jimypbr commited on
Commit
882b536
1 Parent(s): b8fbea0

End of training

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
all_results.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 100.0,
3
+ "eval_accuracy": 0.991421568627451,
4
+ "eval_loss": 0.08062744140625,
5
+ "eval_runtime": 5.6349,
6
+ "eval_samples_per_second": 1303.311,
7
+ "eval_steps_per_second": 4.792,
8
+ "train_loss": 0.4972930908203125,
9
+ "train_runtime": 820.6819,
10
+ "train_samples_per_second": 4242.326,
11
+ "train_steps_per_second": 0.487
12
+ }
config.json ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/vit-base-patch16-224-in21k",
3
+ "architectures": [
4
+ "PoptorchPipelinedViTForImageClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.0,
7
+ "encoder_stride": 16,
8
+ "finetuning_task": "image-classification",
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.0,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "airplane",
14
+ "1": "automobile",
15
+ "2": "bird",
16
+ "3": "cat",
17
+ "4": "deer",
18
+ "5": "dog",
19
+ "6": "frog",
20
+ "7": "horse",
21
+ "8": "ship",
22
+ "9": "truck"
23
+ },
24
+ "image_size": 224,
25
+ "initializer_range": 0.02,
26
+ "intermediate_size": 3072,
27
+ "label2id": {
28
+ "airplane": "0",
29
+ "automobile": "1",
30
+ "bird": "2",
31
+ "cat": "3",
32
+ "deer": "4",
33
+ "dog": "5",
34
+ "frog": "6",
35
+ "horse": "7",
36
+ "ship": "8",
37
+ "truck": "9"
38
+ },
39
+ "layer_norm_eps": 1e-12,
40
+ "model_type": "vit",
41
+ "num_attention_heads": 12,
42
+ "num_channels": 3,
43
+ "num_hidden_layers": 12,
44
+ "patch_size": 16,
45
+ "problem_type": "single_label_classification",
46
+ "qkv_bias": true,
47
+ "torch_dtype": "float16",
48
+ "transformers_version": "4.18.0"
49
+ }
eval_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 100.0,
3
+ "eval_accuracy": 0.991421568627451,
4
+ "eval_loss": 0.08062744140625,
5
+ "eval_runtime": 5.6349,
6
+ "eval_samples_per_second": 1303.311,
7
+ "eval_steps_per_second": 4.792
8
+ }
ipu_config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "device_iterations": 1,
3
+ "embedding_serialization_factor": 1,
4
+ "enable_half_first_order_momentum": true,
5
+ "enable_half_partials": true,
6
+ "executable_cache_dir": "./exe_cache",
7
+ "execute_encoder_on_cpu_for_generation": false,
8
+ "gradient_accumulation_steps": 128,
9
+ "inference_device_iterations": 4,
10
+ "inference_replication_factor": 4,
11
+ "ipus_per_replica": 4,
12
+ "layers_per_ipu": [
13
+ 3,
14
+ 3,
15
+ 3,
16
+ 3
17
+ ],
18
+ "matmul_proportion": [
19
+ 0.3
20
+ ],
21
+ "optimizer_state_offchip": true,
22
+ "optimum_version": "1.1.1",
23
+ "output_mode": "final",
24
+ "profile_dir": "",
25
+ "recompute_checkpoint_every_layer": true,
26
+ "replicated_tensor_sharding": true,
27
+ "replication_factor": 4,
28
+ "seed": 1337,
29
+ "sharded_execution_for_inference": false,
30
+ "transformers_version": "4.18.0",
31
+ "use_popdist": false
32
+ }
preprocessor_config.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_normalize": true,
3
+ "do_resize": true,
4
+ "feature_extractor_type": "ViTFeatureExtractor",
5
+ "image_mean": [
6
+ 0.5,
7
+ 0.5,
8
+ 0.5
9
+ ],
10
+ "image_std": [
11
+ 0.5,
12
+ 0.5,
13
+ 0.5
14
+ ],
15
+ "resample": 2,
16
+ "size": 224
17
