Hugging Face's logo

jjmcarrascosa
/
vit_receipts_classifier

Image Classification
Transformers
PyTorch
TensorBoard
Safetensors
vit
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
2
jjmcarrascosa commited on
Commit
6a3f653
•
1 Parent(s): 24fd50d

add model

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. README.md +63 -0
  2. all_results.json +13 -0
  3. checkpoint-100/config.json +32 -0
  4. checkpoint-100/optimizer.pt +3 -0
  5. checkpoint-100/preprocessor_config.json +17 -0
  6. checkpoint-100/pytorch_model.bin +3 -0
  7. checkpoint-100/rng_state.pth +3 -0
  8. checkpoint-100/scaler.pt +3 -0
  9. checkpoint-100/scheduler.pt +3 -0
  10. checkpoint-100/trainer_state.json +85 -0
  11. checkpoint-100/training_args.bin +3 -0
  12. checkpoint-1000/config.json +32 -0
  13. checkpoint-1000/optimizer.pt +3 -0
  14. checkpoint-1000/preprocessor_config.json +17 -0
  15. checkpoint-1000/pytorch_model.bin +3 -0
  16. checkpoint-1000/rng_state.pth +3 -0
  17. checkpoint-1000/scaler.pt +3 -0
  18. checkpoint-1000/scheduler.pt +3 -0
  19. checkpoint-1000/trainer_state.json +634 -0
  20. checkpoint-1000/training_args.bin +3 -0
  21. config.json +32 -0
  22. eval_results.json +8 -0
  23. preprocessor_config.json +17 -0
  24. pytorch_model.bin +3 -0
  25. runs/Aug26_11-54-12_ip-172-31-14-234/1661514854.9900718/events.out.tfevents.1661514854.ip-172-31-14-234.6104.1 +3 -0
  26. runs/Aug26_11-54-12_ip-172-31-14-234/events.out.tfevents.1661514854.ip-172-31-14-234.6104.0 +3 -0
  27. runs/Aug26_12-04-24_ip-172-31-14-234/1661515473.6557944/events.out.tfevents.1661515473.ip-172-31-14-234.6104.3 +3 -0
  28. runs/Aug26_12-04-24_ip-172-31-14-234/events.out.tfevents.1661515473.ip-172-31-14-234.6104.2 +3 -0
  29. runs/Aug26_12-05-14_ip-172-31-14-234/1661515514.976626/events.out.tfevents.1661515514.ip-172-31-14-234.6104.5 +3 -0
  30. runs/Aug26_12-05-14_ip-172-31-14-234/events.out.tfevents.1661515514.ip-172-31-14-234.6104.4 +3 -0
  31. runs/Aug26_12-05-49_ip-172-31-14-234/1661515550.0803146/events.out.tfevents.1661515550.ip-172-31-14-234.6104.7 +3 -0
  32. runs/Aug26_12-05-49_ip-172-31-14-234/events.out.tfevents.1661515550.ip-172-31-14-234.6104.6 +3 -0
  33. runs/Aug26_12-06-57_ip-172-31-14-234/1661515618.0554335/events.out.tfevents.1661515618.ip-172-31-14-234.6104.9 +3 -0
  34. runs/Aug26_12-06-57_ip-172-31-14-234/events.out.tfevents.1661515618.ip-172-31-14-234.6104.8 +3 -0
  35. runs/Aug26_12-10-06_ip-172-31-14-234/1661515810.9488475/events.out.tfevents.1661515810.ip-172-31-14-234.6104.11 +3 -0
  36. runs/Aug26_12-10-06_ip-172-31-14-234/events.out.tfevents.1661515810.ip-172-31-14-234.6104.10 +3 -0
  37. runs/Aug26_12-57-08_ip-172-31-14-234/1661518636.647917/events.out.tfevents.1661518636.ip-172-31-14-234.6104.13 +3 -0
  38. runs/Aug26_12-57-08_ip-172-31-14-234/events.out.tfevents.1661518636.ip-172-31-14-234.6104.12 +3 -0
  39. runs/Aug26_12-58-28_ip-172-31-14-234/1661518713.4536793/events.out.tfevents.1661518713.ip-172-31-14-234.6104.15 +3 -0
  40. runs/Aug26_12-58-28_ip-172-31-14-234/events.out.tfevents.1661518713.ip-172-31-14-234.6104.14 +3 -0
  41. runs/Aug26_13-38-52_ip-172-31-14-234/1661521155.816326/events.out.tfevents.1661521155.ip-172-31-14-234.6104.17 +3 -0
