Hugging Face's logo

fpadovani
/
fr_childes_13

Fill-Mask
Transformers
Safetensors
roberta
Generated from Trainer
Model card Files Community
fpadovani commited on
Commit
726a7fe
·
verified ·
1 Parent(s): f9c703d

Model save

Browse files
Files changed (2) hide show
  1. README.md +108 -0
  2. model.safetensors +1 -1
README.md ADDED
@@ -0,0 +1,108 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ tags:
4
+ - generated_from_trainer
5
+ model-index:
6
+ - name: fr_childes_13
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
+ # fr_childes_13
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: 1.8321
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: 13
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
+
47
+ ### Training results
48
+
49
+ | Training Loss | Epoch | Step | Validation Loss |
50
+ |:-------------:|:-----:|:------:|:---------------:|
51
+ | No log | 2.5 | 2000 | 7.2410 |
52
+ | 7.2222 | 5.0 | 4000 | 5.9683 |
53
+ | 7.2222 | 7.5 | 6000 | 5.8241 |
54
+ | 5.6899 | 10.0 | 8000 | 5.7266 |
55
+ | 5.6899 | 12.5 | 10000 | 5.6300 |
56
+ | 5.4663 | 15.0 | 12000 | 5.5524 |
57
+ | 5.4663 | 17.5 | 14000 | 5.5122 |
58
+ | 5.3077 | 20.0 | 16000 | 5.4600 |
59
+ | 5.3077 | 22.5 | 18000 | 5.4015 |
60
+ | 5.1915 | 25.0 | 20000 | 5.3367 |
61
+ | 5.1915 | 27.5 | 22000 | 5.1496 |
62
+ | 4.8173 | 30.0 | 24000 | 4.0808 |
63
+ | 4.8173 | 32.5 | 26000 | 3.3695 |
64
+ | 3.387 | 35.0 | 28000 | 3.0722 |
65
+ | 3.387 | 37.5 | 30000 | 2.8992 |
66
+ | 2.8035 | 40.0 | 32000 | 2.7279 |
67
+ | 2.8035 | 42.5 | 34000 | 2.6168 |
68
+ | 2.531 | 45.0 | 36000 | 2.5570 |
69
+ | 2.531 | 47.5 | 38000 | 2.4636 |
70
+ | 2.3359 | 50.0 | 40000 | 2.4193 |
71
+ | 2.3359 | 52.5 | 42000 | 2.3528 |
72
+ | 2.1893 | 55.0 | 44000 | 2.2999 |
73
+ | 2.1893 | 57.5 | 46000 | 2.2412 |
74
+ | 2.0715 | 60.0 | 48000 | 2.1982 |
75
+ | 2.0715 | 62.5 | 50000 | 2.1534 |
76
+ | 1.974 | 65.0 | 52000 | 2.1156 |
77
+ | 1.974 | 67.5 | 54000 | 2.1153 |
78
+ | 1.9016 | 70.0 | 56000 | 2.0625 |
79
+ | 1.9016 | 72.5 | 58000 | 2.0274 |
80
+ | 1.8403 | 75.0 | 60000 | 2.0366 |
81
+ | 1.8403 | 77.5 | 62000 | 1.9956 |
82
+ | 1.7872 | 80.0 | 64000 | 1.9750 |
83
+ | 1.7872 | 82.5 | 66000 | 1.9521 |
84
+ | 1.7439 | 85.0 | 68000 | 1.9579 |
85
+ | 1.7439 | 87.5 | 70000 | 1.9302 |
86
+ | 1.7084 | 90.0 | 72000 | 1.9384 |
87
+ | 1.7084 | 92.5 | 74000 | 1.9067 |
88
+ | 1.6752 | 95.0 | 76000 | 1.9239 |
89
+ | 1.6752 | 97.5 | 78000 | 1.8918 |
90
+ | 1.6482 | 100.0 | 80000 | 1.8803 |
91
+ | 1.6482 | 102.5 | 82000 | 1.8641 |
92
+ | 1.6209 | 105.0 | 84000 | 1.8514 |
93
+ | 1.6209 | 107.5 | 86000 | 1.8467 |
94
+ | 1.5966 | 110.0 | 88000 | 1.8564 |
95
+ | 1.5966 | 112.5 | 90000 | 1.8653 |
96
+ | 1.5815 | 115.0 | 92000 | 1.8481 |
97
+ | 1.5815 | 117.5 | 94000 | 1.8392 |
98
+ | 1.5695 | 120.0 | 96000 | 1.8283 |
99
+ | 1.5695 | 122.5 | 98000 | 1.8264 |
100
+ | 1.5583 | 125.0 | 100000 | 1.8321 |
101
+
102
+
103
+ ### Framework versions
104
+
105
+ - Transformers 4.45.2
106
+ - Pytorch 2.5.1+cu124
107
+ - Datasets 3.0.1
108
+ - Tokenizers 0.20.1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5eb2a2c2c850d26f1e5389b238174e35e60755867d9894a73cddc957e839be33
3
  size 59702184
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5da546c0d24607c6ffe5f9abd3b5d8c022211087389523f2c2353c7ebe8f9551
3
  size 59702184