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/36517e709d3ba2d3_train_data.json
 model_type: AutoModelForCausalLM
@@ -90,7 +90,7 @@ wandb_name: df599836-bbfd-49f6-a757-5c5fca5e9da8
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: df599836-bbfd-49f6-a757-5c5fca5e9da8
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -101,6 +101,8 @@ xformers_attention: null
 # e124c0a6-bff2-9820-acf8-1237fc8463f8
 
 This model is a fine-tuned version of [unsloth/llama-3-8b-Instruct](https://huggingface.co/unsloth/llama-3-8b-Instruct) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.3968
 
 ## 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        | 0.0004 | 1    | 2.9947          |
+| 2.8571        | 0.0042 | 10   | 2.8203          |
+| 2.5022        | 0.0085 | 20   | 2.5769          |
+| 2.4647        | 0.0127 | 30   | 2.4376          |
+| 2.4006        | 0.0170 | 40   | 2.4022          |
+| 2.2941        | 0.0212 | 50   | 2.3968          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41656f7ebb6e8c1e299ce44316645e38ecb53660c4fa100138d9c7bd6e4fd5be
+oid sha256:34d4eb3c9eba9f84936263fe28609b96a495012a4893ad8ec96c9cd6077298cb
 size 84047370