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_22-51-06_hcdsgpu2/events.out.tfevents.1709679072.hcdsgpu2.425864.0 +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_part_augmented_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_part_augmented_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: 4.2341
|
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 | 4 | 5.7017 |
|
48 |
+
| No log | 2.0 | 8 | 4.8243 |
|
49 |
+
| No log | 3.0 | 12 | 4.2161 |
|
50 |
+
| No log | 4.0 | 16 | 4.1014 |
|
51 |
+
| No log | 5.0 | 20 | 3.9067 |
|
52 |
+
| No log | 6.0 | 24 | 3.5973 |
|
53 |
+
| No log | 7.0 | 28 | 3.4625 |
|
54 |
+
| No log | 8.0 | 32 | 3.2923 |
|
55 |
+
| No log | 9.0 | 36 | 3.0460 |
|
56 |
+
| No log | 10.0 | 40 | 3.0642 |
|
57 |
+
| No log | 11.0 | 44 | 2.9330 |
|
58 |
+
| No log | 12.0 | 48 | 2.7947 |
|
59 |
+
| No log | 13.0 | 52 | 3.0615 |
|
60 |
+
| No log | 14.0 | 56 | 2.9273 |
|
61 |
+
| No log | 15.0 | 60 | 3.0324 |
|
62 |
+
| No log | 16.0 | 64 | 2.6561 |
|
63 |
+
| No log | 17.0 | 68 | 2.7789 |
|
64 |
+
| No log | 18.0 | 72 | 2.5054 |
|
65 |
+
| No log | 19.0 | 76 | 2.8232 |
|
66 |
+
| No log | 20.0 | 80 | 2.4932 |
|
67 |
+
| No log | 21.0 | 84 | 2.5147 |
|
68 |
+
| No log | 22.0 | 88 | 2.8377 |
|
69 |
+
| No log | 23.0 | 92 | 2.5432 |
|
70 |
+
| No log | 24.0 | 96 | 2.5512 |
|
71 |
+
| No log | 25.0 | 100 | 2.9915 |
|
72 |
+
| No log | 26.0 | 104 | 2.6478 |
|
73 |
+
| No log | 27.0 | 108 | 2.8110 |
|
74 |
+
| No log | 28.0 | 112 | 2.6179 |
|
75 |
+
| No log | 29.0 | 116 | 2.8059 |
|
76 |
+
| No log | 30.0 | 120 | 3.2133 |
|
77 |
+
| No log | 31.0 | 124 | 2.7674 |
|
78 |
+
| No log | 32.0 | 128 | 3.1243 |
|
79 |
+
| No log | 33.0 | 132 | 2.8242 |
|
80 |
+
| No log | 34.0 | 136 | 2.7191 |
|
81 |
+
| No log | 35.0 | 140 | 3.2406 |
|
82 |
+
| No log | 36.0 | 144 | 2.8088 |
|
83 |
+
| No log | 37.0 | 148 | 2.9646 |
|
84 |
+
| No log | 38.0 | 152 | 3.1245 |
|
85 |
+
| No log | 39.0 | 156 | 2.8702 |
|
86 |
+
| No log | 40.0 | 160 | 3.2391 |
|
87 |
+
| No log | 41.0 | 164 | 3.0288 |
|
88 |
+
| No log | 42.0 | 168 | 3.1027 |
|
89 |
+
| No log | 43.0 | 172 | 3.2709 |
|
90 |
+
| No log | 44.0 | 176 | 3.2453 |
|
91 |
+
| No log | 45.0 | 180 | 3.2891 |
|
92 |
+
| No log | 46.0 | 184 | 3.3928 |
|
93 |
+
| No log | 47.0 | 188 | 3.4382 |
|
94 |
+
| No log | 48.0 | 192 | 3.3950 |
|
95 |
+
| No log | 49.0 | 196 | 3.4928 |
|
96 |
+
| No log | 50.0 | 200 | 3.4344 |
|
97 |
+
| No log | 51.0 | 204 | 3.5276 |
|
98 |
+
| No log | 52.0 | 208 | 3.6908 |
|
99 |
+
| No log | 53.0 | 212 | 3.5055 |
|
100 |
+
| No log | 54.0 | 216 | 3.7674 |
|
101 |
+
| No log | 55.0 | 220 | 3.6039 |
|
102 |
+
| No log | 56.0 | 224 | 3.5207 |
|
103 |
+
| No log | 57.0 | 228 | 3.7664 |
