Hugging Face's logo

floflodebilbao
/
Lora_LED_sum_challenge

PEFT
TensorBoard
Safetensors
Generated from Trainer
Model card Files
xet
Metrics Community
floflodebilbao commited on
Commit
2139ddf
·
verified ·
1 Parent(s): c73e37d

End of training

Browse files
Files changed (7) hide show
  1. README.md +24 -24
  2. adapter_config.json +2 -2
  3. adapter_model.safetensors +1 -1
  4. runs/Jul24_11-17-11_tardis/events.out.tfevents.1753348632.tardis.445419.0 +3 -0
  5. runs/Jul24_11-23-17_tardis/events.out.tfevents.1753348998.tardis.445572.0 +3 -0
  6. runs/Jul24_11-33-00_tardis/events.out.tfevents.1753349581.tardis.445730.0 +3 -0
  7. 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 [allenai/led-base-16384](https://huggingface.co/allenai/led-base-16384) on an unknown dataset.
24
  It achieves the following results on the evaluation set:
25
- - Loss: 9.9818
26
- - Rouge1: 0.2094
27
- - Rouge2: 0.0604
28
- - Rougel: 0.1683
29
- - Rougelsum: 0.1689
30
  - Gen Len: 21.0
31
- - Bleu: 0.0217
32
- - Precisions: 0.0745
33
- - Brevity Penalty: 0.5581
34
- - Length Ratio: 0.6316
35
- - Translation Length: 763.0
36
  - Reference Length: 1208.0
37
- - Precision: 0.8575
38
- - Recall: 0.8525
39
- - F1: 0.8549
40
  - Hashcode: roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.53.1)
41
 
42
  ## Model description
@@ -56,7 +56,7 @@ More information needed
56
  ### Training hyperparameters
57
 
58
  The following hyperparameters were used during training:
59
- - learning_rate: 2e-05
60
  - train_batch_size: 16
61
  - eval_batch_size: 8
62
  - seed: 42
@@ -69,16 +69,16 @@ The following hyperparameters were used during training:
69
 
70
  | 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 |
71
  |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|:------:|:----------:|:---------------:|:------------:|:------------------:|:----------------:|:---------:|:------:|:------:|:---------------------------------------------------------:|
72
- | 10.5321 | 1.0 | 7 | 10.5463 | 0.2094 | 0.0604 | 0.1683 | 0.1689 | 21.0 | 0.0217 | 0.0745 | 0.5581 | 0.6316 | 763.0 | 1208.0 | 0.8575 | 0.8525 | 0.8549 | roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.53.1) |
73
- | 10.3883 | 2.0 | 14 | 10.4317 | 0.2094 | 0.0604 | 0.1683 | 0.1689 | 21.0 | 0.0217 | 0.0745 | 0.5581 | 0.6316 | 763.0 | 1208.0 | 0.8575 | 0.8525 | 0.8549 | roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.53.1) |
74
- | 10.2749 | 3.0 | 21 | 10.3281 | 0.2094 | 0.0604 | 0.1683 | 0.1689 | 21.0 | 0.0217 | 0.0745 | 0.5581 | 0.6316 | 763.0 | 1208.0 | 0.8575 | 0.8525 | 0.8549 | roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.53.1) |
75
- | 10.2327 | 4.0 | 28 | 10.2371 | 0.2094 | 0.0604 | 0.1683 | 0.1689 | 21.0 | 0.0217 | 0.0745 | 0.5581 | 0.6316 | 763.0 | 1208.0 | 0.8575 | 0.8525 | 0.8549 | roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.53.1) |
76
- | 10.1782 | 5.0 | 35 | 10.1595 | 0.2094 | 0.0604 | 0.1683 | 0.1689 | 21.0 | 0.0217 | 0.0745 | 0.5581 | 0.6316 | 763.0 | 1208.0 | 0.8575 | 0.8525 | 0.8549 | roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.53.1) |
77
- | 10.0863 | 6.0 | 42 | 10.0958 | 0.2094 | 0.0604 | 0.1683 | 0.1689 | 21.0 | 0.0217 | 0.0745 | 0.5581 | 0.6316 | 763.0 | 1208.0 | 0.8575 | 0.8525 | 0.8549 | roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.53.1) |
78
- | 9.9788 | 7.0 | 49 | 10.0463 | 0.2094 | 0.0604 | 0.1683 | 0.1689 | 21.0 | 0.0217 | 0.0745 | 0.5581 | 0.6316 | 763.0 | 1208.0 | 0.8575 | 0.8525 | 0.8549 | roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.53.1) |
79
- | 10.0324 | 8.0 | 56 | 10.0111 | 0.2094 | 0.0604 | 0.1683 | 0.1689 | 21.0 | 0.0217 | 0.0745 | 0.5581 | 0.6316 | 763.0 | 1208.0 | 0.8575 | 0.8525 | 0.8549 | roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.53.1) |
80
- | 9.872 | 9.0 | 63 | 9.9897 | 0.2094 | 0.0604 | 0.1683 | 0.1689 | 21.0 | 0.0217 | 0.0745 | 0.5581 | 0.6316 | 763.0 | 1208.0 | 0.8575 | 0.8525 | 0.8549 | roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.53.1) |
81
- | 9.9103 | 10.0 | 70 | 9.9818 | 0.2094 | 0.0604 | 0.1683 | 0.1689 | 21.0 | 0.0217 | 0.0745 | 0.5581 | 0.6316 | 763.0 | 1208.0 | 0.8575 | 0.8525 | 0.8549 | roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.53.1) |
82
 
