Commit
•
0711694
1
Parent(s):
7bff9e8
Training in progress epoch 0
Browse files- .gitattributes +1 -0
- README.md +6 -10
- config.json +20 -24
- sentencepiece.bpe.model +3 -0
- special_tokens_map.json +20 -6
- tf_model.h5 +2 -2
- tokenizer.json +0 -0
- tokenizer_config.json +26 -23
.gitattributes
CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
README.md
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
---
|
2 |
license: mit
|
3 |
-
base_model: badokorach/
|
4 |
tags:
|
5 |
- generated_from_keras_callback
|
6 |
model-index:
|
@@ -13,11 +13,11 @@ probably proofread and complete it, then remove this comment. -->
|
|
13 |
|
14 |
# badokorach/mobilebert-uncased-finetuned-agic-170224
|
15 |
|
16 |
-
This model is a fine-tuned version of [badokorach/
|
17 |
It achieves the following results on the evaluation set:
|
18 |
-
- Train Loss:
|
19 |
- Validation Loss: 0.0
|
20 |
-
- Epoch:
|
21 |
|
22 |
## Model description
|
23 |
|
@@ -36,18 +36,14 @@ More information needed
|
|
36 |
### Training hyperparameters
|
37 |
|
38 |
The following hyperparameters were used during training:
|
39 |
-
- optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': True, 'is_legacy_optimizer': False, 'learning_rate': {'module': None, 'class_name': 'CustomLearningRateScheduler', 'config': {'initial_learning_rate': 3e-05, 'decay_steps': 2736, 'warmup_steps': 304, 'end_learning_rate': 1e-05}, 'registered_name': 'CustomLearningRateScheduler'}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
|
40 |
- training_precision: mixed_float16
|
41 |
|
42 |
### Training results
|
43 |
|
44 |
| Train Loss | Validation Loss | Epoch |
|
45 |
|:----------:|:---------------:|:-----:|
|
46 |
-
|
|
47 |
-
| 0.0737 | 0.0 | 1 |
|
48 |
-
| 0.0272 | 0.0 | 2 |
|
49 |
-
| 0.0135 | 0.0 | 3 |
|
50 |
-
| 0.0080 | 0.0 | 4 |
|
51 |
|
52 |
|
53 |
### Framework versions
|
|
|
1 |
---
|
2 |
license: mit
|
3 |
+
base_model: badokorach/afriqa_afroxlmr_eng_280124
|
4 |
tags:
|
5 |
- generated_from_keras_callback
|
6 |
model-index:
|
|
|
13 |
|
14 |
# badokorach/mobilebert-uncased-finetuned-agic-170224
|
15 |
|
16 |
+
This model is a fine-tuned version of [badokorach/afriqa_afroxlmr_eng_280124](https://huggingface.co/badokorach/afriqa_afroxlmr_eng_280124) on an unknown dataset.
|
17 |
It achieves the following results on the evaluation set:
|
18 |
+
- Train Loss: 1.0244
|
19 |
- Validation Loss: 0.0
|
20 |
+
- Epoch: 0
|
21 |
|
22 |
## Model description
|
23 |
|
|
|
36 |
### Training hyperparameters
|
37 |
|
38 |
The following hyperparameters were used during training:
|
39 |
+
- optimizer: {'inner_optimizer': {'module': 'keras.optimizers', 'class_name': 'Adam', 'config': {'name': 'Adam', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': True, 'is_legacy_optimizer': False, 'learning_rate': {'module': None, 'class_name': 'CustomLearningRateScheduler', 'config': {'initial_learning_rate': 3e-05, 'decay_steps': 2736, 'warmup_steps': 304, 'end_learning_rate': 1e-05}, 'registered_name': 'CustomLearningRateScheduler'}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}, 'registered_name': None}, 'dynamic': True, 'initial_scale': 32768.0, 'dynamic_growth_steps': 2000}
|
40 |
- training_precision: mixed_float16
|
41 |
|
42 |
### Training results
|
43 |
|
44 |
| Train Loss | Validation Loss | Epoch |
|
45 |
|:----------:|:---------------:|:-----:|
|
46 |
+
| 1.0244 | 0.0 | 0 |
|
|
|
|
|
|
|
|
|
47 |
|
48 |
|
49 |
### Framework versions
|
config.json
CHANGED
@@ -1,32 +1,28 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "badokorach/
|
3 |
"architectures": [
|
4 |
-
"
|
5 |
],
|
6 |
"attention_probs_dropout_prob": 0.1,
|
7 |
-
"
|
8 |
"classifier_dropout": null,
|
9 |
-
"
|
10 |
-
"hidden_act": "
|
11 |
-
"hidden_dropout_prob": 0.
