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/5156a924eae71b31_train_data.json
 model_type: AutoModelForCausalLM
@@ -92,7 +92,7 @@ wandb_name: 000d9439-6dc4-4004-b9ff-e45915a45b67
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: 000d9439-6dc4-4004-b9ff-e45915a45b67
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -103,6 +103,8 @@ xformers_attention: null
 # f88a2499-7863-40fe-8e8a-a717b5e783be
 
 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: 3.5257
 
 ## 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    | 4.9655          |
+| 4.7221        | 0.0011 | 10   | 4.5966          |
+| 4.1157        | 0.0022 | 20   | 3.9367          |
+| 3.572         | 0.0033 | 30   | 3.6732          |
+| 3.5714        | 0.0044 | 40   | 3.5499          |
+| 3.2603        | 0.0054 | 50   | 3.5257          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da510a4e438530a8e3ed13365665680c50b307140a15679b4d6e91b2cee768b8
+oid sha256:0e7c17464010053adfce9f5848840802791177edc3eb47ace255ea2c0d9ff06f
 size 50982842