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
79c5d5d
·
verified ·
1 Parent(s): 55d5453

End of training

Browse files
Files changed (17) hide show
  1. README.md +37 -37
  2. all_results.json +8 -8
  3. eval_results.json +4 -4
  4. model.safetensors +1 -1
  5. runs/Dec01_18-53-01_DESKTOP-SKBE9FB/events.out.tfevents.1733100781.DESKTOP-SKBE9FB.5608.0 +3 -0
  6. runs/Dec01_19-03-33_DESKTOP-SKBE9FB/events.out.tfevents.1733101414.DESKTOP-SKBE9FB.15316.0 +3 -0
  7. runs/Dec01_19-04-24_DESKTOP-SKBE9FB/events.out.tfevents.1733101465.DESKTOP-SKBE9FB.6740.0 +3 -0
  8. runs/Dec01_19-06-55_DESKTOP-SKBE9FB/events.out.tfevents.1733101616.DESKTOP-SKBE9FB.17676.0 +3 -0
  9. runs/Dec01_19-07-36_DESKTOP-SKBE9FB/events.out.tfevents.1733101657.DESKTOP-SKBE9FB.17488.0 +3 -0
  10. runs/Dec01_19-08-27_DESKTOP-SKBE9FB/events.out.tfevents.1733101708.DESKTOP-SKBE9FB.16292.0 +3 -0
  11. runs/Dec01_19-09-07_DESKTOP-SKBE9FB/events.out.tfevents.1733101748.DESKTOP-SKBE9FB.6848.0 +3 -0
  12. runs/Dec01_19-24-29_DESKTOP-SKBE9FB/events.out.tfevents.1733102670.DESKTOP-SKBE9FB.17704.0 +3 -0
  13. runs/Dec02_09-42-53_DESKTOP-SKBE9FB/events.out.tfevents.1733154174.DESKTOP-SKBE9FB.8.0 +3 -0
  14. runs/Dec02_09-42-53_DESKTOP-SKBE9FB/events.out.tfevents.1733154311.DESKTOP-SKBE9FB.8.1 +3 -0
  15. train_results.json +4 -4
  16. trainer_state.json +164 -164
  17. training_args.bin +1 -1
README.md CHANGED
@@ -31,7 +31,7 @@ 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: 113.7364
35
  - Accuracy: 0.1087
36
 
37
  ## Model description
@@ -51,7 +51,7 @@ More information needed
51
  ### Training hyperparameters
52
 
53
  The following hyperparameters were used during training:
54
- - learning_rate: 0.00015
55
  - train_batch_size: 16
56
  - eval_batch_size: 16
57
  - seed: 42
@@ -66,41 +66,41 @@ The following hyperparameters were used during training:
66
 
67
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
68
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
69
- | No log | 0.86 | 3 | 113.7364 | 0.1087 |
70
- | No log | 2.0 | 7 | 113.7326 | 0.1087 |
71
- | 114.0068 | 2.86 | 10 | 113.7256 | 0.1087 |
72
- | 114.0068 | 4.0 | 14 | 113.7186 | 0.1087 |
73
- | 114.0068 | 4.86 | 17 | 113.7029 | 0.1087 |
74
- | 113.3375 | 6.0 | 21 | 113.6791 | 0.1087 |
75
- | 113.3375 | 6.86 | 24 | 113.6215 | 0.1087 |
76
- | 113.3375 | 8.0 | 28 | 113.5252 | 0.1087 |
77
- | 111.4746 | 8.86 | 31 | 113.4319 | 0.1087 |
78
- | 111.4746 | 10.0 | 35 | 113.3363 | 0.1087 |
79
- | 111.4746 | 10.86 | 38 | 113.2650 | 0.1087 |
80
- | 115.4431 | 12.0 | 42 | 113.2107 | 0.1087 |
81
- | 115.4431 | 12.86 | 45 | 113.0735 | 0.1087 |
82
- | 115.4431 | 14.0 | 49 | 112.9594 | 0.1087 |
83
- | 111.5901 | 14.86 | 52 | 112.8571 | 0.1087 |
84
- | 111.5901 | 16.0 | 56 | 112.6748 | 0.1087 |
85
- | 111.5901 | 16.86 | 59 | 112.6704 | 0.1087 |
86
- | 112.1751 | 18.0 | 63 | 112.6418 | 0.1087 |
87
- | 112.1751 | 18.86 | 66 | 112.8373 | 0.1087 |
88
- | 112.9078 | 20.0 | 70 | 112.8380 | 0.1087 |
89
- | 112.9078 | 20.86 | 73 | 112.7914 | 0.1087 |
90
- | 112.9078 | 22.0 | 77 | 112.5887 | 0.1087 |
91
- | 113.1403 | 22.86 | 80 | 112.6198 | 0.1087 |
92
- | 113.1403 | 24.0 | 84 | 112.2571 | 0.1087 |
93
- | 113.1403 | 24.86 | 87 | 112.2411 | 0.1087 |
94
- | 112.9338 | 26.0 | 91 | 112.1696 | 0.1087 |
95
- | 112.9338 | 26.86 | 94 | 112.1566 | 0.1087 |
96
- | 112.9338 | 28.0 | 98 | 112.3235 | 0.1087 |
97
- | 111.1035 | 28.86 | 101 | 112.2629 | 0.1087 |
98
- | 111.1035 | 30.0 | 105 | 112.0586 | 0.1087 |
99
- | 111.1035 | 30.86 | 108 | 112.0911 | 0.1087 |
100
- | 112.5756 | 32.0 | 112 | 112.2091 | 0.1087 |
101
- | 112.5756 | 32.86 | 115 | 112.1568 | 0.1087 |
102
- | 112.5756 | 34.0 | 119 | 111.8474 | 0.1087 |
103
- | 112.2756 | 34.29 | 120 | 111.8630 | 0.1087 |
104
 
