End of training

README.md

@@ -1,14 +1,14 @@
 ---
 library_name: peft
-license: apache-2.0
-base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
+license: other
+base_model: Qwen/Qwen2.5-3B-Instruct
 tags:
 - axolotl
 - generated_from_trainer
 datasets:
-- Paladiso/dataset_e70fec0d-c949-48ee-aa83-df5ca1800db5
+- Paladiso/dataset_253c0b71-6970-43c0-adf7-24f5dfa87967
 model-index:
-- name: 6d97a15a-340d-401f-a442-958bfcff5e25
+- name: 56e46106-55ee-42fc-b514-64b2448c7b69
   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: TinyLlama/TinyLlama-1.1B-Chat-v1.0
+base_model: Qwen/Qwen2.5-3B-Instruct
 bf16: auto
 chat_template: llama3
 dataset_prepared_path: /workspace/axolotl/data/prepared
 datasets:
 - ds_type: json
   format: custom
-  path: Paladiso/dataset_e70fec0d-c949-48ee-aa83-df5ca1800db5
+  path: Paladiso/dataset_253c0b71-6970-43c0-adf7-24f5dfa87967
   type:
-    field_input: poem_meter
-    field_instruction: poem_title
-    field_output: poem_verses
+    field_input: input
+    field_instruction: instruction
+    field_output: output
     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/6d97a15a-340d-401f-a442-958bfcff5e25
+hub_model_id: Paladiso/56e46106-55ee-42fc-b514-64b2448c7b69
 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: e70fec0d-c949-48ee-aa83-df5ca1800db5
+wandb_name: 253c0b71-6970-43c0-adf7-24f5dfa87967
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
-wandb_runid: e70fec0d-c949-48ee-aa83-df5ca1800db5
+wandb_runid: 253c0b71-6970-43c0-adf7-24f5dfa87967
 warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
@@ -100,11 +100,11 @@ xformers_attention: null
 
 </details><br>
 
-# 6d97a15a-340d-401f-a442-958bfcff5e25
+# 56e46106-55ee-42fc-b514-64b2448c7b69
 
-This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-Chat-v1.0](https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0) on the Paladiso/dataset_e70fec0d-c949-48ee-aa83-df5ca1800db5 dataset.
+This model is a fine-tuned version of [Qwen/Qwen2.5-3B-Instruct](https://huggingface.co/Qwen/Qwen2.5-3B-Instruct) on the Paladiso/dataset_253c0b71-6970-43c0-adf7-24f5dfa87967 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.1007
+- Loss: 1.4194
 
 ## Model description
 
@@ -138,9 +138,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 2.3283        | 0.0029 | 3    | 2.2312          |
-| 2.1975        | 0.0058 | 6    | 2.1484          |
-| 2.2565        | 0.0087 | 9    | 2.1007          |
+| 2.5051        | 0.0001 | 3    | 2.4359          |
+| 2.2783        | 0.0002 | 6    | 1.8827          |
+| 1.6875        | 0.0003 | 9    | 1.4194          |
 
 
 ### Framework versions