Hugging Face's logo

li-jay-cs
/
gptj-supervised-summarize-checkpoint

Text Generation
Transformers
PyTorch
TensorBoard
gpt2
Generated from Trainer
text-generation-inference
Model card Files
xet
 Metrics Community
1
li-jay-cs commited on
Commit
ce15d4b
·
1 Parent(s): 251fb8b

Model save

Browse files
Files changed (3) hide show
  1. README.md +10 -10
  2. pytorch_model.bin +1 -1
  3. runs/Nov14_08-11-28_ed58f05e541c/events.out.tfevents.1699949499.ed58f05e541c.10087.0 +2 -2
README.md CHANGED
@@ -17,11 +17,11 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  This model is a fine-tuned version of [li-jay-cs/gptj-supervised-summarize-checkpoint](https://huggingface.co/li-jay-cs/gptj-supervised-summarize-checkpoint) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 1.9180
21
- - Rouge1: 0.5817
22
- - Rouge2: 0.1815
23
- - Rougel: 0.3832
24
- - Rougelsum: 0.5069
25
 
26
  ## Model description
27
 
@@ -48,17 +48,17 @@ The following hyperparameters were used during training:
48
  - optimizer: Adam with betas=(0.9,0.95) and epsilon=1e-08
49
  - lr_scheduler_type: linear
50
  - lr_scheduler_warmup_steps: 100
51
- - num_epochs: 1
52
  - mixed_precision_training: Native AMP
53
 
54
  ### Training results
55
 
56
  | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
57
  |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|
58
- | 2.0512 | 0.21 | 500 | 1.9746 | 0.5794 | 0.1755 | 0.3743 | 0.5028 |
59
- | 2.0334 | 0.43 | 1000 | 1.9463 | 0.5795 | 0.1779 | 0.3784 | 0.5032 |
60
- | 1.9925 | 0.64 | 1500 | 1.9287 | 0.5831 | 0.1810 | 0.3812 | 0.5069 |
61
- | 1.9887 | 0.86 | 2000 | 1.9180 | 0.5817 | 0.1815 | 0.3832 | 0.5069 |
62
 
63
 
64
  ### Framework versions
 
17
 
18
  This model is a fine-tuned version of [li-jay-cs/gptj-supervised-summarize-checkpoint](https://huggingface.co/li-jay-cs/gptj-supervised-summarize-checkpoint) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 1.8506
21
+ - Rouge1: 0.5938
22
+ - Rouge2: 0.1912
23
+ - Rougel: 0.3937
24
+ - Rougelsum: 0.5184
25
 
26
  ## Model description
27
 
 
48
  - optimizer: Adam with betas=(0.9,0.95) and epsilon=1e-08
49
  - lr_scheduler_type: linear
50
  - lr_scheduler_warmup_steps: 100
51
+ - num_epochs: 2
52
  - mixed_precision_training: Native AMP
53
 
54
  ### Training results
55
 
56
  | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
57
  |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|
58
+ | 1.904 | 0.43 | 1000 | 1.8633 | 0.5912 | 0.1888 | 0.3913 | 0.5149 |
59
+ | 1.8931 | 0.86 | 2000 | 1.8584 | 0.5907 | 0.1890 | 0.3920 | 0.5153 |
60
+ | 1.8758 | 1.28 | 3000 | 1.8545 | 0.5929 | 0.1906 | 0.3929 | 0.5168 |
61
+ | 1.8699 | 1.71 | 4000 | 1.8506 | 0.5938 | 0.1912 | 0.3937 | 0.5184 |
62
 
63
 
64
  ### Framework versions
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:486a9d5b5946068a1b5cbb803215779614f9ebe2c470104dbcc1cd587942ba5d
3
  size 326120926
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa09caf64af0a9d4b7048c60be8edb1bfb1c8e2ff6e23208ca424c7e00993f3a
3
  size 326120926
runs/Nov14_08-11-28_ed58f05e541c/events.out.tfevents.1699949499.ed58f05e541c.10087.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f1db148953b6eee295f67bf3bc8f57b756fd040d526c020cd665cd106a189690
3
- size 19118
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7159197041453179d71ebda7cbbc58d8745015eb4cd29a9bb1c5b974a06a0a01
3
+ size 21513