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/9d89d053de857c98_train_data.json
 model_type: AutoModelForCausalLM
@@ -90,7 +90,7 @@ wandb_name: 5ae3b7bb-7d8b-4837-9cdf-a80ee679de89
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: 5ae3b7bb-7d8b-4837-9cdf-a80ee679de89
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -101,6 +101,8 @@ xformers_attention: null
 # 2dad033c-4784-42ce-133e-8c273b9ed41c
 
 This model is a fine-tuned version of [NousResearch/Meta-Llama-3-8B-Alternate-Tokenizer](https://huggingface.co/NousResearch/Meta-Llama-3-8B-Alternate-Tokenizer) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.7157
 
 ## 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        | 0.0000 | 1    | 2.2553          |
+| 2.082         | 0.0005 | 10   | 2.0848          |
+| 1.9053        | 0.0009 | 20   | 1.7952          |
+| 1.7729        | 0.0014 | 30   | 1.7358          |
+| 1.6578        | 0.0019 | 40   | 1.7219          |
+| 1.6041        | 0.0024 | 50   | 1.7157          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58afda9d56487cd3b8602847ef5d9ce84220c34db6a74c49af3765fe6567652d
+oid sha256:304cf18d3dd3f118ced04dc1202120fea040d4a2cca04a7117581fe65716cb93
 size 84047370