rendchevi commited on
Commit
43483aa
·
verified ·
1 Parent(s): 6badbfe

End of training

Browse files
Files changed (2) hide show
  1. README.md +77 -0
  2. model.safetensors +1 -1
README.md ADDED
@@ -0,0 +1,77 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: cc-by-nc-4.0
4
+ base_model: AIMH/mental-roberta-large
5
+ tags:
6
+ - generated_from_trainer
7
+ metrics:
8
+ - precision
9
+ - recall
10
+ - accuracy
11
+ model-index:
12
+ - name: mental-roberta-large-tqacd
13
+ results: []
14
+ ---
15
+
16
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
17
+ should probably proofread and complete it, then remove this comment. -->
18
+
19
+ # mental-roberta-large-tqacd
20
+
21
+ This model is a fine-tuned version of [AIMH/mental-roberta-large](https://huggingface.co/AIMH/mental-roberta-large) on the None dataset.
22
+ It achieves the following results on the evaluation set:
23
+ - Loss: 5.1025
24
+ - F1 Macro: 0.2135
25
+ - Precision: 0.2435
26
+ - Recall: 0.2081
27
+ - Accuracy: 0.3960
28
+
29
+ ## Model description
30
+
31
+ More information needed
32
+
33
+ ## Intended uses & limitations
34
+
35
+ More information needed
36
+
37
+ ## Training and evaluation data
38
+
39
+ More information needed
40
+
41
+ ## Training procedure
42
+
43
+ ### Training hyperparameters
44
+
45
+ The following hyperparameters were used during training:
46
+ - learning_rate: 2e-05
47
+ - train_batch_size: 16
48
+ - eval_batch_size: 32
49
+ - seed: 42
50
+ - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
51
+ - lr_scheduler_type: linear
52
+ - lr_scheduler_warmup_ratio: 0.1
53
+ - num_epochs: 20
54
+ - mixed_precision_training: Native AMP
55
+
56
+ ### Training results
57
+
58
+ | Training Loss | Epoch | Step | Validation Loss | F1 Macro | Precision | Recall | Accuracy |
59
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:--------:|
60
+ | No log | 1.0 | 114 | 2.3883 | 0.0709 | 0.0731 | 0.1136 | 0.1683 |
61
+ | No log | 2.0 | 228 | 2.2740 | 0.1730 | 0.1903 | 0.2120 | 0.2921 |
62
+ | No log | 3.0 | 342 | 2.1808 | 0.2186 | 0.2406 | 0.2767 | 0.2723 |
63
+ | No log | 4.0 | 456 | 2.1832 | 0.2306 | 0.2621 | 0.2427 | 0.3069 |
64
+ | 2.0598 | 5.0 | 570 | 2.4082 | 0.2319 | 0.2299 | 0.2796 | 0.3218 |
65
+ | 2.0598 | 6.0 | 684 | 2.6410 | 0.2590 | 0.2524 | 0.2830 | 0.3812 |
66
+ | 2.0598 | 7.0 | 798 | 3.2373 | 0.2529 | 0.2765 | 0.2467 | 0.3861 |
67
+ | 2.0598 | 8.0 | 912 | 3.5088 | 0.2629 | 0.2753 | 0.2573 | 0.3911 |
68
+ | 0.2954 | 9.0 | 1026 | 4.4566 | 0.2175 | 0.2695 | 0.2074 | 0.3812 |
69
+ | 0.2954 | 10.0 | 1140 | 5.1025 | 0.2135 | 0.2435 | 0.2081 | 0.3960 |
70
+
71
+
72
+ ### Framework versions
73
+
74
+ - Transformers 4.57.1
75
+ - Pytorch 2.8.0+cu128
76
+ - Datasets 4.4.1
77
+ - Tokenizers 0.22.1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d1a87137f7f4be78bf1976f2c522b5a4e8e126ddb4eba21401d99013084fdcb1
3
  size 1421532316
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dae02969bdae67f5fad1abb70d3d556feca92e4e3844a1aafac8289b199af991
3
  size 1421532316