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/33485949e15d9f77_train_data.json
 model_type: AutoModelForCausalLM
@@ -90,7 +90,7 @@ wandb_name: 70c25a5e-ace3-4412-8de6-974fdbc9730d
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: 70c25a5e-ace3-4412-8de6-974fdbc9730d
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -101,6 +101,8 @@ xformers_attention: null
 # 70c25a5e-ace3-4412-8de6-974fdbc9730d
 
 This model is a fine-tuned version of [scb10x/llama-3-typhoon-v1.5-8b-instruct](https://huggingface.co/scb10x/llama-3-typhoon-v1.5-8b-instruct) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.1495
 
 ## 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        | 0.0003 | 1    | 1.7318          |
+| 1.636         | 0.0029 | 10   | 1.5165          |
+| 1.4078        | 0.0058 | 20   | 1.2674          |
+| 1.2654        | 0.0088 | 30   | 1.1792          |
+| 1.192         | 0.0117 | 40   | 1.1522          |
+| 1.3038        | 0.0146 | 50   | 1.1495          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eec71c5df35f8ca87d23d8c0bc960bc4c9e19b1fe68179d9aad8c243d4de37aa
+oid sha256:f5508b111a49a050d798cb0303eed3ac18b54afdbc35afd4211a868f31d4db5d
 size 84047370