  42. runs/Aug26_13-38-52_ip-172-31-14-234/1661521180.6339931/events.out.tfevents.1661521180.ip-172-31-14-234.6104.19 +3 -0
  43. runs/Aug26_13-38-52_ip-172-31-14-234/1661521190.0660818/events.out.tfevents.1661521190.ip-172-31-14-234.6104.21 +3 -0
  44. runs/Aug26_13-38-52_ip-172-31-14-234/events.out.tfevents.1661521155.ip-172-31-14-234.6104.16 +3 -0
  45. runs/Aug26_13-38-52_ip-172-31-14-234/events.out.tfevents.1661521180.ip-172-31-14-234.6104.18 +3 -0
  46. runs/Aug26_13-38-52_ip-172-31-14-234/events.out.tfevents.1661521190.ip-172-31-14-234.6104.20 +3 -0
  47. runs/Aug26_18-17-48_ip-172-31-14-234/1661537984.691932/events.out.tfevents.1661537984.ip-172-31-14-234.3094.1 +3 -0
  48. runs/Aug26_18-17-48_ip-172-31-14-234/events.out.tfevents.1661537984.ip-172-31-14-234.3094.0 +3 -0
  49. runs/Aug26_18-17-48_ip-172-31-14-234/events.out.tfevents.1661538929.ip-172-31-14-234.3094.2 +3 -0
  50. train_results.json +8 -0
README.md ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - image-classification
5
+ - generated_from_trainer
6
+ metrics:
7
+ - f1
8
+ model-index:
9
+ - name: vit_tickers_binaryclf
10
+ results: []
11
+ ---
12
+
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
+
16
+ # vit_tickers_binaryclf
17
+
18
+ This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the cord dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 0.0116
21
+ - F1: 0.9991
22
+
23
+ ## Model description
24
+
25
+ More information needed
26
+
27
+ ## Intended uses & limitations
28
+
29
+ More information needed
30
+
31
+ ## Training and evaluation data
32
+
33
+ More information needed
34
+
35
+ ## Training procedure
36
+
37
+ ### Training hyperparameters
38
+
39
+ The following hyperparameters were used during training:
40
+ - learning_rate: 0.0002
41
+ - train_batch_size: 16
42
+ - eval_batch_size: 8
43
+ - seed: 42
44
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
+ - lr_scheduler_type: linear
46
+ - num_epochs: 1
47
+ - mixed_precision_training: Native AMP
48
+
49
+ ### Training results
50
+
51
+ | Training Loss | Epoch | Step | Validation Loss | F1 |
52
+ |:-------------:|:-----:|:----:|:---------------:|:------:|
53
+ | 0.0026 | 0.28 | 500 | 0.0187 | 0.9982 |
54
+ | 0.0186 | 0.56 | 1000 | 0.0116 | 0.9991 |
55
+ | 0.0006 | 0.84 | 1500 | 0.0044 | 0.9997 |
56
+
57
+
58
+ ### Framework versions
59
+
60
+ - Transformers 4.21.2
61
+ - Pytorch 1.11.0+cu102
62
+ - Datasets 2.4.0
63
+ - Tokenizers 0.12.1
all_results.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "eval_f1": 0.9990915697674418,
4
+ "eval_loss": 0.011647290550172329,
5
+ "eval_runtime": 80.9842,
6
+ "eval_samples_per_second": 69.767,
7
+ "eval_steps_per_second": 8.73,
8
+ "total_flos": 2.2123963034966016e+18,
9
+ "train_loss": 0.019373888820827176,
10
+ "train_runtime": 828.3192,
11
+ "train_samples_per_second": 34.467,
12
+ "train_steps_per_second": 2.155
13
+ }
checkpoint-100/config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/vit-base-patch16-224-in21k",
3
+ "architectures": [
4
+ "ViTForImageClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.0,
7