|
104 |
+
| No log | 58.0 | 232 | 3.6691 |
|
105 |
+
| No log | 59.0 | 236 | 3.8616 |
|
106 |
+
| No log | 60.0 | 240 | 3.8205 |
|
107 |
+
| No log | 61.0 | 244 | 3.7291 |
|
108 |
+
| No log | 62.0 | 248 | 3.8077 |
|
109 |
+
| No log | 63.0 | 252 | 3.8206 |
|
110 |
+
| No log | 64.0 | 256 | 3.8853 |
|
111 |
+
| No log | 65.0 | 260 | 3.8590 |
|
112 |
+
| No log | 66.0 | 264 | 3.9854 |
|
113 |
+
| No log | 67.0 | 268 | 3.9274 |
|
114 |
+
| No log | 68.0 | 272 | 4.0262 |
|
115 |
+
| No log | 69.0 | 276 | 3.8579 |
|
116 |
+
| No log | 70.0 | 280 | 3.9751 |
|
117 |
+
| No log | 71.0 | 284 | 4.2422 |
|
118 |
+
| No log | 72.0 | 288 | 4.1787 |
|
119 |
+
| No log | 73.0 | 292 | 3.9151 |
|
120 |
+
| No log | 74.0 | 296 | 3.9608 |
|
121 |
+
| No log | 75.0 | 300 | 4.1232 |
|
122 |
+
| No log | 76.0 | 304 | 4.0234 |
|
123 |
+
| No log | 77.0 | 308 | 4.0918 |
|
124 |
+
| No log | 78.0 | 312 | 4.0514 |
|
125 |
+
| No log | 79.0 | 316 | 4.0795 |
|
126 |
+
| No log | 80.0 | 320 | 4.1405 |
|
127 |
+
| No log | 81.0 | 324 | 4.1280 |
|
128 |
+
| No log | 82.0 | 328 | 4.1595 |
|
129 |
+
| No log | 83.0 | 332 | 4.1415 |
|
130 |
+
| No log | 84.0 | 336 | 4.1331 |
|
131 |
+
| No log | 85.0 | 340 | 4.1055 |
|
132 |
+
| No log | 86.0 | 344 | 4.1037 |
|
133 |
+
| No log | 87.0 | 348 | 4.1784 |
|
134 |
+
| No log | 88.0 | 352 | 4.3121 |
|
135 |
+
| No log | 89.0 | 356 | 4.3265 |
|
136 |
+
| No log | 90.0 | 360 | 4.2712 |
|
137 |
+
| No log | 91.0 | 364 | 4.3229 |
|
138 |
+
| No log | 92.0 | 368 | 4.4004 |
|
139 |
+
| No log | 93.0 | 372 | 4.3406 |
|
140 |
+
| No log | 94.0 | 376 | 4.2753 |
|
141 |
+
| No log | 95.0 | 380 | 4.2900 |
|
142 |
+
| No log | 96.0 | 384 | 4.3123 |
|
143 |
+
| No log | 97.0 | 388 | 4.3006 |
|
144 |
+
| No log | 98.0 | 392 | 4.2566 |
|
145 |
+
| No log | 99.0 | 396 | 4.2362 |
|
146 |
+
| No log | 100.0 | 400 | 4.2341 |
|
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 |
+
2024-03-05T22:57:17,codecarbon,0970cb88-b341-46d9-91e7-f9d40d417782,365.2323637008667,0.05457311794773957,0.00014942026877014697,112.5,1066.556,377.88994789123535,0.011413341000676154,0.10433310896481712,0.03827697523775573,0.154023425203249,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 sha256:59b7a4bc40763e9b2f7ec1b140ffdc35951a9a8f0601794de1a734b871d7dfce
|
3 |
+
size 496250232
|
runs/Mar05_22-51-06_hcdsgpu2/events.out.tfevents.1709679072.hcdsgpu2.425864.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c6ff7aa71f27a0481a2a233ebef6cf95e226e3b007b8dc5af85a419c2bd9d65b
|
3 |
+
size 32054
|
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 sha256:1417e26706c3fa6e02afe8ad18d8a867798ee9a77935fd1f110b943f91315df9
|
3 |
+
size 4920
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|