Hugging Face's logo

floflodebilbao
/
long_T5_sum_challenge

Transformers
TensorBoard
Safetensors
longt5
text2text-generation
Generated from Trainer
Model card Files
xet
Metrics Community
floflodebilbao commited on
Commit
9396fb4
·
verified ·
1 Parent(s): 45fb3d7

End of training

Browse files
Files changed (5) hide show
  1. README.md +26 -17
  2. model.safetensors +1 -1
  3. runs/Jul10_14-34-38_tardis/events.out.tfevents.1752150879.tardis.65808.0 +3 -0
  4. runs/Jul10_14-35-17_tardis/events.out.tfevents.1752150918.tardis.66059.0 +3 -0
  5. training_args.bin +1 -1
README.md CHANGED
@@ -22,21 +22,21 @@ should probably proofread and complete it, then remove this comment. -->
22
 
23
  This model is a fine-tuned version of [google/long-t5-tglobal-base](https://huggingface.co/google/long-t5-tglobal-base) on an unknown dataset.
24
  It achieves the following results on the evaluation set:
25
- - Loss: 23.8385
26
- - Rouge1: 0.1833
27
- - Rouge2: 0.0251
28
- - Rougel: 0.1264
29
- - Rougelsum: 0.1268
30
- - Gen Len: 61.76
31
- - Bleu: 0.0071
32
- - Precisions: 0.035
33
  - Brevity Penalty: 1.0
34
- - Length Ratio: 1.7757
35
- - Translation Length: 2145.0
36
  - Reference Length: 1208.0
37
- - Precision: 0.8212
38
- - Recall: 0.8524
39
- - F1: 0.8364
40
  - Hashcode: roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.53.1)
41
 
42
  ## Model description
@@ -64,15 +64,24 @@ The following hyperparameters were used during training:
64
  - total_train_batch_size: 16
65
  - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
66
  - lr_scheduler_type: linear
67
- - num_epochs: 15
68
 
69
  ### Training results
70
 
71
  | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len | Bleu | Precisions | Brevity Penalty | Length Ratio | Translation Length | Reference Length | Precision | Recall | F1 | Hashcode |
72
  |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|:------:|:----------:|:---------------:|:------------:|:------------------:|:----------------:|:---------:|:------:|:------:|:---------------------------------------------------------:|
73
- | 26.784 | 1.0 | 7 | 28.7642 | 0.1857 | 0.0291 | 0.1273 | 0.1274 | 62.14 | 0.0096 | 0.0361 | 1.0 | 1.8228 | 2202.0 | 1208.0 | 0.8208 | 0.8527 | 0.8364 | roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.53.1) |
74
- | 24.3629 | 2.0 | 14 | 26.0446 | 0.1805 | 0.0271 | 0.1237 | 0.1241 | 62.06 | 0.009 | 0.0346 | 1.0 | 1.7955 | 2169.0 | 1208.0 | 0.8199 | 0.8516 | 0.8354 | roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.53.1) |
75
- | 22.7165 | 3.0 | 21 | 23.8385 | 0.1833 | 0.0251 | 0.1264 | 0.1268 | 61.76 | 0.0071 | 0.035 | 1.0 | 1.7757 | 2145.0 | 1208.0 | 0.8212 | 0.8524 | 0.8364 | roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.53.1) |
 
 
 
 
 
 
 
 
 
76
 
77
 
78
  ### Framework versions
 
22
 
23
  This model is a fine-tuned version of [google/long-t5-tglobal-base](https://huggingface.co/google/long-t5-tglobal-base) on an unknown dataset.
24
  It achieves the following results on the evaluation set:
25
+ - Loss: 5.4854
26
+ - Rouge1: 0.213
27
+ - Rouge2: 0.0584
28
+ - Rougel: 0.1599
29
+ - Rougelsum: 0.1594
30
+ - Gen Len: 63.0
31
+ - Bleu: 0.0227
32
+ - Precisions: 0.0483
33
  - Brevity Penalty: 1.0
34
+ - Length Ratio: 1.8816
35
+ - Translation Length: 2273.0
36
  - Reference Length: 1208.0
37
+ - Precision: 0.825
38
+ - Recall: 0.8586
39
+ - F1: 0.8413
40
  - Hashcode: roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.53.1)
41
 
42
  ## Model description
 
64
  - total_train_batch_size: 16
65
  - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
66
  - lr_scheduler_type: linear
67
+ - num_epochs: 12
68
 
