Hugging Face's logo

Augusto777
/
swinv2-tiny-patch4-window8-256-RH-6e-5

TensorBoard
Safetensors
swinv2
Generated from Trainer
Eval Results (legacy)
Model card Files
xet
 Metrics Community
Augusto777 commited on
Commit
4f9fb8b
·
verified ·
1 Parent(s): 52347e1

End of training

Browse files
Files changed (11) hide show
  1. README.md +117 -0
  2. all_results.json +12 -0
  3. config.json +54 -0
  4. eval_results.json +8 -0
  5. model.safetensors +3 -0
  6. preprocessor_config.json +22 -0
  7. runs/Dec01_10-28-07_DESKTOP-SKBE9FB/events.out.tfevents.1733070489.DESKTOP-SKBE9FB.1292.0 +3 -0
  8. runs/Dec01_10-28-07_DESKTOP-SKBE9FB/events.out.tfevents.1733071075.DESKTOP-SKBE9FB.1292.1 +3 -0
  9. train_results.json +7 -0
  10. trainer_state.json +582 -0
  11. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,117 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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-RH-6e-5
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: 0.6355140186915887
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-RH-6e-5
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: 0.6666
36
+ - Accuracy: 0.6355
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: 6e-05
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 | 1.0 | 8 | 4.6188 | 0.4112 |
71
+ | 4.5343 | 2.0 | 16 | 4.4096 | 0.4112 |
72
+ | 4.5396 | 3.0 | 24 | 3.6784 | 0.4112 |
73
+ | 3.621 | 4.0 | 32 | 2.4800 | 0.4112 |
74
+ | 2.1758 | 5.0 | 40 | 1.2118 | 0.4112 |
75
+ | 2.1758 | 6.0 | 48 | 0.6790 | 0.5888 |
76
+ | 0.8871 | 7.0 | 56 | 0.7903 | 0.5888 |
77
+ | 0.7484 | 8.0 | 64 | 0.7640 | 0.5888 |
78
+ | 0.7414 | 9.0 | 72 | 0.6789 | 0.5888 |
79
+ | 0.6868 | 10.0 | 80 | 0.6770 | 0.5888 |
80
+ | 0.6868 | 11.0 | 88 | 0.6775 | 0.5888 |
81
+ | 0.6771 | 12.0 | 96 | 0.6993 | 0.5888 |
82
+ | 0.7082 | 13.0 | 104 | 0.6765 | 0.5888 |
83
+ | 0.6993 | 14.0 | 112 | 0.6746 | 0.5888 |
84
+ | 0.6798 | 15.0 | 120 | 0.6759 | 0.5888 |
85
+ | 0.6798 | 16.0 | 128 | 0.6734 | 0.5888 |
86
+ | 0.6734 | 17.0 | 136 | 0.6739 | 0.5888 |
87
+ | 0.6832 | 18.0 | 144 | 0.7039 | 0.5888 |
88
+ | 0.6825 | 19.0 | 152 | 0.6767 | 0.5888 |
89
+ | 0.6663 | 20.0 | 160 | 0.6707 | 0.5888 |
90
+ | 0.6663 | 21.0 | 168 | 0.6798 | 0.5888 |
91
+ | 0.6646 | 22.0 | 176 | 0.6723 | 0.5794 |
92
+ | 0.6764 | 23.0 | 184 | 0.6889 | 0.5888 |
93
+ | 0.6808 | 24.0 | 192 | 0.6994 | 0.5888 |
94
+ | 0.6766 | 25.0 | 200 | 0.6691 | 0.5888 |
95
+ | 0.6766 | 26.0 | 208 | 0.6837 | 0.5888 |
96
+ | 0.6698 | 27.0 | 216 | 0.6738 | 0.5701 |
97
+ | 0.6549 | 28.0 | 224 | 0.6695 | 0.5794 |
98
+ | 0.6442 | 29.0 | 232 | 0.7157 | 0.5794 |
99
+ | 0.649 | 30.0 | 240 | 0.6726 | 0.6075 |
100
+ | 0.649 | 31.0 | 248 | 0.6839 | 0.5794 |
101
+ | 0.6388 | 32.0 | 256 | 0.6797 | 0.5888 |
102
+ | 0.6416 | 33.0 | 264 | 0.6714 | 0.5981 |
103
+ | 0.6398 | 34.0 | 272 | 0.6730 | 0.6075 |
104
+ | 0.6522 | 35.0 | 280 | 0.6953 | 0.5794 |
