Question Answering
Transformers
PyTorch
Safetensors
French
camembert
Inference Endpoints
pierre-catie commited on
Commit
bcd3b26
1 Parent(s): f0f5564

Upload 11 files

Browse files
config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "camembert-base",
3
+ "architectures": [
4
+ "CamembertForQuestionAnswering"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 5,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 6,
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": "camembert",
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": "4.24.0",
25
+ "type_vocab_size": 1,
26
+ "use_cache": true,
27
+ "vocab_size": 32005
28
+ }
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b7787c716d1038a1fb967d1b297c8d1438ce12350aa613bd2259ef27323cc67
3
+ size 880378597
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6204c15c7cef356c5a2b4b4c254c71adf9564022176bf383168968f0b09e8115
3
+ size 440202673
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5576f27bac8ba4b04ab0c91fd47df8e65ae8b4a4174a1c7bbb5b1452bfdf042e
3
+ size 16543
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dcc90c5dbe2e57551d6e2915d3d15597313188c44f130a61cf6880a2932ee296
3
+ size 623
sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:988bc5a00281c6d210a5d34bd143d0363741a432fefe741bf71e61b1869d4314
3
+ size 810912
special_tokens_map.json ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<s>NOTUSED",
4
+ "</s>NOTUSED"
5
+ ],
6
+ "bos_token": "<s>",
7
+ "cls_token": "<s>",
8
+ "eos_token": "</s>",
9
+ "mask_token": {
10
+ "content": "<mask>",
11
+ "lstrip": true,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<pad>",
17
+ "sep_token": "</s>",
18
+ "unk_token": "<unk>"
19
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<s>NOTUSED",
4
+ "</s>NOTUSED"
5
+ ],
6
+ "bos_token": "<s>",
7
+ "cls_token": "<s>",
8
+ "eos_token": "</s>",
9
+ "mask_token": {
10
+ "__type": "AddedToken",
11
+ "content": "<mask>",
12
+ "lstrip": true,
13
+ "normalized": true,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ },
17
+ "model_max_length": 512,
18
+ "name_or_path": "camembert-base",
19
+ "pad_token": "<pad>",
20
+ "sep_token": "</s>",
21
+ "special_tokens_map_file": null,
22
+ "tokenizer_class": "CamembertTokenizer",
23
+ "unk_token": "<unk>"
24
+ }
trainer_state.json ADDED
@@ -0,0 +1,156 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.9486271036315324,
5
+ "global_step": 11000,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.09,
12
+ "learning_rate": 7.374631268436578e-05,
13
+ "loss": 3.876,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.18,
18
+ "learning_rate": 9.696569920844328e-05,
19
+ "loss": 1.5925,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 0.27,
24
+ "learning_rate": 9.2254052016585e-05,
25
+ "loss": 1.2572,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 0.35,
30
+ "learning_rate": 8.754240482472673e-05,
31
+ "loss": 1.1371,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 0.44,
36
+ "learning_rate": 8.283075763286845e-05,
37
+ "loss": 1.0932,
38
+ "step": 2500
39
+ },
40
+ {
41
+ "epoch": 0.53,
42
+ "learning_rate": 7.811911044101018e-05,
43
+ "loss": 1.0323,
44
+ "step": 3000
45
+ },
46
+ {
47
+ "epoch": 0.62,
48
+ "learning_rate": 7.340746324915191e-05,
49
+ "loss": 1.0333,
50
+ "step": 3500
51
+ },
52
+ {
53
+ "epoch": 0.71,
54
+ "learning_rate": 6.869581605729364e-05,
55
+ "loss": 0.9684,
56
+ "step": 4000
57
+ },
58
+ {
59
+ "epoch": 0.8,
60
+ "learning_rate": 6.398416886543535e-05,
61
+ "loss": 0.9606,
62
+ "step": 4500
63
+ },
64
+ {
65
+ "epoch": 0.89,
66
+ "learning_rate": 5.927252167357709e-05,
67
+ "loss": 0.9397,
68
+ "step": 5000
69
+ },
70
+ {
71
+ "epoch": 0.97,
72
+ "learning_rate": 5.4560874481718815e-05,
73
+ "loss": 0.8899,
74
+ "step": 5500
75
+ },
76
+ {
77
+ "epoch": 1.0,
78
+ "eval_loss": 1.0070745944976807,
79
+ "eval_runtime": 18.4896,
80
+ "eval_samples_per_second": 176.37,
81
+ "eval_steps_per_second": 7.355,
82
+ "step": 5645
83
+ },
84
+ {
85
+ "epoch": 1.06,
86
+ "learning_rate": 4.984922728986054e-05,
87
+ "loss": 0.733,
88
+ "step": 6000
89
+ },
90
+ {
91
+ "epoch": 1.15,
92
+ "learning_rate": 4.5137580098002266e-05,
93
+ "loss": 0.6544,
94
+ "step": 6500
95
+ },
96
+ {
97
+ "epoch": 1.24,
98
+ "learning_rate": 4.0425932906143985e-05,
99
+ "loss": 0.6608,
100
+ "step": 7000
101
+ },
102
+ {
103
+ "epoch": 1.33,
104
+ "learning_rate": 3.571428571428572e-05,
105
+ "loss": 0.6493,
106
+ "step": 7500
107
+ },
108
+ {
109
+ "epoch": 1.42,
110
+ "learning_rate": 3.100263852242744e-05,
111
+ "loss": 0.6352,
112
+ "step": 8000
113
+ },
114
+ {
115
+ "epoch": 1.51,
116
+ "learning_rate": 2.629099133056917e-05,
117
+ "loss": 0.6268,
118
+ "step": 8500
119
+ },
120
+ {
121
+ "epoch": 1.59,
122
+ "learning_rate": 2.1579344138710894e-05,
123
+ "loss": 0.6172,
124
+ "step": 9000
125
+ },
126
+ {
127
+ "epoch": 1.68,
128
+ "learning_rate": 1.686769694685262e-05,
129
+ "loss": 0.6159,
130
+ "step": 9500
131
+ },
132
+ {
133
+ "epoch": 1.77,
134
+ "learning_rate": 1.2156049754994346e-05,
135
+ "loss": 0.5908,
136
+ "step": 10000
137
+ },
138
+ {
139
+ "epoch": 1.86,
140
+ "learning_rate": 7.444402563136073e-06,
141
+ "loss": 0.59,
142
+ "step": 10500
143
+ },
144
+ {
145
+ "epoch": 1.95,
146
+ "learning_rate": 2.7327553712777988e-06,
147
+ "loss": 0.582,
148
+ "step": 11000
149
+ }
150
+ ],
151
+ "max_steps": 11290,
152
+ "num_train_epochs": 2,
153
+ "total_flos": 6.897685654641254e+16,
154
+ "trial_name": null,
155
+ "trial_params": null
156
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:580efb47b2e7da692d570accc6059a82e6be119ff2c4da4064ea4a41e3332569
3
+ size 3375