Hugging Face's logo

Augusto777
/
swiftformer-xs-DMAE

TensorBoard
Safetensors
swiftformer
Generated from Trainer
Eval Results
Model card Files Metrics Community
Augusto777 commited on
Commit
2610bd5
·
verified ·
1 Parent(s): f318ae5

End of training

Browse files
Files changed (9) hide show
  1. README.md +41 -41
  2. all_results.json +9 -9
  3. eval_results.json +5 -5
  4. model.safetensors +1 -1
  5. runs/Dec02_09-53-34_DESKTOP-SKBE9FB/events.out.tfevents.1733154815.DESKTOP-SKBE9FB.3184.0 +3 -0
  6. runs/Dec02_09-53-34_DESKTOP-SKBE9FB/events.out.tfevents.1733154943.DESKTOP-SKBE9FB.3184.1 +3 -0
  7. train_results.json +4 -4
  8. trainer_state.json +201 -201
  9. training_args.bin +1 -1
README.md CHANGED
@@ -21,7 +21,7 @@ model-index:
21
  metrics:
22
  - name: Accuracy
23
  type: accuracy
24
- value: 0.717391304347826
25
  ---
26
 
27
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -31,8 +31,8 @@ should probably proofread and complete it, then remove this comment. -->
31
 
32
  This model is a fine-tuned version of [MBZUAI/swiftformer-xs](https://huggingface.co/MBZUAI/swiftformer-xs) on the imagefolder dataset.
33
  It achieves the following results on the evaluation set:
34
- - Loss: 0.8492
35
- - Accuracy: 0.7174
36
 
37
  ## Model description
38
 
@@ -51,7 +51,7 @@ More information needed
51
  ### Training hyperparameters
52
 
53
  The following hyperparameters were used during training:
54
- - learning_rate: 0.0003
55
  - train_batch_size: 16
56
  - eval_batch_size: 16
57
  - seed: 42
@@ -64,43 +64,43 @@ The following hyperparameters were used during training:
64
 
65
  ### Training results
66
 
67
- | Training Loss | Epoch | Step | Validation Loss | Accuracy |
68
- |:-------------:|:-----:|:----:|:---------------:|:--------:|
69
- | No log | 0.86 | 3 | 1.3859 | 0.3261 |
70
- | No log | 2.0 | 7 | 1.3806 | 0.5217 |
71
- | 1.3829 | 2.86 | 10 | 1.3677 | 0.5870 |
72
- | 1.3829 | 4.0 | 14 | 1.3037 | 0.6739 |
73
- | 1.3829 | 4.86 | 17 | 1.2540 | 0.6522 |
74
- | 1.3074 | 6.0 | 21 | 1.1509 | 0.6522 |
75
- | 1.3074 | 6.86 | 24 | 1.0882 | 0.6739 |
76
- | 1.3074 | 8.0 | 28 | 1.0569 | 0.6522 |
77
- | 1.1437 | 8.86 | 31 | 1.0536 | 0.6304 |
78
- | 1.1437 | 10.0 | 35 | 0.9993 | 0.6522 |
79
- | 1.1437 | 10.86 | 38 | 0.9819 | 0.6739 |
80
- | 1.0439 | 12.0 | 42 | 0.9593 | 0.6957 |
81
- | 1.0439 | 12.86 | 45 | 0.9359 | 0.6304 |
82
- | 1.0439 | 14.0 | 49 | 0.9467 | 0.6522 |
83
- | 0.9813 | 14.86 | 52 | 0.9331 | 0.6522 |
84
- | 0.9813 | 16.0 | 56 | 0.9386 | 0.6522 |
85
- | 0.9813 | 16.86 | 59 | 0.9266 | 0.6739 |
86
- | 0.8763 | 18.0 | 63 | 0.8833 | 0.6957 |
87
- | 0.8763 | 18.86 | 66 | 0.8679 | 0.6739 |
88
- | 0.9187 | 20.0 | 70 | 0.8639 | 0.6957 |
89
- | 0.9187 | 20.86 | 73 | 0.8492 | 0.7174 |
90
- | 0.9187 | 22.0 | 77 | 0.8846 | 0.6957 |
91
- | 0.8067 | 22.86 | 80 | 0.9083 | 0.6522 |
92
- | 0.8067 | 24.0 | 84 | 0.9269 | 0.6522 |
93
- | 0.8067 | 24.86 | 87 | 0.8849 | 0.6739 |
94
- | 0.7248 | 26.0 | 91 | 0.8935 | 0.6522 |
95
- | 0.7248 | 26.86 | 94 | 0.8719 | 0.6957 |
96
- | 0.7248 | 28.0 | 98 | 0.8759 | 0.6739 |
97
- | 0.773 | 28.86 | 101 | 0.8887 | 0.6739 |
98
- | 0.773 | 30.0 | 105 | 0.9288 | 0.6522 |
99
- | 0.773 | 30.86 | 108 | 0.9041 | 0.6522 |
100
- | 0.7467 | 32.0 | 112 | 0.9017 | 0.6522 |
101
- | 0.7467 | 32.86 | 115 | 0.8767 | 0.6522 |
102
- | 0.7467 | 34.0 | 119 | 0.8993 | 0.6739 |
103
- | 0.7323 | 34.29 | 120 | 0.8946 | 0.6522 |
104
 
105
 
106
  ### Framework versions
 
21
  metrics:
22
  - name: Accuracy
23
  type: accuracy
24
+ value: 0.10869565217391304
25
  ---
26
 
