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/4ca6ec97f17aaaed_train_data.json
 model_type: AutoModelForCausalLM
@@ -90,7 +90,7 @@ wandb_name: d62f37b6-ccf3-45e1-856f-dcf819d05ecf
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: d62f37b6-ccf3-45e1-856f-dcf819d05ecf
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -101,6 +101,8 @@ xformers_attention: null
 # d62f37b6-ccf3-45e1-856f-dcf819d05ecf
 
 This model is a fine-tuned version of [unsloth/gemma-2-9b-it](https://huggingface.co/unsloth/gemma-2-9b-it) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.2337
 
 ## Model description
 
@@ -127,14 +129,19 @@ 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        | 0.0007 | 1    | 2.8181          |
+| 2.6584        | 0.0075 | 10   | 1.9564          |
+| 1.4303        | 0.0149 | 20   | 1.4005          |
+| 1.1902        | 0.0224 | 30   | 1.2775          |
+| 1.4079        | 0.0298 | 40   | 1.2404          |
+| 1.2773        | 0.0373 | 50   | 1.2337          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:595bbf1997f9d5d59a70ffee38fd9518fd12e4f77eb42276b74364131e17e6ba
+oid sha256:f664a6b2a842821ebbecefb87798f106e191cc2b6de7cc61a37b7c33b7e709a7
 size 108247866