
+license: apache-2.0
+base_model: unsloth/Qwen2-0.5B
 tags:
 - axolotl
 - generated_from_trainer
 datasets:
-- Paladiso/dataset_92a8bc35-2c7a-4a62-8dca-171a04f7b68a
+- Paladiso/dataset_259fd7bc-d639-4f39-96d1-9a76d24779cd
 model-index:
-- name: 93339e35-d90e-4abc-91ca-7f238d662672
+- name: 7560d7db-9924-4dbb-83e4-b0ed0920f2df
   results: []
 ---
 
@@ -21,18 +21,18 @@ should probably proofread and complete it, then remove this comment. -->
 axolotl version: `0.6.0`
 ```yaml
 adapter: lora
-base_model: NousResearch/Llama-3.2-1B
+base_model: unsloth/Qwen2-0.5B
 bf16: auto
 chat_template: llama3
 dataset_prepared_path: /workspace/axolotl/data/prepared
 datasets:
 - ds_type: json
   format: custom
-  path: Paladiso/dataset_92a8bc35-2c7a-4a62-8dca-171a04f7b68a
+  path: Paladiso/dataset_259fd7bc-d639-4f39-96d1-9a76d24779cd
   type:
-    field_input: activity
-    field_instruction: topic
-    field_output: text
+    field_input: my_solu
+    field_instruction: prompt
+    field_output: solution
     system_format: '{system}'
     system_prompt: ''
 debug: null
@@ -48,7 +48,7 @@ fsdp_config: null
 gradient_accumulation_steps: 4
 gradient_checkpointing: false
 group_by_length: false
-hub_model_id: Paladiso/93339e35-d90e-4abc-91ca-7f238d662672
+hub_model_id: Paladiso/7560d7db-9924-4dbb-83e4-b0ed0920f2df
 hub_private_repo: true
 hub_repo: null
 hub_strategy: checkpoint
@@ -79,8 +79,6 @@ sample_packing: false
 save_safetensors: true
 saves_per_epoch: 4
 sequence_len: 512
-special_tokens:
-  pad_token: <|end_of_text|>
 strict: false
 tf32: false
 tokenizer_type: AutoTokenizer
@@ -90,10 +88,10 @@ use_accelerate: true
 val_set_size: 0.05
 wandb_entity: null
 wandb_mode: online
-wandb_name: 92a8bc35-2c7a-4a62-8dca-171a04f7b68a
+wandb_name: 259fd7bc-d639-4f39-96d1-9a76d24779cd
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
-wandb_runid: 92a8bc35-2c7a-4a62-8dca-171a04f7b68a
+wandb_runid: 259fd7bc-d639-4f39-96d1-9a76d24779cd
 warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
@@ -102,11 +100,11 @@ xformers_attention: null
 
 </details><br>
 
-# 93339e35-d90e-4abc-91ca-7f238d662672
+# 7560d7db-9924-4dbb-83e4-b0ed0920f2df
 
-This model is a fine-tuned version of [NousResearch/Llama-3.2-1B](https://huggingface.co/NousResearch/Llama-3.2-1B) on the Paladiso/dataset_92a8bc35-2c7a-4a62-8dca-171a04f7b68a dataset.
+This model is a fine-tuned version of [unsloth/Qwen2-0.5B](https://huggingface.co/unsloth/Qwen2-0.5B) on the Paladiso/dataset_259fd7bc-d639-4f39-96d1-9a76d24779cd dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.0217
+- Loss: 0.9505
 
 ## Model description
 
@@ -140,9 +138,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 2.2298        | 0.0014 | 3    | 2.2456          |
-| 2.1131        | 0.0028 | 6    | 2.1594          |
-| 2.0672        | 0.0042 | 9    | 2.0217          |
+| 1.2581        | 0.0001 | 3    | 1.0532          |
+| 1.048         | 0.0001 | 6    | 1.0108          |
+| 0.9347        | 0.0002 | 9    | 0.9505          |
 
 
 ### Framework versions