mansee commited on
Commit
867de38
1 Parent(s): 6c47a35

Training in progress, epoch 1

Browse files
README.md ADDED
@@ -0,0 +1,80 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: microsoft/swin-tiny-patch4-window7-224
4
+ tags:
5
+ - generated_from_trainer
6
+ datasets:
7
+ - imagefolder
8
+ metrics:
9
+ - accuracy
10
+ model-index:
11
+ - name: swin-tiny-patch4-window7-224-finetuned-eurosat
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: train
21
+ args: default
22
+ metrics:
23
+ - name: Accuracy
24
+ type: accuracy
25
+ value: 0.8009728415079044
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
+ # swin-tiny-patch4-window7-224-finetuned-eurosat
32
+
33
+ This model is a fine-tuned version of [microsoft/swin-tiny-patch4-window7-224](https://huggingface.co/microsoft/swin-tiny-patch4-window7-224) on the imagefolder dataset.
34
+ It achieves the following results on the evaluation set:
35
+ - Loss: 0.3679
36
+ - Accuracy: 0.8010
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: 5e-05
56
+ - train_batch_size: 32
57
+ - eval_batch_size: 32
58
+ - seed: 42
59
+ - gradient_accumulation_steps: 4
60
+ - total_train_batch_size: 128
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: 3
65
+
66
+ ### Training results
67
+
68
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
70
+ | 0.5941 | 1.0 | 694 | 0.4620 | 0.7458 |
71
+ | 0.4836 | 2.0 | 1388 | 0.3887 | 0.7924 |
72
+ | 0.4672 | 3.0 | 2082 | 0.3679 | 0.8010 |
73
+
74
+
75
+ ### Framework versions
76
+
77
+ - Transformers 4.35.0
78
+ - Pytorch 1.12.1+cu113
79
+ - Datasets 2.17.1
80
+ - Tokenizers 0.14.1
all_results.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "eval_accuracy": 0.8009728415079044,
4
+ "eval_loss": 0.3678824007511139,
5
+ "eval_runtime": 100.1235,
6
+ "eval_samples_per_second": 98.558,
7
+ "eval_steps_per_second": 3.086,
8
+ "train_loss": 0.5971084463836824,
9
+ "train_runtime": 3243.1106,
10
+ "train_samples_per_second": 82.147,
11
+ "train_steps_per_second": 0.642
12
+ }
config.json ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/swin-tiny-patch4-window7-224",
3
+ "architectures": [
4
+ "SwinForImageClassification"
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": "0_degree",
21
+ "1": "180_degree",
22
+ "2": "270_degree",
23
+ "3": "90_degree"
24
+ },
25
+ "image_size": 224,
26
+ "initializer_range": 0.02,
27
+ "label2id": {
28
+ "0_degree": 0,
29
+ "180_degree": 1,
30
+ "270_degree": 2,
31
+ "90_degree": 3
32
+ },
33
+ "layer_norm_eps": 1e-05,
34
+ "mlp_ratio": 4.0,
35
+ "model_type": "swin",
36
+ "num_channels": 3,
37
+ "num_heads": [
38
+ 3,
39
+ 6,
40
+ 12,
41
+ 24
42
+ ],
43
+ "num_layers": 4,
44
+ "out_features": [
45
+ "stage4"
46
+ ],
47
+ "out_indices": [
48
+ 4
49
+ ],
50
+ "patch_size": 4,
51
+ "path_norm": true,
52
+ "problem_type": "single_label_classification",
53
+ "qkv_bias": true,
54
+ "stage_names": [
55
+ "stem",
56
+ "stage1",
57
+ "stage2",
58
+ "stage3",
59
+ "stage4"
60
+ ],
61
+ "torch_dtype": "float32",
62
+ "transformers_version": "4.40.1",
63
+ "use_absolute_embeddings": false,
64
+ "window_size": 7
65
+ }
eval_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "eval_accuracy": 0.8009728415079044,
4
+ "eval_loss": 0.3678824007511139,
5
+ "eval_runtime": 100.1235,
6
+ "eval_samples_per_second": 98.558,
7
+ "eval_steps_per_second": 3.086
8
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1bb676022e4d760a6fef37fc6370b840e499852e6a99de4730a566a591452574
3
+ size 110348984
preprocessor_config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_valid_processor_keys": [
3
+ "images",
4
+ "do_resize",
5
+ "size",
6
+ "resample",
7
+ "do_rescale",
8
+ "rescale_factor",
9
+ "do_normalize",
10
+ "image_mean",
11
+ "image_std",
12
+ "return_tensors",
13
+ "data_format",
14
+ "input_data_format"
15
+ ],
16
+ "do_normalize": true,
17
+ "do_rescale": true,
18
+ "do_resize": true,
19
+ "image_mean": [
20
+ 0.485,
21
+ 0.456,
22
+ 0.406
23
+ ],
24
+ "image_processor_type": "ViTImageProcessor",
25
+ "image_std": [
26
+ 0.229,
27
+ 0.224,
28
+ 0.225
29
+ ],
30
+ "resample": 3,
31
+ "rescale_factor": 0.00392156862745098,
32
+ "size": {
33
+ "height": 224,
34
+ "width": 224
35
+ }
36
+ }
