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: 8
 mlflow_experiment_name: /tmp/85c2119c8d8593c5_train_data.json
 model_type: AutoModelForCausalLM
@@ -92,7 +92,7 @@ wandb_name: 046af7c5-985e-4829-8a22-5ec259958bab
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: 046af7c5-985e-4829-8a22-5ec259958bab
-warmup_steps: 1
+warmup_steps: 2
 weight_decay: 0.0
 xformers_attention: null
 
@@ -103,6 +103,8 @@ xformers_attention: null
 # 046af7c5-985e-4829-8a22-5ec259958bab
 
 This model is a fine-tuned version of [Maykeye/TinyLLama-v0](https://huggingface.co/Maykeye/TinyLLama-v0) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 11.4611
 
 ## Model description
 
@@ -130,13 +132,17 @@ The following hyperparameters were used during training:
 - 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
+- training_steps: 29
 
 ### Training results
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
 | No log        | 0.0356 | 1    | 12.9937         |
+| No log        | 0.2133 | 6    | 12.3682         |
+| 12.5778       | 0.4267 | 12   | 11.8535         |
+| 12.5778       | 0.64   | 18   | 11.5809         |
+| 11.7256       | 0.8533 | 24   | 11.4611         |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95bcb0c39df9861744c7ba13fc0849b07c8cc94bee9643cfab272347129ae8ed
+oid sha256:ccf8a0a7f3bb4ce95f1d5d4d3e49fd5255a2a31573b8d7e741607e38a1203e5f
 size 416906