Hugging Face's logo

JackWong0911
/
timesformer-base-finetuned-k400-finetuned-kinetic400-subset-epoch6-num_frame_10_spatial_only

Video Classification
Transformers
TensorBoard
Safetensors
timesformer
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
JackWong0911 commited on
Commit
e3b824c
·
verified ·
1 Parent(s): 3c95b21

Training in progress, epoch 1

Browse files
Files changed (6) hide show
  1. all_results.json +8 -0
  2. model.safetensors +1 -1
  3. runs/Apr05_13-14-53_7b9369cb56cb/events.out.tfevents.1712323564.7b9369cb56cb.7949.9 +2 -2
  4. runs/Apr05_13-14-53_7b9369cb56cb/events.out.tfevents.1712323748.7b9369cb56cb.7949.10 +3 -0
  5. test_results.json +8 -0
  6. trainer_state.json +312 -0
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.17,
3
+ "eval_accuracy": 0.8235294117647058,
4
+ "eval_loss": 0.536857008934021,
5
+ "eval_runtime": 31.8618,
6
+ "eval_samples_per_second": 2.134,
7
+ "eval_steps_per_second": 2.134
8
+ }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a8260c01a7f7eeb61a6b094a3599a65bf230e11fb547ee946977e5fa6568821c
3
  size 343259388
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:680c111d326ae7bf5dd27385121df4a0dc44a35ded419babda71d13141d91c9f
3
  size 343259388
runs/Apr05_13-14-53_7b9369cb56cb/events.out.tfevents.1712323564.7b9369cb56cb.7949.9 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fe936fa186656f8a58eb9b507b9e8420266cbdf37cace78c56e0ac994586f8b2
3
- size 411
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e84cc87531dff568ffae0055dace649ecb170e154444f4155821de999042f52
3
+ size 734
runs/Apr05_13-14-53_7b9369cb56cb/events.out.tfevents.1712323748.7b9369cb56cb.7949.10 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b079d74884f7bb6005753991d05ad9fbe4fb305562987ca7d66c3f67160f7ac
3
+ size 32538
test_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.17,
3
+ "eval_accuracy": 0.8235294117647058,
4
+ "eval_loss": 0.536857008934021,
5
+ "eval_runtime": 31.8618,
6
+ "eval_samples_per_second": 2.134,
7
+ "eval_steps_per_second": 2.134
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,312 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8611111111111112,
3
+ "best_model_checkpoint": "timesformer-base-finetuned-k400-finetuned-kinetic400-subset-epoch6-num_frame_10_spatial_only/checkpoint-100",
4
+ "epoch": 5.166666666666667,
5
+ "eval_steps": 500,
6
+ "global_step": 300,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.03,
13
+ "grad_norm": 32.31907272338867,
14
+ "learning_rate": 1.6666666666666667e-05,
15
+ "loss": 1.6709,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.07,
20
+ "grad_norm": 31.60603904724121,
21
+ "learning_rate": 3.3333333333333335e-05,
22
+ "loss": 1.4509,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.1,
27
+ "grad_norm": 26.731109619140625,
28
+ "learning_rate": 5e-05,
29
+ "loss": 1.2292,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.13,
34
+ "grad_norm": 28.381160736083984,
35
+ "learning_rate": 4.814814814814815e-05,
36
+ "loss": 0.938,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.17,
41
+ "grad_norm": 8.430110931396484,
42
+ "learning_rate": 4.62962962962963e-05,
43
+ "loss": 0.7735,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.17,
48
+ "eval_accuracy": 0.7222222222222222,