27
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
31
 
32
  This model is a fine-tuned version of [MBZUAI/swiftformer-xs](https://huggingface.co/MBZUAI/swiftformer-xs) on the imagefolder dataset.
33
  It achieves the following results on the evaluation set:
34
+ - Loss: 4630678434517160409801529569050624.0000
35
+ - Accuracy: 0.1087
36
 
37
  ## Model description
38
 
 
51
  ### Training hyperparameters
52
 
53
  The following hyperparameters were used during training:
54
+ - learning_rate: 0.0005
55
  - train_batch_size: 16
56
  - eval_batch_size: 16
57
  - seed: 42
 
64
 
65
  ### Training results
66
 
67
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
68
+ |:---------------------------------------:|:-----:|:----:|:---------------------------------------:|:--------:|
69
+ | No log | 0.86 | 3 | 4630678434517160409801529569050624.0000 | 0.1087 |
70
+ | No log | 2.0 | 7 | 4630678434517160409801529569050624.0000 | 0.1087 |
71
+ | 4641762144967896284577948103606272.0000 | 2.86 | 10 | 4630678434517160409801529569050624.0000 | 0.1087 |
72
+ | 4641762144967896284577948103606272.0000 | 4.0 | 14 | 4630678434517160409801529569050624.0000 | 0.1087 |
73
+ | 4641762144967896284577948103606272.0000 | 4.86 | 17 | 4630678434517160409801529569050624.0000 | 0.1087 |
74
+ | 4615785211183531864889464880889856.0000 | 6.0 | 21 | 4630678434517160409801529569050624.0000 | 0.1087 |
75
+ | 4615785211183531864889464880889856.0000 | 6.86 | 24 | 4630678434517160409801529569050624.0000 | 0.1087 |
76
+ | 4615785211183531864889464880889856.0000 | 8.0 | 28 | 4630678434517160409801529569050624.0000 | 0.1087 |
77
+ | 4544348643276529710746136018419712.0000 | 8.86 | 31 | 4630678434517160409801529569050624.0000 | 0.1087 |
78
+ | 4544348643276529710746136018419712.0000 | 10.0 | 35 | 4630678434517160409801529569050624.0000 | 0.1087 |
79
+ | 4544348643276529710746136018419712.0000 | 10.86 | 38 | 4630678434517160409801529569050624.0000 | 0.1087 |
80
+ | 4714822395030425258781985118093312.0000 | 12.0 | 42 | 4630678434517160409801529569050624.0000 | 0.1087 |
81
+ | 4714822395030425258781985118093312.0000 | 12.86 | 45 | 4630678434517160409801529569050624.0000 | 0.1087 |
82
+ | 4714822395030425258781985118093312.0000 | 14.0 | 49 | 4630678434517160409801529569050624.0000 | 0.1087 |
83
+ | 4568701399729351711513951590154240.0000 | 14.86 | 52 | 4630678434517160409801529569050624.0000 | 0.1087 |
84
+ | 4568701399729351711513951590154240.0000 | 16.0 | 56 | 4630678434517160409801529569050624.0000 | 0.1087 |
85
+ | 4568701399729351711513951590154240.0000 | 16.86 | 59 | 4630678434517160409801529569050624.0000 | 0.1087 |
86
+ | 4604419931270860299785219619160064.0000 | 18.0 | 63 | 4630678434517160409801529569050624.0000 | 0.1087 |
87
+ | 4604419931270860299785219619160064.0000 | 18.86 | 66 | 4630678434517160409801529569050624.0000 | 0.1087 |
88
+ | 4640138957988385063377199450554368.0000 | 20.0 | 70 | 4630678434517160409801529569050624.0000 | 0.1087 |
89
+ | 4640138957988385063377199450554368.0000 | 20.86 | 73 | 4630678434517160409801529569050624.0000 | 0.1087 |
90
+ | 4640138957988385063377199450554368.0000 | 22.0 | 77 | 4630678434517160409801529569050624.0000 | 0.1087 |
91
+ | 4659621163150642779283602368626688.0000 | 22.86 | 80 | 4630678434517160409801529569050624.0000 | 0.1087 |
92
+ | 4659621163150642779283602368626688.0000 | 24.0 | 84 | 4630678434517160409801529569050624.0000 | 0.1087 |
93
+ | 4659621163150642779283602368626688.0000 | 24.86 | 87 | 4630678434517160409801529569050624.0000 | 0.1087 |
94
+ | 4659620667974627180423642869661696.0000 | 26.0 | 91 | 4630678434517160409801529569050624.0000 | 0.1087 |
95
+ | 4659620667974627180423642869661696.0000 | 26.86 | 94 | 4630678434517160409801529569050624.0000 | 0.1087 |
96
+ | 4659620667974627180423642869661696.0000 | 28.0 | 98 | 4630678434517160409801529569050624.0000 | 0.1087 |
97
+ | 4588184100067625026280314007191552.0000 | 28.86 | 101 | 4630678434517160409801529569050624.0000 | 0.1087 |
98
+ | 4588184100067625026280314007191552.0000 | 30.0 | 105 | 4630678434517160409801529569050624.0000 | 0.1087 |
99
+ | 4588184100067625026280314007191552.0000 | 30.86 | 108 | 4630678434517160409801529569050624.0000 | 0.1087 |
100
+ | 4649880060569514209560777061302272.0000 | 32.0 | 112 | 4630678434517160409801529569050624.0000 | 0.1087 |
101
+ | 4649880060569514209560777061302272.0000 | 32.86 | 115 | 4630678434517160409801529569050624.0000 | 0.1087 |
102
+ | 4649880060569514209560777061302272.0000 | 34.0 | 119 | 4630678434517160409801529569050624.0000 | 0.1087 |
103
+ | 4641762144967896284577948103606272.0000 | 34.29 | 120 | 4630678434517160409801529569050624.0000 | 0.1087 |
104
 
