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/c4a268226a4c41a8_train_data.json
 model_type: AutoModelForCausalLM
@@ -92,7 +92,7 @@ wandb_name: 27b1101c-92c0-4cf0-ba6a-03a34cd699b6
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: 27b1101c-92c0-4cf0-ba6a-03a34cd699b6
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -103,6 +103,8 @@ xformers_attention: null
 # 4f190d2b-a12c-042e-acd6-4a90f8b0320a
 
 This model is a fine-tuned version of [DeepMount00/Llama-3-8b-Ita](https://huggingface.co/DeepMount00/Llama-3-8b-Ita) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.7710
 
 ## Model description
 
@@ -129,14 +131,19 @@ 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        | 0.0001 | 1    | 0.9704          |
+| 0.9344        | 0.0008 | 10   | 0.9052          |
+| 0.8193        | 0.0017 | 20   | 0.8120          |
+| 0.7412        | 0.0025 | 30   | 0.7804          |
+| 0.811         | 0.0034 | 40   | 0.7724          |
+| 0.6917        | 0.0042 | 50   | 0.7710          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9dab97a67303949684f788738b5bed4647296cfe6e6272c1a8b6c81222356b00
+oid sha256:f5a23715b1f9f4e681a7ab1cde6bdcd07f3fe920f80a0b9c9a1d4e1e9c1d6b89
 size 84047370