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/8d9ccb93234edf5c_train_data.json
 model_type: AutoModelForCausalLM
@@ -90,7 +90,7 @@ wandb_name: 958cfbcb-52ec-4cd3-a60a-bdef302bec31
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: 958cfbcb-52ec-4cd3-a60a-bdef302bec31
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -101,6 +101,8 @@ xformers_attention: null
 # 5753769d-ea13-47b0-8fb0-0ac23b133b1b
 
 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: 10.3732
 
 ## Model description
 
@@ -127,14 +129,19 @@ 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        | 0.0003 | 1    | 10.3744         |
+| 10.3759       | 0.0031 | 10   | 10.3742         |
+| 10.3725       | 0.0063 | 20   | 10.3738         |
+| 10.3728       | 0.0094 | 30   | 10.3734         |
+| 10.3755       | 0.0126 | 40   | 10.3733         |
+| 10.3741       | 0.0157 | 50   | 10.3732         |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e02b177c858225c69ceda4efcd156b6e9221d8c2bd0a664f8b6d8914f517d24
+oid sha256:4e0726c2c56fe7da8961d5a51af7c6c5ff621a2e2d72e412fa98336b4078a0c5
 size 33666