105
 
106
  ### Framework versions
all_results.json CHANGED
@@ -1,12 +1,12 @@
1
  {
2
  "epoch": 34.29,
3
- "eval_accuracy": 0.717391304347826,
4
- "eval_loss": 0.8492209315299988,
5
- "eval_runtime": 0.6737,
6
- "eval_samples_per_second": 68.284,
7
- "eval_steps_per_second": 4.453,
8
- "train_loss": 0.9531369884808858,
9
- "train_runtime": 147.6547,
10
- "train_samples_per_second": 57.702,
11
- "train_steps_per_second": 0.813
12
  }
 
1
  {
2
  "epoch": 34.29,
3
+ "eval_accuracy": 0.10869565217391304,
4
+ "eval_loss": 4.6306784345171604e+33,
5
+ "eval_runtime": 0.6036,
6
+ "eval_samples_per_second": 76.204,
7
+ "eval_steps_per_second": 4.97,
8
+ "train_loss": 4.6274205683481073e+33,
9
+ "train_runtime": 126.8689,
10
+ "train_samples_per_second": 67.156,
11
+ "train_steps_per_second": 0.946
12
  }
eval_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 34.29,
3
- "eval_accuracy": 0.717391304347826,
4
- "eval_loss": 0.8492209315299988,
5
- "eval_runtime": 0.6737,
6
- "eval_samples_per_second": 68.284,
7
- "eval_steps_per_second": 4.453
8
  }
 
1
  {
2
  "epoch": 34.29,
3
+ "eval_accuracy": 0.10869565217391304,
4
+ "eval_loss": 4.6306784345171604e+33,
5
+ "eval_runtime": 0.6036,
6
+ "eval_samples_per_second": 76.204,
7
+ "eval_steps_per_second": 4.97
8
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3e0359efe7b86e67f643b1723fbcc70a40720a77587d4a18776d051bb3516544
3
  size 12203648
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2da94344d7102046f3b98629d0b6ff940dba4361060a16e6a35ea4652e934d3
3
  size 12203648
runs/Dec02_09-53-34_DESKTOP-SKBE9FB/events.out.tfevents.1733154815.DESKTOP-SKBE9FB.3184.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:995ffba5c67e030b1044d947cff3a5b9687db5f84de6ccbc572a9bb0726fd8ca
3
+ size 17834
runs/Dec02_09-53-34_DESKTOP-SKBE9FB/events.out.tfevents.1733154943.DESKTOP-SKBE9FB.3184.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b0f5f5c1214410a5cb61ac1c310cd62f3ecf8cf72b12b61cf5a44d8c6a35196
3
+ size 405
train_results.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "epoch": 34.29,
3
- "train_loss": 0.9531369884808858,
4
- "train_runtime": 147.6547,
5
- "train_samples_per_second": 57.702,
6
- "train_steps_per_second": 0.813
7
  }
 
