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/283529cc249a710a_train_data.json
 model_type: AutoModelForCausalLM
@@ -93,7 +93,7 @@ wandb_name: 7617e66a-7992-48b3-945a-d90fb92d6465
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: 7617e66a-7992-48b3-945a-d90fb92d6465
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -104,6 +104,8 @@ xformers_attention: null
 # 4e910b17-9122-dde5-73a0-4324568a8d03
 
 This model is a fine-tuned version of [TinyLlama/TinyLlama_v1.1](https://huggingface.co/TinyLlama/TinyLlama_v1.1) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.4118
 
 ## 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        | 0.0047 | 1    | 1.8301          |
+| 1.7524        | 0.0467 | 10   | 1.6688          |
+| 1.5118        | 0.0935 | 20   | 1.4941          |
+| 1.4469        | 0.1402 | 30   | 1.4368          |
+| 1.4416        | 0.1869 | 40   | 1.4162          |
+| 1.4465        | 0.2336 | 50   | 1.4118          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e2eb96a8fa193c55efc8a46d5778575b30d8121c510158304f7b34f7ca49893
+oid sha256:31c890349771101065e5952dcc9d3586777ec4fd5cbddd5929bab700e7a9be0c
 size 25342042