49
+ "eval_loss": 0.7761979699134827,
50
+ "eval_runtime": 58.8413,
51
+ "eval_samples_per_second": 1.224,
52
+ "eval_steps_per_second": 1.224,
53
+ "step": 50
54
+ },
55
+ {
56
+ "epoch": 1.03,
57
+ "grad_norm": 7.695086479187012,
58
+ "learning_rate": 4.4444444444444447e-05,
59
+ "loss": 0.0949,
60
+ "step": 60
61
+ },
62
+ {
63
+ "epoch": 1.07,
64
+ "grad_norm": 0.16361366212368011,
65
+ "learning_rate": 4.259259259259259e-05,
66
+ "loss": 0.2414,
67
+ "step": 70
68
+ },
69
+ {
70
+ "epoch": 1.1,
71
+ "grad_norm": 0.19437631964683533,
72
+ "learning_rate": 4.074074074074074e-05,
73
+ "loss": 0.1627,
74
+ "step": 80
75
+ },
76
+ {
77
+ "epoch": 1.13,
78
+ "grad_norm": 23.58306121826172,
79
+ "learning_rate": 3.888888888888889e-05,
80
+ "loss": 0.674,
81
+ "step": 90
82
+ },
83
+ {
84
+ "epoch": 1.17,
85
+ "grad_norm": 0.047477759420871735,
86
+ "learning_rate": 3.7037037037037037e-05,
87
+ "loss": 0.1355,
88
+ "step": 100
89
+ },
90
+ {
91
+ "epoch": 1.17,
92
+ "eval_accuracy": 0.8611111111111112,
93
+ "eval_loss": 0.4255567789077759,
94
+ "eval_runtime": 57.9566,
95
+ "eval_samples_per_second": 1.242,
96
+ "eval_steps_per_second": 1.242,
97
+ "step": 100
98
+ },
99
+ {
100
+ "epoch": 2.03,
101
+ "grad_norm": 0.36428090929985046,
102
+ "learning_rate": 3.518518518518519e-05,
103
+ "loss": 0.2783,
104
+ "step": 110
105
+ },
106
+ {
107
+ "epoch": 2.07,
108
+ "grad_norm": 0.09045802056789398,
109
+ "learning_rate": 3.3333333333333335e-05,
110
+ "loss": 0.0191,
111
+ "step": 120
112
+ },
113
+ {
114
+ "epoch": 2.1,
115
+ "grad_norm": 0.11298607289791107,
116
+ "learning_rate": 3.148148148148148e-05,
117
+ "loss": 0.0392,
118
+ "step": 130
119
+ },
120
+ {
121
+ "epoch": 2.13,
122
+ "grad_norm": 0.1291336566209793,
123
+ "learning_rate": 2.962962962962963e-05,
124
+ "loss": 0.0113,
125
+ "step": 140
126
+ },
127
+ {
128
+ "epoch": 2.17,
129
+ "grad_norm": 0.06459435075521469,
130
+ "learning_rate": 2.777777777777778e-05,
131
+ "loss": 0.0014,
132
+ "step": 150
133
+ },
134
+ {
135
+ "epoch": 2.17,
136
+ "eval_accuracy": 0.8194444444444444,
137
+ "eval_loss": 0.5817016363143921,
138
+ "eval_runtime": 58.0229,
139
+ "eval_samples_per_second": 1.241,
140
+ "eval_steps_per_second": 1.241,
141
+ "step": 150
142
+ },
143
+ {
144
+ "epoch": 3.03,
145
+ "grad_norm": 0.023863501846790314,
146
+ "learning_rate": 2.5925925925925925e-05,
147
+ "loss": 0.071,
148
+ "step": 160
149
+ },
150
+ {
151
+ "epoch": 3.07,
152
+ "grad_norm": 0.033055633306503296,
153
+ "learning_rate": 2.4074074074074074e-05,
154
+ "loss": 0.0103,
155
+ "step": 170
156
+ },
157
+ {
158
+ "epoch": 3.1,
159
+ "grad_norm": 0.06424976140260696,
160
+ "learning_rate": 2.2222222222222223e-05,
161
+ "loss": 0.0079,
162
+ "step": 180
163
+ },
164
+ {
165
+ "epoch": 3.13,
166
+ "grad_norm": 0.019295834004878998,
167
+ "learning_rate": 2.037037037037037e-05,
168
+ "loss": 0.0015,
169
+ "step": 190
170
+ },
171
+ {
172
+ "epoch": 3.17,
173
+ "grad_norm": 0.02555103413760662,
174
+ "learning_rate": 1.8518518518518518e-05,
175
+ "loss": 0.001,
176
+ "step": 200
177
+ },
178
+ {
179
+ "epoch": 3.17,
180
+ "eval_accuracy": 0.8611111111111112,
181
+ "eval_loss": 0.4200752079486847,
182
+ "eval_runtime": 58.4996,
183