+ "encoder_stride": 16,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.0,
10
+ "hidden_size": 768,
11
+ "id2label": {
12
+ "0": "ticket",
13
+ "1": "no_ticket"
14
+ },
15
+ "image_size": 224,
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 3072,
18
+ "label2id": {
19
+ "no_ticket": "1",
20
+ "ticket": "0"
21
+ },
22
+ "layer_norm_eps": 1e-12,
23
+ "model_type": "vit",
24
+ "num_attention_heads": 12,
25
+ "num_channels": 3,
26
+ "num_hidden_layers": 12,
27
+ "patch_size": 16,
28
+ "problem_type": "single_label_classification",
29
+ "qkv_bias": true,
30
+ "torch_dtype": "float32",
31
+ "transformers_version": "4.21.2"
32
+ }
checkpoint-100/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c76cf6e845cf62ea3b69bcc85a6631c4ab6e67b85652023f77fe940cbe9ac0e
3
+ size 686517409
checkpoint-100/preprocessor_config.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_normalize": true,
3
+ "do_resize": true,
4
+ "feature_extractor_type": "ViTFeatureExtractor",
5
+ "image_mean": [
6
+ 0.5,
7
+ 0.5,
8
+ 0.5
9
+ ],
10
+ "image_std": [
11
+ 0.5,
12
+ 0.5,
13
+ 0.5
14
+ ],
15
+ "resample": 2,
16
+ "size": 224
17
+ }
checkpoint-100/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff3feb3849f07b0f62eea21518f7985cbd2a65dcd5ee1b4aff35827a7a31c39b
3
+ size 343266993
checkpoint-100/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03a3c1141f8bebf59967bea65fa021fcc2ad8a3d7753ae183d1d946d3f5b6d8e
3
+ size 14503
checkpoint-100/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13a3423b2fe42f204bc8fe2c666ff379f9fd753a0f13613064a5e71e86b519e8
3
+ size 559
checkpoint-100/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb9ecea86613426a26d3837df874fe43f895aa56aa146253b038f43762755e7d
3
+ size 623
checkpoint-100/trainer_state.json ADDED
@@ -0,0 +1,85 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.0053038992919027805,
3
+ "best_model_checkpoint": "./vit_tickers_binaryclf/checkpoint-100",
4
+ "epoch": 0.04149377593360996,
5
+ "global_step": 100,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.0,
12
+ "learning_rate": 0.0001991701244813278,
13
+ "loss": 0.2137,
14
+ "step": 10
15
+ },
16
+ {
17
+ "epoch": 0.01,
18
+ "learning_rate": 0.00019834024896265561,
19
+ "loss": 0.0368,
20
+ "step": 20
21
+ },
22
+ {
23
+ "epoch": 0.01,
24
+ "learning_rate": 0.00019751037344398342,
25
+ "loss": 0.0196,
26
+ "step": 30
27
+ },
28
+ {
29
+ "epoch": 0.02,
30
+ "learning_rate": 0.0001966804979253112,
31
+ "loss": 0.0094,
32
+ "step": 40
33
+ },
34
+ {
35
+ "epoch": 0.02,
36
+ "learning_rate": 0.000195850622406639,
37
+ "loss": 0.0087,
38
+ "step": 50
39
+ },
40
+ {
41
+ "epoch": 0.02,
42
+ "learning_rate": 0.0001950207468879668,
43
+ "loss": 0.0675,
44
+ "step": 60
45
+ },
46
+ {
47
+ "epoch": 0.03,
48
+ "learning_rate": 0.00019419087136929463,
49
+ "loss": 0.0069,
50
+ "step": 70
51
+ },
52
+ {
53
+ "epoch": 0.03,
54
+ "learning_rate": 0.00019336099585062243,
55
+ "loss": 0.0052,
56
+ "step": 80
57
+ },
58
+ {
59
+ "epoch": 0.04,
60
+ "learning_rate": 0.00019253112033195023,
61
+ "loss": 0.0046,
62
+ "step": 90
63
+ },
64
+ {
65
+ "epoch": 0.04,
66
+ "learning_rate": 0.00019170124481327803,
67
+ "loss": 0.0035,
68
+ "step": 100
69
