End of training

README.md

@@ -64,7 +64,7 @@ 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/b18f68398ab8e3b5_train_data.json
 model_type: AutoModelForCausalLM
@@ -89,7 +89,7 @@ wandb_name: 2a899e37-543f-4f31-9eb9-33fe206963ee
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: 2a899e37-543f-4f31-9eb9-33fe206963ee
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -100,6 +100,8 @@ xformers_attention: null
 # b134c54c-9462-843b-ec10-c8f32463b69c
 
 This model is a fine-tuned version of [HuggingFaceM4/tiny-random-LlamaForCausalLM](https://huggingface.co/HuggingFaceM4/tiny-random-LlamaForCausalLM) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 10.3817
 
 ## Model description
 
@@ -126,14 +128,19 @@ 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        | 0.0035 | 1    | 10.3894         |
+| 10.3658       | 0.0352 | 10   | 10.3881         |
+| 10.374        | 0.0705 | 20   | 10.3852         |
+| 10.3712       | 0.1057 | 30   | 10.3831         |
+| 10.3741       | 0.1410 | 40   | 10.3819         |
+| 10.3721       | 0.1762 | 50   | 10.3817         |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bba89af7bbc926dfdecad8a8687b213e506a856ad63608654d82143e2fda31ec
+oid sha256:56bc015d07d8143cd456112f9add8acfeda34369ee21c058c25c4852d2c9f032
 size 33666