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/a11f8217f40ca211_train_data.json
 model_type: AutoModelForCausalLM
@@ -90,7 +90,7 @@ wandb_name: b49985cb-1972-4835-840c-c05792e5f494
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: b49985cb-1972-4835-840c-c05792e5f494
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -101,6 +101,8 @@ xformers_attention: null
 # 95543050-c30c-43e1-a30c-c764cad05be3
 
 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: 0.7608
 
 ## 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        | 0.0008 | 1    | 1.2206          |
+| 1.1771        | 0.0084 | 10   | 1.0230          |
+| 0.8737        | 0.0168 | 20   | 0.8286          |
+| 0.76          | 0.0252 | 30   | 0.7845          |
+| 0.7359        | 0.0336 | 40   | 0.7645          |
+| 0.8369        | 0.0419 | 50   | 0.7608          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77c161ec860d34cbca81ec7c26d581f204121d90174a2cbd869bd1010963ac6c
+oid sha256:40656eba0b2aa4b2c1f43246866a448e044c3c6bd4ec79da9e92a2ba72e6ca7e
 size 84047370