BigTMiami commited on
Commit
2423f21
·
verified ·
1 Parent(s): adb63d6

End of training

Browse files
README.md ADDED
@@ -0,0 +1,69 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ base_model: roberta-base
4
+ tags:
5
+ - generated_from_trainer
6
+ model-index:
7
+ - name: tapt_helpfulness_base_pretraining_model
8
+ results: []
9
+ ---
10
+
11
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
12
+ should probably proofread and complete it, then remove this comment. -->
13
+
14
+ # tapt_helpfulness_base_pretraining_model
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: 1.4502
19
+
20
+ ## Model description
21
+
22
+ More information needed
23
+
24
+ ## Intended uses & limitations
25
+
26
+ More information needed
27
+
28
+ ## Training and evaluation data
29
+
30
+ More information needed
31
+
32
+ ## Training procedure
33
+
34
+ ### Training hyperparameters
35
+
36
+ The following hyperparameters were used during training:
37
+ - learning_rate: 0.0005
38
+ - train_batch_size: 32
39
+ - eval_batch_size: 32
40
+ - seed: 42
41
+ - gradient_accumulation_steps: 11
42
+ - total_train_batch_size: 352
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: 10
47
+
48
+ ### Training results
49
+
50
+ | Training Loss | Epoch | Step | Validation Loss |
51
+ |:-------------:|:-----:|:----:|:---------------:|
52
+ | 1.9099 | 0.97 | 27 | 1.6497 |
53
+ | 1.716 | 1.98 | 55 | 1.6088 |
54
+ | 1.6549 | 2.99 | 83 | 1.5624 |
55
+ | 1.6585 | 3.97 | 110 | 1.5455 |
56
+ | 1.557 | 4.98 | 138 | 1.5446 |
57
+ | 1.5142 | 5.99 | 166 | 1.5057 |
58
+ | 1.4788 | 7.0 | 194 | 1.4934 |
59
+ | 1.5057 | 7.97 | 221 | 1.4714 |
60
+ | 1.4232 | 8.98 | 249 | 1.4541 |
61
+ | 1.3778 | 9.74 | 270 | 1.4498 |
62
+
63
+
64
+ ### Framework versions
65
+
66
+ - Transformers 4.38.2
67
+ - Pytorch 2.2.1+cu121
68
+ - Datasets 2.18.0
69
+ - Tokenizers 0.15.2
runs/Apr15_22-32-56_47f7c53496d7/events.out.tfevents.1713220378.47f7c53496d7.229.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7e1c9a3b40afe97489793669b58a45a1d8e337414808a373d48f3d7c0b3c039d
3
- size 9428
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:884947d1d2bbc9d0e4b3da4ce47be24567e618b922cae2f895670eca15addab0
3
+ size 9782
runs/Apr15_22-32-56_47f7c53496d7/events.out.tfevents.1713221586.47f7c53496d7.229.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba91fb61404aac42a47d7c5d4ae75ceaf3b341b8b15f75722cf7b99883b395fe
3
+ size 359