SauravMaheshkar
commited on
Commit
•
2e1178c
1
Parent(s):
20a202c
Initial Commit
Browse files- .gitignore +2 -0
- config.json +30 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- trainer_state.json +41 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
.gitignore
ADDED
@@ -0,0 +1,2 @@
|
|
|
|
|
1 |
+
# MacOS Stuff
|
2 |
+
**/.DS_Store
|
config.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "../input/huggingface-question-answering-models/multilingual/bert-base-multilingual-cased-finetuned-squad",
|
3 |
+
"architectures": [
|
4 |
+
"BertForQuestionAnswering"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"directionality": "bidi",
|
8 |
+
"gradient_checkpointing": false,
|
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": "bert",
|
17 |
+
"num_attention_heads": 12,
|
18 |
+
"num_hidden_layers": 12,
|
19 |
+
"pad_token_id": 0,
|
20 |
+
"pooler_fc_size": 768,
|
21 |
+
"pooler_num_attention_heads": 12,
|
22 |
+
"pooler_num_fc_layers": 3,
|
23 |
+
"pooler_size_per_head": 128,
|
24 |
+
"pooler_type": "first_token_transform",
|
25 |
+
"position_embedding_type": "absolute",
|
26 |
+
"transformers_version": "4.6.1",
|
27 |
+
"type_vocab_size": 2,
|
28 |
+
"use_cache": true,
|
29 |
+
"vocab_size": 119547
|
30 |
+
}
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ab8d115649221f97a96bca4e8891f5b7a05dc02972f8808755c409f0fc849b8e
|
3 |
+
size 1418239981
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:54e162dc783159f04d85f52d323ddc28396bc373c4404bfa1b47bb7ab4eb16e9
|
3 |
+
size 709146103
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fa6394e83cd1f2beb3e9f92eb56dcc54bb008974590467c835cba7505717a96e
|
3 |
+
size 14657
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:94f1afe4a33f68808776494f2d52851453a5102d021cfde6cbc15324a5d070db
|
3 |
+
size 623
|
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.json
ADDED
The diff for this file is too large to render.
See raw diff
|
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, "model_max_length": 512, "name_or_path": "../input/huggingface-question-answering-models/multilingual/bert-base-multilingual-cased-finetuned-squad", "special_tokens_map_file": "../input/huggingface-question-answering-models/multilingual/bert-base-multilingual-cased-finetuned-squad/special_tokens_map.json", "do_basic_tokenize": true, "never_split": null}
|
trainer_state.json
ADDED
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.9997158283603297,
|
5 |
+
"global_step": 1759,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.28,
|
12 |
+
"learning_rate": 1.5906506632975366e-05,
|
13 |
+
"loss": 0.8044,
|
14 |
+
"step": 500
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.57,
|
18 |
+
"learning_rate": 9.589387239418826e-06,
|
19 |
+
"loss": 0.6525,
|
20 |
+
"step": 1000
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.85,
|
24 |
+
"learning_rate": 3.272267845862287e-06,
|
25 |
+
"loss": 0.6257,
|
26 |
+
"step": 1500
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 1.0,
|
30 |
+
"eval_loss": 0.7384809851646423,
|
31 |
+
"eval_runtime": 3.1281,
|
32 |
+
"eval_samples_per_second": 71.608,
|
33 |
+
"step": 1759
|
34 |
+
}
|
35 |
+
],
|
36 |
+
"max_steps": 1759,
|
37 |
+
"num_train_epochs": 1,
|
38 |
+
"total_flos": 1.1494492138561536e+16,
|
39 |
+
"trial_name": null,
|
40 |
+
"trial_params": null
|
41 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:442b11e37f6fa3642e69dc42b40117a93b33d91a5c47a0605fd8970465de38f5
|
3 |
+
size 2415
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|