+ },
70
+ {
71
+ "epoch": 0.04,
72
+ "eval_f1": 0.995004995004995,
73
+ "eval_loss": 0.0053038992919027805,
74
+ "eval_runtime": 89.5482,
75
+ "eval_samples_per_second": 63.095,
76
+ "eval_steps_per_second": 7.895,
77
+ "step": 100
78
+ }
79
+ ],
80
+ "max_steps": 2410,
81
+ "num_train_epochs": 1,
82
+ "total_flos": 1.239871833833472e+17,
83
+ "trial_name": null,
84
+ "trial_params": null
85
+ }
checkpoint-100/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7190d139ad5a0fa567af75ad6100937cb7eef257dd81a326f122f2bd55946c26
3
+ size 3375
checkpoint-1000/config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/vit-base-patch16-224-in21k",
3
+ "architectures": [
4
+ "ViTForImageClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.0,
7
+ "encoder_stride": 16,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.0,
10
+ "hidden_size": 768,
11
+ "id2label": {
12
+ "0": "ticket",
13
+ "1": "no_ticket"
14
+ },
15
+ "image_size": 224,
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 3072,
18
+ "label2id": {
19
+ "no_ticket": "1",
20
+ "ticket": "0"
21
+ },
22
+ "layer_norm_eps": 1e-12,
23
+ "model_type": "vit",
24
+ "num_attention_heads": 12,
25
+ "num_channels": 3,
26
+ "num_hidden_layers": 12,
27
+ "patch_size": 16,
28
+ "problem_type": "single_label_classification",
29
+ "qkv_bias": true,
30
+ "torch_dtype": "float32",
31
+ "transformers_version": "4.21.2"
32
+ }
checkpoint-1000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5a49ffacdd54365cba271a5383ed69c2e3021cd28a495fb72a08c54d8ec32fd
3
+ size 686517601
checkpoint-1000/preprocessor_config.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_normalize": true,
3
+ "do_resize": true,
4
+ "feature_extractor_type": "ViTFeatureExtractor",
5
+ "image_mean": [
6
+ 0.5,
7
+ 0.5,
8
+ 0.5
9
+ ],
10
+ "image_std": [
11
+ 0.5,
12
+ 0.5,
13
+ 0.5
14
+ ],
15
+ "resample": 2,
16
+ "size": 224
17
+ }
checkpoint-1000/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26d3e6dbcc4e0e19350f8de8fef0ef9aef02adb2dfecc0b3eb7fc3d771081dc8
3
+ size 343266993
checkpoint-1000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:674676e662eeb93778c2b153ffad13aa90b43355da1956ce0b1e01e72f48c8d7
3
+ size 14503
checkpoint-1000/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff7056f60b4eb1e0d398e5fda312325666aecd7325db20104117b258596bb2ef
3
+ size 559
checkpoint-1000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:778b564fd4c63d424951c7614dbfb0014272fa2a4d882590bb6ee6842810da15
3
+ size 623
checkpoint-1000/trainer_state.json ADDED
@@ -0,0 +1,634 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.011647290550172329,
3
+ "best_model_checkpoint": "./vit_tickers_binaryclf/checkpoint-1000",
4
+ "epoch": 0.5602240896358543,
5
+ "global_step": 1000,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.01,
12
+ "learning_rate": 0.0001988795518207283,
13
+ "loss": 0.1948,
14
+ "step": 10
15
+ },
16
+ {
17
+ "epoch": 0.01,
18
+ "learning_rate": 0.0001977591036414566,
19
+ "loss": 0.0625,
20
+ "step": 20
21
+ },
22
+ {
23
+ "epoch": 0.02,
24
+ "learning_rate": 0.00019663865546218486,
25
+ "loss": 0.018,
26
+ "step": 30
27
+ },
28
+ {
29
+ "epoch": 0.02,
30
