wissamantoun
commited on
Commit
•
bf08184
1
Parent(s):
90fa17a
Added model files
Browse files- config.json +28 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- tokenizer_config.json +1 -0
- trainer_state.json +94 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "aubmindlab/araelectra-base-discriminator",
|
3 |
+
"architectures": [
|
4 |
+
"ElectraForQuestionAnswering"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"embedding_size": 768,
|
8 |
+
"generator_hidden_size": 0.33333,
|
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-12,
|
15 |
+
"max_position_embeddings": 512,
|
16 |
+
"model_type": "electra",
|
17 |
+
"num_attention_heads": 12,
|
18 |
+
"num_hidden_layers": 12,
|
19 |
+
"pad_token_id": 0,
|
20 |
+
"position_embedding_type": "absolute",
|
21 |
+
"summary_activation": "gelu",
|
22 |
+
"summary_last_dropout": 0.1,
|
23 |
+
"summary_type": "first",
|
24 |
+
"summary_use_proj": true,
|
25 |
+
"transformers_version": "4.4.0.dev0",
|
26 |
+
"type_vocab_size": 2,
|
27 |
+
"vocab_size": 64000
|
28 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f0d78075c90c4d1ac8daf6f66ca010a94d7b39c8e69cf94133638da7b1365375
|
3 |
+
size 538506935
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"do_lower_case": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "max_len": 512, "do_basic_tokenize": true, "never_split": ["[بريد]", "[مستخدم]", "[رابط]"], "special_tokens_map_file": null, "name_or_path": "aubmindlab/araelectra-base-discriminator"}
|
trainer_state.json
ADDED
@@ -0,0 +1,94 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 3.0,
|
5 |
+
"global_step": 5763,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.26,
|
12 |
+
"learning_rate": 3e-05,
|
13 |
+
"loss": 3.21,
|
14 |
+
"step": 500
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.52,
|
18 |
+
"learning_rate": 2.7912026726057907e-05,
|
19 |
+
"loss": 1.4143,
|
20 |
+
"step": 1000
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.78,
|
24 |
+
"learning_rate": 2.5824053452115813e-05,
|
25 |
+
"loss": 1.2072,
|
26 |
+
"step": 1500
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 1.0,
|
30 |
+
"exact_match": 72.9641693811075,
|
31 |
+
"f1": 84.24962401921071,
|
32 |
+
"step": 1921
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 1.04,
|
36 |
+
"learning_rate": 2.3736080178173723e-05,
|
37 |
+
"loss": 1.1298,
|
38 |
+
"step": 2000
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 1.3,
|
42 |
+
"learning_rate": 2.1648106904231625e-05,
|
43 |
+
"loss": 0.7843,
|
44 |
+
"step": 2500
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 1.56,
|
48 |
+
"learning_rate": 1.956013363028953e-05,
|
49 |
+
"loss": 0.8011,
|
50 |
+
"step": 3000
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 1.82,
|
54 |
+
"learning_rate": 1.7472160356347438e-05,
|
55 |
+
"loss": 0.7699,
|
56 |
+
"step": 3500
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 2.0,
|
60 |
+
"exact_match": 73.0727470141151,
|
61 |
+
"f1": 85.57152971417061,
|
62 |
+
"step": 3842
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 2.08,
|
66 |
+
"learning_rate": 1.5384187082405344e-05,
|
67 |
+
"loss": 0.6582,
|
68 |
+
"step": 4000
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 2.34,
|
72 |
+
"learning_rate": 1.3296213808463252e-05,
|
73 |
+
"loss": 0.4987,
|
74 |
+
"step": 4500
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 2.6,
|
78 |
+
"learning_rate": 1.120824053452116e-05,
|
79 |
+
"loss": 0.4904,
|
80 |
+
"step": 5000
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 2.86,
|
84 |
+
"learning_rate": 9.120267260579064e-06,
|
85 |
+
"loss": 0.4922,
|
86 |
+
"step": 5500
|
87 |
+
}
|
88 |
+
],
|
89 |
+
"max_steps": 7684,
|
90 |
+
"num_train_epochs": 4,
|
91 |
+
"total_flos": 1.429443287350272e+16,
|
92 |
+
"trial_name": null,
|
93 |
+
"trial_params": null
|
94 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cd939f5cdcecf037dbd0697b8ec147570b89f2cada879cee26ec3d4692cbea3e
|
3 |
+
size 2287
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|