Hugging Face's logo

rashid0784
/
dladies_better

Text Classification
Transformers
Safetensors
bert
Inference Endpoints
Model card Files Community
rashid0784 commited on
Commit
f2099aa
·
1 Parent(s): 5e0a1e2

Upload folder using huggingface_hub

Browse files
Files changed (7) hide show
  1. config.json +27 -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 +214 -0
  7. training_args.bin +3 -0
config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "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
+ "problem_type": "single_label_classification",
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.35.0",
24
+ "type_vocab_size": 2,
25
+ "use_cache": true,
26
+ "vocab_size": 30522
27
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3cb67dfff235e197ed2857f29aa9beea6b4f068570288e3d40df7514c26437b7
3
+ size 437958648
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d902cfdd68eefe870ae5a647eeb9a9103b20d4b937da40c2eedaccdf85a37ed
3
+ size 876037893
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7bc69d64f99c4f5d5f1935dba19593a430010bf168d4dede7e169d874e64845a
3
+ size 14575
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1bb1cd7d84b7e49c88ef7a595e38d2198f0bb946bfc900f75be6407dd5543d08
3
+ size 627
trainer_state.json ADDED
@@ -0,0 +1,214 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.029607130214571953,
3
+ "best_model_checkpoint": "model/checkpoint-6500",
4
+ "epoch": 2.138157894736842,
5
+ "eval_steps": 500,
6
+ "global_step": 6500,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.16,
13
+ "learning_rate": 4.7944078947368425e-05,
14
+ "loss": 0.1494,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 0.16,
19
+ "eval_accuracy": 0.9837171052631579,
20
+ "eval_loss": 0.0790267065167427,
21
+ "eval_runtime": 113.0978,
22
+ "eval_samples_per_second": 53.759,
23
+ "eval_steps_per_second": 6.72,
24
+ "step": 500
25
+ },
26
+ {
27
+ "epoch": 0.33,
28
+ "learning_rate": 4.588815789473684e-05,
29
+ "loss": 0.1072,
30
+ "step": 1000
31
+ },
32
+ {
33
+ "epoch": 0.33,
34
+ "eval_accuracy": 0.9824013157894737,
35
+ "eval_loss": 0.06455110013484955,
36
+ "eval_runtime": 113.235,
37
+ "eval_samples_per_second": 53.694,
38
+ "eval_steps_per_second": 6.712,
39
+ "step": 1000
40
+ },
41
+ {
42
+ "epoch": 0.49,
43
+ "learning_rate": 4.383223684210527e-05,
44
+ "loss": 0.0765,
45
+ "step": 1500
46
+ },
47
+ {
48
+ "epoch": 0.49,
49
+ "eval_accuracy": 0.9899671052631579,
50
+ "eval_loss": 0.04877911135554314,
51
+ "eval_runtime": 113.1524,
52
+ "eval_samples_per_second": 53.733,
53
+ "eval_steps_per_second": 6.717,
54
+ "step": 1500
55
+ },
56
+ {
57
+ "epoch": 0.66,
58
+ "learning_rate": 4.177631578947369e-05,
59
+ "loss": 0.0742,
60
+ "step": 2000
61
+ },
62
+ {
63
+ "epoch": 0.66,
64
+ "eval_accuracy": 0.9886513157894737,
65
+ "eval_loss": 0.054583221673965454,
66
+ "eval_runtime": 113.2769,
67
+ "eval_samples_per_second": 53.674,
68
+ "eval_steps_per_second": 6.709,
69
+ "step": 2000
70
+ },
71
+ {
72
+ "epoch": 0.82,
73
+ "learning_rate": 3.972039473684211e-05,
74
+ "loss": 0.0748,
75
+ "step": 2500
76
+ },
77
+ {
78
+ "epoch": 0.82,
79
+ "eval_accuracy": 0.990625,
80
+ "eval_loss": 0.04383059963583946,
81
+ "eval_runtime": 113.3147,
82
+ "eval_samples_per_second": 53.656,
83
+ "eval_steps_per_second": 6.707,
84
+ "step": 2500
85
+ },
86
+ {
87