105
+ | 0.6522 | 36.0 | 288 | 0.6609 | 0.5701 |
106
+ | 0.6376 | 37.0 | 296 | 0.6619 | 0.5794 |
107
+ | 0.6441 | 38.0 | 304 | 0.6654 | 0.6262 |
108
+ | 0.6149 | 39.0 | 312 | 0.6666 | 0.6355 |
109
+ | 0.623 | 40.0 | 320 | 0.6679 | 0.6355 |
110
+
111
+
112
+ ### Framework versions
113
+
114
+ - Transformers 4.36.2
115
+ - Pytorch 2.1.2+cu118
116
+ - Datasets 2.16.1
117
+ - Tokenizers 0.15.0
all_results.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 40.0,
3
+ "eval_accuracy": 0.6355140186915887,
4
+ "eval_loss": 0.666593611240387,
5
+ "eval_runtime": 2.2345,
6
+ "eval_samples_per_second": 47.885,
7
+ "eval_steps_per_second": 3.133,
8
+ "train_loss": 1.0566354274749756,
9
+ "train_runtime": 583.642,
10
+ "train_samples_per_second": 34.131,
11
+ "train_steps_per_second": 0.548
12
+ }
config.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "HR",
21
+ "1": "No HR"
22
+ },
23
+ "image_size": 256,
24
+ "initializer_range": 0.02,
25
+ "label2id": {
26
+ "HR": 0,
27
+ "No HR": 1
28
+ },
29
+ "layer_norm_eps": 1e-05,
30
+ "mlp_ratio": 4.0,
31
+ "model_type": "swinv2",
32
+ "num_channels": 3,
33
+ "num_heads": [
34
+ 3,
35
+ 6,
36
+ 12,
37
+ 24
38
+ ],
39
+ "num_layers": 4,
40
+ "patch_size": 4,
41
+ "path_norm": true,
42
+ "pretrained_window_sizes": [
43
+ 0,
44
+ 0,
45
+ 0,
46
+ 0
47
+ ],
48
+ "problem_type": "single_label_classification",
49
+ "qkv_bias": true,
50
+ "torch_dtype": "float32",
51
+ "transformers_version": "4.36.2",
52
+ "use_absolute_embeddings": false,
53
+ "window_size": 8
54
+ }
eval_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 40.0,
3
+ "eval_accuracy": 0.6355140186915887,
4
+ "eval_loss": 0.666593611240387,
5
+ "eval_runtime": 2.2345,
6
+ "eval_samples_per_second": 47.885,
7
+ "eval_steps_per_second": 3.133
8
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1568fd69d25140b09716c32ac14e9814f7b33bda9c10cf447634bb705bbb3c24
3
+ size 110350128
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_10-28-07_DESKTOP-SKBE9FB/events.out.tfevents.1733070489.DESKTOP-SKBE9FB.1292.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1d831003eb4275dfafba2b36d6999a3cc22dc8bb7fe730a0da0f7eba89015da
3
+ size 22885
runs/Dec01_10-28-07_DESKTOP-SKBE9FB/events.out.tfevents.1733071075.DESKTOP-SKBE9FB.1292.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac844659f9ed9bd5bc81d06873eaa9ea7e9f5b7a98fcc968fb780c818619b178
3
+ size 411
train_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 40.0,
3
+ "train_loss": 1.0566354274749756,
4
+ "train_runtime": 583.642,
5
+ "train_samples_per_second": 34.131,
6
+ "train_steps_per_second": 0.548
7
+ }
trainer_state.json ADDED
@@ -0,0 +1,582 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.6355140186915887,
3
+ "best_model_checkpoint": "swinv2-tiny-patch4-window8-256-RH-6e-5\\checkpoint-312",
4
+ "epoch": 40.0,
5
+ "eval_steps": 500,
