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/e9a08c00192565f5_train_data.json
 model_type: AutoModelForCausalLM
@@ -90,7 +90,7 @@ wandb_name: 94eb7de6-8eee-4dc6-b36d-48325400060a
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: 94eb7de6-8eee-4dc6-b36d-48325400060a
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -101,6 +101,8 @@ xformers_attention: null
 # ce903330-4a0c-4825-9999-8943be9cc5f3
 
 This model is a fine-tuned version of [unsloth/Hermes-3-Llama-3.1-8B](https://huggingface.co/unsloth/Hermes-3-Llama-3.1-8B) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.1338
 
 ## 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        | 0.0007 | 1    | 4.1770          |
+| 3.7342        | 0.0071 | 10   | 3.4282          |
+| 1.8547        | 0.0143 | 20   | 1.5567          |
+| 1.3177        | 0.0214 | 30   | 1.2351          |
+| 1.1119        | 0.0285 | 40   | 1.1479          |
+| 1.1207        | 0.0357 | 50   | 1.1338          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a07ea6cfd7aff86442cb479b6a5cfe20b7075df1c866cce07812ca56298903c
+oid sha256:867215cfea8ea45085f231fb6e92e0e690b9b4e75a4a20ffc69cc29cab05361d
 size 84047370