1
  {
2
  "epoch": 34.29,
3
+ "train_loss": 4.6274205683481073e+33,
4
+ "train_runtime": 126.8689,
5
+ "train_samples_per_second": 67.156,
6
+ "train_steps_per_second": 0.946
7
  }
trainer_state.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
- "best_metric": 0.717391304347826,
3
- "best_model_checkpoint": "swiftformer-xs-DMAE\\checkpoint-73",
4
  "epoch": 34.285714285714285,
5
  "eval_steps": 500,
6
  "global_step": 120,
@@ -10,32 +10,32 @@
10
  "log_history": [
11
  {
12
  "epoch": 0.86,
13
- "eval_accuracy": 0.32608695652173914,
14
- "eval_loss": 1.3858932256698608,
15
- "eval_runtime": 0.8132,
16
- "eval_samples_per_second": 56.568,
17
- "eval_steps_per_second": 3.689,
18
  "step": 3
19
  },
20
  {
21
  "epoch": 2.0,
22
- "eval_accuracy": 0.5217391304347826,
23
- "eval_loss": 1.380622148513794,
24
- "eval_runtime": 0.6061,
25
- "eval_samples_per_second": 75.891,
26
- "eval_steps_per_second": 4.949,
27
  "step": 7
28
  },
29
  {
30
  "epoch": 2.86,
31
- "learning_rate": 0.00025,
32
- "loss": 1.3829,
33
  "step": 10
34
  },
35
  {
36
  "epoch": 2.86,
37
- "eval_accuracy": 0.5869565217391305,
38
- "eval_loss": 1.3677465915679932,
39
  "eval_runtime": 0.6166,
40
  "eval_samples_per_second": 74.597,
41
  "eval_steps_per_second": 4.865,
@@ -43,366 +43,366 @@
43
  },
44
  {
45
  "epoch": 4.0,
46
- "eval_accuracy": 0.6739130434782609,
47
- "eval_loss": 1.3037457466125488,
48
- "eval_runtime": 0.7182,
49
- "eval_samples_per_second": 64.052,
50
- "eval_steps_per_second": 4.177,
51
  "step": 14
52
  },
53
  {
54
  "epoch": 4.86,
55
- "eval_accuracy": 0.6521739130434783,
56
- "eval_loss": 1.2539862394332886,
57
- "eval_runtime": 0.7222,
58
- "eval_samples_per_second": 63.698,
59
- "eval_steps_per_second": 4.154,
60
  "step": 17
61
  },
62
  {
63
  "epoch": 5.71,
64
- "learning_rate": 0.0002777777777777778,
65
- "loss": 1.3074,
66
  "step": 20
67
  },
68
  {
69
  "epoch": 6.0,
70
- "eval_accuracy": 0.6521739130434783,
71
- "eval_loss": 1.15088951587677,
72
- "eval_runtime": 0.6441,
73
- "eval_samples_per_second": 71.413,
74
- "eval_steps_per_second": 4.657,
75
  "step": 21
76
  },
77
  {
78
  "epoch": 6.86,
79
- "eval_accuracy": 0.6739130434782609,
80
- "eval_loss": 1.0881719589233398,
81
- "eval_runtime": 0.6236,
82
- "eval_samples_per_second": 73.76,
83
- "eval_steps_per_second": 4.81,
84
  "step": 24
85
  },
86
  {
87
  "epoch": 8.0,
88
- "eval_accuracy": 0.6521739130434783,
89
- "eval_loss": 1.056923270225525,
90
- "eval_runtime": 1.0408,
91
- "eval_samples_per_second": 44.199,
92
- "eval_steps_per_second": 2.883,
93
  "step": 28
94
  },
95
  {
96
  "epoch": 8.57,
97
- "learning_rate": 0.00025,
98
- "loss": 1.1437,
99
  "step": 30
100
  },
101
  {
102
  "epoch": 8.86,
103
- "eval_accuracy": 0.6304347826086957,
104
- "eval_loss": 1.053645133972168,
105
- "eval_runtime": 0.8772,
106
- "eval_samples_per_second": 52.439,
107
- "eval_steps_per_second": 3.42,
108
  "step": 31
109
  },
110
  {
111
  "epoch": 10.0,
112
- "eval_accuracy": 0.6521739130434783,
113
- "eval_loss": 0.9993222951889038,
114
- "eval_runtime": 1.0778,
115
- "eval_samples_per_second": 42.681,
116
- "eval_steps_per_second": 2.784,
117
  "step": 35
118
  },
119
  {
120
  "epoch": 10.86,
121
- "eval_accuracy": 0.6739130434782609,
122
- "eval_loss": 0.9819307923316956,
123
- "eval_runtime": 0.6542,
124
- "eval_samples_per_second": 70.32,
125
- "eval_steps_per_second": 4.586,
126
  "step": 38
127
  },
128
  {
129
  "epoch": 11.43,
130
- "learning_rate": 0.00022222222222222218,
131
- "loss": 1.0439,
132
  "step": 40
133
  },
134
  {
135
  "epoch": 12.0,
136
- "eval_accuracy": 0.6956521739130435,
137
- "eval_loss": 0.9593490958213806,
138
- "eval_runtime": 1.1103,
139
- "eval_samples_per_second": 41.431,
140
- "eval_steps_per_second": 2.702,
141
  "step": 42
142
  },
143
  {
144
  "epoch": 12.86,
145
- "eval_accuracy": 0.6304347826086957,
146
- "eval_loss": 0.9358569979667664,
147
- "eval_runtime": 0.7992,
148
- "eval_samples_per_second": 57.558,
149
- "eval_steps_per_second": 3.754,
150
  "step": 45
151
  },
152
  {
153
  "epoch": 14.0,
154
- "eval_accuracy": 0.6521739130434783,
155
- "eval_loss": 0.9467045068740845,
156
- "eval_runtime": 1.2303,
157
- "eval_samples_per_second": 37.39,
158
- "eval_steps_per_second": 2.438,
159
  "step": 49
160
  },
161
  {
162
  "epoch": 14.29,
163
- "learning_rate": 0.00019444444444444443,
164
- "loss": 0.9813,
165
  "step": 50
166
  },
167
  {
168
  "epoch": 14.86,
169
- "eval_accuracy": 0.6521739130434783,
170
- "eval_loss": 0.9330639243125916,
171
- "eval_runtime": 0.9252,
172
- "eval_samples_per_second": 49.718,
173
- "eval_steps_per_second": 3.242,
174
  "step": 52
175
  },
176
  {
177
  "epoch": 16.0,
178
- "eval_accuracy": 0.6521739130434783,
179
- "eval_loss": 0.9386307001113892,
180
- "eval_runtime": 0.6156,
181
- "eval_samples_per_second": 74.718,
182
- "eval_steps_per_second": 4.873,
183
  "step": 56
184
  },
185
  {
186
  "epoch": 16.86,
187
- "eval_accuracy": 0.6739130434782609,
188
- "eval_loss": 0.9266453385353088,
189
- "eval_runtime": 0.6812,
190
- "eval_samples_per_second": 67.533,
191
- "eval_steps_per_second": 4.404,
192
  "step": 59
193
  },
194
  {
195
  "epoch": 17.14,
196
- "learning_rate": 0.00016666666666666666,
197
- "loss": 0.8763,
198
  "step": 60
199
  },
200
  {
201
  "epoch": 18.0,
202
- "eval_accuracy": 0.6956521739130435,
203
