Hugging Face's logo

GlycerinLOL
/
LLM_Teached_Bart_From_Scratch

Text2Text Generation
Transformers
TensorBoard
Safetensors
bart
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
GlycerinLOL commited on
Commit
12ab2d3
•
1 Parent(s): ab15eaf

Model save

Browse files
Files changed (3) hide show
  1. README.md +28 -16
  2. model.safetensors +1 -1
  3. runs/Mar04_01-03-39_oi5vv8ctr1709312124223-tkfr5/events.out.tfevents.1709485422.oi5vv8ctr1709312124223-tkfr5.23871.0 +2 -2
README.md CHANGED
@@ -20,15 +20,15 @@ should probably proofread and complete it, then remove this comment. -->
20
 
21
  This model is a fine-tuned version of [facebook/bart-large](https://huggingface.co/facebook/bart-large) on an unknown dataset.
22
  It achieves the following results on the evaluation set:
23
- - Loss: 1.4999
24
- - Rouge1: 0.4331
25
- - Rouge2: 0.2164
26
- - Rougel: 0.3724
27
- - Rougelsum: 0.3725
28
- - Gen Len: 19.9255
29
- - Precision: 0.9125
30
- - Recall: 0.8885
31
- - F1: 0.9002
32
 
33
  ## Model description
34
 
@@ -48,24 +48,36 @@ More information needed
48
 
49
  The following hyperparameters were used during training:
50
  - learning_rate: 2e-05
51
- - train_batch_size: 32
52
  - eval_batch_size: 16
53
  - seed: 42
54
  - gradient_accumulation_steps: 4
55
- - total_train_batch_size: 128
56
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
57
  - lr_scheduler_type: linear
58
- - num_epochs: 4
59
  - mixed_precision_training: Native AMP
60
 
61
  ### Training results
62
 
63
  | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len | Precision | Recall | F1 |
64
  |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|:---------:|:------:|:------:|
65
- | No log | 1.0 | 390 | 1.5709 | 0.4119 | 0.2002 | 0.3529 | 0.3527 | 19.9709 | 0.9093 | 0.8846 | 0.8966 |
66
- | 1.8155 | 2.0 | 781 | 1.5361 | 0.4331 | 0.2157 | 0.3717 | 0.3717 | 19.9185 | 0.9123 | 0.8889 | 0.9003 |
67
- | 1.5875 | 3.0 | 1172 | 1.5030 | 0.4263 | 0.2129 | 0.3671 | 0.3673 | 19.9545 | 0.9117 | 0.8871 | 0.899 |
68
- | 1.4978 | 3.99 | 1560 | 1.4999 | 0.4331 | 0.2164 | 0.3724 | 0.3725 | 19.9255 | 0.9125 | 0.8885 | 0.9002 |
 
 
 
 
 
 
 
 
 
 
 
 
69
 
70
 
71
  ### Framework versions
 
20
 
21
  This model is a fine-tuned version of [facebook/bart-large](https://huggingface.co/facebook/bart-large) on an unknown dataset.
22
  It achieves the following results on the evaluation set:
23
+ - Loss: 1.5434
24
+ - Rouge1: 0.4476
25
+ - Rouge2: 0.2292
26
+ - Rougel: 0.3868
27
+ - Rougelsum: 0.3865
28
+ - Gen Len: 19.9007
29
+ - Precision: 0.9159
30
+ - Recall: 0.8916
31
+ - F1: 0.9034
32
 
33
  ## Model description
34
 
 
48
 
49
  The following hyperparameters were used during training:
50
  - learning_rate: 2e-05
51
+ - train_batch_size: 24
52
  - eval_batch_size: 16
53
  - seed: 42
54
  - gradient_accumulation_steps: 4
55
+ - total_train_batch_size: 96
56
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
57
  - lr_scheduler_type: linear
58
+ - num_epochs: 16
59
  - mixed_precision_training: Native AMP
60
 
