Commit
•
519fa2c
1
Parent(s):
6942ea1
update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,90 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
datasets:
|
| 6 |
+
- break_data
|
| 7 |
+
metrics:
|
| 8 |
+
- bleu
|
| 9 |
+
model-index:
|
| 10 |
+
- name: t5-large-finetuned-break-qdmr-decomposition
|
| 11 |
+
results:
|
| 12 |
+
- task:
|
| 13 |
+
name: Sequence-to-sequence Language Modeling
|
| 14 |
+
type: text2text-generation
|
| 15 |
+
dataset:
|
| 16 |
+
name: break_data
|
| 17 |
+
type: break_data
|
| 18 |
+
config: QDMR
|
| 19 |
+
split: validation
|
| 20 |
+
args: QDMR
|
| 21 |
+
metrics:
|
| 22 |
+
- name: Bleu
|
| 23 |
+
type: bleu
|
| 24 |
+
value: 0.22169382457557757
|
| 25 |
+
---
|
| 26 |
+
|
| 27 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 28 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 29 |
+
|
| 30 |
+
# t5-large-finetuned-break-qdmr-decomposition
|
| 31 |
+
|
| 32 |
+
This model is a fine-tuned version of [t5-large](https://huggingface.co/t5-large) on the break_data dataset.
|
| 33 |
+
It achieves the following results on the evaluation set:
|
| 34 |
+
- Loss: 0.1729
|
| 35 |
+
- Bleu: 0.2217
|
| 36 |
+
- Precisions: [0.928997558602713, 0.8089017135403285, 0.702859772673759, 0.6237525532535746]
|
| 37 |
+
- Brevity Penalty: 0.2926
|
| 38 |
+
- Length Ratio: 0.4487
|
| 39 |
+
- Translation Length: 108954
|
| 40 |
+
- Reference Length: 242845
|
| 41 |
+
|
| 42 |
+
## Model description
|
| 43 |
+
|
| 44 |
+
More information needed
|
| 45 |
+
|
| 46 |
+
## Intended uses & limitations
|
| 47 |
+
|
| 48 |
+
More information needed
|
| 49 |
+
|
| 50 |
+
## Training and evaluation data
|
| 51 |
+
|
| 52 |
+
More information needed
|
| 53 |
+
|
| 54 |
+
## Training procedure
|
| 55 |
+
|
| 56 |
+
### Training hyperparameters
|
| 57 |
+
|
| 58 |
+
The following hyperparameters were used during training:
|
| 59 |
+
- learning_rate: 0.0001
|
| 60 |
+
- train_batch_size: 2
|
| 61 |
+
- eval_batch_size: 2
|
| 62 |
+
- seed: 42
|
| 63 |
+
- gradient_accumulation_steps: 64
|
| 64 |
+
- total_train_batch_size: 128
|
| 65 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 66 |
+
- lr_scheduler_type: linear
|
| 67 |
+
- num_epochs: 10
|
| 68 |
+
|
| 69 |
+
### Training results
|
| 70 |
+
|
| 71 |
+
| Training Loss | Epoch | Step | Validation Loss | Bleu | Precisions | Brevity Penalty | Length Ratio | Translation Length | Reference Length |
|
| 72 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|:--------------------------------------------------------------------------------:|:---------------:|:------------:|:------------------:|:----------------:|
|
| 73 |
+
| No log | 1.0 | 346 | 0.2217 | 0.2190 | [0.9212396799650076, 0.7929651493459373, 0.6788405612515656, 0.5938190356122556] | 0.2973 | 0.4519 | 109738 | 242845 |
|
| 74 |
+
| 0.3597 | 2.0 | 692 | 0.1898 | 0.2213 | [0.9278319373884388, 0.8053505444154309, 0.6955454787943451, 0.6142312076867599] | 0.2944 | 0.4499 | 109245 | 242845 |
|
| 75 |
+
| 0.1943 | 3.0 | 1038 | 0.1780 | 0.2213 | [0.9274868270332188, 0.805860010851872, 0.6987019924149351, 0.6179670572886331] | 0.2936 | 0.4494 | 109125 | 242845 |
|
| 76 |
+
| 0.1943 | 4.0 | 1385 | 0.1722 | 0.2209 | [0.9296421064226247, 0.8077246177717601, 0.6996456975263051, 0.618521199103474] | 0.2926 | 0.4486 | 108943 | 242845 |
|
| 77 |
+
| 0.1588 | 5.0 | 1731 | 0.1708 | 0.2221 | [0.9263551333376084, 0.8062900028599888, 0.7016414100962206, 0.6226711690731253] | 0.2938 | 0.4495 | 109159 | 242845 |
|
| 78 |
+
| 0.1395 | 6.0 | 2077 | 0.1699 | 0.2209 | [0.9307313480922355, 0.8116381660470879, 0.7052247221178113, 0.6255682084446319] | 0.2907 | 0.4473 | 108635 | 242845 |
|
| 79 |
+
| 0.1395 | 7.0 | 2423 | 0.1699 | 0.2219 | [0.9294629418890643, 0.8099284613256393, 0.7035550704165061, 0.623971523603898] | 0.2927 | 0.4487 | 108964 | 242845 |
|
| 80 |
+
| 0.1245 | 8.0 | 2770 | 0.1717 | 0.2215 | [0.9293905921457364, 0.8091923795588686, 0.7026416387368962, 0.6239635641714353] | 0.2924 | 0.4485 | 108909 | 242845 |
|
| 81 |
+
| 0.1152 | 9.0 | 3116 | 0.1724 | 0.2215 | [0.9294489230034706, 0.8091424956007671, 0.7027003876051995, 0.6234366789280084] | 0.2924 | 0.4485 | 108914 | 242845 |
|
| 82 |
+
| 0.1152 | 9.99 | 3460 | 0.1729 | 0.2217 | [0.928997558602713, 0.8089017135403285, 0.702859772673759, 0.6237525532535746] | 0.2926 | 0.4487 | 108954 | 242845 |
|
| 83 |
+
|
| 84 |
+
|
| 85 |
+
### Framework versions
|
| 86 |
+
|
| 87 |
+
- Transformers 4.30.2
|
| 88 |
+
- Pytorch 2.0.1+cu118
|
| 89 |
+
- Datasets 2.13.1
|
| 90 |
+
- Tokenizers 0.13.3
|