Hugging Face's logo

Augusto777
/
swinv2-tiny-patch4-window8-256-RD-aptos19

TensorBoard
Safetensors
swinv2
Generated from Trainer
Eval Results
Model card Files Metrics Community
Augusto777 commited on
Commit
19af606
·
verified ·
1 Parent(s): 30ff47f

End of training

Browse files
Files changed (10) hide show
  1. README.md +38 -43
  2. all_results.json +10 -10
  3. config.json +8 -4
  4. eval_results.json +6 -6
  5. model.safetensors +2 -2
  6. runs/Dec01_09-53-19_DESKTOP-SKBE9FB/events.out.tfevents.1733068401.DESKTOP-SKBE9FB.14448.0 +3 -0
  7. runs/Dec01_09-53-19_DESKTOP-SKBE9FB/events.out.tfevents.1733068593.DESKTOP-SKBE9FB.14448.1 +3 -0
  8. train_results.json +5 -5
  9. trainer_state.json +302 -467
  10. training_args.bin +1 -1
README.md CHANGED
@@ -22,7 +22,7 @@ model-index:
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
- value: 0.616822429906542
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -32,8 +32,8 @@ should probably proofread and complete it, then remove this comment. -->
32
 
33
  This model is a fine-tuned version of [microsoft/swinv2-tiny-patch4-window8-256](https://huggingface.co/microsoft/swinv2-tiny-patch4-window8-256) on the imagefolder dataset.
34
  It achieves the following results on the evaluation set:
35
- - Loss: 0.6580
36
- - Accuracy: 0.6168
37
 
38
  ## Model description
39
 
@@ -67,46 +67,41 @@ The following hyperparameters were used during training:
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
70
- | No log | 1.0 | 8 | 4.5659 | 0.4112 |
71
- | 4.5175 | 2.0 | 16 | 3.6471 | 0.4112 |
72
- | 3.927 | 3.0 | 24 | 1.6286 | 0.4112 |
73
- | 1.6081 | 4.0 | 32 | 0.6781 | 0.5888 |
74
- | 0.7702 | 5.0 | 40 | 0.8357 | 0.5888 |
75
- | 0.7702 | 6.0 | 48 | 0.6766 | 0.5888 |
76
- | 0.7502 | 7.0 | 56 | 0.7522 | 0.4112 |
77
- | 0.7266 | 8.0 | 64 | 0.6792 | 0.5888 |
78
- | 0.6954 | 9.0 | 72 | 0.6881 | 0.5888 |
79
- | 0.6808 | 10.0 | 80 | 0.6780 | 0.5888 |
80
- | 0.6808 | 11.0 | 88 | 0.7130 | 0.5888 |
81
- | 0.7068 | 12.0 | 96 | 0.6771 | 0.5888 |
82
- | 0.6792 | 13.0 | 104 | 0.6779 | 0.5888 |
83
- | 0.6841 | 14.0 | 112 | 0.6766 | 0.5888 |
84
- | 0.6777 | 15.0 | 120 | 0.6861 | 0.5888 |
85
- | 0.6777 | 16.0 | 128 | 0.6773 | 0.5888 |
86
- | 0.6818 | 17.0 | 136 | 0.6806 | 0.5888 |
87
- | 0.6747 | 18.0 | 144 | 0.6929 | 0.5888 |
88
- | 0.6814 | 19.0 | 152 | 0.6767 | 0.5888 |
89
- | 0.6714 | 20.0 | 160 | 0.6745 | 0.5888 |
90
- | 0.6714 | 21.0 | 168 | 0.6852 | 0.5888 |
91
- | 0.6765 | 22.0 | 176 | 0.6816 | 0.5514 |
92
- | 0.6822 | 23.0 | 184 | 0.6983 | 0.5888 |
93
- | 0.6816 | 24.0 | 192 | 0.6706 | 0.5888 |
94
- | 0.6868 | 25.0 | 200 | 0.6982 | 0.5701 |
95
- | 0.6868 | 26.0 | 208 | 0.6878 | 0.5701 |
96
- | 0.6724 | 27.0 | 216 | 0.6785 | 0.5888 |
97
- | 0.6613 | 28.0 | 224 | 0.6843 | 0.5888 |
98
- | 0.6501 | 29.0 | 232 | 0.7126 | 0.5888 |
99
- | 0.6566 | 30.0 | 240 | 0.6917 | 0.5701 |
100
- | 0.6566 | 31.0 | 248 | 0.7020 | 0.5607 |
101
- | 0.6583 | 32.0 | 256 | 0.6782 | 0.5888 |
102
- | 0.6501 | 33.0 | 264 | 0.6647 | 0.5888 |
103
- | 0.654 | 34.0 | 272 | 0.6603 | 0.5981 |
104
- | 0.6604 | 35.0 | 280 | 0.6873 | 0.5794 |
105
- | 0.6604 | 36.0 | 288 | 0.6591 | 0.5794 |
106
- | 0.6456 | 37.0 | 296 | 0.6580 | 0.6168 |
107
- | 0.6483 | 38.0 | 304 | 0.6702 | 0.5981 |
108
- | 0.6151 | 39.0 | 312 | 0.6785 | 0.5981 |
109
- | 0.6291 | 40.0 | 320 | 0.6806 | 0.5981 |
110
 
111
 
112
  ### Framework versions
 
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
+ value: 0.4782608695652174
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
32
 
33
  This model is a fine-tuned version of [microsoft/swinv2-tiny-patch4-window8-256](https://huggingface.co/microsoft/swinv2-tiny-patch4-window8-256) on the imagefolder dataset.
34
  It achieves the following results on the evaluation set:
35
+ - Loss: 1.1496
36
+ - Accuracy: 0.4783
37
 