+ "eval_samples_per_second": 1.231,
184
+ "eval_steps_per_second": 1.231,
185
+ "step": 200
186
+ },
187
+ {
188
+ "epoch": 4.03,
189
+ "grad_norm": 5.690987586975098,
190
+ "learning_rate": 1.6666666666666667e-05,
191
+ "loss": 0.0113,
192
+ "step": 210
193
+ },
194
+ {
195
+ "epoch": 4.07,
196
+ "grad_norm": 0.04108642414212227,
197
+ "learning_rate": 1.4814814814814815e-05,
198
+ "loss": 0.0018,
199
+ "step": 220
200
+ },
201
+ {
202
+ "epoch": 4.1,
203
+ "grad_norm": 0.013796760700643063,
204
+ "learning_rate": 1.2962962962962962e-05,
205
+ "loss": 0.001,
206
+ "step": 230
207
+ },
208
+ {
209
+ "epoch": 4.13,
210
+ "grad_norm": 0.015395864844322205,
211
+ "learning_rate": 1.1111111111111112e-05,
212
+ "loss": 0.0212,
213
+ "step": 240
214
+ },
215
+ {
216
+ "epoch": 4.17,
217
+ "grad_norm": 0.038583505898714066,
218
+ "learning_rate": 9.259259259259259e-06,
219
+ "loss": 0.0013,
220
+ "step": 250
221
+ },
222
+ {
223
+ "epoch": 4.17,
224
+ "eval_accuracy": 0.8472222222222222,
225
+ "eval_loss": 0.38439834117889404,
226
+ "eval_runtime": 57.5706,
227
+ "eval_samples_per_second": 1.251,
228
+ "eval_steps_per_second": 1.251,
229
+ "step": 250
230
+ },
231
+ {
232
+ "epoch": 5.03,
233
+ "grad_norm": 0.7331423759460449,
234
+ "learning_rate": 7.4074074074074075e-06,
235
+ "loss": 0.0018,
236
+ "step": 260
237
+ },
238
+ {
239
+ "epoch": 5.07,
240
+ "grad_norm": 1.2412992715835571,
241
+ "learning_rate": 5.555555555555556e-06,
242
+ "loss": 0.0087,
243
+ "step": 270
244
+ },
245
+ {
246
+ "epoch": 5.1,
247
+ "grad_norm": 0.016475042328238487,
248
+ "learning_rate": 3.7037037037037037e-06,
249
+ "loss": 0.0006,
250
+ "step": 280
251
+ },
252
+ {
253
+ "epoch": 5.13,
254
+ "grad_norm": 0.012038950808346272,
255
+ "learning_rate": 1.8518518518518519e-06,
256
+ "loss": 0.047,
257
+ "step": 290
258
+ },
259
+ {
260
+ "epoch": 5.17,
261
+ "grad_norm": 0.020063335075974464,
262
+ "learning_rate": 0.0,
263
+ "loss": 0.0007,
264
+ "step": 300
265
+ },
266
+ {
267
+ "epoch": 5.17,
268
+ "eval_accuracy": 0.8611111111111112,
269
+ "eval_loss": 0.36808598041534424,
270
+ "eval_runtime": 58.1898,
271
+ "eval_samples_per_second": 1.237,
272
+ "eval_steps_per_second": 1.237,
273
+ "step": 300
274
+ },
275
+ {
276
+ "epoch": 5.17,
277
+ "step": 300,
278
+ "total_flos": 2.32503028660224e+17,
279
+ "train_loss": 0.26357639746895684,
280
+ "train_runtime": 573.7148,
281
+ "train_samples_per_second": 0.523,
282
+ "train_steps_per_second": 0.523
283
+ },
284
+ {
285
+ "epoch": 5.17,
286
+ "eval_accuracy": 0.8235294117647058,
287
+ "eval_loss": 0.536857008934021,
288
+ "eval_runtime": 34.3107,
289
+ "eval_samples_per_second": 1.982,
290
+ "eval_steps_per_second": 1.982,
291
+ "step": 300
292
+ },
293
+ {
294
+ "epoch": 5.17,
295
+ "eval_accuracy": 0.8235294117647058,
296
+ "eval_loss": 0.536857008934021,
297
+ "eval_runtime": 31.8618,
298
+ "eval_samples_per_second": 2.134,
299
+ "eval_steps_per_second": 2.134,
300
+ "step": 300
301
+ }
302
+ ],
303
+ "logging_steps": 10,
304
+ "max_steps": 300,
305
+ "num_input_tokens_seen": 0,
306
+ "num_train_epochs": 9223372036854775807,
307
+ "save_steps": 500,
308
+ "total_flos": 2.32503028660224e+17,
309
+ "train_batch_size": 1,
310
+ "trial_name": null,
311
+ "trial_params": null
312
+ }