105
 
106
  ### Framework versions
 
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: 113.8184
35
  - Accuracy: 0.1087
36
 
37
  ## Model description
 
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
 
66
 
67
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
68
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
69
+ | No log | 0.86 | 3 | 113.8184 | 0.1087 |
70
+ | No log | 2.0 | 7 | 113.8094 | 0.1087 |
71
+ | 114.0867 | 2.86 | 10 | 113.7944 | 0.1087 |
72
+ | 114.0867 | 4.0 | 14 | 113.7881 | 0.1087 |
73
+ | 114.0867 | 4.86 | 17 | 113.7100 | 0.1087 |
74
+ | 113.3425 | 6.0 | 21 | 113.5884 | 0.1087 |
75
+ | 113.3425 | 6.86 | 24 | 113.4998 | 0.1087 |
76
+ | 113.3425 | 8.0 | 28 | 113.0578 | 0.1087 |
77
+ | 111.228 | 8.86 | 31 | 112.8053 | 0.1087 |
78
+ | 111.228 | 10.0 | 35 | 112.5202 | 0.1087 |
79
+ | 111.228 | 10.86 | 38 | 112.5811 | 0.1087 |
80
+ | 114.9647 | 12.0 | 42 | 112.6090 | 0.1087 |
81
+ | 114.9647 | 12.86 | 45 | 112.4973 | 0.1087 |
82
+ | 114.9647 | 14.0 | 49 | 111.9761 | 0.1087 |
83
+ | 110.7738 | 14.86 | 52 | 111.8117 | 0.1087 |
84
+ | 110.7738 | 16.0 | 56 | 111.6589 | 0.1087 |
85
+ | 110.7738 | 16.86 | 59 | 111.5367 | 0.1087 |
86
+ | 111.0505 | 18.0 | 63 | 111.7016 | 0.1087 |
87
+ | 111.0505 | 18.86 | 66 | 111.9068 | 0.1087 |
88
+ | 111.4545 | 20.0 | 70 | 111.6203 | 0.1087 |
89
+ | 111.4545 | 20.86 | 73 | 111.1266 | 0.1087 |
90
+ | 111.4545 | 22.0 | 77 | 110.2879 | 0.1087 |
91
+ | 111.2779 | 22.86 | 80 | 109.8523 | 0.1087 |
92
+ | 111.2779 | 24.0 | 84 | 109.5283 | 0.1087 |
93
+ | 111.2779 | 24.86 | 87 | 109.9590 | 0.1087 |
94
+ | 110.5166 | 26.0 | 91 | 109.9752 | 0.1087 |
95
+ | 110.5166 | 26.86 | 94 | 109.5435 | 0.1087 |
96
+ | 110.5166 | 28.0 | 98 | 109.5712 | 0.1087 |
97
+ | 108.66 | 28.86 | 101 | 108.8924 | 0.1087 |
98
+ | 108.66 | 30.0 | 105 | 108.3990 | 0.1087 |
99
+ | 108.66 | 30.86 | 108 | 108.7050 | 0.1087 |
100
+ | 109.688 | 32.0 | 112 | 108.7237 | 0.1087 |
101
+ | 109.688 | 32.86 | 115 | 109.0679 | 0.1087 |
102
+ | 109.688 | 34.0 | 119 | 108.5750 | 0.1087 |
103
+ | 109.4549 | 34.29 | 120 | 108.5167 | 0.1087 |
104
 
105
 
106
  ### Framework versions
all_results.json CHANGED
@@ -1,12 +1,12 @@
1
  {
2
  "epoch": 34.29,
3
  "eval_accuracy": 0.10869565217391304,
4
- "eval_loss": 113.73644256591797,
5
- "eval_runtime": 0.5946,
6
- "eval_samples_per_second": 77.357,
7
- "eval_steps_per_second": 5.045,
8
- "train_loss": 112.74697774251302,
9
- "train_runtime": 128.6494,
10
- "train_samples_per_second": 66.226,
11
- "train_steps_per_second": 0.933
12
  }
 
1
  {
2
  "epoch": 34.29,
3
  "eval_accuracy": 0.10869565217391304,
4
+ "eval_loss": 113.81844329833984,
5
+ "eval_runtime": 0.6186,
6
+ "eval_samples_per_second": 74.356,
7
+ "eval_steps_per_second": 4.849,
8
+ "train_loss": 111.37485249837239,
9
+ "train_runtime": 136.0598,
10
+ "train_samples_per_second": 62.62,
11
+ "train_steps_per_second": 0.882
12
  }
eval_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 34.29,
3
  "eval_accuracy": 0.10869565217391304,
4
- "eval_loss": 113.73644256591797,
5
- "eval_runtime": 0.5946,
6
- "eval_samples_per_second": 77.357,
7
- "eval_steps_per_second": 5.045
8
  }
 