61
  ### Training results
62
 
63
  | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len | Precision | Recall | F1 |
64
  |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|:---------:|:------:|:------:|
65
+ | 1.836 | 1.0 | 521 | 1.5560 | 0.4155 | 0.2028 | 0.3561 | 0.3559 | 19.9745 | 0.9105 | 0.8843 | 0.8971 |
66
+ | 1.5951 | 2.0 | 1042 | 1.5004 | 0.4333 | 0.2136 | 0.3695 | 0.3694 | 19.9353 | 0.9115 | 0.8886 | 0.8997 |
67
+ | 1.469 | 3.0 | 1563 | 1.4691 | 0.4355 | 0.2176 | 0.3729 | 0.3728 | 19.9385 | 0.912 | 0.8888 | 0.9001 |
68
+ | 1.373 | 4.0 | 2084 | 1.4658 | 0.4311 | 0.2164 | 0.3706 | 0.3704 | 19.9647 | 0.9137 | 0.8877 | 0.9003 |
69
+ | 1.2902 | 5.0 | 2605 | 1.4542 | 0.4368 | 0.2218 | 0.3762 | 0.376 | 19.9498 | 0.9136 | 0.8887 | 0.9008 |
70
+ | 1.222 | 6.0 | 3126 | 1.4584 | 0.4407 | 0.223 | 0.3802 | 0.3798 | 19.9425 | 0.914 | 0.8902 | 0.9018 |
71
+ | 1.1655 | 7.0 | 3647 | 1.4709 | 0.4404 | 0.2246 | 0.3806 | 0.3803 | 19.9327 | 0.9145 | 0.89 | 0.9019 |
72
+ | 1.11 | 8.0 | 4168 | 1.4724 | 0.4435 | 0.2269 | 0.383 | 0.3828 | 19.9084 | 0.9153 | 0.8906 | 0.9026 |
73
+ | 1.0629 | 9.0 | 4689 | 1.4853 | 0.4431 | 0.2273 | 0.3832 | 0.383 | 19.928 | 0.9155 | 0.8908 | 0.9028 |
74
+ | 1.023 | 10.0 | 5210 | 1.5033 | 0.4409 | 0.2247 | 0.3819 | 0.3818 | 19.944 | 0.9152 | 0.8897 | 0.9021 |
75
+ | 0.9862 | 11.0 | 5731 | 1.5074 | 0.4479 | 0.2278 | 0.3862 | 0.386 | 19.9124 | 0.9158 | 0.8916 | 0.9034 |
76
+ | 0.957 | 12.0 | 6252 | 1.5184 | 0.4461 | 0.2264 | 0.3846 | 0.3847 | 19.9033 | 0.9159 | 0.8909 | 0.903 |
77
+ | 0.9315 | 13.0 | 6773 | 1.5269 | 0.4473 | 0.2284 | 0.386 | 0.3858 | 19.9084 | 0.9156 | 0.8912 | 0.9031 |
78
+ | 0.9093 | 14.0 | 7294 | 1.5311 | 0.4453 | 0.2273 | 0.3846 | 0.3843 | 19.9135 | 0.9155 | 0.8909 | 0.9029 |
79
+ | 0.8927 | 15.0 | 7815 | 1.5351 | 0.4457 | 0.2267 | 0.3842 | 0.384 | 19.9065 | 0.9156 | 0.8909 | 0.9029 |
80
+ | 0.8773 | 16.0 | 8336 | 1.5434 | 0.4476 | 0.2292 | 0.3868 | 0.3865 | 19.9007 | 0.9159 | 0.8916 | 0.9034 |
81
 
82
 
83
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e6e930f1da1bc6101030aa1554f1ba9b40c678ff1e65821cb513e1dd323eaff0
3
  size 1625426996
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86653d62387c63009fd513fa40c0acf0ff62b6f21883d2f3af7292a148a2e456
3
  size 1625426996
runs/Mar04_01-03-39_oi5vv8ctr1709312124223-tkfr5/events.out.tfevents.1709485422.oi5vv8ctr1709312124223-tkfr5.23871.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c3e12d686c57b0c079e90fd097154dbc0b3b5cdf9d78f380553515f377e158a2
3
- size 18187
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca832d8e2d40f76dbdcf63f3389d8fdbf05b2be0066e07ff62a7ba9fe7d89ce0
3
+ size 19215