Model save

README.md

@@ -16,9 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # full_review
 
-This model is a fine-tuned version of [Qwen/Qwen2.5-7B](https://huggingface.co/Qwen/Qwen2.5-7B) on the openreview_full_review dataset.
+This model is a fine-tuned version of [Qwen/Qwen2.5-7B](https://huggingface.co/Qwen/Qwen2.5-7B) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.6107
+- Loss: 1.6306
 
 ## Model description
 
@@ -42,9 +42,9 @@ The following hyperparameters were used during training:
 - eval_batch_size: 1
 - seed: 42
 - distributed_type: multi-GPU
-- num_devices: 4
-- total_train_batch_size: 32
-- total_eval_batch_size: 4
+- num_devices: 8
+- total_train_batch_size: 64
+- total_eval_batch_size: 8
 - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: cosine
 - lr_scheduler_warmup_ratio: 0.1
@@ -54,11 +54,8 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 1.6658        | 0.5089 | 600  | 1.6607          |
-| 1.5992        | 1.0178 | 1200 | 1.6405          |
-| 1.6182        | 1.5267 | 1800 | 1.6241          |
-| 1.5463        | 2.0356 | 2400 | 1.6182          |
-| 1.5356        | 2.5445 | 3000 | 1.6117          |
+| 1.6261        | 1.0169 | 600  | 1.6485          |
+| 1.5922        | 2.0339 | 1200 | 1.6306          |
 
 
 ### Framework versions