Model save
Browse files- README.md +154 -0
- config.json +27 -0
- emissions.csv +2 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- runs/Mar05_20-49-54_hcdsgpu2/events.out.tfevents.1709671800.hcdsgpu2.322801.0 +3 -0
- special_tokens_map.json +51 -0
- tokenizer.json +0 -0
- tokenizer_config.json +57 -0
- training_args.bin +3 -0
- vocab.json +0 -0
README.md
ADDED
@@ -0,0 +1,154 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- generated_from_trainer
|
4 |
+
model-index:
|
5 |
+
- name: RoBERTa-legal-de-cased_German_legal_SQuAD_100
|
6 |
+
results: []
|
7 |
+
---
|
8 |
+
|
9 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
10 |
+
should probably proofread and complete it, then remove this comment. -->
|
11 |
+
|
12 |
+
# RoBERTa-legal-de-cased_German_legal_SQuAD_100
|
13 |
+
|
14 |
+
This model was trained from scratch on the None dataset.
|
15 |
+
It achieves the following results on the evaluation set:
|
16 |
+
- Loss: 4.2260
|
17 |
+
|
18 |
+
## Model description
|
19 |
+
|
20 |
+
More information needed
|
21 |
+
|
22 |
+
## Intended uses & limitations
|
23 |
+
|
24 |
+
More information needed
|
25 |
+
|
26 |
+
## Training and evaluation data
|
27 |
+
|
28 |
+
More information needed
|
29 |
+
|
30 |
+
## Training procedure
|
31 |
+
|
32 |
+
### Training hyperparameters
|
33 |
+
|
34 |
+
The following hyperparameters were used during training:
|
35 |
+
- learning_rate: 2e-05
|
36 |
+
- train_batch_size: 128
|
37 |
+
- eval_batch_size: 32
|
38 |
+
- seed: 42
|
39 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
40 |
+
- lr_scheduler_type: linear
|
41 |
+
- num_epochs: 100
|
42 |
+
|
43 |
+
### Training results
|
44 |
+
|
45 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
46 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
47 |
+
| No log | 1.0 | 3 | 5.9228 |
|
48 |
+
| No log | 2.0 | 6 | 5.1584 |
|
49 |
+
| No log | 3.0 | 9 | 4.4722 |
|
50 |
+
| No log | 4.0 | 12 | 4.3006 |
|
51 |
+
| No log | 5.0 | 15 | 3.9646 |
|
52 |
+
| No log | 6.0 | 18 | 3.7561 |
|
53 |
+
| No log | 7.0 | 21 | 3.7752 |
|
54 |
+
| No log | 8.0 | 24 | 3.5251 |
|
55 |
+
| No log | 9.0 | 27 | 3.3693 |
|
56 |
+
| No log | 10.0 | 30 | 2.7792 |
|
57 |
+
| No log | 11.0 | 33 | 2.7920 |
|
58 |
+
| No log | 12.0 | 36 | 2.5177 |
|
59 |
+
| No log | 13.0 | 39 | 2.8277 |
|
60 |
+
| No log | 14.0 | 42 | 2.5462 |
|
61 |
+
| No log | 15.0 | 45 | 2.3764 |
|
62 |
+
| No log | 16.0 | 48 | 2.7200 |
|
63 |
+
| No log | 17.0 | 51 | 2.4224 |
|
64 |
+
| No log | 18.0 | 54 | 2.6360 |
|
65 |
+
| No log | 19.0 | 57 | 2.5139 |
|
66 |
+
| No log | 20.0 | 60 | 2.5286 |
|
67 |
+
| No log | 21.0 | 63 | 2.5525 |
|
68 |
+
| No log | 22.0 | 66 | 2.5557 |
|
69 |
+
| No log | 23.0 | 69 | 2.5851 |
|
70 |
+
| No log | 24.0 | 72 | 2.6613 |
|
71 |
+
| No log | 25.0 | 75 | 2.4638 |
|
72 |
+
| No log | 26.0 | 78 | 2.6485 |
|
73 |
+
| No log | 27.0 | 81 | 2.6063 |
|
74 |
+
| No log | 28.0 | 84 | 2.7276 |
|
75 |
+
| No log | 29.0 | 87 | 2.7871 |
|
76 |
+
| No log | 30.0 | 90 | 2.9418 |
|
77 |
+
| No log | 31.0 | 93 | 2.8691 |
|
78 |
+
| No log | 32.0 | 96 | 3.0506 |
|
79 |
+
| No log | 33.0 | 99 | 2.9157 |
|
80 |
+
| No log | 34.0 | 102 | 3.1377 |
|
81 |
+
| No log | 35.0 | 105 | 3.1237 |
|
82 |
+
| No log | 36.0 | 108 | 3.2247 |
|
83 |
+
| No log | 37.0 | 111 | 3.3549 |
|
84 |
+
| No log | 38.0 | 114 | 3.3263 |
|
85 |
+
| No log | 39.0 | 117 | 3.4797 |
|
86 |
+
| No log | 40.0 | 120 | 3.4006 |
|
87 |
+
| No log | 41.0 | 123 | 3.5591 |
|
88 |
+
| No log | 42.0 | 126 | 3.4942 |
|
89 |
+
| No log | 43.0 | 129 | 3.7169 |
|
90 |
+
| No log | 44.0 | 132 | 3.4945 |
|
91 |
+
| No log | 45.0 | 135 | 3.6505 |
|
92 |
+
| No log | 46.0 | 138 | 3.8140 |