1
  {
2
  "epoch": 34.29,
3
  "eval_accuracy": 0.10869565217391304,
4
+ "eval_loss": 113.81844329833984,
5
+ "eval_runtime": 0.6186,
6
+ "eval_samples_per_second": 74.356,
7
+ "eval_steps_per_second": 4.849
8
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:37a2062fdea25c565927efa1bccc4042e6d74effa034bf445f2c9d3b5d6f1cb3
3
  size 12203648
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe65117317844ece5f5dc4f0f5845b05e9ebd35dc9b078531fa983038481075a
3
  size 12203648
runs/Dec01_18-53-01_DESKTOP-SKBE9FB/events.out.tfevents.1733100781.DESKTOP-SKBE9FB.5608.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:579e5f86745392fc98f33e6da7a920ff2373ffddae2b3031cefed926b508f461
3
+ size 6753
runs/Dec01_19-03-33_DESKTOP-SKBE9FB/events.out.tfevents.1733101414.DESKTOP-SKBE9FB.15316.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9bc02d95e3d89fc5e3997fc351b6e73f5ac1c48c4ecae62be84a3d7e4090ba0
3
+ size 6753
runs/Dec01_19-04-24_DESKTOP-SKBE9FB/events.out.tfevents.1733101465.DESKTOP-SKBE9FB.6740.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:abfd549e84f44578bf9eccd3eb28dd9db8a88e14cd190f2f1a81800d3bacc614
3
+ size 12278
runs/Dec01_19-06-55_DESKTOP-SKBE9FB/events.out.tfevents.1733101616.DESKTOP-SKBE9FB.17676.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fbad66f738556f0c86098df41e871716d80060c8bccb8a100e04386fa79a32e7
3
+ size 5965
runs/Dec01_19-07-36_DESKTOP-SKBE9FB/events.out.tfevents.1733101657.DESKTOP-SKBE9FB.17488.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a4c539c6ba07375d125173c63a1a6843008b202480fbecd8ae7178aa7d0e291
3
+ size 5177
runs/Dec01_19-08-27_DESKTOP-SKBE9FB/events.out.tfevents.1733101708.DESKTOP-SKBE9FB.16292.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a74dd82e0d79afb23ea07955e234f4e45e4338dc46b07bb4125d460884c8fda
3
+ size 5648
runs/Dec01_19-09-07_DESKTOP-SKBE9FB/events.out.tfevents.1733101748.DESKTOP-SKBE9FB.6848.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee5526aaff3da791e890f705193b218704e2bbfec61f3c8fd0dc794d8389dfad
3
+ size 5177
runs/Dec01_19-24-29_DESKTOP-SKBE9FB/events.out.tfevents.1733102670.DESKTOP-SKBE9FB.17704.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9bbe38e6e4a96764749ce47c2e562e70a8683f16e3a1520fce1e8ad7b8fc8b89
3
+ size 7386
runs/Dec02_09-42-53_DESKTOP-SKBE9FB/events.out.tfevents.1733154174.DESKTOP-SKBE9FB.8.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d8b4e07e4679003de18acaf6d4f22d63201aff0e0db6e6fc66fdf6b41b48f0e
3
+ size 17834
runs/Dec02_09-42-53_DESKTOP-SKBE9FB/events.out.tfevents.1733154311.DESKTOP-SKBE9FB.8.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1964859b0a63be59e613359fd4a83d460f4b768734ae5a9f8ce7f967b197d9b4
3
+ size 405
train_results.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "epoch": 34.29,
3
- "train_loss": 112.74697774251302,
4
- "train_runtime": 128.6494,
5
- "train_samples_per_second": 66.226,
6
- "train_steps_per_second": 0.933
7
  }
 
