Sara5115 commited on
Commit
89f629e
·
verified ·
1 Parent(s): f776336

Uploading model files

Browse files
Files changed (49) hide show
  1. README.md +83 -0
  2. all_results.json +13 -0
  3. checkpoint-12/config.json +60 -0
  4. checkpoint-12/model.safetensors +3 -0
  5. checkpoint-12/optimizer.pt +3 -0
  6. checkpoint-12/preprocessor_config.json +23 -0
  7. checkpoint-12/rng_state.pth +3 -0
  8. checkpoint-12/scheduler.pt +3 -0
  9. checkpoint-12/trainer_state.json +59 -0
  10. checkpoint-12/training_args.bin +3 -0
  11. checkpoint-18/config.json +60 -0
  12. checkpoint-18/model.safetensors +3 -0
  13. checkpoint-18/optimizer.pt +3 -0
  14. checkpoint-18/preprocessor_config.json +23 -0
  15. checkpoint-18/rng_state.pth +3 -0
  16. checkpoint-18/scheduler.pt +3 -0
  17. checkpoint-18/trainer_state.json +68 -0
  18. checkpoint-18/training_args.bin +3 -0
  19. checkpoint-24/config.json +60 -0
  20. checkpoint-24/model.safetensors +3 -0
  21. checkpoint-24/optimizer.pt +3 -0
  22. checkpoint-24/preprocessor_config.json +23 -0
  23. checkpoint-24/rng_state.pth +3 -0
  24. checkpoint-24/scheduler.pt +3 -0
  25. checkpoint-24/trainer_state.json +84 -0
  26. checkpoint-24/training_args.bin +3 -0
  27. checkpoint-30/config.json +60 -0
  28. checkpoint-30/model.safetensors +3 -0
  29. checkpoint-30/optimizer.pt +3 -0
  30. checkpoint-30/preprocessor_config.json +23 -0
  31. checkpoint-30/rng_state.pth +3 -0
  32. checkpoint-30/scheduler.pt +3 -0
  33. checkpoint-30/trainer_state.json +100 -0
  34. checkpoint-30/training_args.bin +3 -0
  35. checkpoint-6/config.json +60 -0
  36. checkpoint-6/model.safetensors +3 -0
  37. checkpoint-6/optimizer.pt +3 -0
  38. checkpoint-6/preprocessor_config.json +23 -0
  39. checkpoint-6/rng_state.pth +3 -0
  40. checkpoint-6/scheduler.pt +3 -0
  41. checkpoint-6/trainer_state.json +43 -0
  42. checkpoint-6/training_args.bin +3 -0
  43. config.json +60 -0
  44. eval_results.json +8 -0
  45. model.safetensors +3 -0
  46. preprocessor_config.json +23 -0
  47. train_results.json +8 -0
  48. trainer_state.json +118 -0
  49. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,83 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: apache-2.0
4
+ base_model: microsoft/swin-tiny-patch4-window7-224
5
+ tags:
6
+ - generated_from_trainer
7
+ datasets:
8
+ - imagefolder
9
+ metrics:
10
+ - accuracy
11
+ model-index:
12
+ - name: swin-tiny-patch4-window7-224-BlurClassification
13
+ results:
14
+ - task:
15
+ name: Image Classification
16
+ type: image-classification
17
+ dataset:
18
+ name: imagefolder
19
+ type: imagefolder
20
+ config: default
21
+ split: train
22
+ args: default
23
+ metrics:
24
+ - name: Accuracy
25
+ type: accuracy
26
+ value: 0.9905660377358491
27
+ ---
28
+
29
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
30
+ should probably proofread and complete it, then remove this comment. -->
31
+
32
+ # swin-tiny-patch4-window7-224-BlurClassification
33
+
34
+ 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.
