Hugging Face's logo

tum-nlp
/
neural-news-discriminator-RoBERTa-en

Text Classification
Transformers
Safetensors
English
roberta
Inference Endpoints
Model card Files Community
cmykk commited on
Commit
056a5e7
•
1 Parent(s): 59f7d0e

Upload 7 files

Browse files
Files changed (7) hide show
  1. config.json +28 -0
  2. model.safetensors +3 -0
  3. optimizer.pt +3 -0
  4. rng_state.pth +3 -0
  5. scheduler.pt +3 -0
  6. trainer_state.json +207 -0
  7. 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": "4.36.2",
25
+ "type_vocab_size": 1,
26
+ "use_cache": true,
27
+ "vocab_size": 50265
28
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f95163eefed4fc4201da2af99287470c8dc2e31c18d38a2694ebc371c508db77
3
+ size 498612824
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2227e79fb5553e72058b9e36d76bc888ff3a9da4d33d3f7687866747c551fb22
3
+ size 685336698
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aaa4103ee4fea261d11114f74fca963353c7aa0dc0d43449bc3550625bb6070e
3
+ size 14244
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:962de23ce4defd048f5a85f3eb37946582cc46c56c044ad0265510a2ee6f563d
3
+ size 1064
trainer_state.json ADDED
@@ -0,0 +1,207 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 1.0,
3
+ "best_model_checkpoint": "./en_results/checkpoint-150",
4
+ "epoch": 5.0,
5
+ "eval_steps": 500,
6
+ "global_step": 750,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 1.0,
13
+ "eval_accuracy": 1.0,
14
+ "eval_classification_report": {
15
+ "accuracy": 1.0,
16
+ "macro avg": {
17
+ "f1-score": 1.0,
18
+ "precision": 1.0,
19
+ "recall": 1.0,
20
+ "support": 800.0
21
+ },
22
+ "neural": {
23
+ "f1-score": 1.0,
24
+ "precision": 1.0,
25
+ "recall": 1.0,
26
+ "support": 400.0
27
+ },
28
+ "real": {
29
+ "f1-score": 1.0,
30
+ "precision": 1.0,
31
+ "recall": 1.0,
32
+ "support": 400.0
33
+ },
34
+ "weighted avg": {
35
+ "f1-score": 1.0,
36
+ "precision": 1.0,
37
+ "recall": 1.0,
38
+ "support": 800.0
39
+ }
40
+ },
41
+ "eval_loss": 0.0007810367387719452,
42
+ "eval_runtime": 41.5114,
43
+ "eval_samples_per_second": 19.272,
44
+ "eval_steps_per_second": 1.204,
45
+ "step": 150
46
+ },
47
+ {
48
+ "epoch": 2.0,
49
+ "eval_accuracy": 0.99625,
50
+ "eval_classification_report": {
51
+ "accuracy": 0.99625,
52
+ "macro avg": {
53
+ "f1-score": 0.9962499472648834,
54
+ "precision": 0.9962779156327544,
55
+ "recall": 0.9962500000000001,
56
+ "support": 800.0
57
+ },
58
+ "neural": {
59
+ "f1-score": 0.9962358845671266,
60
+ "precision": 1.0,
61
+ "recall": 0.9925,
62
+ "support": 400.0
63
+ },
64
+ "real": {
65
+ "f1-score": 0.9962640099626401,
66
+ "precision": 0.9925558312655087,
67
+ "recall": 1.0,
68
+ "support": 400.0
69
+ },
70
+ "weighted avg": {
71
+ "f1-score": 0.9962499472648834,
72
+ "precision": 0.9962779156327544,
73
+ "recall": 0.99625,
74
+ "support": 800.0
75
+ }
76
+ },
77
+ "eval_loss": 0.02056434564292431,
78
+ "eval_runtime": 42.6494,
79
+ "eval_samples_per_second": 18.758,
80
+ "eval_steps_per_second": 1.172,
81
+ "step": 300
82
+ },
83
+ {
84
+ "epoch": 3.0,
85