83
 
84
  ### Framework versions
 
22
 
23
  This model is a fine-tuned version of [allenai/led-base-16384](https://huggingface.co/allenai/led-base-16384) on an unknown dataset.
24
  It achieves the following results on the evaluation set:
25
+ - Loss: 4.1136
26
+ - Rouge1: 0.2528
27
+ - Rouge2: 0.0697
28
+ - Rougel: 0.2065
29
+ - Rougelsum: 0.2056
30
  - Gen Len: 21.0
31
+ - Bleu: 0.0273
32
+ - Precisions: 0.097
33
+ - Brevity Penalty: 0.6118
34
+ - Length Ratio: 0.6705
35
+ - Translation Length: 810.0
36
  - Reference Length: 1208.0
37
+ - Precision: 0.8734
38
+ - Recall: 0.8657
39
+ - F1: 0.8695
40
  - Hashcode: roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.53.1)
41
 
42
  ## Model description
 
56
  ### Training hyperparameters
57
 
58
  The following hyperparameters were used during training:
59
+ - learning_rate: 0.001
60
  - train_batch_size: 16
61
  - eval_batch_size: 8
62
  - seed: 42
 
69
 
70
  | 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 |
71
  |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|:------:|:----------:|:---------------:|:------------:|:------------------:|:----------------:|:---------:|:------:|:------:|:---------------------------------------------------------:|
72
+ | 9.3557 | 1.0 | 7 | 8.2857 | 0.1835 | 0.037 | 0.1475 | 0.1474 | 21.0 | 0.0093 | 0.0545 | 0.6661 | 0.7111 | 859.0 | 1208.0 | 0.8595 | 0.8516 | 0.8554 | roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.53.1) |
73
+ | 7.5243 | 2.0 | 14 | 6.2064 | 0.2082 | 0.0492 | 0.1646 | 0.1643 | 19.54 | 0.0117 | 0.073 | 0.58 | 0.6474 | 782.0 | 1208.0 | 0.8725 | 0.8561 | 0.8641 | roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.53.1) |
74
+ | 5.8052 | 3.0 | 21 | 5.2106 | 0.2352 | 0.0577 | 0.1872 | 0.186 | 20.1 | 0.0174 | 0.0764 | 0.6275 | 0.6821 | 824.0 | 1208.0 | 0.875 | 0.86 | 0.8674 | roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.53.1) |
75
+ | 5.2043 | 4.0 | 28 | 4.6310 | 0.2571 | 0.0795 | 0.2055 | 0.2052 | 20.38 | 0.0199 | 0.0913 | 0.5914 | 0.6556 | 792.0 | 1208.0 | 0.8797 | 0.8658 | 0.8726 | roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.53.1) |
76
+ | 4.55 | 5.0 | 35 | 4.3489 | 0.2527 | 0.0755 | 0.2017 | 0.201 | 20.3 | 0.0279 | 0.0973 | 0.5754 | 0.644 | 778.0 | 1208.0 | 0.8804 | 0.8671 | 0.8736 | roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.53.1) |
77
+ | 4.3215 | 6.0 | 42 | 4.2134 | 0.2517 | 0.0742 | 0.2041 | 0.203 | 20.9 | 0.0238 | 0.0888 | 0.6107 | 0.6697 | 809.0 | 1208.0 | 0.8749 | 0.8656 | 0.8702 | roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.53.1) |
