Hugging Face's logo

Augusto777
/
swinv2-tiny-patch4-window8-256-OT

TensorBoard
Safetensors
swinv2
Generated from Trainer
Eval Results
Model card Files Metrics Community
Augusto777 commited on
Commit
39ca2be
·
verified ·
1 Parent(s): 734999f

End of training

Browse files
Files changed (11) hide show
  1. README.md +114 -0
  2. all_results.json +12 -0
  3. config.json +58 -0
  4. eval_results.json +8 -0
  5. model.safetensors +3 -0
  6. preprocessor_config.json +22 -0
  7. runs/Dec01_08-55-13_DESKTOP-SKBE9FB/events.out.tfevents.1733064915.DESKTOP-SKBE9FB.14272.0 +3 -0
  8. runs/Dec01_08-55-13_DESKTOP-SKBE9FB/events.out.tfevents.1733065552.DESKTOP-SKBE9FB.14272.1 +3 -0
  9. train_results.json +7 -0
  10. trainer_state.json +483 -0
  11. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,114 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: microsoft/swinv2-tiny-patch4-window8-256
4
+ tags:
5
+ - generated_from_trainer
6
+ datasets:
7
+ - imagefolder
8
+ metrics:
9
+ - accuracy
10
+ model-index:
11
+ - name: swinv2-tiny-patch4-window8-256-OT
12
+ results:
13
+ - task:
14
+ name: Image Classification
15
+ type: image-classification
16
+ dataset:
17
+ name: imagefolder
18
+ type: imagefolder
19
+ config: default
20
+ split: validation
21
+ args: default
22
+ metrics:
23
+ - name: Accuracy
24
+ type: accuracy
25
+ value: 0.8225806451612904
26
+ ---
27
+
28
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
29
+ should probably proofread and complete it, then remove this comment. -->
30
+
31
+ # swinv2-tiny-patch4-window8-256-OT
32
+
33
+ This model is a fine-tuned version of [microsoft/swinv2-tiny-patch4-window8-256](https://huggingface.co/microsoft/swinv2-tiny-patch4-window8-256) on the imagefolder dataset.
34
+ It achieves the following results on the evaluation set:
35
+ - Loss: 0.6192
36
+ - Accuracy: 0.8226
37
+
38
+ ## Model description
39
+
40
+ More information needed
41
+
42
+ ## Intended uses & limitations
43
+
44
+ More information needed
45
+
46
+ ## Training and evaluation data
47
+
48
+ More information needed
49
+
50
+ ## Training procedure
51
+
52
+ ### Training hyperparameters
53
+
54
+ The following hyperparameters were used during training:
55
+ - learning_rate: 0.00015
56
+ - train_batch_size: 16
57
+ - eval_batch_size: 16
58
+ - seed: 42
59
+ - gradient_accumulation_steps: 4
60
+ - total_train_batch_size: 64
61
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
62
+ - lr_scheduler_type: linear
63
+ - lr_scheduler_warmup_ratio: 0.1
64
+ - num_epochs: 40
65
+
66
+ ### Training results
67
+
68
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
70
+ | No log | 0.91 | 5 | 8.8439 | 0.0806 |
71
+ | 8.7922 | 2.0 | 11 | 8.0016 | 0.0806 |
72
+ | 8.7922 | 2.91 | 16 | 6.0009 | 0.0806 |
73
+ | 6.5264 | 4.0 | 22 | 2.7431 | 0.0806 |
74
+ | 6.5264 | 4.91 | 27 | 1.3018 | 0.4516 |
75
