End of training

README.md

@@ -1,14 +1,13 @@
 ---
 library_name: peft
-license: apache-2.0
-base_model: unsloth/SmolLM2-360M-Instruct
+base_model: Vikhrmodels/Vikhr-7B-instruct_0.4
 tags:
 - axolotl
 - generated_from_trainer
 datasets:
-- Aivesa/dataset_b5e7bccd-18f9-46c0-969e-ae67a7379d19
+- Aivesa/dataset_fab57f05-e769-4df2-8d2b-87afad7cfe22
 model-index:
-- name: 983e8f34-21d7-4a69-a6f8-51cacd900a19
+- name: 0b98a095-60c2-45a0-901e-ac229ae52df0
   results: []
 ---
 
@@ -21,17 +20,17 @@ should probably proofread and complete it, then remove this comment. -->
 axolotl version: `0.6.0`
 ```yaml
 adapter: lora
-base_model: unsloth/SmolLM2-360M-Instruct
+base_model: Vikhrmodels/Vikhr-7B-instruct_0.4
 bf16: auto
 chat_template: llama3
 dataset_prepared_path: /workspace/axolotl/data/prepared
 datasets:
 - ds_type: json
   format: custom
-  path: Aivesa/dataset_b5e7bccd-18f9-46c0-969e-ae67a7379d19
+  path: Aivesa/dataset_fab57f05-e769-4df2-8d2b-87afad7cfe22
   type:
     field_input: input
-    field_instruction: prompt
+    field_instruction: instruction
     field_output: output
     system_format: '{system}'
     system_prompt: ''
@@ -48,7 +47,7 @@ fsdp_config: null
 gradient_accumulation_steps: 4
 gradient_checkpointing: false
 group_by_length: false
-hub_model_id: Aivesa/983e8f34-21d7-4a69-a6f8-51cacd900a19
+hub_model_id: Aivesa/0b98a095-60c2-45a0-901e-ac229ae52df0
 hub_private_repo: true
 hub_repo: null
 hub_strategy: checkpoint
@@ -88,10 +87,10 @@ use_accelerate: true
 val_set_size: 0.05
 wandb_entity: null
 wandb_mode: online
-wandb_name: b5e7bccd-18f9-46c0-969e-ae67a7379d19
+wandb_name: fab57f05-e769-4df2-8d2b-87afad7cfe22
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
-wandb_runid: b5e7bccd-18f9-46c0-969e-ae67a7379d19
+wandb_runid: fab57f05-e769-4df2-8d2b-87afad7cfe22
 warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
@@ -100,11 +99,11 @@ xformers_attention: null
 
 </details><br>
 
-# 983e8f34-21d7-4a69-a6f8-51cacd900a19
+# 0b98a095-60c2-45a0-901e-ac229ae52df0
 
-This model is a fine-tuned version of [unsloth/SmolLM2-360M-Instruct](https://huggingface.co/unsloth/SmolLM2-360M-Instruct) on the Aivesa/dataset_b5e7bccd-18f9-46c0-969e-ae67a7379d19 dataset.
+This model is a fine-tuned version of [Vikhrmodels/Vikhr-7B-instruct_0.4](https://huggingface.co/Vikhrmodels/Vikhr-7B-instruct_0.4) on the Aivesa/dataset_fab57f05-e769-4df2-8d2b-87afad7cfe22 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.2910
+- Loss: 0.9962
 
 ## Model description
 
@@ -138,9 +137,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 1.2887        | 0.0104 | 3    | 1.3102          |
-| 1.4285        | 0.0209 | 6    | 1.3062          |
-| 1.3236        | 0.0313 | 9    | 1.2910          |
+| 0.7196        | 0.0002 | 3    | 1.1272          |
+| 1.1478        | 0.0003 | 6    | 1.0565          |
+| 0.5412        | 0.0005 | 9    | 0.9962          |
 
 
 ### Framework versions