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
33ea907
·
verified ·
1 Parent(s): d3987ef

End of training

Browse files
Files changed (14) hide show
  1. README.md +40 -39
  2. all_results.json +8 -8
  3. config.json +8 -8
  4. eval_results.json +4 -4
  5. model.safetensors +1 -1
  6. runs/Dec02_11-33-33_DESKTOP-SKBE9FB/events.out.tfevents.1733160814.DESKTOP-SKBE9FB.16380.0 +3 -0
  7. runs/Dec02_11-35-09_DESKTOP-SKBE9FB/events.out.tfevents.1733160909.DESKTOP-SKBE9FB.4408.0 +3 -0
  8. runs/Dec02_11-36-38_DESKTOP-SKBE9FB/events.out.tfevents.1733160999.DESKTOP-SKBE9FB.19404.0 +3 -0
  9. runs/Dec02_11-40-14_DESKTOP-SKBE9FB/events.out.tfevents.1733161215.DESKTOP-SKBE9FB.1968.0 +3 -0
  10. runs/Dec02_11-41-54_DESKTOP-SKBE9FB/events.out.tfevents.1733161314.DESKTOP-SKBE9FB.17516.0 +3 -0
  11. runs/Dec02_11-41-54_DESKTOP-SKBE9FB/events.out.tfevents.1733161434.DESKTOP-SKBE9FB.17516.1 +3 -0
  12. train_results.json +4 -4
  13. trainer_state.json +167 -167
  14. 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: 113.8668
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: 2.5e-05
55
  - train_batch_size: 16
56
  - eval_batch_size: 16
57
  - seed: 42
@@ -59,47 +59,48 @@ The following hyperparameters were used during training:
59
  - total_train_batch_size: 64
60
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
61
  - lr_scheduler_type: linear
 
62
  - num_epochs: 40
63
 
64
  ### Training results
65
 
66
- | Training Loss | Epoch | Step | Validation Loss | Accuracy |
67
- |:-------------:|:-----:|:----:|:---------------:|:--------:|
68
- | No log | 0.86 | 3 | 113.8668 | 0.1087 |
69
- | No log | 2.0 | 7 | 113.8652 | 0.1087 |
70
- | 114.139 | 2.86 | 10 | 113.8636 | 0.1087 |
71
- | 114.139 | 4.0 | 14 | 113.8630 | 0.1087 |
72
- | 114.139 | 4.86 | 17 | 113.8617 | 0.1087 |
73
- | 113.4957 | 6.0 | 21 | 113.8592 | 0.1087 |
74
- | 113.4957 | 6.86 | 24 | 113.8579 | 0.1087 |
75
- | 113.4957 | 8.0 | 28 | 113.8578 | 0.1087 |
76
- | 111.7345 | 8.86 | 31 | 113.8550 | 0.1087 |
77
- | 111.7345 | 10.0 | 35 | 113.8531 | 0.1087 |
78
- | 111.7345 | 10.86 | 38 | 113.8520 | 0.1087 |
79
- | 115.9214 | 12.0 | 42 | 113.8497 | 0.1087 |
80
- | 115.9214 | 12.86 | 45 | 113.8484 | 0.1087 |
81
- | 115.9214 | 14.0 | 49 | 113.8455 | 0.1087 |
82
- | 112.3215 | 14.86 | 52 | 113.8392 | 0.1087 |
83
- | 112.3215 | 16.0 | 56 | 113.8351 | 0.1087 |
84
- | 112.3215 | 16.86 | 59 | 113.8354 | 0.1087 |
85
- | 113.1908 | 18.0 | 63 | 113.8316 | 0.1087 |
86
- | 113.1908 | 18.86 | 66 | 113.8295 | 0.1087 |
87
- | 114.062 | 20.0 | 70 | 113.8284 | 0.1087 |
88
- | 114.062 | 20.86 | 73 | 113.8253 | 0.1087 |
89
- | 114.062 | 22.0 | 77 | 113.8235 | 0.1087 |
90
- | 114.5312 | 22.86 | 80 | 113.8207 | 0.1087 |
91
- | 114.5312 | 24.0 | 84 | 113.8126 | 0.1087 |
92
- | 114.5312 | 24.86 | 87 | 113.8100 | 0.1087 |
93
- | 114.5216 | 26.0 | 91 | 113.8053 | 0.1087 |
94
- | 114.5216 | 26.86 | 94 | 113.8032 | 0.1087 |
95
- | 114.5216 | 28.0 | 98 | 113.8035 | 0.1087 |
96
- | 112.7612 | 28.86 | 101 | 113.7992 | 0.1087 |
97
- | 112.7612 | 30.0 | 105 | 113.7939 | 0.1087 |
98
- | 112.7612 | 30.86 | 108 | 113.7967 | 0.1087 |
99
- | 114.2748 | 32.0 | 112 | 113.7973 | 0.1087 |
100
- | 114.2748 | 32.86 | 115 | 113.7971 | 0.1087 |
101
- | 114.2748 | 34.0 | 119 | 113.7908 | 0.1087 |
102
- | 114.0708 | 34.29 | 120 | 113.7932 | 0.1087 |
103
 
104
 
105
  ### 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: 125514790469632.0
35
  - Accuracy: 0.1087
36
 
37
  ## Model description
 
51
  ### Training hyperparameters
52
 
53
  The following hyperparameters were used during training:
54
+ - learning_rate: 1.5e-05
55
  - train_batch_size: 16
56
  - eval_batch_size: 16
57
  - seed: 42
 
