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/382d9148926d4439_train_data.json
 model_type: AutoModelForCausalLM
@@ -92,7 +92,7 @@ wandb_name: 4120f811-7935-417e-8f93-1301e31416e8
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: 4120f811-7935-417e-8f93-1301e31416e8
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -103,6 +103,8 @@ xformers_attention: null
 # 9b662987-1e06-4570-fdf5-70812f8cc991
 
 This model is a fine-tuned version of [tiiuae/falcon-rw-1b](https://huggingface.co/tiiuae/falcon-rw-1b) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.3716
 
 ## Model description
 
@@ -129,14 +131,19 @@ 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        | 0.0001 | 1    | 2.8921          |
+| 11.4882       | 0.0007 | 10   | 2.7373          |
+| 10.0409       | 0.0013 | 20   | 2.4648          |
+| 9.4257        | 0.0020 | 30   | 2.3991          |
+| 9.1672        | 0.0026 | 40   | 2.3750          |
+| 9.8965        | 0.0033 | 50   | 2.3716          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:775c5703e16c17d61a84b349785b09cea1ed0ce24cd58be7f5424614a39e717b
+oid sha256:26e07eba4d31f3f0eb93cc8605b588a9b3fa1e82f079e717d5da57ee326a1df2
 size 25236362