+ | 2.16 | 6.0 | 33 | 1.2696 | 0.4516 |
76
+ | 2.16 | 6.91 | 38 | 1.2057 | 0.4516 |
77
+ | 1.2876 | 8.0 | 44 | 1.2157 | 0.4516 |
78
+ | 1.2876 | 8.91 | 49 | 1.2459 | 0.4516 |
79
+ | 1.2456 | 10.0 | 55 | 1.2110 | 0.4516 |
80
+ | 1.1901 | 10.91 | 60 | 1.1861 | 0.4516 |
81
+ | 1.1901 | 12.0 | 66 | 1.0847 | 0.4677 |
82
+ | 1.0665 | 12.91 | 71 | 1.0944 | 0.4677 |
83
+ | 1.0665 | 14.0 | 77 | 1.1854 | 0.4677 |
84
+ | 1.033 | 14.91 | 82 | 1.0252 | 0.5 |
85
+ | 1.033 | 16.0 | 88 | 1.2164 | 0.5161 |
86
+ | 1.0323 | 16.91 | 93 | 1.0643 | 0.5 |
87
+ | 1.0323 | 18.0 | 99 | 0.9802 | 0.6613 |
88
+ | 0.9329 | 18.91 | 104 | 0.9475 | 0.5968 |
89
+ | 0.8619 | 20.0 | 110 | 0.9115 | 0.6452 |
90
+ | 0.8619 | 20.91 | 115 | 0.8894 | 0.6452 |
91
+ | 0.8019 | 22.0 | 121 | 0.8276 | 0.6935 |
92
+ | 0.8019 | 22.91 | 126 | 0.8156 | 0.6774 |
93
+ | 0.7675 | 24.0 | 132 | 0.7928 | 0.6290 |
94
+ | 0.7675 | 24.91 | 137 | 0.7163 | 0.7419 |
95
+ | 0.6762 | 26.0 | 143 | 0.7388 | 0.6774 |
96
+ | 0.6762 | 26.91 | 148 | 0.6519 | 0.7581 |
97
+ | 0.6771 | 28.0 | 154 | 0.6710 | 0.7419 |
98
+ | 0.6771 | 28.91 | 159 | 0.6074 | 0.7581 |
99
+ | 0.6424 | 30.0 | 165 | 0.6729 | 0.7258 |
100
+ | 0.6139 | 30.91 | 170 | 0.5744 | 0.7903 |
101
+ | 0.6139 | 32.0 | 176 | 0.6192 | 0.8226 |
102
+ | 0.5713 | 32.91 | 181 | 0.6453 | 0.7903 |
103
+ | 0.5713 | 34.0 | 187 | 0.6392 | 0.7903 |
104
+ | 0.5462 | 34.91 | 192 | 0.5956 | 0.8226 |
105
+ | 0.5462 | 36.0 | 198 | 0.5893 | 0.8226 |
106
+ | 0.5393 | 36.36 | 200 | 0.5898 | 0.8226 |
107
+
108
+
109
+ ### Framework versions
110
+
111
+ - Transformers 4.36.2
112
+ - Pytorch 2.1.2+cu118
113
+ - Datasets 2.16.1
114
+ - Tokenizers 0.15.0
all_results.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 36.36,
3
+ "eval_accuracy": 0.8225806451612904,
4
+ "eval_loss": 0.6192476749420166,
5
+ "eval_runtime": 2.2055,
6
+ "eval_samples_per_second": 28.111,
7
+ "eval_steps_per_second": 1.814,
8
+ "train_loss": 1.5982162952423096,
9
+ "train_runtime": 635.1405,
10
+ "train_samples_per_second": 22.042,
11
+ "train_steps_per_second": 0.315
12
+ }
config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/swinv2-tiny-patch4-window8-256",
3
+ "architectures": [
4
+ "Swinv2ForImageClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.0,
7
+ "depths": [
8
+ 2,
9
+ 2,
10
+ 6,
11
+ 2
12
+ ],
13
+ "drop_path_rate": 0.1,
14
+ "embed_dim": 96,
15
+ "encoder_stride": 32,
16
+ "hidden_act": "gelu",
17
+ "hidden_dropout_prob": 0.0,
18
+ "hidden_size": 768,
19
+ "id2label": {
20
+ "0": "active",
21
+ "1": "active-inactive",
22
+ "2": "healthy",
23
+ "3": "inactive"
24
+ },
25
+ "image_size": 256,
26
+ "initializer_range": 0.02,
27
+ "label2id": {
28
+ "active": 0,
29
+ "active-inactive": 1,
30
+ "healthy": 2,
31
+ "inactive": 3
32
+ },
33
+ "layer_norm_eps": 1e-05,
34
+ "mlp_ratio": 4.0,
35
+ "model_type": "swinv2",
36
+ "num_channels": 3,
37
