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: 8
 mlflow_experiment_name: /tmp/dc0abfe34c05583b_train_data.json
 model_type: AutoModelForCausalLM
@@ -91,7 +91,7 @@ wandb_name: 6af7590a-a64a-4086-ae7c-b96b1ade6ef8
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: 6af7590a-a64a-4086-ae7c-b96b1ade6ef8
-warmup_steps: 1
+warmup_steps: 2
 weight_decay: 0.0
 xformers_attention: null
 
@@ -102,6 +102,8 @@ xformers_attention: null
 # 6af7590a-a64a-4086-ae7c-b96b1ade6ef8
 
 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: 1.5313
 
 ## Model description
 
@@ -129,13 +131,17 @@ The following hyperparameters were used during training:
 - 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
+- training_steps: 17
 
 ### Training results
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
 | No log        | 0.0590 | 1    | 4.4012          |
+| No log        | 0.2362 | 4    | 3.7896          |
+| No log        | 0.4723 | 8    | 2.3424          |
+| 3.3311        | 0.7085 | 12   | 1.6681          |
+| 3.3311        | 0.9446 | 16   | 1.5313          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:059f0e5fe1bda4258b8c47db28a35d49852cae57ad4e36b6cfc4aed416fd8b2e
+oid sha256:bcc4d9bee8574ac7c849b234b307bc60ff606e49f2d0436c94c5da6c840b5aa9
 size 84047370