WpythonW commited on
Commit
02f6c4f
·
verified ·
1 Parent(s): 40e4dbe

Upload folder using huggingface_hub

Browse files
Files changed (7) hide show
  1. config.json +9 -1
  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 +216 -0
  7. training_args.bin +3 -0
config.json CHANGED
@@ -8,8 +8,16 @@
8
  "hidden_act": "gelu",
9
  "hidden_dropout_prob": 0.0,
10
  "hidden_size": 768,
 
 
 
 
11
  "initializer_range": 0.02,
12
  "intermediate_size": 3072,
 
 
 
 
13
  "layer_norm_eps": 1e-12,
14
  "max_length": 1024,
15
  "model_type": "audio-spectrogram-transformer",
@@ -21,5 +29,5 @@
21
  "qkv_bias": true,
22
  "time_stride": 10,
23
  "torch_dtype": "float32",
24
- "transformers_version": "4.44.2"
25
  }
 
8
  "hidden_act": "gelu",
9
  "hidden_dropout_prob": 0.0,
10
  "hidden_size": 768,
11
+ "id2label": {
12
+ "0": "fake",
13
+ "1": "real"
14
+ },
15
  "initializer_range": 0.02,
16
  "intermediate_size": 3072,
17
+ "label2id": {
18
+ "fake": 0,
19
+ "real": 1
20
+ },
21
  "layer_norm_eps": 1e-12,
22
  "max_length": 1024,
23
  "model_type": "audio-spectrogram-transformer",
 