|
93 |
+
| No log | 47.0 | 141 | 3.6130 |
|
94 |
+
| No log | 48.0 | 144 | 3.7540 |
|
95 |
+
| No log | 49.0 | 147 | 3.8348 |
|
96 |
+
| No log | 50.0 | 150 | 3.6891 |
|
97 |
+
| No log | 51.0 | 153 | 4.0070 |
|
98 |
+
| No log | 52.0 | 156 | 3.6862 |
|
99 |
+
| No log | 53.0 | 159 | 3.7079 |
|
100 |
+
| No log | 54.0 | 162 | 3.8575 |
|
101 |
+
| No log | 55.0 | 165 | 3.8289 |
|
102 |
+
| No log | 56.0 | 168 | 3.7587 |
|
103 |
+
| No log | 57.0 | 171 | 3.8340 |
|
104 |
+
| No log | 58.0 | 174 | 3.9874 |
|
105 |
+
| No log | 59.0 | 177 | 3.8551 |
|
106 |
+
| No log | 60.0 | 180 | 3.8965 |
|
107 |
+
| No log | 61.0 | 183 | 4.0559 |
|
108 |
+
| No log | 62.0 | 186 | 3.8465 |
|
109 |
+
| No log | 63.0 | 189 | 3.7458 |
|
110 |
+
| No log | 64.0 | 192 | 4.0292 |
|
111 |
+
| No log | 65.0 | 195 | 4.0496 |
|
112 |
+
| No log | 66.0 | 198 | 4.0003 |
|
113 |
+
| No log | 67.0 | 201 | 3.8945 |
|
114 |
+
| No log | 68.0 | 204 | 3.9783 |
|
115 |
+
| No log | 69.0 | 207 | 4.0237 |
|
116 |
+
| No log | 70.0 | 210 | 3.9025 |
|
117 |
+
| No log | 71.0 | 213 | 3.9833 |
|
118 |
+
| No log | 72.0 | 216 | 4.1072 |
|
119 |
+
| No log | 73.0 | 219 | 4.0925 |
|
120 |
+
| No log | 74.0 | 222 | 3.9960 |
|
121 |
+
| No log | 75.0 | 225 | 4.0591 |
|
122 |
+
| No log | 76.0 | 228 | 4.2426 |
|
123 |
+
| No log | 77.0 | 231 | 4.2512 |
|
124 |
+
| No log | 78.0 | 234 | 3.9990 |
|
125 |
+
| No log | 79.0 | 237 | 4.0195 |
|
126 |
+
| No log | 80.0 | 240 | 4.2469 |
|
127 |
+
| No log | 81.0 | 243 | 4.2971 |
|
128 |
+
| No log | 82.0 | 246 | 4.1226 |
|
129 |
+
| No log | 83.0 | 249 | 4.0175 |
|
130 |
+
| No log | 84.0 | 252 | 4.0675 |
|
131 |
+
| No log | 85.0 | 255 | 4.3040 |
|
132 |
+
| No log | 86.0 | 258 | 4.3384 |
|
133 |
+
| No log | 87.0 | 261 | 4.1458 |
|
134 |
+
| No log | 88.0 | 264 | 4.0272 |
|
135 |
+
| No log | 89.0 | 267 | 4.0698 |
|
136 |
+
| No log | 90.0 | 270 | 4.1462 |
|
137 |
+
| No log | 91.0 | 273 | 4.2191 |
|
138 |
+
| No log | 92.0 | 276 | 4.2766 |
|
139 |
+
| No log | 93.0 | 279 | 4.3133 |
|
140 |
+
| No log | 94.0 | 282 | 4.3103 |
|
141 |
+
| No log | 95.0 | 285 | 4.2714 |
|
142 |
+
| No log | 96.0 | 288 | 4.2322 |
|
143 |
+
| No log | 97.0 | 291 | 4.2125 |
|
144 |
+
| No log | 98.0 | 294 | 4.2165 |
|
145 |
+
| No log | 99.0 | 297 | 4.2257 |
|
146 |
+
| No log | 100.0 | 300 | 4.2260 |
|
147 |
+
|
148 |
+
|
149 |
+
### Framework versions
|
150 |
+
|
151 |
+
- Transformers 4.36.2
|
152 |
+
- Pytorch 2.1.2+cu121
|
153 |
+
- Datasets 2.14.7
|
154 |
+
- Tokenizers 0.15.0
|
config.json
ADDED
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "/ltstorage/shares/datasets/glllm/data/from_scratch/RoBERTa/RoBERTa-legal-de-cased",
|
3 |
+
"architectures": [
|
4 |
+
"RobertaForQuestionAnswering"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.1,
|
12 |
+
"hidden_size": 768,
|
13 |
+
"initializer_range": 0.02,
|
14 |
+
"intermediate_size": 3072,
|
15 |
+
"layer_norm_eps": 1e-05,
|
16 |
+
"max_position_embeddings": 514,
|
17 |
+
"model_type": "roberta",
|
18 |
+
"num_attention_heads": 12,
|
19 |
+
"num_hidden_layers": 12,
|
20 |
+
"pad_token_id": 1,
|
21 |
+
"position_embedding_type": "absolute",
|
22 |
+
"torch_dtype": "float32",
|
23 |
+
"transformers_version": "4.36.2",
|
24 |
+
"type_vocab_size": 1,
|
25 |
+
"use_cache": true,
|
26 |
+
"vocab_size": 50265
|
27 |
+
}
|
emissions.csv
ADDED
@@ -0,0 +1,2 @@
|
|
|
|
|
|
|
1 |
+
timestamp,project_name,run_id,duration,emissions,emissions_rate,cpu_power,gpu_power,ram_power,cpu_energy,gpu_energy,ram_energy,energy_consumed,country_name,country_iso_code,region,cloud_provider,cloud_region,os,python_version,codecarbon_version,cpu_count,cpu_model,gpu_count,gpu_model,longitude,latitude,ram_total_size,tracking_mode,on_cloud,pue
