End of training

README.md

@@ -1,7 +1,7 @@
 ---
 library_name: peft
 license: llama3.2
-base_model: unsloth/Llama-3.2-3B-Instruct
+base_model: unsloth/Llama-3.2-1B-Instruct
 tags:
 - axolotl
 - generated_from_trainer
@@ -19,22 +19,13 @@ should probably proofread and complete it, then remove this comment. -->
 axolotl version: `0.4.1`
 ```yaml
 adapter: lora
-base_model: unsloth/Llama-3.2-3B-Instruct
+base_model: unsloth/Llama-3.2-1B-Instruct
 bf16: auto
 chat_template: llama3
 dataset_prepared_path: null
 datasets:
-- data_files:
-  - alpaca_2k_test_train_data.json
-  ds_type: json
-  path: /workspace/input_data/alpaca_2k_test_train_data.json
-  type:
-    field_input: input
-    field_instruction: instruction
-    field_output: output
-    field_system: text
-    system_format: '{system}'
-    system_prompt: ''
+- path: mhenrichsen/alpaca_2k_test
+  type: alpaca
 debug: null
 deepspeed: null
 early_stopping_patience: null
@@ -65,7 +56,7 @@ lora_target_linear: true
 lr_scheduler: cosine
 max_steps: 10
 micro_batch_size: 2
-mlflow_experiment_name: /tmp/alpaca_2k_test_train_data.json
+mlflow_experiment_name: mhenrichsen/alpaca_2k_test
 model_type: LlamaForCausalLM
 num_epochs: 1
 optimizer: adamw_bnb_8bit
@@ -86,7 +77,7 @@ wandb_entity: breakfasthut
 wandb_mode: online
 wandb_project: tuning-miner
 wandb_run: miner
-wandb_runid: 38a84026-8f15-419b-afa8-a97fbd07e799
+wandb_runid: 383a850e-bb15-45a2-8f4b-fc96eb001a74
 warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
@@ -97,9 +88,9 @@ xformers_attention: null
 
 # tuning-miner-output
 
-This model is a fine-tuned version of [unsloth/Llama-3.2-3B-Instruct](https://huggingface.co/unsloth/Llama-3.2-3B-Instruct) on the None dataset.
+This model is a fine-tuned version of [unsloth/Llama-3.2-1B-Instruct](https://huggingface.co/unsloth/Llama-3.2-1B-Instruct) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0912
+- Loss: 1.2168
 
 ## Model description
 
@@ -133,10 +124,10 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 0.2093        | 0.0047 | 1    | 0.3442          |
-| 0.0777        | 0.0140 | 3    | 0.3320          |
-| 0.0852        | 0.0281 | 6    | 0.2251          |
-| 0.0449        | 0.0421 | 9    | 0.0912          |
+| 1.3218        | 0.0042 | 1    | 1.2625          |
+| 1.3028        | 0.0126 | 3    | 1.2629          |
+| 1.4831        | 0.0253 | 6    | 1.2133          |
+| 1.2899        | 0.0379 | 9    | 1.2168          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:82adfb42eb8867327adba9f02bed01a776266e6d21f03b8dae1c8b298347e6ce
-size 97396522
+oid sha256:e11e87d9f4c05d9e49cabe8c727e90dd550085dc314ff9ba6e0633297e846e2e
+size 45169354