1
  {
2
  "epoch": 34.29,
3
+ "train_loss": 111.37485249837239,
4
+ "train_runtime": 136.0598,
5
+ "train_samples_per_second": 62.62,
6
+ "train_steps_per_second": 0.882
7
  }
trainer_state.json CHANGED
@@ -11,295 +11,295 @@
11
  {
12
  "epoch": 0.86,
13
  "eval_accuracy": 0.10869565217391304,
14
- "eval_loss": 113.73644256591797,
15
- "eval_runtime": 0.6432,
16
- "eval_samples_per_second": 71.522,
17
- "eval_steps_per_second": 4.664,
18
  "step": 3
19
  },
20
  {
21
  "epoch": 2.0,
22
  "eval_accuracy": 0.10869565217391304,
23
- "eval_loss": 113.73255157470703,
24
- "eval_runtime": 0.6031,
25
- "eval_samples_per_second": 76.268,
26
- "eval_steps_per_second": 4.974,
27
  "step": 7
28
  },
29
  {
30
  "epoch": 2.86,
31
- "learning_rate": 0.000125,
32
- "loss": 114.0068,
33
  "step": 10
34
  },
35
  {
36
  "epoch": 2.86,
37
  "eval_accuracy": 0.10869565217391304,
38
- "eval_loss": 113.72559356689453,
39
- "eval_runtime": 0.8182,
40
- "eval_samples_per_second": 56.221,
41
- "eval_steps_per_second": 3.667,
42
  "step": 10
43
  },
44
  {
45
  "epoch": 4.0,
46
  "eval_accuracy": 0.10869565217391304,
47
- "eval_loss": 113.71858215332031,
48
- "eval_runtime": 0.5882,
49
- "eval_samples_per_second": 78.211,
50
- "eval_steps_per_second": 5.101,
51
  "step": 14
52
  },
53
  {
54
  "epoch": 4.86,
55
  "eval_accuracy": 0.10869565217391304,
56
- "eval_loss": 113.7029037475586,
57
- "eval_runtime": 0.5851,
58
- "eval_samples_per_second": 78.615,
59
- "eval_steps_per_second": 5.127,
60
  "step": 17
61
  },
62
  {
63
  "epoch": 5.71,
64
- "learning_rate": 0.0001388888888888889,
65
- "loss": 113.3375,
66
  "step": 20
67
  },
68
  {
69
  "epoch": 6.0,
70
  "eval_accuracy": 0.10869565217391304,
71
- "eval_loss": 113.67913818359375,
72
- "eval_runtime": 0.5952,
73
- "eval_samples_per_second": 77.291,
74
- "eval_steps_per_second": 5.041,
75
  "step": 21
76
  },
77
  {
78
  "epoch": 6.86,
79
  "eval_accuracy": 0.10869565217391304,
80
- "eval_loss": 113.62146759033203,
81
- "eval_runtime": 0.5841,
82
- "eval_samples_per_second": 78.749,
83
- "eval_steps_per_second": 5.136,
84
  "step": 24
85
  },
86
  {
87
  "epoch": 8.0,
88
  "eval_accuracy": 0.10869565217391304,
89
- "eval_loss": 113.5252456665039,
90
- "eval_runtime": 0.5881,
91
- "eval_samples_per_second": 78.214,
92
- "eval_steps_per_second": 5.101,
93
  "step": 28
94
  },
95
  {
96
  "epoch": 8.57,
97
- "learning_rate": 0.000125,
98
- "loss": 111.4746,
99
  "step": 30
100
  },
101
  {
102
  "epoch": 8.86,
103
  "eval_accuracy": 0.10869565217391304,
104
- "eval_loss": 113.43194580078125,
105
- "eval_runtime": 0.6071,
106
- "eval_samples_per_second": 75.766,
107
- "eval_steps_per_second": 4.941,
108
  "step": 31
109
  },
110
  {
111
  "epoch": 10.0,
112
  "eval_accuracy": 0.10869565217391304,
113
- "eval_loss": 113.33634948730469,
114
- "eval_runtime": 0.7002,
115
- "eval_samples_per_second": 65.698,
116
- "eval_steps_per_second": 4.285,
117
  "step": 35
118
  },
119
  {
120
  "epoch": 10.86,
121
  "eval_accuracy": 0.10869565217391304,
122
- "eval_loss": 113.2650375366211,
123
- "eval_runtime": 0.5971,
124
- "eval_samples_per_second": 77.035,
125
- "eval_steps_per_second": 5.024,
126
  "step": 38
127
  },
128
  {
129
  "epoch": 11.43,
130
- "learning_rate": 0.00011111111111111109,
131
- "loss": 115.4431,
132
  "step": 40
133
  },
134
  {
135
  "epoch": 12.0,
136
  "eval_accuracy": 0.10869565217391304,
137
- "eval_loss": 113.21066284179688,
138
- "eval_runtime": 0.6032,
139
- "eval_samples_per_second": 76.266,
140
- "eval_steps_per_second": 4.974,
141
  "step": 42
142
  },
143
  {
144
  "epoch": 12.86,
145
  "eval_accuracy": 0.10869565217391304,
146
- "eval_loss": 113.073486328125,
147
- "eval_runtime": 0.6161,
148
- "eval_samples_per_second": 74.659,
149
- "eval_steps_per_second": 4.869,
150
  "step": 45
151
  },
152
  {
153
  "epoch": 14.0,
154
  "eval_accuracy": 0.10869565217391304,
155
- "eval_loss": 112.95938873291016,
156
- "eval_runtime": 0.5966,
157
- "eval_samples_per_second": 77.098,
158
- "eval_steps_per_second": 5.028,
159
  "step": 49
160
  },
161
  {
162
  "epoch": 14.29,
163
- "learning_rate": 9.722222222222222e-05,
164
- "loss": 111.5901,
165
  "step": 50
166
  },
167
  {
168
  "epoch": 14.86,
169
  "eval_accuracy": 0.10869565217391304,
170
- "eval_loss": 112.85713195800781,
171
- "eval_runtime": 0.5917,
172
- "eval_samples_per_second": 77.748,
173
- "eval_steps_per_second": 5.071,
174
  "step": 52
175
  },
176
  {
177
  "epoch": 16.0,
178
  "eval_accuracy": 0.10869565217391304,
179
- "eval_loss": 112.6748275756836,
180
- "eval_runtime": 0.6246,
181
- "eval_samples_per_second": 73.641,
182
- "eval_steps_per_second": 4.803,
183
  "step": 56
184
  },
185
  {
186
  "epoch": 16.86,
187
  "eval_accuracy": 0.10869565217391304,
188
- "eval_loss": 112.67044067382812,
189
- "eval_runtime": 0.5956,
190
- "eval_samples_per_second": 77.227,
191
- "eval_steps_per_second": 5.037,
192
  "step": 59
193
  },
194
  {
195
  "epoch": 17.14,
196
- "learning_rate": 8.333333333333333e-05,
197
- "loss": 112.1751,
198
  "step": 60
199
  },
200
  {
201
  "epoch": 18.0,
202
  "eval_accuracy": 0.10869565217391304,
203
- "eval_loss": 112.64176177978516,
204
- "eval_runtime": 0.5781,
205
- "eval_samples_per_second": 79.567,
206
- "eval_steps_per_second": 5.189,
