End of training

README.md

@@ -1,14 +1,14 @@
 ---
 library_name: peft
-license: apache-2.0
-base_model: unsloth/mistral-7b-instruct-v0.2
+license: mit
+base_model: dunzhang/stella_en_1.5B_v5
 tags:
 - axolotl
 - generated_from_trainer
 datasets:
-- Aivesa/dataset_cb3acbb3-babd-4857-af0b-0acdfd981c3f
+- Aivesa/dataset_03c41c63-6b0e-4ed5-9f81-56376e0a210d
 model-index:
-- name: 7bdbb3ac-dc6f-480f-88ef-a529585172da
+- name: 9a8f4254-967e-416a-81ef-cf1e0f17f5a2
   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: unsloth/mistral-7b-instruct-v0.2
+base_model: dunzhang/stella_en_1.5B_v5
 bf16: auto
 chat_template: llama3
 dataset_prepared_path: /workspace/axolotl/data/prepared
 datasets:
 - ds_type: json
   format: custom
-  path: Aivesa/dataset_cb3acbb3-babd-4857-af0b-0acdfd981c3f
+  path: Aivesa/dataset_03c41c63-6b0e-4ed5-9f81-56376e0a210d
   type:
-    field_input: yl
-    field_instruction: x
-    field_output: yw
+    field_input: reason
+    field_instruction: query
+    field_output: response
     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: Aivesa/7bdbb3ac-dc6f-480f-88ef-a529585172da
+hub_model_id: Aivesa/9a8f4254-967e-416a-81ef-cf1e0f17f5a2
 hub_private_repo: true
 hub_repo: null
 hub_strategy: checkpoint
@@ -88,10 +88,10 @@ use_accelerate: true
 val_set_size: 0.05
 wandb_entity: null
 wandb_mode: online
-wandb_name: cb3acbb3-babd-4857-af0b-0acdfd981c3f
+wandb_name: 03c41c63-6b0e-4ed5-9f81-56376e0a210d
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
-wandb_runid: cb3acbb3-babd-4857-af0b-0acdfd981c3f
+wandb_runid: 03c41c63-6b0e-4ed5-9f81-56376e0a210d
 warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
@@ -100,11 +100,11 @@ xformers_attention: null
 
 </details><br>
 
-# 7bdbb3ac-dc6f-480f-88ef-a529585172da
+# 9a8f4254-967e-416a-81ef-cf1e0f17f5a2
 
-This model is a fine-tuned version of [unsloth/mistral-7b-instruct-v0.2](https://huggingface.co/unsloth/mistral-7b-instruct-v0.2) on the Aivesa/dataset_cb3acbb3-babd-4857-af0b-0acdfd981c3f dataset.
+This model is a fine-tuned version of [dunzhang/stella_en_1.5B_v5](https://huggingface.co/dunzhang/stella_en_1.5B_v5) on the Aivesa/dataset_03c41c63-6b0e-4ed5-9f81-56376e0a210d dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.0666
+- Loss: 12.1019
 
 ## Model description
 
@@ -138,9 +138,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 5.3209        | 0.0001 | 3    | 1.3254          |
-| 5.0926        | 0.0002 | 6    | 1.1666          |
-| 3.9323        | 0.0003 | 9    | 1.0666          |
+| 52.2992       | 0.0004 | 3    | 13.1028         |
+| 51.79         | 0.0009 | 6    | 12.7737         |
+| 48.6273       | 0.0013 | 9    | 12.1019         |
 
 
 ### Framework versions