ZongqianLi
commited on
Commit
•
269abd5
1
Parent(s):
b1ff8ac
Upload 8 files
Browse files- config.json +26 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +14 -0
- trainer_state.json +151 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "ZongqianLi/bert_base_cased_scsmall",
|
3 |
+
"architectures": [
|
4 |
+
"BertForQuestionAnswering"
|
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 |
+
"torch_dtype": "float32",
|
22 |
+
"transformers_version": "4.25.1",
|
23 |
+
"type_vocab_size": 2,
|
24 |
+
"use_cache": true,
|
25 |
+
"vocab_size": 28996
|
26 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ade81f419776d92b0c2201c3d39afec1e9d02a875b4d83fee958feea61b2362d
|
3 |
+
size 430952497
|
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 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"do_lower_case": false,
|
4 |
+
"mask_token": "[MASK]",
|
5 |
+
"model_max_length": 512,
|
6 |
+
"name_or_path": "ZongqianLi/bert_base_cased_scsmall",
|
7 |
+
"pad_token": "[PAD]",
|
8 |
+
"sep_token": "[SEP]",
|
9 |
+
"special_tokens_map_file": null,
|
10 |
+
"strip_accents": null,
|
11 |
+
"tokenize_chinese_chars": true,
|
12 |
+
"tokenizer_class": "BertTokenizer",
|
13 |
+
"unk_token": "[UNK]"
|
14 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,151 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 9.0,
|
5 |
+
"global_step": 2475,
|
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": 3e-05,
|
13 |
+
"loss": 1.8887,
|
14 |
+
"step": 275
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 1.0,
|
18 |
+
"eval_exact_match": 52.092806342544016,
|
19 |
+
"eval_f1": 61.062173113283656,
|
20 |
+
"eval_runtime": 3.5591,
|
21 |
+
"eval_samples_per_second": 2409.9,
|
22 |
+
"eval_steps_per_second": 7.586,
|
23 |
+
"step": 275
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 2.0,
|
27 |
+
"learning_rate": 3e-05,
|
28 |
+
"loss": 1.0166,
|
29 |
+
"step": 550
|
30 |
+
},
|
31 |
+
{
|
32 |
+
"epoch": 2.0,
|
33 |
+
"eval_exact_match": 51.544829194357,
|
34 |
+
"eval_f1": 61.20871417240919,
|
35 |
+
"eval_runtime": 3.0486,
|
36 |
+
"eval_samples_per_second": 2813.392,
|
37 |
+
"eval_steps_per_second": 8.856,
|
38 |
+
"step": 550
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 3.0,
|
42 |
+
"learning_rate": 3e-05,
|
43 |
+
"loss": 0.8084,
|
44 |
+
"step": 825
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 3.0,
|
48 |
+
"eval_exact_match": 52.745715285064705,
|
49 |
+
"eval_f1": 61.686663146219274,
|
50 |
+
"eval_runtime": 3.0412,
|
51 |
+
"eval_samples_per_second": 2820.232,
|
52 |
+
"eval_steps_per_second": 8.878,
|
53 |
+
"step": 825
|
54 |
+
},
|
55 |
+
{
|
56 |
+
"epoch": 4.0,
|
57 |
+
"learning_rate": 3e-05,
|
58 |
+
"loss": 0.661,
|
59 |
+
"step": 1100
|
60 |
+
},
|
61 |
+
{
|
62 |
+
"epoch": 4.0,
|
63 |
+
"eval_exact_match": 52.302669931211376,
|
64 |
+
"eval_f1": 61.55649613642499,
|
65 |
+
"eval_runtime": 3.0099,
|
66 |
+
"eval_samples_per_second": 2849.557,
|
67 |
+
"eval_steps_per_second": 8.97,
|
68 |
+
"step": 1100
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 5.0,
|
72 |
+
"learning_rate": 3e-05,
|
73 |
+
"loss": 0.5426,
|
74 |
+
"step": 1375
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 5.0,
|
78 |
+
"eval_exact_match": 52.209397225136996,
|
79 |
+
"eval_f1": 61.19204443173771,
|
80 |
+
"eval_runtime": 3.0395,
|
81 |
+
"eval_samples_per_second": 2821.812,
|
82 |
+
"eval_steps_per_second": 8.883,
|
83 |
+
"step": 1375
|
84 |
+
},
|
85 |
+
{
|
86 |
+
"epoch": 6.0,
|
87 |
+
"learning_rate": 3e-05,
|
88 |
+
"loss": 0.4487,
|
89 |
+
"step": 1650
|
90 |
+
},
|
91 |
+
{
|
92 |
+
"epoch": 6.0,
|
93 |
+
"eval_exact_match": 54.10982861140259,
|
94 |
+
"eval_f1": 62.138631414166056,
|
95 |
+
"eval_runtime": 3.0046,
|
96 |
+
"eval_samples_per_second": 2854.628,
|
97 |
+
"eval_steps_per_second": 8.986,
|
98 |
+
"step": 1650
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 7.0,
|
102 |
+
"learning_rate": 3e-05,
|
103 |
+
"loss": 0.3729,
|
104 |
+
"step": 1925
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 7.0,
|
108 |
+
"eval_exact_match": 54.28471493529206,
|
109 |
+
"eval_f1": 62.01717049776823,
|
110 |
+
"eval_runtime": 2.9983,
|
111 |
+
"eval_samples_per_second": 2860.629,
|
112 |
+
"eval_steps_per_second": 9.005,
|
113 |
+
"step": 1925
|
114 |
+
},
|
115 |
+
{
|
116 |
+
"epoch": 8.0,
|
117 |
+
"learning_rate": 3e-05,
|
118 |
+
"loss": 0.3054,
|
119 |
+
"step": 2200
|
120 |
+
},
|
121 |
+
{
|
122 |
+
"epoch": 8.0,
|
123 |
+
"eval_exact_match": 53.65512416928996,
|
124 |
+
"eval_f1": 61.57642196405224,
|
125 |
+
"eval_runtime": 3.0344,
|
126 |
+
"eval_samples_per_second": 2826.588,
|
127 |
+
"eval_steps_per_second": 8.898,
|
128 |
+
"step": 2200
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 9.0,
|
132 |
+
"learning_rate": 3e-05,
|
133 |
+
"loss": 0.2554,
|
134 |
+
"step": 2475
|
135 |
+
},
|
136 |
+
{
|
137 |
+
"epoch": 9.0,
|
138 |
+
"eval_exact_match": 55.2640783490731,
|
139 |
+
"eval_f1": 62.4332153138502,
|
140 |
+
"eval_runtime": 3.0011,
|
141 |
+
"eval_samples_per_second": 2857.957,
|
142 |
+
"eval_steps_per_second": 8.997,
|
143 |
+
"step": 2475
|
144 |
+
}
|
145 |
+
],
|
146 |
+
"max_steps": 2750,
|
147 |
+
"num_train_epochs": 10,
|
148 |
+
"total_flos": 298038669082624.0,
|
149 |
+
"trial_name": null,
|
150 |
+
"trial_params": null
|
151 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:df38e3f550464aa6d474819d22e2db5521cd32e5ff67d2d68812478b92a76301
|
3 |
+
size 5039
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|