- "eval_loss": 0.8833379149436951,
204
- "eval_runtime": 0.6407,
205
- "eval_samples_per_second": 71.8,
206
- "eval_steps_per_second": 4.683,
207
  "step": 63
208
  },
209
  {
210
  "epoch": 18.86,
211
- "eval_accuracy": 0.6739130434782609,
212
- "eval_loss": 0.8679067492485046,
213
- "eval_runtime": 0.6221,
214
- "eval_samples_per_second": 73.938,
215
- "eval_steps_per_second": 4.822,
216
  "step": 66
217
  },
218
  {
219
  "epoch": 20.0,
220
- "learning_rate": 0.0001388888888888889,
221
- "loss": 0.9187,
222
  "step": 70
223
  },
224
  {
225
  "epoch": 20.0,
226
- "eval_accuracy": 0.6956521739130435,
227
- "eval_loss": 0.8639189600944519,
228
- "eval_runtime": 0.6146,
229
- "eval_samples_per_second": 74.84,
230
- "eval_steps_per_second": 4.881,
231
  "step": 70
232
  },
233
  {
234
  "epoch": 20.86,
235
- "eval_accuracy": 0.717391304347826,
236
- "eval_loss": 0.8492209315299988,
237
- "eval_runtime": 0.6021,
238
- "eval_samples_per_second": 76.395,
239
- "eval_steps_per_second": 4.982,
240
  "step": 73
241
  },
242
  {
243
  "epoch": 22.0,
244
- "eval_accuracy": 0.6956521739130435,
245
- "eval_loss": 0.8846498727798462,
246
- "eval_runtime": 0.6817,
247
- "eval_samples_per_second": 67.482,
248
- "eval_steps_per_second": 4.401,
249
  "step": 77
250
  },
251
  {
252
  "epoch": 22.86,
253
- "learning_rate": 0.00011111111111111109,
254
- "loss": 0.8067,
255
  "step": 80
256
  },
257
  {
258
  "epoch": 22.86,
259
- "eval_accuracy": 0.6521739130434783,
260
- "eval_loss": 0.9083214402198792,
261
- "eval_runtime": 0.5901,
262
- "eval_samples_per_second": 77.947,
263
- "eval_steps_per_second": 5.083,
264
  "step": 80
265
  },
266
  {
267
  "epoch": 24.0,
268
- "eval_accuracy": 0.6521739130434783,
269
- "eval_loss": 0.9269394278526306,
270
- "eval_runtime": 0.5941,
271
- "eval_samples_per_second": 77.424,
272
- "eval_steps_per_second": 5.049,
273
  "step": 84
274
  },
275
  {
276
  "epoch": 24.86,
277
- "eval_accuracy": 0.6739130434782609,
278
- "eval_loss": 0.8849068284034729,
279
- "eval_runtime": 0.5811,
280
- "eval_samples_per_second": 79.154,
281
- "eval_steps_per_second": 5.162,
282
  "step": 87
283
  },
284
  {
285
  "epoch": 25.71,
286
- "learning_rate": 8.333333333333333e-05,
287
- "loss": 0.7248,
288
  "step": 90
289
  },
290
  {
291
  "epoch": 26.0,
292
- "eval_accuracy": 0.6521739130434783,
293
- "eval_loss": 0.8935391902923584,
294
- "eval_runtime": 0.5891,
295
- "eval_samples_per_second": 78.081,
296
- "eval_steps_per_second": 5.092,
297
  "step": 91
298
  },
299
  {
300
  "epoch": 26.86,
301
- "eval_accuracy": 0.6956521739130435,
302
- "eval_loss": 0.8718845248222351,
303
- "eval_runtime": 0.5891,
304
- "eval_samples_per_second": 78.081,
305
- "eval_steps_per_second": 5.092,
306
  "step": 94
307
  },
308
  {
309
  "epoch": 28.0,
310
- "eval_accuracy": 0.6739130434782609,
311
- "eval_loss": 0.8758830428123474,
312
- "eval_runtime": 0.6101,
313
- "eval_samples_per_second": 75.393,
314
- "eval_steps_per_second": 4.917,
315
  "step": 98
316
  },
317
  {
318
  "epoch": 28.57,
319
- "learning_rate": 5.5555555555555545e-05,
320
- "loss": 0.773,
321
  "step": 100
322
  },
323
  {
324
  "epoch": 28.86,
325
- "eval_accuracy": 0.6739130434782609,
326
- "eval_loss": 0.8886707425117493,
327
- "eval_runtime": 0.5751,
328
- "eval_samples_per_second": 79.98,
329
- "eval_steps_per_second": 5.216,
330
  "step": 101
331
  },
332
  {
333
  "epoch": 30.0,
334
- "eval_accuracy": 0.6521739130434783,
335
- "eval_loss": 0.9288129210472107,
336
- "eval_runtime": 0.5851,
337
- "eval_samples_per_second": 78.615,
338
- "eval_steps_per_second": 5.127,
339
  "step": 105
340
  },
341
  {
342
  "epoch": 30.86,
343
- "eval_accuracy": 0.6521739130434783,
344
- "eval_loss": 0.9040660858154297,
345
- "eval_runtime": 0.5871,
346
- "eval_samples_per_second": 78.345,
347
- "eval_steps_per_second": 5.109,
348
  "step": 108
349
  },
350
  {
351
  "epoch": 31.43,
352
- "learning_rate": 2.7777777777777772e-05,
353
- "loss": 0.7467,
354
  "step": 110
355
  },
356
  {
357
  "epoch": 32.0,
358
- "eval_accuracy": 0.6521739130434783,
359
- "eval_loss": 0.9017118215560913,
360
- "eval_runtime": 0.5852,
361
- "eval_samples_per_second": 78.612,
362
- "eval_steps_per_second": 5.127,
363
  "step": 112
364
  },
365
  {
366
  "epoch": 32.86,
367
- "eval_accuracy": 0.6521739130434783,
368
- "eval_loss": 0.8766883611679077,
369
- "eval_runtime": 0.5811,
370
- "eval_samples_per_second": 79.156,
371
- "eval_steps_per_second": 5.162,
372
  "step": 115
373
  },
374
  {
375
  "epoch": 34.0,
376
- "eval_accuracy": 0.6739130434782609,
377
- "eval_loss": 0.8992951512336731,
378
- "eval_runtime": 0.5791,
379
- "eval_samples_per_second": 79.427,
380
- "eval_steps_per_second": 5.18,
381
  "step": 119
382
  },
383
  {
384
  "epoch": 34.29,
385
  "learning_rate": 0.0,
386
- "loss": 0.7323,
387
  "step": 120
388
  },
389
  {
390
  "epoch": 34.29,
391
- "eval_accuracy": 0.6521739130434783,
392
- "eval_loss": 0.8945603370666504,
393
- "eval_runtime": 0.5791,
394
- "eval_samples_per_second": 79.427,
395
- "eval_steps_per_second": 5.18,
396
  "step": 120
397
  },
398
  {
399
  "epoch": 34.29,
400
  "step": 120,
401
  "total_flos": 2.0027429927092224e+16,
402
- "train_loss": 0.9531369884808858,
403
- "train_runtime": 147.6547,
404
- "train_samples_per_second": 57.702,
405
- "train_steps_per_second": 0.813
406
  }
407
  ],
408
  "logging_steps": 10,
 
