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/76751ed2b4662481_train_data.json
 model_type: AutoModelForCausalLM
@@ -92,7 +92,7 @@ wandb_name: 534f2501-25a2-454e-b259-017951fac668
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: 534f2501-25a2-454e-b259-017951fac668
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -103,6 +103,8 @@ xformers_attention: null
 # dcc8c1d1-bb81-dade-08a6-f71099da91bb
 
 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: 3.4873
 
 ## 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        | 0.0000 | 1    | 5.3835          |
+| 19.5946       | 0.0001 | 10   | 3.9862          |
+| 14.0964       | 0.0003 | 20   | 3.5989          |
+| 14.9684       | 0.0004 | 30   | 3.5218          |
+| 14.4036       | 0.0006 | 40   | 3.4930          |
+| 14.3889       | 0.0007 | 50   | 3.4873          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80fa7b9f81effaeb1827dc67961aa705cc2725039ef660a74e263ec57863f62c
+oid sha256:f572538502e8246e8e7b175759cfe6d7e267a66913275d0eceee736222f052d5
 size 84047370