35
+ It achieves the following results on the evaluation set:
36
+ - Loss: 0.0157
37
+ - Accuracy: 0.9906
38
+
39
+ ## Model description
40
+
41
+ More information needed
42
+
43
+ ## Intended uses & limitations
44
+
45
+ More information needed
46
+
47
+ ## Training and evaluation data
48
+
49
+ More information needed
50
+
51
+ ## Training procedure
52
+
53
+ ### Training hyperparameters
54
+
55
+ The following hyperparameters were used during training:
56
+ - learning_rate: 5e-05
57
+ - train_batch_size: 32
58
+ - eval_batch_size: 32
59
+ - seed: 42
60
+ - gradient_accumulation_steps: 4
61
+ - total_train_batch_size: 128
62
+ - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
63
+ - lr_scheduler_type: linear
64
+ - lr_scheduler_warmup_ratio: 0.1
65
+ - num_epochs: 5
66
+
67
+ ### Training results
68
+
69
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
70
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
71
+ | No log | 1.0 | 6 | 0.2406 | 0.9811 |
72
+ | 0.4213 | 2.0 | 12 | 0.0446 | 0.9874 |
73
+ | 0.4213 | 3.0 | 18 | 0.0409 | 0.9811 |
74
+ | 0.021 | 4.0 | 24 | 0.0157 | 0.9906 |
75
+ | 0.0132 | 5.0 | 30 | 0.0318 | 0.9811 |
76
+
77
+
78
+ ### Framework versions
79
+
80
+ - Transformers 4.50.3
81
+ - Pytorch 2.6.0+cpu
82
+ - Datasets 3.5.0
83
+ - Tokenizers 0.21.1
all_results.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.0,
3
+ "eval_accuracy": 0.9905660377358491,
4
+ "eval_loss": 0.01574210450053215,
5
+ "eval_runtime": 16.0331,
6
+ "eval_samples_per_second": 19.834,
7
+ "eval_steps_per_second": 0.624,
8
+ "total_flos": 9.221571913752576e+16,
9
+ "train_loss": 0.15185614277919132,
10
+ "train_runtime": 591.7097,
11
+ "train_samples_per_second": 6.27,
12
+ "train_steps_per_second": 0.051
13
+ }
checkpoint-12/config.json ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "SwinForImageClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.0,
6
+ "depths": [
7
+ 2,
8
+ 2,
9
+ 6,
10
+ 2
11
+ ],
12
+ "drop_path_rate": 0.1,
13
+ "embed_dim": 96,
14
+ "encoder_stride": 32,
15
+ "hidden_act": "gelu",
16
+ "hidden_dropout_prob": 0.0,
17
+ "hidden_size": 768,
18
+ "id2label": {
19
+ "0": "Blur",
20
+ "1": "Not Blur"
21
+ },
22
+ "image_size": 224,
23
+ "initializer_range": 0.02,
24
+ "label2id": {
25
+ "Blur": 0,
26
+ "Not Blur": 1
27
+ },
28
+ "layer_norm_eps": 1e-05,
29
+ "mlp_ratio": 4.0,
30
+ "model_type": "swin",
31
+ "num_channels": 3,
32
+ "num_heads": [
33
+ 3,
34
+ 6,
35
+ 12,
36
+ 24
37
+ ],
38
+ "num_layers": 4,
39
+ "out_features": [
40
+ "stage4"
41
+ ],
42
+ "out_indices": [
43
+ 4
44
+ ],
45
+ "patch_size": 4,
46
+ "path_norm": true,
47
+ "problem_type": "single_label_classification",
48
+ "qkv_bias": true,
49
+ "stage_names": [
50
+ "stem",
51
+ "stage1",
52
+ "stage2",
53
+ "stage3",
54
+ "stage4"
55
+ ],
56
+ "torch_dtype": "float32",
57
+ "transformers_version": "4.50.3",
58
+ "use_absolute_embeddings": false,
59
+ "window_size": 7
60
+ }
checkpoint-12/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8195bbc44dd4da8d53f9e7603e9b4af610eb1ed4febd7798cd089c1cc14eff86
3
+ size 110342832
checkpoint-12/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e32f73969c912b2e97726afa8cf19ef78831cc2d356334457dcba1c95d22e251
3
+ size 220344378
checkpoint-12/preprocessor_config.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_convert_rgb": null,
3
+ "do_normalize": true,
4
+ "do_rescale": true,
5
+ "do_resize": true,
6
+ "image_mean": [
7
+ 0.485,
8
+ 0.456,
9
+ 0.406
10
+ ],
11
+ "image_processor_type": "ViTImageProcessor",
12
+ "image_std": [
13
+ 0.229,
14
+ 0.224,
15
+ 0.225
16
+ ],
17
+ "resample": 3,
18
+ "rescale_factor": 0.00392156862745098,
19
+ "size": {
20
+ "height": 224,
21
+ "width": 224
22
+ }
23
+ }
checkpoint-12/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8dd3ed1a0808009195fb02026a7232e6001954a850b055f64b3c886e80c6ce96
3
+ size 13990
checkpoint-12/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f2f1413092f4c72eab6937d9c2a69dab3898e360c5bab300fdec529439e39db
3
+ size 1064
