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
4efc56c
•
1 Parent(s): c79421b

Fine-tuned GPT-2 on Wikitext-2

Browse files
Files changed (4) hide show
  1. README.md +35 -35
  2. model.safetensors +1 -1
  3. runs/Jul03_15-26-30_7de6f6a510b5/events.out.tfevents.1720020391.7de6f6a510b5.789.8 +2 -2
  4. runs/Jul03_15-26-30_7de6f6a510b5/events.out.tfevents.1720022871.7de6f6a510b5.789.9 +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: 3.7863
19
 
20
  ## Model description
21
 
@@ -48,40 +48,40 @@ The following hyperparameters were used during training:
48
 
49
  | Training Loss | Epoch | Step | Validation Loss |
50
  |:-------------:|:------:|:-----:|:---------------:|
51
- | No log | 0.0871 | 400 | 4.0717 |
52
- | 1.1036 | 0.1743 | 800 | 4.2755 |
53
- | 0.5557 | 0.2614 | 1200 | 4.2846 |
54
- | 0.5875 | 0.3486 | 1600 | 4.3302 |
55
- | 0.7643 | 0.4357 | 2000 | 4.2009 |
56
- | 0.7643 | 0.5229 | 2400 | 4.2351 |
57
- | 0.8454 | 0.6100 | 2800 | 4.1802 |
58
- | 0.8842 | 0.6972 | 3200 | 4.1432 |
59
- | 0.9623 | 0.7843 | 3600 | 4.1293 |
60
- | 1.035 | 0.8715 | 4000 | 4.1069 |
61
- | 1.035 | 0.9586 | 4400 | 4.0661 |
62
- | 1.0997 | 1.0458 | 4800 | 4.1568 |
63
- | 0.9309 | 1.1329 | 5200 | 4.1577 |
64
- | 0.9472 | 1.2200 | 5600 | 4.1401 |
65
- | 0.9693 | 1.3072 | 6000 | 4.0909 |
66
- | 0.9693 | 1.3943 | 6400 | 4.1024 |
67
- | 0.9997 | 1.4815 | 6800 | 4.0739 |
68
- | 1.0231 | 1.5686 | 7200 | 4.0358 |
69
- | 1.0753 | 1.6558 | 7600 | 4.0478 |
70
- | 1.0979 | 1.7429 | 8000 | 4.0195 |
71
- | 1.0979 | 1.8301 | 8400 | 3.9682 |
72
- | 1.1759 | 1.9172 | 8800 | 3.9687 |
73
- | 1.1717 | 2.0044 | 9200 | 3.9502 |
74
- | 1.126 | 2.0915 | 9600 | 3.9832 |
75
- | 1.1136 | 2.1786 | 10000 | 3.9696 |
76
- | 1.1136 | 2.2658 | 10400 | 3.9509 |
77
- | 1.1521 | 2.3529 | 10800 | 3.9246 |
78
- | 1.186 | 2.4401 | 11200 | 3.9041 |
79
- | 1.2276 | 2.5272 | 11600 | 3.8872 |
80
- | 1.2686 | 2.6144 | 12000 | 3.8677 |
81
- | 1.2686 | 2.7015 | 12400 | 3.8415 |
82
- | 1.3043 | 2.7887 | 12800 | 3.8204 |
83
- | 1.3474 | 2.8758 | 13200 | 3.8007 |
84
- | 1.3954 | 2.9630 | 13600 | 3.7884 |
85
 
86
 
87
  ### 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: 3.8830
19
 
20
  ## Model description
21
 
 
48
 
49
  | Training Loss | Epoch | Step | Validation Loss |
50
  |:-------------:|:------:|:-----:|:---------------:|
51
+ | No log | 0.0871 | 400 | 4.2671 |
52
+ | 1.0011 | 0.1743 | 800 | 4.5104 |
53
+ | 0.4041 | 0.2614 | 1200 | 4.5219 |
54
+ | 0.4304 | 0.3486 | 1600 | 4.5754 |
55
+ | 0.5773 | 0.4357 | 2000 | 4.4567 |
56
+ | 0.5773 | 0.5229 | 2400 | 4.4879 |
57
+ | 0.6563 | 0.6100 | 2800 | 4.4276 |
58
+ | 0.6965 | 0.6972 | 3200 | 4.4034 |
59
+ | 0.7728 | 0.7843 | 3600 | 4.3906 |
60
+ | 0.8479 | 0.8715 | 4000 | 4.3692 |
61
+ | 0.8479 | 0.9586 | 4400 | 4.3255 |
62
+ | 0.9187 | 1.0458 | 4800 | 4.4073 |
63
+ | 0.7619 | 1.1329 | 5200 | 4.4022 |
64
+ | 0.7889 | 1.2200 | 5600 | 4.3840 |
65
+ | 0.8156 | 1.3072 | 6000 | 4.3322 |
66
+ | 0.8156 | 1.3943 | 6400 | 4.3391 |
67
+ | 0.8547 | 1.4815 | 6800 | 4.2961 |
68
+ | 0.8862 | 1.5686 | 7200 | 4.2534 |
69
+ | 0.9424 | 1.6558 | 7600 | 4.2652 |
70
+ | 0.9764 | 1.7429 | 8000 | 4.2246 |
71
+ | 0.9764 | 1.8301 | 8400 | 4.1637 |
72
+ | 1.0649 | 1.9172 | 8800 | 4.1581 |
73
+ | 1.0692 | 2.0044 | 9200 | 4.1303 |
74
+ | 1.0272 | 2.0915 | 9600 | 4.1594 |
75
+ | 1.0207 | 2.1786 | 10000 | 4.1426 |
76
+ | 1.0207 | 2.2658 | 10400 | 4.1154 |
77
+ | 1.0669 | 2.3529 | 10800 | 4.0789 |
78
+ | 1.1129 | 2.4401 | 11200 | 4.0485 |
79
+ | 1.1645 | 2.5272 | 11600 | 4.0232 |
80
+ | 1.2151 | 2.6144 | 12000 | 3.9955 |
81
+ | 1.2151 | 2.7015 | 12400 | 3.9612 |
82
+ | 1.262 | 2.7887 | 12800 | 3.9308 |
83
+ | 1.3164 | 2.8758 | 13200 | 3.9033 |
84
+ | 1.3759 | 2.9630 | 13600 | 3.8860 |
85
 
86
 
87
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3425cd7a426bf60818dd5c05aeec5f98357c75b5ac7acd3707664d01226653f7
3
  size 497774208
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3cf3dd926baddf275f3dee77a0ade1195e86a7048d07a82a5c810ac2eb21b57e
3
  size 497774208
runs/Jul03_15-26-30_7de6f6a510b5/events.out.tfevents.1720020391.7de6f6a510b5.789.8 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ee939fed32b7441b53873060dfd31d462f677857b06035a8d93d82a34ee9edba
3
- size 20001
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8994cc61006af9c80b100b7bc1e4ea086265fb9f1d13e5ab547611378ab08d46
3
+ size 20355
runs/Jul03_15-26-30_7de6f6a510b5/events.out.tfevents.1720022871.7de6f6a510b5.789.9 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d668ccb9e9d0901560acbc2e8e992e2d4e59a207b84ae1f7553c1d6ca752cc41
3
+ size 359