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/f4b386ab5b6129fe_train_data.json
 model_type: AutoModelForCausalLM
@@ -89,7 +89,7 @@ wandb_name: b1ced71a-7c1a-4319-bf12-cb423f062ae7
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: b1ced71a-7c1a-4319-bf12-cb423f062ae7
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -100,6 +100,8 @@ xformers_attention: null
 # a438ba4c-70af-a16e-eecd-f67b359ed272
 
 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: 0.6118
 
 ## 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        | 0.0007 | 1    | 0.8495          |
+| 0.6592        | 0.0068 | 10   | 0.7865          |
+| 0.5597        | 0.0137 | 20   | 0.6528          |
+| 0.609         | 0.0205 | 30   | 0.6227          |
+| 0.5579        | 0.0274 | 40   | 0.6132          |
+| 0.4916        | 0.0342 | 50   | 0.6118          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e75bf4b49faf80165f7880305c0c2b39960d7506c7ac6c7d0f9ea295febf877
+oid sha256:5613e4da612fc09ee4d6a07addb54d8f1e2f9c99e623a25d3bcaf63fc834ccb9
 size 84047370