checkpoint-12/trainer_state.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 12,
3
+ "best_metric": 0.9874213836477987,
4
+ "best_model_checkpoint": "swin-tiny-patch4-window7-224-BlurClassification\\checkpoint-12",
5
+ "epoch": 2.0,
6
+ "eval_steps": 500,
7
+ "global_step": 12,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 1.0,
14
+ "eval_accuracy": 0.9811320754716981,
15
+ "eval_loss": 0.24062196910381317,
16
+ "eval_runtime": 13.6835,
17
+ "eval_samples_per_second": 23.24,
18
+ "eval_steps_per_second": 0.731,
19
+ "step": 6
20
+ },
21
+ {
22
+ "epoch": 1.6666666666666665,
23
+ "grad_norm": 1.9544028043746948,
24
+ "learning_rate": 3.7037037037037037e-05,
25
+ "loss": 0.4213,
26
+ "step": 10
27
+ },
28
+ {
29
+ "epoch": 2.0,
30
+ "eval_accuracy": 0.9874213836477987,
31
+ "eval_loss": 0.044603366404771805,
32
+ "eval_runtime": 15.0982,
33
+ "eval_samples_per_second": 21.062,
34
+ "eval_steps_per_second": 0.662,
35
+ "step": 12
36
+ }
37
+ ],
38
+ "logging_steps": 10,
39
+ "max_steps": 30,
40
+ "num_input_tokens_seen": 0,
41
+ "num_train_epochs": 5,
42
+ "save_steps": 500,
43
+ "stateful_callbacks": {
44
+ "TrainerControl": {
45
+ "args": {
46
+ "should_epoch_stop": false,
47
+ "should_evaluate": false,
48
+ "should_log": false,
49
+ "should_save": true,
50
+ "should_training_stop": false
51
+ },
52
+ "attributes": {}
53
+ }
54
+ },
55
+ "total_flos": 3.68862876550103e+16,
56
+ "train_batch_size": 32,
57
+ "trial_name": null,
58
+ "trial_params": null
59
+ }
checkpoint-12/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80a6480d20da699fccade53c3fd9b35b8e309a5b9e1bfeca6411e3b8969645d4
3
+ size 5368
checkpoint-18/config.json ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "SwinForImageClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.0,
6
+ "depths": [
7
+ 2,
8
+ 2,
9
+ 6,
10
+ 2
11
+ ],
12
+ "drop_path_rate": 0.1,
13
+ "embed_dim": 96,
14
+ "encoder_stride": 32,
15
+ "hidden_act": "gelu",
16
+ "hidden_dropout_prob": 0.0,
17
+ "hidden_size": 768,
18
+ "id2label": {
19
+ "0": "Blur",
20
+ "1": "Not Blur"
21
+ },
22
+ "image_size": 224,
23
+ "initializer_range": 0.02,
24
+ "label2id": {
25
+ "Blur": 0,
26
+ "Not Blur": 1
27
+ },
28
+ "layer_norm_eps": 1e-05,
29
+ "mlp_ratio": 4.0,
30
+ "model_type": "swin",
31
+ "num_channels": 3,
32
+ "num_heads": [
33
+ 3,
34
+ 6,
35
+ 12,
36
+ 24
37
+ ],
38
+ "num_layers": 4,
39
+ "out_features": [
40
+ "stage4"
41
+ ],
42
+ "out_indices": [
43
+ 4
44
+ ],
45
+ "patch_size": 4,
46
+ "path_norm": true,
47
+ "problem_type": "single_label_classification",
48
+ "qkv_bias": true,
49
+ "stage_names": [
50
+ "stem",
51
+ "stage1",
52
+ "stage2",
53
+ "stage3",
54
+ "stage4"
55
+ ],
56
+ "torch_dtype": "float32",
57
+ "transformers_version": "4.50.3",
58
+ "use_absolute_embeddings": false,
59
+ "window_size": 7
60
+ }
checkpoint-18/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35ef7d163551a39ffc7a2f954367f081c3505d93ae245f93a62a15a8f55d04cc
3
+ size 110342832
checkpoint-18/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c480f0bc3698638b2d64720ba290ae1c161a354f6f9c5f9001d69546ae5eb18
3
+ size 220344378
checkpoint-18/preprocessor_config.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_convert_rgb": null,
3
+ "do_normalize": true,
4
+ "do_rescale": true,
5
+ "do_resize": true,
6
+ "image_mean": [
7
+ 0.485,
8
+ 0.456,
9
+ 0.406
10
+ ],
11
+ "image_processor_type": "ViTImageProcessor",
12
+ "image_std": [
13
+ 0.229,
14
+ 0.224,
15
+ 0.225
16
+ ],
17
+ "resample": 3,
18
+ "rescale_factor": 0.00392156862745098,
19
+ "size": {
20
+ "height": 224,
21
+ "width": 224
22
+ }
23
+ }
checkpoint-18/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99782682d2d47ef04cd6f2c565f515faba8a59a3d6862a9224c20fa4a6f8d818
3
+ size 13990
checkpoint-18/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2da14a189d5f117747b898056d794d80fb122263e64d9e6f675ea725914671df
3
+ size 1064
checkpoint-18/trainer_state.json ADDED
@@ -0,0 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 12,
3
+ "best_metric": 0.9874213836477987,
4