59
  - total_train_batch_size: 64
60
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
61
  - lr_scheduler_type: linear
62
+ - lr_scheduler_warmup_ratio: 0.01
63
  - num_epochs: 40
64
 
65
  ### Training results
66
 
67
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
68
+ |:-----------------:|:-----:|:----:|:-----------------:|:--------:|
69
+ | No log | 0.86 | 3 | 125514790469632.0 | 0.1087 |
70
+ | No log | 2.0 | 7 | 125514790469632.0 | 0.1087 |
71
+ | 125815215043379.2 | 2.86 | 10 | 125514790469632.0 | 0.1087 |
72
+ | 125815215043379.2 | 4.0 | 14 | 125514790469632.0 | 0.1087 |
73
+ | 125815215043379.2 | 4.86 | 17 | 125514790469632.0 | 0.1087 |
74
+ | 125111108842291.2 | 6.0 | 21 | 125514790469632.0 | 0.1087 |
75
+ | 125111108842291.2 | 6.86 | 24 | 125514790469632.0 | 0.1087 |
76
+ | 125111108842291.2 | 8.0 | 28 | 125514790469632.0 | 0.1087 |
77
+ | 123174816789299.2 | 8.86 | 31 | 125514790469632.0 | 0.1087 |
78
+ | 123174816789299.2 | 10.0 | 35 | 125514790469632.0 | 0.1087 |
79
+ | 123174816789299.2 | 10.86 | 38 | 125514790469632.0 | 0.1087 |
80
+ | 127795517089382.4 | 12.0 | 42 | 125514790469632.0 | 0.1087 |
81
+ | 127795517089382.4 | 12.86 | 45 | 125514790469632.0 | 0.1087 |
82
+ | 127795517089382.4 | 14.0 | 49 | 125514790469632.0 | 0.1087 |
83
+ | 123834899575603.2 | 14.86 | 52 | 125514790469632.0 | 0.1087 |
84
+ | 123834899575603.2 | 16.0 | 56 | 125514790469632.0 | 0.1087 |
85
+ | 123834899575603.2 | 16.86 | 59 | 125514790469632.0 | 0.1087 |
86
+ | 124803052312985.6 | 18.0 | 63 | 125514790469632.0 | 0.1087 |
87
+ | 124803052312985.6 | 18.86 | 66 | 125514790469632.0 | 0.1087 |
88
+ | 125771218472140.8 | 20.0 | 70 | 125514790469632.0 | 0.1087 |
89
+ | 125771218472140.8 | 20.86 | 73 | 125514790469632.0 | 0.1087 |
90
+ | 125771218472140.8 | 22.0 | 77 | 125514790469632.0 | 0.1087 |
91
+ | 126299284701184.0 | 22.86 | 80 | 125514790469632.0 | 0.1087 |
92
+ | 126299284701184.0 | 24.0 | 84 | 125514790469632.0 | 0.1087 |
93
+ | 126299284701184.0 | 24.86 | 87 | 125514790469632.0 | 0.1087 |
94
+ | 126299271279411.2 | 26.0 | 91 | 125514790469632.0 | 0.1087 |
95
+ | 126299271279411.2 | 26.86 | 94 | 125514790469632.0 | 0.1087 |
96
+ | 126299271279411.2 | 28.0 | 98 | 125514790469632.0 | 0.1087 |
97
+ | 124362979226419.2 | 28.86 | 101 | 125514790469632.0 | 0.1087 |
98
+ | 124362979226419.2 | 30.0 | 105 | 125514790469632.0 | 0.1087 |
99
+ | 124362979226419.2 | 30.86 | 108 | 125514790469632.0 | 0.1087 |
100
+ | 126035251586662.4 | 32.0 | 112 | 125514790469632.0 | 0.1087 |
101
+ | 126035251586662.4 | 32.86 | 115 | 125514790469632.0 | 0.1087 |
102
+ | 126035251586662.4 | 34.0 | 119 | 125514790469632.0 | 0.1087 |
103
+ | 125815215043379.2 | 34.29 | 120 | 125514790469632.0 | 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": 113.86678314208984,
5
- "eval_runtime": 0.6487,
6
- "eval_samples_per_second": 70.916,
7
- "eval_steps_per_second": 4.625,
8
- "train_loss": 113.75203348795573,
9
- "train_runtime": 131.4365,
10
- "train_samples_per_second": 64.822,
11
- "train_steps_per_second": 0.913
12
  }
 
1
  {
2
  "epoch": 34.29,
3
  "eval_accuracy": 0.10869565217391304,
4
+ "eval_loss": 125514790469632.0,
5
+ "eval_runtime": 0.7827,
6
+ "eval_samples_per_second": 58.772,
7
+ "eval_steps_per_second": 3.833,
8
+ "train_loss": 125426485830178.14,
9
+ "train_runtime": 118.5658,
10
+ "train_samples_per_second": 71.859,
11
+ "train_steps_per_second": 1.012
12
  }
config.json CHANGED
@@ -28,16 +28,16 @@
28
  ],
29
  "hidden_act": "gelu",
30
  "id2label": {
31
- "0": "avanzada",
32
- "1": "leve",
33
- "2": "moderada",
34
- "3": "no dmae"
35
  },
36
  "label2id": {
37
- "avanzada": 0,
38
- "leve": 1,
39
- "moderada": 2,
40
- "no dmae": 3
41
  },
42
  "layer_scale_init_value": 1e-05,
43
  "mlp_ratio": 4,
 
