Hugging Face's logo

jordanfan
/
bart_baseline_peft

Text2Text Generation
Transformers
TensorBoard
Safetensors
bart
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
jordanfan commited on
Commit
5396c92
•
1 Parent(s): 24ce7e9

training completed[prod]: bart_baseline_peft

Browse files
Files changed (3) hide show
  1. README.md +14 -16
  2. generation_config.json +13 -0
  3. runs/Apr02_18-55-35_b649ef780a74/events.out.tfevents.1712084136.b649ef780a74.217.0 +2 -2
README.md CHANGED
@@ -1,9 +1,8 @@
1
  ---
2
  license: apache-2.0
3
- library_name: peft
4
  tags:
5
  - generated_from_trainer
6
- base_model: facebook/bart-large
7
  model-index:
8
  - name: bart_baseline_peft
9
  results: []
@@ -16,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  This model is a fine-tuned version of [facebook/bart-large](https://huggingface.co/facebook/bart-large) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: 1.0693
20
 
21
  ## Model description
22
 
@@ -48,23 +47,22 @@ The following hyperparameters were used during training:
48
 
49
  | Training Loss | Epoch | Step | Validation Loss |
50
  |:-------------:|:-----:|:----:|:---------------:|
51
- | No log | 0.18 | 250 | 1.1968 |
52
- | 1.7053 | 0.35 | 500 | 1.1435 |
53
- | 1.7053 | 0.53 | 750 | 1.1399 |
54
- | 1.2238 | 0.71 | 1000 | 1.1146 |
55
- | 1.2238 | 0.89 | 1250 | 1.1072 |
56
- | 1.2006 | 1.06 | 1500 | 1.0856 |
57
- | 1.2006 | 1.24 | 1750 | 1.0841 |
58
- | 1.1399 | 1.42 | 2000 | 1.0757 |
59
- | 1.1399 | 1.6 | 2250 | 1.0771 |
60
- | 1.1393 | 1.77 | 2500 | 1.0709 |
61
- | 1.1393 | 1.95 | 2750 | 1.0693 |
62
 
63
 
64
  ### Framework versions
65
 
66
- - PEFT 0.10.0
67
  - Transformers 4.38.2
68
  - Pytorch 2.2.1+cu121
69
  - Datasets 2.18.0
70
- - Tokenizers 0.15.2
 
1
  ---
2
  license: apache-2.0
3
+ base_model: facebook/bart-large
4
  tags:
5
  - generated_from_trainer
 
6
  model-index:
7
  - name: bart_baseline_peft
8
  results: []
 
15
 
16
  This model is a fine-tuned version of [facebook/bart-large](https://huggingface.co/facebook/bart-large) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Loss: 1.0163
19
 
20
  ## Model description
21
 
 
47
 
48
  | Training Loss | Epoch | Step | Validation Loss |
49
  |:-------------:|:-----:|:----:|:---------------:|
50
+ | No log | 0.18 | 250 | 1.4711 |
51
+ | 1.8588 | 0.35 | 500 | 1.4005 |
52
+ | 1.8588 | 0.53 | 750 | 1.3036 |
53
+ | 1.4092 | 0.71 | 1000 | 1.2629 |
54
+ | 1.4092 | 0.89 | 1250 | 1.2011 |
55
+ | 1.2502 | 1.06 | 1500 | 1.1580 |
56
+ | 1.2502 | 1.24 | 1750 | 1.1387 |
57
+ | 0.9815 | 1.42 | 2000 | 1.1045 |
58
+ | 0.9815 | 1.6 | 2250 | 1.0710 |
59
+ | 0.9213 | 1.77 | 2500 | 1.0347 |
60
+ | 0.9213 | 1.95 | 2750 | 1.0163 |
61
 
62
 
63
  ### Framework versions
64
 
 
65
  - Transformers 4.38.2
66
  - Pytorch 2.2.1+cu121
67
  - Datasets 2.18.0
68
+ - Tokenizers 0.15.2
generation_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "decoder_start_token_id": 2,
5
+ "early_stopping": true,
6
+ "eos_token_id": 2,
7
+ "forced_bos_token_id": 0,
8
+ "forced_eos_token_id": 2,
9
+ "no_repeat_ngram_size": 3,
10
+ "num_beams": 4,
11
+ "pad_token_id": 1,
12
+ "transformers_version": "4.38.2"
13
+ }
runs/Apr02_18-55-35_b649ef780a74/events.out.tfevents.1712084136.b649ef780a74.217.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f94fa264e93ca244a4ea285123e03e7757958e0ebf10a8a2ea1d74eaf2dfd831
3
- size 8794
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c4615ed518cc30e70b5709c1c0a5f89f9132333bc1b6f0bd844ea2f9c070e097
3
+ size 10172