38
  ## Model description
39
 
 
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
70
+ | No log | 0.86 | 3 | 7.9281 | 0.1087 |
71
+ | No log | 2.0 | 7 | 7.6171 | 0.1087 |
72
+ | 7.7567 | 2.86 | 10 | 6.5765 | 0.1087 |
73
+ | 7.7567 | 4.0 | 14 | 4.1867 | 0.1087 |
74
+ | 7.7567 | 4.86 | 17 | 2.5570 | 0.1087 |
75
+ | 4.0833 | 6.0 | 21 | 1.5007 | 0.4565 |
76
+ | 4.0833 | 6.86 | 24 | 1.2815 | 0.4565 |
77
+ | 4.0833 | 8.0 | 28 | 1.2261 | 0.4565 |
78
+ | 1.3508 | 8.86 | 31 | 1.3183 | 0.3261 |
79
+ | 1.3508 | 10.0 | 35 | 1.2317 | 0.4565 |
80
+ | 1.3508 | 10.86 | 38 | 1.2423 | 0.4565 |
81
+ | 1.2181 | 12.0 | 42 | 1.2674 | 0.4565 |
82
+ | 1.2181 | 12.86 | 45 | 1.2563 | 0.4565 |
83
+ | 1.2181 | 14.0 | 49 | 1.2323 | 0.4565 |
84
+ | 1.2726 | 14.86 | 52 | 1.2210 | 0.4565 |
85
+ | 1.2726 | 16.0 | 56 | 1.2288 | 0.4565 |
86
+ | 1.2726 | 16.86 | 59 | 1.2345 | 0.4565 |
87
+ | 1.2059 | 18.0 | 63 | 1.2165 | 0.4565 |
88
+ | 1.2059 | 18.86 | 66 | 1.2282 | 0.4565 |
89
+ | 1.2036 | 20.0 | 70 | 1.2004 | 0.4565 |
90
+ | 1.2036 | 20.86 | 73 | 1.2020 | 0.4565 |
91
+ | 1.2036 | 22.0 | 77 | 1.2049 | 0.4565 |
92
+ | 1.1678 | 22.86 | 80 | 1.2028 | 0.4565 |
93
+ | 1.1678 | 24.0 | 84 | 1.1945 | 0.4565 |
94
+ | 1.1678 | 24.86 | 87 | 1.1906 | 0.4565 |
95
+ | 1.1522 | 26.0 | 91 | 1.1865 | 0.4565 |
96
+ | 1.1522 | 26.86 | 94 | 1.1812 | 0.4565 |
97
+ | 1.1522 | 28.0 | 98 | 1.1760 | 0.4565 |
98
+ | 1.1451 | 28.86 | 101 | 1.1714 | 0.4565 |
99
+ | 1.1451 | 30.0 | 105 | 1.1713 | 0.4565 |
100
+ | 1.1451 | 30.86 | 108 | 1.1578 | 0.4565 |
101
+ | 1.1252 | 32.0 | 112 | 1.1496 | 0.4783 |
102
+ | 1.1252 | 32.86 | 115 | 1.1471 | 0.4783 |
103
+ | 1.1252 | 34.0 | 119 | 1.1465 | 0.4565 |
104
+ | 1.126 | 34.29 | 120 | 1.1464 | 0.4565 |
 
 
 
 
 
105
 
106
 
107
  ### Framework versions
all_results.json CHANGED
@@ -1,12 +1,12 @@
1
  {
2
- "epoch": 40.0,
3
- "eval_accuracy": 0.616822429906542,
4
- "eval_loss": 0.6579955816268921,
5
- "eval_runtime": 2.141,
6
- "eval_samples_per_second": 49.976,
7
- "eval_steps_per_second": 3.269,
8
- "train_loss": 0.9269241958856582,
9
- "train_runtime": 591.2866,
10
- "train_samples_per_second": 33.689,
11
- "train_steps_per_second": 0.541
12
  }
 
1
  {
2
+ "epoch": 34.29,
3
+ "eval_accuracy": 0.4782608695652174,
4
+ "eval_loss": 1.1496002674102783,
5
+ "eval_runtime": 0.7277,
6
+ "eval_samples_per_second": 63.215,
7
+ "eval_steps_per_second": 4.123,
8
+ "train_loss": 1.9839425007502238,
9
+ "train_runtime": 191.8806,
10
+ "train_samples_per_second": 44.403,
11
+ "train_steps_per_second": 0.625
12
  }
config.json CHANGED
@@ -17,14 +17,18 @@
17
  "hidden_dropout_prob": 0.0,
18
  "hidden_size": 768,
19
  "id2label": {
20
- "0": "HR",
21
- "1": "No HR"
 
 
22
  },
23
  "image_size": 256,
24
  "initializer_range": 0.02,
25
  "label2id": {
26
- "HR": 0,
27
- "No HR": 1
 
 
28
  },
29
  "layer_norm_eps": 1e-05,
30
  "mlp_ratio": 4.0,
 
17
  "hidden_dropout_prob": 0.0,
18
  "hidden_size": 768,
19
  "id2label": {
20
+ "0": "avanzada",
21
+ "1": "leve",
22
+ "2": "moderada",
23
+ "3": "no dmae"
24
  },
25
  "image_size": 256,
26
  "initializer_range": 0.02,
27
  "label2id": {
28
+ "avanzada": 0,
29
+ "leve": 1,
30
+ "moderada": 2,
31
+ "no dmae": 3
32
  },
33
  "layer_norm_eps": 1e-05,
34
  "mlp_ratio": 4.0,
eval_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
- "epoch": 40.0,
3
- "eval_accuracy": 0.616822429906542,
4
- "eval_loss": 0.6579955816268921,
5
- "eval_runtime": 2.141,
6
- "eval_samples_per_second": 49.976,
7
- "eval_steps_per_second": 3.269
8
  }
 
1
  {
2
+ "epoch": 34.29,
3
+ "eval_accuracy": 0.4782608695652174,
4
+ "eval_loss": 1.1496002674102783,
5
+ "eval_runtime": 0.7277,
6
+ "eval_samples_per_second": 63.215,
7
+ "eval_steps_per_second": 4.123
8
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:691a7da7dff5da0f33c5a07a6d3ca99d97e130cf310c3632dabed4a981c7d394
3
- size 110350128
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2bbafaf79288bb55851f0a6aa95877e24c2692f513bdc340d3dcf3a0a78aa4a4
3
+ size 110356296
runs/Dec01_09-53-19_DESKTOP-SKBE9FB/events.out.tfevents.1733068401.DESKTOP-SKBE9FB.14448.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ec56d52c679c6e9c19c88cdff6593358e4f282fe84d75a0ace050873283190f
3
+ size 18103
runs/Dec01_09-53-19_DESKTOP-SKBE9FB/events.out.tfevents.1733068593.DESKTOP-SKBE9FB.14448.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef5882a3a779f6c2aac1064d34bc3e88664610a5b979d1f1b2ef5132bf8b1286
3
+ size 405
train_results.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
- "epoch": 40.0,
3
- "train_loss": 0.9269241958856582,
4
- "train_runtime": 591.2866,
5
- "train_samples_per_second": 33.689,
6
- "train_steps_per_second": 0.541
7
  }
 