28
  ],
29
  "hidden_act": "gelu",
30
  "id2label": {
31
+ "0": "LABEL_0",
32
+ "1": "LABEL_1",
33
+ "2": "LABEL_2",
34
+ "3": "LABEL_3"
35
  },
36
  "label2id": {
37
+ "LABEL_0": 0,
38
+ "LABEL_1": 1,
39
+ "LABEL_2": 2,
40
+ "LABEL_3": 3
41
  },
42
  "layer_scale_init_value": 1e-05,
43
  "mlp_ratio": 4,
eval_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 34.29,
3
  "eval_accuracy": 0.10869565217391304,
4
- "eval_loss": 113.86678314208984,
5
- "eval_runtime": 0.6487,
6
- "eval_samples_per_second": 70.916,
7
- "eval_steps_per_second": 4.625
8
  }
 
1
  {
2
  "epoch": 34.29,
3
  "eval_accuracy": 0.10869565217391304,
4
+ "eval_loss": 125514790469632.0,
5
+ "eval_runtime": 0.7827,
6
+ "eval_samples_per_second": 58.772,
7
+ "eval_steps_per_second": 3.833
8
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:debfd6b2b6d15236fd33ba40707563aedea5995b0c33019829328fa5b74fb0e2
3
  size 12203648
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1035ad2070ee3a87574225f6b1e39422e066b8e076433a911aa6c6733f807ef5
3
  size 12203648
runs/Dec02_11-33-33_DESKTOP-SKBE9FB/events.out.tfevents.1733160814.DESKTOP-SKBE9FB.16380.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c22bcd40eca1b779fffeb671cc84f11ded4821bc85645f9942028879d0e6343
3
+ size 11492
runs/Dec02_11-35-09_DESKTOP-SKBE9FB/events.out.tfevents.1733160909.DESKTOP-SKBE9FB.4408.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57e4eb6658106c13d65d08bca1729e96980114d64819c7bbe1ea2ac865477833
3
+ size 9282
runs/Dec02_11-36-38_DESKTOP-SKBE9FB/events.out.tfevents.1733160999.DESKTOP-SKBE9FB.19404.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8a04284c81afc110142f44944ac8b125035082889acb7008608d0341f363eeb
3
+ size 5333
runs/Dec02_11-40-14_DESKTOP-SKBE9FB/events.out.tfevents.1733161215.DESKTOP-SKBE9FB.1968.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:132c8f0602c5f4b06e956935e6168414a896996d4c109ebd08997f03241dadcd
3
+ size 12753
runs/Dec02_11-41-54_DESKTOP-SKBE9FB/events.out.tfevents.1733161314.DESKTOP-SKBE9FB.17516.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0d2b9a44b8a39afbc1998b559b54f5ac60f3f1cb5f0033d324a600122d4bf21
3
+ size 17838
runs/Dec02_11-41-54_DESKTOP-SKBE9FB/events.out.tfevents.1733161434.DESKTOP-SKBE9FB.17516.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:801a2e03f0d4ba46fe194a675a2e4f1e2ec741d580ad7e07d4f3aa458d0e7d92
3
+ size 405
train_results.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "epoch": 34.29,
3
- "train_loss": 113.75203348795573,
4
- "train_runtime": 131.4365,
5
- "train_samples_per_second": 64.822,
6
- "train_steps_per_second": 0.913
7
  }
 