|
12 |
-
"hidden_size":
|
13 |
"initializer_range": 0.02,
|
14 |
-
"intermediate_size":
|
15 |
-
"
|
16 |
-
"
|
17 |
-
"
|
18 |
-
"
|
19 |
-
"
|
20 |
-
"
|
21 |
-
"
|
22 |
-
"
|
23 |
-
"
|
24 |
-
"pad_token_id": 0,
|
25 |
"transformers_version": "4.35.2",
|
26 |
-
"
|
27 |
-
"
|
28 |
-
"
|
29 |
-
"use_bottleneck": true,
|
30 |
-
"use_bottleneck_attention": false,
|
31 |
-
"vocab_size": 30522
|
32 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "badokorach/afriqa_afroxlmr_eng_280124",
|
3 |
"architectures": [
|
4 |
+
"XLMRobertaForQuestionAnswering"
|
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": "xlm-roberta",
|
18 |
+
"num_attention_heads": 12,
|
19 |
+
"num_hidden_layers": 12,
|
20 |
+
"output_past": true,
|
21 |
+
"pad_token_id": 1,
|
22 |
+
"position_embedding_type": "absolute",
|
23 |
+
"torch_dtype": "float32",
|
|
|
24 |
"transformers_version": "4.35.2",
|
25 |
+
"type_vocab_size": 1,
|
26 |
+
"use_cache": true,
|
27 |
+
"vocab_size": 250002
|
|
|
|
|
|
|
28 |
}
|
sentencepiece.bpe.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
|
3 |
+
size 5069051
|
special_tokens_map.json
CHANGED
@@ -1,34 +1,48 @@
|
|
1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2 |
"cls_token": {
|
3 |
-
"content": "
|
4 |
"lstrip": false,
|
5 |
"normalized": false,
|
6 |
"rstrip": false,
|
7 |
"single_word": false
|
8 |
},
|
9 |
-
"
|
10 |
-
"content": "
|
11 |
"lstrip": false,
|
12 |
"normalized": false,
|
13 |
"rstrip": false,
|
14 |
"single_word": false
|
15 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
16 |
"pad_token": {
|
17 |
-
"content": "
|
18 |
"lstrip": false,
|
19 |
"normalized": false,
|
20 |
"rstrip": false,
|
21 |
"single_word": false
|
22 |
},
|
23 |
"sep_token": {
|
24 |
-
"content": "
|
25 |
"lstrip": false,
|
26 |
"normalized": false,
|
27 |
"rstrip": false,
|
28 |
"single_word": false
|
29 |
},
|
30 |
"unk_token": {
|
31 |
-
"content": "
|
32 |
"lstrip": false,
|
33 |
"normalized": false,
|
34 |
"rstrip": false,
|
|
|
1 |
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
"cls_token": {
|
10 |
+
"content": "<s>",
|
11 |
"lstrip": false,
|
12 |
"normalized": false,
|
13 |
"rstrip": false,
|
14 |
"single_word": false
|
15 |
},
|
16 |
+
"eos_token": {
|
17 |
+
"content": "</s>",
|
18 |
"lstrip": false,
|
19 |
"normalized": false,
|
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": false,
|
34 |
"rstrip": false,
|
35 |
"single_word": false
|
36 |
},
|
37 |
"sep_token": {
|
38 |
+
"content": "</s>",
|
39 |
"lstrip": false,
|
40 |
"normalized": false,
|
41 |
"rstrip": false,
|
42 |
"single_word": false
|
43 |
},
|
44 |
"unk_token": {
|
45 |
+
"content": "<unk>",
|
46 |
"lstrip": false,
|
47 |
"normalized": false,
|
48 |
"rstrip": false,
|
tf_model.h5
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ba5b8eb12e62ba8528e74449fad33961e8961bc374eaa3d521d0de3af66a8082
