End of training
Browse files- README.md +145 -0
- config.json +27 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- special_tokens_map.json +15 -0
- tokenizer.json +0 -0
- tokenizer_config.json +58 -0
- training_args.bin +3 -0
- vocab.json +0 -0
README.md
ADDED
@@ -0,0 +1,145 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: transformers
|
3 |
+
license: mit
|
4 |
+
base_model: roberta-base
|
5 |
+
tags:
|
6 |
+
- generated_from_trainer
|
7 |
+
metrics:
|
8 |
+
- accuracy
|
9 |
+
model-index:
|
10 |
+
- name: roberta-sst2-fine-tuning-shuttleworth-t2
|
11 |
+
results: []
|
12 |
+
---
|
13 |
+
|
14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
15 |
+
should probably proofread and complete it, then remove this comment. -->
|
16 |
+
|
17 |
+
# roberta-sst2-fine-tuning-shuttleworth-t2
|
18 |
+
|
19 |
+
This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on an unknown dataset.
|
20 |
+
It achieves the following results on the evaluation set:
|
21 |
+
- Loss: 0.3491
|
22 |
+
- Accuracy: 0.9335
|
23 |
+
|
24 |
+
## Model description
|
25 |
+
|
26 |
+
More information needed
|
27 |
+
|
28 |
+
## Intended uses & limitations
|
29 |
+
|
30 |
+
More information needed
|
31 |
+
|
32 |
+
## Training and evaluation data
|
33 |
+
|
34 |
+
More information needed
|
35 |
+
|
36 |
+
## Training procedure
|
37 |
+
|
38 |
+
### Training hyperparameters
|
39 |
+
|
40 |
+
The following hyperparameters were used during training:
|
41 |
+
- learning_rate: 1e-05
|
42 |
+
- train_batch_size: 16
|
43 |
+
- eval_batch_size: 16
|
44 |
+
- seed: 42
|
45 |
+
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
46 |
+
- lr_scheduler_type: linear
|
47 |
+
- lr_scheduler_warmup_ratio: 0.06
|
48 |
+
- num_epochs: 5
|
49 |
+
|
50 |
+
### Training results
|
51 |
+
|
52 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
53 |
+
|:-------------:|:------:|:-----:|:---------------:|:--------:|
|
54 |
+
| 0.6887 | 0.0594 | 250 | 0.6925 | 0.5092 |
|
55 |
+
| 0.3907 | 0.1188 | 500 | 0.2747 | 0.9048 |
|
56 |
+
| 0.2923 | 0.1781 | 750 | 0.2581 | 0.8968 |
|
57 |
+
| 0.29 | 0.2375 | 1000 | 0.2650 | 0.9140 |
|
58 |
+
| 0.2636 | 0.2969 | 1250 | 0.2180 | 0.9255 |
|
59 |
+
| 0.2501 | 0.3563 | 1500 | 0.2401 | 0.9278 |
|
60 |
+
| 0.2485 | 0.4157 | 1750 | 0.2941 | 0.9060 |
|
61 |
+
| 0.2465 | 0.4751 | 2000 | 0.2908 | 0.9117 |
|
62 |
+
| 0.2255 | 0.5344 | 2250 | 0.3400 | 0.9094 |
|
63 |
+
| 0.2563 | 0.5938 | 2500 | 0.2383 | 0.9255 |
|
64 |
+
| 0.239 | 0.6532 | 2750 | 0.2242 | 0.9300 |
|
65 |
+
| 0.2412 | 0.7126 | 3000 | 0.2647 | 0.9243 |
|
66 |
+
| 0.2303 | 0.7720 | 3250 | 0.2391 | 0.9323 |
|
67 |
+
| 0.2479 | 0.8314 | 3500 | 0.2478 | 0.9312 |
|
68 |
+
| 0.2365 | 0.8907 | 3750 | 0.2826 | 0.9278 |
|
69 |
+
| 0.2034 | 0.9501 | 4000 | 0.2374 | 0.9346 |
|
70 |
+
| 0.1981 | 1.0095 | 4250 | 0.2414 | 0.9289 |
|
71 |
+
| 0.2038 | 1.0689 | 4500 | 0.2832 | 0.9358 |
|
72 |
+
| 0.1478 | 1.1283 | 4750 | 0.2674 | 0.9335 |
