Commit
•
4e8f662
1
Parent(s):
a39cd4e
Training in progress epoch 0
Browse files- .DS_Store +3 -0
- .gitattributes +1 -0
- README.md +55 -0
- config.json +97 -0
- merges.txt +0 -0
- special_tokens_map.json +20 -0
- tf_model.h5 +3 -0
- tokenizer_config.json +140 -0
- vocab.json +0 -0
.DS_Store
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:def7c47a48840c606127a323cf9f83177faa75bdffefff48e9fcb5e64dac932b
|
3 |
+
size 6148
|
.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 |
+
.DS_Store filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
base_model: flaubert/flaubert_base_cased
|
4 |
+
tags:
|
5 |
+
- generated_from_keras_callback
|
6 |
+
model-index:
|
7 |
+
- name: christopheparisse/hf_age_80_model
|
8 |
+
results: []
|
9 |
+
---
|
10 |
+
|
11 |
+
<!-- This model card has been generated automatically according to the information Keras had access to. You should
|
12 |
+
probably proofread and complete it, then remove this comment. -->
|
13 |
+
|
14 |
+
# christopheparisse/hf_age_80_model
|
15 |
+
|
16 |
+
This model is a fine-tuned version of [flaubert/flaubert_base_cased](https://huggingface.co/flaubert/flaubert_base_cased) on an unknown dataset.
|
17 |
+
It achieves the following results on the evaluation set:
|
18 |
+
- Train Loss: 1.4268
|
19 |
+
- Validation Loss: 1.3637
|
20 |
+
- Train Accuracy: 0.4140
|
21 |
+
- Epoch: 0
|
22 |
+
|
23 |
+
## Model description
|
24 |
+
|
25 |
+
More information needed
|
26 |
+
|
27 |
+
## Intended uses & limitations
|
28 |
+
|
29 |
+
More information needed
|
30 |
+
|
31 |
+
## Training and evaluation data
|
32 |
+
|
33 |
+
More information needed
|
34 |
+
|
35 |
+
## Training procedure
|
36 |
+
|
37 |
+
### Training hyperparameters
|
38 |
+
|
39 |
+
The following hyperparameters were used during training:
|
40 |
+
- optimizer: {'name': 'Adam', 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 18925, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
|
41 |
+
- training_precision: float32
|
42 |
+
|
43 |
+
### Training results
|
44 |
+
|
45 |
+
| Train Loss | Validation Loss | Train Accuracy | Epoch |
|
46 |
+
|:----------:|:---------------:|:--------------:|:-----:|
|
47 |
+
| 1.4268 | 1.3637 | 0.4140 | 0 |
|
48 |
+
|
49 |
+
|
50 |
+
### Framework versions
|
51 |
+
|
52 |
+
- Transformers 4.36.0
|
53 |
+
- TensorFlow 2.13.1
|
54 |
+
- Datasets 2.15.0
|
55 |
+
- Tokenizers 0.15.0
|
config.json
ADDED
@@ -0,0 +1,97 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "flaubert/flaubert_base_cased",
|
3 |
+
"amp": 1,
|
4 |
+
"architectures": [
|
5 |
+
"FlaubertForSequenceClassification"
|
6 |
+
],
|
7 |
+
"asm": false,
|
8 |
+
"attention_dropout": 0.1,
|
9 |
+
"bos_index": 0,
|
10 |
+
"bos_token_id": 0,
|
11 |
+
"bptt": 512,
|
12 |
+
"causal": false,
|
13 |
+
"clip_grad_norm": 5,
|
14 |
+
"dropout": 0.1,
|
15 |
+
"emb_dim": 768,
|
16 |
+
"embed_init_std": 0.02209708691207961,
