https://huggingface.co/abhikr487/lab2_efficient

README.md

@@ -22,7 +22,7 @@ model-index:
     metrics:
     - name: Bleu
       type: bleu
-      value: 50.29242417597565
+      value: 51.56963230203597
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -32,8 +32,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [Helsinki-NLP/opus-mt-en-fr](https://huggingface.co/Helsinki-NLP/opus-mt-en-fr) on the kde4 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.9594
-- Bleu: 50.2924
+- Loss: 0.8936
+- Bleu: 51.5696
 
 ## Model description
 
@@ -53,15 +53,16 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 2e-05
-- train_batch_size: 64
+- train_batch_size: 32
 - eval_batch_size: 64
 - seed: 42
-- gradient_accumulation_steps: 2
+- gradient_accumulation_steps: 4
 - total_train_batch_size: 128
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine
 - lr_scheduler_warmup_ratio: 0.1
 - num_epochs: 2
+- mixed_precision_training: Native AMP
 
 ### Training results
 

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a1c7554d7b1c6064bcad50862a2ca9896524be4721027732b35afc2ba859e64
+oid sha256:9a1d3d7add0197415769767af7674d72e034eea84717eee957a26a7f3c70a61b
 size 298705768

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d16b3da439db74f99eec8b232f35c7f32b83b0770c973b10fe9ef395111dd530
+oid sha256:b8130e8c9d8102c2e6b79e77c073d74aa4148f49058f8867c2e8b907d4587890
 size 5112