1
  {
2
  "epoch": 34.29,
3
+ "train_loss": 125426485830178.14,
4
+ "train_runtime": 118.5658,
5
+ "train_samples_per_second": 71.859,
6
+ "train_steps_per_second": 1.012
7
  }
trainer_state.json CHANGED
@@ -11,398 +11,398 @@
11
  {
12
  "epoch": 0.86,
13
  "eval_accuracy": 0.10869565217391304,
14
- "eval_loss": 113.86678314208984,
15
- "eval_runtime": 0.6737,
16
- "eval_samples_per_second": 68.283,
17
- "eval_steps_per_second": 4.453,
18
  "step": 3
19
  },
20
  {
21
  "epoch": 2.0,
22
  "eval_accuracy": 0.10869565217391304,
23
- "eval_loss": 113.8652114868164,
24
- "eval_runtime": 0.6176,
25
- "eval_samples_per_second": 74.476,
26
- "eval_steps_per_second": 4.857,
27
  "step": 7
28
  },
29
  {
30
  "epoch": 2.86,
31
- "learning_rate": 2.2916666666666667e-05,
32
- "loss": 114.139,
33
  "step": 10
34
  },
35
  {
36
  "epoch": 2.86,
37
  "eval_accuracy": 0.10869565217391304,
38
- "eval_loss": 113.86360168457031,
39
- "eval_runtime": 0.6252,
40
- "eval_samples_per_second": 73.581,
41
- "eval_steps_per_second": 4.799,
42
  "step": 10
43
  },
44
  {
45
  "epoch": 4.0,
46
  "eval_accuracy": 0.10869565217391304,
47
- "eval_loss": 113.86296081542969,
48
- "eval_runtime": 0.6111,
49
- "eval_samples_per_second": 75.27,
50
- "eval_steps_per_second": 4.909,
51
  "step": 14
52
  },
53
  {
54
  "epoch": 4.86,
55
  "eval_accuracy": 0.10869565217391304,
56
- "eval_loss": 113.86167907714844,
57
- "eval_runtime": 0.6116,
58
- "eval_samples_per_second": 75.206,
59
- "eval_steps_per_second": 4.905,
60
  "step": 17
61
  },
62
  {
63
  "epoch": 5.71,
64
- "learning_rate": 2.0833333333333336e-05,
65
- "loss": 113.4957,
66
  "step": 20
67
  },
68
  {
69
  "epoch": 6.0,
70
  "eval_accuracy": 0.10869565217391304,
71
- "eval_loss": 113.85923767089844,
72
- "eval_runtime": 0.6187,
73
- "eval_samples_per_second": 74.355,
74
- "eval_steps_per_second": 4.849,
75
  "step": 21
76
  },
77
  {
78
  "epoch": 6.86,
79
  "eval_accuracy": 0.10869565217391304,
80
- "eval_loss": 113.8578872680664,
81
- "eval_runtime": 0.6091,
82
- "eval_samples_per_second": 75.517,
83
- "eval_steps_per_second": 4.925,
84
  "step": 24
85
  },
86
  {
87
  "epoch": 8.0,
88
  "eval_accuracy": 0.10869565217391304,
89
- "eval_loss": 113.8578109741211,
90
- "eval_runtime": 0.6207,
91
- "eval_samples_per_second": 74.114,
92
- "eval_steps_per_second": 4.834,
93
  "step": 28
94
  },
95
  {
96
  "epoch": 8.57,
97
- "learning_rate": 1.8750000000000002e-05,
98
- "loss": 111.7345,
99
  "step": 30
100
  },
101
  {
102
  "epoch": 8.86,
103
  "eval_accuracy": 0.10869565217391304,
104
- "eval_loss": 113.8550033569336,
105
- "eval_runtime": 0.6176,
106
- "eval_samples_per_second": 74.476,
107
- "eval_steps_per_second": 4.857,
108
  "step": 31
109
  },
110
  {
111
  "epoch": 10.0,
112
  "eval_accuracy": 0.10869565217391304,
113
- "eval_loss": 113.85313415527344,
114
- "eval_runtime": 0.5966,
115
- "eval_samples_per_second": 77.098,
116
- "eval_steps_per_second": 5.028,
117
  "step": 35
118
  },
119
  {
120
  "epoch": 10.86,
121
  "eval_accuracy": 0.10869565217391304,
122
- "eval_loss": 113.85196685791016,
123
- "eval_runtime": 0.6032,
124
- "eval_samples_per_second": 76.266,
125
- "eval_steps_per_second": 4.974,
126
  "step": 38
127
  },
128
  {
129
  "epoch": 11.43,
130
- "learning_rate": 1.6666666666666667e-05,
131
- "loss": 115.9214,
132
  "step": 40
133
  },
134
  {
135
  "epoch": 12.0,
136
  "eval_accuracy": 0.10869565217391304,
137
- "eval_loss": 113.84968566894531,
138
- "eval_runtime": 0.5951,
139
- "eval_samples_per_second": 77.294,
140
- "eval_steps_per_second": 5.041,
141
  "step": 42
142
  },
143
  {
144
  "epoch": 12.86,
145
  "eval_accuracy": 0.10869565217391304,
146
- "eval_loss": 113.8483657836914,
147
- "eval_runtime": 0.6171,
148
- "eval_samples_per_second": 74.538,
149
- "eval_steps_per_second": 4.861,
150
  "step": 45
151
  },
152
  {
153
  "epoch": 14.0,
154
  "eval_accuracy": 0.10869565217391304,
155
- "eval_loss": 113.84552001953125,
156
- "eval_runtime": 0.6081,
157
- "eval_samples_per_second": 75.641,
158
- "eval_steps_per_second": 4.933,
159
  "step": 49
160
  },
161
  {
162
  "epoch": 14.29,
163
- "learning_rate": 1.4583333333333335e-05,
164
- "loss": 112.3215,
165
  "step": 50
166
  },
167
  {
168
  "epoch": 14.86,
169
  "eval_accuracy": 0.10869565217391304,
170
- "eval_loss": 113.83916473388672,
171
- "eval_runtime": 0.7172,
172
- "eval_samples_per_second": 64.142,
173
- "eval_steps_per_second": 4.183,
174
  "step": 52
175
  },
176
  {
177
  "epoch": 16.0,
178
  "eval_accuracy": 0.10869565217391304,
179
- "eval_loss": 113.83506774902344,
180
- "eval_runtime": 0.6271,
181
- "eval_samples_per_second": 73.349,
182
- "eval_steps_per_second": 4.784,
183
  "step": 56
184
  },
185
  {
186
  "epoch": 16.86,
187
  "eval_accuracy": 0.10869565217391304,
188
- "eval_loss": 113.83540344238281,
189
- "eval_runtime": 0.6112,
190
- "eval_samples_per_second": 75.268,
191
- "eval_steps_per_second": 4.909,
192
  "step": 59
193
  },
194
  {
195
  "epoch": 17.14,
196
- "learning_rate": 1.25e-05,
197
- "loss": 113.1908,
198
  "step": 60
199
  },
200
  {
201
  "epoch": 18.0,
202
  "eval_accuracy": 0.10869565217391304,
203
- "eval_loss": 113.83159637451172,
204
- "eval_runtime": 0.6036,
205
- "eval_samples_per_second": 76.204,
206