|
17 |
+
"encoder_only": true,
|
18 |
+
"end_n_top": 5,
|
19 |
+
"eos_index": 1,
|
20 |
+
"fp16": true,
|
21 |
+
"gelu_activation": true,
|
22 |
+
"group_by_size": true,
|
23 |
+
"id2label": {
|
24 |
+
"0": "LABEL_0",
|
25 |
+
"1": "LABEL_1",
|
26 |
+
"2": "LABEL_2",
|
27 |
+
"3": "LABEL_3",
|
28 |
+
"4": "LABEL_4",
|
29 |
+
"5": "LABEL_5",
|
30 |
+
"6": "LABEL_6"
|
31 |
+
},
|
32 |
+
"id2lang": {
|
33 |
+
"0": "fr"
|
34 |
+
},
|
35 |
+
"init_std": 0.02,
|
36 |
+
"is_encoder": true,
|
37 |
+
"label2id": {
|
38 |
+
"LABEL_0": 0,
|
39 |
+
"LABEL_1": 1,
|
40 |
+
"LABEL_2": 2,
|
41 |
+
"LABEL_3": 3,
|
42 |
+
"LABEL_4": 4,
|
43 |
+
"LABEL_5": 5,
|
44 |
+
"LABEL_6": 6
|
45 |
+
},
|
46 |
+
"lang2id": {
|
47 |
+
"fr": 0
|
48 |
+
},
|
49 |
+
"lang_id": 0,
|
50 |
+
"langs": [
|
51 |
+
"fr"
|
52 |
+
],
|
53 |
+
"layer_norm_eps": 1e-12,
|
54 |
+
"layerdrop": 0.0,
|
55 |
+
"lg_sampling_factor": -1,
|
56 |
+
"lgs": "fr",
|
57 |
+
"mask_index": 5,
|
58 |
+
"mask_token_id": 0,
|
59 |
+
"max_batch_size": 0,
|
60 |
+
"max_position_embeddings": 512,
|
61 |
+
"max_vocab": -1,
|
62 |
+
"mlm_steps": [
|
63 |
+
[
|
64 |
+
"fr",
|
65 |
+
null
|
66 |
+
]
|
67 |
+
],
|
68 |
+
"model_type": "flaubert",
|
69 |
+
"n_heads": 12,
|
70 |
+
"n_langs": 1,
|
71 |
+
"n_layers": 12,
|
72 |
+
"pad_index": 2,
|
73 |
+
"pad_token_id": 2,
|
74 |
+
"pre_norm": false,
|
75 |
+
"sample_alpha": 0,
|
76 |
+
"share_inout_emb": true,
|
77 |
+
"sinusoidal_embeddings": false,
|
78 |
+
"start_n_top": 5,
|
79 |
+
"summary_activation": null,
|
80 |
+
"summary_first_dropout": 0.1,
|
81 |
+
"summary_proj_to_labels": true,
|
82 |
+
"summary_type": "first",
|
83 |
+
"summary_use_proj": true,
|
84 |
+
"tokens_per_batch": -1,
|
85 |
+
"transformers_version": "4.36.0",
|
86 |
+
"unk_index": 3,
|
87 |
+
"use_lang_emb": true,
|
88 |
+
"vocab_size": 68729,
|
89 |
+
"word_blank": 0,
|
90 |
+
"word_dropout": 0,
|
91 |
+
"word_keep": 0.1,
|
92 |
+
"word_mask": 0.8,
|
93 |
+
"word_mask_keep_rand": "0.8,0.1,0.1",
|
94 |
+
"word_pred": 0.15,
|
95 |
+
"word_rand": 0.1,
|
96 |
+
"word_shuffle": 0
|
97 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
special_tokens_map.json
ADDED
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<special0>",
|
4 |
+
"<special1>",
|
5 |
+
"<special2>",
|
6 |
+
"<special3>",
|
7 |
+
"<special4>",
|
8 |
+
"<special5>",
|
9 |
+
"<special6>",
|
10 |
+
"<special7>",
|
11 |
+
"<special8>",
|
12 |
+
"<special9>"
|
13 |
+
],
|
14 |
+
"bos_token": "<s>",
|
15 |
+
"cls_token": "</s>",
|
16 |
+
"mask_token": "<special1>",
|
17 |
+
"pad_token": "<pad>",
|
18 |
+
"sep_token": "</s>",
|
19 |
+
"unk_token": "<unk>"
|
20 |
+
}
|
tf_model.h5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e9f818c0f10c544b3de83a07e98bdb83a179f928ef6a763179286611284a72db
|
3 |
+
size 553176456
|
tokenizer_config.json
ADDED