1
  {
2
+ "epoch": 34.29,
3
+ "train_loss": 1.9839425007502238,
4
+ "train_runtime": 191.8806,
5
+ "train_samples_per_second": 44.403,
6
+ "train_steps_per_second": 0.625
7
  }
trainer_state.json CHANGED
@@ -1,581 +1,416 @@
1
  {
2
- "best_metric": 0.616822429906542,
3
- "best_model_checkpoint": "swinv2-tiny-patch4-window8-256-RD-aptos19\\checkpoint-296",
4
- "epoch": 40.0,
5
  "eval_steps": 500,
6
- "global_step": 320,
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": 0.411214953271028,
14
- "eval_loss": 4.565852165222168,
15
- "eval_runtime": 2.7444,
16
- "eval_samples_per_second": 38.988,
17
- "eval_steps_per_second": 2.551,
18
- "step": 8
19
- },
20
- {
21
- "epoch": 1.25,
22
- "learning_rate": 4.6874999999999994e-05,
23
- "loss": 4.5175,
24
- "step": 10
25
  },
26
  {
27
  "epoch": 2.0,
28
- "eval_accuracy": 0.411214953271028,
29
- "eval_loss": 3.647094964981079,
30
- "eval_runtime": 1.9164,
31
- "eval_samples_per_second": 55.833,
32
- "eval_steps_per_second": 3.653,
33
- "step": 16
34
  },
35
  {
36
- "epoch": 2.5,
37
- "learning_rate": 9.374999999999999e-05,
38
- "loss": 3.927,
39
- "step": 20
40
- },
41
- {
42
- "epoch": 3.0,
43
- "eval_accuracy": 0.411214953271028,
44
- "eval_loss": 1.6286081075668335,
45
- "eval_runtime": 1.9645,
46
- "eval_samples_per_second": 54.468,
47
- "eval_steps_per_second": 3.563,
48
- "step": 24
49
  },
50
  {
51
- "epoch": 3.75,
52
- "learning_rate": 0.000140625,
53
- "loss": 1.6081,
54
- "step": 30
 
 
 
