Hugging Face's logo

sonnv
/
toxic_detection

Text Classification
Transformers
PyTorch
xlm-roberta
Model card Files
xet
Community
1
sonnv commited on
Commit
0d1a25a
·
1 Parent(s): 40fd62e

update sonnv

Browse files
Files changed (7) hide show
  1. config.json +29 -0
  2. optimizer.pt +3 -0
  3. pytorch_model.bin +3 -0
  4. rng_state.pth +3 -0
  5. scheduler.pt +3 -0
  6. trainer_state.json +220 -0
  7. training_args.bin +3 -0
config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "xlm-roberta-base",
3
+ "architectures": [
4
+ "XLMRobertaForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 3072,
15
+ "layer_norm_eps": 1e-05,
16
+ "max_position_embeddings": 514,
17
+ "model_type": "xlm-roberta",
18
+ "num_attention_heads": 12,
19
+ "num_hidden_layers": 12,
20
+ "output_past": true,
21
+ "pad_token_id": 1,
22
+ "position_embedding_type": "absolute",
23
+ "problem_type": "single_label_classification",
24
+ "torch_dtype": "float32",
25
+ "transformers_version": "4.22.1",
26
+ "type_vocab_size": 1,
27
+ "use_cache": true,
28
+ "vocab_size": 250002
29
+ }
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c078cae414aaecb8f4cda382a247ce3d00ed540f497783c4e2a6f9fa0a13326
3
+ size 231586033
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd6bd9ec1ad74e1ff7fb9872b40e28317ab3b606da8eaf108b01577950458d25
3
+ size 1112249581
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eac080601103a688f9a709c5daf572398cea8e701e92ce3f8f412c98694c3186
3
+ size 13611
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b453d648e57ddd9c3968264ce42553e4615f300f807a71ce521f9024adb0b7b2
3
+ size 623
trainer_state.json ADDED
@@ -0,0 +1,220 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.0012385094305500388,
3
+ "best_model_checkpoint": "./model/checkpoint-500",
4
+ "epoch": 30.0,
5
+ "global_step": 600,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 2.5,
12
+ "learning_rate": 9.482758620689655e-07,
13
+ "loss": 0.1587,
14
+ "step": 50
15
+ },
16
+ {
17
+ "epoch": 2.5,
18
+ "eval_Acc": 1.0,
19
+ "eval_loss": 0.006247001700103283,
20
+ "eval_macro_F1": 1.0,
21
+ "eval_runtime": 0.3079,
22
+ "eval_samples_per_second": 324.744,
23
+ "eval_steps_per_second": 12.99,
24
+ "eval_weighted_F1": 1.0,
25
+ "step": 50
26
+ },
27
+ {
28
+ "epoch": 5.0,
29
+ "learning_rate": 8.620689655172412e-07,
30
+ "loss": 0.1631,
31
+ "step": 100
32
+ },
33
+ {
34
+ "epoch": 5.0,
35
+ "eval_Acc": 0.99,
36
+ "eval_loss": 0.0467730276286602,
37
+ "eval_macro_F1": 0.988936829295276,
38
+ "eval_runtime": 0.3093,
39
+ "eval_samples_per_second": 323.311,
40
+ "eval_steps_per_second": 12.932,
41
+ "eval_weighted_F1": 0.9899657041708153,
42
+ "step": 100
43
+ },
44
+ {
45
+ "epoch": 7.5,
46
+ "learning_rate": 7.758620689655172e-07,
47
+ "loss": 0.1274,
48
+ "step": 150
49
+ },
50
+ {
51
+ "epoch": 7.5,
52
+ "eval_Acc": 1.0,
53
+ "eval_loss": 0.003920665942132473,
54
+ "eval_macro_F1": 1.0,
55
+ "eval_runtime": 0.2879,
56
+ "eval_samples_per_second": 347.397,
57
+ "eval_steps_per_second": 13.896,
58
+ "eval_weighted_F1": 1.0,
59
+ "step": 150
60
+ },
61
+ {
62
+ "epoch": 10.0,
63
+ "learning_rate": 6.896551724137931e-07,
64
+ "loss": 0.108,
65
+ "step": 200
66
+ },
67
+ {
68
+ "epoch": 10.0,
69
+ "eval_Acc": 1.0,
70
+ "eval_loss": 0.008137707598507404,
71
+ "eval_macro_F1": 1.0,
72
+ "eval_runtime": 0.2882,
73
+ "eval_samples_per_second": 346.98,
74
+ "eval_steps_per_second": 13.879,
75
+ "eval_weighted_F1": 1.0,
76
+ "step": 200
77
+ },
78
+ {
79
+ "epoch": 12.5,
80
+ "learning_rate": 6.03448275862069e-07,