207
  "step": 63
208
  },
209
  {
210
  "epoch": 18.86,
211
  "eval_accuracy": 0.10869565217391304,
212
- "eval_loss": 112.83734130859375,
213
- "eval_runtime": 0.5902,
214
- "eval_samples_per_second": 77.946,
215
- "eval_steps_per_second": 5.083,
216
  "step": 66
217
  },
218
  {
219
  "epoch": 20.0,
220
- "learning_rate": 6.944444444444444e-05,
221
- "loss": 112.9078,
222
  "step": 70
223
  },
224
  {
225
  "epoch": 20.0,
226
  "eval_accuracy": 0.10869565217391304,
227
- "eval_loss": 112.83795166015625,
228
- "eval_runtime": 0.6191,
229
- "eval_samples_per_second": 74.297,
230
- "eval_steps_per_second": 4.845,
231
  "step": 70
232
  },
233
  {
234
  "epoch": 20.86,
235
  "eval_accuracy": 0.10869565217391304,
236
- "eval_loss": 112.79137420654297,
237
- "eval_runtime": 0.6136,
238
- "eval_samples_per_second": 74.962,
239
- "eval_steps_per_second": 4.889,
240
  "step": 73
241
  },
242
  {
243
  "epoch": 22.0,
244
  "eval_accuracy": 0.10869565217391304,
245
- "eval_loss": 112.58869934082031,
246
- "eval_runtime": 0.5846,
247
- "eval_samples_per_second": 78.681,
248
- "eval_steps_per_second": 5.131,
249
  "step": 77
250
  },
251
  {
252
  "epoch": 22.86,
253
- "learning_rate": 5.5555555555555545e-05,
254
- "loss": 113.1403,
255
  "step": 80
256
  },
257
  {
258
  "epoch": 22.86,
259
  "eval_accuracy": 0.10869565217391304,
260
- "eval_loss": 112.61984252929688,
261
- "eval_runtime": 0.6196,
262
- "eval_samples_per_second": 74.236,
263
- "eval_steps_per_second": 4.841,
264
  "step": 80
265
  },
266
  {
267
  "epoch": 24.0,
268
  "eval_accuracy": 0.10869565217391304,
269
- "eval_loss": 112.25711059570312,
270
- "eval_runtime": 0.6051,
271
- "eval_samples_per_second": 76.016,
272
- "eval_steps_per_second": 4.958,
273
  "step": 84
274
  },
275
  {
276
  "epoch": 24.86,
277
  "eval_accuracy": 0.10869565217391304,
278
- "eval_loss": 112.2410659790039,
279
- "eval_runtime": 0.5831,
280
- "eval_samples_per_second": 78.884,
281
- "eval_steps_per_second": 5.145,
282
  "step": 87
283
  },
284
  {
285
  "epoch": 25.71,
286
- "learning_rate": 4.1666666666666665e-05,
287
- "loss": 112.9338,
288
  "step": 90
289
  },
290
  {
291
  "epoch": 26.0,
292
  "eval_accuracy": 0.10869565217391304,
293
- "eval_loss": 112.16959381103516,
294
- "eval_runtime": 0.6226,
295
- "eval_samples_per_second": 73.878,
296
- "eval_steps_per_second": 4.818,
297
  "step": 91
298
  },
299
  {
300
  "epoch": 26.86,
301
  "eval_accuracy": 0.10869565217391304,
302
- "eval_loss": 112.15655517578125,
303
  "eval_runtime": 0.6151,
304
  "eval_samples_per_second": 74.78,
305
  "eval_steps_per_second": 4.877,
@@ -308,101 +308,101 @@
308
  {
309
  "epoch": 28.0,
310
  "eval_accuracy": 0.10869565217391304,
311
- "eval_loss": 112.32354736328125,
312
- "eval_runtime": 0.5866,
313
- "eval_samples_per_second": 78.413,
314
- "eval_steps_per_second": 5.114,
315
  "step": 98
316
  },
317
  {
318
  "epoch": 28.57,
319
- "learning_rate": 2.7777777777777772e-05,
320
- "loss": 111.1035,
321
  "step": 100
322
  },
323
  {
324
  "epoch": 28.86,
325
  "eval_accuracy": 0.10869565217391304,
326
- "eval_loss": 112.26287841796875,
327
- "eval_runtime": 0.5856,
328
- "eval_samples_per_second": 78.547,
329
- "eval_steps_per_second": 5.123,
330
  "step": 101
331
  },
332
  {
333
  "epoch": 30.0,
334
  "eval_accuracy": 0.10869565217391304,
335
- "eval_loss": 112.05860137939453,
336
- "eval_runtime": 0.6191,
337
- "eval_samples_per_second": 74.297,
338
- "eval_steps_per_second": 4.845,
339
  "step": 105
340
  },
341
  {
342
  "epoch": 30.86,
343
  "eval_accuracy": 0.10869565217391304,
344
- "eval_loss": 112.09107208251953,
345
- "eval_runtime": 0.5961,
346
- "eval_samples_per_second": 77.164,
347
- "eval_steps_per_second": 5.032,
348
  "step": 108
349
  },
350
  {
351
  "epoch": 31.43,
352
- "learning_rate": 1.3888888888888886e-05,
353
- "loss": 112.5756,
354
  "step": 110
355
  },
356
  {
357
  "epoch": 32.0,
358
  "eval_accuracy": 0.10869565217391304,
359
- "eval_loss": 112.2091293334961,
360
- "eval_runtime": 0.6056,
361
- "eval_samples_per_second": 75.952,
362
- "eval_steps_per_second": 4.953,
363
  "step": 112
364
  },
365
  {
366
  "epoch": 32.86,
367
  "eval_accuracy": 0.10869565217391304,
368
- "eval_loss": 112.1567611694336,
369
- "eval_runtime": 0.6136,
370
- "eval_samples_per_second": 74.962,
371
- "eval_steps_per_second": 4.889,
372
  "step": 115
373
  },
374
  {
375
  "epoch": 34.0,
376
  "eval_accuracy": 0.10869565217391304,
377
- "eval_loss": 111.84735870361328,
378
- "eval_runtime": 0.5926,
379
- "eval_samples_per_second": 77.618,
380
- "eval_steps_per_second": 5.062,
381
  "step": 119
382
  },
383
  {
384
  "epoch": 34.29,
385
  "learning_rate": 0.0,
386
- "loss": 112.2756,
387
  "step": 120
388
  },
389
  {
390
  "epoch": 34.29,
391
  "eval_accuracy": 0.10869565217391304,
392
- "eval_loss": 111.86297607421875,
393
- "eval_runtime": 0.5896,
394
- "eval_samples_per_second": 78.014,
395
- "eval_steps_per_second": 5.088,
396
  "step": 120
397
  },
398
  {
399
  "epoch": 34.29,
400
  "step": 120,
401
  "total_flos": 2.0027429927092224e+16,
402
- "train_loss": 112.74697774251302,
403
- "train_runtime": 128.6494,
404
- "train_samples_per_second": 66.226,
405
- "train_steps_per_second": 0.933
406
  }
407
  ],
408
  "logging_steps": 10,
 
