End of training

README.md

@@ -1,12 +1,12 @@
 ---
-license: apache-2.0
+license: mit
 library_name: peft
 tags:
 - axolotl
 - generated_from_trainer
-base_model: unsloth/Qwen2.5-0.5B-Instruct
+base_model: unsloth/Phi-3-mini-4k-instruct
 model-index:
-- name: f2c37cd7-d8ff-4753-9fa2-fd45b186c216
+- name: 31813020-2e0e-42ee-b232-f5fa4e28a89f
   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: unsloth/Qwen2.5-0.5B-Instruct
+base_model: unsloth/Phi-3-mini-4k-instruct
 bf16: auto
 datasets:
 - data_files:
-  - 8a7bfa6a070007c1_train_data.json
+  - c5ccc15ac08967d9_train_data.json
   ds_type: json
   format: custom
-  path: 8a7bfa6a070007c1_train_data.json
+  path: c5ccc15ac08967d9_train_data.json
   type:
     field: null
     field_input: null
-    field_instruction: question
-    field_output: answer
+    field_instruction: instruction
+    field_output: positive_sample
     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/f2c37cd7-d8ff-4753-9fa2-fd45b186c216
+hub_model_id: FatCat87/31813020-2e0e-42ee-b232-f5fa4e28a89f
 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: f2c37cd7-d8ff-4753-9fa2-fd45b186c216
+wandb_name: 31813020-2e0e-42ee-b232-f5fa4e28a89f
 wandb_project: subnet56
-wandb_runid: f2c37cd7-d8ff-4753-9fa2-fd45b186c216
+wandb_runid: 31813020-2e0e-42ee-b232-f5fa4e28a89f
 wandb_watch: null
 warmup_ratio: 0.05
 weight_decay: 0.0
@@ -94,12 +94,12 @@ xformers_attention: null
 
 </details><br>
 
-[<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/lrmaou1e)
-# f2c37cd7-d8ff-4753-9fa2-fd45b186c216
+[<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/7w4rbqlp)
+# 31813020-2e0e-42ee-b232-f5fa4e28a89f
 
-This model is a fine-tuned version of [unsloth/Qwen2.5-0.5B-Instruct](https://huggingface.co/unsloth/Qwen2.5-0.5B-Instruct) on the None dataset.
+This model is a fine-tuned version of [unsloth/Phi-3-mini-4k-instruct](https://huggingface.co/unsloth/Phi-3-mini-4k-instruct) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.2166
+- Loss: 2.2099
 
 ## Model description
 
@@ -129,17 +129,16 @@ 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: 4
 - num_epochs: 1
 
 ### Training results
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 2.1114        | 0.0103 | 1    | 2.1366          |
-| 1.4492        | 0.2577 | 25   | 1.4891          |
-| 1.2531        | 0.5155 | 50   | 1.2947          |
-| 1.2349        | 0.7732 | 75   | 1.2166          |
+| 2.1696        | 0.2222 | 1    | 2.2843          |
+| 2.1709        | 0.4444 | 2    | 2.2461          |
+| 2.2248        | 0.6667 | 3    | 2.2188          |
+| 2.1473        | 0.8889 | 4    | 2.2099          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17fafc8aac5daab6d28871a91efcc7e449fad0523da85cd7ab1b29ab5192d64b
-size 70506570
+oid sha256:bb32d290fa1fa6e943dd8ecdfd2be0ff94a14fb6a8025f63d21d460822eb0750
+size 239237322