+ "best_model_checkpoint": "swin-tiny-patch4-window7-224-BlurClassification\\checkpoint-12",
5
+ "epoch": 3.0,
6
+ "eval_steps": 500,
7
+ "global_step": 18,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 1.0,
14
+ "eval_accuracy": 0.9811320754716981,
15
+ "eval_loss": 0.24062196910381317,
16
+ "eval_runtime": 13.6835,
17
+ "eval_samples_per_second": 23.24,
18
+ "eval_steps_per_second": 0.731,
19
+ "step": 6
20
+ },
21
+ {
22
+ "epoch": 1.6666666666666665,
23
+ "grad_norm": 1.9544028043746948,
24
+ "learning_rate": 3.7037037037037037e-05,
25
+ "loss": 0.4213,
26
+ "step": 10
27
+ },
28
+ {
29
+ "epoch": 2.0,
30
+ "eval_accuracy": 0.9874213836477987,
31
+ "eval_loss": 0.044603366404771805,
32
+ "eval_runtime": 15.0982,
33
+ "eval_samples_per_second": 21.062,
34
+ "eval_steps_per_second": 0.662,
35
+ "step": 12
36
+ },
37
+ {
38
+ "epoch": 3.0,
39
+ "eval_accuracy": 0.9811320754716981,
40
+ "eval_loss": 0.04091091454029083,
41
+ "eval_runtime": 15.2601,
42
+ "eval_samples_per_second": 20.839,
43
+ "eval_steps_per_second": 0.655,
44
+ "step": 18
45
+ }
46
+ ],
47
+ "logging_steps": 10,
48
+ "max_steps": 30,
49
+ "num_input_tokens_seen": 0,
50
+ "num_train_epochs": 5,
51
+ "save_steps": 500,
52
+ "stateful_callbacks": {
53
+ "TrainerControl": {
54
+ "args": {
55
+ "should_epoch_stop": false,
56
+ "should_evaluate": false,
57
+ "should_log": false,
58
+ "should_save": true,
59
+ "should_training_stop": false
60
+ },
61
+ "attributes": {}
62
+ }
63
+ },
64
+ "total_flos": 5.532943148251546e+16,
65
+ "train_batch_size": 32,
66
+ "trial_name": null,
67
+ "trial_params": null
68
+ }
checkpoint-18/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80a6480d20da699fccade53c3fd9b35b8e309a5b9e1bfeca6411e3b8969645d4
3
+ size 5368
checkpoint-24/config.json ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "SwinForImageClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.0,
6
+ "depths": [
7
+ 2,
8
+ 2,
9
+ 6,
10
+ 2
11
+ ],
12
+ "drop_path_rate": 0.1,
13
+ "embed_dim": 96,
14
+ "encoder_stride": 32,
15
+ "hidden_act": "gelu",
16
+ "hidden_dropout_prob": 0.0,
17
+ "hidden_size": 768,
18
+ "id2label": {
19
+ "0": "Blur",
20
+ "1": "Not Blur"
21
+ },
22
+ "image_size": 224,
23
+ "initializer_range": 0.02,
24
+ "label2id": {
25
+ "Blur": 0,
26
+ "Not Blur": 1
27
+ },
28
+ "layer_norm_eps": 1e-05,
29
+ "mlp_ratio": 4.0,
30
+ "model_type": "swin",
31
+ "num_channels": 3,
32
+ "num_heads": [
33
+ 3,
34
+ 6,
35
+ 12,
36
+ 24
37
+ ],
38
+ "num_layers": 4,
39
+ "out_features": [
40
+ "stage4"
41
+ ],
42
+ "out_indices": [
43
+ 4
44
+ ],
45
+ "patch_size": 4,
46
+ "path_norm": true,
47
+ "problem_type": "single_label_classification",
48
+ "qkv_bias": true,
49
+ "stage_names": [
50
+ "stem",
51
+ "stage1",
52
+ "stage2",
53
+ "stage3",
54
+ "stage4"
55
+ ],
56
+ "torch_dtype": "float32",
57
+ "transformers_version": "4.50.3",
58
+ "use_absolute_embeddings": false,
59
+ "window_size": 7
60
+ }
checkpoint-24/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:44fdf1f251b8696d2f545a8ed9c3b22fd0130bc9a47c5f25d463f8e51fd851a4
3
+ size 110342832
checkpoint-24/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:40c69a68931f3af6eeda9957e8258b9afda890b8351900ad93a118d46533d6cc
3
+ size 220344378
checkpoint-24/preprocessor_config.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_convert_rgb": null,
3
+ "do_normalize": true,
4
+ "do_rescale": true,
5
+ "do_resize": true,
6
+ "image_mean": [
7
+ 0.485,
8
+ 0.456,
9
+ 0.406
10
+ ],
11
+ "image_processor_type": "ViTImageProcessor",
12
+ "image_std": [
13
+ 0.229,
14
+ 0.224,
15
+ 0.225
16
+ ],
17
+ "resample": 3,
18
+ "rescale_factor": 0.00392156862745098,
19
+ "size": {
20
+ "height": 224,
21
+ "width": 224
22
+ }
23
+ }
checkpoint-24/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ce01fab0c58450aae729eac60b8c54c5a2418607f2ab1ff0001252adf321d91
3
+ size 13990
checkpoint-24/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed02afe9507feaf7f01463213ce827a21ac38d87a144d9ae9996caf5251d6055
3
+ size 1064
checkpoint-24/trainer_state.json ADDED
