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: 1
+max_steps: 50
 micro_batch_size: 2
 mlflow_experiment_name: /tmp/3ca4bea0393c2456_train_data.json
 model_type: AutoModelForCausalLM
@@ -90,7 +90,7 @@ wandb_name: f45440b4-8f02-4836-93a1-52acac717022
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: f45440b4-8f02-4836-93a1-52acac717022
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -101,6 +101,8 @@ xformers_attention: null
 # c5db66b5-89ca-4755-bff7-b592e99eb772
 
 This model is a fine-tuned version of [WhiteRabbitNeo/Llama-3-WhiteRabbitNeo-8B-v2.0](https://huggingface.co/WhiteRabbitNeo/Llama-3-WhiteRabbitNeo-8B-v2.0) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.0151
 
 ## Model description
 
@@ -127,14 +129,19 @@ 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        | 0.0006 | 1    | 1.4701          |
+| 1.1383        | 0.0061 | 10   | 1.4146          |
+| 0.8763        | 0.0123 | 20   | 1.1584          |
+| 1.0365        | 0.0184 | 30   | 1.0480          |
+| 0.9924        | 0.0246 | 40   | 1.0201          |
+| 1.081         | 0.0307 | 50   | 1.0151          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07cb1cec3e08a9bd031037a77c08d1d51c3c81c96a486ec982e3a524fbb48a77
+oid sha256:cfe8d4dedac70cee72dd371926636a6fb93c5908a328fef500e8cb6d8c29a63c
 size 84047370