Hugging Face's logo

NLPinas
/
EMoBERT-tl

Text Classification
Transformers
PyTorch
roberta
Inference Endpoints
Model card Files Community
1
jaspercatapang commited on
Commit
078f0be
·
1 Parent(s): 9fa6cff

Upload 6 files

Browse files
Files changed (6) hide show
  1. config.json +28 -0
  2. pytorch_model.bin +3 -0
  3. rng_state.pth +3 -0
  4. scheduler.pt +3 -0
  5. trainer_state.json +181 -0
  6. training_args.bin +3 -0
config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "roberta-base",
3
+ "architectures": [
4
+ "RobertaForSequenceClassification"
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": "roberta",
18
+ "num_attention_heads": 12,
19
+ "num_hidden_layers": 12,
20
+ "pad_token_id": 1,
21
+ "position_embedding_type": "absolute",
22
+ "problem_type": "single_label_classification",
23
+ "torch_dtype": "float32",
24
+ "transformers_version": "4.33.2",
25
+ "type_vocab_size": 1,
26
+ "use_cache": true,
27
+ "vocab_size": 50265
28
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f4b1dea38c1cff5f2b75ac41b8cd8c593dc22160efa25d0a5a057163af88ec5
3
+ size 498657649
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee09e7cc1d93020856f86c161ed896da595b8a55f4b4ccd0aebf26bffd1e9c24
3
+ size 14575
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7229e52dc3faef6c706ce56d5c97adfb8f09a50484a80b71292134f954f16048
3
+ size 627
trainer_state.json ADDED
@@ -0,0 +1,181 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 28.125,
5
+ "eval_steps": 100,
6
+ "global_step": 900,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 3.12,
13
+ "learning_rate": 8.958333333333334e-07,
14
+ "loss": 0.5457,
15
+ "step": 100
16
+ },
17
+ {
18
+ "epoch": 3.12,
19
+ "eval_accuracy": 0.783256880733945,
20
+ "eval_f1": 0.8134254689042448,
21
+ "eval_loss": 0.4702916741371155,
22
+ "eval_precision": 0.8477366255144033,
23
+ "eval_recall": 0.7817836812144212,
24
+ "eval_runtime": 8.092,
25
+ "eval_samples_per_second": 107.761,
26
+ "eval_steps_per_second": 1.73,
27
+ "step": 100
28
+ },
29
+ {
30
+ "epoch": 6.25,
31
+ "learning_rate": 7.916666666666666e-07,
32
+ "loss": 0.4347,
33
+ "step": 200
34
+ },
35
+ {
36
+ "epoch": 6.25,
37
+ "eval_accuracy": 0.8279816513761468,
38
+ "eval_f1": 0.8557692307692307,
39
+ "eval_loss": 0.3783995807170868,
40
+ "eval_precision": 0.8674463937621832,
41
+ "eval_recall": 0.8444022770398482,
42
+ "eval_runtime": 7.9109,
43
+ "eval_samples_per_second": 110.228,
44
+ "eval_steps_per_second": 1.77,
45
+ "step": 200
46
+ },
47
+ {
48
+ "epoch": 9.38,
49
+ "learning_rate": 6.875e-07,
50
+ "loss": 0.3672,
51
+ "step": 300
52
+ },
53
+ {
54
+ "epoch": 9.38,
55
+ "eval_accuracy": 0.8497706422018348,
56
+ "eval_f1": 0.8751191611058151,
57
+ "eval_loss": 0.3128945529460907,
58
+ "eval_precision": 0.8793103448275862,
59
+ "eval_recall": 0.8709677419354839,
60
+ "eval_runtime": 7.9781,
61
+ "eval_samples_per_second": 109.299,
62
+ "eval_steps_per_second": 1.755,
63
+ "step": 300
64
+ },
65
+ {
66
+ "epoch": 12.5,
67
+ "learning_rate": 5.833333333333334e-07,
68
+ "loss": 0.3251,
69
+ "step": 400
70
+ },
71
+ {
72
+ "epoch": 12.5,
73