runs/Apr09_15-29-38_img-srch-kworker2/events.out.tfevents.1712656780.img-srch-kworker2.513913.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45b23db60d9f1ca4d338ee436c6af4a048a053906ba9c10b973f0b61a05a145d
3
+ size 5703
runs/Apr09_15-36-44_img-srch-kworker2/events.out.tfevents.1712657205.img-srch-kworker2.515115.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:851c998a0ef86c21e95b468e76eb7c8ca4268e5dfe1d0695e437cd26cc8c930e
3
+ size 38722
runs/Apr09_15-36-44_img-srch-kworker2/events.out.tfevents.1712660576.img-srch-kworker2.515115.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2beda33168cb2cfc0cf46537e35bbe20497cbb684f76024cafd631e3f0d63cc8
3
+ size 411
runs/Apr29_15-06-40_img-srch-kworker3/events.out.tfevents.1714383412.img-srch-kworker3.432422.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1236ff50aaa4fc7108587d74655a929efd992fa761cbc6bf4ec8b719292acd8
3
+ size 5446
runs/Apr29_15-16-00_img-srch-kworker3/events.out.tfevents.1714383962.img-srch-kworker3.434621.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:459a44c1c7b8ac1cd24394952ceeade9d4f191f76fd047256b3ff6d3dddab154
3
+ size 4184
runs/Apr29_15-20-12_img-srch-kworker3/events.out.tfevents.1714384213.img-srch-kworker3.435443.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:673fddb264419ab50c3075481a7cdb80a594d3cf33e271637009a55a5e15a748
3
+ size 20073
train_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "train_loss": 0.5971084463836824,
4
+ "train_runtime": 3243.1106,
5
+ "train_samples_per_second": 82.147,
6
+ "train_steps_per_second": 0.642
7
+ }
trainer_state.json ADDED
@@ -0,0 +1,1303 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8009728415079044,
3
+ "best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned-eurosat/checkpoint-2082",
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 2082,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.01,
13
+ "learning_rate": 2.3923444976076554e-06,
14
+ "loss": 1.4479,
15
+ "step": 10
16
+ },
17
+ {
18
+ "epoch": 0.03,
19
+ "learning_rate": 4.784688995215311e-06,
20
+ "loss": 1.4139,
21
+ "step": 20
22
+ },
23
+ {
24
+ "epoch": 0.04,
25
+ "learning_rate": 7.177033492822967e-06,
26
+ "loss": 1.4006,
27
+ "step": 30
28
+ },
29
+ {
30
+ "epoch": 0.06,
31
+ "learning_rate": 9.569377990430622e-06,
32
+ "loss": 1.3654,
33
+ "step": 40
34
+ },
35
+ {
36
+ "epoch": 0.07,
37
+ "learning_rate": 1.1961722488038278e-05,
38
+ "loss": 1.3395,
39
+ "step": 50
40
+ },
41
+ {
42
+ "epoch": 0.09,
43
+ "learning_rate": 1.4354066985645934e-05,
44
+ "loss": 1.2985,
45
+ "step": 60
46
+ },
47
+ {
48
+ "epoch": 0.1,
49
+ "learning_rate": 1.674641148325359e-05,
50
+ "loss": 1.2354,
51
+ "step": 70
52
+ },
53
+ {
54
+ "epoch": 0.12,
55
+ "learning_rate": 1.9138755980861243e-05,
56
+ "loss": 1.1581,
57
+ "step": 80
58
+ },
59
+ {
60
+ "epoch": 0.13,
61
+ "learning_rate": 2.1531100478468903e-05,
62
+ "loss": 1.0563,
63
+ "step": 90
64
+ },
65
+ {
66
+ "epoch": 0.14,
67
+ "learning_rate": 2.3923444976076556e-05,
68
+ "loss": 0.9842,
69
+ "step": 100
70
+ },
71
+ {
72
+ "epoch": 0.16,
73
+ "learning_rate": 2.6315789473684212e-05,
74
+ "loss": 0.9439,
75
+ "step": 110
76
+ },
77
+ {
78
+ "epoch": 0.17,
79
+ "learning_rate": 2.8708133971291868e-05,
80
+ "loss": 0.9081,
81
+ "step": 120
82
+ },
83
+ {
84
+ "epoch": 0.19,
85
+ "learning_rate": 3.110047846889952e-05,
86
+ "loss": 0.8584,
87
+ "step": 130
88
+ },
89
+ {
90
+ "epoch": 0.2,
91
+ "learning_rate": 3.349282296650718e-05,
92
+ "loss": 0.8333,
93
+ "step": 140
94
+ },
95
+ {
96
+ "epoch": 0.22,
97
+ "learning_rate": 3.5885167464114834e-05,
98
+ "loss": 0.8098,
99
+ "step": 150
100
+ },
101
+ {
102
+ "epoch": 0.23,
103
+ "learning_rate": 3.8277511961722486e-05,
104
+ "loss": 0.812,
105
+ "step": 160
106
+ },
107
+ {
108
+ "epoch": 0.24,
109
+ "learning_rate": 4.0669856459330146e-05,
110
+ "loss": 0.7806,
111
+ "step": 170
112
+ },
113
+ {
114
+ "epoch": 0.26,
115
+ "learning_rate": 4.3062200956937806e-05,
116
+ "loss": 0.8163,
117
+ "step": 180
118
+ },
119
+ {
120
+ "epoch": 0.27,
121
+ "learning_rate": 4.545454545454546e-05,
122
+ "loss": 0.7505,
123
+ "step": 190
124
+ },
125
+ {
126
+ "epoch": 0.29,
127
+ "learning_rate": 4.784688995215311e-05,
