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/a3c9e9e6152f5465_train_data.json
 model_type: AutoModelForCausalLM
@@ -92,7 +92,7 @@ wandb_name: e385d764-6bfd-46b4-b5c5-7e0e1dbc84bb
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: e385d764-6bfd-46b4-b5c5-7e0e1dbc84bb
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -103,6 +103,8 @@ xformers_attention: null
 # dd64d11d-ab56-40d6-8e31-d59ccda2769f
 
 This model is a fine-tuned version of [heegyu/WizardVicuna-open-llama-3b-v2](https://huggingface.co/heegyu/WizardVicuna-open-llama-3b-v2) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1670
 
 ## 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        | 0.0011 | 1    | 0.2809          |
+| 0.2355        | 0.0109 | 10   | 0.2501          |
+| 0.1628        | 0.0218 | 20   | 0.1868          |
+| 0.1349        | 0.0326 | 30   | 0.1726          |
+| 0.1564        | 0.0435 | 40   | 0.1675          |
+| 0.1299        | 0.0544 | 50   | 0.1670          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9be8a520ccfc8e0f2f4d12edafe2c13edbca3b7fba40002b1f00199f21ad019f
+oid sha256:4c22d1cf9b5423c9701e4a5ac6ab04f367d2e4b954123a3e6bd3ba2a33beb9ce
 size 50982842