Model save

README.md

@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [deepseek-ai/deepseek-coder-7b-instruct-v1.5](https://huggingface.co/deepseek-ai/deepseek-coder-7b-instruct-v1.5) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.9089
+- Loss: 1.0356
 
 ## Model description
 
@@ -36,24 +36,25 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 5e-06
-- train_batch_size: 4
-- eval_batch_size: 4
+- train_batch_size: 2
+- eval_batch_size: 2
 - seed: 42
-- gradient_accumulation_steps: 16
-- total_train_batch_size: 64
+- distributed_type: multi-GPU
+- num_devices: 4
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 16
+- total_eval_batch_size: 8
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine
 - lr_scheduler_warmup_steps: 10
-- num_epochs: 4
+- num_epochs: 2
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 0.0199        | 1.0   | 1    | 0.9079          |
-| 0.0199        | 2.0   | 2    | 0.9081          |
-| 0.0199        | 3.0   | 3    | 0.9107          |
-| 0.0199        | 4.0   | 4    | 0.9089          |
+| 0.2366        | 1.0   | 1    | 1.0393          |
+| 0.3171        | 2.0   | 2    | 1.0356          |
 
 
 ### Framework versions