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: 50
+max_steps: 1
 micro_batch_size: 2
 mlflow_experiment_name: /tmp/7bf008f868df7676_train_data.json
 model_type: AutoModelForCausalLM
@@ -92,7 +92,7 @@ wandb_name: b87a1aa2-af60-4e3a-9472-0069e560eb93
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: b87a1aa2-af60-4e3a-9472-0069e560eb93
-warmup_steps: 10
+warmup_steps: 1
 weight_decay: 0.0
 xformers_attention: null
 
@@ -103,8 +103,6 @@ xformers_attention: null
 # b87a1aa2-af60-4e3a-9472-0069e560eb93
 
 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: nan
 
 ## Model description
 
@@ -131,18 +129,14 @@ 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: 10
-- training_steps: 16
+- lr_scheduler_warmup_steps: 2
+- training_steps: 1
 
 ### Training results
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
 | No log        | 0.0635 | 1    | nan             |
-| No log        | 0.2540 | 4    | nan             |
-| 0.0           | 0.5079 | 8    | nan             |
-| 0.0           | 0.7619 | 12   | nan             |
-| 0.0           | 1.0317 | 16   | nan             |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5702e1449ad39a4c34bbca7db19f85b49559f09dbf99326bca4ebcf34e7dcaf3
+oid sha256:91a63a8435ed0708f16832e84a8cc57e13167428547c4b65d1eca21436254955
 size 25236362