6
+ "global_step": 320,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 1.0,
13
+ "eval_accuracy": 0.411214953271028,
14
+ "eval_loss": 4.618819713592529,
15
+ "eval_runtime": 1.8874,
16
+ "eval_samples_per_second": 56.691,
17
+ "eval_steps_per_second": 3.709,
18
+ "step": 8
19
+ },
20
+ {
21
+ "epoch": 1.25,
22
+ "learning_rate": 1.8750000000000002e-05,
23
+ "loss": 4.5343,
24
+ "step": 10
25
+ },
26
+ {
27
+ "epoch": 2.0,
28
+ "eval_accuracy": 0.411214953271028,
29
+ "eval_loss": 4.409636974334717,
30
+ "eval_runtime": 1.8724,
31
+ "eval_samples_per_second": 57.145,
32
+ "eval_steps_per_second": 3.738,
33
+ "step": 16
34
+ },
35
+ {
36
+ "epoch": 2.5,
37
+ "learning_rate": 3.7500000000000003e-05,
38
+ "loss": 4.5396,
39
+ "step": 20
40
+ },
41
+ {
42
+ "epoch": 3.0,
43
+ "eval_accuracy": 0.411214953271028,
44
+ "eval_loss": 3.6783952713012695,
45
+ "eval_runtime": 1.8845,
46
+ "eval_samples_per_second": 56.78,
47
+ "eval_steps_per_second": 3.715,
48
+ "step": 24
49
+ },
50
+ {
51
+ "epoch": 3.75,
52
+ "learning_rate": 5.625e-05,
53
+ "loss": 3.621,
54
+ "step": 30
55
+ },
56
+ {
57
+ "epoch": 4.0,
58
+ "eval_accuracy": 0.411214953271028,
59
+ "eval_loss": 2.479982852935791,
60
+ "eval_runtime": 1.8659,
61
+ "eval_samples_per_second": 57.344,
62
+ "eval_steps_per_second": 3.751,
63
+ "step": 32
64
+ },
65
+ {
66
+ "epoch": 5.0,
67
+ "learning_rate": 5.833333333333333e-05,
68
+ "loss": 2.1758,
69
+ "step": 40
70
+ },
71
+ {
72
+ "epoch": 5.0,
73
+ "eval_accuracy": 0.411214953271028,
74
+ "eval_loss": 1.2117878198623657,
75
+ "eval_runtime": 1.864,
76
+ "eval_samples_per_second": 57.405,
77
+ "eval_steps_per_second": 3.755,
78
+ "step": 40
79
+ },
80
+ {
81
+ "epoch": 6.0,
82
+ "eval_accuracy": 0.5887850467289719,
83
+ "eval_loss": 0.6790419816970825,
84
+ "eval_runtime": 1.9149,
85
+ "eval_samples_per_second": 55.876,
86
+ "eval_steps_per_second": 3.655,
87
+ "step": 48
88
+ },
89
+ {
90
+ "epoch": 6.25,
91
+ "learning_rate": 5.625e-05,
92
+ "loss": 0.8871,
93
+ "step": 50
94
+ },
95
+ {
96
+ "epoch": 7.0,
97
+ "eval_accuracy": 0.5887850467289719,
98
+ "eval_loss": 0.7903054356575012,
99
+ "eval_runtime": 1.9304,
100
+ "eval_samples_per_second": 55.428,
101
+ "eval_steps_per_second": 3.626,
102
+ "step": 56
103
+ },
104
+ {
105
+ "epoch": 7.5,
106
+ "learning_rate": 5.416666666666667e-05,
107
+ "loss": 0.7484,
108
+ "step": 60
109
+ },
110
+ {
111
+ "epoch": 8.0,
112
+ "eval_accuracy": 0.5887850467289719,
113
+ "eval_loss": 0.7640213370323181,
114
+ "eval_runtime": 1.8494,
115
+ "eval_samples_per_second": 57.856,
116
+ "eval_steps_per_second": 3.785,
117
+ "step": 64
118
+ },
119
+ {
120
+ "epoch": 8.75,
121
+ "learning_rate": 5.208333333333334e-05,
122
+ "loss": 0.7414,
123
+ "step": 70
124
+ },
125
+ {
126
+ "epoch": 9.0,
127
+ "eval_accuracy": 0.5887850467289719,
128
+ "eval_loss": 0.6789357662200928,