128
+ "loss": 0.744,
129
+ "step": 200
130
+ },
131
+ {
132
+ "epoch": 0.3,
133
+ "learning_rate": 4.997330485851575e-05,
134
+ "loss": 0.7064,
135
+ "step": 210
136
+ },
137
+ {
138
+ "epoch": 0.32,
139
+ "learning_rate": 4.9706353443673256e-05,
140
+ "loss": 0.7661,
141
+ "step": 220
142
+ },
143
+ {
144
+ "epoch": 0.33,
145
+ "learning_rate": 4.943940202883076e-05,
146
+ "loss": 0.738,
147
+ "step": 230
148
+ },
149
+ {
150
+ "epoch": 0.35,
151
+ "learning_rate": 4.917245061398826e-05,
152
+ "loss": 0.7195,
153
+ "step": 240
154
+ },
155
+ {
156
+ "epoch": 0.36,
157
+ "learning_rate": 4.890549919914576e-05,
158
+ "loss": 0.7131,
159
+ "step": 250
160
+ },
161
+ {
162
+ "epoch": 0.37,
163
+ "learning_rate": 4.863854778430326e-05,
164
+ "loss": 0.7106,
165
+ "step": 260
166
+ },
167
+ {
168
+ "epoch": 0.39,
169
+ "learning_rate": 4.837159636946076e-05,
170
+ "loss": 0.7293,
171
+ "step": 270
172
+ },
173
+ {
174
+ "epoch": 0.4,
175
+ "learning_rate": 4.810464495461826e-05,
176
+ "loss": 0.6959,
177
+ "step": 280
178
+ },
179
+ {
180
+ "epoch": 0.42,
181
+ "learning_rate": 4.783769353977576e-05,
182
+ "loss": 0.6844,
183
+ "step": 290
184
+ },
185
+ {
186
+ "epoch": 0.43,
187
+ "learning_rate": 4.7570742124933263e-05,
188
+ "loss": 0.6965,
189
+ "step": 300
190
+ },
191
+ {
192
+ "epoch": 0.45,
193
+ "learning_rate": 4.7303790710090764e-05,
194
+ "loss": 0.6807,
195
+ "step": 310
196
+ },
197
+ {
198
+ "epoch": 0.46,
199
+ "learning_rate": 4.703683929524827e-05,
200
+ "loss": 0.6954,
201
+ "step": 320
202
+ },
203
+ {
204
+ "epoch": 0.48,
205
+ "learning_rate": 4.6769887880405766e-05,
206
+ "loss": 0.6814,
207
+ "step": 330
208
+ },
209
+ {
210
+ "epoch": 0.49,
211
+ "learning_rate": 4.650293646556327e-05,
212
+ "loss": 0.6482,
213
+ "step": 340
214
+ },
215
+ {
216
+ "epoch": 0.5,
217
+ "learning_rate": 4.623598505072077e-05,
218
+ "loss": 0.6268,
219
+ "step": 350
220
+ },
221
+ {
222
+ "epoch": 0.52,
223
+ "learning_rate": 4.5969033635878276e-05,
224
+ "loss": 0.6598,
225
+ "step": 360
226
+ },
227
+ {
228
+ "epoch": 0.53,
229
+ "learning_rate": 4.570208222103578e-05,
230
+ "loss": 0.6507,
231
+ "step": 370
232
+ },
233
+ {
234
+ "epoch": 0.55,
235
+ "learning_rate": 4.543513080619328e-05,
236
+ "loss": 0.6453,
237
+ "step": 380
238
+ },
239
+ {
240
+ "epoch": 0.56,
241
+ "learning_rate": 4.516817939135078e-05,
242
+ "loss": 0.6599,
243
+ "step": 390
244
+ },
245
+ {
246
+ "epoch": 0.58,
247
+ "learning_rate": 4.490122797650827e-05,
248
+ "loss": 0.6673,
249
+ "step": 400
250
+ },
251
+ {
252
+ "epoch": 0.59,
253
+ "learning_rate": 4.463427656166578e-05,
254
+ "loss": 0.6551,
255
+ "step": 410
256
+ },
257
+ {
258
+ "epoch": 0.61,
259
+ "learning_rate": 4.436732514682328e-05,
260
+ "loss": 0.6788,
261
+ "step": 420
262
+ },
263
+ {
264
+ "epoch": 0.62,
265
+ "learning_rate": 4.410037373198078e-05,
266
+ "loss": 0.6611,
267
+ "step": 430
268
+ },
269
+ {
270
+ "epoch": 0.63,
271
+ "learning_rate": 4.383342231713828e-05,
272
+ "loss": 0.6666,
273
+ "step": 440
274
+ },
275
+ {
276
+ "epoch": 0.65,
277
+ "learning_rate": 4.3566470902295784e-05,
278
+ "loss": 0.6465,
279
+ "step": 450
280
+ },
281
+ {
282
+ "epoch": 0.66,
283
+ "learning_rate": 4.329951948745329e-05,
284
+ "loss": 0.6702,
285
+ "step": 460
286
+ },
287
+ {
288
+ "epoch": 0.68,
289
+ "learning_rate": 4.3032568072610786e-05,
290
+ "loss": 0.6287,
291
+ "step": 470
292
+ },
293
+ {
294
+ "epoch": 0.69,
295
+ "learning_rate": 4.276561665776829e-05,
296
+ "loss": 0.6588,
297
+ "step": 480
298
+ },
299
+ {
300
+ "epoch": 0.71,
301
+ "learning_rate": 4.249866524292579e-05,
302
+ "loss": 0.6607,
303
+ "step": 490
304
+ },
305
+ {
306
+ "epoch": 0.72,
307
+ "learning_rate": 4.223171382808329e-05,
308
+ "loss": 0.6183,
309
+ "step": 500
310
+ },
311
+ {
312
+ "epoch": 0.73,
313
+ "learning_rate": 4.1964762413240796e-05,
314
+ "loss": 0.6261,
315
+ "step": 510
316
+ },
317
+ {
318
+ "epoch": 0.75,
319
+ "learning_rate": 4.16978109983983e-05,
320
+ "loss": 0.6595,
321
+ "step": 520
322
+ },
323
+ {
324
+ "epoch": 0.76,
325
+ "learning_rate": 4.143085958355579e-05,
326
+ "loss": 0.6274,
327
+ "step": 530
328
+ },
329
+ {
330
+ "epoch": 0.78,
331