@@ -0,0 +1,140 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": "</s>",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"2": {
|
20 |
+
"content": "<pad>",
|
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 |
+
"4": {
|
36 |
+
"content": "<special0>",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
},
|
43 |
+
"5": {
|
44 |
+
"content": "<special1>",
|
45 |
+
"lstrip": false,
|
46 |
+
"normalized": false,
|
47 |
+
"rstrip": false,
|
48 |
+
"single_word": false,
|
49 |
+
"special": true
|
50 |
+
},
|
51 |
+
"6": {
|
52 |
+
"content": "<special2>",
|
53 |
+
"lstrip": false,
|
54 |
+
"normalized": false,
|
55 |
+
"rstrip": false,
|
56 |
+
"single_word": false,
|
57 |
+
"special": true
|
58 |
+
},
|
59 |
+
"7": {
|
60 |
+
"content": "<special3>",
|
61 |
+
"lstrip": false,
|
62 |
+
"normalized": false,
|
63 |
+
"rstrip": false,
|
64 |
+
"single_word": false,
|
65 |
+
"special": true
|
66 |
+
},
|
67 |
+
"8": {
|
68 |
+
"content": "<special4>",
|
69 |
+
"lstrip": false,
|
70 |
+
"normalized": false,
|
71 |
+
"rstrip": false,
|
72 |
+
"single_word": false,
|
73 |
+
"special": true
|
74 |
+
},
|
75 |
+
"9": {
|
76 |
+
"content": "<special5>",
|
77 |
+
"lstrip": false,
|
78 |
+
"normalized": false,
|
79 |
+
"rstrip": false,
|
80 |
+
"single_word": false,
|
81 |
+
"special": true
|
82 |
+
},
|
83 |
+
"10": {
|
84 |
+
"content": "<special6>",
|
85 |
+
"lstrip": false,
|
86 |
+
"normalized": false,
|
87 |
+
"rstrip": false,
|
88 |
+
"single_word": false,
|
89 |
+
"special": true
|
90 |
+
},
|
91 |
+
"11": {
|
92 |
+
"content": "<special7>",
|
93 |
+
"lstrip": false,
|
94 |
+
"normalized": false,
|
95 |
+
"rstrip": false,
|
96 |
+
"single_word": false,
|
97 |
+
"special": true
|
98 |
+
},
|
99 |
+
"12": {
|
100 |
+
"content": "<special8>",
|
101 |
+
"lstrip": false,
|
102 |
+
"normalized": false,
|
103 |
+
"rstrip": false,
|
104 |
+
"single_word": false,
|
105 |
+
"special": true
|
106 |
+
},
|
107 |
+
"13": {
|
108 |
+
"content": "<special9>",
|
109 |
+
"lstrip": false,
|
110 |
+
"normalized": false,
|
111 |
+
"rstrip": false,
|
112 |
+
"single_word": false,
|
113 |
+
"special": true
|
114 |
+
}
|
115 |
+
},
|
116 |
+
"additional_special_tokens": [
|
117 |
+
"<special0>",
|
118 |
+
"<special1>",
|
119 |
+
"<special2>",
|
120 |
+
"<special3>",
|
121 |
+
"<special4>",
|
122 |
+
"<special5>",
|
123 |
+
"<special6>",
|
124 |
+
"<special7>",
|
125 |
+
"<special8>",
|
126 |
+
"<special9>"
|
127 |
+
],
|
128 |
+
"bos_token": "<s>",
|
129 |
+
"clean_up_tokenization_spaces": true,
|
130 |
+
"cls_token": "</s>",
|
131 |
+
"do_lower_case": false,
|
132 |
+
"id2lang": null,
|
133 |
+
"lang2id": null,
|
134 |
+
"mask_token": "<special1>",
|
135 |
+
"model_max_length": 512,
|
136 |
+
"pad_token": "<pad>",
|
137 |
+
"sep_token": "</s>",
|
138 |
+
"tokenizer_class": "FlaubertTokenizer",
|
139 |
+
"unk_token": "<unk>"
|
140 |
+
}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|