End of training

README.md

@@ -65,7 +65,7 @@ lora_model_dir: null
 lora_r: 8
 lora_target_linear: true
 lr_scheduler: cosine
-max_steps: 50
+max_steps: 1
 micro_batch_size: 2
 mlflow_experiment_name: /tmp/d0f81a550932409c_train_data.json
 model_type: AutoModelForCausalLM
@@ -90,7 +90,7 @@ wandb_name: 3d882c8f-3ef5-464c-a31b-6e6b5783b65b
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: 3d882c8f-3ef5-464c-a31b-6e6b5783b65b
-warmup_steps: 10
+warmup_steps: 1
 weight_decay: 0.0
 xformers_attention: null
 
@@ -101,8 +101,6 @@ xformers_attention: null
 # 3d882c8f-3ef5-464c-a31b-6e6b5783b65b
 
 This model is a fine-tuned version of [unsloth/llama-3-8b-Instruct](https://huggingface.co/unsloth/llama-3-8b-Instruct) on the None dataset.
-It achieves the following results on the evaluation set:
-- Loss: 0.0001
 
 ## Model description
 
@@ -129,19 +127,14 @@ 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: 10
-- training_steps: 50
+- lr_scheduler_warmup_steps: 2
+- training_steps: 1
 
 ### Training results
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
 | No log        | 0.0024 | 1    | 13.6639         |
-| 11.3824       | 0.0242 | 10   | 7.9953          |
-| 0.5223        | 0.0484 | 20   | 0.0597          |
-| 0.0002        | 0.0726 | 30   | 0.0006          |
-| 0.0007        | 0.0968 | 40   | 0.0001          |
-| 0.0002        | 0.1210 | 50   | 0.0001          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b43bdc9016f29ec5f591fdda5164c80dfe545927e61ade5b6d0a26142c9e903a
+oid sha256:648d733305c48a35e4d492350a9c1d144ada4bead312c7f333536590dc554bc8
 size 84047370