129
+ "eval_runtime": 1.8705,
130
+ "eval_samples_per_second": 57.204,
131
+ "eval_steps_per_second": 3.742,
132
+ "step": 72
133
+ },
134
+ {
135
+ "epoch": 10.0,
136
+ "learning_rate": 5e-05,
137
+ "loss": 0.6868,
138
+ "step": 80
139
+ },
140
+ {
141
+ "epoch": 10.0,
142
+ "eval_accuracy": 0.5887850467289719,
143
+ "eval_loss": 0.6770228743553162,
144
+ "eval_runtime": 1.862,
145
+ "eval_samples_per_second": 57.466,
146
+ "eval_steps_per_second": 3.759,
147
+ "step": 80
148
+ },
149
+ {
150
+ "epoch": 11.0,
151
+ "eval_accuracy": 0.5887850467289719,
152
+ "eval_loss": 0.6774561405181885,
153
+ "eval_runtime": 1.9195,
154
+ "eval_samples_per_second": 55.745,
155
+ "eval_steps_per_second": 3.647,
156
+ "step": 88
157
+ },
158
+ {
159
+ "epoch": 11.25,
160
+ "learning_rate": 4.791666666666667e-05,
161
+ "loss": 0.6771,
162
+ "step": 90
163
+ },
164
+ {
165
+ "epoch": 12.0,
166
+ "eval_accuracy": 0.5887850467289719,
167
+ "eval_loss": 0.6992754340171814,
168
+ "eval_runtime": 1.8744,
169
+ "eval_samples_per_second": 57.084,
170
+ "eval_steps_per_second": 3.734,
171
+ "step": 96
172
+ },
173
+ {
174
+ "epoch": 12.5,
175
+ "learning_rate": 4.5833333333333334e-05,
176
+ "loss": 0.7082,
177
+ "step": 100
178
+ },
179
+ {
180
+ "epoch": 13.0,
181
+ "eval_accuracy": 0.5887850467289719,
182
+ "eval_loss": 0.6765372157096863,
183
+ "eval_runtime": 1.904,
184
+ "eval_samples_per_second": 56.199,
185
+ "eval_steps_per_second": 3.677,
186
+ "step": 104
187
+ },
188
+ {
189
+ "epoch": 13.75,
190
+ "learning_rate": 4.375e-05,
191
+ "loss": 0.6993,
192
+ "step": 110
193
+ },
194
+ {
195
+ "epoch": 14.0,
196
+ "eval_accuracy": 0.5887850467289719,
197
+ "eval_loss": 0.6745595335960388,
198
+ "eval_runtime": 1.8884,
199
+ "eval_samples_per_second": 56.661,
200
+ "eval_steps_per_second": 3.707,
201
+ "step": 112
202
+ },
203
+ {
204
+ "epoch": 15.0,
205
+ "learning_rate": 4.1666666666666665e-05,
206
+ "loss": 0.6798,
207
+ "step": 120
208
+ },
209
+ {
210
+ "epoch": 15.0,
211
+ "eval_accuracy": 0.5887850467289719,
212
+ "eval_loss": 0.6758854985237122,
213
+ "eval_runtime": 1.922,
214
+ "eval_samples_per_second": 55.672,
215
+ "eval_steps_per_second": 3.642,
216
+ "step": 120
217
+ },
218
+ {
219
+ "epoch": 16.0,
220
+ "eval_accuracy": 0.5887850467289719,
221
+ "eval_loss": 0.6734067797660828,
222
+ "eval_runtime": 1.8769,
223
+ "eval_samples_per_second": 57.008,
224
+ "eval_steps_per_second": 3.729,
225
+ "step": 128
226
+ },
227
+ {
228
+ "epoch": 16.25,
229
+ "learning_rate": 3.958333333333333e-05,
230
+ "loss": 0.6734,
231
+ "step": 130
232
+ },
233
+ {
234
+ "epoch": 17.0,
235
+ "eval_accuracy": 0.5887850467289719,
236
+ "eval_loss": 0.673911988735199,
237
+ "eval_runtime": 1.9047,
238
+ "eval_samples_per_second": 56.178,
239
+ "eval_steps_per_second": 3.675,
240
+ "step": 136
241
+ },
242
+ {
243
+ "epoch": 17.5,
244