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c1a5b816c77c323209956e4a7e94d42cc01dda0ceda26f8b00acd999cd88caf
3
+ size 171676081
runs/Jun29_15-30-10_gbnwp-pod015-2.ipu.graphcore.ai/1656513160.6009438/events.out.tfevents.1656513160.gbnwp-pod015-2.ipu.graphcore.ai ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f804a495ec240ebfe2ccadcdc8fbf184fb747f76f815d1bbd09b0c5d7dafb883
3
+ size 3932
runs/Jun29_15-30-10_gbnwp-pod015-2.ipu.graphcore.ai/events.out.tfevents.1656513160.gbnwp-pod015-2.ipu.graphcore.ai ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be928dac95ecd92a556c7adc352f3d7cd55812115d0bfbf3b1a338efd4e3312b
3
+ size 9937
runs/Jun29_15-30-10_gbnwp-pod015-2.ipu.graphcore.ai/events.out.tfevents.1656514106.gbnwp-pod015-2.ipu.graphcore.ai ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89527ca9feddecab0d2c8373e33f972bc8cf0a6fd17be4f301ce0fc085845373
3
+ size 40
train_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 100.0,
3
+ "train_loss": 0.4972930908203125,
4
+ "train_runtime": 820.6819,
5
+ "train_samples_per_second": 4242.326,
6
+ "train_steps_per_second": 0.487
7
+ }
trainer_state.json ADDED
@@ -0,0 +1,266 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 100.0,
5
+ "global_step": 400,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 2.5,
12
+ "learning_rate": 1e-05,
13
+ "loss": 2.2814,
14
+ "step": 10
15
+ },
16
+ {
17
+ "epoch": 5.0,
18
+ "learning_rate": 2e-05,
19
+ "loss": 2.2162,
20
+ "step": 20
21
+ },
22
+ {
23
+ "epoch": 7.5,
24
+ "learning_rate": 3e-05,
25
+ "loss": 2.06,
26
+ "step": 30
27
+ },
28
+ {
29
+ "epoch": 10.0,
30
+ "learning_rate": 4e-05,
31
+ "loss": 1.7632,
32
+ "step": 40
33
+ },
34
+ {
35
+ "epoch": 12.5,
36
+ "learning_rate": 5e-05,
37
+ "loss": 1.3906,
38
+ "step": 50
39
+ },
40
+ {
41
+ "epoch": 15.0,
42
+ "learning_rate": 6e-05,
43
+ "loss": 1.0958,
44
+ "step": 60
45
+ },
46
+ {
47
+ "epoch": 17.5,
48
+ "learning_rate": 7e-05,
49
+ "loss": 0.8168,
50
+ "step": 70
51
+ },
52
+ {
53
+ "epoch": 20.0,
54
+ "learning_rate": 8e-05,
55
+ "loss": 0.6212,
56
+ "step": 80
57
+ },
58
+ {
59
+ "epoch": 22.5,
60
+ "learning_rate": 9e-05,
61
+ "loss": 0.5377,
62
+ "step": 90
63
+ },
64
+ {
65
+ "epoch": 25.0,
66
+ "learning_rate": 0.0001,
67
+ "loss": 0.4409,
68
+ "step": 100
69
+ },
70
+ {
71
+ "epoch": 27.5,
72
+ "learning_rate": 9.972609476841367e-05,
73
+ "loss": 0.4009,
74
+ "step": 110
75
+ },
76
+ {
77
+ "epoch": 30.0,
78
+ "learning_rate": 9.890738003669029e-05,
79
+ "loss": 0.3598,
80
+ "step": 120
81
+ },
82
+ {
83
+ "epoch": 32.5,
84
+ "learning_rate": 9.755282581475769e-05,
85
+ "loss": 0.2784,
86
+ "step": 130
87
+ },
88
+ {
89
+ "epoch": 35.0,
90
+ "learning_rate": 9.567727288213005e-05,
91
+ "loss": 0.3299,
92
+ "step": 140
93
+ },
94
+ {
95
+ "epoch": 37.5,
96
+ "learning_rate": 9.330127018922194e-05,
97
+ "loss": 0.3236,
98
+ "step": 150
99
+ },
100
+ {
101
+ "epoch": 40.0,
102
+ "learning_rate": 9.045084971874738e-05,
103
+ "loss": 0.2714,
104
+ "step": 160
105
+ },
106
+ {
107
+ "epoch": 42.5,
108
+ "learning_rate": 8.715724127386972e-05,
109
+ "loss": 0.2654,
110
+ "step": 170
111
+ },
112
+ {
113
+ "epoch": 45.0,
114
+ "learning_rate": 8.345653031794292e-05,
115
+ "loss": 0.254,
116
+ "step": 180
117
+ },
118
+ {
119
+ "epoch": 47.5,
120
