Hugging Face's logo

fpadovani
/
fr_childes_42

Fill-Mask
Transformers
Safetensors
roberta
Generated from Trainer
Model card Files Community
fpadovani commited on
Commit
4c6c11a
·
verified ·
1 Parent(s): c228de5

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: fr_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
+ # fr_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: 4.1449
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 | 2.5 | 2000 | 6.5725 |
53
+ | 6.5185 | 5.0 | 4000 | 4.9264 |
54
+ | 6.5185 | 7.5 | 6000 | 4.4682 |
55
+ | 4.3057 | 10.0 | 8000 | 4.2043 |
56
+ | 4.3057 | 12.5 | 10000 | 4.0196 |
57
+ | 3.8252 | 15.0 | 12000 | 3.8793 |
58
+ | 3.8252 | 17.5 | 14000 | 3.7737 |
59
+ | 3.5527 | 20.0 | 16000 | 3.6714 |
60
+ | 3.5527 | 22.5 | 18000 | 3.5939 |
61
+ | 3.3505 | 25.0 | 20000 | 3.5267 |
62
+ | 3.3505 | 27.5 | 22000 | 3.4637 |
63
+ | 3.183 | 30.0 | 24000 | 3.4215 |
64
+ | 3.183 | 32.5 | 26000 | 3.3818 |
65
+ | 3.0393 | 35.0 | 28000 | 3.3493 |
66
+ | 3.0393 | 37.5 | 30000 | 3.3345 |
67
+ | 2.9118 | 40.0 | 32000 | 3.3137 |
68
+ | 2.9118 | 42.5 | 34000 | 3.3158 |
69
+ | 2.7946 | 45.0 | 36000 | 3.3074 |
70
+ | 2.7946 | 47.5 | 38000 | 3.3315 |
71
+ | 2.682 | 50.0 | 40000 | 3.3343 |
72
+ | 2.682 | 52.5 | 42000 | 3.3576 |
73
+ | 2.5612 | 55.0 | 44000 | 3.3741 |
74
+ | 2.5612 | 57.5 | 46000 | 3.4210 |
75
+ | 2.4371 | 60.0 | 48000 | 3.4420 |
76
+ | 2.4371 | 62.5 | 50000 | 3.4921 |
77
+ | 2.3257 | 65.0 | 52000 | 3.5113 |
78
+ | 2.3257 | 67.5 | 54000 | 3.5672 |
79
+ | 2.2264 | 70.0 | 56000 | 3.5861 |
80
+ | 2.2264 | 72.5 | 58000 | 3.6404 |
81
+ | 2.1379 | 75.0 | 60000 | 3.6712 |
82
+ | 2.1379 | 77.5 | 62000 | 3.7178 |
83
+ | 2.0592 | 80.0 | 64000 | 3.7306 |
84
+ | 2.0592 | 82.5 | 66000 | 3.7847 |
85
+ | 1.9888 | 85.0 | 68000 | 3.8042 |
86
+ | 1.9888 | 87.5 | 70000 | 3.8581 |
87
+ | 1.9259 | 90.0 | 72000 | 3.8752 |
88
+ | 1.9259 | 92.5 | 74000 | 3.9158 |
89
+ | 1.8696 | 95.0 | 76000 | 3.9281 |
90
+ | 1.8696 | 97.5 | 78000 | 3.9651 |
91
+ | 1.8186 | 100.0 | 80000 | 3.9848 |
92
+ | 1.8186 | 102.5 | 82000 | 4.0198 |
93
+ | 1.7735 | 105.0 | 84000 | 4.0294 |
94
+ | 1.7735 | 107.5 | 86000 | 4.0608 |
95
+ | 1.7319 | 110.0 | 88000 | 4.0724 |
96
+ | 1.7319 | 112.5 | 90000 | 4.0939 |
97
+ | 1.6956 | 115.0 | 92000 | 4.1053 |
98
+ | 1.6956 | 117.5 | 94000 | 4.1268 |
99
+ | 1.6642 | 120.0 | 96000 | 4.1355 |
100
+ | 1.6642 | 122.5 | 98000 | 4.1429 |
101
+ | 1.639 | 125.0 | 100000 | 4.1449 |
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 sha256:63e39625c067459b3f0161ff612c9f6d57678528596cd36c9b6e35804f4d60ad
3
  size 51007160
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a04169962d5652fb4e8716bf7a0495b7bd84c205ff87d870d3b150ad39350a54
3
  size 51007160