End of training

README.md

@@ -66,7 +66,7 @@ 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/c441df2ff485ee77_train_data.json
 model_type: AutoModelForCausalLM
@@ -93,7 +93,7 @@ wandb_name: b775eeb7-0ab1-46b4-be17-23daa557e389
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: b775eeb7-0ab1-46b4-be17-23daa557e389
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -104,6 +104,8 @@ xformers_attention: null
 # b775eeb7-0ab1-46b4-be17-23daa557e389
 
 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: 0.8255
 
 ## Model description
 
@@ -130,14 +132,19 @@ 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        | 0.0011 | 1    | 0.9507          |
+| 3.7606        | 0.0106 | 10   | 0.8952          |
+| 3.2362        | 0.0213 | 20   | 0.8569          |
+| 3.0118        | 0.0319 | 30   | 0.8356          |
+| 3.1935        | 0.0426 | 40   | 0.8273          |
+| 2.8325        | 0.0532 | 50   | 0.8255          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f02cc8b9c92d435d7f5afbc160e5011d4456016fe057d90c2c2448cd87dcb94
+oid sha256:31fb21c53bb49bda93171af28b19979f8f2080d3a823b4755674dda9cd3da599
 size 84047370