- "eval_steps_per_second": 4.97,
207
  "step": 63
208
  },
209
  {
210
  "epoch": 18.86,
211
  "eval_accuracy": 0.10869565217391304,
212
- "eval_loss": 113.82946014404297,
213
- "eval_runtime": 0.6282,
214
- "eval_samples_per_second": 73.23,
215
- "eval_steps_per_second": 4.776,
216
  "step": 66
217
  },
218
  {
219
  "epoch": 20.0,
220
- "learning_rate": 1.0416666666666668e-05,
221
- "loss": 114.062,
222
  "step": 70
223
  },
224
  {
225
  "epoch": 20.0,
226
  "eval_accuracy": 0.10869565217391304,
227
- "eval_loss": 113.82839965820312,
228
- "eval_runtime": 0.5991,
229
- "eval_samples_per_second": 76.778,
230
- "eval_steps_per_second": 5.007,
231
  "step": 70
232
  },
233
  {
234
  "epoch": 20.86,
235
  "eval_accuracy": 0.10869565217391304,
236
- "eval_loss": 113.8253402709961,
237
- "eval_runtime": 0.5961,
238
- "eval_samples_per_second": 77.162,
239
- "eval_steps_per_second": 5.032,
240
  "step": 73
241
  },
242
  {
243
  "epoch": 22.0,
244
  "eval_accuracy": 0.10869565217391304,
245
- "eval_loss": 113.82349395751953,
246
- "eval_runtime": 0.7817,
247
- "eval_samples_per_second": 58.847,
248
- "eval_steps_per_second": 3.838,
249
  "step": 77
250
  },
251
  {
252
  "epoch": 22.86,
253
- "learning_rate": 8.333333333333334e-06,
254
- "loss": 114.5312,
255
  "step": 80
256
  },
257
  {
258
  "epoch": 22.86,
259
  "eval_accuracy": 0.10869565217391304,
260
- "eval_loss": 113.82068634033203,
261
- "eval_runtime": 0.6071,
262
- "eval_samples_per_second": 75.766,
263
- "eval_steps_per_second": 4.941,
264
  "step": 80
265
  },
266
  {
267
  "epoch": 24.0,
268
  "eval_accuracy": 0.10869565217391304,
269
- "eval_loss": 113.81257629394531,
270
- "eval_runtime": 0.6061,
271
- "eval_samples_per_second": 75.891,
272
- "eval_steps_per_second": 4.949,
273
  "step": 84
274
  },
275
  {
276
  "epoch": 24.86,
277
  "eval_accuracy": 0.10869565217391304,
278
- "eval_loss": 113.81000518798828,
279
- "eval_runtime": 0.6011,
280
- "eval_samples_per_second": 76.522,
281
- "eval_steps_per_second": 4.991,
282
  "step": 87
283
  },
284
  {
285
  "epoch": 25.71,
286
- "learning_rate": 6.25e-06,
287
- "loss": 114.5216,
288
  "step": 90
289
  },
290
  {
291
  "epoch": 26.0,
292
  "eval_accuracy": 0.10869565217391304,
293
- "eval_loss": 113.80531311035156,
294
- "eval_runtime": 0.5966,
295
- "eval_samples_per_second": 77.098,
296
- "eval_steps_per_second": 5.028,
297
  "step": 91
298
  },
299
  {
300
  "epoch": 26.86,
301
  "eval_accuracy": 0.10869565217391304,
302
- "eval_loss": 113.80321502685547,
303
- "eval_runtime": 0.6162,
304
- "eval_samples_per_second": 74.657,
305
- "eval_steps_per_second": 4.869,
306
  "step": 94
307
  },
308
  {
309
  "epoch": 28.0,
310
  "eval_accuracy": 0.10869565217391304,
311
- "eval_loss": 113.803466796875,
312
- "eval_runtime": 0.5991,
313
- "eval_samples_per_second": 76.777,
314
- "eval_steps_per_second": 5.007,
315
  "step": 98
316
  },
317
  {
318
  "epoch": 28.57,
319
- "learning_rate": 4.166666666666667e-06,
320
- "loss": 112.7612,
321
  "step": 100
322
  },
323
  {
324
  "epoch": 28.86,
325
  "eval_accuracy": 0.10869565217391304,
326
- "eval_loss": 113.7991714477539,
327
- "eval_runtime": 0.6142,
328
- "eval_samples_per_second": 74.9,
329
- "eval_steps_per_second": 4.885,
330
  "step": 101
331
  },
332
  {
333
  "epoch": 30.0,
334
  "eval_accuracy": 0.10869565217391304,
335
- "eval_loss": 113.7939224243164,
336
- "eval_runtime": 0.6141,
337
- "eval_samples_per_second": 74.902,
338
- "eval_steps_per_second": 4.885,
339
  "step": 105
340
  },
341
  {
342
  "epoch": 30.86,
343
  "eval_accuracy": 0.10869565217391304,
344
- "eval_loss": 113.79671478271484,
345
- "eval_runtime": 0.6337,
346
- "eval_samples_per_second": 72.594,
347
- "eval_steps_per_second": 4.734,
348
  "step": 108
349
  },
350
  {
351
  "epoch": 31.43,
352
- "learning_rate": 2.0833333333333334e-06,
353
- "loss": 114.2748,
354
  "step": 110
355
  },
356
  {
357
  "epoch": 32.0,
358
  "eval_accuracy": 0.10869565217391304,
359
- "eval_loss": 113.79725646972656,
360
- "eval_runtime": 0.6392,
361
- "eval_samples_per_second": 71.97,
362
- "eval_steps_per_second": 4.694,
363
  "step": 112
364
  },
365
  {
366
  "epoch": 32.86,
367
  "eval_accuracy": 0.10869565217391304,
368
- "eval_loss": 113.79711151123047,
369
- "eval_runtime": 0.5956,
370
- "eval_samples_per_second": 77.228,
371
- "eval_steps_per_second": 5.037,
372
  "step": 115
373
  },
374
  {
375
  "epoch": 34.0,
376
  "eval_accuracy": 0.10869565217391304,
377
- "eval_loss": 113.7907943725586,
378
- "eval_runtime": 0.5981,
379
- "eval_samples_per_second": 76.906,
380
- "eval_steps_per_second": 5.016,
381
  "step": 119
382
  },
383
  {
384
  "epoch": 34.29,
385
  "learning_rate": 0.0,
386
- "loss": 114.0708,
387
  "step": 120
388
  },
389
  {
390
  "epoch": 34.29,
391
  "eval_accuracy": 0.10869565217391304,
392
- "eval_loss": 113.79315948486328,
393
- "eval_runtime": 0.5946,
394
- "eval_samples_per_second": 77.358,
395
- "eval_steps_per_second": 5.045,
396
  "step": 120
397
  },
398
  {
399
  "epoch": 34.29,
400
  "step": 120,
401
  "total_flos": 2.0027429927092224e+16,
402
- "train_loss": 113.75203348795573,
403
- "train_runtime": 131.4365,
404
- "train_samples_per_second": 64.822,
405
- "train_steps_per_second": 0.913
406
  }
407
  ],
408
  "logging_steps": 10,
 
