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/177cf310bb056dd2_train_data.json
 model_type: AutoModelForCausalLM
@@ -90,7 +90,7 @@ wandb_name: f89d2b33-ad51-4971-beba-5ade3b17b0b9
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: f89d2b33-ad51-4971-beba-5ade3b17b0b9
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -101,6 +101,8 @@ xformers_attention: null
 # e0d7760f-3f4c-48e9-8fb3-6eda3857a592
 
 This model is a fine-tuned version of [unsloth/mistral-7b-v0.3](https://huggingface.co/unsloth/mistral-7b-v0.3) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.5106
 
 ## 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    | 1.7880          |
+| 6.9275        | 0.0013 | 10   | 1.6407          |
+| 5.9363        | 0.0027 | 20   | 1.5450          |
+| 5.9678        | 0.0040 | 30   | 1.5205          |
+| 6.2598        | 0.0054 | 40   | 1.5124          |
+| 5.535         | 0.0067 | 50   | 1.5106          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:82b73a4d50264c61088653086f88c35169a1770aab89c9d0aa97795af678c1cb
+oid sha256:ff1bab889cb91b087642fbe84a4ef1b7b74ec1c2f4bd0eac0e35884f6ac7c408
 size 84047370