End of training

README.md

@@ -59,7 +59,7 @@ 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/d9bf134d8c3d5800_train_data.json
 model_type: AutoModelForCausalLM
@@ -86,7 +86,7 @@ wandb_name: c02917cc-8f87-4062-9fdc-c3e78cea4836
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: c02917cc-8f87-4062-9fdc-c3e78cea4836
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -97,6 +97,8 @@ xformers_attention: null
 # c02917cc-8f87-4062-9fdc-c3e78cea4836
 
 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: 1.7612
 
 ## Model description
 
@@ -123,14 +125,19 @@ 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    | 2.2269          |
+| 9.6147        | 0.0013 | 10   | 2.0748          |
+| 7.7107        | 0.0026 | 20   | 1.8417          |
+| 6.855         | 0.0038 | 30   | 1.7847          |
+| 7.0684        | 0.0051 | 40   | 1.7659          |
+| 6.9004        | 0.0064 | 50   | 1.7612          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ab99f3f0d4e804d9cb2c93113de625924047979d5099b5ce7980e020c1fd754
+oid sha256:36471be237bc34c1469507e13be244ad08cc98d9737f60a3bc121e7ee2d8144f
 size 25236362