Model save
Browse files- README.md +18 -32
- config.json +1 -1
- generation_config.json +1 -1
- model.safetensors +1 -1
- runs/Apr22_22-45-04_12febbe3b1cc/events.out.tfevents.1713825949.12febbe3b1cc.34.0 +3 -0
- runs/Apr22_22-47-59_12febbe3b1cc/events.out.tfevents.1713826096.12febbe3b1cc.34.1 +3 -0
- runs/Apr22_22-51-08_12febbe3b1cc/events.out.tfevents.1713826271.12febbe3b1cc.34.2 +3 -0
- tokenizer.json +1 -1
- training_args.bin +2 -2
README.md
CHANGED
@@ -17,14 +17,14 @@ should probably proofread and complete it, then remove this comment. -->
|
|
17 |
|
18 |
This model is a fine-tuned version of [yazdipour/text-to-sparql-t5-small-qald9](https://huggingface.co/yazdipour/text-to-sparql-t5-small-qald9) on the None dataset.
|
19 |
It achieves the following results on the evaluation set:
|
20 |
-
- Loss: 0.
|
21 |
- Gen Len: 19.0
|
22 |
-
- P: 0.
|
23 |
-
- R: 0.
|
24 |
-
- F1: 0.
|
25 |
-
- Bleu-score:
|
26 |
-
- Bleu-precisions: [
|
27 |
-
- Bleu-bp: 0.
|
28 |
|
29 |
## Model description
|
30 |
|
@@ -49,38 +49,24 @@ The following hyperparameters were used during training:
|
|
49 |
- seed: 42
|
50 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
51 |
- lr_scheduler_type: linear
|
52 |
-
- num_epochs:
|
53 |
- mixed_precision_training: Native AMP
|
54 |
|
55 |
### Training results
|
56 |
|
57 |
-
| Training Loss | Epoch | Step | Validation Loss | Gen Len | P | R | F1 | Bleu-score | Bleu-precisions
|
58 |
-
|
59 |
-
| No log | 1.0 |
|
60 |
-
| No log | 2.0 |
|
61 |
-
| No log | 3.0 |
|
62 |
-
| No log | 4.0 |
|
63 |
-
| No log | 5.0 |
|
64 |
-
| No log | 6.0 |
|
65 |
-
| No log | 7.0 | 196 | 0.0008 | 19.0 | 0.6665 | 0.1769 | 0.4085 | 12.0496 | [98.39650145772595, 98.13559322033899, 97.77327935222672, 97.23618090452261] | 0.1231 |
|
66 |
-
| No log | 8.0 | 224 | 0.0003 | 19.0 | 0.6665 | 0.1769 | 0.4085 | 12.0496 | [98.39650145772595, 98.13559322033899, 97.77327935222672, 97.23618090452261] | 0.1231 |
|
67 |
-
| No log | 9.0 | 252 | 0.0005 | 19.0 | 0.6665 | 0.1769 | 0.4085 | 12.0496 | [98.39650145772595, 98.13559322033899, 97.77327935222672, 97.23618090452261] | 0.1231 |
|
68 |
-
| No log | 10.0 | 280 | 0.0002 | 19.0 | 0.6665 | 0.1769 | 0.4085 | 12.0496 | [98.39650145772595, 98.13559322033899, 97.77327935222672, 97.23618090452261] | 0.1231 |
|
69 |
-
| No log | 11.0 | 308 | 0.0002 | 19.0 | 0.6665 | 0.1769 | 0.4085 | 12.0496 | [98.39650145772595, 98.13559322033899, 97.77327935222672, 97.23618090452261] | 0.1231 |
|
70 |
-
| No log | 12.0 | 336 | 0.0001 | 19.0 | 0.6665 | 0.1769 | 0.4085 | 12.0496 | [98.39650145772595, 98.13559322033899, 97.77327935222672, 97.23618090452261] | 0.1231 |
|
71 |
-
| No log | 13.0 | 364 | 0.0002 | 19.0 | 0.6665 | 0.1769 | 0.4085 | 12.0496 | [98.39650145772595, 98.13559322033899, 97.77327935222672, 97.23618090452261] | 0.1231 |
|
72 |
-