+ "eval_accuracy": 0.99625,
86
+ "eval_classification_report": {
87
+ "accuracy": 0.99625,
88
+ "macro avg": {
89
+ "f1-score": 0.9962499472648834,
90
+ "precision": 0.9962779156327544,
91
+ "recall": 0.9962500000000001,
92
+ "support": 800.0
93
+ },
94
+ "neural": {
95
+ "f1-score": 0.9962358845671266,
96
+ "precision": 1.0,
97
+ "recall": 0.9925,
98
+ "support": 400.0
99
+ },
100
+ "real": {
101
+ "f1-score": 0.9962640099626401,
102
+ "precision": 0.9925558312655087,
103
+ "recall": 1.0,
104
+ "support": 400.0
105
+ },
106
+ "weighted avg": {
107
+ "f1-score": 0.9962499472648834,
108
+ "precision": 0.9962779156327544,
109
+ "recall": 0.99625,
110
+ "support": 800.0
111
+ }
112
+ },
113
+ "eval_loss": 0.025120796635746956,
114
+ "eval_runtime": 41.1287,
115
+ "eval_samples_per_second": 19.451,
116
+ "eval_steps_per_second": 1.216,
117
+ "step": 450
118
+ },
119
+ {
120
+ "epoch": 3.33,
121
+ "learning_rate": 5e-05,
122
+ "loss": 0.1053,
123
+ "step": 500
124
+ },
125
+ {
126
+ "epoch": 4.0,
127
+ "eval_accuracy": 0.9975,
128
+ "eval_classification_report": {
129
+ "accuracy": 0.9975,
130
+ "macro avg": {
131
+ "f1-score": 0.9974999843749024,
132
+ "precision": 0.9975124378109452,
133
+ "recall": 0.9975,
134
+ "support": 800.0
135
+ },
136
+ "neural": {
137
+ "f1-score": 0.9975062344139651,
138
+ "precision": 0.9950248756218906,
139
+ "recall": 1.0,
140
+ "support": 400.0
141
+ },
142
+ "real": {
143
+ "f1-score": 0.9974937343358395,
144
+ "precision": 1.0,
145
+ "recall": 0.995,
146
+ "support": 400.0
147
+ },
148
+ "weighted avg": {
149
+ "f1-score": 0.9974999843749024,
150
+ "precision": 0.9975124378109453,
151
+ "recall": 0.9975,
152
+ "support": 800.0
153
+ }
154
+ },
155
+ "eval_loss": 0.014787975698709488,
156
+ "eval_runtime": 40.7396,
157
+ "eval_samples_per_second": 19.637,
158
+ "eval_steps_per_second": 1.227,
159
+ "step": 600
160
+ },
161
+ {
162
+ "epoch": 5.0,
163
+ "eval_accuracy": 1.0,
164
+ "eval_classification_report": {
165
+ "accuracy": 1.0,
166
+ "macro avg": {
167
+ "f1-score": 1.0,
168
+ "precision": 1.0,
169
+ "recall": 1.0,
170
+ "support": 800.0
171
+ },
172
+ "neural": {
173
+ "f1-score": 1.0,
174
+ "precision": 1.0,
175
+ "recall": 1.0,
176
+ "support": 400.0
177
+ },
178
+ "real": {
179
+ "f1-score": 1.0,
180
+ "precision": 1.0,
181
+ "recall": 1.0,
182
+ "support": 400.0
183
+ },
184
+ "weighted avg": {
185
+ "f1-score": 1.0,
186
+ "precision": 1.0,
187
+ "recall": 1.0,
188
+ "support": 800.0
189
+ }
190
+ },
191
+ "eval_loss": 1.6821481040096842e-05,
192
+ "eval_runtime": 30.459,
193
+ "eval_samples_per_second": 26.265,
194
+ "eval_steps_per_second": 1.642,
195
+ "step": 750
196
+ }
197
+ ],
198
+ "logging_steps": 500,
199
+ "max_steps": 15000,
200
+ "num_input_tokens_seen": 0,
201
+ "num_train_epochs": 100,
202
+ "save_steps": 500,
203
+ "total_flos": 3157332664320000.0,
204
+ "train_batch_size": 16,
205
+ "trial_name": null,
206
+ "trial_params": null
207
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:168411abf1a1450fc9ae01ba8bb66204b999faf69da6dddbddf31aea9d627785
3
+ size 4664