Hugging Face's logo

mixtralyanis
/
bart_samsum_v2

Text2Text Generation
Transformers
TensorBoard
Safetensors
bart
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
mixtralyanis commited on
Commit
d487725
•
1 Parent(s): be8c400

End of training

Browse files
Files changed (4) hide show
  1. README.md +56 -2
  2. model.safetensors +1 -1
  3. runs/Feb24_12-26-36_a191c644522c/events.out.tfevents.1708777603.a191c644522c.2522.0 +3 -0
  4. training_args.bin +1 -1
README.md CHANGED
@@ -14,6 +14,8 @@ should probably proofread and complete it, then remove this comment. -->
14
  # bart_samsum_v2
15
 
16
  This model is a fine-tuned version of [facebook/bart-large-cnn](https://huggingface.co/facebook/bart-large-cnn) on the None dataset.
 
 
17
 
18
  ## Model description
19
 
@@ -32,7 +34,7 @@ More information needed
32
  ### Training hyperparameters
33
 
34
  The following hyperparameters were used during training:
35
- - learning_rate: 5e-05
36
  - train_batch_size: 4
37
  - eval_batch_size: 4
38
  - seed: 42
@@ -40,11 +42,63 @@ The following hyperparameters were used during training:
40
  - total_train_batch_size: 64
41
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
  - lr_scheduler_type: linear
43
- - lr_scheduler_warmup_steps: 500
44
  - num_epochs: 10
45
 
46
  ### Training results
47
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
48
 
49
 
50
  ### Framework versions
 
14
  # bart_samsum_v2
15
 
16
  This model is a fine-tuned version of [facebook/bart-large-cnn](https://huggingface.co/facebook/bart-large-cnn) on the None dataset.
17
+ It achieves the following results on the evaluation set:
18
+ - Loss: 0.9055
19
 
20
  ## Model description
21
 
 
34
  ### Training hyperparameters
35
 
36
  The following hyperparameters were used during training:
37
+ - learning_rate: 1e-05
38
  - train_batch_size: 4
39
  - eval_batch_size: 4
40
  - seed: 42
 
42
  - total_train_batch_size: 64
43
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
  - lr_scheduler_type: linear
45
+ - lr_scheduler_warmup_steps: 5
46
  - num_epochs: 10
47
 
48
  ### Training results
49
 
50
+ | Training Loss | Epoch | Step | Validation Loss |
51
+ |:-------------:|:-----:|:----:|:---------------:|
52
+ | 9.4233 | 0.17 | 1 | 9.1990 |
53
+ | 9.5213 | 0.34 | 2 | 8.8988 |
54
+ | 9.1833 | 0.52 | 3 | 8.5352 |
55
+ | 8.9925 | 0.69 | 4 | 8.2488 |
56
+ | 8.4764 | 0.86 | 5 | 7.9750 |
57
+ | 8.1476 | 1.03 | 6 | 7.6447 |
58
+ | 7.8018 | 1.2 | 7 | 7.3010 |
59
+ | 7.4513 | 1.38 | 8 | 6.9432 |
60
+ | 7.0989 | 1.55 | 9 | 6.5388 |
61
+ | 6.6235 | 1.72 | 10 | 6.0939 |
62
+ | 6.4569 | 1.89 | 11 | 5.6696 |
63
+ | 6.1586 | 2.06 | 12 | 5.2364 |
64
+ | 5.5829 | 2.24 | 13 | 4.7483 |
65
+ | 5.1618 | 2.41 | 14 | 4.3015 |
66
+ | 4.6379 | 2.58 | 15 | 3.9224 |
67
+ | 4.3306 | 2.75 | 16 | 3.5770 |
68
+ | 4.0446 | 2.92 | 17 | 3.2700 |
69
+ | 3.721 | 3.1 | 18 | 3.0062 |
70
+ | 3.5989 | 3.27 | 19 | 2.7701 |
71
+ | 3.2333 | 3.44 | 20 | 2.5514 |
72
+ | 3.03 | 3.61 | 21 | 2.3574 |
73
+ | 2.7969 | 3.78 | 22 | 2.1917 |
74
+ | 2.65 | 3.96 | 23 | 2.0489 |
75
+ | 2.4654 | 4.13 | 24 | 1.9216 |
76
+ | 2.2993 | 4.3 | 25 | 1.8079 |
77
+ | 2.292 | 4.47 | 26 | 1.7075 |
78
+ | 2.1275 | 4.65 | 27 | 1.6178 |
79
+ | 2.0392 | 4.82 | 28 | 1.5364 |
80
+ | 1.9177 | 4.99 | 29 | 1.4631 |
81
+ | 1.8414 | 5.16 | 30 | 1.3969 |
82
+ | 1.823 | 5.33 | 31 | 1.3376 |
83
+ | 1.6799 | 5.51 | 32 | 1.2845 |
84
+ | 1.6504 | 5.68 | 33 | 1.2368 |
85
+ | 1.6111 | 5.85 | 34 | 1.1933 |
86
+ | 1.538 | 6.02 | 35 | 1.1531 |
87
+ | 1.4641 | 6.19 | 36 | 1.1163 |
88
+ | 1.4927 | 6.37 | 37 | 1.0832 |
89
+ | 1.4657 | 6.54 | 38 | 1.0536 |
90
+ | 1.4045 | 6.71 | 39 | 1.0276 |
91
+ | 1.371 | 6.88 | 40 | 1.0049 |
92
+ | 1.3339 | 7.05 | 41 | 0.9852 |
93
+ | 1.3281 | 7.23 | 42 | 0.9682 |
94
+ | 1.2857 | 7.4 | 43 | 0.9535 |
95
+ | 1.324 | 7.57 | 44 | 0.9410 |
96
+ | 1.2581 | 7.74 | 45 | 0.9306 |
97
+ | 1.2301 | 7.91 | 46 | 0.9221 |
98
+ | 1.2526 | 8.09 | 47 | 0.9153 |
99
+ | 1.2499 | 8.26 | 48 | 0.9104 |
100
+ | 1.2298 | 8.43 | 49 | 0.9072 |
101
+ | 1.195 | 8.6 | 50 | 0.9055 |
102
 
103
 
104
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:95660a65038b292a44abe9d6dcee407632bd4ab0bd93d3280abec51f48fbbfd6
3
  size 1625422896
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:935420fb6270923989ed921e8ca920a3e8b8b90dde9b055a2d5167f867602dfd
3
  size 1625422896
runs/Feb24_12-26-36_a191c644522c/events.out.tfevents.1708777603.a191c644522c.2522.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9068a709c58d119fb099a74e353ee23c3d8878586b170351c5a61cb0f4bafc6
3
+ size 29538
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9e7387e592d9bd67fc538beda761553a9bcff1b98d2eef5b53e640fc88810a76
3
  size 4856
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd0bf47838fa209da9cf15ef8adcdf0acf78d16e1f940656c757affbb61caaae
3
  size 4856