End of training

README.md

@@ -1,13 +1,14 @@
 ---
 library_name: peft
-base_model: Korabbit/llama-2-ko-7b
+license: apache-2.0
+base_model: echarlaix/tiny-random-mistral
 tags:
 - axolotl
 - generated_from_trainer
 datasets:
-- Paladiso/dataset_6f876187-6d0a-4410-b9c7-16623cec1fad
+- Paladiso/dataset_c2294ea4-f15b-4e48-866d-856c7fe6510b
 model-index:
-- name: 30353663-cac7-44d6-a6f6-fbfa5b116bba
+- name: fd53c9e8-b6ee-4f33-ac83-e5ccb83c294c
   results: []
 ---
 
@@ -20,18 +21,18 @@ should probably proofread and complete it, then remove this comment. -->
 axolotl version: `0.6.0`
 ```yaml
 adapter: lora
-base_model: Korabbit/llama-2-ko-7b
+base_model: echarlaix/tiny-random-mistral
 bf16: auto
 chat_template: llama3
 dataset_prepared_path: /workspace/axolotl/data/prepared
 datasets:
 - ds_type: json
   format: custom
-  path: Paladiso/dataset_6f876187-6d0a-4410-b9c7-16623cec1fad
+  path: Paladiso/dataset_c2294ea4-f15b-4e48-866d-856c7fe6510b
   type:
-    field_input: Description
-    field_instruction: Prompt
-    field_output: GT
+    field_input: answer
+    field_instruction: problem
+    field_output: generated_solution
     system_format: '{system}'
     system_prompt: ''
 debug: null
@@ -47,7 +48,7 @@ fsdp_config: null
 gradient_accumulation_steps: 4
 gradient_checkpointing: false
 group_by_length: false
-hub_model_id: Paladiso/30353663-cac7-44d6-a6f6-fbfa5b116bba
+hub_model_id: Paladiso/fd53c9e8-b6ee-4f33-ac83-e5ccb83c294c
 hub_private_repo: true
 hub_repo: null
 hub_strategy: checkpoint
@@ -89,10 +90,10 @@ use_accelerate: true
 val_set_size: 0.05
 wandb_entity: null
 wandb_mode: online
-wandb_name: 6f876187-6d0a-4410-b9c7-16623cec1fad
+wandb_name: c2294ea4-f15b-4e48-866d-856c7fe6510b
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
-wandb_runid: 6f876187-6d0a-4410-b9c7-16623cec1fad
+wandb_runid: c2294ea4-f15b-4e48-866d-856c7fe6510b
 warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
@@ -101,11 +102,11 @@ xformers_attention: null
 
 </details><br>
 
-# 30353663-cac7-44d6-a6f6-fbfa5b116bba
+# fd53c9e8-b6ee-4f33-ac83-e5ccb83c294c
 
-This model is a fine-tuned version of [Korabbit/llama-2-ko-7b](https://huggingface.co/Korabbit/llama-2-ko-7b) on the Paladiso/dataset_6f876187-6d0a-4410-b9c7-16623cec1fad dataset.
+This model is a fine-tuned version of [echarlaix/tiny-random-mistral](https://huggingface.co/echarlaix/tiny-random-mistral) on the Paladiso/dataset_c2294ea4-f15b-4e48-866d-856c7fe6510b dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.7657
+- Loss: 10.3783
 
 ## Model description
 
@@ -139,9 +140,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 6.9731        | 0.0110 | 3    | 6.6195          |
-| 4.871         | 0.0220 | 6    | 3.0740          |
-| 1.0696        | 0.0329 | 9    | 0.7657          |
+| 41.5244       | 0.0026 | 3    | 10.3795         |
+| 41.5271       | 0.0052 | 6    | 10.3790         |
+| 41.5326       | 0.0077 | 9    | 10.3783         |
 
 
 ### Framework versions