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/55d5b9c1f2d0eba0_train_data.json
 model_type: AutoModelForCausalLM
@@ -91,7 +91,7 @@ wandb_name: 879e95b8-ef0b-48b1-86fe-47876c38f22f
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: 879e95b8-ef0b-48b1-86fe-47876c38f22f
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -102,6 +102,8 @@ xformers_attention: null
 # e27389de-041f-45f6-8f60-377cdbd7f01d
 
 This model is a fine-tuned version of [aisingapore/llama3-8b-cpt-sea-lionv2.1-instruct](https://huggingface.co/aisingapore/llama3-8b-cpt-sea-lionv2.1-instruct) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.4144
 
 ## 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        | 0.0002 | 1    | 2.3437          |
+| 2.2151        | 0.0018 | 10   | 2.1924          |
+| 2.0181        | 0.0037 | 20   | 1.7055          |
+| 1.6656        | 0.0055 | 30   | 1.5272          |
+| 1.5847        | 0.0074 | 40   | 1.4329          |
+| 1.4583        | 0.0092 | 50   | 1.4144          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e001206c34d5ad3aa44cde985cf58ca44d6a32cc184a0f11b8b175d0dc0a1c99
+oid sha256:6350a06d2a110c04dae6dc36f9c433e4bd6950727ab268a549c2081760c0ea65
 size 84047370