11
  {
12
  "epoch": 0.86,
13
  "eval_accuracy": 0.10869565217391304,
14
+ "eval_loss": 125514790469632.0,
15
+ "eval_runtime": 0.6752,
16
+ "eval_samples_per_second": 68.133,
17
+ "eval_steps_per_second": 4.443,
18
  "step": 3
19
  },
20
  {
21
  "epoch": 2.0,
22
  "eval_accuracy": 0.10869565217391304,
23
+ "eval_loss": 125514790469632.0,
24
+ "eval_runtime": 0.6336,
25
+ "eval_samples_per_second": 72.596,
26
+ "eval_steps_per_second": 4.734,
27
  "step": 7
28
  },
29
  {
30
  "epoch": 2.86,
31
+ "learning_rate": 1.3983050847457627e-05,
32
+ "loss": 125815215043379.2,
33
  "step": 10
34
  },
35
  {
36
  "epoch": 2.86,
37
  "eval_accuracy": 0.10869565217391304,
38
+ "eval_loss": 125514790469632.0,
39
+ "eval_runtime": 0.5891,
40
+ "eval_samples_per_second": 78.08,
41
+ "eval_steps_per_second": 5.092,
42
  "step": 10
43
  },
44
  {
45
  "epoch": 4.0,
46
  "eval_accuracy": 0.10869565217391304,
47
+ "eval_loss": 125514790469632.0,
48
+ "eval_runtime": 0.6282,
49
+ "eval_samples_per_second": 73.224,
50
+ "eval_steps_per_second": 4.775,
51
  "step": 14
52
  },
53
  {
54
  "epoch": 4.86,
55
  "eval_accuracy": 0.10869565217391304,
56
+ "eval_loss": 125514790469632.0,
57
+ "eval_runtime": 0.7697,
58
+ "eval_samples_per_second": 59.765,
59
+ "eval_steps_per_second": 3.898,
60
  "step": 17
61
  },
62
  {
63
  "epoch": 5.71,
64
+ "learning_rate": 1.2711864406779661e-05,
65
+ "loss": 125111108842291.2,
66
  "step": 20
67
  },
68
  {
69
  "epoch": 6.0,
70
  "eval_accuracy": 0.10869565217391304,
71
+ "eval_loss": 125514790469632.0,
72
+ "eval_runtime": 0.6382,
73
+ "eval_samples_per_second": 72.082,
74
+ "eval_steps_per_second": 4.701,
75
  "step": 21
76
  },
77
  {
78
  "epoch": 6.86,
79
  "eval_accuracy": 0.10869565217391304,
80
+ "eval_loss": 125514790469632.0,
81
+ "eval_runtime": 0.6992,
82
+ "eval_samples_per_second": 65.792,
83
+ "eval_steps_per_second": 4.291,
84
  "step": 24
85
  },
86
  {
87
  "epoch": 8.0,
88
  "eval_accuracy": 0.10869565217391304,
89
+ "eval_loss": 125514790469632.0,
90
+ "eval_runtime": 0.5911,
91
+ "eval_samples_per_second": 77.815,
92
+ "eval_steps_per_second": 5.075,
93
  "step": 28
94
  },
95
  {
96
  "epoch": 8.57,
97
+ "learning_rate": 1.1440677966101694e-05,
98
+ "loss": 123174816789299.2,
99
  "step": 30
100
  },
101
  {
102
  "epoch": 8.86,
103
  "eval_accuracy": 0.10869565217391304,
104
+ "eval_loss": 125514790469632.0,
105
+ "eval_runtime": 0.6712,
106
+ "eval_samples_per_second": 68.539,
107
+ "eval_steps_per_second": 4.47,
108
  "step": 31
109
  },
110
  {
111
  "epoch": 10.0,
112
  "eval_accuracy": 0.10869565217391304,
113
+ "eval_loss": 125514790469632.0,
114
+ "eval_runtime": 0.6397,
115
+ "eval_samples_per_second": 71.913,
116
+ "eval_steps_per_second": 4.69,
117
  "step": 35
118
  },
119
  {
120
  "epoch": 10.86,
121
  "eval_accuracy": 0.10869565217391304,
122
+ "eval_loss": 125514790469632.0,
123
+ "eval_runtime": 0.5671,
124
+ "eval_samples_per_second": 81.109,
125
+ "eval_steps_per_second": 5.29,
126
  "step": 38
127
  },
128
  {
129
  "epoch": 11.43,
130
+ "learning_rate": 1.016949152542373e-05,
131
+ "loss": 127795517089382.4,
132
  "step": 40
133
  },
134
  {
135
  "epoch": 12.0,
136
  "eval_accuracy": 0.10869565217391304,
137
+ "eval_loss": 125514790469632.0,
138
+ "eval_runtime": 0.6006,
139
+ "eval_samples_per_second": 76.585,
140
+ "eval_steps_per_second": 4.995,
141
  "step": 42
142
  },
143
  {
144
  "epoch": 12.86,
145
  "eval_accuracy": 0.10869565217391304,
146
+ "eval_loss": 125514790469632.0,