| No log | 14.0 | 392 | 0.0001 | 19.0 | 0.6665 | 0.1769 | 0.4085 | 12.0496 | [98.39650145772595, 98.13559322033899, 97.77327935222672, 97.23618090452261] | 0.1231 |
|
73 |
-
| No log | 15.0 | 420 | 0.0001 | 19.0 | 0.6665 | 0.1769 | 0.4085 | 12.0496 | [98.39650145772595, 98.13559322033899, 97.77327935222672, 97.23618090452261] | 0.1231 |
|
74 |
-
| No log | 16.0 | 448 | 0.0001 | 19.0 | 0.6665 | 0.1769 | 0.4085 | 12.0496 | [98.39650145772595, 98.13559322033899, 97.77327935222672, 97.23618090452261] | 0.1231 |
|
75 |
-
| No log | 17.0 | 476 | 0.0001 | 19.0 | 0.6665 | 0.1769 | 0.4085 | 12.0496 | [98.39650145772595, 98.13559322033899, 97.77327935222672, 97.23618090452261] | 0.1231 |
|
76 |
-
| 0.088 | 18.0 | 504 | 0.0001 | 19.0 | 0.6665 | 0.1769 | 0.4085 | 12.0496 | [98.39650145772595, 98.13559322033899, 97.77327935222672, 97.23618090452261] | 0.1231 |
|
77 |
-
| 0.088 | 19.0 | 532 | 0.0001 | 19.0 | 0.6665 | 0.1769 | 0.4085 | 12.0496 | [98.39650145772595, 98.13559322033899, 97.77327935222672, 97.23618090452261] | 0.1231 |
|
78 |
-
| 0.088 | 20.0 | 560 | 0.0001 | 19.0 | 0.6665 | 0.1769 | 0.4085 | 12.0496 | [98.39650145772595, 98.13559322033899, 97.77327935222672, 97.23618090452261] | 0.1231 |
|
79 |
|
80 |
|
81 |
### Framework versions
|
82 |
|
83 |
-
- Transformers 4.
|
84 |
- Pytorch 2.1.2
|
85 |
-
- Datasets 2.
|
86 |
- Tokenizers 0.15.2
|
|
|
17 |
|
18 |
This model is a fine-tuned version of [yazdipour/text-to-sparql-t5-small-qald9](https://huggingface.co/yazdipour/text-to-sparql-t5-small-qald9) on the None dataset.
|
19 |
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 0.1904
|
21 |
- Gen Len: 19.0
|
22 |
+
- P: 0.6916
|
23 |
+
- R: 0.1882
|
24 |
+
- F1: 0.4284
|
25 |
+
- Bleu-score: 18.7965
|
26 |
+
- Bleu-precisions: [90.93198992443325, 84.87165483342436, 81.27608825283244, 77.3473407747866]
|
27 |
+
- Bleu-bp: 0.2252
|
28 |
|
29 |
## Model description
|
30 |
|
|
|
49 |
- seed: 42
|
50 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
51 |
- lr_scheduler_type: linear
|
52 |
+
- num_epochs: 6
|
53 |
- mixed_precision_training: Native AMP
|
54 |
|
55 |
### Training results
|
56 |
|
57 |
+
| Training Loss | Epoch | Step | Validation Loss | Gen Len | P | R | F1 | Bleu-score | Bleu-precisions | Bleu-bp |
|
58 |
+
|:-------------:|:-----:|:----:|:---------------:|:-------:|:------:|:------:|:------:|:----------:|:-----------------------------------------------------------------------------:|:-------:|
|
59 |
+
| No log | 1.0 | 20 | 0.9776 | 19.0 | 0.5292 | 0.1024 | 0.3076 | 5.9735 | [80.91603053435115, 56.84062059238364, 43.75, 33.693693693693696] | 0.1171 |
|
60 |
+
| No log | 2.0 | 40 | 0.4290 | 19.0 | 0.6499 | 0.1726 | 0.4010 | 16.8298 | [86.98903290129611, 74.29805615550755, 68.90459363957598, 63.082901554404145] | 0.2312 |
|
61 |
+
| No log | 3.0 | 60 | 0.2963 | 19.0 | 0.6656 | 0.1836 | 0.4141 | 16.5278 | [88.91739353514623, 77.82729805013928, 73.36989640463132, 68.66173503698722] | 0.2151 |