|
3 |
+
size 1110105320
|
tokenizer.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
CHANGED
@@ -1,58 +1,61 @@
|
|
1 |
{
|
2 |
"added_tokens_decoder": {
|
3 |
"0": {
|
4 |
-
"content": "
|
5 |
"lstrip": false,
|
6 |
"normalized": false,
|
7 |
"rstrip": false,
|
8 |
"single_word": false,
|
9 |
"special": true
|
10 |
},
|
11 |
-
"
|
12 |
-
"content": "
|
13 |
"lstrip": false,
|
14 |
"normalized": false,
|
15 |
"rstrip": false,
|
16 |
"single_word": false,
|
17 |
"special": true
|
18 |
},
|
19 |
-
"
|
20 |
-
"content": "
|
21 |
"lstrip": false,
|
22 |
"normalized": false,
|
23 |
"rstrip": false,
|
24 |
"single_word": false,
|
25 |
"special": true
|
26 |
},
|
27 |
-
"
|
28 |
-
"content": "
|
29 |
"lstrip": false,
|
30 |
"normalized": false,
|
31 |
"rstrip": false,
|
32 |
"single_word": false,
|
33 |
"special": true
|
34 |
},
|
35 |
-
"
|
36 |
-
"content": "
|
37 |
-
"lstrip":
|
38 |
"normalized": false,
|
39 |
"rstrip": false,
|
40 |
"single_word": false,
|
41 |
"special": true
|
42 |
}
|
43 |
},
|
|
|
44 |
"clean_up_tokenization_spaces": true,
|
45 |
-
"cls_token": "
|
46 |
-
"
|
47 |
-
"
|
48 |
-
"
|
49 |
-
"
|
50 |
-
"
|
51 |
-
"
|
52 |
-
"
|
53 |
-
"
|
54 |
-
"
|
55 |
-
"
|
56 |
-
"tokenizer_class": "
|
57 |
-
"
|
|
|
|
|
58 |
}
|
|
|
1 |
{
|
2 |
"added_tokens_decoder": {
|
3 |
"0": {
|
4 |
+
"content": "<s>",
|
5 |
"lstrip": false,
|
6 |
"normalized": false,
|
7 |
"rstrip": false,
|
8 |
"single_word": false,
|
9 |
"special": true
|
10 |
},
|
11 |
+
"1": {
|
12 |
+
"content": "<pad>",
|
13 |
"lstrip": false,
|
14 |
"normalized": false,
|
15 |
"rstrip": false,
|
16 |
"single_word": false,
|
17 |
"special": true
|
18 |
},
|
19 |
+
"2": {
|
20 |
+
"content": "</s>",
|
21 |
"lstrip": false,
|
22 |
"normalized": false,
|
23 |
"rstrip": false,
|
24 |
"single_word": false,
|
25 |
"special": true
|
26 |
},
|
27 |
+
"3": {
|
28 |
+
"content": "<unk>",
|
29 |
"lstrip": false,
|
30 |
"normalized": false,
|
31 |
"rstrip": false,
|
32 |
"single_word": false,
|
33 |
"special": true
|
34 |
},
|
35 |
+
"250001": {
|
36 |
+
"content": "<mask>",
|
37 |
+
"lstrip": true,
|
38 |
"normalized": false,
|
39 |
"rstrip": false,
|
40 |
"single_word": false,
|
41 |
"special": true
|
42 |
}
|
43 |
},
|
44 |
+
"bos_token": "<s>",
|
45 |
"clean_up_tokenization_spaces": true,
|
46 |
+
"cls_token": "<s>",
|
47 |
+
"eos_token": "</s>",
|
48 |
+
"mask_token": "<mask>",
|
49 |
+
"max_length": 384,
|
50 |
+
"model_max_length": 512,
|
51 |
+
"pad_to_multiple_of": null,
|
52 |
+
"pad_token": "<pad>",
|
53 |
+
"pad_token_type_id": 0,
|
54 |
+
"padding_side": "right",
|
55 |
+
"sep_token": "</s>",
|
56 |
+
"stride": 128,
|
57 |
+
"tokenizer_class": "XLMRobertaTokenizer",
|
58 |
+
"truncation_side": "right",
|
59 |
+
"truncation_strategy": "only_second",
|
60 |
+
"unk_token": "<unk>"
|
61 |
}
|