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/30ea7f734daf098c_train_data.json
 model_type: AutoModelForCausalLM
@@ -90,7 +90,7 @@ wandb_name: 838f5336-e02f-4107-ba8a-a9ab66e7518c
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: 838f5336-e02f-4107-ba8a-a9ab66e7518c
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -101,6 +101,8 @@ xformers_attention: null
 # 6cde6f7e-6345-b822-f7bc-5410183f36bb
 
 This model is a fine-tuned version of [unsloth/mistral-7b-v0.3](https://huggingface.co/unsloth/mistral-7b-v0.3) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.1230
 
 ## 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        | 0.0008 | 1    | 1.6690          |
+| 5.8111        | 0.0083 | 10   | 1.2979          |
+| 4.7368        | 0.0166 | 20   | 1.1431          |
+| 4.4379        | 0.0249 | 30   | 1.1310          |
+| 4.6996        | 0.0333 | 40   | 1.1245          |
+| 4.355         | 0.0416 | 50   | 1.1230          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:edadb6318ea7febe5d6a93f30e84743de19ace6f192369f420590f1867130c7a
+oid sha256:f8f76df109eac4f5e810bcb538afe145e1ef87f65f2e8093e41eca7233fc0877
 size 84047370