+ "learning_rate": 4.116390816871329e-05,
332
+ "loss": 0.6195,
333
+ "step": 540
334
+ },
335
+ {
336
+ "epoch": 0.79,
337
+ "learning_rate": 4.089695675387079e-05,
338
+ "loss": 0.6537,
339
+ "step": 550
340
+ },
341
+ {
342
+ "epoch": 0.81,
343
+ "learning_rate": 4.06300053390283e-05,
344
+ "loss": 0.607,
345
+ "step": 560
346
+ },
347
+ {
348
+ "epoch": 0.82,
349
+ "learning_rate": 4.03630539241858e-05,
350
+ "loss": 0.622,
351
+ "step": 570
352
+ },
353
+ {
354
+ "epoch": 0.84,
355
+ "learning_rate": 4.00961025093433e-05,
356
+ "loss": 0.6408,
357
+ "step": 580
358
+ },
359
+ {
360
+ "epoch": 0.85,
361
+ "learning_rate": 3.9829151094500804e-05,
362
+ "loss": 0.6265,
363
+ "step": 590
364
+ },
365
+ {
366
+ "epoch": 0.86,
367
+ "learning_rate": 3.9562199679658305e-05,
368
+ "loss": 0.6149,
369
+ "step": 600
370
+ },
371
+ {
372
+ "epoch": 0.88,
373
+ "learning_rate": 3.9295248264815805e-05,
374
+ "loss": 0.6153,
375
+ "step": 610
376
+ },
377
+ {
378
+ "epoch": 0.89,
379
+ "learning_rate": 3.9028296849973306e-05,
380
+ "loss": 0.5777,
381
+ "step": 620
382
+ },
383
+ {
384
+ "epoch": 0.91,
385
+ "learning_rate": 3.876134543513081e-05,
386
+ "loss": 0.6042,
387
+ "step": 630
388
+ },
389
+ {
390
+ "epoch": 0.92,
391
+ "learning_rate": 3.849439402028831e-05,
392
+ "loss": 0.5802,
393
+ "step": 640
394
+ },
395
+ {
396
+ "epoch": 0.94,
397
+ "learning_rate": 3.822744260544581e-05,
398
+ "loss": 0.617,
399
+ "step": 650
400
+ },
401
+ {
402
+ "epoch": 0.95,
403
+ "learning_rate": 3.796049119060332e-05,
404
+ "loss": 0.5741,
405
+ "step": 660
406
+ },
407
+ {
408
+ "epoch": 0.97,
409
+ "learning_rate": 3.769353977576081e-05,
410
+ "loss": 0.5801,
411
+ "step": 670
412
+ },
413
+ {
414
+ "epoch": 0.98,
415
+ "learning_rate": 3.742658836091831e-05,
416
+ "loss": 0.5933,
417
+ "step": 680
418
+ },
419
+ {
420
+ "epoch": 0.99,
421
+ "learning_rate": 3.715963694607581e-05,
422
+ "loss": 0.5941,
423
+ "step": 690
424
+ },
425
+ {
426
+ "epoch": 1.0,
427
+ "eval_accuracy": 0.7458451560599919,
428
+ "eval_loss": 0.46203261613845825,
429
+ "eval_runtime": 104.9031,
430
+ "eval_samples_per_second": 94.068,
431
+ "eval_steps_per_second": 2.946,
432
+ "step": 694
433
+ },
434
+ {
435
+ "epoch": 1.01,
436
+ "learning_rate": 3.689268553123332e-05,
437
+ "loss": 0.592,
438
+ "step": 700
439
+ },
440
+ {
441
+ "epoch": 1.02,
442
+ "learning_rate": 3.662573411639082e-05,
443
+ "loss": 0.5486,
444
+ "step": 710
445
+ },
446
+ {
447
+ "epoch": 1.04,
448
+ "learning_rate": 3.635878270154832e-05,
449
+ "loss": 0.5445,
450
+ "step": 720
451
+ },
452
+ {
453
+ "epoch": 1.05,
454
+ "learning_rate": 3.609183128670582e-05,
455
+ "loss": 0.5543,
456
+ "step": 730
457
+ },
458
+ {
459
+ "epoch": 1.07,
460
+ "learning_rate": 3.582487987186332e-05,
461
+ "loss": 0.5438,
462
+ "step": 740
463
+ },
464
+ {
465
+ "epoch": 1.08,
466
+ "learning_rate": 3.5557928457020825e-05,
467
+ "loss": 0.557,
468
+ "step": 750
469
+ },
470
+ {
471
+ "epoch": 1.1,
472
+ "learning_rate": 3.5290977042178326e-05,
473
+ "loss": 0.5419,
474
+ "step": 760
475
+ },
476
+ {
477
+ "epoch": 1.11,
478
+ "learning_rate": 3.502402562733583e-05,
479
+ "loss": 0.5643,
480
+ "step": 770
481
+ },
482
+ {
483
+ "epoch": 1.12,
484
+ "learning_rate": 3.475707421249333e-05,
485
+ "loss": 0.584,
486
+ "step": 780
487
+ },
488
+ {
489
+ "epoch": 1.14,
490
+ "learning_rate": 3.449012279765083e-05,
491
+ "loss": 0.5938,
492
+ "step": 790
493
+ },
494
+ {
495
+ "epoch": 1.15,
496
+ "learning_rate": 3.422317138280833e-05,
497
+ "loss": 0.5766,
498
+ "step": 800
499
+ },
500
+ {
501
+ "epoch": 1.17,
502
+ "learning_rate": 3.395621996796583e-05,
503
+ "loss": 0.574,
504
+ "step": 810
505
+ },
506
+ {
507
+ "epoch": 1.18,
508
+ "learning_rate": 3.368926855312333e-05,
509
+ "loss": 0.5888,
510
+ "step": 820
511
+ },
512
+ {
513
+ "epoch": 1.2,
514
+ "learning_rate": 3.342231713828083e-05,
515
+ "loss": 0.5593,
516
+ "step": 830
517
+ },
518
+ {
519
+ "epoch": 1.21,
520
+ "learning_rate": 3.315536572343833e-05,
521
+ "loss": 0.56,
522
+ "step": 840
523
+ },
524
+ {
525
+ "epoch": 1.22,
526
+ "learning_rate": 3.288841430859584e-05,
527
+ "loss": 0.5459,
528
+ "step": 850
529
+ },
530
+ {
531
+ "epoch": 1.24,