+ "eval_accuracy": 0.8658256880733946,
74
+ "eval_f1": 0.8925619834710744,
75
+ "eval_loss": 0.29092392325401306,
76
+ "eval_precision": 0.8647686832740213,
77
+ "eval_recall": 0.9222011385199241,
78
+ "eval_runtime": 8.2084,
79
+ "eval_samples_per_second": 106.233,
80
+ "eval_steps_per_second": 1.706,
81
+ "step": 400
82
+ },
83
+ {
84
+ "epoch": 15.62,
85
+ "learning_rate": 4.791666666666667e-07,
86
+ "loss": 0.2957,
87
+ "step": 500
88
+ },
89
+ {
90
+ "epoch": 15.62,
91
+ "eval_accuracy": 0.8715596330275229,
92
+ "eval_f1": 0.8968692449355433,
93
+ "eval_loss": 0.27530843019485474,
94
+ "eval_precision": 0.8711985688729875,
95
+ "eval_recall": 0.9240986717267552,
96
+ "eval_runtime": 8.2097,
97
+ "eval_samples_per_second": 106.216,
98
+ "eval_steps_per_second": 1.705,
99
+ "step": 500
100
+ },
101
+ {
102
+ "epoch": 18.75,
103
+ "learning_rate": 3.75e-07,
104
+ "loss": 0.2763,
105
+ "step": 600
106
+ },
107
+ {
108
+ "epoch": 18.75,
109
+ "eval_accuracy": 0.8784403669724771,
110
+ "eval_f1": 0.8990476190476191,
111
+ "eval_loss": 0.25807398557662964,
112
+ "eval_precision": 0.9024856596558317,
113
+ "eval_recall": 0.8956356736242884,
114
+ "eval_runtime": 8.114,
115
+ "eval_samples_per_second": 107.468,
116
+ "eval_steps_per_second": 1.725,
117
+ "step": 600
118
+ },
119
+ {
120
+ "epoch": 21.88,
121
+ "learning_rate": 2.708333333333333e-07,
122
+ "loss": 0.2595,
123
+ "step": 700
124
+ },
125
+ {
126
+ "epoch": 21.88,
127
+ "eval_accuracy": 0.8841743119266054,
128
+ "eval_f1": 0.906567992599445,
129
+ "eval_loss": 0.25655582547187805,
130
+ "eval_precision": 0.8844765342960289,
131
+ "eval_recall": 0.9297912713472486,
132
+ "eval_runtime": 8.2553,
133
+ "eval_samples_per_second": 105.63,
134
+ "eval_steps_per_second": 1.696,
135
+ "step": 700
136
+ },
137
+ {
138
+ "epoch": 25.0,
139
+ "learning_rate": 1.6666666666666665e-07,
140
+ "loss": 0.2521,
141
+ "step": 800
142
+ },
143
+ {
144
+ "epoch": 25.0,
145
+ "eval_accuracy": 0.8807339449541285,
146
+ "eval_f1": 0.9017013232514178,
147
+ "eval_loss": 0.24835383892059326,
148
+ "eval_precision": 0.8983050847457628,
149
+ "eval_recall": 0.905123339658444,
150
+ "eval_runtime": 8.3369,
151
+ "eval_samples_per_second": 104.595,
152
+ "eval_steps_per_second": 1.679,
153
+ "step": 800
154
+ },
155
+ {
156
+ "epoch": 28.12,
157
+ "learning_rate": 6.25e-08,
158
+ "loss": 0.2399,
159
+ "step": 900
160
+ },
161
+ {
162
+ "epoch": 28.12,
163
+ "eval_accuracy": 0.8853211009174312,
164
+ "eval_f1": 0.9070631970260222,
165
+ "eval_loss": 0.2506503164768219,
166
+ "eval_precision": 0.8888888888888888,
167
+ "eval_recall": 0.9259962049335864,
168
+ "eval_runtime": 8.3716,
169
+ "eval_samples_per_second": 104.161,
170
+ "eval_steps_per_second": 1.672,
171
+ "step": 900
172
+ }
173
+ ],
174
+ "logging_steps": 100,
175
+ "max_steps": 960,
176
+ "num_train_epochs": 30,
177
+ "save_steps": 100,
178
+ "total_flos": 3761172536371200.0,
179
+ "trial_name": null,
180
+ "trial_params": null
181
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ae0b017007eca9efbdb38584c473ebd6b4dc0ae1ac2c1c8fea320b141f03c46
3
+ size 3963