End of training

README.md

@@ -66,7 +66,7 @@ lora_model_dir: null
 lora_r: 8
 lora_target_linear: true
 lr_scheduler: cosine
-max_steps: 1
+max_steps: 50
 micro_batch_size: 2
 mlflow_experiment_name: /tmp/7e7b154b9c0207c9_train_data.json
 model_type: AutoModelForCausalLM
@@ -91,7 +91,7 @@ wandb_name: 815118bb-697a-4367-8efd-aa63b4c2dd84
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: 815118bb-697a-4367-8efd-aa63b4c2dd84
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -102,6 +102,8 @@ xformers_attention: null
 # 5bffdcbc-e109-e343-7c14-c596ad38e219
 
 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: 1.7215
 
 ## Model description
 
@@ -128,14 +130,19 @@ The following hyperparameters were used during training:
 - total_train_batch_size: 8
 - optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: cosine
-- lr_scheduler_warmup_steps: 2
-- training_steps: 1
+- lr_scheduler_warmup_steps: 10
+- training_steps: 50
 
 ### Training results
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
 | No log        | 0.0001 | 1    | 1.9813          |
+| 1.8771        | 0.0014 | 10   | 1.9381          |
+| 1.8302        | 0.0027 | 20   | 1.7977          |
+| 1.6933        | 0.0041 | 30   | 1.7454          |
+| 1.7811        | 0.0055 | 40   | 1.7245          |
+| 1.6069        | 0.0069 | 50   | 1.7215          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01a1d19e46ff0aa92dd58dce2aa6719b451eb875b2b167457c3c3bd78eb08c3e
+oid sha256:46a3067a0da75e5d4a0dca5f177de66b570e208852d1a2412b1e102a23e23255
 size 22624970