|
73 |
+
| 0.2093 | 1.1876 | 5000 | 0.2612 | 0.9392 |
|
74 |
+
| 0.1984 | 1.2470 | 5250 | 0.2418 | 0.9427 |
|
75 |
+
| 0.1836 | 1.3064 | 5500 | 0.2635 | 0.9381 |
|
76 |
+
| 0.1827 | 1.3658 | 5750 | 0.2924 | 0.9243 |
|
77 |
+
| 0.1835 | 1.4252 | 6000 | 0.2754 | 0.9289 |
|
78 |
+
| 0.1911 | 1.4846 | 6250 | 0.2762 | 0.9346 |
|
79 |
+
| 0.1874 | 1.5439 | 6500 | 0.2190 | 0.9381 |
|
80 |
+
| 0.1918 | 1.6033 | 6750 | 0.2548 | 0.9415 |
|
81 |
+
| 0.1805 | 1.6627 | 7000 | 0.2336 | 0.9358 |
|
82 |
+
| 0.1798 | 1.7221 | 7250 | 0.2671 | 0.9415 |
|
83 |
+
| 0.1875 | 1.7815 | 7500 | 0.2633 | 0.9312 |
|
84 |
+
| 0.1957 | 1.8409 | 7750 | 0.2512 | 0.9404 |
|
85 |
+
| 0.1629 | 1.9002 | 8000 | 0.2643 | 0.9415 |
|
86 |
+
| 0.1618 | 1.9596 | 8250 | 0.2867 | 0.9312 |
|
87 |
+
| 0.1463 | 2.0190 | 8500 | 0.3041 | 0.9369 |
|
88 |
+
| 0.1295 | 2.0784 | 8750 | 0.3021 | 0.9381 |
|
89 |
+
| 0.1544 | 2.1378 | 9000 | 0.3249 | 0.9335 |
|
90 |
+
| 0.1704 | 2.1971 | 9250 | 0.3550 | 0.9346 |
|
91 |
+
| 0.1277 | 2.2565 | 9500 | 0.3159 | 0.9404 |
|
92 |
+
| 0.157 | 2.3159 | 9750 | 0.3019 | 0.9381 |
|
93 |
+
| 0.1675 | 2.3753 | 10000 | 0.2930 | 0.9392 |
|
94 |
+
| 0.1447 | 2.4347 | 10250 | 0.2990 | 0.9346 |
|
95 |
+
| 0.1658 | 2.4941 | 10500 | 0.2928 | 0.9346 |
|
96 |
+
| 0.1676 | 2.5534 | 10750 | 0.3317 | 0.9369 |
|
97 |
+
| 0.1439 | 2.6128 | 11000 | 0.2950 | 0.9358 |
|
98 |
+
| 0.1827 | 2.6722 | 11250 | 0.2892 | 0.9369 |
|
99 |
+
| 0.1333 | 2.7316 | 11500 | 0.3014 | 0.9300 |
|
100 |
+
| 0.1283 | 2.7910 | 11750 | 0.3216 | 0.9404 |
|
101 |
+
| 0.1349 | 2.8504 | 12000 | 0.3030 | 0.9369 |
|
102 |
+
| 0.1548 | 2.9097 | 12250 | 0.3232 | 0.9358 |
|
103 |
+
| 0.1566 | 2.9691 | 12500 | 0.2929 | 0.9381 |
|
104 |
+
| 0.115 | 3.0285 | 12750 | 0.3122 | 0.9392 |
|
105 |
+
| 0.1137 | 3.0879 | 13000 | 0.3419 | 0.9369 |
|
106 |
+
| 0.1471 | 3.1473 | 13250 | 0.3507 | 0.9392 |
|
107 |
+
| 0.1325 | 3.2067 | 13500 | 0.3332 | 0.9369 |
|
108 |
+
| 0.1313 | 3.2660 | 13750 | 0.3053 | 0.9415 |
|
109 |
+
| 0.1471 | 3.3254 | 14000 | 0.2984 | 0.9346 |
|
110 |
+
| 0.1071 | 3.3848 | 14250 | 0.3294 | 0.9335 |
|
111 |
+
| 0.1273 | 3.4442 | 14500 | 0.2874 | 0.9392 |
|
112 |
+
| 0.1203 | 3.5036 | 14750 | 0.3479 | 0.9392 |
|
113 |
+
| 0.1233 | 3.5629 | 15000 | 0.3529 | 0.9300 |
|
114 |
+
| 0.0993 | 3.6223 | 15250 | 0.3450 | 0.9346 |
|
115 |
+
| 0.1525 | 3.6817 | 15500 | 0.3439 | 0.9335 |
|
116 |
+
| 0.119 | 3.7411 | 15750 | 0.3740 | 0.9289 |
|
117 |
+
| 0.1081 | 3.8005 | 16000 | 0.3389 | 0.9381 |
|
118 |
+
| 0.1138 | 3.8599 | 16250 | 0.3383 | 0.9358 |
|
119 |
+
| 0.123 | 3.9192 | 16500 | 0.3234 | 0.9369 |
|
120 |
+
| 0.1197 | 3.9786 | 16750 | 0.3422 | 0.9346 |
|
121 |
+
| 0.1351 | 4.0380 | 17000 | 0.3424 | 0.9312 |
|
122 |
+
| 0.1006 | 4.0974 | 17250 | 0.3290 | 0.9392 |
|
123 |
+
| 0.0989 | 4.1568 | 17500 | 0.3456 | 0.9346 |
|
124 |
+
| 0.1003 | 4.2162 | 17750 | 0.3636 | 0.9346 |
|
125 |
+
| 0.0911 | 4.2755 | 18000 | 0.3685 | 0.9346 |
|
126 |