1
  {
2
+ "best_metric": 0.10869565217391304,
3
+ "best_model_checkpoint": "swiftformer-xs-DMAE\\checkpoint-3",
4
  "epoch": 34.285714285714285,
5
  "eval_steps": 500,
6
  "global_step": 120,
 
10
  "log_history": [
11
  {
12
  "epoch": 0.86,
13
+ "eval_accuracy": 0.10869565217391304,
14
+ "eval_loss": 4.6306784345171604e+33,
15
+ "eval_runtime": 0.6507,
16
+ "eval_samples_per_second": 70.697,
17
+ "eval_steps_per_second": 4.611,
18
  "step": 3
19
  },
20
  {
21
  "epoch": 2.0,
22
+ "eval_accuracy": 0.10869565217391304,
23
+ "eval_loss": 4.6306784345171604e+33,
24
+ "eval_runtime": 0.5966,
25
+ "eval_samples_per_second": 77.098,
26
+ "eval_steps_per_second": 5.028,
27
  "step": 7
28
  },
29
  {
30
  "epoch": 2.86,
31
+ "learning_rate": 0.0004166666666666667,
32
+ "loss": 4.641762144967896e+33,
33
  "step": 10
34
  },
35
  {
36
  "epoch": 2.86,
37
+ "eval_accuracy": 0.10869565217391304,
38
+ "eval_loss": 4.6306784345171604e+33,
39
  "eval_runtime": 0.6166,
40
  "eval_samples_per_second": 74.597,
41
  "eval_steps_per_second": 4.865,
 
