training completed[dev]: 512 128
Browse files- README.md +81 -0
- all_results.json +12 -0
- generation_config.json +7 -0
- model.safetensors +1 -1
- runs/Mar30_02-19-53_9404495fcefe/events.out.tfevents.1711765198.9404495fcefe.1247.0 +2 -2
- test_results.json +12 -0
README.md
ADDED
@@ -0,0 +1,81 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: t5-base
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
metrics:
|
7 |
+
- rouge
|
8 |
+
- wer
|
9 |
+
model-index:
|
10 |
+
- name: t-5-base-baseline
|
11 |
+
results: []
|
12 |
+
---
|
13 |
+
|
14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
15 |
+
should probably proofread and complete it, then remove this comment. -->
|
16 |
+
|
17 |
+
# t-5-base-baseline
|
18 |
+
|
19 |
+
This model is a fine-tuned version of [t5-base](https://huggingface.co/t5-base) on an unknown dataset.
|
20 |
+
It achieves the following results on the evaluation set:
|
21 |
+
- Loss: 1.1785
|
22 |
+
- Rouge1: 0.6774
|
23 |
+
- Rouge2: 0.4106
|
24 |
+
- Rougel: 0.6163
|
25 |
+
- Rougelsum: 0.6162
|
26 |
+
- Wer: 0.4869
|
27 |
+
- Bleurt: 0.3779
|
28 |
+
|
29 |
+
## Model description
|
30 |
+
|
31 |
+
More information needed
|
32 |
+
|
33 |
+
## Intended uses & limitations
|
34 |
+
|
35 |
+
More information needed
|
36 |
+
|
37 |
+
## Training and evaluation data
|
38 |
+
|
39 |
+
More information needed
|
40 |
+
|
41 |
+
## Training procedure
|
42 |
+
|
43 |
+
### Training hyperparameters
|
44 |
+
|
45 |
+
The following hyperparameters were used during training:
|
46 |
+
- learning_rate: 2e-05
|
47 |
+
- train_batch_size: 6
|
48 |
+
- eval_batch_size: 6
|
49 |
+
- seed: 42
|
50 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
51 |
+
- lr_scheduler_type: linear
|
52 |
+
- num_epochs: 2
|
53 |
+
- mixed_precision_training: Native AMP
|
54 |
+
|
55 |
+
### Training results
|
56 |
+
|
57 |
+
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Wer | Bleurt |
|
58 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:------:|:------:|
|
59 |
+
| No log | 0.13 | 250 | 1.3316 | 0.651 | 0.3769 | 0.5867 | 0.5868 | 0.5217 | 0.3009 |
|
60 |
+
| 1.7919 | 0.27 | 500 | 1.2776 | 0.6595 | 0.3865 | 0.5963 | 0.5963 | 0.5108 | 0.3009 |
|
61 |
+
| 1.7919 | 0.4 | 750 | 1.2513 | 0.6635 | 0.393 | 0.6015 | 0.6016 | 0.5039 | 0.3009 |
|
62 |
+
| 1.3552 | 0.53 | 1000 | 1.2326 | 0.6668 | 0.3967 | 0.6049 | 0.6049 | 0.5008 | 0.3009 |
|
63 |
+
| 1.3552 | 0.66 | 1250 | 1.2236 | 0.6692 | 0.4 | 0.6073 | 0.6073 | 0.4972 | 0.3314 |
|
64 |
+
| 1.3074 | 0.8 | 1500 | 1.2118 | 0.6713 | 0.4022 | 0.6094 | 0.6094 | 0.4953 | 0.3314 |
|
65 |
+
| 1.3074 | 0.93 | 1750 | 1.2022 | 0.6715 | 0.4035 | 0.6106 | 0.6106 | 0.4932 | 0.2798 |
|
66 |
+
| 1.3037 | 1.06 | 2000 | 1.1972 | 0.6731 | 0.4053 | 0.6118 | 0.6118 | 0.4916 | 0.3771 |
|
67 |
+
| 1.3037 | 1.2 | 2250 | 1.1909 | 0.675 | 0.4068 | 0.6137 | 0.6136 | 0.4905 | 0.3314 |
|
68 |
+
| 1.2676 | 1.33 | 2500 | 1.1889 | 0.6761 | 0.4087 | 0.6144 | 0.6144 | 0.4893 | 0.3314 |
|
69 |
+
| 1.2676 | 1.46 | 2750 | 1.1848 | 0.6763 | 0.4091 | 0.6151 | 0.6151 | 0.4884 | 0.3314 |
|
70 |
+
| 1.2796 | 1.6 | 3000 | 1.1829 | 0.6771 | 0.4095 | 0.6155 | 0.6155 | 0.488 | 0.3123 |
|
71 |
+
| 1.2796 | 1.73 | 3250 | 1.1808 | 0.6769 | 0.4101 | 0.6159 | 0.6159 | 0.4876 | 0.3779 |
|
72 |
+
| 1.2489 | 1.86 | 3500 | 1.1787 | 0.6772 | 0.4105 | 0.6162 | 0.6162 | 0.4869 | 0.3771 |
|
73 |
+
| 1.2489 | 1.99 | 3750 | 1.1785 | 0.6774 | 0.4106 | 0.6163 | 0.6162 | 0.4869 | 0.3779 |
|
74 |
+
|
75 |
+
|
76 |
+
### Framework versions
|
77 |
+
|
78 |
+
- Transformers 4.38.2
|
79 |
+
- Pytorch 2.2.1+cu121
|
80 |
+
- Datasets 2.18.0
|
81 |
+
- Tokenizers 0.15.2
|
all_results.json
ADDED
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"test_BLEURT": -0.9706,
|
3 |
+
"test_WER": 0.4816,
|
4 |
+
"test_loss": 1.195426344871521,
|
5 |
+
"test_rouge1": 0.6823,
|
6 |
+
"test_rouge2": 0.4189,
|
7 |
+
"test_rougeL": 0.6225,
|
8 |
+
"test_rougeLsum": 0.6219,
|
9 |
+
"test_runtime": 31.876,
|
10 |
+
"test_samples_per_second": 11.827,
|
11 |
+
"test_steps_per_second": 1.976
|
12 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"decoder_start_token_id": 0,
|
4 |
+
"eos_token_id": 1,
|
5 |
+
"pad_token_id": 0,
|
6 |
+
"transformers_version": "4.38.2"
|
7 |
+
}
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 891644712
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0b9613afbb9d6a6140659f4336ce375e04d821d1506dcda5db5e31ff0cf1c38a
|
3 |
size 891644712
|
runs/Mar30_02-19-53_9404495fcefe/events.out.tfevents.1711765198.9404495fcefe.1247.0
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7d680ebf640682e5c704e98c675270309c65587d32949cdab9980c31217703da
|
3 |
+
size 15967
|
test_results.json
ADDED
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"test_BLEURT": -0.9706,
|
3 |
+
"test_WER": 0.4816,
|
4 |
+
"test_loss": 1.195426344871521,
|
5 |
+
"test_rouge1": 0.6823,
|
6 |
+
"test_rouge2": 0.4189,
|
7 |
+
"test_rougeL": 0.6225,
|
8 |
+
"test_rougeLsum": 0.6219,
|
9 |
+
"test_runtime": 31.876,
|
10 |
+
"test_samples_per_second": 11.827,
|
11 |
+
"test_steps_per_second": 1.976
|
12 |
+
}
|