+ "num_heads": [
38
+ 3,
39
+ 6,
40
+ 12,
41
+ 24
42
+ ],
43
+ "num_layers": 4,
44
+ "patch_size": 4,
45
+ "path_norm": true,
46
+ "pretrained_window_sizes": [
47
+ 0,
48
+ 0,
49
+ 0,
50
+ 0
51
+ ],
52
+ "problem_type": "single_label_classification",
53
+ "qkv_bias": true,
54
+ "torch_dtype": "float32",
55
+ "transformers_version": "4.36.2",
56
+ "use_absolute_embeddings": false,
57
+ "window_size": 8
58
+ }
eval_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 36.36,
3
+ "eval_accuracy": 0.8225806451612904,
4
+ "eval_loss": 0.6192476749420166,
5
+ "eval_runtime": 2.2055,
6
+ "eval_samples_per_second": 28.111,
7
+ "eval_steps_per_second": 1.814
8
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3214c6824a0b80c4170aab8f439a40e0105af49a25705134f03e98077009bd31
3
+ size 110356296
preprocessor_config.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_normalize": true,
3
+ "do_rescale": true,
4
+ "do_resize": true,
5
+ "image_mean": [
6
+ 0.485,
7
+ 0.456,
8
+ 0.406
9
+ ],
10
+ "image_processor_type": "ViTImageProcessor",
11
+ "image_std": [
12
+ 0.229,
13
+ 0.224,
14
+ 0.225
15
+ ],
16
+ "resample": 3,
17
+ "rescale_factor": 0.00392156862745098,
18
+ "size": {
19
+ "height": 256,
20
+ "width": 256
21
+ }
22
+ }
runs/Dec01_08-55-13_DESKTOP-SKBE9FB/events.out.tfevents.1733064915.DESKTOP-SKBE9FB.14272.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c184e0f04dbf34f59f3d9cc7b4724f7be5a53ee2a5b6763231bc1a38512b8fb
3
+ size 20077
runs/Dec01_08-55-13_DESKTOP-SKBE9FB/events.out.tfevents.1733065552.DESKTOP-SKBE9FB.14272.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ee16268c9dd2b7d3009690c6049a65e008d1528314aeac071ae080fd2bc0b12
3
+ size 411
train_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 36.36,
3
+ "train_loss": 1.5982162952423096,
4
+ "train_runtime": 635.1405,
5
+ "train_samples_per_second": 22.042,
6
+ "train_steps_per_second": 0.315
7
+ }
trainer_state.json ADDED
@@ -0,0 +1,483 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8225806451612904,
3
+ "best_model_checkpoint": "swinv2-tiny-patch4-window8-256-OT\\checkpoint-176",
4
+ "epoch": 36.36363636363637,
5
+ "eval_steps": 500,
6
+ "global_step": 200,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.91,
13
+ "eval_accuracy": 0.08064516129032258,
14
+ "eval_loss": 8.843916893005371,
15
+ "eval_runtime": 2.8151,
16
+ "eval_samples_per_second": 22.024,
17
+ "eval_steps_per_second": 1.421,
18
+ "step": 5
19
+ },
20
+ {
21
+ "epoch": 1.82,
22
+ "learning_rate": 7.5e-05,
23
+ "loss": 8.7922,
24
+ "step": 10
25
+ },
26
+ {
27
+ "epoch": 2.0,
28
+ "eval_accuracy": 0.08064516129032258,
29
+ "eval_loss": 8.001582145690918,
30
+ "eval_runtime": 2.1045,
31
+ "eval_samples_per_second": 29.461,
32
+ "eval_steps_per_second": 1.901,
33
+ "step": 11
34
+ },
35
+ {
36
+ "epoch": 2.91,
37
+ "eval_accuracy": 0.08064516129032258,
38
