End of training

README.md

@@ -1,14 +1,14 @@
 ---
 library_name: peft
-license: other
-base_model: deepseek-ai/deepseek-coder-6.7b-instruct
+license: mit
+base_model: NousResearch/Nous-Hermes-llama-2-7b
 tags:
 - axolotl
 - generated_from_trainer
 datasets:
-- Paladiso/dataset_41dda0c6-8e48-48bb-9249-f42e27a517b0
+- Paladiso/dataset_2a4738f3-e023-46f4-ae13-2b8b3faf7cb2
 model-index:
-- name: e60510e7-49f8-4df0-b938-c6cafe3f3d52
+- name: 0b7c2404-8bda-4a1e-b967-80d5a73d032a
   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: deepseek-ai/deepseek-coder-6.7b-instruct
+base_model: NousResearch/Nous-Hermes-llama-2-7b
 bf16: auto
 chat_template: llama3
 dataset_prepared_path: /workspace/axolotl/data/prepared
 datasets:
 - ds_type: json
   format: custom
-  path: Paladiso/dataset_41dda0c6-8e48-48bb-9249-f42e27a517b0
+  path: Paladiso/dataset_2a4738f3-e023-46f4-ae13-2b8b3faf7cb2
   type:
-    field_input: input
-    field_instruction: instruction
-    field_output: output
+    field_input: title
+    field_instruction: category
+    field_output: title_category
     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: Paladiso/e60510e7-49f8-4df0-b938-c6cafe3f3d52
+hub_model_id: Paladiso/0b7c2404-8bda-4a1e-b967-80d5a73d032a
 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: 41dda0c6-8e48-48bb-9249-f42e27a517b0
+wandb_name: 2a4738f3-e023-46f4-ae13-2b8b3faf7cb2
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
-wandb_runid: 41dda0c6-8e48-48bb-9249-f42e27a517b0
+wandb_runid: 2a4738f3-e023-46f4-ae13-2b8b3faf7cb2
 warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
@@ -100,11 +100,11 @@ xformers_attention: null
 
 </details><br>
 
-# e60510e7-49f8-4df0-b938-c6cafe3f3d52
+# 0b7c2404-8bda-4a1e-b967-80d5a73d032a
 
-This model is a fine-tuned version of [deepseek-ai/deepseek-coder-6.7b-instruct](https://huggingface.co/deepseek-ai/deepseek-coder-6.7b-instruct) on the Paladiso/dataset_41dda0c6-8e48-48bb-9249-f42e27a517b0 dataset.
+This model is a fine-tuned version of [NousResearch/Nous-Hermes-llama-2-7b](https://huggingface.co/NousResearch/Nous-Hermes-llama-2-7b) on the Paladiso/dataset_2a4738f3-e023-46f4-ae13-2b8b3faf7cb2 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.7043
+- Loss: 0.4806
 
 ## Model description
 
@@ -138,9 +138,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 1.8538        | 0.0007 | 3    | 1.9522          |
-| 1.5454        | 0.0015 | 6    | 1.9174          |
-| 1.5226        | 0.0022 | 9    | 1.7043          |
+| 1.5304        | 0.0000 | 3    | 1.4527          |
+| 1.3865        | 0.0001 | 6    | 1.1237          |
+| 0.7958        | 0.0001 | 9    | 0.4806          |
 
 
 ### Framework versions