Hugging Face's logo

olonok
/
flan-t5-large-samsum

PEFT
Safetensors
Generated from Trainer
Model card Files Community
olonok commited on
Commit
ca82802
•
1 Parent(s): bb7370b

olonok/t5-large-billsum-lora-summarization

Browse files
Files changed (4) hide show
  1. README.md +19 -25
  2. adapter_config.json +3 -3
  3. adapter_model.safetensors +1 -1
  4. training_args.bin +2 -2
README.md CHANGED
@@ -1,10 +1,9 @@
1
  ---
2
  license: apache-2.0
3
- base_model: google/flan-t5-large
4
  tags:
5
  - generated_from_trainer
6
- metrics:
7
- - rouge
8
  model-index:
9
  - name: flan-t5-large-samsum
10
  results: []
@@ -17,12 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  This model is a fine-tuned version of [google/flan-t5-large](https://huggingface.co/google/flan-t5-large) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: nan
21
- - Rouge1: 48.5905
22
- - Rouge2: 24.4216
23
- - Rougel: 41.0265
24
- - Rougelsum: 44.7321
25
- - Gen Len: 16.9927
26
 
27
  ## Model description
28
 
@@ -41,34 +35,34 @@ More information needed
41
  ### Training hyperparameters
42
 
43
  The following hyperparameters were used during training:
44
- - learning_rate: 5e-05
45
  - train_batch_size: 8
46
  - eval_batch_size: 8
47
  - seed: 42
48
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
49
  - lr_scheduler_type: linear
50
  - num_epochs: 10
51
- - mixed_precision_training: Native AMP
52
 
53
  ### Training results
54
 
55
- | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
56
- |:-------------:|:-----:|:-----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:-------:|
57
- | 0.0 | 1.0 | 1842 | nan | 48.5905 | 24.4216 | 41.0265 | 44.7321 | 16.9927 |
58
- | 0.0 | 2.0 | 3684 | nan | 48.5905 | 24.4216 | 41.0265 | 44.7321 | 16.9927 |
59
- | 0.0 | 3.0 | 5526 | nan | 48.5905 | 24.4216 | 41.0265 | 44.7321 | 16.9927 |
60
- | 0.0 | 4.0 | 7368 | nan | 48.5905 | 24.4216 | 41.0265 | 44.7321 | 16.9927 |
61
- | 0.0 | 5.0 | 9210 | nan | 48.5905 | 24.4216 | 41.0265 | 44.7321 | 16.9927 |
62
- | 0.0 | 6.0 | 11052 | nan | 48.5905 | 24.4216 | 41.0265 | 44.7321 | 16.9927 |
63
- | 0.0 | 7.0 | 12894 | nan | 48.5905 | 24.4216 | 41.0265 | 44.7321 | 16.9927 |
64
- | 0.0 | 8.0 | 14736 | nan | 48.5905 | 24.4216 | 41.0265 | 44.7321 | 16.9927 |
65
- | 0.0 | 9.0 | 16578 | nan | 48.5905 | 24.4216 | 41.0265 | 44.7321 | 16.9927 |
66
- | 0.0 | 10.0 | 18420 | nan | 48.5905 | 24.4216 | 41.0265 | 44.7321 | 16.9927 |
67
 
68
 
69
  ### Framework versions
70
 
71
- - Transformers 4.35.2
 
72
  - Pytorch 2.1.0+cu121
73
  - Datasets 2.17.1
74
- - Tokenizers 0.15.2
 
1
  ---
2
  license: apache-2.0
3
+ library_name: peft
4
  tags:
5
  - generated_from_trainer
6
+ base_model: google/flan-t5-large
 
7
  model-index:
8
  - name: flan-t5-large-samsum
9
  results: []
 
16
 
17
  This model is a fine-tuned version of [google/flan-t5-large](https://huggingface.co/google/flan-t5-large) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 0.9492
 
 
 
 
 
20
 
21
  ## Model description
22
 
 
35
  ### Training hyperparameters
36
 
37
  The following hyperparameters were used during training:
38
+ - learning_rate: 0.001
39
  - train_batch_size: 8
40
  - eval_batch_size: 8
41
  - seed: 42
42
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
43
  - lr_scheduler_type: linear
44
  - num_epochs: 10
 
45
 
46
  ### Training results
47
 
48
+ | Training Loss | Epoch | Step | Validation Loss |
49
+ |:-------------:|:-----:|:-----:|:---------------:|
50
+ | 1.2035 | 1.0 | 4738 | 1.0323 |
51
+ | 1.1186 | 2.0 | 9476 | 1.0119 |
52
+ | 1.0904 | 3.0 | 14214 | 0.9983 |
53
+ | 1.0591 | 4.0 | 18952 | 0.9858 |
54
+ | 1.0319 | 5.0 | 23690 | 0.9711 |
55
+ | 0.9659 | 6.0 | 28428 | 0.9620 |
56
+ | 0.9388 | 7.0 | 33166 | 0.9547 |
57
+ | 0.9148 | 8.0 | 37904 | 0.9510 |
58
+ | 0.8681 | 9.0 | 42642 | 0.9486 |
59
+ | 0.8502 | 10.0 | 47380 | 0.9492 |
60
 
61
 
62
  ### Framework versions
63
 
64
+ - PEFT 0.8.2
65
+ - Transformers 4.37.2
66
  - Pytorch 2.1.0+cu121
67
  - Datasets 2.17.1
68
+ - Tokenizers 0.15.2
adapter_config.json CHANGED
@@ -9,7 +9,7 @@
9
  "layers_pattern": null,
10
  "layers_to_transform": null,
11
  "loftq_config": {},
12
- "lora_alpha": 16,
13
  "lora_dropout": 0.05,
14
  "megatron_config": null,
15
  "megatron_core": "megatron.core",
@@ -19,8 +19,8 @@
19
  "rank_pattern": {},
20
  "revision": null,
21
  "target_modules": [
22
- "v",
23
- "q"
24
  ],
25
  "task_type": "SEQ_2_SEQ_LM",
26
  "use_rslora": false
 
9
  "layers_pattern": null,
10
  "layers_to_transform": null,
11
  "loftq_config": {},
12
+ "lora_alpha": 32,
13
  "lora_dropout": 0.05,
14
  "megatron_config": null,
15
  "megatron_core": "megatron.core",
 
19
  "rank_pattern": {},
20
  "revision": null,
21
  "target_modules": [
22
+ "q",
23
+ "v"
24
  ],
25
  "task_type": "SEQ_2_SEQ_LM",
26
  "use_rslora": false
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2c2c8656fd319e4e8d06bdf81240d6ed7d889f7bbd4fc95a1c0b25de17ea1b9c
3
  size 18915328
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c7c5ac35f29e13a91b6d23b78825859de5f753a4723f9c4722a52526011c23f
3
  size 18915328
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7d23573195b2a8196a2656f5bcd2a905b23e2cf323714de2e8015d5a6de3f6ac
3
- size 4728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b3b0652318343b4ca07d0d9eb4124d5624fe3fbfcdf26828d63ed2c87973969d
3
+ size 4856