+ "learning_rate": 7.938926261462366e-05,
121
+ "loss": 0.2223,
122
+ "step": 190
123
+ },
124
+ {
125
+ "epoch": 50.0,
126
+ "learning_rate": 7.500000000000001e-05,
127
+ "loss": 0.2671,
128
+ "step": 200
129
+ },
130
+ {
131
+ "epoch": 52.5,
132
+ "learning_rate": 7.033683215379002e-05,
133
+ "loss": 0.2293,
134
+ "step": 210
135
+ },
136
+ {
137
+ "epoch": 55.0,
138
+ "learning_rate": 6.545084971874738e-05,
139
+ "loss": 0.2235,
140
+ "step": 220
141
+ },
142
+ {
143
+ "epoch": 57.5,
144
+ "learning_rate": 6.0395584540887963e-05,
145
+ "loss": 0.2031,
146
+ "step": 230
147
+ },
148
+ {
149
+ "epoch": 60.0,
150
+ "learning_rate": 5.522642316338268e-05,
151
+ "loss": 0.2034,
152
+ "step": 240
153
+ },
154
+ {
155
+ "epoch": 62.5,
156
+ "learning_rate": 5e-05,
157
+ "loss": 0.189,
158
+ "step": 250
159
+ },
160
+ {
161
+ "epoch": 65.0,
162
+ "learning_rate": 4.477357683661734e-05,
163
+ "loss": 0.1788,
164
+ "step": 260
165
+ },
166
+ {
167
+ "epoch": 67.5,
168
+ "learning_rate": 3.960441545911204e-05,
169
+ "loss": 0.1698,
170
+ "step": 270
171
+ },
172
+ {
173
+ "epoch": 70.0,
174
+ "learning_rate": 3.4549150281252636e-05,
175
+ "loss": 0.2309,
176
+ "step": 280
177
+ },
178
+ {
179
+ "epoch": 72.5,
180
+ "learning_rate": 2.9663167846209998e-05,
181
+ "loss": 0.1637,
182
+ "step": 290
183
+ },
184
+ {
185
+ "epoch": 75.0,
186
+ "learning_rate": 2.500000000000001e-05,
187
+ "loss": 0.1669,
188
+ "step": 300
189
+ },
190
+ {
191
+ "epoch": 77.5,
192
+ "learning_rate": 2.061073738537635e-05,
193
+ "loss": 0.1786,
194
+ "step": 310
195
+ },
196
+ {
197
+ "epoch": 80.0,
198
+ "learning_rate": 1.6543469682057106e-05,
199
+ "loss": 0.1792,
200
+ "step": 320
201
+ },
202
+ {
203
+ "epoch": 82.5,
204
+ "learning_rate": 1.2842758726130283e-05,
205
+ "loss": 0.1874,
206
+ "step": 330
207
+ },
208
+ {
209
+ "epoch": 85.0,
210
+ "learning_rate": 9.549150281252633e-06,
211
+ "loss": 0.1805,
212
+ "step": 340
213
+ },
214
+ {
215
+ "epoch": 87.5,
216
+ "learning_rate": 6.698729810778065e-06,
217
+ "loss": 0.196,
218
+ "step": 350
219
+ },
220
+ {
221
+ "epoch": 90.0,
222
+ "learning_rate": 4.322727117869951e-06,
223
+ "loss": 0.1615,
224
+ "step": 360
225
+ },
226
+ {
227
+ "epoch": 92.5,
228
+ "learning_rate": 2.4471741852423237e-06,
229
+ "loss": 0.1481,
230
+ "step": 370
231
+ },
232
+ {
233
+ "epoch": 95.0,
234
+ "learning_rate": 1.0926199633097157e-06,
235
+ "loss": 0.1633,
236
+ "step": 380
237
+ },
238
+ {
239
+ "epoch": 97.5,
240
+ "learning_rate": 2.7390523158633554e-07,
241
+ "loss": 0.1673,
242
+ "step": 390
243
+ },
244
+ {
245
+ "epoch": 100.0,
246
+ "learning_rate": 0.0,
247
+ "loss": 0.1748,
248
+ "step": 400
249
+ },
250
+ {
251
+ "epoch": 100.0,
252
+ "step": 400,
253
+ "total_flos": 1.3814551337974377e+23,
254
+ "train_loss": 0.4972930908203125,
255
+ "train_runtime": 820.6819,
256
+ "train_samples_per_second": 4242.326,
257
+ "train_steps_per_second": 0.487
258
+ }
259
+ ],
260
+ "max_steps": 400,
261
+ "num_train_epochs": 100,
262
+ "start_time": 1656513160.5917685,
263
+ "total_flos": 1.3814551337974377e+23,
264
+ "trial_name": null,
265
+ "trial_params": null
266
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c65d55748ded654a5268d5d3306f7d9bc246dcf963ea6627514b18c0c2311c3
3
+ size 2735