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: null
@@ -56,7 +64,7 @@ lora_target_linear: true
 lr_scheduler: cosine
 max_steps: 10
 micro_batch_size: 2
-mlflow_experiment_name: mhenrichsen/alpaca_2k_test
+mlflow_experiment_name: /tmp/MATH-Hard_train_data.json
 model_type: LlamaForCausalLM
 num_epochs: 1
 optimizer: adamw_bnb_8bit
@@ -77,7 +85,7 @@ wandb_entity: breakfasthut
 wandb_mode: online
 wandb_project: tuning-miner
 wandb_run: miner
-wandb_runid: 383a850e-bb15-45a2-8f4b-fc96eb001a74
+wandb_runid: ab3318ee-d929-45d5-97e1-ccfee77df372
 warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
@@ -90,7 +98,7 @@ 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: 1.2168
+- Loss: 0.9018
 
 ## Model description
 
@@ -124,10 +132,10 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 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          |
+| 1.0005        | 0.0026 | 1    | 1.0009          |
+| 0.9902        | 0.0077 | 3    | 0.9955          |
+| 0.8842        | 0.0155 | 6    | 0.9534          |
+| 0.9599        | 0.0232 | 9    | 0.9018          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e11e87d9f4c05d9e49cabe8c727e90dd550085dc314ff9ba6e0633297e846e2e
+oid sha256:0f03b57cee6d30f47901b118b5bd6c333f6b6baaef97d63290ab632a02e841a7
 size 45169354