43
  },
44
  {
45
  "epoch": 4.0,
46
+ "eval_accuracy": 0.10869565217391304,
47
+ "eval_loss": 4.6306784345171604e+33,
48
+ "eval_runtime": 0.6132,
49
+ "eval_samples_per_second": 75.022,
50
+ "eval_steps_per_second": 4.893,
51
  "step": 14
52
  },
53
  {
54
  "epoch": 4.86,
55
+ "eval_accuracy": 0.10869565217391304,
56
+ "eval_loss": 4.6306784345171604e+33,
57
+ "eval_runtime": 0.6151,
58
+ "eval_samples_per_second": 74.78,
59
+ "eval_steps_per_second": 4.877,
60
  "step": 17
61
  },
62
  {
63
  "epoch": 5.71,
64
+ "learning_rate": 0.000462962962962963,
65
+ "loss": 4.615785211183532e+33,
66
  "step": 20
67
  },
68
  {
69
  "epoch": 6.0,
70
+ "eval_accuracy": 0.10869565217391304,
71
+ "eval_loss": 4.6306784345171604e+33,
72
+ "eval_runtime": 0.6142,
73
+ "eval_samples_per_second": 74.9,
74
+ "eval_steps_per_second": 4.885,
75
  "step": 21
76
  },
77
  {
78
  "epoch": 6.86,
79
+ "eval_accuracy": 0.10869565217391304,
80
+ "eval_loss": 4.6306784345171604e+33,
81
+ "eval_runtime": 0.6281,
82
+ "eval_samples_per_second": 73.231,
83
+ "eval_steps_per_second": 4.776,
84
  "step": 24
85
  },
86
  {
87
  "epoch": 8.0,
88
+ "eval_accuracy": 0.10869565217391304,
89
+ "eval_loss": 4.6306784345171604e+33,
90
+ "eval_runtime": 0.5936,
91
+ "eval_samples_per_second": 77.487,
92
+ "eval_steps_per_second": 5.054,
93
  "step": 28
94
  },
95
  {
96
  "epoch": 8.57,
97
+ "learning_rate": 0.0004166666666666667,
98
+ "loss": 4.5443486432765297e+33,
99
  "step": 30
100
  },
101
  {
102
  "epoch": 8.86,
103
+ "eval_accuracy": 0.10869565217391304,
104
+ "eval_loss": 4.6306784345171604e+33,
105
+ "eval_runtime": 0.6712,
106
+ "eval_samples_per_second": 68.537,
107
+ "eval_steps_per_second": 4.47,
108
  "step": 31
109
  },
110
  {
111
  "epoch": 10.0,
112
+ "eval_accuracy": 0.10869565217391304,
113
+ "eval_loss": 4.6306784345171604e+33,
114
+ "eval_runtime": 0.5982,
115
+ "eval_samples_per_second": 76.903,
116
+ "eval_steps_per_second": 5.015,
117
  "step": 35
118
  },
119
  {
120
  "epoch": 10.86,
121
+ "eval_accuracy": 0.10869565217391304,
122
+ "eval_loss": 4.6306784345171604e+33,
123
+ "eval_runtime": 0.5791,
124
+ "eval_samples_per_second": 79.427,
125
+ "eval_steps_per_second": 5.18,
126
  "step": 38
127
  },
128
  {
129
  "epoch": 11.43,
130
+ "learning_rate": 0.00037037037037037035,
131
+ "loss": 4.714822395030425e+33,
132
  "step": 40
133
  },
134
  {
135
  "epoch": 12.0,
136
+ "eval_accuracy": 0.10869565217391304,
137
+ "eval_loss": 4.6306784345171604e+33,
138
+ "eval_runtime": 0.5751,
139
+ "eval_samples_per_second": 79.982,
140
+ "eval_steps_per_second": 5.216,
141
  "step": 42
142
  },
143
  {
144
  "epoch": 12.86,
145
+ "eval_accuracy": 0.10869565217391304,
146
+ "eval_loss": 4.6306784345171604e+33,
147
+ "eval_runtime": 0.5746,
148
+ "eval_samples_per_second": 80.051,
149
+ "eval_steps_per_second": 5.221,
150
  "step": 45
151
  },
152
  {
153
  "epoch": 14.0,
154
+ "eval_accuracy": 0.10869565217391304,
155
+ "eval_loss": 4.6306784345171604e+33,
156
+ "eval_runtime": 0.6457,
157
+ "eval_samples_per_second": 71.246,
158
+ "eval_steps_per_second": 4.646,
159
  "step": 49
160
  },
161
  {
162
  "epoch": 14.29,
163
+ "learning_rate": 0.00032407407407407406,
164
+ "loss": 4.5687013997293517e+33,
165
  "step": 50
166
  },
167
  {
168
  "epoch": 14.86,
169
+ "eval_accuracy": 0.10869565217391304,
170
+ "eval_loss": 4.6306784345171604e+33,
171
+ "eval_runtime": 0.5916,
172
+ "eval_samples_per_second": 77.75,
173
+ "eval_steps_per_second": 5.071,
174
  "step": 52
175
  },
176
  {
177
  "epoch": 16.0,
178
+ "eval_accuracy": 0.10869565217391304,
179
+ "eval_loss": 4.6306784345171604e+33,
180
+ "eval_runtime": 0.5736,
181
+ "eval_samples_per_second": 80.19,
182
+ "eval_steps_per_second": 5.23,
183
  "step": 56
184
  },
185
  {
186
  "epoch": 16.86,
187
+ "eval_accuracy": 0.10869565217391304,
188
+ "eval_loss": 4.6306784345171604e+33,
189
+ "eval_runtime": 0.5951,
190
+ "eval_samples_per_second": 77.294,
191
+ "eval_steps_per_second": 5.041,
192
  "step": 59
193
  },
194
  {
195
  "epoch": 17.14,
196
+ "learning_rate": 0.0002777777777777778,
197
+ "loss": 4.6044199312708603e+33,
198
  "step": 60
199
  },
200
  {
201
  "epoch": 18.0,
202
+ "eval_accuracy": 0.10869565217391304,
203
+ "eval_loss": 4.6306784345171604e+33,
204
+ "eval_runtime": 0.5936,
205
+ "eval_samples_per_second": 77.488,
206
+ "eval_steps_per_second": 5.054,
207
  "step": 63
208
  },
209
  {
210
  "epoch": 18.86,
211
+ "eval_accuracy": 0.10869565217391304,
212
+ "eval_loss": 4.6306784345171604e+33,
213
+ "eval_runtime": 0.5736,
214
+ "eval_samples_per_second": 80.19,
215
+ "eval_steps_per_second": 5.23,
216
  "step": 66
217
  },
218
  {
219
  "epoch": 20.0,
220
+ "learning_rate": 0.0002314814814814815,
221
+ "loss": 4.640138957988385e+33,
222
  "step": 70
223
  },
224
  {
225
  "epoch": 20.0,
226
+ "eval_accuracy": 0.10869565217391304,
227
+ "eval_loss": 4.6306784345171604e+33,
228
+ "eval_runtime": 0.5836,
229
+ "eval_samples_per_second": 78.816,
230
+ "eval_steps_per_second": 5.14,
231