+ "epoch": 0.99,
88
+ "learning_rate": 3.7664473684210526e-05,
89
+ "loss": 0.0437,
90
+ "step": 3000
91
+ },
92
+ {
93
+ "epoch": 0.99,
94
+ "eval_accuracy": 0.9901315789473685,
95
+ "eval_loss": 0.05416030064225197,
96
+ "eval_runtime": 113.1123,
97
+ "eval_samples_per_second": 53.752,
98
+ "eval_steps_per_second": 6.719,
99
+ "step": 3000
100
+ },
101
+ {
102
+ "epoch": 1.15,
103
+ "learning_rate": 3.560855263157895e-05,
104
+ "loss": 0.0134,
105
+ "step": 3500
106
+ },
107
+ {
108
+ "epoch": 1.15,
109
+ "eval_accuracy": 0.990953947368421,
110
+ "eval_loss": 0.05749928951263428,
111
+ "eval_runtime": 113.4787,
112
+ "eval_samples_per_second": 53.578,
113
+ "eval_steps_per_second": 6.697,
114
+ "step": 3500
115
+ },
116
+ {
117
+ "epoch": 1.32,
118
+ "learning_rate": 3.355263157894737e-05,
119
+ "loss": 0.0277,
120
+ "step": 4000
121
+ },
122
+ {
123
+ "epoch": 1.32,
124
+ "eval_accuracy": 0.9904605263157895,
125
+ "eval_loss": 0.06314379721879959,
126
+ "eval_runtime": 113.4629,
127
+ "eval_samples_per_second": 53.586,
128
+ "eval_steps_per_second": 6.698,
129
+ "step": 4000
130
+ },
131
+ {
132
+ "epoch": 1.48,
133
+ "learning_rate": 3.1496710526315794e-05,
134
+ "loss": 0.0231,
135
+ "step": 4500
136
+ },
137
+ {
138
+ "epoch": 1.48,
139
+ "eval_accuracy": 0.9912828947368421,
140
+ "eval_loss": 0.04834901914000511,
141
+ "eval_runtime": 113.5144,
142
+ "eval_samples_per_second": 53.561,
143
+ "eval_steps_per_second": 6.695,
144
+ "step": 4500
145
+ },
146
+ {
147
+ "epoch": 1.64,
148
+ "learning_rate": 2.944078947368421e-05,
149
+ "loss": 0.0243,
150
+ "step": 5000
151
+ },
152
+ {
153
+ "epoch": 1.64,
154
+ "eval_accuracy": 0.9901315789473685,
155
+ "eval_loss": 0.06605446338653564,
156
+ "eval_runtime": 113.6185,
157
+ "eval_samples_per_second": 53.512,
158
+ "eval_steps_per_second": 6.689,
159
+ "step": 5000
160
+ },
161
+ {
162
+ "epoch": 1.81,
163
+ "learning_rate": 2.7384868421052633e-05,
164
+ "loss": 0.0232,
165
+ "step": 5500
166
+ },
167
+ {
168
+ "epoch": 1.81,
169
+ "eval_accuracy": 0.9932565789473684,
170
+ "eval_loss": 0.037462268024683,
171
+ "eval_runtime": 112.9475,
172
+ "eval_samples_per_second": 53.83,
173
+ "eval_steps_per_second": 6.729,
174
+ "step": 5500
175
+ },
176
+ {
177
+ "epoch": 1.97,
178
+ "learning_rate": 2.5328947368421052e-05,
179
+ "loss": 0.0198,
180
+ "step": 6000
181
+ },
182
+ {
183
+ "epoch": 1.97,
184
+ "eval_accuracy": 0.9945723684210527,
185
+ "eval_loss": 0.034890029579401016,
186
+ "eval_runtime": 112.9353,
187
+ "eval_samples_per_second": 53.836,
188
+ "eval_steps_per_second": 6.73,
189
+ "step": 6000
190
+ },
191
+ {
192
+ "epoch": 2.14,
193
+ "learning_rate": 2.3273026315789475e-05,
194
+ "loss": 0.0122,
195
+ "step": 6500
196
+ },
197
+ {
198
+ "epoch": 2.14,
199
+ "eval_accuracy": 0.9962171052631579,
200
+ "eval_loss": 0.029607130214571953,
201
+ "eval_runtime": 112.9987,
202
+ "eval_samples_per_second": 53.806,
203
+ "eval_steps_per_second": 6.726,
204
+ "step": 6500
205
+ }
206
+ ],
207
+ "logging_steps": 500,
208
+ "max_steps": 12160,
209
+ "num_train_epochs": 4,
210
+ "save_steps": 500,
211
+ "total_flos": 1.368177487872e+16,
212
+ "trial_name": null,
213
+ "trial_params": null
214
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e002583a70b29f889e4fecc361d241d0dab660af8d5b8139f8947aa3e48c84f6
3
+ size 4091