update model card README.md

README.md

@@ -1,28 +1,13 @@
 ---
 license: apache-2.0
-base_model: t5-small
+base_model: Helsinki-NLP/opus-mt-en-fr
 tags:
 - generated_from_trainer
 datasets:
 - opus_books
-metrics:
-- bleu
 model-index:
 - name: my_awesome_opus_books_model
-  results:
-  - task:
-      name: Sequence-to-sequence Language Modeling
-      type: text2text-generation
-    dataset:
-      name: opus_books
-      type: opus_books
-      config: en-fr
-      split: train
-      args: en-fr
-    metrics:
-    - name: Bleu
-      type: bleu
-      value: 5.8566
+  results: []
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -30,11 +15,16 @@ should probably proofread and complete it, then remove this comment. -->
 
 # my_awesome_opus_books_model
 
-This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on the opus_books dataset.
+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 opus_books dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.5833
-- Bleu: 5.8566
-- Gen Len: 17.5702
+- eval_loss: 0.4408
+- eval_bleu: 26.022
+- eval_gen_len: 33.4854
+- eval_runtime: 2692.7929
+- eval_samples_per_second: 9.439
+- eval_steps_per_second: 0.295
+- epoch: 1.0
+- step: 3178
 
 ## Model description
 
@@ -57,20 +47,10 @@ The following hyperparameters were used during training:
 - train_batch_size: 32
 - eval_batch_size: 32
 - seed: 42
-- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- optimizer: Adam with betas=(0.9,0.98) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 5
-
-### Training results
-
-| Training Loss | Epoch | Step  | Validation Loss | Bleu   | Gen Len |
-|:-------------:|:-----:|:-----:|:---------------:|:------:|:-------:|
-| 1.9015        | 1.0   | 2542  | 1.6661          | 5.2359 | 17.6094 |
-| 1.8317        | 2.0   | 5084  | 1.6218          | 5.6007 | 17.5847 |
-| 1.8044        | 3.0   | 7626  | 1.5990          | 5.7289 | 17.5749 |
-| 1.7948        | 4.0   | 10168 | 1.5868          | 5.8245 | 17.5718 |
-| 1.7794        | 5.0   | 12710 | 1.5833          | 5.8566 | 17.5702 |
-
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 15
 
 ### Framework versions