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/a87227c2bc002e03_train_data.json
 model_type: AutoModelForCausalLM
@@ -92,7 +92,7 @@ wandb_name: 76d0e767-6bbe-483d-954b-e67a04f97841
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: 76d0e767-6bbe-483d-954b-e67a04f97841
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -103,6 +103,8 @@ xformers_attention: null
 # 880b0062-7dc3-470d-a567-8d9bddacad23
 
 This model is a fine-tuned version of [NousResearch/Yarn-Mistral-7b-64k](https://huggingface.co/NousResearch/Yarn-Mistral-7b-64k) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.1137
 
 ## Model description
 
@@ -129,14 +131,19 @@ 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        | 0.0002 | 1    | 1.4592          |
+| 5.5568        | 0.0017 | 10   | 1.2137          |
+| 4.4071        | 0.0034 | 20   | 1.1461          |
+| 4.6977        | 0.0051 | 30   | 1.1235          |
+| 4.6641        | 0.0068 | 40   | 1.1151          |
+| 4.2082        | 0.0085 | 50   | 1.1137          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ed5f073678f4d40a5a7c9ec887f8bc26fb9fc2e54d9957f3e78703695b303e5
+oid sha256:a98738bce991a2ae79e1cbb712263347ad4f0aa105c708be0dbbeb460a13f8de
 size 84047370