55
  },
56
  {
57
  "epoch": 4.0,
58
- "eval_accuracy": 0.5887850467289719,
59
- "eval_loss": 0.6780943274497986,
60
- "eval_runtime": 1.9235,
61
- "eval_samples_per_second": 55.629,
62
- "eval_steps_per_second": 3.639,
63
- "step": 32
64
- },
65
- {
66
- "epoch": 5.0,
67
- "learning_rate": 0.00014583333333333332,
68
- "loss": 0.7702,
69
- "step": 40
70
- },
71
- {
72
- "epoch": 5.0,
73
- "eval_accuracy": 0.5887850467289719,
74
- "eval_loss": 0.8356828689575195,
75
- "eval_runtime": 2.0574,
76
- "eval_samples_per_second": 52.007,
77
- "eval_steps_per_second": 3.402,
78
- "step": 40
79
  },
80
  {
81
  "epoch": 6.0,
82
- "eval_accuracy": 0.5887850467289719,
83
- "eval_loss": 0.6765593886375427,
84
- "eval_runtime": 1.9495,
85
- "eval_samples_per_second": 54.887,
86
- "eval_steps_per_second": 3.591,
87
- "step": 48
88
- },
89
- {
90
- "epoch": 6.25,
91
- "learning_rate": 0.000140625,
92
- "loss": 0.7502,
93
- "step": 50
94
- },
95
- {
96
- "epoch": 7.0,
97
- "eval_accuracy": 0.411214953271028,
98
- "eval_loss": 0.7522286176681519,
99
- "eval_runtime": 2.091,
100
- "eval_samples_per_second": 51.172,
101
- "eval_steps_per_second": 3.348,
102
- "step": 56
103
- },
104
- {
105
- "epoch": 7.5,
106
- "learning_rate": 0.00013541666666666666,
107
- "loss": 0.7266,
108
- "step": 60
109
  },
110
  {
111
  "epoch": 8.0,
112
- "eval_accuracy": 0.5887850467289719,
113
- "eval_loss": 0.679230809211731,
114
- "eval_runtime": 2.0074,
115
- "eval_samples_per_second": 53.301,
116
- "eval_steps_per_second": 3.487,
117
- "step": 64
118
- },
119
- {
120
- "epoch": 8.75,
121
- "learning_rate": 0.00013020833333333333,
122
- "loss": 0.6954,
123
- "step": 70
124
  },
125
  {
126
- "epoch": 9.0,
127
- "eval_accuracy": 0.5887850467289719,
128
- "eval_loss": 0.6881440877914429,
129
- "eval_runtime": 1.8339,
130
- "eval_samples_per_second": 58.345,
131
- "eval_steps_per_second": 3.817,
132
- "step": 72
133
- },
134
- {
135
- "epoch": 10.0,
136
  "learning_rate": 0.000125,
137
- "loss": 0.6808,
138
- "step": 80
139
- },
140
- {
141
- "epoch": 10.0,
142
- "eval_accuracy": 0.5887850467289719,
143
- "eval_loss": 0.6780060529708862,
144
- "eval_runtime": 1.8679,
145
- "eval_samples_per_second": 57.282,
146
- "eval_steps_per_second": 3.747,
147
- "step": 80
148
  },
149
  {
150
- "epoch": 11.0,
151
- "eval_accuracy": 0.5887850467289719,
152
- "eval_loss": 0.7129637598991394,
153
- "eval_runtime": 2.0595,
154
- "eval_samples_per_second": 51.955,
155
- "eval_steps_per_second": 3.399,
156
- "step": 88
157
  },
158
  {
159
- "epoch": 11.25,
160
- "learning_rate": 0.00011979166666666666,
161
- "loss": 0.7068,
162
- "step": 90
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
163
  },
164
  {
165
  "epoch": 12.0,
166
- "eval_accuracy": 0.5887850467289719,
167
- "eval_loss": 0.6770886778831482,
168
- "eval_runtime": 1.8579,
169
- "eval_samples_per_second": 57.591,
170
- "eval_steps_per_second": 3.768,
171
- "step": 96
172
  },
173
  {
174
- "epoch": 12.5,
175
- "learning_rate": 0.00011458333333333332,
176
- "loss": 0.6792,
177
- "step": 100
178
- },
179
- {
180
- "epoch": 13.0,
181
- "eval_accuracy": 0.5887850467289719,
182
- "eval_loss": 0.6779045462608337,
183
- "eval_runtime": 1.9391,
184
- "eval_samples_per_second": 55.179,
185
- "eval_steps_per_second": 3.61,
186
- "step": 104
187
- },
188
- {
189
- "epoch": 13.75,
190
- "learning_rate": 0.00010937499999999999,
191
- "loss": 0.6841,
192
- "step": 110
193
  },
194
  {
195
  "epoch": 14.0,
196
- "eval_accuracy": 0.5887850467289719,
197
- "eval_loss": 0.6766365170478821,
198
- "eval_runtime": 2.0285,
199
- "eval_samples_per_second": 52.749,
200
- "eval_steps_per_second": 3.451,
201
- "step": 112
202
  },
203
  {
204
- "epoch": 15.0,
205
- "learning_rate": 0.00010416666666666666,
206
- "loss": 0.6777,
207
- "step": 120
208
  },
209
  {
210
- "epoch": 15.0,
211
- "eval_accuracy": 0.5887850467289719,
212
- "eval_loss": 0.6860565543174744,
213
- "eval_runtime": 2.0915,
214
- "eval_samples_per_second": 51.159,
215
- "eval_steps_per_second": 3.347,
216
- "step": 120
217
  },
218
  {
219
  "epoch": 16.0,
220
- "eval_accuracy": 0.5887850467289719,
221
- "eval_loss": 0.6773396134376526,
222
- "eval_runtime": 1.948,
223
- "eval_samples_per_second": 54.928,
224
- "eval_steps_per_second": 3.593,
225
- "step": 128
226
- },
227
- {
228
- "epoch": 16.25,
229
- "learning_rate": 9.895833333333332e-05,
230
- "loss": 0.6818,
231
- "step": 130
232
  },
233
  {
234
- "epoch": 17.0,
235
- "eval_accuracy": 0.5887850467289719,
236
- "eval_loss": 0.6805893182754517,
237
- "eval_runtime": 1.8914,
238
- "eval_samples_per_second": 56.57,
239
- "eval_steps_per_second": 3.701,
240
- "step": 136
241
  },
242
  {
243
- "epoch": 17.5,
244
- "learning_rate": 9.374999999999999e-05,
245
- "loss": 0.6747,
246
- "step": 140
247
  },
248
  {
249
  "epoch": 18.0,
250
- "eval_accuracy": 0.5887850467289719,
251
- "eval_loss": 0.6928897500038147,
252
- "eval_runtime": 1.9231,
253
- "eval_samples_per_second": 55.639,
254
- "eval_steps_per_second": 3.64,
255
- "step": 144
256
  },
257
  {
258
- "epoch": 18.75,
259
- "learning_rate": 8.854166666666666e-05,
260
- "loss": 0.6814,
261
- "step": 150
262
- },
263
- {
264
- "epoch": 19.0,
265
- "eval_accuracy": 0.5887850467289719,
266
- "eval_loss": 0.6767390370368958,
267
- "eval_runtime": 1.8514,
268
- "eval_samples_per_second": 57.793,
269
- "eval_steps_per_second": 3.781,
270
- "step": 152
271
  },
272
  {
273
  "epoch": 20.0,
274
- "learning_rate": 8.333333333333333e-05,
275
- "loss": 0.6714,
276
- "step": 160
277
  },
278
  {
279
  "epoch": 20.0,
280
- "eval_accuracy": 0.5887850467289719,
281
- "eval_loss": 0.6744682788848877,
282
- "eval_runtime": 1.9225,
283
- "eval_samples_per_second": 55.658,
284
- "eval_steps_per_second": 3.641,
285
- "step": 160
286
- },
287
- {
288
- "epoch": 21.0,
289
- "eval_accuracy": 0.5887850467289719,
290
- "eval_loss": 0.6852397322654724,
291
- "eval_runtime": 1.91,
292
- "eval_samples_per_second": 56.022,
293
- "eval_steps_per_second": 3.665,
294
- "step": 168
295
  },
296
  {
297
- "epoch": 21.25,
298
- "learning_rate": 7.8125e-05,
299
- "loss": 0.6765,
300
- "step": 170
 
 
 
301
  },
302
  {
303
  "epoch": 22.0,
304
- "eval_accuracy": 0.5514018691588785,
305
- "eval_loss": 0.6815980672836304,
306
- "eval_runtime": 1.932,
307
- "eval_samples_per_second": 55.384,
308
- "eval_steps_per_second": 3.623,
309
- "step": 176
310
  },
311
  {
312
- "epoch": 22.5,
313
- "learning_rate": 7.291666666666666e-05,
314
- "loss": 0.6822,
315
- "step": 180
316
- },
317
- {
318
- "epoch": 23.0,
319
- "eval_accuracy": 0.5887850467289719,
320
- "eval_loss": 0.6982948184013367,
321
- "eval_runtime": 1.964,
322
- "eval_samples_per_second": 54.482,
323
- "eval_steps_per_second": 3.564,
324
- "step": 184
325
  },
326
  {
327
- "epoch": 23.75,
328
- "learning_rate": 6.770833333333333e-05,
329
- "loss": 0.6816,
330
- "step": 190
 
 
 