532
+ "learning_rate": 3.262146289375334e-05,
533
+ "loss": 0.546,
534
+ "step": 860
535
+ },
536
+ {
537
+ "epoch": 1.25,
538
+ "learning_rate": 3.2354511478910836e-05,
539
+ "loss": 0.5236,
540
+ "step": 870
541
+ },
542
+ {
543
+ "epoch": 1.27,
544
+ "learning_rate": 3.208756006406834e-05,
545
+ "loss": 0.5608,
546
+ "step": 880
547
+ },
548
+ {
549
+ "epoch": 1.28,
550
+ "learning_rate": 3.1820608649225845e-05,
551
+ "loss": 0.5749,
552
+ "step": 890
553
+ },
554
+ {
555
+ "epoch": 1.3,
556
+ "learning_rate": 3.1553657234383346e-05,
557
+ "loss": 0.5551,
558
+ "step": 900
559
+ },
560
+ {
561
+ "epoch": 1.31,
562
+ "learning_rate": 3.1286705819540846e-05,
563
+ "loss": 0.5638,
564
+ "step": 910
565
+ },
566
+ {
567
+ "epoch": 1.33,
568
+ "learning_rate": 3.101975440469835e-05,
569
+ "loss": 0.5491,
570
+ "step": 920
571
+ },
572
+ {
573
+ "epoch": 1.34,
574
+ "learning_rate": 3.075280298985585e-05,
575
+ "loss": 0.5183,
576
+ "step": 930
577
+ },
578
+ {
579
+ "epoch": 1.35,
580
+ "learning_rate": 3.0485851575013346e-05,
581
+ "loss": 0.5334,
582
+ "step": 940
583
+ },
584
+ {
585
+ "epoch": 1.37,
586
+ "learning_rate": 3.021890016017085e-05,
587
+ "loss": 0.5396,
588
+ "step": 950
589
+ },
590
+ {
591
+ "epoch": 1.38,
592
+ "learning_rate": 2.995194874532835e-05,
593
+ "loss": 0.5919,
594
+ "step": 960
595
+ },
596
+ {
597
+ "epoch": 1.4,
598
+ "learning_rate": 2.9684997330485852e-05,
599
+ "loss": 0.5492,
600
+ "step": 970
601
+ },
602
+ {
603
+ "epoch": 1.41,
604
+ "learning_rate": 2.9418045915643356e-05,
605
+ "loss": 0.54,
606
+ "step": 980
607
+ },
608
+ {
609
+ "epoch": 1.43,
610
+ "learning_rate": 2.9151094500800857e-05,
611
+ "loss": 0.5464,
612
+ "step": 990
613
+ },
614
+ {
615
+ "epoch": 1.44,
616
+ "learning_rate": 2.8884143085958358e-05,
617
+ "loss": 0.5424,
618
+ "step": 1000
619
+ },
620
+ {
621
+ "epoch": 1.46,
622
+ "learning_rate": 2.8617191671115856e-05,
623
+ "loss": 0.5649,
624
+ "step": 1010
625
+ },
626
+ {
627
+ "epoch": 1.47,
628
+ "learning_rate": 2.8350240256273357e-05,
629
+ "loss": 0.5231,
630
+ "step": 1020
631
+ },
632
+ {
633
+ "epoch": 1.48,
634
+ "learning_rate": 2.808328884143086e-05,
635
+ "loss": 0.5286,
636
+ "step": 1030
637
+ },
638
+ {
639
+ "epoch": 1.5,
640
+ "learning_rate": 2.7816337426588362e-05,
641
+ "loss": 0.5373,
642
+ "step": 1040
643
+ },
644
+ {
645
+ "epoch": 1.51,
646
+ "learning_rate": 2.7549386011745866e-05,
647
+ "loss": 0.5611,
648
+ "step": 1050
649
+ },
650
+ {
651
+ "epoch": 1.53,
652
+ "learning_rate": 2.7282434596903367e-05,
653
+ "loss": 0.5209,
654
+ "step": 1060
655
+ },
656
+ {
657
+ "epoch": 1.54,
658
+ "learning_rate": 2.7015483182060868e-05,
659
+ "loss": 0.5659,
660
+ "step": 1070
661
+ },
662
+ {
663
+ "epoch": 1.56,
664
+ "learning_rate": 2.6748531767218365e-05,
665
+ "loss": 0.5597,
666
+ "step": 1080
667
+ },
668
+ {
669
+ "epoch": 1.57,
670
+ "learning_rate": 2.6481580352375866e-05,
671
+ "loss": 0.5446,
672
+ "step": 1090
673
+ },
674
+ {
675
+ "epoch": 1.59,
676
+ "learning_rate": 2.621462893753337e-05,
677
+ "loss": 0.5282,
678
+ "step": 1100
679
+ },
680
+ {
681
+ "epoch": 1.6,
682
+ "learning_rate": 2.594767752269087e-05,
683
+ "loss": 0.5635,
684
+ "step": 1110
685
+ },
686
+ {
687
+ "epoch": 1.61,
688
+ "learning_rate": 2.5680726107848373e-05,
689
+ "loss": 0.5449,
690
+ "step": 1120
691
+ },
692
+ {
693
+ "epoch": 1.63,
694
+ "learning_rate": 2.5413774693005877e-05,
695
+ "loss": 0.5426,
696
+ "step": 1130
697
+ },
698
+ {
699
+ "epoch": 1.64,
700
+ "learning_rate": 2.5146823278163374e-05,
701
+ "loss": 0.4938,
702
+ "step": 1140
703
+ },
704
+ {
705
+ "epoch": 1.66,
706
+ "learning_rate": 2.487987186332088e-05,
707
+ "loss": 0.532,
708
+ "step": 1150
709
+ },
710
+ {
711
+ "epoch": 1.67,
712
+ "learning_rate": 2.4612920448478376e-05,
713
+ "loss": 0.552,
714
+ "step": 1160
715
+ },
716
+ {
717
+ "epoch": 1.69,
718
+ "learning_rate": 2.434596903363588e-05,
719
+ "loss": 0.5506,
720
+ "step": 1170
721
+ },
722
+ {
723
+ "epoch": 1.7,
724
+ "learning_rate": 2.407901761879338e-05,
725
+ "loss": 0.5466,
726
+ "step": 1180
727
+ },
728
+ {
729
+ "epoch": 1.71,
730
+ "learning_rate": 2.3812066203950882e-05,
731
+ "loss": 0.5244,