69
  ### Training results
70
 
71
  | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len | Bleu | Precisions | Brevity Penalty | Length Ratio | Translation Length | Reference Length | Precision | Recall | F1 | Hashcode |
72
  |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|:------:|:----------:|:---------------:|:------------:|:------------------:|:----------------:|:---------:|:------:|:------:|:---------------------------------------------------------:|
73
+ | No log | 1.0 | 7 | 27.4874 | 0.1894 | 0.0306 | 0.1306 | 0.13 | 62.3 | 0.0098 | 0.0373 | 1.0 | 1.8228 | 2202.0 | 1208.0 | 0.822 | 0.8535 | 0.8374 | roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.53.1) |
74
+ | No log | 2.0 | 14 | 24.5878 | 0.1835 | 0.0281 | 0.1272 | 0.1264 | 62.18 | 0.0096 | 0.0363 | 1.0 | 1.8212 | 2200.0 | 1208.0 | 0.8214 | 0.8526 | 0.8367 | roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.53.1) |
75
+ | No log | 3.0 | 21 | 22.4680 | 0.2061 | 0.0403 | 0.1455 | 0.145 | 62.22 | 0.0131 | 0.0417 | 1.0 | 1.8427 | 2226.0 | 1208.0 | 0.8262 | 0.8566 | 0.8411 | roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.53.1) |
76
+ | No log | 4.0 | 28 | 20.6365 | 0.2107 | 0.0484 | 0.1534 | 0.1519 | 62.42 | 0.019 | 0.0454 | 1.0 | 1.8419 | 2225.0 | 1208.0 | 0.8253 | 0.8572 | 0.8409 | roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.53.1) |
77
+ | No log | 5.0 | 35 | 18.9949 | 0.2169 | 0.0537 | 0.153 | 0.1529 | 62.5 | 0.0193 | 0.0467 | 1.0 | 1.8469 | 2231.0 | 1208.0 | 0.8263 | 0.8584 | 0.842 | roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.53.1) |
78
+ | No log | 6.0 | 42 | 17.3457 | 0.2186 | 0.0567 | 0.1579 | 0.1579 | 62.68 | 0.0216 | 0.0478 | 1.0 | 1.8502 | 2235.0 | 1208.0 | 0.8277 | 0.8589 | 0.843 | roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.53.1) |
79
+ | No log | 7.0 | 49 | 15.5073 | 0.2186 | 0.057 | 0.1596 | 0.1595 | 62.28 | 0.0216 | 0.0473 | 1.0 | 1.832 | 2213.0 | 1208.0 | 0.8281 | 0.8583 | 0.8429 | roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.53.1) |
80
+ | No log | 8.0 | 56 | 13.2173 | 0.2162 | 0.0541 | 0.1537 | 0.1541 | 62.48 | 0.0201 | 0.046 | 1.0 | 1.856 | 2242.0 | 1208.0 | 0.8271 | 0.858 | 0.8422 | roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.53.1) |
81
+ | No log | 9.0 | 63 | 10.4288 | 0.21 | 0.0523 | 0.1517 | 0.1524 | 62.48 | 0.0195 | 0.0451 | 1.0 | 1.8684 | 2257.0 | 1208.0 | 0.8264 | 0.8572 | 0.8415 | roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.53.1) |
82
+ | No log | 10.0 | 70 | 7.6309 | 0.22 | 0.0595 | 0.1633 | 0.1641 | 63.0 | 0.0255 | 0.0492 | 1.0 | 1.894 | 2288.0 | 1208.0 | 0.8285 | 0.8594 | 0.8436 | roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.53.1) |
83
+ | No log | 11.0 | 77 | 5.9244 | 0.2238 | 0.0623 | 0.1702 | 0.1704 | 63.0 | 0.024 | 0.0496 | 1.0 | 1.8949 | 2289.0 | 1208.0 | 0.8284 | 0.86 | 0.8438 | roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.53.1) |
84
+ | No log | 12.0 | 84 | 5.4854 | 0.213 | 0.0584 | 0.1599 | 0.1594 | 63.0 | 0.0227 | 0.0483 | 1.0 | 1.8816 | 2273.0 | 1208.0 | 0.825 | 0.8586 | 0.8413 | roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.53.1) |
85
 
86
 
87
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7f61a888f2e7573b794807a2f639c3220cfcd6c58d68d48370db3fe11e7ef445
3
  size 1187780840
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4dc5f4391f7cc5c655a57e3a127ea8d999bfd3c5f9714d28fa15808ba308047
3
  size 1187780840
runs/Jul10_14-34-38_tardis/events.out.tfevents.1752150879.tardis.65808.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:abb1e9225c81ce8e0ac86c82c20db8b6e3252e4ceb4342f1b08caf8c480b0a8a
3
+ size 5349
runs/Jul10_14-35-17_tardis/events.out.tfevents.1752150918.tardis.66059.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf8ccd1cda7946f7c80b972d490c70c2419f1c571bfe70d75b2e8be0e30b008f
3
+ size 19281
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fcdc7402eb621c8482e6f2e03f830af901a418053952a24c6c883b8bc5ddb32d
3
  size 5905
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ac1b2dc5034a528c903614a99bd46968c910de5bf73d0e54dbe3b1a5315c215
3
  size 5905