11
  {
12
  "epoch": 0.86,
13
  "eval_accuracy": 0.10869565217391304,
14
+ "eval_loss": 113.81844329833984,
15
+ "eval_runtime": 0.9277,
16
+ "eval_samples_per_second": 49.584,
17
+ "eval_steps_per_second": 3.234,
18
  "step": 3
19
  },
20
  {
21
  "epoch": 2.0,
22
  "eval_accuracy": 0.10869565217391304,
23
+ "eval_loss": 113.80943298339844,
24
+ "eval_runtime": 0.5649,
25
+ "eval_samples_per_second": 81.43,
26
+ "eval_steps_per_second": 5.311,
27
  "step": 7
28
  },
29
  {
30
  "epoch": 2.86,
31
+ "learning_rate": 0.00025,
32
+ "loss": 114.0867,
33
  "step": 10
34
  },
35
  {
36
  "epoch": 2.86,
37
  "eval_accuracy": 0.10869565217391304,
38
+ "eval_loss": 113.79438018798828,
39
+ "eval_runtime": 0.6062,
40
+ "eval_samples_per_second": 75.888,
41
+ "eval_steps_per_second": 4.949,
42
  "step": 10
43
  },
44
  {
45
  "epoch": 4.0,
46
  "eval_accuracy": 0.10869565217391304,
47
+ "eval_loss": 113.78809356689453,
48
+ "eval_runtime": 0.6076,
49
+ "eval_samples_per_second": 75.702,
50
+ "eval_steps_per_second": 4.937,
51
  "step": 14
52
  },
53
  {
54
  "epoch": 4.86,
55
  "eval_accuracy": 0.10869565217391304,
56
+ "eval_loss": 113.70995330810547,
57
+ "eval_runtime": 0.6162,
58
+ "eval_samples_per_second": 74.657,
59
+ "eval_steps_per_second": 4.869,
60
  "step": 17
61
  },
62
  {
63
  "epoch": 5.71,
64
+ "learning_rate": 0.0002777777777777778,
65
+ "loss": 113.3425,
66
  "step": 20
67
  },
68
  {
69
  "epoch": 6.0,
70
  "eval_accuracy": 0.10869565217391304,
71
+ "eval_loss": 113.58837890625,
72
+ "eval_runtime": 0.6537,
73
+ "eval_samples_per_second": 70.373,
74
+ "eval_steps_per_second": 4.59,
75
  "step": 21
76
  },
77
  {
78
  "epoch": 6.86,
79
  "eval_accuracy": 0.10869565217391304,
80
+ "eval_loss": 113.49983978271484,
81
+ "eval_runtime": 0.5761,
82
+ "eval_samples_per_second": 79.843,
83
+ "eval_steps_per_second": 5.207,
84
  "step": 24
85
  },
86
  {
87
  "epoch": 8.0,
88
  "eval_accuracy": 0.10869565217391304,
89
+ "eval_loss": 113.05781555175781,
90
+ "eval_runtime": 2.1702,
91
+ "eval_samples_per_second": 21.196,
92
+ "eval_steps_per_second": 1.382,
93
  "step": 28
94
  },
95
  {
96
  "epoch": 8.57,
97
+ "learning_rate": 0.00025,
98
+ "loss": 111.228,
99
  "step": 30
100
  },
101
  {
102
  "epoch": 8.86,
103
  "eval_accuracy": 0.10869565217391304,
104
+ "eval_loss": 112.80531311035156,
105
+ "eval_runtime": 0.5921,
106
+ "eval_samples_per_second": 77.685,
107
+ "eval_steps_per_second": 5.066,
108
  "step": 31
109
  },
110
  {
111
  "epoch": 10.0,
112
  "eval_accuracy": 0.10869565217391304,
113
+ "eval_loss": 112.52015686035156,
114
+ "eval_runtime": 0.6021,
115
+ "eval_samples_per_second": 76.395,
116
+ "eval_steps_per_second": 4.982,
117
  "step": 35
118
  },
119
  {
120
  "epoch": 10.86,
121
  "eval_accuracy": 0.10869565217391304,
122
+ "eval_loss": 112.58113861083984,
123
+ "eval_runtime": 0.5977,
124
+ "eval_samples_per_second": 76.964,
125
+ "eval_steps_per_second": 5.019,
126
  "step": 38
127
  },
128
  {
129
  "epoch": 11.43,
130
+ "learning_rate": 0.00022222222222222218,
131
+ "loss": 114.9647,
132
  "step": 40
133
  },
134
  {
135
  "epoch": 12.0,
136
  "eval_accuracy": 0.10869565217391304,
137
+ "eval_loss": 112.60899353027344,
138
+ "eval_runtime": 0.5971,
139
+ "eval_samples_per_second": 77.035,
140
+ "eval_steps_per_second": 5.024,
141
  "step": 42
142
  },
143
  {
144
  "epoch": 12.86,
145
  "eval_accuracy": 0.10869565217391304,
146
+ "eval_loss": 112.49734497070312,
147
+ "eval_runtime": 0.5906,
148
+ "eval_samples_per_second": 77.882,
149
+ "eval_steps_per_second": 5.079,
150
  "step": 45
151
  },
152
  {
153
  "epoch": 14.0,
154
  "eval_accuracy": 0.10869565217391304,
155
+ "eval_loss": 111.97610473632812,
156
+ "eval_runtime": 0.5781,
157
+ "eval_samples_per_second": 79.567,
158
+ "eval_steps_per_second": 5.189,
159
  "step": 49
160
