End of training
Browse files- README.md +17 -24
- model.safetensors +1 -1
README.md
CHANGED
|
@@ -1,11 +1,6 @@
|
|
| 1 |
---
|
| 2 |
tags:
|
| 3 |
- generated_from_trainer
|
| 4 |
-
metrics:
|
| 5 |
-
- precision
|
| 6 |
-
- recall
|
| 7 |
-
- f1
|
| 8 |
-
- accuracy
|
| 9 |
model-index:
|
| 10 |
- name: UDOP-finetuned-DocLayNet-3
|
| 11 |
results: []
|
|
@@ -18,11 +13,16 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 18 |
|
| 19 |
This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
-
-
|
| 22 |
-
-
|
| 23 |
-
-
|
| 24 |
-
-
|
| 25 |
-
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 26 |
|
| 27 |
## Model description
|
| 28 |
|
|
@@ -41,27 +41,20 @@ More information needed
|
|
| 41 |
### Training hyperparameters
|
| 42 |
|
| 43 |
The following hyperparameters were used during training:
|
| 44 |
-
- learning_rate:
|
| 45 |
-
- train_batch_size:
|
| 46 |
-
- eval_batch_size:
|
| 47 |
- seed: 42
|
|
|
|
|
|
|
| 48 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 49 |
- lr_scheduler_type: linear
|
| 50 |
- lr_scheduler_warmup_ratio: 0.1
|
| 51 |
-
- training_steps:
|
| 52 |
-
|
| 53 |
-
### Training results
|
| 54 |
-
|
| 55 |
-
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
| 56 |
-
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
|
| 57 |
-
| 1.0703 | 5.81 | 500 | 0.7495 | 0.6946 | 0.7581 | 0.7249 | 0.8152 |
|
| 58 |
-
| 0.2524 | 11.63 | 1000 | 0.8365 | 0.6714 | 0.7688 | 0.7168 | 0.7962 |
|
| 59 |
-
| 0.136 | 17.44 | 1500 | 0.7624 | 0.6743 | 0.7903 | 0.7277 | 0.8246 |
|
| 60 |
-
|
| 61 |
|
| 62 |
### Framework versions
|
| 63 |
|
| 64 |
- Transformers 4.39.0.dev0
|
| 65 |
-
- Pytorch 2.1
|
| 66 |
- Datasets 2.18.0
|
| 67 |
- Tokenizers 0.15.2
|
|
|
|
| 1 |
---
|
| 2 |
tags:
|
| 3 |
- generated_from_trainer
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4 |
model-index:
|
| 5 |
- name: UDOP-finetuned-DocLayNet-3
|
| 6 |
results: []
|
|
|
|
| 13 |
|
| 14 |
This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
|
| 15 |
It achieves the following results on the evaluation set:
|
| 16 |
+
- eval_loss: 0.7407
|
| 17 |
+
- eval_precision: 0.6058
|
| 18 |
+
- eval_recall: 0.5870
|
| 19 |
+
- eval_f1: 0.5962
|
| 20 |
+
- eval_accuracy: 0.7863
|
| 21 |
+
- eval_runtime: 16.2128
|
| 22 |
+
- eval_samples_per_second: 3.886
|
| 23 |
+
- eval_steps_per_second: 1.974
|
| 24 |
+
- epoch: 18.6
|
| 25 |
+
- step: 800
|
| 26 |
|
| 27 |
## Model description
|
| 28 |
|
|
|
|
| 41 |
### Training hyperparameters
|
| 42 |
|
| 43 |
The following hyperparameters were used during training:
|
| 44 |
+
- learning_rate: 2e-05
|
| 45 |
+
- train_batch_size: 2
|
| 46 |
+
- eval_batch_size: 2
|
| 47 |
- seed: 42
|
| 48 |
+
- gradient_accumulation_steps: 8
|
| 49 |
+
- total_train_batch_size: 16
|
| 50 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 51 |
- lr_scheduler_type: linear
|
| 52 |
- lr_scheduler_warmup_ratio: 0.1
|
| 53 |
+
- training_steps: 1000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 54 |
|
| 55 |
### Framework versions
|
| 56 |
|
| 57 |
- Transformers 4.39.0.dev0
|
| 58 |
+
- Pytorch 2.2.1+cu121
|
| 59 |
- Datasets 2.18.0
|
| 60 |
- Tokenizers 0.15.2
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1355766676
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:18232de3292659132c05f65eebfabf492419318e5acc6a70042059621b58b991
|
| 3 |
size 1355766676
|