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/1cac2a1c4d61a866_train_data.json
 model_type: AutoModelForCausalLM
@@ -92,7 +92,7 @@ wandb_name: 86f200e3-0b57-48d8-8a57-4874461ba469
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: 86f200e3-0b57-48d8-8a57-4874461ba469
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -103,6 +103,8 @@ xformers_attention: null
 # bfb40f1e-a273-cc8f-3425-54157447d677
 
 This model is a fine-tuned version of [NousResearch/Yarn-Mistral-7b-128k](https://huggingface.co/NousResearch/Yarn-Mistral-7b-128k) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.9657
 
 ## 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        | 0.0001 | 1    | 3.5616          |
+| 10.5872       | 0.0009 | 10   | 1.8805          |
+| 4.8581        | 0.0019 | 20   | 1.0459          |
+| 3.597         | 0.0028 | 30   | 0.9960          |
+| 4.1012        | 0.0038 | 40   | 0.9693          |
+| 3.7209        | 0.0047 | 50   | 0.9657          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b997e3efac264eed62ce463f477c89b8f282ca19224c73cb03fb5ca82770e2a
+oid sha256:d926ff42371437c12ed3f599c7aa0cec8f129a9c4e5e6ddbf32100ce63574858
 size 84047370