Hugging Face's logo

GlycerinLOL
/
LLM_Teached_Pegasus_50k

Text2Text Generation
Transformers
TensorBoard
Safetensors
pegasus
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
GlycerinLOL commited on
Commit
5bcd218
•
1 Parent(s): 21128aa

Model save

Browse files
Files changed (3) hide show
  1. README.md +19 -15
  2. model.safetensors +1 -1
  3. runs/Mar02_21-24-26_oi5vv8ctr1709312124223-tkfr5/events.out.tfevents.1709385884.oi5vv8ctr1709312124223-tkfr5.32755.0 +2 -2
README.md CHANGED
@@ -19,15 +19,15 @@ should probably proofread and complete it, then remove this comment. -->
19
 
20
  This model is a fine-tuned version of [google/pegasus-xsum](https://huggingface.co/google/pegasus-xsum) on an unknown dataset.
21
  It achieves the following results on the evaluation set:
22
- - Loss: 1.6541
23
- - Rouge1: 0.4665
24
- - Rouge2: 0.2182
25
- - Rougel: 0.3824
26
- - Rougelsum: 0.3824
27
- - Gen Len: 26.5458
28
- - Precision: 0.9101
29
- - Recall: 0.9085
30
- - F1: 0.9092
31
 
32
  ## Model description
33
 
@@ -54,7 +54,7 @@ The following hyperparameters were used during training:
54
  - total_train_batch_size: 128
55
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
56
  - lr_scheduler_type: linear
57
- - num_epochs: 12
58
  - mixed_precision_training: Native AMP
59
 
60
  ### Training results
@@ -68,11 +68,15 @@ The following hyperparameters were used during training:
68
  | 1.8271 | 5.0 | 1951 | 0.9074 | 26.3015 | 1.7033 | 0.9087 | 0.9065 | 0.4561 | 0.2098 | 0.3735 | 0.3734 |
69
  | 1.8067 | 6.0 | 2340 | 0.9077 | 26.4389 | 1.6897 | 0.9089 | 0.9069 | 0.4592 | 0.2114 | 0.3762 | 0.3759 |
70
  | 1.7833 | 7.0 | 2731 | 0.9079 | 26.3745 | 1.6819 | 0.9092 | 0.9071 | 0.4598 | 0.2115 | 0.3764 | 0.376 |
71
- | 1.7683 | 8.0 | 3120 | 1.6763 | 0.4621 | 0.2133 | 0.3791 | 0.3789 | 26.6204| 0.9094 | 0.9076 | 0.9083 |
72
- | 1.7559 | 9.0 | 3511 | 1.6662 | 0.4632 | 0.215 | 0.38 | 0.3799 | 26.424 | 0.9098 | 0.9078 | 0.9086 |
73
- | 1.7559 | 10.0 | 3902 | 1.6594 | 0.4651 | 0.2168 | 0.3812 | 0.3812 | 26.5425| 0.9099 | 0.9082 | 0.9089 |
74
- | 1.7357 | 11.0 | 4293 | 1.6555 | 0.4663 | 0.2178 | 0.3824 | 0.3823 | 26.6051| 0.91 | 0.9086 | 0.9091 |
75
- | 1.7297 | 11.99 | 4680 | 1.6541 | 0.4665 | 0.2182 | 0.3824 | 0.3824 | 26.5458| 0.9101 | 0.9085 | 0.9092 |
 
 
 
 
76
 
77
 
78
  ### Framework versions
 
19
 
20
  This model is a fine-tuned version of [google/pegasus-xsum](https://huggingface.co/google/pegasus-xsum) on an unknown dataset.
21
  It achieves the following results on the evaluation set:
22
+ - Loss: 1.6378
23
+ - Rouge1: 0.4698
24
+ - Rouge2: 0.2197
25
+ - Rougel: 0.385
26
+ - Rougelsum: 0.3849
27
+ - Gen Len: 26.5251
28
+ - Precision: 0.9107
29
+ - Recall: 0.909
30
+ - F1: 0.9096
31
 
32
  ## Model description
33
 
 
54
  - total_train_batch_size: 128
55
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
56
  - lr_scheduler_type: linear
57
+ - num_epochs: 16
58
  - mixed_precision_training: Native AMP
59
 
60
  ### Training results
 
68
  | 1.8271 | 5.0 | 1951 | 0.9074 | 26.3015 | 1.7033 | 0.9087 | 0.9065 | 0.4561 | 0.2098 | 0.3735 | 0.3734 |
69
  | 1.8067 | 6.0 | 2340 | 0.9077 | 26.4389 | 1.6897 | 0.9089 | 0.9069 | 0.4592 | 0.2114 | 0.3762 | 0.3759 |
70
  | 1.7833 | 7.0 | 2731 | 0.9079 | 26.3745 | 1.6819 | 0.9092 | 0.9071 | 0.4598 | 0.2115 | 0.3764 | 0.376 |
71
+ | 1.7683 | 8.0 | 3120 | 0.9083 | 26.6204 | 1.6763 | 0.9094 | 0.9076 | 0.4621 | 0.2133 | 0.3791 | 0.3789 |
72
+ | 1.7559 | 9.0 | 3511 | 0.9086 | 26.424 | 1.6662 | 0.9098 | 0.9078 | 0.4632 | 0.215 | 0.38 | 0.3799 |
73
+ | 1.7559 | 10.0 | 3902 | 0.9089 | 26.5425 | 1.6594 | 0.9099 | 0.9082 | 0.4651 | 0.2168 | 0.3812 | 0.3812 |
74
+ | 1.7357 | 11.0 | 4293 | 0.9091 | 26.6051 | 1.6555 | 0.91 | 0.9086 | 0.4663 | 0.2178 | 0.3824 | 0.3823 |
75
+ | 1.7297 | 12.0 | 4680 | 1.6508 | 0.4668 | 0.2175 | 0.3823 | 0.3822 | 26.4393| 0.9103 | 0.9084 | 0.9092 |
76
+ | 1.7165 | 13.0 | 5071 | 1.6451 | 0.4687 | 0.2191 | 0.3834 | 0.3834 | 26.6385| 0.9103 | 0.9089 | 0.9094 |
77
+ | 1.7165 | 14.0 | 5462 | 1.6405 | 0.4691 | 0.2193 | 0.3845 | 0.3844 | 26.4156| 0.9106 | 0.9087 | 0.9095 |
78
+ | 1.7068 | 15.0 | 5853 | 1.6383 | 0.4699 | 0.2204 | 0.3853 | 0.3853 | 26.4571| 0.9108 | 0.9089 | 0.9097 |
79
+ | 1.7004 | 15.99 | 6240 | 1.6378 | 0.4698 | 0.2197 | 0.385 | 0.3849 | 26.5251| 0.9107 | 0.909 | 0.9096 |
80
 
81
 
82
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:756216d04640485ba567c583de3d2544a8a714043469cf6d6cfba74a3a2a413d
3
  size 2279458540
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d57eb397523b839820ba2cac8026a7a1aaaaff451594eda57186e97d8d5a385
3
  size 2279458540
runs/Mar02_21-24-26_oi5vv8ctr1709312124223-tkfr5/events.out.tfevents.1709385884.oi5vv8ctr1709312124223-tkfr5.32755.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c61fd4628cdb06ce7bbdb3bf714cb76d3000a7b27ad1cf20b8b6be7d42f22fb4
3
- size 8452
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:466e13393607a6f3dc378956c5295fa4ee923be27b342c30902e02ed8c5dc482
3
+ size 9480