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/0843e95ee80abad0_train_data.json
 model_type: AutoModelForCausalLM
@@ -91,7 +91,7 @@ wandb_name: b43e697e-b6c6-404e-b8e1-76f07dcaad35
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: b43e697e-b6c6-404e-b8e1-76f07dcaad35
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -102,6 +102,8 @@ xformers_attention: null
 # b33ba7ba-c80b-2416-fcaf-e3f33ae4821b
 
 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: 10.3691
 
 ## 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        | 0.0022 | 1    | 10.3702         |
+| 10.3703       | 0.0220 | 10   | 10.3700         |
+| 10.3734       | 0.0441 | 20   | 10.3696         |
+| 10.3701       | 0.0661 | 30   | 10.3693         |
+| 10.3669       | 0.0881 | 40   | 10.3692         |
+| 10.3669       | 0.1101 | 50   | 10.3691         |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb94379d4011e047603a958da829ac55fb239b05f6ff9f5ba32950816e48b463
+oid sha256:f4011155362dd39f89d4c5db5e0865ad361463972eb9024d44a3819a499370b1
 size 33666