End of training

README.md

@@ -66,7 +66,7 @@ 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/ffc3f58dd484b795_train_data.json
 model_type: AutoModelForCausalLM
@@ -91,7 +91,7 @@ wandb_name: 2cea2f99-2186-4c6e-992c-091d7e4a3365
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: 2cea2f99-2186-4c6e-992c-091d7e4a3365
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -102,6 +102,8 @@ xformers_attention: null
 # 7a866d7f-b300-95b3-abda-b06123c7d0b0
 
 This model is a fine-tuned version of [NousResearch/Hermes-3-Llama-3.1-8B](https://huggingface.co/NousResearch/Hermes-3-Llama-3.1-8B) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.2752
 
 ## 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        | 0.0003 | 1    | 1.5785          |
+| 1.4257        | 0.0026 | 10   | 1.1762          |
+| 0.4485        | 0.0052 | 20   | 0.3973          |
+| 0.3264        | 0.0078 | 30   | 0.3233          |
+| 0.2693        | 0.0104 | 40   | 0.2838          |
+| 0.2861        | 0.0129 | 50   | 0.2752          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bed0cbab891e93ad8d3623039dbc3e54351a006e4c2fbed175c112ea2f629b56
+oid sha256:5d92f86cfa5929127ff3dcd0bb1da5a572d903588a394b375e3e4ef96e9b0795
 size 84047370