End of training

README.md

@@ -64,7 +64,7 @@ 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/5aa481aafe9887da_train_data.json
 model_type: AutoModelForCausalLM
@@ -89,7 +89,7 @@ wandb_name: ed74e10b-b01f-41f6-8404-7bad9053d62b
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: ed74e10b-b01f-41f6-8404-7bad9053d62b
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -100,6 +100,8 @@ xformers_attention: null
 # ed74e10b-b01f-41f6-8404-7bad9053d62b
 
 This model is a fine-tuned version of [NousResearch/Yarn-Llama-2-7b-64k](https://huggingface.co/NousResearch/Yarn-Llama-2-7b-64k) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.3887
 
 ## Model description
 
@@ -126,14 +128,19 @@ 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        | 0.0033 | 1    | 1.5814          |
+| 6.2149        | 0.0329 | 10   | 1.5433          |
+| 6.018         | 0.0658 | 20   | 1.4256          |
+| 5.5577        | 0.0987 | 30   | 1.3944          |
+| 5.4495        | 0.1316 | 40   | 1.3895          |
+| 5.0081        | 0.1645 | 50   | 1.3887          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:823dcb5aa96f9a8584540c8a2e5726e0689d214cd113b38d9db6b24afe6fc602
+oid sha256:a345f4a3094fbbd9cfaa0a1f73de9259568fd77f77d181e25d45960274387b1b
 size 80115210