+ "learning_rate": 3.7500000000000003e-05,
245
+ "loss": 0.6832,
246
+ "step": 140
247
+ },
248
+ {
249
+ "epoch": 18.0,
250
+ "eval_accuracy": 0.5887850467289719,
251
+ "eval_loss": 0.7038590908050537,
252
+ "eval_runtime": 1.9054,
253
+ "eval_samples_per_second": 56.155,
254
+ "eval_steps_per_second": 3.674,
255
+ "step": 144
256
+ },
257
+ {
258
+ "epoch": 18.75,
259
+ "learning_rate": 3.541666666666667e-05,
260
+ "loss": 0.6825,
261
+ "step": 150
262
+ },
263
+ {
264
+ "epoch": 19.0,
265
+ "eval_accuracy": 0.5887850467289719,
266
+ "eval_loss": 0.676673412322998,
267
+ "eval_runtime": 1.975,
268
+ "eval_samples_per_second": 54.178,
269
+ "eval_steps_per_second": 3.544,
270
+ "step": 152
271
+ },
272
+ {
273
+ "epoch": 20.0,
274
+ "learning_rate": 3.3333333333333335e-05,
275
+ "loss": 0.6663,
276
+ "step": 160
277
+ },
278
+ {
279
+ "epoch": 20.0,
280
+ "eval_accuracy": 0.5887850467289719,
281
+ "eval_loss": 0.670670747756958,
282
+ "eval_runtime": 1.8789,
283
+ "eval_samples_per_second": 56.947,
284
+ "eval_steps_per_second": 3.725,
285
+ "step": 160
286
+ },
287
+ {
288
+ "epoch": 21.0,
289
+ "eval_accuracy": 0.5887850467289719,
290
+ "eval_loss": 0.6798433661460876,
291
+ "eval_runtime": 1.888,
292
+ "eval_samples_per_second": 56.675,
293
+ "eval_steps_per_second": 3.708,
294
+ "step": 168
295
+ },
296
+ {
297
+ "epoch": 21.25,
298
+ "learning_rate": 3.125e-05,
299
+ "loss": 0.6646,
300
+ "step": 170
301
+ },
302
+ {
303
+ "epoch": 22.0,
304
+ "eval_accuracy": 0.5794392523364486,
305
+ "eval_loss": 0.672282874584198,
306
+ "eval_runtime": 1.8865,
307
+ "eval_samples_per_second": 56.72,
308
+ "eval_steps_per_second": 3.711,
309
+ "step": 176
310
+ },
311
+ {
312
+ "epoch": 22.5,
313
+ "learning_rate": 2.9166666666666666e-05,
314
+ "loss": 0.6764,
315
+ "step": 180
316
+ },
317
+ {
318
+ "epoch": 23.0,
319
+ "eval_accuracy": 0.5887850467289719,
320
+ "eval_loss": 0.6889127492904663,
321
+ "eval_runtime": 1.8825,
322
+ "eval_samples_per_second": 56.839,
323
+ "eval_steps_per_second": 3.718,
324
+ "step": 184
325
+ },
326
+ {
327
+ "epoch": 23.75,
328
+ "learning_rate": 2.7083333333333335e-05,
329
+ "loss": 0.6808,
330
+ "step": 190
331
+ },
332
+ {
333
+ "epoch": 24.0,
334
+ "eval_accuracy": 0.5887850467289719,
335
+ "eval_loss": 0.6993632316589355,
336
+ "eval_runtime": 2.065,
337
+ "eval_samples_per_second": 51.816,
338
+ "eval_steps_per_second": 3.39,
339
+ "step": 192
340
+ },
341
+ {
342
+ "epoch": 25.0,
343
+ "learning_rate": 2.5e-05,
344
+ "loss": 0.6766,
345
+ "step": 200
346
+ },
347
+ {
348
+ "epoch": 25.0,
349
+ "eval_accuracy": 0.5887850467289719,
350
+ "eval_loss": 0.6691157221794128,
351
+ "eval_runtime": 1.8589,
352
+ "eval_samples_per_second": 57.56,
353
+ "eval_steps_per_second": 3.766,
354
+ "step": 200
355
+ },
356
+ {
357
+ "epoch": 26.0,
358
+ "eval_accuracy": 0.5887850467289719,
359
