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/78d892729ae2d55a_train_data.json
 model_type: AutoModelForCausalLM
@@ -92,7 +92,7 @@ wandb_name: 7ded3f98-bc26-4ed5-8801-6d5a32508b44
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: 7ded3f98-bc26-4ed5-8801-6d5a32508b44
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -103,6 +103,8 @@ xformers_attention: null
 # 6d8a7adc-bc86-d639-0c10-857e2635d700
 
 This model is a fine-tuned version of [microsoft/phi-1_5](https://huggingface.co/microsoft/phi-1_5) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.2311
 
 ## 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        | 0.0002 | 1    | 1.2953          |
+| 1.2986        | 0.0021 | 10   | 1.2798          |
+| 1.2363        | 0.0041 | 20   | 1.2551          |
+| 1.2362        | 0.0062 | 30   | 1.2390          |
+| 1.1591        | 0.0083 | 40   | 1.2322          |
+| 1.2465        | 0.0103 | 50   | 1.2311          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a01de176b1f6da3f0bae90fec9335d10d71f5b152bf305956aa90352afe9bfc
+oid sha256:162d4ef723092b92fb8c2d93a94781280e452ab3102c16d39fd19f2051442fc2
 size 28414730