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/ce816352783d6c6e_train_data.json
 model_type: AutoModelForCausalLM
@@ -89,7 +89,7 @@ wandb_name: 461e6e57-c33a-4f33-b0b1-af14904088ab
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: 461e6e57-c33a-4f33-b0b1-af14904088ab
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -100,6 +100,8 @@ xformers_attention: null
 # 461e6e57-c33a-4f33-b0b1-af14904088ab
 
 This model is a fine-tuned version of [trl-internal-testing/tiny-random-LlamaForCausalLM](https://huggingface.co/trl-internal-testing/tiny-random-LlamaForCausalLM) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 10.3775
 
 ## 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        | 0.0000 | 1    | 10.3781         |
+| 10.3777       | 0.0003 | 10   | 10.3780         |
+| 10.3767       | 0.0006 | 20   | 10.3778         |
+| 10.3771       | 0.0009 | 30   | 10.3776         |
+| 10.3773       | 0.0012 | 40   | 10.3775         |
+| 10.3749       | 0.0015 | 50   | 10.3775         |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7da61dcab9b6859dbee7e72ad4b32918bb8b24be62a2cbabe53a23e05352a17f
+oid sha256:3808dceb5e0e67953542a2c532b34c51127b59760edeb12ccd94f4fdc9627260
 size 33666