End of training

README.md

@@ -1,6 +1,6 @@
 ---
 license: apache-2.0
-base_model: t5-small
+base_model: t5-base
 tags:
 - generated_from_trainer
 datasets:
@@ -16,13 +16,13 @@ model-index:
     dataset:
       name: opus_books
       type: opus_books
-      config: en-pt
+      config: es-pt
       split: train
-      args: en-pt
+      args: es-pt
     metrics:
     - name: Bleu
       type: bleu
-      value: 0.3989
+      value: 0.8634
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -30,11 +30,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 # opus_books_es_pt
 
-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 [t5-base](https://huggingface.co/t5-base) on the opus_books dataset.
 It achieves the following results on the evaluation set:
-- Loss: 3.3303
-- Bleu: 0.3989
-- Gen Len: 17.5302
+- Loss: 2.3338
+- Bleu: 0.8634
+- Gen Len: 18.4624
 
 ## Model description
 
@@ -54,8 +54,8 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 2e-05
-- train_batch_size: 16
-- eval_batch_size: 16
+- train_batch_size: 8
+- eval_batch_size: 8
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
@@ -66,16 +66,16 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Bleu   | Gen Len |
 |:-------------:|:-----:|:----:|:---------------:|:------:|:-------:|
-| No log        | 1.0   | 71   | 3.7759          | 0.5559 | 16.9715 |
-| No log        | 2.0   | 142  | 3.5343          | 0.517  | 17.2776 |
-| No log        | 3.0   | 213  | 3.4102          | 0.4355 | 17.4448 |
-| No log        | 4.0   | 284  | 3.3491          | 0.4057 | 17.516  |
-| No log        | 5.0   | 355  | 3.3303          | 0.3989 | 17.5302 |
+| No log        | 1.0   | 133  | 2.5425          | 0.5463 | 18.5526 |
+| No log        | 2.0   | 266  | 2.4200          | 0.7483 | 18.515  |
+| No log        | 3.0   | 399  | 2.3680          | 0.7772 | 18.5226 |
+| 2.705         | 4.0   | 532  | 2.3432          | 0.8192 | 18.4962 |
+| 2.705         | 5.0   | 665  | 2.3338          | 0.8634 | 18.4624 |
 
 
 ### Framework versions
 
 - Transformers 4.36.1
-- Pytorch 2.1.0+cu121
-- Datasets 2.15.0
+- Pytorch 2.0.0
+- Datasets 2.1.0
 - Tokenizers 0.15.0

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52d19bbb208486b780016794d3702f05c8763ab3105dbbb7c1e737aa19184555
+oid sha256:044eee3e57364eb7b029f74c1914596642eecdcb1bd00b85b77c5cd2d2f2d85c
 size 891644712

runs/Dec17_14-29-40_222b4dc5c326/events.out.tfevents.1702823381.222b4dc5c326.42.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d73fc141f5543be713240a0a190d623171cb3da290e9ffc6f0e47299306c033
-size 6634
+oid sha256:a917ad8ac542c1c3dca75e5d128d185e2d5791b8020c1f4e1f3e59ec8d6d23f9
+size 7728