331
  },
332
  {
333
  "epoch": 24.0,
334
- "eval_accuracy": 0.5887850467289719,
335
- "eval_loss": 0.6706489324569702,
336
- "eval_runtime": 1.8679,
337
- "eval_samples_per_second": 57.282,
338
- "eval_steps_per_second": 3.747,
339
- "step": 192
340
  },
341
  {
342
- "epoch": 25.0,
343
- "learning_rate": 6.25e-05,
344
- "loss": 0.6868,
345
- "step": 200
 
 
 
346
  },
347
  {
348
- "epoch": 25.0,
349
- "eval_accuracy": 0.5700934579439252,
350
- "eval_loss": 0.6981963515281677,
351
- "eval_runtime": 1.8699,
352
- "eval_samples_per_second": 57.221,
353
- "eval_steps_per_second": 3.743,
354
- "step": 200
355
  },
356
  {
357
  "epoch": 26.0,
358
- "eval_accuracy": 0.5700934579439252,
359
- "eval_loss": 0.687846839427948,
360
- "eval_runtime": 1.861,
361
- "eval_samples_per_second": 57.497,
362
- "eval_steps_per_second": 3.762,
363
- "step": 208
364
- },
365
- {
366
- "epoch": 26.25,
367
- "learning_rate": 5.729166666666666e-05,
368
- "loss": 0.6724,
369
- "step": 210
370
- },
371
- {
372
- "epoch": 27.0,
373
- "eval_accuracy": 0.5887850467289719,
374
- "eval_loss": 0.678459107875824,
375
- "eval_runtime": 2.0455,
376
- "eval_samples_per_second": 52.31,
377
- "eval_steps_per_second": 3.422,
378
- "step": 216
379
  },
380
  {
381
- "epoch": 27.5,
382
- "learning_rate": 5.208333333333333e-05,
383
- "loss": 0.6613,
384
- "step": 220
 
 
 
385
  },
386
  {
387
  "epoch": 28.0,
388
- "eval_accuracy": 0.5887850467289719,
389
- "eval_loss": 0.6843389272689819,
390
- "eval_runtime": 1.9034,
391
- "eval_samples_per_second": 56.214,
392
- "eval_steps_per_second": 3.678,
393
- "step": 224
394
  },
395
  {
396
- "epoch": 28.75,
397
- "learning_rate": 4.6874999999999994e-05,
398
- "loss": 0.6501,
399
- "step": 230
400
- },
401
- {
402
- "epoch": 29.0,
403
- "eval_accuracy": 0.5887850467289719,
404
- "eval_loss": 0.7126495242118835,
405
- "eval_runtime": 1.8679,
406
- "eval_samples_per_second": 57.283,
407
- "eval_steps_per_second": 3.747,
408
- "step": 232
409
  },
410
  {
411
- "epoch": 30.0,
412
- "learning_rate": 4.1666666666666665e-05,
413
- "loss": 0.6566,
414
- "step": 240
 
 
 
415
  },
416
  {
417
  "epoch": 30.0,
418
- "eval_accuracy": 0.5700934579439252,
419
- "eval_loss": 0.6917204260826111,
420
- "eval_runtime": 1.9,
421
- "eval_samples_per_second": 56.317,
422
- "eval_steps_per_second": 3.684,
423
- "step": 240
424
- },
425
- {
426
- "epoch": 31.0,
427
- "eval_accuracy": 0.5607476635514018,
428
- "eval_loss": 0.7020335793495178,
429
- "eval_runtime": 1.9735,
430
- "eval_samples_per_second": 54.219,
431
- "eval_steps_per_second": 3.547,
432
- "step": 248
433
- },
434
- {
435
- "epoch": 31.25,
436
- "learning_rate": 3.645833333333333e-05,
437
- "loss": 0.6583,
438
- "step": 250
439
  },
440
  {
441
  "epoch": 32.0,
442
- "eval_accuracy": 0.5887850467289719,
443
- "eval_loss": 0.6781743764877319,
444
- "eval_runtime": 1.9435,
445
- "eval_samples_per_second": 55.056,
446
- "eval_steps_per_second": 3.602,
447
- "step": 256
448
- },
449
- {
450
- "epoch": 32.5,
451
- "learning_rate": 3.125e-05,
452
- "loss": 0.6501,
453
- "step": 260
454
- },
455
- {
456
- "epoch": 33.0,
457
- "eval_accuracy": 0.5887850467289719,
458
- "eval_loss": 0.664716362953186,
459
- "eval_runtime": 1.995,
460
- "eval_samples_per_second": 53.635,
461
- "eval_steps_per_second": 3.509,
462
- "step": 264
463
  },
464
  {
465
- "epoch": 33.75,
466
- "learning_rate": 2.6041666666666665e-05,
467
- "loss": 0.654,
468
- "step": 270
 
 
 
