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/65fd82ad19f16c75_train_data.json
 model_type: AutoModelForCausalLM
@@ -92,7 +92,7 @@ wandb_name: 220f5bdf-ee52-4d23-b6fc-214a608a9a57
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: 220f5bdf-ee52-4d23-b6fc-214a608a9a57
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -103,6 +103,8 @@ xformers_attention: null
 # 220f5bdf-ee52-4d23-b6fc-214a608a9a57
 
 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: 0.2170
 
 ## 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    | 2.3392          |
+| 7.4539        | 0.0005 | 10   | 1.6229          |
+| 2.2435        | 0.0010 | 20   | 0.4580          |
+| 1.5351        | 0.0015 | 30   | 0.2728          |
+| 1.3549        | 0.0020 | 40   | 0.2227          |
+| 1.0639        | 0.0025 | 50   | 0.2170          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e27f740fbadab2ab7d86472aca17f19fe373c7d32d469998bd5b585a2a2f0b8c
+oid sha256:c73b199fd9069304426be76af5aba35c2594045303ff9baf0aa001bf0eabeb76
 size 25236362