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/13fe2da19dfd2cc8_train_data.json
 model_type: AutoModelForCausalLM
@@ -90,7 +90,7 @@ wandb_name: 87e605dc-7855-4690-84e6-8164f5e9f81e
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: 87e605dc-7855-4690-84e6-8164f5e9f81e
-warmup_steps: 1
+warmup_steps: 2
 weight_decay: 0.0
 xformers_attention: null
 
@@ -101,6 +101,8 @@ xformers_attention: null
 # 87e605dc-7855-4690-84e6-8164f5e9f81e
 
 This model is a fine-tuned version of [unsloth/tinyllama](https://huggingface.co/unsloth/tinyllama) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.2608
 
 ## Model description
 
@@ -128,13 +130,18 @@ 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: 50
 
 ### Training results
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
 | No log        | 0.0028 | 1    | 4.3551          |
+| 3.6053        | 0.0277 | 10   | 3.0411          |
+| 2.8277        | 0.0554 | 20   | 2.6206          |
+| 2.4681        | 0.0831 | 30   | 2.3795          |
+| 2.3263        | 0.1108 | 40   | 2.2777          |
+| 2.2721        | 0.1386 | 50   | 2.2608          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a4688a6278d0aff93a0532613f6edc0f4bd7798549c1518a5cdaab28e35e7aa
+oid sha256:beb3258ac9ab5e0dbc42d269acd32ee84190b71245057bd46901aaf4e898eda8
 size 25342042