147
+ "eval_runtime": 0.6276,
148
+ "eval_samples_per_second": 73.289,
149
+ "eval_steps_per_second": 4.78,
150
  "step": 45
151
  },
152
  {
153
  "epoch": 14.0,
154
  "eval_accuracy": 0.10869565217391304,
155
+ "eval_loss": 125514790469632.0,
156
+ "eval_runtime": 0.7082,
157
+ "eval_samples_per_second": 64.957,
158
+ "eval_steps_per_second": 4.236,
159
  "step": 49
160
  },
161
  {
162
  "epoch": 14.29,
163
+ "learning_rate": 8.898305084745763e-06,
164
+ "loss": 123834899575603.2,
165
  "step": 50
166
  },
167
  {
168
  "epoch": 14.86,
169
  "eval_accuracy": 0.10869565217391304,
170
+ "eval_loss": 125514790469632.0,
171
+ "eval_runtime": 0.6297,
172
+ "eval_samples_per_second": 73.056,
173
+ "eval_steps_per_second": 4.765,
174
  "step": 52
175
  },
176
  {
177
  "epoch": 16.0,
178
  "eval_accuracy": 0.10869565217391304,
179
+ "eval_loss": 125514790469632.0,
180
+ "eval_runtime": 0.5916,
181
+ "eval_samples_per_second": 77.75,
182
+ "eval_steps_per_second": 5.071,
183
  "step": 56
184
  },
185
  {
186
  "epoch": 16.86,
187
  "eval_accuracy": 0.10869565217391304,
188
+ "eval_loss": 125514790469632.0,
189
+ "eval_runtime": 0.6366,
190
+ "eval_samples_per_second": 72.253,
191
+ "eval_steps_per_second": 4.712,
192
  "step": 59
193
  },
194
  {
195
  "epoch": 17.14,
196
+ "learning_rate": 7.627118644067796e-06,
197
+ "loss": 124803052312985.6,
198
  "step": 60
199
  },
200
  {
201
  "epoch": 18.0,
202
  "eval_accuracy": 0.10869565217391304,
203
+ "eval_loss": 125514790469632.0,
204
+ "eval_runtime": 0.5896,
205
+ "eval_samples_per_second": 78.013,
206
+ "eval_steps_per_second": 5.088,
207
  "step": 63
208
  },
209
  {
210
  "epoch": 18.86,
211
  "eval_accuracy": 0.10869565217391304,
212
+ "eval_loss": 125514790469632.0,
213
+ "eval_runtime": 0.6182,
214
+ "eval_samples_per_second": 74.415,
215
+ "eval_steps_per_second": 4.853,
216
  "step": 66
217
  },
218
  {
219
  "epoch": 20.0,
220
+ "learning_rate": 6.3559322033898304e-06,
221
+ "loss": 125771218472140.8,
222
  "step": 70
223
  },
224
  {
225
  "epoch": 20.0,
226
  "eval_accuracy": 0.10869565217391304,
227
+ "eval_loss": 125514790469632.0,
228
+ "eval_runtime": 0.6432,
229
+ "eval_samples_per_second": 71.522,
230
+ "eval_steps_per_second": 4.664,
231
  "step": 70
232
  },
233
  {
234
  "epoch": 20.86,
235
  "eval_accuracy": 0.10869565217391304,
236
+ "eval_loss": 125514790469632.0,
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": 125514790469632.0,
246
+ "eval_runtime": 0.6517,
247
+ "eval_samples_per_second": 70.59,
248
+ "eval_steps_per_second": 4.604,
249
  "step": 77
250
  },
251
  {
252
  "epoch": 22.86,
253
+ "learning_rate": 5.084745762711865e-06,
254
+ "loss": 126299284701184.0,
255
  "step": 80
256
  },
257
  {
258
  "epoch": 22.86,
259
  "eval_accuracy": 0.10869565217391304,
260
+ "eval_loss": 125514790469632.0,
261
+ "eval_runtime": 0.6347,
262
+ "eval_samples_per_second": 72.481,
263
+ "eval_steps_per_second": 4.727,
264
  "step": 80
265
  },
266
  {
267
  "epoch": 24.0,
268
  "eval_accuracy": 0.10869565217391304,
269
+ "eval_loss": 125514790469632.0,
270
+ "eval_runtime": 0.6672,
271
+ "eval_samples_per_second": 68.95,
272
+ "eval_steps_per_second": 4.497,
273
  "step": 84
274
  },
275
  {
276
  "epoch": 24.86,
277
  "eval_accuracy": 0.10869565217391304,
278
+ "eval_loss": 125514790469632.0,
279
+ "eval_runtime": 0.5776,
280
+ "eval_samples_per_second": 79.634,
281
+ "eval_steps_per_second": 5.194,
282
  "step": 87
283
  },
284
  {
285
