End of training

README.md

@@ -1,11 +1,12 @@
 ---
+license: apache-2.0
 library_name: peft
 tags:
 - axolotl
 - generated_from_trainer
-base_model: NousResearch/CodeLlama-7b-hf
+base_model: Qwen/Qwen2.5-7B
 model-index:
-- name: dd4fc5a2-6909-4a86-9daa-5f331abe2c01
+- name: 211398b0-8dec-40bf-98cd-b07bbe034d0d
   results: []
 ---
 
@@ -18,19 +19,19 @@ should probably proofread and complete it, then remove this comment. -->
 axolotl version: `0.4.1`
 ```yaml
 adapter: lora
-base_model: NousResearch/CodeLlama-7b-hf
+base_model: Qwen/Qwen2.5-7B
 bf16: auto
 datasets:
 - data_files:
-  - 68196c6f79661e46_train_data.json
+  - 0b901dd4780c49c3_train_data.json
   ds_type: json
   format: custom
-  path: 68196c6f79661e46_train_data.json
+  path: 0b901dd4780c49c3_train_data.json
   type:
     field: null
-    field_input: province
-    field_instruction: name
-    field_output: text
+    field_input: filename
+    field_instruction: image
+    field_output: description
     field_system: null
     format: null
     no_input_format: null
@@ -50,7 +51,7 @@ fsdp_config: null
 gradient_accumulation_steps: 4
 gradient_checkpointing: true
 group_by_length: false
-hub_model_id: FatCat87/dd4fc5a2-6909-4a86-9daa-5f331abe2c01
+hub_model_id: FatCat87/211398b0-8dec-40bf-98cd-b07bbe034d0d
 learning_rate: 0.0002
 load_in_4bit: false
 load_in_8bit: true
@@ -72,8 +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
@@ -82,9 +82,9 @@ val_set_size: 0.1
 wandb_entity: fatcat87-taopanda
 wandb_log_model: null
 wandb_mode: online
-wandb_name: dd4fc5a2-6909-4a86-9daa-5f331abe2c01
+wandb_name: 211398b0-8dec-40bf-98cd-b07bbe034d0d
 wandb_project: subnet56
-wandb_runid: dd4fc5a2-6909-4a86-9daa-5f331abe2c01
+wandb_runid: 211398b0-8dec-40bf-98cd-b07bbe034d0d
 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/l88bnryn)
-# dd4fc5a2-6909-4a86-9daa-5f331abe2c01
+[<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/9v06q3re)
+# 211398b0-8dec-40bf-98cd-b07bbe034d0d
 
-This model is a fine-tuned version of [NousResearch/CodeLlama-7b-hf](https://huggingface.co/NousResearch/CodeLlama-7b-hf) on the None dataset.
+This model is a fine-tuned version of [Qwen/Qwen2.5-7B](https://huggingface.co/Qwen/Qwen2.5-7B) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.5991
+- Loss: 2.7297
 
 ## Model description
 
@@ -129,16 +129,17 @@ 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
 - num_epochs: 1
 
 ### Training results
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 2.126         | 0.0714 | 1    | 2.1321          |
-| 1.9978        | 0.2857 | 4    | 1.8969          |
-| 1.708         | 0.5714 | 8    | 1.6721          |
-| 1.6096        | 0.8571 | 12   | 1.5991          |
+| 2.9662        | 0.0292 | 1    | 3.0365          |
+| 2.7785        | 0.2628 | 9    | 2.8105          |
+| 2.6114        | 0.5255 | 18   | 2.7439          |
+| 2.7969        | 0.7883 | 27   | 2.7297          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9b5c674b93258d79cc9c95a11a9b3fb3e60a9939840002fa344a6ad74404bb8
-size 319977674
+oid sha256:bda74a44617597e9a9438cc17de7bc054884900837070c7331eb6376d552494f
+size 323103018