@@ -0,0 +1,84 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 24,
3
+ "best_metric": 0.9905660377358491,
4
+ "best_model_checkpoint": "swin-tiny-patch4-window7-224-BlurClassification\\checkpoint-24",
5
+ "epoch": 4.0,
6
+ "eval_steps": 500,
7
+ "global_step": 24,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 1.0,
14
+ "eval_accuracy": 0.9811320754716981,
15
+ "eval_loss": 0.24062196910381317,
16
+ "eval_runtime": 13.6835,
17
+ "eval_samples_per_second": 23.24,
18
+ "eval_steps_per_second": 0.731,
19
+ "step": 6
20
+ },
21
+ {
22
+ "epoch": 1.6666666666666665,
23
+ "grad_norm": 1.9544028043746948,
24
+ "learning_rate": 3.7037037037037037e-05,
25
+ "loss": 0.4213,
26
+ "step": 10
27
+ },
28
+ {
29
+ "epoch": 2.0,
30
+ "eval_accuracy": 0.9874213836477987,
31
+ "eval_loss": 0.044603366404771805,
32
+ "eval_runtime": 15.0982,
33
+ "eval_samples_per_second": 21.062,
34
+ "eval_steps_per_second": 0.662,
35
+ "step": 12
36
+ },
37
+ {
38
+ "epoch": 3.0,
39
+ "eval_accuracy": 0.9811320754716981,
40
+ "eval_loss": 0.04091091454029083,
41
+ "eval_runtime": 15.2601,
42
+ "eval_samples_per_second": 20.839,
43
+ "eval_steps_per_second": 0.655,
44
+ "step": 18
45
+ },
46
+ {
47
+ "epoch": 3.3333333333333335,
48
+ "grad_norm": 3.980639934539795,
49
+ "learning_rate": 1.8518518518518518e-05,
50
+ "loss": 0.021,
51
+ "step": 20
52
+ },
53
+ {
54
+ "epoch": 4.0,
55
+ "eval_accuracy": 0.9905660377358491,
56
+ "eval_loss": 0.01574210450053215,
57
+ "eval_runtime": 24.6406,
58
+ "eval_samples_per_second": 12.906,
59
+ "eval_steps_per_second": 0.406,
60
+ "step": 24
61
+ }
62
+ ],
63
+ "logging_steps": 10,
64
+ "max_steps": 30,
65
+ "num_input_tokens_seen": 0,
66
+ "num_train_epochs": 5,
67
+ "save_steps": 500,
68
+ "stateful_callbacks": {
69
+ "TrainerControl": {
70
+ "args": {
71
+ "should_epoch_stop": false,
72
+ "should_evaluate": false,
73
+ "should_log": false,
74
+ "should_save": true,
75
+ "should_training_stop": false
76
+ },
77
+ "attributes": {}
78
+ }
79
+ },
80
+ "total_flos": 7.37725753100206e+16,
81
+ "train_batch_size": 32,
82
+ "trial_name": null,
83
+ "trial_params": null
84
+ }
checkpoint-24/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80a6480d20da699fccade53c3fd9b35b8e309a5b9e1bfeca6411e3b8969645d4
3
+ size 5368
checkpoint-30/config.json ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "SwinForImageClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.0,
6
+ "depths": [
7
+ 2,
8
+ 2,
9
+ 6,
10
+ 2
11
+ ],
12
+ "drop_path_rate": 0.1,
13
+ "embed_dim": 96,
14
+ "encoder_stride": 32,
15
+ "hidden_act": "gelu",
16
+ "hidden_dropout_prob": 0.0,
17
+ "hidden_size": 768,
18
+ "id2label": {
19
+ "0": "Blur",
20
+ "1": "Not Blur"
21
+ },
22
+ "image_size": 224,
23
+ "initializer_range": 0.02,
24
+ "label2id": {
25
+ "Blur": 0,
26
+ "Not Blur": 1
27
+ },
28
+ "layer_norm_eps": 1e-05,
29
+ "mlp_ratio": 4.0,
30
+ "model_type": "swin",
31
+ "num_channels": 3,
32
+ "num_heads": [
33
+ 3,
34
+ 6,
35
+ 12,
36
+ 24
37
+ ],
38
+ "num_layers": 4,
39
+ "out_features": [
40
+ "stage4"
41
+ ],
42
+ "out_indices": [
43
+ 4
44
+ ],
45
+ "patch_size": 4,
46
+ "path_norm": true,
47
+ "problem_type": "single_label_classification",
48
+ "qkv_bias": true,
49
+ "stage_names": [
50
+ "stem",
51
+ "stage1",
52
+ "stage2",
53
+ "stage3",
54
+ "stage4"
55
+ ],
56
+ "torch_dtype": "float32",
57
+ "transformers_version": "4.50.3",
58
+ "use_absolute_embeddings": false,
59
+ "window_size": 7
60
+ }
checkpoint-30/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:423f28c0425ff540941b4ff0b0e3362ff6f551fda738091624b23cc04ca1d8d5
3
+ size 110342832
checkpoint-30/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b39ce1f172ec83f2e02bf903926706415ac23bde6545918665da15e70011dc97
3
+ size 220344378
checkpoint-30/preprocessor_config.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_convert_rgb": null,
3
+ "do_normalize": true,
4
+ "do_rescale": true,
5
+ "do_resize": true,
6
+ "image_mean": [
7
+ 0.485,
8
+ 0.456,
9
+ 0.406
10
+ ],
11
+ "image_processor_type": "ViTImageProcessor",
