End of training

README.md

@@ -1,12 +1,12 @@
 ---
-license: mit
+license: apache-2.0
 library_name: peft
 tags:
 - axolotl
 - generated_from_trainer
-base_model: microsoft/Phi-3.5-mini-instruct
+base_model: Qwen/Qwen2.5-0.5B
 model-index:
-- name: bebc098a-34ef-4279-bfd4-76bb95526dba
+- name: 6201afaa-a647-4d6e-b7ef-21dbf1764a57
   results: []
 ---
 
@@ -19,19 +19,19 @@ should probably proofread and complete it, then remove this comment. -->
 axolotl version: `0.4.1`
 ```yaml
 adapter: lora
-base_model: microsoft/Phi-3.5-mini-instruct
+base_model: Qwen/Qwen2.5-0.5B
 bf16: auto
 datasets:
 - data_files:
-  - 0e75859cf9d8cc9a_train_data.json
+  - e7d5bcb285c8a077_train_data.json
   ds_type: json
   format: custom
-  path: 0e75859cf9d8cc9a_train_data.json
+  path: e7d5bcb285c8a077_train_data.json
   type:
     field: null
-    field_input: null
-    field_instruction: question
-    field_output: answer
+    field_input: disorder
+    field_instruction: input
+    field_output: dssp3
     field_system: null
     format: null
     no_input_format: null
@@ -51,7 +51,7 @@ fsdp_config: null
 gradient_accumulation_steps: 4
 gradient_checkpointing: true
 group_by_length: false
-hub_model_id: FatCat87/bebc098a-34ef-4279-bfd4-76bb95526dba
+hub_model_id: FatCat87/6201afaa-a647-4d6e-b7ef-21dbf1764a57
 learning_rate: 0.0002
 load_in_4bit: false
 load_in_8bit: true
@@ -82,9 +82,9 @@ val_set_size: 0.1
 wandb_entity: fatcat87-taopanda
 wandb_log_model: null
 wandb_mode: online
-wandb_name: bebc098a-34ef-4279-bfd4-76bb95526dba
+wandb_name: 6201afaa-a647-4d6e-b7ef-21dbf1764a57
 wandb_project: subnet56
-wandb_runid: bebc098a-34ef-4279-bfd4-76bb95526dba
+wandb_runid: 6201afaa-a647-4d6e-b7ef-21dbf1764a57
 wandb_watch: null
 warmup_ratio: 0.05
 weight_decay: 0.0
@@ -94,11 +94,12 @@ xformers_attention: null
 
 </details><br>
 
-# bebc098a-34ef-4279-bfd4-76bb95526dba
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/fatcat87-taopanda/subnet56/runs/rxyx3cte)
+# 6201afaa-a647-4d6e-b7ef-21dbf1764a57
 
-This model is a fine-tuned version of [microsoft/Phi-3.5-mini-instruct](https://huggingface.co/microsoft/Phi-3.5-mini-instruct) on the None dataset.
+This model is a fine-tuned version of [Qwen/Qwen2.5-0.5B](https://huggingface.co/Qwen/Qwen2.5-0.5B) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.8199
+- Loss: 1.1313
 
 ## Model description
 
@@ -128,23 +129,23 @@ The following hyperparameters were used during training:
 - total_eval_batch_size: 4
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine
-- lr_scheduler_warmup_steps: 2
+- lr_scheduler_warmup_steps: 8
 - num_epochs: 1
 
 ### Training results
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 4.8381        | 0.0435 | 1    | 0.8313          |
-| 4.5187        | 0.2609 | 6    | 0.8197          |
-| 4.0981        | 0.5217 | 12   | 0.8163          |
-| 3.886         | 0.7826 | 18   | 0.8199          |
+| 1.951         | 0.0051 | 1    | 1.9665          |
+| 1.1794        | 0.2506 | 49   | 1.1707          |
+| 1.124         | 0.5013 | 98   | 1.1384          |
+| 1.1442        | 0.7519 | 147  | 1.1313          |
 
 
 ### Framework versions
 
 - PEFT 0.11.1
-- Transformers 4.44.2
+- Transformers 4.42.3
 - Pytorch 2.3.0+cu121
 - Datasets 2.19.1
 - Tokenizers 0.19.1

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c1b3a76cfdd55b91b883fc7275929ce3c900bb1c70573c0f7d7a78968472fbc5
-size 201419466
+oid sha256:85f0f329502f927827eed212d6bff3aca2a61fa1e4be9c07333007fe5f411614
+size 70506570