+ "eval_loss": 6.000851154327393,
39
+ "eval_runtime": 2.0735,
40
+ "eval_samples_per_second": 29.901,
41
+ "eval_steps_per_second": 1.929,
42
+ "step": 16
43
+ },
44
+ {
45
+ "epoch": 3.64,
46
+ "learning_rate": 0.00015,
47
+ "loss": 6.5264,
48
+ "step": 20
49
+ },
50
+ {
51
+ "epoch": 4.0,
52
+ "eval_accuracy": 0.08064516129032258,
53
+ "eval_loss": 2.7431113719940186,
54
+ "eval_runtime": 2.1035,
55
+ "eval_samples_per_second": 29.475,
56
+ "eval_steps_per_second": 1.902,
57
+ "step": 22
58
+ },
59
+ {
60
+ "epoch": 4.91,
61
+ "eval_accuracy": 0.45161290322580644,
62
+ "eval_loss": 1.3018240928649902,
63
+ "eval_runtime": 2.0906,
64
+ "eval_samples_per_second": 29.656,
65
+ "eval_steps_per_second": 1.913,
66
+ "step": 27
67
+ },
68
+ {
69
+ "epoch": 5.45,
70
+ "learning_rate": 0.00014166666666666665,
71
+ "loss": 2.16,
72
+ "step": 30
73
+ },
74
+ {
75
+ "epoch": 6.0,
76
+ "eval_accuracy": 0.45161290322580644,
77
+ "eval_loss": 1.2696114778518677,
78
+ "eval_runtime": 2.0785,
79
+ "eval_samples_per_second": 29.829,
80
+ "eval_steps_per_second": 1.924,
81
+ "step": 33
82
+ },
83
+ {
84
+ "epoch": 6.91,
85
+ "eval_accuracy": 0.45161290322580644,
86
+ "eval_loss": 1.2057440280914307,
87
+ "eval_runtime": 2.5671,
88
+ "eval_samples_per_second": 24.152,
89
+ "eval_steps_per_second": 1.558,
90
+ "step": 38
91
+ },
92
+ {
93
+ "epoch": 7.27,
94
+ "learning_rate": 0.0001333333333333333,
95
+ "loss": 1.2876,
96
+ "step": 40
97
+ },
98
+ {
99
+ "epoch": 8.0,
100
+ "eval_accuracy": 0.45161290322580644,
101
+ "eval_loss": 1.2157402038574219,
102
+ "eval_runtime": 2.1295,
103
+ "eval_samples_per_second": 29.115,
104
+ "eval_steps_per_second": 1.878,
105
+ "step": 44
106
+ },
107
+ {
108
+ "epoch": 8.91,
109
+ "eval_accuracy": 0.45161290322580644,
110
+ "eval_loss": 1.245875597000122,
111
+ "eval_runtime": 2.141,
112
+ "eval_samples_per_second": 28.958,
113
+ "eval_steps_per_second": 1.868,
114
+ "step": 49
115
+ },
116
+ {
117
+ "epoch": 9.09,
118
+ "learning_rate": 0.000125,
119
+ "loss": 1.2456,
120
+ "step": 50
121
+ },
122
+ {
123
+ "epoch": 10.0,
124
+ "eval_accuracy": 0.45161290322580644,
125
+ "eval_loss": 1.210959792137146,
126
+ "eval_runtime": 2.181,
127
+ "eval_samples_per_second": 28.427,
128
+ "eval_steps_per_second": 1.834,
129
+ "step": 55
130
+ },
131
+ {
132
+ "epoch": 10.91,
133
+ "learning_rate": 0.00011666666666666665,
134
+ "loss": 1.1901,
135
+ "step": 60
136
+ },
137
+ {
138
+ "epoch": 10.91,
139
+ "eval_accuracy": 0.45161290322580644,
140
+ "eval_loss": 1.1861207485198975,
141
+ "eval_runtime": 2.094,
142
+ "eval_samples_per_second": 29.608,
143
+ "eval_steps_per_second": 1.91,
144
+ "step": 60
145
+ },
146
+ {
147
+ "epoch": 12.0,
148
+ "eval_accuracy": 0.46774193548387094,
149
+ "eval_loss": 1.0847262144088745,
150
+ "eval_runtime": 2.212,
151
+ "eval_samples_per_second": 28.028,
152
