Hugging Face's logo

cuba6112
/
orion

Question Answering
Transformers
TensorBoard
Safetensors
English
gpt2
text-generation
fine-tuned
text-generation-inference
Inference Endpoints
Model card Files Metrics Community
cuba6112 commited on
Commit
37e7bd0
•
1 Parent(s): c6236f3

Fine-tuned GPT-2 on Wikitext-2

Browse files
Files changed (4) hide show
  1. README.md +39 -16
  2. model.safetensors +1 -1
  3. runs/Jun30_21-23-50_Delta6112/events.out.tfevents.1719797030.Delta6112.24560.4 +2 -2
  4. runs/Jun30_21-23-50_Delta6112/events.out.tfevents.1719799714.Delta6112.24560.5 +3 -0
README.md CHANGED
@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  This model is a fine-tuned version of [cuba6112/orion](https://huggingface.co/cuba6112/orion) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
- - Loss: 2.8471
19
 
20
  ## Model description
21
 
@@ -34,31 +34,54 @@ More information needed
34
  ### Training hyperparameters
35
 
36
  The following hyperparameters were used during training:
37
- - learning_rate: 5e-05
38
  - train_batch_size: 8
39
  - eval_batch_size: 8
40
  - seed: 42
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: 1
45
  - mixed_precision_training: Native AMP
46
 
47
  ### Training results
48
 
49
- | Training Loss | Epoch | Step | Validation Loss |
50
- |:-------------:|:------:|:----:|:---------------:|
51
- | No log | 0.0871 | 400 | 2.8882 |
52
- | 2.9006 | 0.1743 | 800 | 2.9229 |
53
- | 2.6909 | 0.2614 | 1200 | 2.9341 |
54
- | 2.6634 | 0.3486 | 1600 | 2.9170 |
55
- | 2.769 | 0.4357 | 2000 | 2.9012 |
56
- | 2.769 | 0.5229 | 2400 | 2.8874 |
57
- | 2.8258 | 0.6100 | 2800 | 2.8755 |
58
- | 2.8313 | 0.6972 | 3200 | 2.8689 |
59
- | 2.9336 | 0.7843 | 3600 | 2.8605 |
60
- | 2.9614 | 0.8715 | 4000 | 2.8522 |
61
- | 2.9614 | 0.9586 | 4400 | 2.8481 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
62
 
63
 
64
  ### Framework versions
 
15
 
16
  This model is a fine-tuned version of [cuba6112/orion](https://huggingface.co/cuba6112/orion) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Loss: 2.9051
19
 
20
  ## Model description
21
 
 
34
  ### Training hyperparameters
35
 
36
  The following hyperparameters were used during training:
37
+ - learning_rate: 2e-05
38
  - train_batch_size: 8
39
  - eval_batch_size: 8
40
  - seed: 42
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: 3
45
  - mixed_precision_training: Native AMP
46
 
47
  ### Training results
48
 
49
+ | Training Loss | Epoch | Step | Validation Loss |
50
+ |:-------------:|:------:|:-----:|:---------------:|
51
+ | No log | 0.0871 | 400 | 2.9643 |
52
+ | 2.3368 | 0.1743 | 800 | 3.0703 |
53
+ | 1.9165 | 0.2614 | 1200 | 3.0753 |
54
+ | 1.9558 | 0.3486 | 1600 | 3.0568 |
55
+ | 2.2234 | 0.4357 | 2000 | 2.9665 |
56
+ | 2.2234 | 0.5229 | 2400 | 2.9577 |
57
+ | 2.3365 | 0.6100 | 2800 | 2.9338 |
58
+ | 2.3944 | 0.6972 | 3200 | 2.9116 |
59
+ | 2.5464 | 0.7843 | 3600 | 2.8948 |
60
+ | 2.6256 | 0.8715 | 4000 | 2.8809 |
61
+ | 2.6256 | 0.9586 | 4400 | 2.8674 |
62
+ | 2.7123 | 1.0458 | 4800 | 2.9054 |
63
+ | 2.5281 | 1.1329 | 5200 | 2.9048 |
64
+ | 2.494 | 1.2200 | 5600 | 2.9072 |
65
+ | 2.4786 | 1.3072 | 6000 | 2.9004 |
66
+ | 2.4786 | 1.3943 | 6400 | 2.9019 |
67
+ | 2.4863 | 1.4815 | 6800 | 2.8996 |
68
+ | 2.4702 | 1.5686 | 7200 | 2.8983 |
69
+ | 2.5037 | 1.6558 | 7600 | 2.9061 |
70
+ | 2.4735 | 1.7429 | 8000 | 2.9015 |
71
+ | 2.4735 | 1.8301 | 8400 | 2.8933 |
72
+ | 2.5219 | 1.9172 | 8800 | 2.8995 |
73
+ | 2.4786 | 2.0044 | 9200 | 2.9007 |
74
+ | 2.4405 | 2.0915 | 9600 | 2.9105 |
75
+ | 2.4194 | 2.1786 | 10000 | 2.9117 |
76
+ | 2.4194 | 2.2658 | 10400 | 2.9109 |
77
+ | 2.4449 | 2.3529 | 10800 | 2.9095 |
78
+ | 2.4213 | 2.4401 | 11200 | 2.9069 |
79
+ | 2.4322 | 2.5272 | 11600 | 2.9115 |
80
+ | 2.4498 | 2.6144 | 12000 | 2.9072 |
81
+ | 2.4498 | 2.7015 | 12400 | 2.9053 |
82
+ | 2.4326 | 2.7887 | 12800 | 2.9054 |
83
+ | 2.4407 | 2.8758 | 13200 | 2.9059 |
84
+ | 2.4504 | 2.9630 | 13600 | 2.9053 |
85
 
86
 
87
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7d5c41b82f9cc483019ddbb4e75328a29a1fe216d64a61d47bc9a234f3349b32
3
  size 497774208
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cdcf918da9bee0cc4b60ad138e3e17a643ba3d0b82d990072fd93c0623999ee1
3
  size 497774208
runs/Jun30_21-23-50_Delta6112/events.out.tfevents.1719797030.Delta6112.24560.4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:799abf9f1cb12162c2f61c45f5ed9ad5f1a55b74113242900d95c352bf046e2a
3
- size 19875
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95b55918e14083128b72c2b47536c7fc9f9b386802d27c15ca1cd4b7949c4175
3
+ size 20229
runs/Jun30_21-23-50_Delta6112/events.out.tfevents.1719799714.Delta6112.24560.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a38f9eb13132da0c9957ea61b8874e37c5975c3c2563e30a60a0ce5d82f1c428
3
+ size 359