732
+ "step": 1190
733
+ },
734
+ {
735
+ "epoch": 1.73,
736
+ "learning_rate": 2.3545114789108383e-05,
737
+ "loss": 0.5397,
738
+ "step": 1200
739
+ },
740
+ {
741
+ "epoch": 1.74,
742
+ "learning_rate": 2.3278163374265884e-05,
743
+ "loss": 0.5262,
744
+ "step": 1210
745
+ },
746
+ {
747
+ "epoch": 1.76,
748
+ "learning_rate": 2.301121195942339e-05,
749
+ "loss": 0.5458,
750
+ "step": 1220
751
+ },
752
+ {
753
+ "epoch": 1.77,
754
+ "learning_rate": 2.2744260544580886e-05,
755
+ "loss": 0.5445,
756
+ "step": 1230
757
+ },
758
+ {
759
+ "epoch": 1.79,
760
+ "learning_rate": 2.247730912973839e-05,
761
+ "loss": 0.5246,
762
+ "step": 1240
763
+ },
764
+ {
765
+ "epoch": 1.8,
766
+ "learning_rate": 2.221035771489589e-05,
767
+ "loss": 0.5366,
768
+ "step": 1250
769
+ },
770
+ {
771
+ "epoch": 1.82,
772
+ "learning_rate": 2.194340630005339e-05,
773
+ "loss": 0.5158,
774
+ "step": 1260
775
+ },
776
+ {
777
+ "epoch": 1.83,
778
+ "learning_rate": 2.1676454885210893e-05,
779
+ "loss": 0.5354,
780
+ "step": 1270
781
+ },
782
+ {
783
+ "epoch": 1.84,
784
+ "learning_rate": 2.1409503470368394e-05,
785
+ "loss": 0.5365,
786
+ "step": 1280
787
+ },
788
+ {
789
+ "epoch": 1.86,
790
+ "learning_rate": 2.1142552055525898e-05,
791
+ "loss": 0.5094,
792
+ "step": 1290
793
+ },
794
+ {
795
+ "epoch": 1.87,
796
+ "learning_rate": 2.0875600640683396e-05,
797
+ "loss": 0.5393,
798
+ "step": 1300
799
+ },
800
+ {
801
+ "epoch": 1.89,
802
+ "learning_rate": 2.0608649225840897e-05,
803
+ "loss": 0.4804,
804
+ "step": 1310
805
+ },
806
+ {
807
+ "epoch": 1.9,
808
+ "learning_rate": 2.03416978109984e-05,
809
+ "loss": 0.4944,
810
+ "step": 1320
811
+ },
812
+ {
813
+ "epoch": 1.92,
814
+ "learning_rate": 2.00747463961559e-05,
815
+ "loss": 0.5167,
816
+ "step": 1330
817
+ },
818
+ {
819
+ "epoch": 1.93,
820
+ "learning_rate": 1.9807794981313403e-05,
821
+ "loss": 0.5164,
822
+ "step": 1340
823
+ },
824
+ {
825
+ "epoch": 1.95,
826
+ "learning_rate": 1.9540843566470904e-05,
827
+ "loss": 0.522,
828
+ "step": 1350
829
+ },
830
+ {
831
+ "epoch": 1.96,
832
+ "learning_rate": 1.9273892151628405e-05,
833
+ "loss": 0.5077,
834
+ "step": 1360
835
+ },
836
+ {
837
+ "epoch": 1.97,
838
+ "learning_rate": 1.9006940736785906e-05,
839
+ "loss": 0.5311,
840
+ "step": 1370
841
+ },
842
+ {
843
+ "epoch": 1.99,
844
+ "learning_rate": 1.8739989321943407e-05,
845
+ "loss": 0.4836,
846
+ "step": 1380
847
+ },
848
+ {
849
+ "epoch": 2.0,
850
+ "eval_accuracy": 0.792359140656668,
851
+ "eval_loss": 0.38869696855545044,
852
+ "eval_runtime": 102.7122,
853
+ "eval_samples_per_second": 96.074,
854
+ "eval_steps_per_second": 3.008,
855
+ "step": 1388
856
+ },
857
+ {
858
+ "epoch": 2.0,
859
+ "learning_rate": 1.847303790710091e-05,
860
+ "loss": 0.4986,
861
+ "step": 1390
862
+ },
863
+ {
864
+ "epoch": 2.02,
865
+ "learning_rate": 1.820608649225841e-05,
866
+ "loss": 0.5246,
867
+ "step": 1400
868
+ },
869
+ {
870
+ "epoch": 2.03,
871
+ "learning_rate": 1.7939135077415913e-05,
872
+ "loss": 0.5002,
873
+ "step": 1410
874
+ },
875
+ {
876
+ "epoch": 2.05,
877
+ "learning_rate": 1.7672183662573414e-05,
878
+ "loss": 0.4831,
879
+ "step": 1420
880
+ },
881
+ {
882
+ "epoch": 2.06,
883
+ "learning_rate": 1.740523224773091e-05,
884
+ "loss": 0.516,
885
+ "step": 1430
886
+ },
887
+ {
888
+ "epoch": 2.07,
889
+ "learning_rate": 1.7138280832888415e-05,
890
+ "loss": 0.491,
891
+ "step": 1440
892
+ },
893
+ {
894
+ "epoch": 2.09,
895
+ "learning_rate": 1.6871329418045916e-05,
896
+ "loss": 0.5351,
897
+ "step": 1450
898
+ },
899
+ {
900
+ "epoch": 2.1,
901
+ "learning_rate": 1.660437800320342e-05,
902
+ "loss": 0.5093,
903
+ "step": 1460
904
+ },
905
+ {
906
+ "epoch": 2.12,
907
+ "learning_rate": 1.6337426588360918e-05,
908
+ "loss": 0.5097,
909
+ "step": 1470
910
+ },
911
+ {
912
+ "epoch": 2.13,
913
+ "learning_rate": 1.607047517351842e-05,
914
+ "loss": 0.4834,
915
+ "step": 1480
916
+ },
917
+ {
918
+ "epoch": 2.15,
919
+ "learning_rate": 1.5803523758675923e-05,
920
+ "loss": 0.4861,
921
+ "step": 1490
922
+ },
923
+ {
924
+ "epoch": 2.16,
925
+ "learning_rate": 1.553657234383342e-05,
926
+ "loss": 0.4907,
927
+ "step": 1500
928
+ },
929
+ {
930
+ "epoch": 2.18,