78
+ | 4.168 | 7.0 | 49 | 4.1657 | 0.2409 | 0.0632 | 0.1934 | 0.194 | 20.82 | 0.0244 | 0.0901 | 0.5857 | 0.6515 | 787.0 | 1208.0 | 0.8728 | 0.8645 | 0.8686 | roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.53.1) |
79
+ | 4.0873 | 8.0 | 56 | 4.1293 | 0.2382 | 0.0584 | 0.1928 | 0.1924 | 20.96 | 0.0215 | 0.0849 | 0.5971 | 0.6598 | 797.0 | 1208.0 | 0.8732 | 0.8644 | 0.8687 | roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.53.1) |
80
+ | 3.9975 | 9.0 | 63 | 4.1130 | 0.2466 | 0.0657 | 0.1984 | 0.1977 | 20.98 | 0.0253 | 0.091 | 0.6084 | 0.668 | 807.0 | 1208.0 | 0.8719 | 0.8644 | 0.8681 | roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.53.1) |
81
+ | 3.9602 | 10.0 | 70 | 4.1136 | 0.2528 | 0.0697 | 0.2065 | 0.2056 | 21.0 | 0.0273 | 0.097 | 0.6118 | 0.6705 | 810.0 | 1208.0 | 0.8734 | 0.8657 | 0.8695 | roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.53.1) |
82
 
83
 
84
  ### Framework versions
adapter_config.json CHANGED
@@ -25,9 +25,9 @@
25
  "revision": null,
26
  "target_modules": [
27
  "k_proj",
28
- "v_proj",
29
  "q_proj",
30
- "out_proj"
 
31
  ],
32
  "task_type": "SEQ_2_SEQ_LM",
33
  "trainable_token_indices": null,
 
25
  "revision": null,
26
  "target_modules": [
27
  "k_proj",
 
28
  "q_proj",
29
+ "out_proj",
30
+ "v_proj"
31
  ],
32
  "task_type": "SEQ_2_SEQ_LM",
33
  "trainable_token_indices": null,
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1106339c0a0312575fa18131271402b2385dc21c9a462fee974cdcda3c0eae15
3
  size 2372496
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59246d560518384e5f67fb19948670e7ca73b58d9135d07998a3d5d6fbb64a8d
3
  size 2372496
runs/Jul24_11-17-11_tardis/events.out.tfevents.1753348632.tardis.445419.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5d5dd08fe49b72926dfb4368a433bb6ac026c5d8fbf651f22855d75e952d797
3
+ size 13638
runs/Jul24_11-23-17_tardis/events.out.tfevents.1753348998.tardis.445572.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75e1418b073a59af95486d3b2ff04696bcd4574fc7dd7092aa5e0a5804a0d584
3
+ size 16316
runs/Jul24_11-33-00_tardis/events.out.tfevents.1753349581.tardis.445730.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:073572dcc03051f16f5ba172e977589969dbcd909da7ba10eca79293264ce202
3
+ size 19342
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:227b3210ed894811841b7bc7cacff511016b97328d32b4bd3bb6e89661ba5555
3
  size 5905
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9a913b5be24445939b94a1a2b6e884005d748a4e59552ab3b1831f4df9d3ab1
3
  size 5905