Initial model upload
Browse files- config.json +27 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +7 -0
- tokenizer_config.json +15 -0
- trainer_state.json +106 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "bert-base-uncased",
|
3 |
+
"architectures": [
|
4 |
+
"BertForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
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 |
+
"position_embedding_type": "absolute",
|
21 |
+
"problem_type": "single_label_classification",
|
22 |
+
"torch_dtype": "float32",
|
23 |
+
"transformers_version": "4.27.1",
|
24 |
+
"type_vocab_size": 2,
|
25 |
+
"use_cache": true,
|
26 |
+
"vocab_size": 30522
|
27 |
+
}
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c1a33c26d7040bf2acc1b529b44ae64c63c22f2fcdad871053abafd4f1018ed0
|
3 |
+
size 875982277
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fd03f5e24d474d459a6d2164ca0536f56cbd1feae13422db3c13c87dbda2a5ca
|
3 |
+
size 438005109
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6005d0b43f6886d0e79ddefeaa5e3a123b6145495050bdab8de20f32abc5c313
|
3 |
+
size 13553
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:774d04b2dcf03201bd2602a1cb915e72a7872edbe0cd966a84361a859043a1a3
|
3 |
+
size 627
|
special_tokens_map.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"mask_token": "[MASK]",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
+
"sep_token": "[SEP]",
|
6 |
+
"unk_token": "[UNK]"
|
7 |
+
}
|
tokenizer_config.json
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"do_basic_tokenize": true,
|
4 |
+
"do_lower_case": true,
|
5 |
+
"mask_token": "[MASK]",
|
6 |
+
"model_max_length": 512,
|
7 |
+
"never_split": null,
|
8 |
+
"pad_token": "[PAD]",
|
9 |
+
"sep_token": "[SEP]",
|
10 |
+
"special_tokens_map_file": null,
|
11 |
+
"strip_accents": null,
|
12 |
+
"tokenize_chinese_chars": true,
|
13 |
+
"tokenizer_class": "BertTokenizer",
|
14 |
+
"unk_token": "[UNK]"
|
15 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,106 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 5.0,
|
5 |
+
"global_step": 60,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 1.0,
|
12 |
+
"learning_rate": 1.6000000000000003e-05,
|
13 |
+
"loss": 0.4916,
|
14 |
+
"step": 12
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 1.0,
|
18 |
+
"eval_accuracy": 0.9361702127659575,
|
19 |
+
"eval_f1": 0.9362281082645824,
|
20 |
+
"eval_loss": 0.2990593910217285,
|
21 |
+
"eval_precision": 0.9371338267036695,
|
22 |
+
"eval_recall": 0.9361702127659575,
|
23 |
+
"eval_runtime": 20.3046,
|
24 |
+
"eval_samples_per_second": 2.315,
|
25 |
+
"eval_steps_per_second": 0.148,
|
26 |
+
"step": 12
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 2.0,
|
30 |
+
"learning_rate": 1.2e-05,
|
31 |
+
"loss": 0.2834,
|
32 |
+
"step": 24
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 2.0,
|
36 |
+
"eval_accuracy": 0.9574468085106383,
|
37 |
+
"eval_f1": 0.957485353068147,
|
38 |
+
"eval_loss": 0.1967730075120926,
|
39 |
+
"eval_precision": 0.9609929078014184,
|
40 |
+
"eval_recall": 0.9574468085106383,
|
41 |
+
"eval_runtime": 21.6345,
|
42 |
+
"eval_samples_per_second": 2.172,
|
43 |
+
"eval_steps_per_second": 0.139,
|
44 |
+
"step": 24
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 3.0,
|
48 |
+
"learning_rate": 8.000000000000001e-06,
|
49 |
+
"loss": 0.185,
|
50 |
+
"step": 36
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 3.0,
|
54 |
+
"eval_accuracy": 0.9574468085106383,
|
55 |
+
"eval_f1": 0.957485353068147,
|
56 |
+
"eval_loss": 0.15521566569805145,
|
57 |
+
"eval_precision": 0.9609929078014184,
|
58 |
+
"eval_recall": 0.9574468085106383,
|
59 |
+
"eval_runtime": 19.4305,
|
60 |
+
"eval_samples_per_second": 2.419,
|
61 |
+
"eval_steps_per_second": 0.154,
|
62 |
+
"step": 36
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 4.0,
|
66 |
+
"learning_rate": 4.000000000000001e-06,
|
67 |
+
"loss": 0.1162,
|
68 |
+
"step": 48
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 4.0,
|
72 |
+
"eval_accuracy": 0.9787234042553191,
|
73 |
+
"eval_f1": 0.9787427027548607,
|
74 |
+
"eval_loss": 0.09382404386997223,
|
75 |
+
"eval_precision": 0.9796484736355227,
|
76 |
+
"eval_recall": 0.9787234042553191,
|
77 |
+
"eval_runtime": 20.1514,
|
78 |
+
"eval_samples_per_second": 2.332,
|
79 |
+
"eval_steps_per_second": 0.149,
|
80 |
+
"step": 48
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 5.0,
|
84 |
+
"learning_rate": 0.0,
|
85 |
+
"loss": 0.0842,
|
86 |
+
"step": 60
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 5.0,
|
90 |
+
"eval_accuracy": 0.9787234042553191,
|
91 |
+
"eval_f1": 0.9787427027548607,
|
92 |
+
"eval_loss": 0.09307459741830826,
|
93 |
+
"eval_precision": 0.9796484736355227,
|
94 |
+
"eval_recall": 0.9787234042553191,
|
95 |
+
"eval_runtime": 22.1003,
|
96 |
+
"eval_samples_per_second": 2.127,
|
97 |
+
"eval_steps_per_second": 0.136,
|
98 |
+
"step": 60
|
99 |
+
}
|
100 |
+
],
|
101 |
+
"max_steps": 60,
|
102 |
+
"num_train_epochs": 5,
|
103 |
+
"total_flos": 60515542732800.0,
|
104 |
+
"trial_name": null,
|
105 |
+
"trial_params": null
|
106 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:545641e34bac4bf92d5455de55c9c35c3eba533194ef158ed108a3427c6305ab
|
3 |
+
size 3515
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|