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/ac97fde3045e6c49_train_data.json
 model_type: AutoModelForCausalLM
@@ -90,7 +90,7 @@ wandb_name: 0c937bed-41f3-4a3f-afb4-4db0e61eff26
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: 0c937bed-41f3-4a3f-afb4-4db0e61eff26
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -101,6 +101,8 @@ xformers_attention: null
 # 01b092b7-7e7a-ccbc-4011-c74e23a869d1
 
 This model is a fine-tuned version of [unsloth/Mistral-Nemo-Base-2407](https://huggingface.co/unsloth/Mistral-Nemo-Base-2407) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.1157
 
 ## 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    | 2.2312          |
+| 8.8291        | 0.0074 | 10   | 2.1780          |
+| 8.6161        | 0.0147 | 20   | 2.1303          |
+| 8.1037        | 0.0221 | 30   | 2.1198          |
+| 8.2349        | 0.0294 | 40   | 2.1164          |
+| 8.4466        | 0.0368 | 50   | 2.1157          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f30c959727ad0279c1b5131a087115e9037172e550dac25069d02b71f9e586c5
+oid sha256:956e9547b1b5bfae3211273132a050fa70c6f4c866179773041fd7f1db47f6f2
 size 114234314