469
  },
470
  {
471
  "epoch": 34.0,
472
- "eval_accuracy": 0.5981308411214953,
473
- "eval_loss": 0.6602646112442017,
474
- "eval_runtime": 1.9045,
475
- "eval_samples_per_second": 56.184,
476
- "eval_steps_per_second": 3.676,
477
- "step": 272
478
- },
479
- {
480
- "epoch": 35.0,
481
- "learning_rate": 2.0833333333333333e-05,
482
- "loss": 0.6604,
483
- "step": 280
484
  },
485
  {
486
- "epoch": 35.0,
487
- "eval_accuracy": 0.5794392523364486,
488
- "eval_loss": 0.6873165965080261,
489
- "eval_runtime": 2.238,
490
- "eval_samples_per_second": 47.81,
491
- "eval_steps_per_second": 3.128,
492
- "step": 280
493
- },
494
- {
495
- "epoch": 36.0,
496
- "eval_accuracy": 0.5794392523364486,
497
- "eval_loss": 0.6591372489929199,
498
- "eval_runtime": 1.8624,
499
- "eval_samples_per_second": 57.451,
500
- "eval_steps_per_second": 3.758,
501
- "step": 288
502
- },
503
- {
504
- "epoch": 36.25,
505
- "learning_rate": 1.5625e-05,
506
- "loss": 0.6456,
507
- "step": 290
508
- },
509
- {
510
- "epoch": 37.0,
511
- "eval_accuracy": 0.616822429906542,
512
- "eval_loss": 0.6579955816268921,
513
- "eval_runtime": 1.9735,
514
- "eval_samples_per_second": 54.218,
515
- "eval_steps_per_second": 3.547,
516
- "step": 296
517
- },
518
- {
519
- "epoch": 37.5,
520
- "learning_rate": 1.0416666666666666e-05,
521
- "loss": 0.6483,
522
- "step": 300
523
- },
524
- {
525
- "epoch": 38.0,
526
- "eval_accuracy": 0.5981308411214953,
527
- "eval_loss": 0.6702041029930115,
528
- "eval_runtime": 1.9475,
529
- "eval_samples_per_second": 54.943,
530
- "eval_steps_per_second": 3.594,
531
- "step": 304
532
- },
533
- {
534
- "epoch": 38.75,
535
- "learning_rate": 5.208333333333333e-06,
536
- "loss": 0.6151,
537
- "step": 310
538
  },
539
  {
540
- "epoch": 39.0,
541
- "eval_accuracy": 0.5981308411214953,
542
- "eval_loss": 0.6784998774528503,
543
- "eval_runtime": 2.054,
544
- "eval_samples_per_second": 52.094,
545
- "eval_steps_per_second": 3.408,
546
- "step": 312
547
  },
548
  {
549
- "epoch": 40.0,
550
- "learning_rate": 0.0,
551
- "loss": 0.6291,
552
- "step": 320
553
- },
554
- {
555
- "epoch": 40.0,
556
- "eval_accuracy": 0.5981308411214953,
557
- "eval_loss": 0.6806396245956421,
558
- "eval_runtime": 1.92,
559
- "eval_samples_per_second": 55.73,
560
- "eval_steps_per_second": 3.646,
561
- "step": 320
562
- },
563
- {
564
- "epoch": 40.0,
565
- "step": 320,
566
- "total_flos": 6.480838238876467e+17,
567
- "train_loss": 0.9269241958856582,
568
- "train_runtime": 591.2866,
569
- "train_samples_per_second": 33.689,
570
- "train_steps_per_second": 0.541
571
  }
572
  ],
573
  "logging_steps": 10,
574
- "max_steps": 320,
575
  "num_input_tokens_seen": 0,
576
  "num_train_epochs": 40,
577
  "save_steps": 500,
578
- "total_flos": 6.480838238876467e+17,
579
  "train_batch_size": 16,
580
  "trial_name": null,
581
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.4782608695652174,
3
+ "best_model_checkpoint": "swinv2-tiny-patch4-window8-256-RD-aptos19\\checkpoint-112",
4
+ "epoch": 34.285714285714285,
5
  "eval_steps": 500,
6
+ "global_step": 120,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
+ "epoch": 0.86,
13
+ "eval_accuracy": 0.10869565217391304,
14
+ "eval_loss": 7.928128242492676,
15
+ "eval_runtime": 0.9501,
16
+ "eval_samples_per_second": 48.414,
17
+ "eval_steps_per_second": 3.157,
18
+ "step": 3
 
 
 
 
 
 
19
  },
20
  {
21
  "epoch": 2.0,
22
+ "eval_accuracy": 0.10869565217391304,
23
+ "eval_loss": 7.61707067489624,
24
+ "eval_runtime": 0.7517,
25
+ "eval_samples_per_second": 61.197,
26
+ "eval_steps_per_second": 3.991,
27
+ "step": 7
28
  },
29
  {
30
+ "epoch": 2.86,
31
+ "learning_rate": 0.000125,
32
+ "loss": 7.7567,
33
+ "step": 10
 
 
 
 
 
 
 
 
 
34
  },
35
  {
36
+ "epoch": 2.86,
37
+ "eval_accuracy": 0.10869565217391304,
38
+ "eval_loss": 6.576500415802002,
39
+ "eval_runtime": 0.7152,
40
+ "eval_samples_per_second": 64.321,
41
+ "eval_steps_per_second": 4.195,
42
+ "step": 10
43
  },
44
  {
45
  "epoch": 4.0,
46
+ "eval_accuracy": 0.10869565217391304,
47
+ "eval_loss": 4.186661243438721,
48
+ "eval_runtime": 0.7112,
49
+ "eval_samples_per_second": 64.683,
50
+ "eval_steps_per_second": 4.218,
51
+ "step": 14
52
+ },
53
+ {
54
+ "epoch": 4.86,
55
+ "eval_accuracy": 0.10869565217391304,
56
+ "eval_loss": 2.5570228099823,
57
+ "eval_runtime": 0.7112,
58
+ "eval_samples_per_second": 64.683,
59
+ "eval_steps_per_second": 4.218,
60
+ "step": 17
61
+ },
62
+ {
63
+ "epoch": 5.71,
64
+ "learning_rate": 0.0001388888888888889,
65
+ "loss": 4.0833,
66
+ "step": 20
67
  },
68
  {
69
  "epoch": 6.0,
70
+ "eval_accuracy": 0.45652173913043476,
71
+ "eval_loss": 1.5007256269454956,
72
+ "eval_runtime": 0.7232,
73
+ "eval_samples_per_second": 63.609,
74
+ "eval_steps_per_second": 4.148,
75
+ "step": 21
76
+ },
77
+ {
78
+ "epoch": 6.86,
79
+ "eval_accuracy": 0.45652173913043476,
80
+ "eval_loss": 1.281486988067627,
81
+ "eval_runtime": 0.7177,
82
+ "eval_samples_per_second": 64.096,
83
+ "eval_steps_per_second": 4.18,
84
+ "step": 24
 
 
 
 
 
 
 
 
 
 
 
 
85
  },
86
  {
87
  "epoch": 8.0,
88
+ "eval_accuracy": 0.45652173913043476,
89
+ "eval_loss": 1.2261085510253906,
90
+ "eval_runtime": 0.7117,
91
+ "eval_samples_per_second": 64.637,
92
+ "eval_steps_per_second": 4.215,
93
+ "step": 28
 
 
 
 
 
 
94
  },
95
  {
96
+ "epoch": 8.57,
 
 
 
 
 
 
 
 
 
97
  "learning_rate": 0.000125,
98
+ "loss": 1.3508,
99
+ "step": 30
 
 
 
 
 
 
 
 
 