  },
161
  {
162
  "epoch": 14.29,
163
+ "learning_rate": 0.00019444444444444443,
164
+ "loss": 110.7738,
165
  "step": 50
166
  },
167
  {
168
  "epoch": 14.86,
169
  "eval_accuracy": 0.10869565217391304,
170
+ "eval_loss": 111.81171417236328,
171
+ "eval_runtime": 0.5761,
172
+ "eval_samples_per_second": 79.841,
173
+ "eval_steps_per_second": 5.207,
174
  "step": 52
175
  },
176
  {
177
  "epoch": 16.0,
178
  "eval_accuracy": 0.10869565217391304,
179
+ "eval_loss": 111.65890502929688,
180
+ "eval_runtime": 0.5781,
181
+ "eval_samples_per_second": 79.567,
182
+ "eval_steps_per_second": 5.189,
183
  "step": 56
184
  },
185
  {
186
  "epoch": 16.86,
187
  "eval_accuracy": 0.10869565217391304,
188
+ "eval_loss": 111.53672790527344,
189
+ "eval_runtime": 0.5771,
190
+ "eval_samples_per_second": 79.703,
191
+ "eval_steps_per_second": 5.198,
192
  "step": 59
193
  },
194
  {
195
  "epoch": 17.14,
196
+ "learning_rate": 0.00016666666666666666,
197
+ "loss": 111.0505,
198
  "step": 60
199
  },
200
  {
201
  "epoch": 18.0,
202
  "eval_accuracy": 0.10869565217391304,
203
+ "eval_loss": 111.7016372680664,
204
+ "eval_runtime": 0.6091,
205
+ "eval_samples_per_second": 75.517,
206
+ "eval_steps_per_second": 4.925,
207
  "step": 63
208
  },
209
  {
210
  "epoch": 18.86,
211
  "eval_accuracy": 0.10869565217391304,
212
+ "eval_loss": 111.90676879882812,
213
+ "eval_runtime": 0.6357,
214
+ "eval_samples_per_second": 72.366,
215
+ "eval_steps_per_second": 4.72,
216
  "step": 66
217
  },
218
  {
219
  "epoch": 20.0,
220
+ "learning_rate": 0.0001388888888888889,
221
+ "loss": 111.4545,
222
  "step": 70
223
  },
224
  {
225
  "epoch": 20.0,
226
  "eval_accuracy": 0.10869565217391304,
227
+ "eval_loss": 111.62030792236328,
228
+ "eval_runtime": 0.6126,
229
+ "eval_samples_per_second": 75.084,
230
+ "eval_steps_per_second": 4.897,
231
  "step": 70
232
  },
233
  {
234
  "epoch": 20.86,
235
  "eval_accuracy": 0.10869565217391304,
236
+ "eval_loss": 111.12662506103516,
237
+ "eval_runtime": 0.6051,
238
+ "eval_samples_per_second": 76.016,
239
+ "eval_steps_per_second": 4.958,
240
  "step": 73
241
  },
242
  {
243
  "epoch": 22.0,
244
  "eval_accuracy": 0.10869565217391304,
245
+ "eval_loss": 110.28787231445312,
246
+ "eval_runtime": 0.6352,
247
+ "eval_samples_per_second": 72.422,
248
+ "eval_steps_per_second": 4.723,
249
  "step": 77
250
  },
251
  {
252
  "epoch": 22.86,
253
+ "learning_rate": 0.00011111111111111109,
254
+ "loss": 111.2779,
255
  "step": 80
256
  },
257
  {
258
  "epoch": 22.86,
259
  "eval_accuracy": 0.10869565217391304,
260
+ "eval_loss": 109.85228729248047,
261
+ "eval_runtime": 0.5951,
262
+ "eval_samples_per_second": 77.292,
263
+ "eval_steps_per_second": 5.041,
264
  "step": 80
265
  },
266
  {
267
  "epoch": 24.0,
268
  "eval_accuracy": 0.10869565217391304,
269
+ "eval_loss": 109.52828979492188,
270
+ "eval_runtime": 0.5951,
271
+ "eval_samples_per_second": 77.292,
272
+ "eval_steps_per_second": 5.041,
273
  "step": 84
274
  },
275
  {
276
  "epoch": 24.86,
277
  "eval_accuracy": 0.10869565217391304,
278
+ "eval_loss": 109.9590072631836,
279
+ "eval_runtime": 0.5836,
280
+ "eval_samples_per_second": 78.816,
281
+ "eval_steps_per_second": 5.14,
282
  "step": 87
283
  },
284
  {
285
  "epoch": 25.71,
286
+ "learning_rate": 8.333333333333333e-05,
287
+ "loss": 110.5166,
288
  "step": 90
289
  },
290
  {
291
  "epoch": 26.0,
292
  "eval_accuracy": 0.10869565217391304,
293
+ "eval_loss": 109.97518157958984,
294
+ "eval_runtime": 0.6056,
295
+ "eval_samples_per_second": 75.952,
296
+ "eval_steps_per_second": 4.953,
297
  "step": 91
298
  },
299
  {
300
  "epoch": 26.86,
301
  "eval_accuracy": 0.10869565217391304,
302
+ "eval_loss": 109.54348754882812,
303
  "eval_runtime": 0.6151,
304
  "eval_samples_per_second": 74.78,
305
  "eval_steps_per_second": 4.877,
 
