Hugging Face's logo

BigTMiami
/
tapt_helpfulness_base_pretraining_model_final

Fill-Mask
Transformers
TensorBoard
Safetensors
roberta
Generated from Trainer
Model card Files
xet
Metrics Community
BigTMiami commited on
Commit
fdc2959
·
verified ·
1 Parent(s): 3a1e374

End of training

Browse files
Files changed (4) hide show
  1. README.md +52 -11
  2. model.safetensors +1 -1
  3. runs/Apr16_15-59-48_f412fc789800/events.out.tfevents.1713283190.f412fc789800.2047.0 +2 -2
  4. runs/Apr16_15-59-48_f412fc789800/events.out.tfevents.1713288685.f412fc789800.2047.1 +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 [roberta-base](https://huggingface.co/roberta-base) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
- - Loss: 1.5970
19
 
20
  ## Model description
21
 
@@ -34,7 +34,7 @@ More information needed
34
  ### Training hyperparameters
35
 
36
  The following hyperparameters were used during training:
37
- - learning_rate: 0.0005
38
  - train_batch_size: 21
39
  - eval_batch_size: 21
40
  - seed: 42
@@ -42,19 +42,60 @@ The following hyperparameters were used during training:
42
  - total_train_batch_size: 42
43
  - optimizer: Adam with betas=(0.9,0.98) and epsilon=1e-06
44
  - lr_scheduler_type: linear
45
- - lr_scheduler_warmup_ratio: 0.06
46
  - num_epochs: 100
47
 
48
  ### Training results
49
 
50
- | Training Loss | Epoch | Step | Validation Loss |
51
- |:-------------:|:-----:|:----:|:---------------:|
52
- | 1.7917 | 1.0 | 232 | 1.5959 |
53
- | 1.7109 | 2.0 | 465 | 1.6216 |
54
- | 1.7571 | 3.0 | 697 | 1.6839 |
55
- | 1.8098 | 4.0 | 930 | 1.7498 |
56
- | 1.9035 | 5.0 | 1162 | 1.8368 |
57
- | 1.9617 | 6.0 | 1395 | 1.9273 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
58
 
59
 
60
  ### Framework versions
 
15
 
16
  This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Loss: 1.4543
19
 
20
  ## Model description
21
 
 
34
  ### Training hyperparameters
35
 
36
  The following hyperparameters were used during training:
37
+ - learning_rate: 0.0001
38
  - train_batch_size: 21
39
  - eval_batch_size: 21
40
  - seed: 42
 
42
  - total_train_batch_size: 42
43
  - optimizer: Adam with betas=(0.9,0.98) and epsilon=1e-06
44
  - lr_scheduler_type: linear
 
45
  - num_epochs: 100
46
 
47
  ### Training results
48
 
49
+ | Training Loss | Epoch | Step | Validation Loss |
50
+ |:-------------:|:-----:|:-----:|:---------------:|
51
+ | 1.7697 | 1.0 | 232 | 1.5904 |
52
+ | 1.6633 | 2.0 | 465 | 1.5650 |
53
+ | 1.6314 | 3.0 | 697 | 1.5461 |
54
+ | 1.594 | 4.0 | 930 | 1.5243 |
55
+ | 1.5766 | 5.0 | 1162 | 1.5312 |
56
+ | 1.5451 | 6.0 | 1395 | 1.5194 |
57
+ | 1.5271 | 7.0 | 1627 | 1.5034 |
58
+ | 1.5038 | 8.0 | 1860 | 1.5080 |
59
+ | 1.4906 | 9.0 | 2092 | 1.4942 |
60
+ | 1.4801 | 10.0 | 2325 | 1.4783 |
61
+ | 1.4638 | 11.0 | 2557 | 1.4900 |
62
+ | 1.4407 | 12.0 | 2790 | 1.4820 |
63
+ | 1.4285 | 13.0 | 3022 | 1.4692 |
64
+ | 1.4177 | 14.0 | 3255 | 1.4698 |
65
+ | 1.4051 | 15.0 | 3487 | 1.4790 |
66
+ | 1.3899 | 16.0 | 3720 | 1.4800 |
67
+ | 1.3832 | 17.0 | 3952 | 1.4730 |
68
+ | 1.3706 | 18.0 | 4185 | 1.4656 |
69
+ | 1.3617 | 19.0 | 4417 | 1.4625 |
70
+ | 1.3464 | 20.0 | 4650 | 1.4699 |
71
+ | 1.3449 | 21.0 | 4882 | 1.4641 |
72
+ | 1.3258 | 22.0 | 5115 | 1.4554 |
73
+ | 1.3248 | 23.0 | 5347 | 1.4595 |
74
+ | 1.3119 | 24.0 | 5580 | 1.4643 |
75
+ | 1.3087 | 25.0 | 5812 | 1.4589 |
76
+ | 1.2942 | 26.0 | 6045 | 1.4633 |
77
+ | 1.2875 | 27.0 | 6277 | 1.4517 |
78
+ | 1.2731 | 28.0 | 6510 | 1.4506 |
79
+ | 1.2727 | 29.0 | 6742 | 1.4501 |
80
+ | 1.261 | 30.0 | 6975 | 1.4492 |
81
+ | 1.2559 | 31.0 | 7207 | 1.4553 |
82
+ | 1.2437 | 32.0 | 7440 | 1.4429 |
83
+ | 1.2404 | 33.0 | 7672 | 1.4456 |
84
+ | 1.2301 | 34.0 | 7905 | 1.4497 |
85
+ | 1.2277 | 35.0 | 8137 | 1.4400 |
86
+ | 1.2154 | 36.0 | 8370 | 1.4491 |
87
+ | 1.2118 | 37.0 | 8602 | 1.4521 |
88
+ | 1.2022 | 38.0 | 8835 | 1.4362 |
89
+ | 1.2027 | 39.0 | 9067 | 1.4431 |
90
+ | 1.1883 | 40.0 | 9300 | 1.4526 |
91
+ | 1.1861 | 41.0 | 9532 | 1.4596 |
92
+ | 1.1747 | 42.0 | 9765 | 1.4390 |
93
+ | 1.1708 | 43.0 | 9997 | 1.4501 |
94
+ | 1.1636 | 44.0 | 10230 | 1.4549 |
95
+ | 1.1623 | 45.0 | 10462 | 1.4616 |
96
+ | 1.1569 | 46.0 | 10695 | 1.4379 |
97
+ | 1.149 | 47.0 | 10927 | 1.4492 |
98
+ | 1.1401 | 48.0 | 11160 | 1.4502 |
99
 
100
 
101
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fa182121c8de4438cd1d4e1292375d74811a62c92b61677f0f6f3f20d7606e6c
3
  size 498813948
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:591de4284210942f0077d53a2e2960808a3f015d758ffd00d1d257043a9d9af3
3
  size 498813948
runs/Apr16_15-59-48_f412fc789800/events.out.tfevents.1713283190.f412fc789800.2047.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:464117a64cc84a9d4963fd513de7c8d485887b025198b576d9e9de2568f99472
3
- size 27797
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:002fb43ccbb5d7f328da009fdcd28a7c812b1c95bf9ca81919d775c843d898bb
3
+ size 28151
runs/Apr16_15-59-48_f412fc789800/events.out.tfevents.1713288685.f412fc789800.2047.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa73ba116ed67eef963cb61b1343be504b805fd81d4bbdb66064f4598979048b
3
+ size 359