|
62 |
+
| No log | 4.0 | 80 | 0.2363 | 19.0 | 0.6889 | 0.1852 | 0.4255 | 18.5923 | [90.74823053589485, 84.64912280701755, 81.07784431137725, 77.24274406332454] | 0.2232 |
|
63 |
+
| No log | 5.0 | 100 | 0.2048 | 19.0 | 0.6939 | 0.1885 | 0.4296 | 18.9610 | [91.04627766599597, 85.22355507088332, 81.78571428571429, 77.98165137614679] | 0.2261 |
|
64 |
+
| No log | 6.0 | 120 | 0.1904 | 19.0 | 0.6916 | 0.1882 | 0.4284 | 18.7965 | [90.93198992443325, 84.87165483342436, 81.27608825283244, 77.3473407747866] | 0.2252 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
65 |
|
66 |
|
67 |
### Framework versions
|
68 |
|
69 |
+
- Transformers 4.39.3
|
70 |
- Pytorch 2.1.2
|
71 |
+
- Datasets 2.18.0
|
72 |
- Tokenizers 0.15.2
|
config.json
CHANGED
@@ -56,7 +56,7 @@
|
|
56 |
}
|
57 |
},
|
58 |
"torch_dtype": "float32",
|
59 |
-
"transformers_version": "4.
|
60 |
"use_cache": true,
|
61 |
"vocab_size": 32128
|
62 |
}
|
|
|
56 |
}
|
57 |
},
|
58 |
"torch_dtype": "float32",
|
59 |
+
"transformers_version": "4.39.3",
|
60 |
"use_cache": true,
|
61 |
"vocab_size": 32128
|
62 |
}
|
generation_config.json
CHANGED
@@ -2,5 +2,5 @@
|
|
2 |
"decoder_start_token_id": 0,
|
3 |
"eos_token_id": 1,
|
4 |
"pad_token_id": 0,
|
5 |
-
"transformers_version": "4.
|
6 |
}
|
|
|
2 |
"decoder_start_token_id": 0,
|
3 |
"eos_token_id": 1,
|
4 |
"pad_token_id": 0,
|
5 |
+
"transformers_version": "4.39.3"
|
6 |
}
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 242041896
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3040f6082e1b000bed853febc7324ae3b7bb0ec2acbc40d92281ff2458ed6e9c
|
3 |
size 242041896
|
runs/Apr22_22-45-04_12febbe3b1cc/events.out.tfevents.1713825949.12febbe3b1cc.34.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c03f9ee19a193466c333fae80986cf1f2ef92643b1abf21084f4671aaa82263f
|
3 |
+
size 23117
|
runs/Apr22_22-47-59_12febbe3b1cc/events.out.tfevents.1713826096.12febbe3b1cc.34.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3c4c66b4ed78860bb33dfb060bbd1e8f0700bdcd4ffe22f5d08bc48295483c24
|
3 |
+
size 9381
|
runs/Apr22_22-51-08_12febbe3b1cc/events.out.tfevents.1713826271.12febbe3b1cc.34.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:37b04cc264ec5718df79187021c3d0e51952027e0782f19bb610d032870473ea
|
3 |
+
size 9381
|
tokenizer.json
CHANGED
@@ -2,7 +2,7 @@
|
|
2 |
"version": "1.0",
|
3 |
"truncation": {
|
4 |
"direction": "Right",
|
5 |
-
"max_length":
|
6 |
"strategy": "LongestFirst",
|
7 |
"stride": 0
|
8 |
},
|
|
|
2 |
"version": "1.0",
|
3 |
"truncation": {
|
4 |
"direction": "Right",
|
5 |
+
"max_length": 311,
|
6 |
"strategy": "LongestFirst",
|
7 |
"stride": 0
|
8 |
},
|
training_args.bin
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:c5003922b9e2b265dba83758a3758b4d3d7cd30d639265dc99db198d5a5bb781
|
3 |
+
size 5176
|