initial model commit
Browse files- config.json +41 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- scheduler.pt +3 -0
- test_results.p +0 -0
- tokenizer_config.json +1 -0
- trainer_state.json +40 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "bert-base-uncased",
|
3 |
+
"architectures": [
|
4 |
+
"BertForTokenClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"gradient_checkpointing": false,
|
8 |
+
"hidden_act": "gelu",
|
9 |
+
"hidden_dropout_prob": 0.1,
|
10 |
+
"hidden_size": 768,
|
11 |
+
"id2label": {
|
12 |
+
"0": "B-problem",
|
13 |
+
"1": "B-treatment",
|
14 |
+
"2": "I-test",
|
15 |
+
"3": "I-treatment",
|
16 |
+
"4": "B-test",
|
17 |
+
"5": "O",
|
18 |
+
"6": "I-problem"
|
19 |
+
},
|
20 |
+
"initializer_range": 0.02,
|
21 |
+
"intermediate_size": 3072,
|
22 |
+
"label2id": {
|
23 |
+
"B-problem": 0,
|
24 |
+
"B-test": 4,
|
25 |
+
"B-treatment": 1,
|
26 |
+
"I-problem": 6,
|
27 |
+
"I-test": 2,
|
28 |
+
"I-treatment": 3,
|
29 |
+
"O": 5
|
30 |
+
},
|
31 |
+
"layer_norm_eps": 1e-12,
|
32 |
+
"max_position_embeddings": 512,
|
33 |
+
"model_type": "bert",
|
34 |
+
"num_attention_heads": 12,
|
35 |
+
"num_hidden_layers": 12,
|
36 |
+
"pad_token_id": 0,
|
37 |
+
"position_embedding_type": "absolute",
|
38 |
+
"type_vocab_size": 2,
|
39 |
+
"use_cache": true,
|
40 |
+
"vocab_size": 30522
|
41 |
+
}
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2a0d5fd22aefaa226895d974f21332c65b50c447cd75e3bb6a51ad72f6c6e32d
|
3 |
+
size 871301101
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:90bad4af900151870a8de3e791ab1bd511b9638b3e0fa5110294f4eb626db49a
|
3 |
+
size 435676663
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e1894384c96e65ff4c71168eb3cea96ec4e99cf8d0eb01111f6ffe6bbc26ccaa
|
3 |
+
size 623
|
test_results.p
ADDED
Binary file (555 Bytes). View file
|
|
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, "model_max_length": 512, "name_or_path": "bert-base-uncased"}
|
trainer_state.json
ADDED
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 2.9761904761904763,
|
5 |
+
"global_step": 2125,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.7002801120448179,
|
12 |
+
"learning_rate": 3.832866479925304e-05,
|
13 |
+
"loss": 0.2923659973144531,
|
14 |
+
"step": 500
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 1.4005602240896358,
|
18 |
+
"learning_rate": 2.665732959850607e-05,
|
19 |
+
"loss": 0.12518920135498046,
|
20 |
+
"step": 1000
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 2.100840336134454,
|
24 |
+
"learning_rate": 1.4985994397759103e-05,
|
25 |
+
"loss": 0.08236197662353516,
|
26 |
+
"step": 1500
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 2.8011204481792715,
|
30 |
+
"learning_rate": 3.3146591970121383e-06,
|
31 |
+
"loss": 0.03941415023803711,
|
32 |
+
"step": 2000
|
33 |
+
}
|
34 |
+
],
|
35 |
+
"max_steps": 2142,
|
36 |
+
"num_train_epochs": 3,
|
37 |
+
"total_flos": 2843017475953152,
|
38 |
+
"trial_name": null,
|
39 |
+
"trial_params": null
|
40 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4e3f0d4c42ed125cb0e18463a06d056eef55c65dc3f317af6f1db3f4ad32d292
|
3 |
+
size 2095
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|