81
+ "loss": 0.1032,
82
+ "step": 250
83
+ },
84
+ {
85
+ "epoch": 12.5,
86
+ "eval_Acc": 0.97,
87
+ "eval_loss": 0.11218936741352081,
88
+ "eval_macro_F1": 0.9676410311724732,
89
+ "eval_runtime": 0.2888,
90
+ "eval_samples_per_second": 346.313,
91
+ "eval_steps_per_second": 13.853,
92
+ "eval_weighted_F1": 0.9702621076475029,
93
+ "step": 250
94
+ },
95
+ {
96
+ "epoch": 15.0,
97
+ "learning_rate": 5.172413793103448e-07,
98
+ "loss": 0.1117,
99
+ "step": 300
100
+ },
101
+ {
102
+ "epoch": 15.0,
103
+ "eval_Acc": 1.0,
104
+ "eval_loss": 0.008067261427640915,
105
+ "eval_macro_F1": 1.0,
106
+ "eval_runtime": 0.2984,
107
+ "eval_samples_per_second": 335.167,
108
+ "eval_steps_per_second": 13.407,
109
+ "eval_weighted_F1": 1.0,
110
+ "step": 300
111
+ },
112
+ {
113
+ "epoch": 17.5,
114
+ "learning_rate": 4.310344827586206e-07,
115
+ "loss": 0.0855,
116
+ "step": 350
117
+ },
118
+ {
119
+ "epoch": 17.5,
120
+ "eval_Acc": 1.0,
121
+ "eval_loss": 0.0037926011718809605,
122
+ "eval_macro_F1": 1.0,
123
+ "eval_runtime": 0.2856,
124
+ "eval_samples_per_second": 350.082,
125
+ "eval_steps_per_second": 14.003,
126
+ "eval_weighted_F1": 1.0,
127
+ "step": 350
128
+ },
129
+ {
130
+ "epoch": 20.0,
131
+ "learning_rate": 3.4482758620689656e-07,
132
+ "loss": 0.0871,
133
+ "step": 400
134
+ },
135
+ {
136
+ "epoch": 20.0,
137
+ "eval_Acc": 1.0,
138
+ "eval_loss": 0.00232470384798944,
139
+ "eval_macro_F1": 1.0,
140
+ "eval_runtime": 0.2916,
141
+ "eval_samples_per_second": 342.994,
142
+ "eval_steps_per_second": 13.72,
143
+ "eval_weighted_F1": 1.0,
144
+ "step": 400
145
+ },
146
+ {
147
+ "epoch": 22.5,
148
+ "learning_rate": 2.586206896551724e-07,
149
+ "loss": 0.0746,
150
+ "step": 450
151
+ },
152
+ {
153
+ "epoch": 22.5,
154
+ "eval_Acc": 1.0,
155
+ "eval_loss": 0.0018292993772774935,
156
+ "eval_macro_F1": 1.0,
157
+ "eval_runtime": 0.3231,
158
+ "eval_samples_per_second": 309.536,
159
+ "eval_steps_per_second": 12.381,
160
+ "eval_weighted_F1": 1.0,
161
+ "step": 450
162
+ },
163
+ {
164
+ "epoch": 25.0,
165
+ "learning_rate": 1.7241379310344828e-07,
166
+ "loss": 0.0726,
167
+ "step": 500
168
+ },
169
+ {
170
+ "epoch": 25.0,
171
+ "eval_Acc": 1.0,
172
+ "eval_loss": 0.0012385094305500388,
173
+ "eval_macro_F1": 1.0,
174
+ "eval_runtime": 0.2944,
175
+ "eval_samples_per_second": 339.647,
176
+ "eval_steps_per_second": 13.586,
177
+ "eval_weighted_F1": 1.0,
178
+ "step": 500
179
+ },
180
+ {
181
+ "epoch": 27.5,
182
+ "learning_rate": 8.620689655172414e-08,
183
+ "loss": 0.077,
184
+ "step": 550
185
+ },
186
+ {
187
+ "epoch": 27.5,
188
+ "eval_Acc": 1.0,
189
+ "eval_loss": 0.001301100361160934,
190
+ "eval_macro_F1": 1.0,
191
+ "eval_runtime": 0.2913,
192
+ "eval_samples_per_second": 343.306,
193
+ "eval_steps_per_second": 13.732,
194
+ "eval_weighted_F1": 1.0,
195
+ "step": 550
196
+ },
197
+ {
198
+ "epoch": 30.0,
199
+ "learning_rate": 0.0,
200
+ "loss": 0.0686,
201
+ "step": 600
202
+ },
203
+ {
204
+ "epoch": 30.0,
205
+ "eval_Acc": 1.0,
206
+ "eval_loss": 0.0012519867159426212,
207
+ "eval_macro_F1": 1.0,
208
+ "eval_runtime": 0.2884,
209
+ "eval_samples_per_second": 346.698,
210
+ "eval_steps_per_second": 13.868,
211
+ "eval_weighted_F1": 1.0,
212
+ "step": 600
213
+ }
214
+ ],
215
+ "max_steps": 600,
216
+ "num_train_epochs": 30,
217
+ "total_flos": 2458772812339200.0,
218
+ "trial_name": null,
219
+ "trial_params": null
220
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c34755b20db0761a6da5d8b837645de9543f1748466bb4f206f5a024117c731
3
+ size 3375