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/fc6556bef624abe2_train_data.json
 model_type: AutoModelForCausalLM
@@ -91,7 +91,7 @@ wandb_name: 52a40105-9474-496b-9fd5-193267764fd6
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: 52a40105-9474-496b-9fd5-193267764fd6
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -102,6 +102,8 @@ xformers_attention: null
 # d0ca77b3-de94-45ff-7cda-41c853c009c6
 
 This model is a fine-tuned version of [HuggingFaceH4/tiny-random-LlamaForCausalLM](https://huggingface.co/HuggingFaceH4/tiny-random-LlamaForCausalLM) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 10.3589
 
 ## Model description
 
@@ -128,14 +130,19 @@ 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        | 0.0002 | 1    | 10.3640         |
+| 10.3623       | 0.0017 | 10   | 10.3632         |
+| 10.3634       | 0.0034 | 20   | 10.3612         |
+| 10.3647       | 0.0051 | 30   | 10.3598         |
+| 10.3597       | 0.0068 | 40   | 10.3590         |
+| 10.3584       | 0.0085 | 50   | 10.3589         |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:143a52e46764f0038cbf531f436516025c7f119cbd96d1450cc4a8db57e219b9
+oid sha256:ca1066834febab6eba31c3534091d98a31545f6149db82bad0d245adb4de9d5a
 size 33666