+ "learning_rate": 0.00019551820728291316,
31
+ "loss": 0.0079,
32
+ "step": 40
33
+ },
34
+ {
35
+ "epoch": 0.03,
36
+ "learning_rate": 0.00019439775910364145,
37
+ "loss": 0.0311,
38
+ "step": 50
39
+ },
40
+ {
41
+ "epoch": 0.03,
42
+ "learning_rate": 0.00019327731092436975,
43
+ "loss": 0.0072,
44
+ "step": 60
45
+ },
46
+ {
47
+ "epoch": 0.04,
48
+ "learning_rate": 0.00019215686274509807,
49
+ "loss": 0.0053,
50
+ "step": 70
51
+ },
52
+ {
53
+ "epoch": 0.04,
54
+ "learning_rate": 0.00019103641456582636,
55
+ "loss": 0.0037,
56
+ "step": 80
57
+ },
58
+ {
59
+ "epoch": 0.05,
60
+ "learning_rate": 0.00018991596638655463,
61
+ "loss": 0.0038,
62
+ "step": 90
63
+ },
64
+ {
65
+ "epoch": 0.06,
66
+ "learning_rate": 0.00018879551820728292,
67
+ "loss": 0.004,
68
+ "step": 100
69
+ },
70
+ {
71
+ "epoch": 0.06,
72
+ "learning_rate": 0.00018767507002801122,
73
+ "loss": 0.244,
74
+ "step": 110
75
+ },
76
+ {
77
+ "epoch": 0.07,
78
+ "learning_rate": 0.0001865546218487395,
79
+ "loss": 0.1787,
80
+ "step": 120
81
+ },
82
+ {
83
+ "epoch": 0.07,
84
+ "learning_rate": 0.0001854341736694678,
85
+ "loss": 0.084,
86
+ "step": 130
87
+ },
88
+ {
89
+ "epoch": 0.08,
90
+ "learning_rate": 0.00018431372549019607,
91
+ "loss": 0.0118,
92
+ "step": 140
93
+ },
94
+ {
95
+ "epoch": 0.08,
96
+ "learning_rate": 0.00018319327731092437,
97
+ "loss": 0.0053,
98
+ "step": 150
99
+ },
100
+ {
101
+ "epoch": 0.09,
102
+ "learning_rate": 0.00018207282913165266,
103
+ "loss": 0.1699,
104
+ "step": 160
105
+ },
106
+ {
107
+ "epoch": 0.1,
108
+ "learning_rate": 0.00018095238095238095,
109
+ "loss": 0.1418,
110
+ "step": 170
111
+ },
112
+ {
113
+ "epoch": 0.1,
114
+ "learning_rate": 0.00017983193277310925,
115
+ "loss": 0.0859,
116
+ "step": 180
117
+ },
118
+ {
119
+ "epoch": 0.11,
120
+ "learning_rate": 0.00017871148459383754,
121
+ "loss": 0.0463,
122
+ "step": 190
123
+ },
124
+ {
125
+ "epoch": 0.11,
126
+ "learning_rate": 0.00017759103641456584,
127
+ "loss": 0.0699,
128
+ "step": 200
129
+ },
130
+ {
131
+ "epoch": 0.12,
132
+ "learning_rate": 0.00017647058823529413,
133
+ "loss": 0.0116,
134
+ "step": 210
135
+ },
136
+ {
137
+ "epoch": 0.12,
138
+ "learning_rate": 0.00017535014005602242,
139
+ "loss": 0.0046,
140
+ "step": 220
141
+ },
142
+ {
143
+ "epoch": 0.13,
144
+ "learning_rate": 0.00017422969187675072,
145
+ "loss": 0.076,
146
+ "step": 230
147
+ },
148
+ {
149
+ "epoch": 0.13,
150
+ "learning_rate": 0.000173109243697479,
151
+ "loss": 0.0159,
152
+ "step": 240
153
+ },
154
+ {
155
+ "epoch": 0.14,
156
+ "learning_rate": 0.0001719887955182073,
157
+ "loss": 0.0372,
158
+ "step": 250
159
+ },
160
+ {
161
+ "epoch": 0.15,
162
+ "learning_rate": 0.00017086834733893557,
163
+ "loss": 0.0603,
164
+ "step": 260
165
+ },
166
+ {
167
+ "epoch": 0.15,
168
+ "learning_rate": 0.00016974789915966387,
169
+ "loss": 0.0581,
170
+ "step": 270
171
+ },
172
+ {
173
+ "epoch": 0.16,
174
+ "learning_rate": 0.00016862745098039216,
175
+ "loss": 0.0122,
176
+ "step": 280
177
+ },
178
+ {
179
+ "epoch": 0.16,
180
+ "learning_rate": 0.00016750700280112045,
181
+ "loss": 0.0411,
182
+ "step": 290
183
+ },
184
+ {
185
+ "epoch": 0.17,
186
