Training complete

README.md

@@ -24,7 +24,7 @@ model-index:
     metrics:
     - name: Bleu
       type: bleu
-      value: 52.90371209759549
+      value: 52.08491969802704
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -34,9 +34,8 @@ 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: 0.8554
-- Model Preparation Time: 0.0039
-- Bleu: 52.9037
+- Loss: 0.8809
+- Bleu: 52.0849
 
 ## Model description
 
@@ -56,8 +55,8 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 2e-05
-- train_batch_size: 32
-- eval_batch_size: 64
+- train_batch_size: 64
+- eval_batch_size: 128
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
@@ -70,7 +69,7 @@ The following hyperparameters were used during training:
 
 ### Framework versions
 
-- Transformers 4.44.2
-- Pytorch 2.4.1+cu121
+- Transformers 4.45.1
+- Pytorch 2.4.0
 - Datasets 3.0.1
-- Tokenizers 0.19.1
+- Tokenizers 0.20.0

generation_config.json

@@ -12,5 +12,5 @@
   "num_beams": 4,
   "pad_token_id": 59513,
   "renormalize_logits": true,
-  "transformers_version": "4.44.2"
+  "transformers_version": "4.45.1"
 }

runs/Oct19_07-31-04_a80db434f000/events.out.tfevents.1729324871.a80db434f000.30.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:311b619a195f471d8c627281d28cdcf373ab8f0f55b4c8aa8aa73f5e3a93d28f
-size 9738
+oid sha256:4d618218492a68167d1d55802a90ca2381170893acbf4753faddf481ad28c541
+size 10092

runs/Oct19_07-31-04_a80db434f000/events.out.tfevents.1729332363.a80db434f000.30.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b8b67e7fa59cd73f22b4509f0e62bdcfddb2be3c9cee1e003359ec1655c17e1
+size 407