29
  "qkv_bias": true,
30
  "time_stride": 10,
31
  "torch_dtype": "float32",
32
+ "transformers_version": "4.47.0"
33
  }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ceab72e5dc3684140897d5c2a3b2593a7ea147ed1ff2614ede555c59383efed8
3
+ size 344790040
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e72365216c73fd30bbb2b91d525f6b987587dd780debcaf06c0cef3c069130d1
3
+ size 689692538
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48ee9b73399c28d7e668360bf1d5a4d11095c4738bf96c13f7bb6fbff59f8ccb
3
+ size 14244
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16ae9b4ab5daafbb59448b3702971ecfae343b959586f11e64de68c29a0039bb
3
+ size 1064
trainer_state.json ADDED
@@ -0,0 +1,216 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.9945750452079566,
3
+ "best_model_checkpoint": "./results/checkpoint-90",
4
+ "epoch": 2.4193548387096775,
5
+ "eval_steps": 30,
6
+ "global_step": 150,
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,
13
+ "eval_accuracy": 0.4335378323108384,
14
+ "eval_f1": 0.0,
15
+ "eval_loss": 0.8338117599487305,
16
+ "eval_precision": 0.0,
17
+ "eval_recall": 0.0,
18
+ "eval_roc_auc": 0.49765258215962443,
19
+ "eval_runtime": 21.4766,
20
+ "eval_samples_per_second": 22.769,
21
+ "eval_steps_per_second": 0.372,
22
+ "step": 0
23
+ },
24
+ {
25
+ "epoch": 0.16129032258064516,
26
+ "grad_norm": 248532.359375,
27
+ "learning_rate": 5e-05,
28
+ "loss": 0.6955,
29
+ "step": 10
30
+ },
31
+ {
32
+ "epoch": 0.3225806451612903,
33
+ "grad_norm": 282179.78125,
34
+ "learning_rate": 4.918032786885246e-05,
35
+ "loss": 0.3455,
36
+ "step": 20
37
+ },
38
+ {
39
+ "epoch": 0.4838709677419355,
40
+ "grad_norm": 89623.296875,
41
+ "learning_rate": 4.836065573770492e-05,
42
+ "loss": 0.1399,
43
+ "step": 30
44
+ },
45
+ {
46
+ "epoch": 0.4838709677419355,
47
+ "eval_accuracy": 0.983640081799591,
48
+ "eval_f1": 0.9852941176470589,
49
+ "eval_loss": 0.04734700545668602,
50
+ "eval_precision": 1.0,
51
+ "eval_recall": 0.9710144927536232,
52
+ "eval_roc_auc": 0.9855072463768115,
53
+ "eval_runtime": 23.8626,
54
+ "eval_samples_per_second": 20.492,
55
+ "eval_steps_per_second": 0.335,
56
+ "step": 30
57
+ },
58
+ {
59
+ "epoch": 0.6451612903225806,
60
+ "grad_norm": 94711.421875,
61
+ "learning_rate": 4.754098360655738e-05,
62
+ "loss": 0.1264,
63
+ "step": 40
64
+ },
65
+ {
66
+ "epoch": 0.8064516129032258,
67
+ "grad_norm": 5300.99853515625,
68
+ "learning_rate": 4.672131147540984e-05,
69
+ "loss": 0.0676,
70
+ "step": 50
71
+ },
72
+ {
73
+ "epoch": 0.967741935483871,
74
+ "grad_norm": 832800.4375,
75
+ "learning_rate": 4.59016393442623e-05,
76
+ "loss": 0.1843,
77
+ "step": 60
78
+ },
79
+ {
80
+ "epoch": 0.967741935483871,
81
+ "eval_accuracy": 0.9938650306748467,
82
+ "eval_f1": 0.9945553539019963,
83
+ "eval_loss": 0.016523737460374832,
84
+ "eval_precision": 0.9963636363636363,
85
+ "eval_recall": 0.9927536231884058,
86
+ "eval_roc_auc": 0.9940293937538274,
87
+ "eval_runtime": 23.1377,
88
+ "eval_samples_per_second": 21.134,
89
+ "eval_steps_per_second": 0.346,
90
+ "step": 60
91
+ },
92
+ {
93
+ "epoch": 1.129032258064516,
94
+ "grad_norm": 165031.5,
95
+ "learning_rate": 4.508196721311476e-05,
96
+ "loss": 0.1003,
97
+ "step": 70
98
+ },
99
+ {
100
+ "epoch": 1.2903225806451613,
101
+ "grad_norm": 6823.15771484375,
102
+ "learning_rate": 4.426229508196721e-05,
103
+ "loss": 0.0504,
104
+ "step": 80
105
+ },
106
+ {
107
+ "epoch": 1.4516129032258065,
108
+ "grad_norm": 103032.0625,
109
+ "learning_rate": 4.3442622950819674e-05,
110
+ "loss": 0.0636,
111
+ "step": 90
112
+ },
113
+ {
114
+ "epoch": 1.4516129032258065,
115
+ "eval_accuracy": 0.9938650306748467,
116
+ "eval_f1": 0.9945750452079566,
117
+ "eval_loss": 0.024305040016770363,
118
+ "eval_precision": 0.9927797833935018,
119
+ "eval_recall": 0.9963768115942029,
120
+ "eval_roc_auc": 0.9934935701163503,
121
+ "eval_runtime": 23.6734,
122
+ "eval_samples_per_second": 20.656,
123
+ "eval_steps_per_second": 0.338,
124
+ "step": 90
125
+ },
126
+ {
127
+ "epoch": 1.6129032258064515,
128
+ "grad_norm": 1728276.875,
129
+ "learning_rate": 4.262295081967213e-05,
130
+ "loss": 0.2189,
131
+ "step": 100
132
+ },
133
+ {
134
+ "epoch": 1.7741935483870968,
135
+ "grad_norm": 168125.453125,
136
+ "learning_rate": 4.1803278688524595e-05,
137
+ "loss": 0.0983,
138
+ "step": 110
139
+ },
140
+ {
141
+ "epoch": 1.935483870967742,
142
+ "grad_norm": 88308.171875,
143
+ "learning_rate": 4.098360655737705e-05,
144
+ "loss": 0.073,
145
+ "step": 120
146
+ },
147
+ {
148
+ "epoch": 1.935483870967742,
149
+ "eval_accuracy": 0.9775051124744376,
150
+ "eval_f1": 0.9796672828096119,
151
+ "eval_loss": 0.10954457521438599,
152
+ "eval_precision": 1.0,
153
+ "eval_recall": 0.9601449275362319,
154
+ "eval_roc_auc": 0.980072463768116,
155
+ "eval_runtime": 23.0631,
156
+ "eval_samples_per_second": 21.203,
157
+ "eval_steps_per_second": 0.347,
158
+ "step": 120
159
+ },
160
+ {
161
+ "epoch": 2.096774193548387,
162
+ "grad_norm": 120.51848602294922,
163
+ "learning_rate": 4.016393442622951e-05,
164
+ "loss": 0.1133,
165
+ "step": 130
166
+ },
167
+ {
168
+ "epoch": 2.258064516129032,
169
+ "grad_norm": 14.447233200073242,
170
+ "learning_rate": 3.934426229508197e-05,
171
+ "loss": 0.2497,
172
+ "step": 140
173
+ },
174
+ {
175
+ "epoch": 2.4193548387096775,
176
+ "grad_norm": 458481.71875,
177
+ "learning_rate": 3.8524590163934424e-05,
178
+ "loss": 0.1631,
179
+ "step": 150
180
+ },
181
+ {
182
+ "epoch": 2.4193548387096775,
183
+ "eval_accuracy": 0.967280163599182,
184
+ "eval_f1": 0.9701492537313433,
185
+ "eval_loss": 0.21287178993225098,
186
+ "eval_precision": 1.0,
187
+ "eval_recall": 0.9420289855072463,
188
+ "eval_roc_auc": 0.9710144927536232,
189
+ "eval_runtime": 23.3482,
190
+ "eval_samples_per_second": 20.944,
191
+ "eval_steps_per_second": 0.343,
192
+ "step": 150
193
+ }
194
+ ],
195
+ "logging_steps": 10,
196
+ "max_steps": 620,
197
+ "num_input_tokens_seen": 0,
198
+ "num_train_epochs": 10,
199
+ "save_steps": 150,
200
+ "stateful_callbacks": {
201
+ "TrainerControl": {
202
+ "args": {
203
+ "should_epoch_stop": false,
204
+ "should_evaluate": false,
205
+ "should_log": false,
206
+ "should_save": true,
207
+ "should_training_stop": false
208
+ },
209
+ "attributes": {}
210
+ }
211
+ },
212
+ "total_flos": 3.2129066109763584e+17,
213
+ "train_batch_size": 32,
214
+ "trial_name": null,
215
+ "trial_params": null
216
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41e1d94b2b5afa105209ff866921531f2fe24b77b96ea7daa667e3c48788b45f
3
+ size 5304