12
+ "image_std": [
13
+ 0.229,
14
+ 0.224,
15
+ 0.225
16
+ ],
17
+ "resample": 3,
18
+ "rescale_factor": 0.00392156862745098,
19
+ "size": {
20
+ "height": 224,
21
+ "width": 224
22
+ }
23
+ }
checkpoint-30/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c2abc28794e7a672fd704848730ad7c6dc9f8bc919e9bd45690cd19111054ee
3
+ size 13990
checkpoint-30/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0af9e190801d1ef0d8a3b8e3dd199750cc410b521a382c693f6c5e98c1df7bae
3
+ size 1064
checkpoint-30/trainer_state.json ADDED
@@ -0,0 +1,100 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 24,
3
+ "best_metric": 0.9905660377358491,
4
+ "best_model_checkpoint": "swin-tiny-patch4-window7-224-BlurClassification\\checkpoint-24",
5
+ "epoch": 5.0,
6
+ "eval_steps": 500,
7
+ "global_step": 30,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 1.0,
14
+ "eval_accuracy": 0.9811320754716981,
15
+ "eval_loss": 0.24062196910381317,
16
+ "eval_runtime": 13.6835,
17
+ "eval_samples_per_second": 23.24,
18
+ "eval_steps_per_second": 0.731,
19
+ "step": 6
20
+ },
21
+ {
22
+ "epoch": 1.6666666666666665,
23
+ "grad_norm": 1.9544028043746948,
24
+ "learning_rate": 3.7037037037037037e-05,
25
+ "loss": 0.4213,
26
+ "step": 10
27
+ },
28
+ {
29
+ "epoch": 2.0,
30
+ "eval_accuracy": 0.9874213836477987,
31
+ "eval_loss": 0.044603366404771805,
32
+ "eval_runtime": 15.0982,
33
+ "eval_samples_per_second": 21.062,
34
+ "eval_steps_per_second": 0.662,
35
+ "step": 12
36
+ },
37
+ {
38
+ "epoch": 3.0,
39
+ "eval_accuracy": 0.9811320754716981,
40
+ "eval_loss": 0.04091091454029083,
41
+ "eval_runtime": 15.2601,
42
+ "eval_samples_per_second": 20.839,
43
+ "eval_steps_per_second": 0.655,
44
+ "step": 18
45
+ },
46
+ {
47
+ "epoch": 3.3333333333333335,
48
+ "grad_norm": 3.980639934539795,
49
+ "learning_rate": 1.8518518518518518e-05,
50
+ "loss": 0.021,
51
+ "step": 20
52
+ },
53
+ {
54
+ "epoch": 4.0,
55
+ "eval_accuracy": 0.9905660377358491,
56
+ "eval_loss": 0.01574210450053215,
57
+ "eval_runtime": 24.6406,
58
+ "eval_samples_per_second": 12.906,
59
+ "eval_steps_per_second": 0.406,
60
+ "step": 24
61
+ },
62
+ {
63
+ "epoch": 5.0,
64
+ "grad_norm": 0.16489173471927643,
65
+ "learning_rate": 0.0,
66
+ "loss": 0.0132,
67
+ "step": 30
68
+ },
69
+ {
70
+ "epoch": 5.0,
71
+ "eval_accuracy": 0.9811320754716981,
72
+ "eval_loss": 0.031806472688913345,
73
+ "eval_runtime": 15.5494,
74
+ "eval_samples_per_second": 20.451,
75
+ "eval_steps_per_second": 0.643,
76
+ "step": 30
77
+ }
78
+ ],
79
+ "logging_steps": 10,
80
+ "max_steps": 30,
81
+ "num_input_tokens_seen": 0,
82
+ "num_train_epochs": 5,
83
+ "save_steps": 500,
84
+ "stateful_callbacks": {
85
+ "TrainerControl": {
86
+ "args": {
87
+ "should_epoch_stop": false,
88
+ "should_evaluate": false,
89
+ "should_log": false,
90
+ "should_save": true,
91
+ "should_training_stop": true
92
+ },
93
+ "attributes": {}
94
+ }
95
+ },
96
+ "total_flos": 9.221571913752576e+16,
97
+ "train_batch_size": 32,
98
+ "trial_name": null,
99
+ "trial_params": null
100
+ }
checkpoint-30/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80a6480d20da699fccade53c3fd9b35b8e309a5b9e1bfeca6411e3b8969645d4
3
+ size 5368
checkpoint-6/config.json ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "SwinForImageClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.0,
6
+ "depths": [
7
+ 2,
8
+ 2,
9
+ 6,
10
+ 2
11
+ ],
12
+ "drop_path_rate": 0.1,
13
+ "embed_dim": 96,
14
+ "encoder_stride": 32,
15
+ "hidden_act": "gelu",
16
+ "hidden_dropout_prob": 0.0,
17
+ "hidden_size": 768,
18
+ "id2label": {
19
+ "0": "Blur",
20
+ "1": "Not Blur"
21
+ },
22
+ "image_size": 224,
23
+ "initializer_range": 0.02,
24
+ "label2id": {
25
+ "Blur": 0,
26
+ "Not Blur": 1
27
+ },
28
+ "layer_norm_eps": 1e-05,
29
+ "mlp_ratio": 4.0,
30
+ "model_type": "swin",
31
+ "num_channels": 3,
32
+ "num_heads": [
33
+ 3,
34
+ 6,
35
+ 12,
36
+ 24
37
+ ],
38
+ "num_layers": 4,
39
+ "out_features": [
40
+ "stage4"
41
+ ],
42
+ "out_indices": [
43
+ 4
44
+ ],
45
+ "patch_size": 4,
46