+ "eval_steps_per_second": 1.808,
153
+ "step": 66
154
+ },
155
+ {
156
+ "epoch": 12.73,
157
+ "learning_rate": 0.00010833333333333333,
158
+ "loss": 1.0665,
159
+ "step": 70
160
+ },
161
+ {
162
+ "epoch": 12.91,
163
+ "eval_accuracy": 0.46774193548387094,
164
+ "eval_loss": 1.0943629741668701,
165
+ "eval_runtime": 2.08,
166
+ "eval_samples_per_second": 29.808,
167
+ "eval_steps_per_second": 1.923,
168
+ "step": 71
169
+ },
170
+ {
171
+ "epoch": 14.0,
172
+ "eval_accuracy": 0.46774193548387094,
173
+ "eval_loss": 1.1853879690170288,
174
+ "eval_runtime": 2.093,
175
+ "eval_samples_per_second": 29.623,
176
+ "eval_steps_per_second": 1.911,
177
+ "step": 77
178
+ },
179
+ {
180
+ "epoch": 14.55,
181
+ "learning_rate": 9.999999999999999e-05,
182
+ "loss": 1.033,
183
+ "step": 80
184
+ },
185
+ {
186
+ "epoch": 14.91,
187
+ "eval_accuracy": 0.5,
188
+ "eval_loss": 1.025220274925232,
189
+ "eval_runtime": 2.4167,
190
+ "eval_samples_per_second": 25.655,
191
+ "eval_steps_per_second": 1.655,
192
+ "step": 82
193
+ },
194
+ {
195
+ "epoch": 16.0,
196
+ "eval_accuracy": 0.5161290322580645,
197
+ "eval_loss": 1.216417908668518,
198
+ "eval_runtime": 2.2296,
199
+ "eval_samples_per_second": 27.808,
200
+ "eval_steps_per_second": 1.794,
201
+ "step": 88
202
+ },
203
+ {
204
+ "epoch": 16.36,
205
+ "learning_rate": 9.166666666666667e-05,
206
+ "loss": 1.0323,
207
+ "step": 90
208
+ },
209
+ {
210
+ "epoch": 16.91,
211
+ "eval_accuracy": 0.5,
212
+ "eval_loss": 1.0642980337142944,
213
+ "eval_runtime": 2.199,
214
+ "eval_samples_per_second": 28.194,
215
+ "eval_steps_per_second": 1.819,
216
+ "step": 93
217
+ },
218
+ {
219
+ "epoch": 18.0,
220
+ "eval_accuracy": 0.6612903225806451,
221
+ "eval_loss": 0.9802310466766357,
222
+ "eval_runtime": 2.1395,
223
+ "eval_samples_per_second": 28.979,
224
+ "eval_steps_per_second": 1.87,
225
+ "step": 99
226
+ },
227
+ {
228
+ "epoch": 18.18,
229
+ "learning_rate": 8.333333333333333e-05,
230
+ "loss": 0.9329,
231
+ "step": 100
232
+ },
233
+ {
234
+ "epoch": 18.91,
235
+ "eval_accuracy": 0.5967741935483871,
236
+ "eval_loss": 0.9474769830703735,
237
+ "eval_runtime": 2.179,
238
+ "eval_samples_per_second": 28.453,
239
+ "eval_steps_per_second": 1.836,
240
+ "step": 104
241
+ },
242
+ {
243
+ "epoch": 20.0,
244
+ "learning_rate": 7.5e-05,
245
+ "loss": 0.8619,
246
+ "step": 110
247
+ },
248
+ {
249
+ "epoch": 20.0,
250
+ "eval_accuracy": 0.6451612903225806,
251
+ "eval_loss": 0.9114610552787781,
252
+ "eval_runtime": 2.125,
253
+ "eval_samples_per_second": 29.176,
254
+ "eval_steps_per_second": 1.882,
255
+ "step": 110
256
+ },
257
+ {
258
+ "epoch": 20.91,
259
+ "eval_accuracy": 0.6451612903225806,
260
+ "eval_loss": 0.8893528580665588,
261
+ "eval_runtime": 2.2755,
262
+ "eval_samples_per_second": 27.246,
263
+ "eval_steps_per_second": 1.758,
264
+ "step": 115
265
+ },
266
+ {
267