931
+ "learning_rate": 1.5269620928990925e-05,
932
+ "loss": 0.5012,
933
+ "step": 1510
934
+ },
935
+ {
936
+ "epoch": 2.19,
937
+ "learning_rate": 1.5002669514148426e-05,
938
+ "loss": 0.448,
939
+ "step": 1520
940
+ },
941
+ {
942
+ "epoch": 2.2,
943
+ "learning_rate": 1.4735718099305925e-05,
944
+ "loss": 0.4973,
945
+ "step": 1530
946
+ },
947
+ {
948
+ "epoch": 2.22,
949
+ "learning_rate": 1.4468766684463428e-05,
950
+ "loss": 0.506,
951
+ "step": 1540
952
+ },
953
+ {
954
+ "epoch": 2.23,
955
+ "learning_rate": 1.420181526962093e-05,
956
+ "loss": 0.4568,
957
+ "step": 1550
958
+ },
959
+ {
960
+ "epoch": 2.25,
961
+ "learning_rate": 1.3934863854778431e-05,
962
+ "loss": 0.489,
963
+ "step": 1560
964
+ },
965
+ {
966
+ "epoch": 2.26,
967
+ "learning_rate": 1.366791243993593e-05,
968
+ "loss": 0.4819,
969
+ "step": 1570
970
+ },
971
+ {
972
+ "epoch": 2.28,
973
+ "learning_rate": 1.3400961025093433e-05,
974
+ "loss": 0.516,
975
+ "step": 1580
976
+ },
977
+ {
978
+ "epoch": 2.29,
979
+ "learning_rate": 1.3134009610250936e-05,
980
+ "loss": 0.494,
981
+ "step": 1590
982
+ },
983
+ {
984
+ "epoch": 2.31,
985
+ "learning_rate": 1.2867058195408435e-05,
986
+ "loss": 0.4747,
987
+ "step": 1600
988
+ },
989
+ {
990
+ "epoch": 2.32,
991
+ "learning_rate": 1.2600106780565938e-05,
992
+ "loss": 0.4525,
993
+ "step": 1610
994
+ },
995
+ {
996
+ "epoch": 2.33,
997
+ "learning_rate": 1.2333155365723439e-05,
998
+ "loss": 0.4705,
999
+ "step": 1620
1000
+ },
1001
+ {
1002
+ "epoch": 2.35,
1003
+ "learning_rate": 1.206620395088094e-05,
1004
+ "loss": 0.5065,
1005
+ "step": 1630
1006
+ },
1007
+ {
1008
+ "epoch": 2.36,
1009
+ "learning_rate": 1.179925253603844e-05,
1010
+ "loss": 0.469,
1011
+ "step": 1640
1012
+ },
1013
+ {
1014
+ "epoch": 2.38,
1015
+ "learning_rate": 1.1532301121195943e-05,
1016
+ "loss": 0.4831,
1017
+ "step": 1650
1018
+ },
1019
+ {
1020
+ "epoch": 2.39,
1021
+ "learning_rate": 1.1265349706353444e-05,
1022
+ "loss": 0.4784,
1023
+ "step": 1660
1024
+ },
1025
+ {
1026
+ "epoch": 2.41,
1027
+ "learning_rate": 1.0998398291510947e-05,
1028
+ "loss": 0.4768,
1029
+ "step": 1670
1030
+ },
1031
+ {
1032
+ "epoch": 2.42,
1033
+ "learning_rate": 1.0731446876668448e-05,
1034
+ "loss": 0.4718,
1035
+ "step": 1680
1036
+ },
1037
+ {
1038
+ "epoch": 2.44,
1039
+ "learning_rate": 1.0464495461825948e-05,
1040
+ "loss": 0.4492,
1041
+ "step": 1690
1042
+ },
1043
+ {
1044
+ "epoch": 2.45,
1045
+ "learning_rate": 1.019754404698345e-05,
1046
+ "loss": 0.4921,
1047
+ "step": 1700
1048
+ },
1049
+ {
1050
+ "epoch": 2.46,
1051
+ "learning_rate": 9.93059263214095e-06,
1052
+ "loss": 0.4963,
1053
+ "step": 1710
1054
+ },
1055
+ {
1056
+ "epoch": 2.48,
1057
+ "learning_rate": 9.663641217298453e-06,
1058
+ "loss": 0.5026,
1059
+ "step": 1720
1060
+ },
1061
+ {
1062
+ "epoch": 2.49,
1063
+ "learning_rate": 9.396689802455954e-06,
1064
+ "loss": 0.4952,
1065
+ "step": 1730
1066
+ },
1067
+ {
1068
+ "epoch": 2.51,
1069
+ "learning_rate": 9.129738387613455e-06,
1070
+ "loss": 0.4896,
1071
+ "step": 1740
1072
+ },
1073
+ {
1074
+ "epoch": 2.52,
1075
+ "learning_rate": 8.862786972770956e-06,
1076
+ "loss": 0.4523,
1077
+ "step": 1750
1078
+ },
1079
+ {
1080
+ "epoch": 2.54,
1081
+ "learning_rate": 8.595835557928457e-06,
1082
+ "loss": 0.4524,
1083
+ "step": 1760
1084
+ },
1085
+ {
1086
+ "epoch": 2.55,
1087
+ "learning_rate": 8.32888414308596e-06,
1088
+ "loss": 0.5124,
1089
+ "step": 1770
1090
+ },
1091
+ {
1092
+ "epoch": 2.56,
1093
+ "learning_rate": 8.06193272824346e-06,
1094
+ "loss": 0.5054,
1095
+ "step": 1780
1096
+ },
1097
+ {
1098
+ "epoch": 2.58,
1099
+ "learning_rate": 7.794981313400963e-06,
1100
+ "loss": 0.5123,
1101
+ "step": 1790
1102
+ },
1103
+ {
1104
+ "epoch": 2.59,
1105
+ "learning_rate": 7.528029898558463e-06,
1106
+ "loss": 0.4805,
1107
+ "step": 1800
1108
+ },
1109
+ {
1110
+ "epoch": 2.61,
1111
+ "learning_rate": 7.261078483715964e-06,
1112
+ "loss": 0.511,
1113
+ "step": 1810
1114
+ },
1115
+ {
1116
+ "epoch": 2.62,
1117
+ "learning_rate": 6.9941270688734655e-06,
1118
+ "loss": 0.4488,
1119
+ "step": 1820
1120
+ },
1121
+ {
1122
+ "epoch": 2.64,
1123
+ "learning_rate": 6.727175654030966e-06,
1124