+ "path_norm": true,
47
+ "problem_type": "single_label_classification",
48
+ "qkv_bias": true,
49
+ "stage_names": [
50
+ "stem",
51
+ "stage1",
52
+ "stage2",
53
+ "stage3",
54
+ "stage4"
55
+ ],
56
+ "torch_dtype": "float32",
57
+ "transformers_version": "4.50.3",
58
+ "use_absolute_embeddings": false,
59
+ "window_size": 7
60
+ }
checkpoint-6/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48c5519f52bbf38cdab15370cc3a4dcf554b8baf0b6e68901113269ade2026e3
3
+ size 110342832
checkpoint-6/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3dc7154caaa88efd8c78a318fecd107848c6685cf4249478a415d2ad1c48edc7
3
+ size 220344378
checkpoint-6/preprocessor_config.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_convert_rgb": null,
3
+ "do_normalize": true,
4
+ "do_rescale": true,
5
+ "do_resize": true,
6
+ "image_mean": [
7
+ 0.485,
8
+ 0.456,
9
+ 0.406
10
+ ],
11
+ "image_processor_type": "ViTImageProcessor",
12
+ "image_std": [
13
+ 0.229,
14
+ 0.224,
15
+ 0.225
16
+ ],
17
+ "resample": 3,
18
+ "rescale_factor": 0.00392156862745098,
19
+ "size": {
20
+ "height": 224,
21
+ "width": 224
22
+ }
23
+ }
checkpoint-6/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5ba69db1281009caea6fa844ee42a1c39f1d2c7ac3bc135fa284cffbc0999cd
3
+ size 13990
checkpoint-6/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:279e841118dcb53786f0ba365c7d4ddfbc42f3e40c3deab71cdb7f11be91203d
3
+ size 1064
checkpoint-6/trainer_state.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 6,
3
+ "best_metric": 0.9811320754716981,
4
+ "best_model_checkpoint": "swin-tiny-patch4-window7-224-BlurClassification\\checkpoint-6",
5
+ "epoch": 1.0,
6
+ "eval_steps": 500,
7
+ "global_step": 6,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 1.0,
14
+ "eval_accuracy": 0.9811320754716981,
15
+ "eval_loss": 0.24062196910381317,
16
+ "eval_runtime": 13.6835,
17
+ "eval_samples_per_second": 23.24,
18
+ "eval_steps_per_second": 0.731,
19
+ "step": 6
20
+ }
21
+ ],
22
+ "logging_steps": 10,
23
+ "max_steps": 30,
24
+ "num_input_tokens_seen": 0,
25
+ "num_train_epochs": 5,
26
+ "save_steps": 500,
27
+ "stateful_callbacks": {
28
+ "TrainerControl": {
29
+ "args": {
30
+ "should_epoch_stop": false,
31
+ "should_evaluate": false,
32
+ "should_log": false,
33
+ "should_save": true,
34
+ "should_training_stop": false
35
+ },
36
+ "attributes": {}
37
+ }
38
+ },
39
+ "total_flos": 1.844314382750515e+16,
40
+ "train_batch_size": 32,
41
+ "trial_name": null,
42
+ "trial_params": null
43
+ }
checkpoint-6/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80a6480d20da699fccade53c3fd9b35b8e309a5b9e1bfeca6411e3b8969645d4
3
+ size 5368
config.json ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "SwinForImageClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.0,
6
+ "depths": [
7
+ 2,
8
+ 2,
9
+ 6,
10
+ 2
11
+ ],
12
+ "drop_path_rate": 0.1,
13
+ "embed_dim": 96,
14
+ "encoder_stride": 32,
15
+ "hidden_act": "gelu",
16
+ "hidden_dropout_prob": 0.0,
17
+ "hidden_size": 768,
18
+ "id2label": {
19
+ "0": "Blur",
20
+ "1": "Not Blur"
21
+ },
22
+ "image_size": 224,
23
+ "initializer_range": 0.02,
24
+ "label2id": {
25
+ "Blur": 0,
26
+ "Not Blur": 1
27
+ },
28
+ "layer_norm_eps": 1e-05,
29
+ "mlp_ratio": 4.0,
30
+ "model_type": "swin",
31
+ "num_channels": 3,
32
+ "num_heads": [
33
+ 3,
34
+ 6,
35
+ 12,
36
+ 24
37
+ ],
38
+ "num_layers": 4,
39
+ "out_features": [
40
+ "stage4"
41
+ ],
42
+ "out_indices": [
43
+ 4
44
+ ],
45
+ "patch_size": 4,
46
+ "path_norm": true,
47
+ "problem_type": "single_label_classification",
48
+ "qkv_bias": true,
49
+ "stage_names": [
50
+ "stem",
51
+ "stage1",
52
+ "stage2",
53
+ "stage3",
54
+ "stage4"
55
+ ],
56
+ "torch_dtype": "float32",
57
+ "transformers_version": "4.50.3",
58
+ "use_absolute_embeddings": false,
59
+ "window_size": 7
60
+ }
eval_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.0,
3
+ "eval_accuracy": 0.9905660377358491,
4
+ "eval_loss": 0.01574210450053215,
5
+ "eval_runtime": 16.0331,
6
+ "eval_samples_per_second": 19.834,
7
+ "eval_steps_per_second": 0.624
