End of training

README.md

@@ -1,14 +1,14 @@
 ---
 library_name: peft
-license: apache-2.0
-base_model: unsloth/Qwen2-0.5B
+license: llama3.2
+base_model: NousResearch/Llama-3.2-1B
 tags:
 - axolotl
 - generated_from_trainer
 datasets:
-- Paladiso/dataset_259fd7bc-d639-4f39-96d1-9a76d24779cd
+- Paladiso/dataset_1bf2f8e1-ac8b-46d1-ad4c-485628fd6876
 model-index:
-- name: 4b6ed69e-2443-47fc-8caf-8b37adfc9ba9
+- name: 69dbc3dd-1016-41b9-8587-11fb54d74c38
   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: unsloth/Qwen2-0.5B
+base_model: NousResearch/Llama-3.2-1B
 bf16: auto
 chat_template: llama3
 dataset_prepared_path: /workspace/axolotl/data/prepared
 datasets:
 - ds_type: json
   format: custom
-  path: Paladiso/dataset_259fd7bc-d639-4f39-96d1-9a76d24779cd
+  path: Paladiso/dataset_1bf2f8e1-ac8b-46d1-ad4c-485628fd6876
   type:
-    field_input: my_solu
-    field_instruction: prompt
-    field_output: solution
+    field_instruction: intent
+    field_output: snippet
     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: Paladiso/4b6ed69e-2443-47fc-8caf-8b37adfc9ba9
+hub_model_id: Paladiso/69dbc3dd-1016-41b9-8587-11fb54d74c38
 hub_private_repo: true
 hub_repo: null
 hub_strategy: checkpoint
@@ -79,6 +78,8 @@ 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
@@ -88,10 +89,10 @@ use_accelerate: true
 val_set_size: 0.05
 wandb_entity: null
 wandb_mode: online
-wandb_name: 259fd7bc-d639-4f39-96d1-9a76d24779cd
+wandb_name: 1bf2f8e1-ac8b-46d1-ad4c-485628fd6876
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
-wandb_runid: 259fd7bc-d639-4f39-96d1-9a76d24779cd
+wandb_runid: 1bf2f8e1-ac8b-46d1-ad4c-485628fd6876
 warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
@@ -100,11 +101,11 @@ xformers_attention: null
 
 </details><br>
 
-# 4b6ed69e-2443-47fc-8caf-8b37adfc9ba9
+# 69dbc3dd-1016-41b9-8587-11fb54d74c38
 
-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.
+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_1bf2f8e1-ac8b-46d1-ad4c-485628fd6876 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.9491
+- Loss: 2.6703
 
 ## Model description
 
@@ -138,9 +139,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 1.2592        | 0.0001 | 3    | 1.0529          |
-| 1.0489        | 0.0001 | 6    | 1.0084          |
-| 0.9325        | 0.0002 | 9    | 0.9491          |
+| 3.3628        | 0.0094 | 3    | 3.4313          |
+| 3.5282        | 0.0189 | 6    | 3.2452          |
+| 2.6317        | 0.0283 | 9    | 2.6703          |
 
 
 ### Framework versions