308
  {
309
  "epoch": 28.0,
310
  "eval_accuracy": 0.10869565217391304,
311
+ "eval_loss": 109.57117462158203,
312
+ "eval_runtime": 0.6156,
313
+ "eval_samples_per_second": 74.718,
314
+ "eval_steps_per_second": 4.873,
315
  "step": 98
316
  },
317
  {
318
  "epoch": 28.57,
319
+ "learning_rate": 5.5555555555555545e-05,
320
+ "loss": 108.66,
321
  "step": 100
322
  },
323
  {
324
  "epoch": 28.86,
325
  "eval_accuracy": 0.10869565217391304,
326
+ "eval_loss": 108.89238739013672,
327
+ "eval_runtime": 0.6327,
328
+ "eval_samples_per_second": 72.71,
329
+ "eval_steps_per_second": 4.742,
330
  "step": 101
331
  },
332
  {
333
  "epoch": 30.0,
334
  "eval_accuracy": 0.10869565217391304,
335
+ "eval_loss": 108.39895629882812,
336
+ "eval_runtime": 0.6281,
337
+ "eval_samples_per_second": 73.232,
338
+ "eval_steps_per_second": 4.776,
339
  "step": 105
340
  },
341
  {
342
  "epoch": 30.86,
343
  "eval_accuracy": 0.10869565217391304,
344
+ "eval_loss": 108.70501708984375,
345
+ "eval_runtime": 0.6417,
346
+ "eval_samples_per_second": 71.69,
347
+ "eval_steps_per_second": 4.675,
348
  "step": 108
349
  },
350
  {
351
  "epoch": 31.43,
352
+ "learning_rate": 2.7777777777777772e-05,
353
+ "loss": 109.688,
354
  "step": 110
355
  },
356
  {
357
  "epoch": 32.0,
358
  "eval_accuracy": 0.10869565217391304,
359
+ "eval_loss": 108.7237319946289,
360
+ "eval_runtime": 0.6112,
361
+ "eval_samples_per_second": 75.267,
362
+ "eval_steps_per_second": 4.909,
363
  "step": 112
364
  },
365
  {
366
  "epoch": 32.86,
367
  "eval_accuracy": 0.10869565217391304,
368
+ "eval_loss": 109.0678939819336,
369
+ "eval_runtime": 0.6072,
370
+ "eval_samples_per_second": 75.763,
371
+ "eval_steps_per_second": 4.941,
372
  "step": 115
373
  },
374
  {
375
  "epoch": 34.0,
376
  "eval_accuracy": 0.10869565217391304,
377
+ "eval_loss": 108.574951171875,
378
+ "eval_runtime": 0.6091,
379
+ "eval_samples_per_second": 75.516,
380
+ "eval_steps_per_second": 4.925,
381
  "step": 119
382
  },
383
  {
384
  "epoch": 34.29,
385
  "learning_rate": 0.0,
386
+ "loss": 109.4549,
387
  "step": 120
388
  },
389
  {
390
  "epoch": 34.29,
391
  "eval_accuracy": 0.10869565217391304,
392
+ "eval_loss": 108.5167465209961,
393
+ "eval_runtime": 0.6016,
394
+ "eval_samples_per_second": 76.457,
395
+ "eval_steps_per_second": 4.986,
396
  "step": 120
397
  },
398
  {
399
  "epoch": 34.29,
400
  "step": 120,
401
  "total_flos": 2.0027429927092224e+16,
402
+ "train_loss": 111.37485249837239,
403
+ "train_runtime": 136.0598,
404
+ "train_samples_per_second": 62.62,
405
+ "train_steps_per_second": 0.882
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 sha256:3167ae056426e39cedb2d2abec62f92123cfad39beb1fe893e34fb5f5a3a4aa2
3
  size 4728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb32682ac9637aabf7bfeee556e5232c7b3af6054a8291210f22ee42fe3540cf
3
  size 4728