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/cb305d5f6127a19b_train_data.json
 model_type: AutoModelForCausalLM
@@ -91,7 +91,7 @@ wandb_name: 4d5e9f67-16c2-4bc8-945a-2b905e76e685
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: 4d5e9f67-16c2-4bc8-945a-2b905e76e685
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -102,6 +102,8 @@ xformers_attention: null
 # d31cb386-9b80-d5aa-a82a-7baa77139349
 
 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: 0.5862
 
 ## 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        | 0.0018 | 1    | 0.7454          |
+| 0.6796        | 0.0175 | 10   | 0.6747          |
+| 0.6739        | 0.0351 | 20   | 0.6101          |
+| 0.615         | 0.0526 | 30   | 0.5953          |
+| 0.6262        | 0.0702 | 40   | 0.5875          |
+| 0.5802        | 0.0877 | 50   | 0.5862          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33a8695a81a79d938893e530b20b896cce2c209d057daa55b7776114a5defffb
+oid sha256:7397e302d8358d4f157f041339413247b91f4225a8572270db9a7a145a2d404a
 size 84047370