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/0978bbd0f6e05684_train_data.json
 model_type: AutoModelForCausalLM
@@ -90,7 +90,7 @@ wandb_name: 5de7b49b-4dff-4a17-9193-6d28cb60bf62
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: 5de7b49b-4dff-4a17-9193-6d28cb60bf62
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -101,6 +101,8 @@ xformers_attention: null
 # 5de7b49b-4dff-4a17-9193-6d28cb60bf62
 
 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: 10.4235
 
 ## 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        | 0.0007 | 1    | 10.4358         |
+| 10.4524       | 0.0071 | 10   | 10.4338         |
+| 10.4113       | 0.0142 | 20   | 10.4292         |
+| 10.3971       | 0.0212 | 30   | 10.4256         |
+| 10.4289       | 0.0283 | 40   | 10.4238         |
+| 10.4022       | 0.0354 | 50   | 10.4235         |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e5671c2aa86b6712256544099007a16255525c783d7e9d2cacc909e34e026197
+oid sha256:8e62d56486515826479622edc21661408a4e9ef9bda4011cca8dec5fad1f8990
 size 33666