+
| 0.0959 | 4.3349 | 18250 | 0.3547 | 0.9358 |
|
127 |
+
| 0.1057 | 4.3943 | 18500 | 0.3543 | 0.9323 |
|
128 |
+
| 0.1135 | 4.4537 | 18750 | 0.3506 | 0.9346 |
|
129 |
+
| 0.1083 | 4.5131 | 19000 | 0.3361 | 0.9369 |
|
130 |
+
| 0.0909 | 4.5724 | 19250 | 0.3597 | 0.9369 |
|
131 |
+
| 0.0966 | 4.6318 | 19500 | 0.3673 | 0.9369 |
|
132 |
+
| 0.0749 | 4.6912 | 19750 | 0.3665 | 0.9346 |
|
133 |
+
| 0.0987 | 4.7506 | 20000 | 0.3592 | 0.9335 |
|
134 |
+
| 0.111 | 4.8100 | 20250 | 0.3531 | 0.9335 |
|
135 |
+
| 0.0946 | 4.8694 | 20500 | 0.3502 | 0.9346 |
|
136 |
+
| 0.1023 | 4.9287 | 20750 | 0.3486 | 0.9346 |
|
137 |
+
| 0.0889 | 4.9881 | 21000 | 0.3491 | 0.9335 |
|
138 |
+
|
139 |
+
|
140 |
+
### Framework versions
|
141 |
+
|
142 |
+
- Transformers 4.52.4
|
143 |
+
- Pytorch 2.7.0+cu128
|
144 |
+
- Datasets 3.6.0
|
145 |
+
- Tokenizers 0.21.1
|
config.json
ADDED
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"RobertaForSequenceClassification"
|
4 |
+
],
|
5 |
+
"attention_probs_dropout_prob": 0.1,
|
6 |
+
"bos_token_id": 0,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"eos_token_id": 2,
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 768,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 3072,
|
14 |
+
"layer_norm_eps": 1e-05,
|
15 |
+
"max_position_embeddings": 514,
|
16 |
+
"model_type": "roberta",
|
17 |
+
"num_attention_heads": 12,
|
18 |
+
"num_hidden_layers": 12,
|
19 |
+
"pad_token_id": 1,
|
20 |
+
"position_embedding_type": "absolute",
|
21 |
+
"problem_type": "single_label_classification",
|
22 |
+
"torch_dtype": "float32",
|
23 |
+
"transformers_version": "4.52.4",
|
24 |
+
"type_vocab_size": 1,
|
25 |
+
"use_cache": true,
|
26 |
+
"vocab_size": 50265
|
27 |
+
}
|
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 sha256:4d0f91e2c5c7b15b66883692ccd8cf7bb7c2e81214e8c2041216d6f5f03e5141
|
3 |
+
size 498612824
|
special_tokens_map.json
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"cls_token": "<s>",
|
4 |
+
"eos_token": "</s>",
|
5 |
+
"mask_token": {
|
6 |
+
"content": "<mask>",
|
7 |
+
"lstrip": true,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false
|
11 |
+
},
|
12 |
+
"pad_token": "<pad>",
|
13 |
+
"sep_token": "</s>",
|
14 |
+
"unk_token": "<unk>"
|
15 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"50264": {
|
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": false,
|
47 |
+
"cls_token": "<s>",
|
48 |
+
"eos_token": "</s>",
|
49 |
+
"errors": "replace",
|
50 |
+
"extra_special_tokens": {},
|
51 |
+
"mask_token": "<mask>",
|
52 |
+
"model_max_length": 512,
|
53 |
+
"pad_token": "<pad>",
|
54 |
+
"sep_token": "</s>",
|
55 |
+
"tokenizer_class": "RobertaTokenizer",
|
56 |
+
"trim_offsets": true,
|
57 |
+
"unk_token": "<unk>"
|
58 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b2dc71bc4ea80da480951c4e6076b1374800e00d0a2fb7585bd752e8a65f0de1
|
3 |
+
size 5777
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|