+ "loss": 0.491,
1125
+ "step": 1830
1126
+ },
1127
+ {
1128
+ "epoch": 2.65,
1129
+ "learning_rate": 6.460224239188468e-06,
1130
+ "loss": 0.5166,
1131
+ "step": 1840
1132
+ },
1133
+ {
1134
+ "epoch": 2.67,
1135
+ "learning_rate": 6.193272824345969e-06,
1136
+ "loss": 0.4727,
1137
+ "step": 1850
1138
+ },
1139
+ {
1140
+ "epoch": 2.68,
1141
+ "learning_rate": 5.926321409503471e-06,
1142
+ "loss": 0.4733,
1143
+ "step": 1860
1144
+ },
1145
+ {
1146
+ "epoch": 2.69,
1147
+ "learning_rate": 5.659369994660972e-06,
1148
+ "loss": 0.4678,
1149
+ "step": 1870
1150
+ },
1151
+ {
1152
+ "epoch": 2.71,
1153
+ "learning_rate": 5.3924185798184735e-06,
1154
+ "loss": 0.4781,
1155
+ "step": 1880
1156
+ },
1157
+ {
1158
+ "epoch": 2.72,
1159
+ "learning_rate": 5.1254671649759744e-06,
1160
+ "loss": 0.4796,
1161
+ "step": 1890
1162
+ },
1163
+ {
1164
+ "epoch": 2.74,
1165
+ "learning_rate": 4.858515750133475e-06,
1166
+ "loss": 0.4743,
1167
+ "step": 1900
1168
+ },
1169
+ {
1170
+ "epoch": 2.75,
1171
+ "learning_rate": 4.591564335290977e-06,
1172
+ "loss": 0.4762,
1173
+ "step": 1910
1174
+ },
1175
+ {
1176
+ "epoch": 2.77,
1177
+ "learning_rate": 4.324612920448479e-06,
1178
+ "loss": 0.4579,
1179
+ "step": 1920
1180
+ },
1181
+ {
1182
+ "epoch": 2.78,
1183
+ "learning_rate": 4.05766150560598e-06,
1184
+ "loss": 0.4649,
1185
+ "step": 1930
1186
+ },
1187
+ {
1188
+ "epoch": 2.8,
1189
+ "learning_rate": 3.7907100907634816e-06,
1190
+ "loss": 0.4576,
1191
+ "step": 1940
1192
+ },
1193
+ {
1194
+ "epoch": 2.81,
1195
+ "learning_rate": 3.5237586759209825e-06,
1196
+ "loss": 0.4711,
1197
+ "step": 1950
1198
+ },
1199
+ {
1200
+ "epoch": 2.82,
1201
+ "learning_rate": 3.256807261078484e-06,
1202
+ "loss": 0.4942,
1203
+ "step": 1960
1204
+ },
1205
+ {
1206
+ "epoch": 2.84,
1207
+ "learning_rate": 2.989855846235985e-06,
1208
+ "loss": 0.4716,
1209
+ "step": 1970
1210
+ },
1211
+ {
1212
+ "epoch": 2.85,
1213
+ "learning_rate": 2.7229044313934865e-06,
1214
+ "loss": 0.4874,
1215
+ "step": 1980
1216
+ },
1217
+ {
1218
+ "epoch": 2.87,
1219
+ "learning_rate": 2.455953016550988e-06,
1220
+ "loss": 0.4933,
1221
+ "step": 1990
1222
+ },
1223
+ {
1224
+ "epoch": 2.88,
1225
+ "learning_rate": 2.189001601708489e-06,
1226
+ "loss": 0.4802,
1227
+ "step": 2000
1228
+ },
1229
+ {
1230
+ "epoch": 2.9,
1231
+ "learning_rate": 1.9220501868659905e-06,
1232
+ "loss": 0.4897,
1233
+ "step": 2010
1234
+ },
1235
+ {
1236
+ "epoch": 2.91,
1237
+ "learning_rate": 1.6550987720234916e-06,
1238
+ "loss": 0.4512,
1239
+ "step": 2020
1240
+ },
1241
+ {
1242
+ "epoch": 2.93,
1243
+ "learning_rate": 1.3881473571809932e-06,
1244
+ "loss": 0.4543,
1245
+ "step": 2030
1246
+ },
1247
+ {
1248
+ "epoch": 2.94,
1249
+ "learning_rate": 1.1211959423384945e-06,
1250
+ "loss": 0.48,
1251
+ "step": 2040
1252
+ },
1253
+ {
1254
+ "epoch": 2.95,
1255
+ "learning_rate": 8.542445274959957e-07,
1256
+ "loss": 0.4739,
1257
+ "step": 2050
1258
+ },
1259
+ {
1260
+ "epoch": 2.97,
1261
+ "learning_rate": 5.872931126534971e-07,
1262
+ "loss": 0.4669,
1263
+ "step": 2060
1264
+ },
1265
+ {
1266
+ "epoch": 2.98,
1267
+ "learning_rate": 3.203416978109984e-07,
1268
+ "loss": 0.4674,
1269
+ "step": 2070
1270
+ },
1271
+ {
1272
+ "epoch": 3.0,
1273
+ "learning_rate": 5.339028296849973e-08,
1274
+ "loss": 0.4672,
1275
+ "step": 2080
1276
+ },
1277
+ {
1278
+ "epoch": 3.0,
1279
+ "eval_accuracy": 0.8009728415079044,
1280
+ "eval_loss": 0.3678824007511139,
1281
+ "eval_runtime": 102.7271,
1282
+ "eval_samples_per_second": 96.06,
1283
+ "eval_steps_per_second": 3.008,
1284
+ "step": 2082
1285
+ },
1286
+ {
1287
+ "epoch": 3.0,
1288
+ "step": 2082,
1289
+ "total_flos": 6.622303803251835e+18,
1290
+ "train_loss": 0.5971084463836824,
1291
+ "train_runtime": 3243.1106,
1292
+ "train_samples_per_second": 82.147,
1293
+ "train_steps_per_second": 0.642
1294
+ }
1295
+ ],
1296
+ "logging_steps": 10,
1297
+ "max_steps": 2082,
1298
+ "num_train_epochs": 3,
1299
+ "save_steps": 500,
1300
+ "total_flos": 6.622303803251835e+18,
1301
+ "trial_name": null,
1302
+ "trial_params": null
1303
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab59f10af9b146c044ec25db9cc1bc7025b7ecde2028da062ec09b989b87eb06
3
+ size 4603