End of training

README.md

@@ -1,14 +1,14 @@
 ---
 library_name: peft
-license: llama3
-base_model: elyza/Llama-3-ELYZA-JP-8B
+license: apache-2.0
+base_model: unsloth/SmolLM2-1.7B-Instruct
 tags:
 - axolotl
 - generated_from_trainer
 datasets:
-- Aivesa/dataset_bdc5d8b7-c291-4772-a9f7-28e2904ac8b5
+- Aivesa/dataset_cc7b5f3d-eecb-4daa-9844-bd4974fc68db
 model-index:
-- name: 434a68e1-d75e-4689-8d0a-bd66ca606b4d
+- name: 9cfa6bee-9b15-49d8-a539-cea54d4e60b7
   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: elyza/Llama-3-ELYZA-JP-8B
+base_model: unsloth/SmolLM2-1.7B-Instruct
 bf16: auto
 chat_template: llama3
 dataset_prepared_path: /workspace/axolotl/data/prepared
 datasets:
 - ds_type: json
   format: custom
-  path: Aivesa/dataset_bdc5d8b7-c291-4772-a9f7-28e2904ac8b5
+  path: Aivesa/dataset_cc7b5f3d-eecb-4daa-9844-bd4974fc68db
   type:
-    field_instruction: question
-    field_output: answer
+    field_instruction: text
+    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/434a68e1-d75e-4689-8d0a-bd66ca606b4d
+hub_model_id: Aivesa/9cfa6bee-9b15-49d8-a539-cea54d4e60b7
 hub_private_repo: true
 hub_repo: null
 hub_strategy: checkpoint
@@ -78,8 +78,6 @@ sample_packing: false
 save_safetensors: true
 saves_per_epoch: 4
 sequence_len: 512
-special_tokens:
-  pad_token: <|eot_id|>
 strict: false
 tf32: false
 tokenizer_type: AutoTokenizer
@@ -89,10 +87,10 @@ use_accelerate: true
 val_set_size: 0.05
 wandb_entity: null
 wandb_mode: online
-wandb_name: bdc5d8b7-c291-4772-a9f7-28e2904ac8b5
+wandb_name: cc7b5f3d-eecb-4daa-9844-bd4974fc68db
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
-wandb_runid: bdc5d8b7-c291-4772-a9f7-28e2904ac8b5
+wandb_runid: cc7b5f3d-eecb-4daa-9844-bd4974fc68db
 warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
@@ -101,11 +99,11 @@ xformers_attention: null
 
 </details><br>
 
-# 434a68e1-d75e-4689-8d0a-bd66ca606b4d
+# 9cfa6bee-9b15-49d8-a539-cea54d4e60b7
 
-This model is a fine-tuned version of [elyza/Llama-3-ELYZA-JP-8B](https://huggingface.co/elyza/Llama-3-ELYZA-JP-8B) on the Aivesa/dataset_bdc5d8b7-c291-4772-a9f7-28e2904ac8b5 dataset.
+This model is a fine-tuned version of [unsloth/SmolLM2-1.7B-Instruct](https://huggingface.co/unsloth/SmolLM2-1.7B-Instruct) on the Aivesa/dataset_cc7b5f3d-eecb-4daa-9844-bd4974fc68db dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.2094
+- Loss: 1.2979
 
 ## Model description
 
@@ -139,9 +137,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 2.3553        | 0.0051 | 3    | 2.4666          |
-| 2.5075        | 0.0101 | 6    | 2.4014          |
-| 2.7115        | 0.0152 | 9    | 2.2094          |
+| 1.3508        | 0.0055 | 3    | 1.3070          |
+| 1.1703        | 0.0110 | 6    | 1.3050          |
+| 1.1769        | 0.0165 | 9    | 1.2979          |
 
 
 ### Framework versions