End of training

README.md

@@ -24,8 +24,16 @@ bf16: auto
 chat_template: llama3
 dataset_prepared_path: null
 datasets:
-- path: mhenrichsen/alpaca_2k_test
-  type: alpaca
+- data_files:
+  - MATH-Hard_train_data.json
+  ds_type: json
+  path: /workspace/input_data/MATH-Hard_train_data.json
+  type:
+    field_input: problem
+    field_instruction: type
+    field_output: solution
+    system_format: '{system}'
+    system_prompt: ''
 debug: null
 deepspeed: null
 early_stopping_patience: 3
@@ -57,7 +65,7 @@ lora_target_linear: true
 lr_scheduler: cosine
 max_steps: 150
 micro_batch_size: 10
-mlflow_experiment_name: mhenrichsen/alpaca_2k_test
+mlflow_experiment_name: /tmp/MATH-Hard_train_data.json
 model_type: LlamaForCausalLM
 num_epochs: 5
 optimizer: adamw_bnb_8bit
@@ -78,7 +86,7 @@ wandb_entity: besimray24-rayon
 wandb_mode: online
 wandb_project: Public_TuningSN
 wandb_run: miner_id_24
-wandb_runid: 383a850e-bb15-45a2-8f4b-fc96eb001a74
+wandb_runid: efa31d17-18f5-4448-b1b4-f65721354910
 warmup_steps: 10
 weight_decay: 0.01
 xformers_attention: null
@@ -91,7 +99,7 @@ xformers_attention: null
 
 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: 1.1679
+- Loss: 0.7629
 
 ## Model description
 
@@ -125,13 +133,14 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 1.3028        | 0.0211 | 1    | 1.2579          |
-| 1.3521        | 0.4211 | 20   | 1.1702          |
-| 1.1977        | 0.8421 | 40   | 1.1533          |
-| 1.099         | 1.2632 | 60   | 1.1519          |
-| 1.0658        | 1.6842 | 80   | 1.1523          |
-| 1.0091        | 2.1053 | 100  | 1.1575          |
-| 1.1045        | 2.5263 | 120  | 1.1679          |
+| 0.9595        | 0.0129 | 1    | 0.9746          |
+| 0.9359        | 0.2572 | 20   | 0.8169          |
+| 0.7895        | 0.5145 | 40   | 0.7905          |
+| 0.7524        | 0.7717 | 60   | 0.7785          |
+| 0.8127        | 1.0289 | 80   | 0.7698          |
+| 0.7258        | 1.2862 | 100  | 0.7665          |
+| 0.8212        | 1.5434 | 120  | 0.7636          |
+| 0.6807        | 1.8006 | 140  | 0.7629          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06f5758c8cb21c14363a1d12df2489b3350d89721ddf69a0a83c34d8d1b99ba6
+oid sha256:b27b15e9ee1833ae31432908afae3349855d2b7e578bcca141463bb3dcf1c209
 size 45169354

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9ac5f431e68bc0be3e94d65a484f12f766b83dc919f1a2a7192b4fa03404081
+oid sha256:e8f124971f6e45e066092c45814571663abeeb1c7c37d9b8a60eedfc0a06e172
 size 45118424