|
2 |
+
2024-03-05T20:54:18,codecarbon,9f031422-18ad-4f55-a226-a3b2e250e6f4,257.15593576431274,0.03829073343305628,0.000148900834504362,112.5,978.501,377.88994789123535,0.008035989612340927,0.0731007331849595,0.026932417077603354,0.10806913987490377,Germany,DEU,free and hanseatic city of hamburg,,,Linux-6.5.0-21-generic-x86_64-with-glibc2.35,3.11.4,2.2.3,128,AMD EPYC 7543 32-Core Processor,4,4 x NVIDIA A40,9.9683,53.5649,1007.7065277099609,machine,N,1.0
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:83232fbe37864ab3a0d074c7de5a567ad862349d8a61b23f0a4d432981ecbf2d
|
3 |
+
size 496250232
|
runs/Mar05_20-49-54_hcdsgpu2/events.out.tfevents.1709671800.hcdsgpu2.322801.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2fae0f9fff4c87c86698991b8989bfbd2a01ebbe0b25c3e263c4b842e19f48cd
|
3 |
+
size 31954
|
special_tokens_map.json
ADDED
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": true,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"cls_token": {
|
10 |
+
"content": "<s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": true,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"eos_token": {
|
17 |
+
"content": "</s>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": true,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"mask_token": {
|
24 |
+
"content": "<mask>",
|
25 |
+
"lstrip": true,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
},
|
30 |
+
"pad_token": {
|
31 |
+
"content": "<pad>",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": true,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false
|
36 |
+
},
|
37 |
+
"sep_token": {
|
38 |
+
"content": "</s>",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": true,
|
41 |
+
"rstrip": false,
|
42 |
+
"single_word": false
|
43 |
+
},
|
44 |
+
"unk_token": {
|
45 |
+
"content": "<unk>",
|
46 |
+
"lstrip": false,
|
47 |
+
"normalized": true,
|
48 |
+
"rstrip": false,
|
49 |
+
"single_word": false
|
50 |
+
}
|
51 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"0": {
|
5 |
+
"content": "<s>",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": true,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false,
|
10 |
+
"special": true
|
11 |
+
},
|
12 |
+
"1": {
|
13 |
+
"content": "<pad>",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": true,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false,
|
18 |
+
"special": true
|
19 |
+
},
|
20 |
+
"2": {
|
21 |
+
"content": "</s>",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": true,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false,
|
26 |
+
"special": true
|
27 |
+
},
|
28 |
+
"3": {
|
29 |
+
"content": "<unk>",
|
30 |
+
"lstrip": false,
|
31 |
+
"normalized": true,
|
32 |
+
"rstrip": false,
|
33 |
+
"single_word": false,
|
34 |
+
"special": true
|
35 |
+
},
|
36 |
+
"4": {
|
37 |
+
"content": "<mask>",
|
38 |
+
"lstrip": true,
|
39 |
+
"normalized": false,
|
40 |
+
"rstrip": false,
|
41 |
+
"single_word": false,
|
42 |
+
"special": true
|
43 |
+
}
|
44 |
+
},
|
45 |
+
"bos_token": "<s>",
|
46 |
+
"clean_up_tokenization_spaces": true,
|
47 |
+
"cls_token": "<s>",
|
48 |
+
"eos_token": "</s>",
|
49 |
+
"errors": "replace",
|
50 |
+
"mask_token": "<mask>",
|
51 |
+
"model_max_length": 1000000000000000019884624838656,
|
52 |
+
"pad_token": "<pad>",
|
53 |
+
"sep_token": "</s>",
|
54 |
+
"tokenizer_class": "RobertaTokenizer",
|
55 |
+
"trim_offsets": true,
|
56 |
+
"unk_token": "<unk>"
|
57 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0f2712a58c74b0e809254331d631850c8179fac7f34a8b55e07c85477c752a8c
|
3 |
+
size 4920
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|