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/4889bc8206f0e694_train_data.json
 model_type: AutoModelForCausalLM
@@ -90,7 +90,7 @@ wandb_name: c35c0a4a-d327-439a-8ada-cff09572ce21
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: c35c0a4a-d327-439a-8ada-cff09572ce21
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -101,6 +101,8 @@ xformers_attention: null
 # caf2b39a-2bd8-cd64-e860-1519bca9563b
 
 This model is a fine-tuned version of [unsloth/mistral-7b-v0.2](https://huggingface.co/unsloth/mistral-7b-v0.2) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.6960
 
 ## 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        | 0.0000 | 1    | 1.2287          |
+| 4.4813        | 0.0002 | 10   | 0.9441          |
+| 3.4189        | 0.0005 | 20   | 0.7675          |
+| 2.9912        | 0.0007 | 30   | 0.7161          |
+| 2.8351        | 0.0009 | 40   | 0.6992          |
+| 2.5839        | 0.0012 | 50   | 0.6960          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e889376fa87a02554a027bb67743b6983dc6b36e57069f9c1e87176c6853fb1
+oid sha256:8b5abffe5d8a45d01e24eb264b1967526a63a8c6b86edf6aa8a8ed92f7d3f1a3
 size 84047370