1epoch trained on PAWS
Browse files- .gitignore +1 -0
- all_results.json +8 -0
- config.json +29 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- tokenizer_config.json +1 -0
- train_results.json +8 -0
- trainer_state.json +37 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*
|
all_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 1.0,
|
3 |
+
"train_loss": 5.64251610059892,
|
4 |
+
"train_runtime": 333.7038,
|
5 |
+
"train_samples": 7931,
|
6 |
+
"train_samples_per_second": 23.767,
|
7 |
+
"train_steps_per_second": 2.973
|
8 |
+
}
|
config.json
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"exBertForMaskedLM"
|
4 |
+
],
|
5 |
+
"attention_probs_dropout_prob": 0.1,
|
6 |
+
"base_model": "beomi/kcbert-base",
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"eos_token_id": 2,
|
9 |
+
"ex_hidden_size": 252,
|
10 |
+
"ex_intermediate_size": 1024,
|
11 |
+
"ex_num_attention_heads": 12,
|
12 |
+
"ex_num_hidden_layers": 12,
|
13 |
+
"ex_vocab_size": 20135,
|
14 |
+
"hidden_act": "gelu",
|
15 |
+
"hidden_dropout_prob": 0.1,
|
16 |
+
"hidden_size": 768,
|
17 |
+
"initializer_range": 0.02,
|
18 |
+
"intermediate_size": 3072,
|
19 |
+
"layer_norm_eps": 1e-12,
|
20 |
+
"max_position_embeddings": 300,
|
21 |
+
"model_type": "exbert",
|
22 |
+
"num_attention_heads": 12,
|
23 |
+
"num_hidden_layers": 12,
|
24 |
+
"pad_token_id": 1,
|
25 |
+
"transformers_version": "4.7.0.dev0",
|
26 |
+
"type_vocab_size": 2,
|
27 |
+
"use_cache": true,
|
28 |
+
"vocab_size": 50135
|
29 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:22b79319a7b3d601effaa9452c0128d7e3ba5c7395cc26f885bd79257f03aa7d
|
3 |
+
size 672770099
|
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": true, "do_basic_tokenize": true, "never_split": null, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "use_fast": true, "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "exbert"}
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 1.0,
|
3 |
+
"train_loss": 5.64251610059892,
|
4 |
+
"train_runtime": 333.7038,
|
5 |
+
"train_samples": 7931,
|
6 |
+
"train_samples_per_second": 23.767,
|
7 |
+
"train_steps_per_second": 2.973
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.0,
|
5 |
+
"global_step": 992,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.0,
|
12 |
+
"learning_rate": 4.994959677419355e-05,
|
13 |
+
"loss": 10.8889,
|
14 |
+
"step": 1
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.5,
|
18 |
+
"learning_rate": 2.4798387096774196e-05,
|
19 |
+
"loss": 5.9914,
|
20 |
+
"step": 500
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 1.0,
|
24 |
+
"step": 992,
|
25 |
+
"total_flos": 2400440637256200.0,
|
26 |
+
"train_loss": 5.64251610059892,
|
27 |
+
"train_runtime": 333.7038,
|
28 |
+
"train_samples_per_second": 23.767,
|
29 |
+
"train_steps_per_second": 2.973
|
30 |
+
}
|
31 |
+
],
|
32 |
+
"max_steps": 992,
|
33 |
+
"num_train_epochs": 1,
|
34 |
+
"total_flos": 2400440637256200.0,
|
35 |
+
"trial_name": null,
|
36 |
+
"trial_params": null
|
37 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c726d8f9c0eb16add1fb83e2d0607a69ad2a6405e5ee5d0744223baa48c49873
|
3 |
+
size 2479
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|