+ "eval_loss": 0.683734655380249,
360
+ "eval_runtime": 1.8344,
361
+ "eval_samples_per_second": 58.329,
362
+ "eval_steps_per_second": 3.816,
363
+ "step": 208
364
+ },
365
+ {
366
+ "epoch": 26.25,
367
+ "learning_rate": 2.2916666666666667e-05,
368
+ "loss": 0.6698,
369
+ "step": 210
370
+ },
371
+ {
372
+ "epoch": 27.0,
373
+ "eval_accuracy": 0.5700934579439252,
374
+ "eval_loss": 0.673797607421875,
375
+ "eval_runtime": 1.9525,
376
+ "eval_samples_per_second": 54.802,
377
+ "eval_steps_per_second": 3.585,
378
+ "step": 216
379
+ },
380
+ {
381
+ "epoch": 27.5,
382
+ "learning_rate": 2.0833333333333333e-05,
383
+ "loss": 0.6549,
384
+ "step": 220
385
+ },
386
+ {
387
+ "epoch": 28.0,
388
+ "eval_accuracy": 0.5794392523364486,
389
+ "eval_loss": 0.6694583892822266,
390
+ "eval_runtime": 2.1597,
391
+ "eval_samples_per_second": 49.545,
392
+ "eval_steps_per_second": 3.241,
393
+ "step": 224
394
+ },
395
+ {
396
+ "epoch": 28.75,
397
+ "learning_rate": 1.8750000000000002e-05,
398
+ "loss": 0.6442,
399
+ "step": 230
400
+ },
401
+ {
402
+ "epoch": 29.0,
403
+ "eval_accuracy": 0.5794392523364486,
404
+ "eval_loss": 0.7157074213027954,
405
+ "eval_runtime": 1.8589,
406
+ "eval_samples_per_second": 57.56,
407
+ "eval_steps_per_second": 3.766,
408
+ "step": 232
409
+ },
410
+ {
411
+ "epoch": 30.0,
412
+ "learning_rate": 1.6666666666666667e-05,
413
+ "loss": 0.649,
414
+ "step": 240
415
+ },
416
+ {
417
+ "epoch": 30.0,
418
+ "eval_accuracy": 0.6074766355140186,
419
+ "eval_loss": 0.6725906133651733,
420
+ "eval_runtime": 1.8929,
421
+ "eval_samples_per_second": 56.526,
422
+ "eval_steps_per_second": 3.698,
423
+ "step": 240
424
+ },
425
+ {
426
+ "epoch": 31.0,
427
+ "eval_accuracy": 0.5794392523364486,
428
+ "eval_loss": 0.6838603019714355,
429
+ "eval_runtime": 1.8925,
430
+ "eval_samples_per_second": 56.54,
431
+ "eval_steps_per_second": 3.699,
432
+ "step": 248
433
+ },
434
+ {
435
+ "epoch": 31.25,
436
+ "learning_rate": 1.4583333333333333e-05,
437
+ "loss": 0.6388,
438
+ "step": 250
439
+ },
440
+ {
441
+ "epoch": 32.0,
442
+ "eval_accuracy": 0.5887850467289719,
443
+ "eval_loss": 0.679723858833313,
444
+ "eval_runtime": 1.858,
445
+ "eval_samples_per_second": 57.59,
446
+ "eval_steps_per_second": 3.768,
447
+ "step": 256
448
+ },
449
+ {
450
+ "epoch": 32.5,
451
+ "learning_rate": 1.25e-05,
452
+ "loss": 0.6416,
453
+ "step": 260
454
+ },
455
+ {
456
+ "epoch": 33.0,
457
+ "eval_accuracy": 0.5981308411214953,
458
+ "eval_loss": 0.6713680624961853,
459
+ "eval_runtime": 1.9354,
460
+ "eval_samples_per_second": 55.284,
461
+ "eval_steps_per_second": 3.617,
462
+ "step": 264
463
+ },
464
+ {
465
+ "epoch": 33.75,
466
+ "learning_rate": 1.0416666666666666e-05,
467
+ "loss": 0.6398,
468
+ "step": 270
469
+ },
470
+ {
471
+ "epoch": 34.0,
472
+ "eval_accuracy": 0.6074766355140186,
473
+ "eval_loss": 0.6730300188064575,