100
  },
101
  {
102
+ "epoch": 8.86,
103
+ "eval_accuracy": 0.32608695652173914,
104
+ "eval_loss": 1.3183497190475464,
105
+ "eval_runtime": 0.7152,
106
+ "eval_samples_per_second": 64.321,
107
+ "eval_steps_per_second": 4.195,
108
+ "step": 31
109
  },
110
  {
111
+ "epoch": 10.0,
112
+ "eval_accuracy": 0.45652173913043476,
113
+ "eval_loss": 1.2316819429397583,
114
+ "eval_runtime": 0.7077,
115
+ "eval_samples_per_second": 65.003,
116
+ "eval_steps_per_second": 4.239,
117
+ "step": 35
118
+ },
119
+ {
120
+ "epoch": 10.86,
121
+ "eval_accuracy": 0.45652173913043476,
122
+ "eval_loss": 1.2423183917999268,
123
+ "eval_runtime": 0.7252,
124
+ "eval_samples_per_second": 63.432,
125
+ "eval_steps_per_second": 4.137,
126
+ "step": 38
127
+ },
128
+ {
129
+ "epoch": 11.43,
130
+ "learning_rate": 0.00011111111111111109,
131
+ "loss": 1.2181,
132
+ "step": 40
133
  },
134
  {
135
  "epoch": 12.0,
136
+ "eval_accuracy": 0.45652173913043476,
137
+ "eval_loss": 1.2673752307891846,
138
+ "eval_runtime": 0.7102,
139
+ "eval_samples_per_second": 64.773,
140
+ "eval_steps_per_second": 4.224,
141
+ "step": 42
142
  },
143
  {
144
+ "epoch": 12.86,
145
+ "eval_accuracy": 0.45652173913043476,
146
+ "eval_loss": 1.2562559843063354,
147
+ "eval_runtime": 0.7212,
148
+ "eval_samples_per_second": 63.785,
149
+ "eval_steps_per_second": 4.16,
150
+ "step": 45
 
 
 
 
 
 
 
 
 
 
 
 
151
  },
152
  {
153
  "epoch": 14.0,
154
+ "eval_accuracy": 0.45652173913043476,
155
+ "eval_loss": 1.2322901487350464,
156
+ "eval_runtime": 0.7672,
157
+ "eval_samples_per_second": 59.961,
158
+ "eval_steps_per_second": 3.91,
159
+ "step": 49
160
  },
161
  {
162
+ "epoch": 14.29,
163
+ "learning_rate": 9.722222222222222e-05,
164
+ "loss": 1.2726,
165
+ "step": 50
166
  },
167
  {
168
+ "epoch": 14.86,
169
+ "eval_accuracy": 0.45652173913043476,
170
+ "eval_loss": 1.2209585905075073,
171
+ "eval_runtime": 0.7922,
172
+ "eval_samples_per_second": 58.068,
173
+ "eval_steps_per_second": 3.787,
174
+ "step": 52
175
  },
176
  {
177
  "epoch": 16.0,
178
+ "eval_accuracy": 0.45652173913043476,
179
+ "eval_loss": 1.2287598848342896,
180
+ "eval_runtime": 0.7472,
181
+ "eval_samples_per_second": 61.566,
182
+ "eval_steps_per_second": 4.015,
183
+ "step": 56
 
 
 
 
 
 
184
  },
185
  {
186
+ "epoch": 16.86,
187
+ "eval_accuracy": 0.45652173913043476,
188
+ "eval_loss": 1.2344818115234375,
189
+ "eval_runtime": 0.7232,
190
+ "eval_samples_per_second": 63.609,
191
+ "eval_steps_per_second": 4.148,
192
+ "step": 59
193
  },
194
  {
195
+ "epoch": 17.14,
196
+ "learning_rate": 8.333333333333333e-05,
197
+ "loss": 1.2059,
198
+ "step": 60
199
  },
200
  {
201
  "epoch": 18.0,
202
+ "eval_accuracy": 0.45652173913043476,
203
+ "eval_loss": 1.2165099382400513,
204
+ "eval_runtime": 0.8322,
205
+ "eval_samples_per_second": 55.276,
206
+ "eval_steps_per_second": 3.605,
207
+ "step": 63
208
  },
209
  {
210
+ "epoch": 18.86,
211
+ "eval_accuracy": 0.45652173913043476,
212
+ "eval_loss": 1.2281591892242432,
213
+ "eval_runtime": 0.7042,
214
+ "eval_samples_per_second": 65.326,
215
+ "eval_steps_per_second": 4.26,
216
+ "step": 66
 
 
 
 
 
 
217
  },
218
  {
219
  "epoch": 20.0,
220
+ "learning_rate": 6.944444444444444e-05,
221
+ "loss": 1.2036,
222
+ "step": 70
223
  },
224
  {
225
  "epoch": 20.0,
226
+ "eval_accuracy": 0.45652173913043476,
227
+ "eval_loss": 1.200390338897705,
228
+ "eval_runtime": 0.8892,
229
+ "eval_samples_per_second": 51.731,
230
+ "eval_steps_per_second": 3.374,
231
+ "step": 70
 
 
 
 
 
 
 
 
 
232
  },
233
  {
234
+ "epoch": 20.86,
235
+ "eval_accuracy": 0.45652173913043476,
236
+ "eval_loss": 1.2020065784454346,
237
+ "eval_runtime": 0.7291,
238
+ "eval_samples_per_second": 63.094,
239
+ "eval_steps_per_second": 4.115,
240
+ "step": 73
241
  },
242
  {
243
  "epoch": 22.0,
244
+ "eval_accuracy": 0.45652173913043476,
245
+ "eval_loss": 1.204913854598999,
246
+ "eval_runtime": 0.7177,
247
+ "eval_samples_per_second": 64.096,
248
+ "eval_steps_per_second": 4.18,
249
+ "step": 77
250
  },
251
  {
252
+ "epoch": 22.86,
253
+ "learning_rate": 5.5555555555555545e-05,
254
+ "loss": 1.1678,
255
+ "step": 80
 
 
 
 
 
 
 
 
 
