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/63b2c3d17a7119c4_train_data.json
 model_type: AutoModelForCausalLM
@@ -90,7 +90,7 @@ wandb_name: 23bd49e2-e6e3-4aaf-9ec2-e88a5dc7e63f
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: 23bd49e2-e6e3-4aaf-9ec2-e88a5dc7e63f
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -101,6 +101,8 @@ xformers_attention: null
 # 5f81226d-d3c8-28c3-3141-e20fe4ecf530
 
 This model is a fine-tuned version of [unsloth/gemma-7b-it](https://huggingface.co/unsloth/gemma-7b-it) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.4109
 
 ## 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        | 0.0001 | 1    | 3.3750          |
+| 3.1999        | 0.0006 | 10   | 2.7063          |
+| 2.4459        | 0.0012 | 20   | 2.5182          |
+| 2.2607        | 0.0018 | 30   | 2.4519          |
+| 2.6541        | 0.0023 | 40   | 2.4153          |
+| 2.4092        | 0.0029 | 50   | 2.4109          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c91654717265c47a62049ee2ba750e84eb1654e848bf08891e19d64db55f5f75
+oid sha256:73fbe8dc998c3ca16dc96b110ddcb692ceefe4c650d0a8ebf9a64eb5b707ad4e
 size 100149034