  "epoch": 25.71,
286
+ "learning_rate": 3.813559322033898e-06,
287
+ "loss": 126299271279411.2,
288
  "step": 90
289
  },
290
  {
291
  "epoch": 26.0,
292
  "eval_accuracy": 0.10869565217391304,
293
+ "eval_loss": 125514790469632.0,
294
+ "eval_runtime": 0.6411,
295
+ "eval_samples_per_second": 71.747,
296
+ "eval_steps_per_second": 4.679,
297
  "step": 91
298
  },
299
  {
300
  "epoch": 26.86,
301
  "eval_accuracy": 0.10869565217391304,
302
+ "eval_loss": 125514790469632.0,
303
+ "eval_runtime": 0.8482,
304
+ "eval_samples_per_second": 54.233,
305
+ "eval_steps_per_second": 3.537,
306
  "step": 94
307
  },
308
  {
309
  "epoch": 28.0,
310
  "eval_accuracy": 0.10869565217391304,
311
+ "eval_loss": 125514790469632.0,
312
+ "eval_runtime": 0.6537,
313
+ "eval_samples_per_second": 70.374,
314
+ "eval_steps_per_second": 4.59,
315
  "step": 98
316
  },
317
  {
318
  "epoch": 28.57,
319
+ "learning_rate": 2.5423728813559323e-06,
320
+ "loss": 124362979226419.2,
321
  "step": 100
322
  },
323
  {
324
  "epoch": 28.86,
325
  "eval_accuracy": 0.10869565217391304,
326
+ "eval_loss": 125514790469632.0,
327
+ "eval_runtime": 0.6962,
328
+ "eval_samples_per_second": 66.075,
329
+ "eval_steps_per_second": 4.309,
330
  "step": 101
331
  },
332
  {
333
  "epoch": 30.0,
334
  "eval_accuracy": 0.10869565217391304,
335
+ "eval_loss": 125514790469632.0,
336
+ "eval_runtime": 0.6326,
337
+ "eval_samples_per_second": 72.71,
338
+ "eval_steps_per_second": 4.742,
339
  "step": 105
340
  },
341
  {
342
  "epoch": 30.86,
343
  "eval_accuracy": 0.10869565217391304,
344
+ "eval_loss": 125514790469632.0,
345
+ "eval_runtime": 0.6402,
346
+ "eval_samples_per_second": 71.857,
347
+ "eval_steps_per_second": 4.686,
348
  "step": 108
349
  },
350
  {
351
  "epoch": 31.43,
352
+ "learning_rate": 1.2711864406779662e-06,
353
+ "loss": 126035251586662.4,
354
  "step": 110
355
  },
356
  {
357
  "epoch": 32.0,
358
  "eval_accuracy": 0.10869565217391304,
359
+ "eval_loss": 125514790469632.0,
360
+ "eval_runtime": 0.6121,
361
+ "eval_samples_per_second": 75.147,
362
+ "eval_steps_per_second": 4.901,
363
  "step": 112
364
  },
365
  {
366
  "epoch": 32.86,
367
  "eval_accuracy": 0.10869565217391304,
368
+ "eval_loss": 125514790469632.0,
369
+ "eval_runtime": 0.6086,
370
+ "eval_samples_per_second": 75.578,
371
+ "eval_steps_per_second": 4.929,
372
  "step": 115
373
  },
374
  {
375
  "epoch": 34.0,
376
  "eval_accuracy": 0.10869565217391304,
377
+ "eval_loss": 125514790469632.0,
378
+ "eval_runtime": 0.6832,
379
+ "eval_samples_per_second": 67.335,
380
+ "eval_steps_per_second": 4.391,
381
  "step": 119
382
  },
383
  {
384
  "epoch": 34.29,
385
  "learning_rate": 0.0,
386
+ "loss": 125815215043379.2,
387
  "step": 120
388
  },
389
  {
390
  "epoch": 34.29,
391
  "eval_accuracy": 0.10869565217391304,
392
+ "eval_loss": 125514790469632.0,
393
+ "eval_runtime": 0.7702,
394
+ "eval_samples_per_second": 59.727,
395
+ "eval_steps_per_second": 3.895,
396
  "step": 120
397
  },
398
  {
399
  "epoch": 34.29,
400
  "step": 120,
401
  "total_flos": 2.0027429927092224e+16,
402
+ "train_loss": 125426485830178.14,
403
+ "train_runtime": 118.5658,
404
+ "train_samples_per_second": 71.859,
405
+ "train_steps_per_second": 1.012
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:a3df9ef77f964a231a079193edbe54fab4c39d9bd25184de47de575af773cd47
3
  size 4728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a91f88bea1e185b418ec30a052c8063d1bfa737392ffba8d69a2062f259c9369
3
  size 4728