  "step": 70
232
  },
233
  {
234
  "epoch": 20.86,
235
+ "eval_accuracy": 0.10869565217391304,
236
+ "eval_loss": 4.6306784345171604e+33,
237
+ "eval_runtime": 0.6777,
238
+ "eval_samples_per_second": 67.88,
239
+ "eval_steps_per_second": 4.427,
240
  "step": 73
241
  },
242
  {
243
  "epoch": 22.0,
244
+ "eval_accuracy": 0.10869565217391304,
245
+ "eval_loss": 4.6306784345171604e+33,
246
+ "eval_runtime": 0.5766,
247
+ "eval_samples_per_second": 79.773,
248
+ "eval_steps_per_second": 5.203,
249
  "step": 77
250
  },
251
  {
252
  "epoch": 22.86,
253
+ "learning_rate": 0.00018518518518518518,
254
+ "loss": 4.659621163150643e+33,
255
  "step": 80
256
  },
257
  {
258
  "epoch": 22.86,
259
+ "eval_accuracy": 0.10869565217391304,
260
+ "eval_loss": 4.6306784345171604e+33,
261
+ "eval_runtime": 0.5801,
262
+ "eval_samples_per_second": 79.292,
263
+ "eval_steps_per_second": 5.171,
264
  "step": 80
265
  },
266
  {
267
  "epoch": 24.0,
268
+ "eval_accuracy": 0.10869565217391304,
269
+ "eval_loss": 4.6306784345171604e+33,
270
+ "eval_runtime": 0.6001,
271
+ "eval_samples_per_second": 76.649,
272
+ "eval_steps_per_second": 4.999,
273
  "step": 84
274
  },
275
  {
276
  "epoch": 24.86,
277
+ "eval_accuracy": 0.10869565217391304,
278
+ "eval_loss": 4.6306784345171604e+33,
279
+ "eval_runtime": 0.5656,
280
+ "eval_samples_per_second": 81.325,
281
+ "eval_steps_per_second": 5.304,
282
  "step": 87
283
  },
284
  {
285
  "epoch": 25.71,
286
+ "learning_rate": 0.0001388888888888889,
287
+ "loss": 4.659620667974627e+33,
288
  "step": 90
289
  },
290
  {
291
  "epoch": 26.0,
292
+ "eval_accuracy": 0.10869565217391304,
293
+ "eval_loss": 4.6306784345171604e+33,
294
+ "eval_runtime": 0.5741,
295
+ "eval_samples_per_second": 80.121,
296
+ "eval_steps_per_second": 5.225,
297
  "step": 91
298
  },
299
  {
300
  "epoch": 26.86,
301
+ "eval_accuracy": 0.10869565217391304,
302
+ "eval_loss": 4.6306784345171604e+33,
303
+ "eval_runtime": 0.5846,
304
+ "eval_samples_per_second": 78.681,
305
+ "eval_steps_per_second": 5.131,
306
  "step": 94
307
  },
308
  {
309
  "epoch": 28.0,
310
+ "eval_accuracy": 0.10869565217391304,
311
+ "eval_loss": 4.6306784345171604e+33,
312
+ "eval_runtime": 0.6051,
313
+ "eval_samples_per_second": 76.015,
314
+ "eval_steps_per_second": 4.958,
315
  "step": 98
316
  },
317
  {
318
  "epoch": 28.57,
319
+ "learning_rate": 9.259259259259259e-05,
320
+ "loss": 4.588184100067625e+33,
321
  "step": 100
322
  },
323
  {
324
  "epoch": 28.86,
325
+ "eval_accuracy": 0.10869565217391304,
326
+ "eval_loss": 4.6306784345171604e+33,
327
+ "eval_runtime": 0.5796,
328
+ "eval_samples_per_second": 79.36,
329
+ "eval_steps_per_second": 5.176,
330
  "step": 101
331
  },
332
  {
333
  "epoch": 30.0,
334
+ "eval_accuracy": 0.10869565217391304,
335
+ "eval_loss": 4.6306784345171604e+33,
336
+ "eval_runtime": 0.5726,
337
+ "eval_samples_per_second": 80.33,
338
+ "eval_steps_per_second": 5.239,
339
  "step": 105
340
  },
341
  {
342
  "epoch": 30.86,
343
+ "eval_accuracy": 0.10869565217391304,
344
+ "eval_loss": 4.6306784345171604e+33,
345
+ "eval_runtime": 0.6887,
346
+ "eval_samples_per_second": 66.796,
347
+ "eval_steps_per_second": 4.356,
348
  "step": 108
349
  },
350
  {
351
  "epoch": 31.43,
352
+ "learning_rate": 4.6296296296296294e-05,
353
+ "loss": 4.649880060569514e+33,
354
  "step": 110
355
  },
356
  {
357
  "epoch": 32.0,
358
+ "eval_accuracy": 0.10869565217391304,
359
+ "eval_loss": 4.6306784345171604e+33,
360
+ "eval_runtime": 0.5901,
361
+ "eval_samples_per_second": 77.949,
362
+ "eval_steps_per_second": 5.084,
363
  "step": 112
364
  },
365
  {
366
  "epoch": 32.86,
367
+ "eval_accuracy": 0.10869565217391304,
368
+ "eval_loss": 4.6306784345171604e+33,
369
+ "eval_runtime": 0.5836,
370
+ "eval_samples_per_second": 78.816,
371
+ "eval_steps_per_second": 5.14,
372
  "step": 115
373
  },
374
  {
375
  "epoch": 34.0,
376
+ "eval_accuracy": 0.10869565217391304,
377
+ "eval_loss": 4.6306784345171604e+33,
378
+ "eval_runtime": 0.5936,
379
+ "eval_samples_per_second": 77.488,
380
+ "eval_steps_per_second": 5.054,
381
  "step": 119
382
  },
383
  {
384
  "epoch": 34.29,
385
  "learning_rate": 0.0,
386
+ "loss": 4.641762144967896e+33,
387
  "step": 120
388
  },
389
  {
390
  "epoch": 34.29,
391
+ "eval_accuracy": 0.10869565217391304,
392
+ "eval_loss": 4.6306784345171604e+33,
393
+ "eval_runtime": 0.6026,
394
+ "eval_samples_per_second": 76.331,
395
+ "eval_steps_per_second": 4.978,
396
  "step": 120
397
  },
398
  {
399
  "epoch": 34.29,
400
  "step": 120,
401
  "total_flos": 2.0027429927092224e+16,
402
+ "train_loss": 4.6274205683481073e+33,
403
+ "train_runtime": 126.8689,
404
+ "train_samples_per_second": 67.156,
405
+ "train_steps_per_second": 0.946
406
  }
407
  ],
408
  "logging_steps": 10,
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f2e9b757d1b8c4a487ce9b5ba75d5e825afd3a6e4d73ad2d6c3dd161720724df
3
  size 4728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ad758ffe21c1a41f402e7f5c6095bca97da7069871e180ed134cd9299116e56
3
  size 4728