Hugging Face's logo

owenMills
/
bart-pas-lora

PEFT
Safetensors
Generated from Trainer
Model card Files
xet
 Community
owenMills commited on
Commit
27d3bdc
·
verified ·
1 Parent(s): 5daba40

End of training

Browse files
Files changed (5) hide show
  1. README.md +13 -3
  2. adapter_config.json +2 -2
  3. adapter_model.safetensors +1 -1
  4. tokenizer.json +1 -1
  5. training_args.bin +2 -2
README.md CHANGED
@@ -5,6 +5,8 @@ tags:
5
  - base_model:adapter:owenMills/bart-pas-model
6
  - lora
7
  - transformers
 
 
8
  model-index:
9
  - name: bart-pas-lora
10
  results: []
@@ -16,6 +18,12 @@ should probably proofread and complete it, then remove this comment. -->
16
  # bart-pas-lora
17
 
18
  This model is a fine-tuned version of [owenMills/bart-pas-model](https://huggingface.co/owenMills/bart-pas-model) on an unknown dataset.
 
 
 
 
 
 
19
 
20
  ## Model description
21
 
@@ -34,7 +42,7 @@ More information needed
34
  ### Training hyperparameters
35
 
36
  The following hyperparameters were used during training:
37
- - learning_rate: 0.0001
38
  - train_batch_size: 2
39
  - eval_batch_size: 2
40
  - seed: 42
@@ -43,12 +51,14 @@ The following hyperparameters were used during training:
43
  - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
44
  - lr_scheduler_type: linear
45
  - lr_scheduler_warmup_ratio: 0.05
46
- - num_epochs: 5
47
- - mixed_precision_training: Native AMP
48
  - label_smoothing_factor: 0.1
49
 
50
  ### Training results
51
 
 
 
 
52
 
53
 
54
  ### Framework versions
 
5
  - base_model:adapter:owenMills/bart-pas-model
6
  - lora
7
  - transformers
8
+ metrics:
9
+ - rouge
10
  model-index:
11
  - name: bart-pas-lora
12
  results: []
 
18
  # bart-pas-lora
19
 
20
  This model is a fine-tuned version of [owenMills/bart-pas-model](https://huggingface.co/owenMills/bart-pas-model) on an unknown dataset.
21
+ It achieves the following results on the evaluation set:
22
+ - Loss: 2.6618
23
+ - Rouge1: 46.92
24
+ - Rouge2: 38.48
25
+ - Rougel: 43.2
26
+ - Rougelsum: 43.34
27
 
28
  ## Model description
29
 
 
42
  ### Training hyperparameters
43
 
44
  The following hyperparameters were used during training:
45
+ - learning_rate: 5e-05
46
  - train_batch_size: 2
47
  - eval_batch_size: 2
48
  - seed: 42
 
51
  - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
52
  - lr_scheduler_type: linear
53
  - lr_scheduler_warmup_ratio: 0.05
54
+ - num_epochs: 1
 
55
  - label_smoothing_factor: 0.1
56
 
57
  ### Training results
58
 
59
+ | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
60
+ |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|
61
+ | 4.4614 | 1.0 | 13 | 2.6618 | 46.92 | 38.48 | 43.2 | 43.34 |
62
 
63
 
64
  ### Framework versions
adapter_config.json CHANGED
@@ -25,9 +25,9 @@
25
  "rank_pattern": {},
26
  "revision": null,
27
  "target_modules": [
28
- "v_proj",
29
- "q_proj",
30
  "k_proj",
 
 
31
  "out_proj"
32
  ],
33
  "target_parameters": null,
 
25
  "rank_pattern": {},
26
  "revision": null,
27
  "target_modules": [
 
 
28
  "k_proj",
29
+ "q_proj",
30
+ "v_proj",
31
  "out_proj"
32
  ],
33
  "target_parameters": null,
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6df519d924b7d1265088d65d5fb9102c458f7c34601ecdfc19d76c0a641287fd
3
  size 3558984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46dd291dd9aff30ee62021f617563be413d61b36e57540c40218b43995d62155
3
  size 3558984
tokenizer.json CHANGED
@@ -2,7 +2,7 @@
2
  "version": "1.0",
3
  "truncation": {
4
  "direction": "Right",
5
- "max_length": 192,
6
  "strategy": "LongestFirst",
7
  "stride": 0
8
  },
 
2
  "version": "1.0",
3
  "truncation": {
4
  "direction": "Right",
5
+ "max_length": 256,
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 sha256:529804336fb8f4bc5688b03fcc072cc255cd5cff082a1cce28789285b24a6e1b
3
- size 6033
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88605e9b4b9a12758e996712f8e0760d330610b609bae362b1057908e4f85e1c
3
+ size 5969