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/5f4ede612e9164dd_train_data.json
 model_type: AutoModelForCausalLM
@@ -92,7 +92,7 @@ wandb_name: 0249fb8a-a8bc-4e19-8e1d-927140aa744c
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: 0249fb8a-a8bc-4e19-8e1d-927140aa744c
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -103,6 +103,8 @@ xformers_attention: null
 # 70289470-0353-4797-9941-b0c91972f138
 
 This model is a fine-tuned version of [tiiuae/falcon-7b](https://huggingface.co/tiiuae/falcon-7b) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.5950
 
 ## 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        | 0.0033 | 1    | 2.2976          |
+| 9.5121        | 0.0327 | 10   | 2.2191          |
+| 7.8665        | 0.0654 | 20   | 1.7415          |
+| 7.1608        | 0.0981 | 30   | 1.6466          |
+| 6.4862        | 0.1308 | 40   | 1.6009          |
+| 6.2259        | 0.1635 | 50   | 1.5950          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10b8f4cf8278f51c591d08e57d07be5f36cef85b6faee9a22f2da30cec1ccfa5
+oid sha256:b42c8ff00155a2bfacf62f14738e5cd575172543819a5ed8c51c70189aca58bc
 size 65367946