End of training

README.md

@@ -18,15 +18,15 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [naver-clova-ix/donut-base](https://huggingface.co/naver-clova-ix/donut-base) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4744
-- Bleu: 0.0692
-- Precisions: [0.8295218295218295, 0.7735849056603774, 0.7247956403269755, 0.6838709677419355]
-- Brevity Penalty: 0.0921
-- Length Ratio: 0.2955
-- Translation Length: 481
+- Loss: 0.4050
+- Bleu: 0.0639
+- Precisions: [0.79957805907173, 0.7386091127098321, 0.7083333333333334, 0.6765676567656765]
+- Brevity Penalty: 0.0876
+- Length Ratio: 0.2912
+- Translation Length: 474
 - Reference Length: 1628
-- Cer: 0.7527
-- Wer: 0.8232
+- Cer: 0.7653
+- Wer: 0.8371
 
 ## Model description
 
@@ -45,7 +45,7 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 1.5730263550306148e-05
+- learning_rate: 1.2045081648781836e-05
 - train_batch_size: 1
 - eval_batch_size: 1
 - seed: 42
@@ -53,15 +53,18 @@ The following hyperparameters were used during training:
 - total_train_batch_size: 2
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 2
+- num_epochs: 5
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Bleu   | Precisions                                                                       | Brevity Penalty | Length Ratio | Translation Length | Reference Length | Cer    | Wer    |
 |:-------------:|:-----:|:----:|:---------------:|:------:|:--------------------------------------------------------------------------------:|:---------------:|:------------:|:------------------:|:----------------:|:------:|:------:|
-| 0.0161        | 1.0   | 253  | 0.5007          | 0.0697 | [0.8189300411522634, 0.7505827505827506, 0.7043010752688172, 0.6603174603174603] | 0.0954          | 0.2985       | 486                | 1628             | 0.7575 | 0.8257 |
-| 0.0151        | 2.0   | 506  | 0.4744          | 0.0692 | [0.8295218295218295, 0.7735849056603774, 0.7247956403269755, 0.6838709677419355] | 0.0921          | 0.2955       | 481                | 1628             | 0.7527 | 0.8232 |
+| 0.9353        | 1.0   | 253  | 0.6228          | 0.0486 | [0.7096774193548387, 0.6053921568627451, 0.5612535612535613, 0.5102040816326531] | 0.0820          | 0.2856       | 465                | 1628             | 0.7751 | 0.8592 |
+| 0.462         | 2.0   | 506  | 0.4846          | 0.0568 | [0.7913978494623656, 0.7058823529411765, 0.6609686609686609, 0.6224489795918368] | 0.0820          | 0.2856       | 465                | 1628             | 0.7650 | 0.8423 |
+| 0.4071        | 3.0   | 759  | 0.4226          | 0.0626 | [0.7899159663865546, 0.711217183770883, 0.6767955801104972, 0.6459016393442623]  | 0.0889          | 0.2924       | 476                | 1628             | 0.7685 | 0.8436 |
+| 0.3007        | 4.0   | 1012 | 0.4092          | 0.0638 | [0.7957894736842105, 0.7344497607655502, 0.7008310249307479, 0.6644736842105263] | 0.0883          | 0.2918       | 475                | 1628             | 0.7640 | 0.8397 |
+| 0.3114        | 5.0   | 1265 | 0.4050          | 0.0639 | [0.79957805907173, 0.7386091127098321, 0.7083333333333334, 0.6765676567656765]   | 0.0876          | 0.2912       | 474                | 1628             | 0.7653 | 0.8371 |
 
 
 ### Framework versions

metrics.jsonl

@@ -2,3 +2,4 @@
 {"eval_loss": 0.4845726191997528, "eval_bleu": 0.05677403569488881, "eval_precisions": [0.7913978494623656, 0.7058823529411765, 0.6609686609686609, 0.6224489795918368], "eval_brevity_penalty": 0.08199678262097645, "eval_length_ratio": 0.2856265356265356, "eval_translation_length": 465, "eval_reference_length": 1628, "eval_cer": 0.7650115721103663, "eval_wer": 0.8422781322989256, "eval_runtime": 74.2244, "eval_samples_per_second": 0.768, "eval_steps_per_second": 0.768, "epoch": 2.0}
 {"eval_loss": 0.4225582778453827, "eval_bleu": 0.06258728631080523, "eval_precisions": [0.7899159663865546, 0.711217183770883, 0.6767955801104972, 0.6459016393442623], "eval_brevity_penalty": 0.08890667390552527, "eval_length_ratio": 0.29238329238329236, "eval_translation_length": 476, "eval_reference_length": 1628, "eval_cer": 0.7685442110284281, "eval_wer": 0.8435798205201185, "eval_runtime": 74.6527, "eval_samples_per_second": 0.764, "eval_steps_per_second": 0.764, "epoch": 3.0}
 {"eval_loss": 0.409177303314209, "eval_bleu": 0.06375586413177027, "eval_precisions": [0.7957894736842105, 0.7344497607655502, 0.7008310249307479, 0.6644736842105263], "eval_brevity_penalty": 0.08826881356184386, "eval_length_ratio": 0.2917690417690418, "eval_translation_length": 475, "eval_reference_length": 1628, "eval_cer": 0.7640123871107425, "eval_wer": 0.839666929775041, "eval_runtime": 74.6634, "eval_samples_per_second": 0.763, "eval_steps_per_second": 0.763, "epoch": 4.0}
+{"eval_loss": 0.40500399470329285, "eval_bleu": 0.06391799322352495, "eval_precisions": [0.79957805907173, 0.7386091127098321, 0.7083333333333334, 0.6765676567656765], "eval_brevity_penalty": 0.08763286710738645, "eval_length_ratio": 0.29115479115479115, "eval_translation_length": 474, "eval_reference_length": 1628, "eval_cer": 0.7653196697608013, "eval_wer": 0.8371441755209847, "eval_runtime": 74.3335, "eval_samples_per_second": 0.767, "eval_steps_per_second": 0.767, "epoch": 5.0}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e46dd39331cbed5b94dad0ccc7810fa2fbd59b443f7c6b7a80306991a1b45dd8
+oid sha256:5c37243ba325b8ab602dbff931cf5aaf2af83b4d72896f6bcea9a364b0b33735
 size 809103512

runs/May30_15-29-21_ip-172-16-168-165.ec2.internal/events.out.tfevents.1717082961.ip-172-16-168-165.ec2.internal.8916.1

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0db72ba757f25c63f8cd56790cd670f10bbed8c360d1d399924eebb6dce3f654
-size 13937
+oid sha256:dbdb008a882eef252485b8e67fdaa88aff28672c0e416f7f8f4d23d22fc70e62
+size 15363