+ "epoch": 21.82,
268
+ "learning_rate": 6.666666666666666e-05,
269
+ "loss": 0.8019,
270
+ "step": 120
271
+ },
272
+ {
273
+ "epoch": 22.0,
274
+ "eval_accuracy": 0.6935483870967742,
275
+ "eval_loss": 0.8276461958885193,
276
+ "eval_runtime": 2.182,
277
+ "eval_samples_per_second": 28.414,
278
+ "eval_steps_per_second": 1.833,
279
+ "step": 121
280
+ },
281
+ {
282
+ "epoch": 22.91,
283
+ "eval_accuracy": 0.6774193548387096,
284
+ "eval_loss": 0.8156123757362366,
285
+ "eval_runtime": 2.1835,
286
+ "eval_samples_per_second": 28.394,
287
+ "eval_steps_per_second": 1.832,
288
+ "step": 126
289
+ },
290
+ {
291
+ "epoch": 23.64,
292
+ "learning_rate": 5.8333333333333326e-05,
293
+ "loss": 0.7675,
294
+ "step": 130
295
+ },
296
+ {
297
+ "epoch": 24.0,
298
+ "eval_accuracy": 0.6290322580645161,
299
+ "eval_loss": 0.7928251624107361,
300
+ "eval_runtime": 2.7367,
301
+ "eval_samples_per_second": 22.655,
302
+ "eval_steps_per_second": 1.462,
303
+ "step": 132
304
+ },
305
+ {
306
+ "epoch": 24.91,
307
+ "eval_accuracy": 0.7419354838709677,
308
+ "eval_loss": 0.7163397669792175,
309
+ "eval_runtime": 2.3511,
310
+ "eval_samples_per_second": 26.371,
311
+ "eval_steps_per_second": 1.701,
312
+ "step": 137
313
+ },
314
+ {
315
+ "epoch": 25.45,
316
+ "learning_rate": 4.9999999999999996e-05,
317
+ "loss": 0.6762,
318
+ "step": 140
319
+ },
320
+ {
321
+ "epoch": 26.0,
322
+ "eval_accuracy": 0.6774193548387096,
323
+ "eval_loss": 0.7387820482254028,
324
+ "eval_runtime": 2.261,
325
+ "eval_samples_per_second": 27.421,
326
+ "eval_steps_per_second": 1.769,
327
+ "step": 143
328
+ },
329
+ {
330
+ "epoch": 26.91,
331
+ "eval_accuracy": 0.7580645161290323,
332
+ "eval_loss": 0.6518718004226685,
333
+ "eval_runtime": 2.2715,
334
+ "eval_samples_per_second": 27.294,
335
+ "eval_steps_per_second": 1.761,
336
+ "step": 148
337
+ },
338
+ {
339
+ "epoch": 27.27,
340
+ "learning_rate": 4.1666666666666665e-05,
341
+ "loss": 0.6771,
342
+ "step": 150
343
+ },
344
+ {
345
+ "epoch": 28.0,
346
+ "eval_accuracy": 0.7419354838709677,
347
+ "eval_loss": 0.6709696054458618,
348
+ "eval_runtime": 2.6851,
349
+ "eval_samples_per_second": 23.09,
350
+ "eval_steps_per_second": 1.49,
351
+ "step": 154
352
+ },
353
+ {
354
+ "epoch": 28.91,
355
+ "eval_accuracy": 0.7580645161290323,
356
+ "eval_loss": 0.6073653697967529,
357
+ "eval_runtime": 2.3635,
358
+ "eval_samples_per_second": 26.232,
359
+ "eval_steps_per_second": 1.692,
360
+ "step": 159
361
+ },
362
+ {
363
+ "epoch": 29.09,
364
+ "learning_rate": 3.333333333333333e-05,
365
+ "loss": 0.6424,
366
+ "step": 160
367
+ },
368
+ {
369
+ "epoch": 30.0,
370
+ "eval_accuracy": 0.7258064516129032,
371
+ "eval_loss": 0.672946035861969,
372
+ "eval_runtime": 2.2598,
373
+ "eval_samples_per_second": 27.436,
374
+ "eval_steps_per_second": 1.77,
375
+ "step": 165
376
+ },
377
+ {
378
+ "epoch": 30.91,
