Upload 11 files
Browse files- config.json +33 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +13 -0
- trainer_state.json +130 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"id2label": {
|
13 |
+
"0": "LABEL_0"
|
14 |
+
},
|
15 |
+
"initializer_range": 0.02,
|
16 |
+
"intermediate_size": 3072,
|
17 |
+
"label2id": {
|
18 |
+
"LABEL_0": 0
|
19 |
+
},
|
20 |
+
"layer_norm_eps": 1e-12,
|
21 |
+
"max_position_embeddings": 512,
|
22 |
+
"model_type": "bert",
|
23 |
+
"num_attention_heads": 12,
|
24 |
+
"num_hidden_layers": 12,
|
25 |
+
"pad_token_id": 0,
|
26 |
+
"position_embedding_type": "absolute",
|
27 |
+
"problem_type": "regression",
|
28 |
+
"torch_dtype": "float32",
|
29 |
+
"transformers_version": "4.30.2",
|
30 |
+
"type_vocab_size": 2,
|
31 |
+
"use_cache": true,
|
32 |
+
"vocab_size": 30522
|
33 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:92a9290d75d56a55d09db55ea9b08fdb9e65e95752660c11260bf640a7e13dc9
|
3 |
+
size 437959756
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d71d5417da955faa1a745e2eaa3edfeed4d3304cf665d2a65e7970b03797a5d9
|
3 |
+
size 876037381
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:022fd76978723e84b8149bf600baede404ef35969f64caa455287ea140e574ef
|
3 |
+
size 14575
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:31558495b40f2ee0d94426e672d16587cc8116f4afc4aa78b49a4d4ee2d466f4
|
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.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"clean_up_tokenization_spaces": true,
|
3 |
+
"cls_token": "[CLS]",
|
4 |
+
"do_lower_case": true,
|
5 |
+
"mask_token": "[MASK]",
|
6 |
+
"model_max_length": 512,
|
7 |
+
"pad_token": "[PAD]",
|
8 |
+
"sep_token": "[SEP]",
|
9 |
+
"strip_accents": null,
|
10 |
+
"tokenize_chinese_chars": true,
|
11 |
+
"tokenizer_class": "BertTokenizer",
|
12 |
+
"unk_token": "[UNK]"
|
13 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,130 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 2.0,
|
5 |
+
"global_step": 5972,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.17,
|
12 |
+
"learning_rate": 2.7488278633623578e-05,
|
13 |
+
"loss": 0.0111,
|
14 |
+
"step": 500
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.33,
|
18 |
+
"eval_loss": 0.011657167226076126,
|
19 |
+
"eval_runtime": 165.5471,
|
20 |
+
"eval_samples_per_second": 309.211,
|
21 |
+
"eval_steps_per_second": 4.832,
|
22 |
+
"step": 995
|
23 |
+
},
|
24 |
+
{
|
25 |
+
"epoch": 0.33,
|
26 |
+
"learning_rate": 2.4976557267247155e-05,
|
27 |
+
"loss": 0.0095,
|
28 |
+
"step": 1000
|
29 |
+
},
|
30 |
+
{
|
31 |
+
"epoch": 0.5,
|
32 |
+
"learning_rate": 2.246483590087073e-05,
|
33 |
+
"loss": 0.0092,
|
34 |
+
"step": 1500
|
35 |
+
},
|
36 |
+
{
|
37 |
+
"epoch": 0.67,
|
38 |
+
"eval_loss": 0.011485742405056953,
|
39 |
+
"eval_runtime": 165.5589,
|
40 |
+
"eval_samples_per_second": 309.189,
|
41 |
+
"eval_steps_per_second": 4.832,
|
42 |
+
"step": 1990
|
43 |
+
},
|
44 |
+
{
|
45 |
+
"epoch": 0.67,
|
46 |
+
"learning_rate": 1.9953114534494306e-05,
|
47 |
+
"loss": 0.0091,
|
48 |
+
"step": 2000
|
49 |
+
},
|
50 |
+
{
|
51 |
+
"epoch": 0.84,
|
52 |
+
"learning_rate": 1.7441393168117883e-05,
|
53 |
+
"loss": 0.009,
|
54 |
+
"step": 2500
|
55 |
+
},
|
56 |
+
{
|
57 |
+
"epoch": 1.0,
|
58 |
+
"eval_loss": 0.011583332903683186,
|
59 |
+
"eval_runtime": 165.5818,
|
60 |
+
"eval_samples_per_second": 309.146,
|
61 |
+
"eval_steps_per_second": 4.831,
|
62 |
+
"step": 2985
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 1.0,
|
66 |
+
"learning_rate": 1.4929671801741461e-05,
|
67 |
+
"loss": 0.0091,
|
68 |
+
"step": 3000
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 1.17,
|
72 |
+
"learning_rate": 1.2417950435365037e-05,
|
73 |
+
"loss": 0.0079,
|
74 |
+
"step": 3500
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 1.33,
|
78 |
+
"eval_loss": 0.01197287067770958,
|
79 |
+
"eval_runtime": 165.5801,
|
80 |
+
"eval_samples_per_second": 309.15,
|
81 |
+
"eval_steps_per_second": 4.831,
|
82 |
+
"step": 3980
|
83 |
+
},
|
84 |
+
{
|
85 |
+
"epoch": 1.34,
|
86 |
+
"learning_rate": 9.906229068988614e-06,
|
87 |
+
"loss": 0.008,
|
88 |
+
"step": 4000
|
89 |
+
},
|
90 |
+
{
|
91 |
+
"epoch": 1.51,
|
92 |
+
"learning_rate": 7.394507702612191e-06,
|
93 |
+
"loss": 0.008,
|
94 |
+
"step": 4500
|
95 |
+
},
|
96 |
+
{
|
97 |
+
"epoch": 1.67,
|
98 |
+
"eval_loss": 0.012653556652367115,
|
99 |
+
"eval_runtime": 165.5534,
|
100 |
+
"eval_samples_per_second": 309.199,
|
101 |
+
"eval_steps_per_second": 4.832,
|
102 |
+
"step": 4975
|
103 |
+
},
|
104 |
+
{
|
105 |
+
"epoch": 1.67,
|
106 |
+
"learning_rate": 4.882786336235767e-06,
|
107 |
+
"loss": 0.0077,
|
108 |
+
"step": 5000
|
109 |
+
},
|
110 |
+
{
|
111 |
+
"epoch": 1.84,
|
112 |
+
"learning_rate": 2.3710649698593436e-06,
|
113 |
+
"loss": 0.0073,
|
114 |
+
"step": 5500
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 2.0,
|
118 |
+
"eval_loss": 0.012686667963862419,
|
119 |
+
"eval_runtime": 165.5035,
|
120 |
+
"eval_samples_per_second": 309.293,
|
121 |
+
"eval_steps_per_second": 4.834,
|
122 |
+
"step": 5970
|
123 |
+
}
|
124 |
+
],
|
125 |
+
"max_steps": 5972,
|
126 |
+
"num_train_epochs": 2,
|
127 |
+
"total_flos": 2.01113970314453e+17,
|
128 |
+
"trial_name": null,
|
129 |
+
"trial_params": null
|
130 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:091fe01e18a966c5e79d16b6a2ff15657a9325e8f7c79e666f62de41cab4b701
|
3 |
+
size 3963
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|