End of training

README.md

@@ -4,9 +4,9 @@ library_name: peft
 tags:
 - axolotl
 - generated_from_trainer
-base_model: princeton-nlp/Sheared-LLaMA-1.3B
+base_model: Qwen/Qwen2.5-1.5B
 model-index:
-- name: 76e772b1-fe02-45e3-aa5b-7b36ec7abf8d
+- name: 1a4c1a98-2c44-4d6c-a706-eb21745cbeb9
   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: princeton-nlp/Sheared-LLaMA-1.3B
+base_model: Qwen/Qwen2.5-1.5B
 bf16: auto
 datasets:
 - data_files:
-  - cb26f8bb8a47c11f_train_data.json
+  - 3aa8598218912f7b_train_data.json
   ds_type: json
   format: custom
-  path: cb26f8bb8a47c11f_train_data.json
+  path: 3aa8598218912f7b_train_data.json
   type:
     field: null
     field_input: null
-    field_instruction: instruction
-    field_output: output
+    field_instruction: query
+    field_output: text
     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: FatCat87/76e772b1-fe02-45e3-aa5b-7b36ec7abf8d
+hub_model_id: FatCat87/1a4c1a98-2c44-4d6c-a706-eb21745cbeb9
 learning_rate: 0.0002
 load_in_4bit: false
 load_in_8bit: true
@@ -73,8 +73,7 @@ sample_packing: true
 saves_per_epoch: 1
 seed: 701
 sequence_len: 4096
-special_tokens:
-  pad_token: </s>
+special_tokens: null
 strict: false
 tf32: false
 tokenizer_type: AutoTokenizer
@@ -83,9 +82,9 @@ val_set_size: 0.1
 wandb_entity: fatcat87-taopanda
 wandb_log_model: null
 wandb_mode: online
-wandb_name: 76e772b1-fe02-45e3-aa5b-7b36ec7abf8d
+wandb_name: 1a4c1a98-2c44-4d6c-a706-eb21745cbeb9
 wandb_project: subnet56
-wandb_runid: 76e772b1-fe02-45e3-aa5b-7b36ec7abf8d
+wandb_runid: 1a4c1a98-2c44-4d6c-a706-eb21745cbeb9
 wandb_watch: null
 warmup_ratio: 0.05
 weight_decay: 0.0
@@ -95,12 +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/edodtlvp)
-# 76e772b1-fe02-45e3-aa5b-7b36ec7abf8d
+[<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/2tuw4i2f)
+# 1a4c1a98-2c44-4d6c-a706-eb21745cbeb9
 
-This model is a fine-tuned version of [princeton-nlp/Sheared-LLaMA-1.3B](https://huggingface.co/princeton-nlp/Sheared-LLaMA-1.3B) on the None dataset.
+This model is a fine-tuned version of [Qwen/Qwen2.5-1.5B](https://huggingface.co/Qwen/Qwen2.5-1.5B) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.5490
+- Loss: 2.4703
 
 ## Model description
 
@@ -130,17 +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: 9
 - num_epochs: 1
 
 ### Training results
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 1.8322        | 0.0050 | 1    | 1.9699          |
-| 1.5589        | 0.2537 | 51   | 1.6483          |
-| 1.4753        | 0.5075 | 102  | 1.5744          |
-| 1.4788        | 0.7612 | 153  | 1.5490          |
+| 2.724         | 0.0952 | 1    | 2.7997          |
+| 2.6075        | 0.2857 | 3    | 2.6428          |
+| 2.4169        | 0.5714 | 6    | 2.4890          |
+| 2.3835        | 0.8571 | 9    | 2.4703          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0ba8c4ee480fe38718ba5baef8c771892e5806bacea580ba0421ba81448e4eb
-size 120052362
+oid sha256:30d2c742e5487f8931f8d076fcadff6b2317cdbea3731425d444008f743f7695
+size 147859242