379
+ "learning_rate": 2.4999999999999998e-05,
380
+ "loss": 0.6139,
381
+ "step": 170
382
+ },
383
+ {
384
+ "epoch": 30.91,
385
+ "eval_accuracy": 0.7903225806451613,
386
+ "eval_loss": 0.5744480490684509,
387
+ "eval_runtime": 2.189,
388
+ "eval_samples_per_second": 28.323,
389
+ "eval_steps_per_second": 1.827,
390
+ "step": 170
391
+ },
392
+ {
393
+ "epoch": 32.0,
394
+ "eval_accuracy": 0.8225806451612904,
395
+ "eval_loss": 0.6192476749420166,
396
+ "eval_runtime": 2.142,
397
+ "eval_samples_per_second": 28.945,
398
+ "eval_steps_per_second": 1.867,
399
+ "step": 176
400
+ },
401
+ {
402
+ "epoch": 32.73,
403
+ "learning_rate": 1.6666666666666664e-05,
404
+ "loss": 0.5713,
405
+ "step": 180
406
+ },
407
+ {
408
+ "epoch": 32.91,
409
+ "eval_accuracy": 0.7903225806451613,
410
+ "eval_loss": 0.6452686190605164,
411
+ "eval_runtime": 2.1495,
412
+ "eval_samples_per_second": 28.844,
413
+ "eval_steps_per_second": 1.861,
414
+ "step": 181
415
+ },
416
+ {
417
+ "epoch": 34.0,
418
+ "eval_accuracy": 0.7903225806451613,
419
+ "eval_loss": 0.6392035484313965,
420
+ "eval_runtime": 2.1965,
421
+ "eval_samples_per_second": 28.226,
422
+ "eval_steps_per_second": 1.821,
423
+ "step": 187
424
+ },
425
+ {
426
+ "epoch": 34.55,
427
+ "learning_rate": 8.333333333333332e-06,
428
+ "loss": 0.5462,
429
+ "step": 190
430
+ },
431
+ {
432
+ "epoch": 34.91,
433
+ "eval_accuracy": 0.8225806451612904,
434
+ "eval_loss": 0.5955818295478821,
435
+ "eval_runtime": 2.247,
436
+ "eval_samples_per_second": 27.592,
437
+ "eval_steps_per_second": 1.78,
438
+ "step": 192
439
+ },
440
+ {
441
+ "epoch": 36.0,
442
+ "eval_accuracy": 0.8225806451612904,
443
+ "eval_loss": 0.5892814993858337,
444
+ "eval_runtime": 2.5326,
445
+ "eval_samples_per_second": 24.481,
446
+ "eval_steps_per_second": 1.579,
447
+ "step": 198
448
+ },
449
+ {
450
+ "epoch": 36.36,
451
+ "learning_rate": 0.0,
452
+ "loss": 0.5393,
453
+ "step": 200
454
+ },
455
+ {
456
+ "epoch": 36.36,
457
+ "eval_accuracy": 0.8225806451612904,
458
+ "eval_loss": 0.5898378491401672,
459
+ "eval_runtime": 2.2395,
460
+ "eval_samples_per_second": 27.685,
461
+ "eval_steps_per_second": 1.786,
462
+ "step": 200
463
+ },
464
+ {
465
+ "epoch": 36.36,
466
+ "step": 200,
467
+ "total_flos": 4.141200256480051e+17,
468
+ "train_loss": 1.5982162952423096,
469
+ "train_runtime": 635.1405,
470
+ "train_samples_per_second": 22.042,
471
+ "train_steps_per_second": 0.315
472
+ }
473
+ ],
474
+ "logging_steps": 10,
475
+ "max_steps": 200,
476
+ "num_input_tokens_seen": 0,
477
+ "num_train_epochs": 40,
478
+ "save_steps": 500,
479
+ "total_flos": 4.141200256480051e+17,
480
+ "train_batch_size": 16,
481
+ "trial_name": null,
482
+ "trial_params": null
483
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:321e93e7bf62b0b233add9dd1100daadcfb5f668f9371973e023e25b48742f3d
3
+ size 4728