Hugging Face's logo

fpadovani
/
de_childes_42

Fill-Mask
Transformers
Safetensors
roberta
Generated from Trainer
Model card Files Community
fpadovani commited on
Commit
0015b4a
·
verified ·
1 Parent(s): 854bb42

Model save

Browse files
Files changed (3) hide show
  1. README.md +109 -0
  2. generation_config.json +6 -0
  3. model.safetensors +1 -1
README.md ADDED
@@ -0,0 +1,109 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ tags:
4
+ - generated_from_trainer
5
+ model-index:
6
+ - name: de_childes_42
7
+ results: []
8
+ ---
9
+
10
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
11
+ should probably proofread and complete it, then remove this comment. -->
12
+
13
+ # de_childes_42
14
+
15
+ This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
16
+ It achieves the following results on the evaluation set:
17
+ - Loss: 4.1897
18
+
19
+ ## Model description
20
+
21
+ More information needed
22
+
23
+ ## Intended uses & limitations
24
+
25
+ More information needed
26
+
27
+ ## Training and evaluation data
28
+
29
+ More information needed
30
+
31
+ ## Training procedure
32
+
33
+ ### Training hyperparameters
34
+
35
+ The following hyperparameters were used during training:
36
+ - learning_rate: 0.0001
37
+ - train_batch_size: 16
38
+ - eval_batch_size: 16
39
+ - seed: 42
40
+ - gradient_accumulation_steps: 2
41
+ - total_train_batch_size: 32
42
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
43
+ - lr_scheduler_type: linear
44
+ - lr_scheduler_warmup_steps: 40000
45
+ - training_steps: 100000
46
+ - mixed_precision_training: Native AMP
47
+
48
+ ### Training results
49
+
50
+ | Training Loss | Epoch | Step | Validation Loss |
51
+ |:-------------:|:-------:|:------:|:---------------:|
52
+ | No log | 1.5021 | 2000 | 7.0336 |
53
+ | 6.9417 | 3.0041 | 4000 | 5.8112 |
54
+ | 6.9417 | 4.5062 | 6000 | 5.4586 |
55
+ | 5.2077 | 6.0083 | 8000 | 5.1717 |
56
+ | 5.2077 | 7.5103 | 10000 | 4.9583 |
57
+ | 4.7315 | 9.0124 | 12000 | 4.8002 |
58
+ | 4.7315 | 10.5145 | 14000 | 4.6706 |
59
+ | 4.4253 | 12.0165 | 16000 | 4.5552 |
60
+ | 4.4253 | 13.5186 | 18000 | 4.4522 |
61
+ | 4.1962 | 15.0207 | 20000 | 4.3739 |
62
+ | 4.1962 | 16.5227 | 22000 | 4.2925 |
63
+ | 4.0105 | 18.0248 | 24000 | 4.2277 |
64
+ | 4.0105 | 19.5268 | 26000 | 4.1706 |
65
+ | 3.857 | 21.0289 | 28000 | 4.1245 |
66
+ | 3.857 | 22.5310 | 30000 | 4.0846 |
67
+ | 3.7298 | 24.0330 | 32000 | 4.0589 |
68
+ | 3.7298 | 25.5351 | 34000 | 4.0266 |
69
+ | 3.6218 | 27.0372 | 36000 | 4.0028 |
70
+ | 3.6218 | 28.5392 | 38000 | 3.9863 |
71
+ | 3.5278 | 30.0413 | 40000 | 3.9732 |
72
+ | 3.5278 | 31.5434 | 42000 | 3.9720 |
73
+ | 3.4351 | 33.0454 | 44000 | 3.9599 |
74
+ | 3.4351 | 34.5475 | 46000 | 3.9566 |
75
+ | 3.3444 | 36.0496 | 48000 | 3.9572 |
76
+ | 3.3444 | 37.5516 | 50000 | 3.9680 |
77
+ | 3.2651 | 39.0537 | 52000 | 3.9788 |
78
+ | 3.2651 | 40.5558 | 54000 | 3.9815 |
79
+ | 3.1966 | 42.0578 | 56000 | 3.9928 |
80
+ | 3.1966 | 43.5599 | 58000 | 4.0061 |
81
+ | 3.1344 | 45.0620 | 60000 | 4.0126 |
82
+ | 3.1344 | 46.5640 | 62000 | 4.0198 |
83
+ | 3.0785 | 48.0661 | 64000 | 4.0377 |
84
+ | 3.0785 | 49.5682 | 66000 | 4.0502 |
85
+ | 3.0287 | 51.0702 | 68000 | 4.0644 |
86
+ | 3.0287 | 52.5723 | 70000 | 4.0714 |
87
+ | 2.9837 | 54.0744 | 72000 | 4.0852 |
88
+ | 2.9837 | 55.5764 | 74000 | 4.0964 |
89
+ | 2.9422 | 57.0785 | 76000 | 4.1148 |
90
+ | 2.9422 | 58.5805 | 78000 | 4.1221 |
91
+ | 2.9052 | 60.0826 | 80000 | 4.1276 |
92
+ | 2.9052 | 61.5847 | 82000 | 4.1346 |
93
+ | 2.8708 | 63.0867 | 84000 | 4.1505 |
94
+ | 2.8708 | 64.5888 | 86000 | 4.1574 |
95
+ | 2.839 | 66.0909 | 88000 | 4.1675 |
96
+ | 2.839 | 67.5929 | 90000 | 4.1727 |
97
+ | 2.8117 | 69.0950 | 92000 | 4.1767 |
98
+ | 2.8117 | 70.5971 | 94000 | 4.1823 |
99
+ | 2.7886 | 72.0991 | 96000 | 4.1867 |
100
+ | 2.7886 | 73.6012 | 98000 | 4.1872 |
101
+ | 2.768 | 75.1033 | 100000 | 4.1897 |
102
+
103
+
104
+ ### Framework versions
105
+
106
+ - Transformers 4.45.2
107
+ - Pytorch 2.5.1+cu124
108
+ - Datasets 3.0.1
109
+ - Tokenizers 0.20.1
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "eos_token_id": 1,
5
+ "transformers_version": "4.45.2"
6
+ }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6ac982519ad3562884a3e13f3d4c42d6ed503198faab547ec15a60bb20677e7f
3
  size 51007160
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:164fbb8f0f3a7eea35ce7bec29603bcbee094a9ca3ebfd3a29864ea885b13725
3
  size 51007160