256
  },
257
  {
258
+ "epoch": 22.86,
259
+ "eval_accuracy": 0.45652173913043476,
260
+ "eval_loss": 1.2027997970581055,
261
+ "eval_runtime": 0.6892,
262
+ "eval_samples_per_second": 66.748,
263
+ "eval_steps_per_second": 4.353,
264
+ "step": 80
265
  },
266
  {
267
  "epoch": 24.0,
268
+ "eval_accuracy": 0.45652173913043476,
269
+ "eval_loss": 1.1945043802261353,
270
+ "eval_runtime": 0.7222,
271
+ "eval_samples_per_second": 63.698,
272
+ "eval_steps_per_second": 4.154,
273
+ "step": 84
274
  },
275
  {
276
+ "epoch": 24.86,
277
+ "eval_accuracy": 0.45652173913043476,
278
+ "eval_loss": 1.1905990839004517,
279
+ "eval_runtime": 0.7337,
280
+ "eval_samples_per_second": 62.698,
281
+ "eval_steps_per_second": 4.089,
282
+ "step": 87
283
  },
284
  {
285
+ "epoch": 25.71,
286
+ "learning_rate": 4.1666666666666665e-05,
287
+ "loss": 1.1522,
288
+ "step": 90
 
 
 
289
  },
290
  {
291
  "epoch": 26.0,
292
+ "eval_accuracy": 0.45652173913043476,
293
+ "eval_loss": 1.186482310295105,
294
+ "eval_runtime": 0.7167,
295
+ "eval_samples_per_second": 64.184,
296
+ "eval_steps_per_second": 4.186,
297
+ "step": 91
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
298
  },
299
  {
300
+ "epoch": 26.86,
301
+ "eval_accuracy": 0.45652173913043476,
302
+ "eval_loss": 1.1811820268630981,
303
+ "eval_runtime": 0.7077,
304
+ "eval_samples_per_second": 65.002,
305
+ "eval_steps_per_second": 4.239,
306
+ "step": 94
307
  },
308
  {
309
  "epoch": 28.0,
310
+ "eval_accuracy": 0.45652173913043476,
311
+ "eval_loss": 1.176020860671997,
312
+ "eval_runtime": 0.7072,
313
+ "eval_samples_per_second": 65.049,
314
+ "eval_steps_per_second": 4.242,
315
+ "step": 98
316
  },
317
  {
318
+ "epoch": 28.57,
319
+ "learning_rate": 2.7777777777777772e-05,
320
+ "loss": 1.1451,
321
+ "step": 100
 
 
 
 
 
 
 
 
 
322
  },
323
  {
324
+ "epoch": 28.86,
325
+ "eval_accuracy": 0.45652173913043476,
326
+ "eval_loss": 1.1714065074920654,
327
+ "eval_runtime": 0.7102,
328
+ "eval_samples_per_second": 64.774,
329
+ "eval_steps_per_second": 4.224,
330
+ "step": 101
331
  },
332
  {
333
  "epoch": 30.0,
334
+ "eval_accuracy": 0.45652173913043476,
335
+ "eval_loss": 1.1712819337844849,
336
+ "eval_runtime": 0.7352,
337
+ "eval_samples_per_second": 62.569,
338
+ "eval_steps_per_second": 4.081,
339
+ "step": 105
340
+ },
341
+ {
342
+ "epoch": 30.86,
343
+ "eval_accuracy": 0.45652173913043476,
344
+ "eval_loss": 1.157778263092041,
345
+ "eval_runtime": 0.7122,
346
+ "eval_samples_per_second": 64.591,
347
+ "eval_steps_per_second": 4.212,
348
+ "step": 108
349
+ },
350
+ {
351
+ "epoch": 31.43,
352
+ "learning_rate": 1.3888888888888886e-05,
353
+ "loss": 1.1252,
354
+ "step": 110
355
  },
356
  {
357
  "epoch": 32.0,
358
+ "eval_accuracy": 0.4782608695652174,
359
+ "eval_loss": 1.1496002674102783,
360
+ "eval_runtime": 0.7732,
361
+ "eval_samples_per_second": 59.494,
362
+ "eval_steps_per_second": 3.88,
363
+ "step": 112
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
364
  },
365
  {
366
+ "epoch": 32.86,
367
+ "eval_accuracy": 0.4782608695652174,
368
+ "eval_loss": 1.147078275680542,
369
+ "eval_runtime": 0.7077,
370
+ "eval_samples_per_second": 65.003,
371
+ "eval_steps_per_second": 4.239,
372
+ "step": 115
373
  },
374
  {
375
  "epoch": 34.0,
376
+ "eval_accuracy": 0.45652173913043476,
377
+ "eval_loss": 1.1464524269104004,
378
+ "eval_runtime": 0.7257,
379
+ "eval_samples_per_second": 63.389,
380
+ "eval_steps_per_second": 4.134,
381
+ "step": 119
 
 
 
 
 
 
382
  },
383
  {
384
+ "epoch": 34.29,
385
+ "learning_rate": 0.0,
386
+ "loss": 1.126,
387
+ "step": 120
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
388
  },
389
  {
390
+ "epoch": 34.29,
391
+ "eval_accuracy": 0.45652173913043476,
392
+ "eval_loss": 1.146438479423523,
393
+ "eval_runtime": 0.7242,
394
+ "eval_samples_per_second": 63.52,
395
+ "eval_steps_per_second": 4.143,
396
+ "step": 120
397
  },
398
  {
399
+ "epoch": 34.29,
400
+ "step": 120,
401
+ "total_flos": 2.3770905934823424e+17,
402
+ "train_loss": 1.9839425007502238,
403
+ "train_runtime": 191.8806,
404
+ "train_samples_per_second": 44.403,
405
+ "train_steps_per_second": 0.625
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
406
  }
407
  ],
408
  "logging_steps": 10,
409
+ "max_steps": 120,
410
  "num_input_tokens_seen": 0,
411
  "num_train_epochs": 40,
412
  "save_steps": 500,
413
+ "total_flos": 2.3770905934823424e+17,
414
  "train_batch_size": 16,
415
  "trial_name": null,
416
  "trial_params": null
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:286446616bdd5be4f0ebdfa59bcd1e531fbeabf7ae4299f8fc32c01515d20841
3
  size 4792
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e62b78acd952e808e64b4871e09ec24dd21c511e1bf3135487647306a65d4eb2
3
  size 4792