8
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:44fdf1f251b8696d2f545a8ed9c3b22fd0130bc9a47c5f25d463f8e51fd851a4
3
+ size 110342832
preprocessor_config.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_convert_rgb": null,
3
+ "do_normalize": true,
4
+ "do_rescale": true,
5
+ "do_resize": true,
6
+ "image_mean": [
7
+ 0.485,
8
+ 0.456,
9
+ 0.406
10
+ ],
11
+ "image_processor_type": "ViTImageProcessor",
12
+ "image_std": [
13
+ 0.229,
14
+ 0.224,
15
+ 0.225
16
+ ],
17
+ "resample": 3,
18
+ "rescale_factor": 0.00392156862745098,
19
+ "size": {
20
+ "height": 224,
21
+ "width": 224
22
+ }
23
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.0,
3
+ "total_flos": 9.221571913752576e+16,
4
+ "train_loss": 0.15185614277919132,
5
+ "train_runtime": 591.7097,
6
+ "train_samples_per_second": 6.27,
7
+ "train_steps_per_second": 0.051
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,118 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 24,
3
+ "best_metric": 0.9905660377358491,
4
+ "best_model_checkpoint": "swin-tiny-patch4-window7-224-BlurClassification\\checkpoint-24",
5
+ "epoch": 5.0,
6
+ "eval_steps": 500,
7
+ "global_step": 30,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 1.0,
14
+ "eval_accuracy": 0.9811320754716981,
15
+ "eval_loss": 0.24062196910381317,
16
+ "eval_runtime": 13.6835,
17
+ "eval_samples_per_second": 23.24,
18
+ "eval_steps_per_second": 0.731,
19
+ "step": 6
20
+ },
21
+ {
22
+ "epoch": 1.6666666666666665,
23
+ "grad_norm": 1.9544028043746948,
24
+ "learning_rate": 3.7037037037037037e-05,
25
+ "loss": 0.4213,
26
+ "step": 10
27
+ },
28
+ {
29
+ "epoch": 2.0,
30
+ "eval_accuracy": 0.9874213836477987,
31
+ "eval_loss": 0.044603366404771805,
32
+ "eval_runtime": 15.0982,
33
+ "eval_samples_per_second": 21.062,
34
+ "eval_steps_per_second": 0.662,
35
+ "step": 12
36
+ },
37
+ {
38
+ "epoch": 3.0,
39
+ "eval_accuracy": 0.9811320754716981,
40
+ "eval_loss": 0.04091091454029083,
41
+ "eval_runtime": 15.2601,
42
+ "eval_samples_per_second": 20.839,
43
+ "eval_steps_per_second": 0.655,
44
+ "step": 18
45
+ },
46
+ {
47
+ "epoch": 3.3333333333333335,
48
+ "grad_norm": 3.980639934539795,
49
+ "learning_rate": 1.8518518518518518e-05,
50
+ "loss": 0.021,
51
+ "step": 20
52
+ },
53
+ {
54
+ "epoch": 4.0,
55
+ "eval_accuracy": 0.9905660377358491,
56
+ "eval_loss": 0.01574210450053215,
57
+ "eval_runtime": 24.6406,
58
+ "eval_samples_per_second": 12.906,
59
+ "eval_steps_per_second": 0.406,
60
+ "step": 24
61
+ },
62
+ {
63
+ "epoch": 5.0,
64
+ "grad_norm": 0.16489173471927643,
65
+ "learning_rate": 0.0,
66
+ "loss": 0.0132,
67
+ "step": 30
68
+ },
69
+ {
70
+ "epoch": 5.0,
71
+ "eval_accuracy": 0.9811320754716981,
72
+ "eval_loss": 0.031806472688913345,
73
+ "eval_runtime": 15.5494,
74
+ "eval_samples_per_second": 20.451,
75
+ "eval_steps_per_second": 0.643,
76
+ "step": 30
77
+ },
78
+ {
79
+ "epoch": 5.0,
80
+ "step": 30,
81
+ "total_flos": 9.221571913752576e+16,
82
+ "train_loss": 0.15185614277919132,
83
+ "train_runtime": 591.7097,
84
+ "train_samples_per_second": 6.27,
85
+ "train_steps_per_second": 0.051
86
+ },
87
+ {
88
+ "epoch": 5.0,
89
+ "eval_accuracy": 0.9905660377358491,
90
+ "eval_loss": 0.01574210450053215,
91
+ "eval_runtime": 16.0331,
92
+ "eval_samples_per_second": 19.834,
93
+ "eval_steps_per_second": 0.624,
94
+ "step": 30
95
+ }
96
+ ],
97
+ "logging_steps": 10,
98
+ "max_steps": 30,
99
+ "num_input_tokens_seen": 0,
100
+ "num_train_epochs": 5,
101
+ "save_steps": 500,
102
+ "stateful_callbacks": {
103
+ "TrainerControl": {
104
+ "args": {
105
+ "should_epoch_stop": false,
106
+ "should_evaluate": false,
107
+ "should_log": false,
108
+ "should_save": true,
109
+ "should_training_stop": true
110
+ },
111
+ "attributes": {}
112
+ }
113
+ },
114
+ "total_flos": 9.221571913752576e+16,
115
+ "train_batch_size": 32,
116
+ "trial_name": null,
117
+ "trial_params": null
118
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80a6480d20da699fccade53c3fd9b35b8e309a5b9e1bfeca6411e3b8969645d4
3
+ size 5368