474
+ "eval_runtime": 1.961,
475
+ "eval_samples_per_second": 54.565,
476
+ "eval_steps_per_second": 3.57,
477
+ "step": 272
478
+ },
479
+ {
480
+ "epoch": 35.0,
481
+ "learning_rate": 8.333333333333334e-06,
482
+ "loss": 0.6522,
483
+ "step": 280
484
+ },
485
+ {
486
+ "epoch": 35.0,
487
+ "eval_accuracy": 0.5794392523364486,
488
+ "eval_loss": 0.6953481435775757,
489
+ "eval_runtime": 1.901,
490
+ "eval_samples_per_second": 56.288,
491
+ "eval_steps_per_second": 3.682,
492
+ "step": 280
493
+ },
494
+ {
495
+ "epoch": 36.0,
496
+ "eval_accuracy": 0.5700934579439252,
497
+ "eval_loss": 0.6608957052230835,
498
+ "eval_runtime": 1.8975,
499
+ "eval_samples_per_second": 56.391,
500
+ "eval_steps_per_second": 3.689,
501
+ "step": 288
502
+ },
503
+ {
504
+ "epoch": 36.25,
505
+ "learning_rate": 6.25e-06,
506
+ "loss": 0.6376,
507
+ "step": 290
508
+ },
509
+ {
510
+ "epoch": 37.0,
511
+ "eval_accuracy": 0.5794392523364486,
512
+ "eval_loss": 0.6618574857711792,
513
+ "eval_runtime": 1.9264,
514
+ "eval_samples_per_second": 55.543,
515
+ "eval_steps_per_second": 3.634,
516
+ "step": 296
517
+ },
518
+ {
519
+ "epoch": 37.5,
520
+ "learning_rate": 4.166666666666667e-06,
521
+ "loss": 0.6441,
522
+ "step": 300
523
+ },
524
+ {
525
+ "epoch": 38.0,
526
+ "eval_accuracy": 0.6261682242990654,
527
+ "eval_loss": 0.6653915047645569,
528
+ "eval_runtime": 1.921,
529
+ "eval_samples_per_second": 55.701,
530
+ "eval_steps_per_second": 3.644,
531
+ "step": 304
532
+ },
533
+ {
534
+ "epoch": 38.75,
535
+ "learning_rate": 2.0833333333333334e-06,
536
+ "loss": 0.6149,
537
+ "step": 310
538
+ },
539
+ {
540
+ "epoch": 39.0,
541
+ "eval_accuracy": 0.6355140186915887,
542
+ "eval_loss": 0.666593611240387,
543
+ "eval_runtime": 1.9335,
544
+ "eval_samples_per_second": 55.341,
545
+ "eval_steps_per_second": 3.62,
546
+ "step": 312
547
+ },
548
+ {
549
+ "epoch": 40.0,
550
+ "learning_rate": 0.0,
551
+ "loss": 0.623,
552
+ "step": 320
553
+ },
554
+ {
555
+ "epoch": 40.0,
556
+ "eval_accuracy": 0.6355140186915887,
557
+ "eval_loss": 0.6678972840309143,
558
+ "eval_runtime": 1.8599,
559
+ "eval_samples_per_second": 57.529,
560
+ "eval_steps_per_second": 3.764,
561
+ "step": 320
562
+ },
563
+ {
564
+ "epoch": 40.0,
565
+ "step": 320,
566
+ "total_flos": 6.480838238876467e+17,
567
+ "train_loss": 1.0566354274749756,
568
+ "train_runtime": 583.642,
569
+ "train_samples_per_second": 34.131,
570
+ "train_steps_per_second": 0.548
571
+ }
572
+ ],
573
+ "logging_steps": 10,
574
+ "max_steps": 320,
575
+ "num_input_tokens_seen": 0,
576
+ "num_train_epochs": 40,
577
+ "save_steps": 500,
578
+ "total_flos": 6.480838238876467e+17,
579
+ "train_batch_size": 16,
580
+ "trial_name": null,
581
+ "trial_params": null
582
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c750c8906515f1f5903f95e4190b3e6df876a86b61beaacb45209684817120d
3
+ size 4792