+ "learning_rate": 0.00016638655462184875,
187
+ "loss": 0.0232,
188
+ "step": 300
189
+ },
190
+ {
191
+ "epoch": 0.17,
192
+ "learning_rate": 0.00016526610644257704,
193
+ "loss": 0.0189,
194
+ "step": 310
195
+ },
196
+ {
197
+ "epoch": 0.18,
198
+ "learning_rate": 0.00016414565826330534,
199
+ "loss": 0.0293,
200
+ "step": 320
201
+ },
202
+ {
203
+ "epoch": 0.18,
204
+ "learning_rate": 0.00016302521008403363,
205
+ "loss": 0.041,
206
+ "step": 330
207
+ },
208
+ {
209
+ "epoch": 0.19,
210
+ "learning_rate": 0.00016190476190476192,
211
+ "loss": 0.1021,
212
+ "step": 340
213
+ },
214
+ {
215
+ "epoch": 0.2,
216
+ "learning_rate": 0.00016078431372549022,
217
+ "loss": 0.0216,
218
+ "step": 350
219
+ },
220
+ {
221
+ "epoch": 0.2,
222
+ "learning_rate": 0.0001596638655462185,
223
+ "loss": 0.0747,
224
+ "step": 360
225
+ },
226
+ {
227
+ "epoch": 0.21,
228
+ "learning_rate": 0.00015854341736694678,
229
+ "loss": 0.0056,
230
+ "step": 370
231
+ },
232
+ {
233
+ "epoch": 0.21,
234
+ "learning_rate": 0.00015742296918767507,
235
+ "loss": 0.0043,
236
+ "step": 380
237
+ },
238
+ {
239
+ "epoch": 0.22,
240
+ "learning_rate": 0.00015630252100840337,
241
+ "loss": 0.0045,
242
+ "step": 390
243
+ },
244
+ {
245
+ "epoch": 0.22,
246
+ "learning_rate": 0.00015518207282913166,
247
+ "loss": 0.0449,
248
+ "step": 400
249
+ },
250
+ {
251
+ "epoch": 0.23,
252
+ "learning_rate": 0.00015417366946778713,
253
+ "loss": 0.0539,
254
+ "step": 410
255
+ },
256
+ {
257
+ "epoch": 0.24,
258
+ "learning_rate": 0.0001530532212885154,
259
+ "loss": 0.0032,
260
+ "step": 420
261
+ },
262
+ {
263
+ "epoch": 0.24,
264
+ "learning_rate": 0.0001519327731092437,
265
+ "loss": 0.0402,
266
+ "step": 430
267
+ },
268
+ {
269
+ "epoch": 0.25,
270
+ "learning_rate": 0.00015081232492997199,
271
+ "loss": 0.0336,
272
+ "step": 440
273
+ },
274
+ {
275
+ "epoch": 0.25,
276
+ "learning_rate": 0.00014969187675070028,
277
+ "loss": 0.0038,
278
+ "step": 450
279
+ },
280
+ {
281
+ "epoch": 0.26,
282
+ "learning_rate": 0.00014857142857142857,
283
+ "loss": 0.0415,
284
+ "step": 460
285
+ },
286
+ {
287
+ "epoch": 0.26,
288
+ "learning_rate": 0.00014745098039215687,
289
+ "loss": 0.0037,
290
+ "step": 470
291
+ },
292
+ {
293
+ "epoch": 0.27,
294
+ "learning_rate": 0.00014633053221288516,
295
+ "loss": 0.0028,
296
+ "step": 480
297
+ },
298
+ {
299
+ "epoch": 0.27,
300
+ "learning_rate": 0.00014521008403361346,
301
+ "loss": 0.04,
302
+ "step": 490
303
+ },
304
+ {
305
+ "epoch": 0.28,
306
+ "learning_rate": 0.00014408963585434175,
307
+ "loss": 0.0026,
308
+ "step": 500
309
+ },
310
+ {
311
+ "epoch": 0.28,
312
+ "eval_f1": 0.9981801637852593,
313
+ "eval_loss": 0.018740175291895866,
314
+ "eval_runtime": 83.1765,
315
+ "eval_samples_per_second": 67.928,
316
+ "eval_steps_per_second": 8.5,
317
+ "step": 500
318
+ },
319
+ {
320
+ "epoch": 0.29,
321
+ "learning_rate": 0.00014296918767507004,
322
+ "loss": 0.0028,
323
+ "step": 510
324
+ },
325
+ {
326
+ "epoch": 0.29,
327
+ "learning_rate": 0.00014184873949579834,
328
+ "loss": 0.0024,
329
+ "step": 520
330
+ },
331
+ {
332
+ "epoch": 0.3,
333
+ "learning_rate": 0.00014072829131652663,
334
+ "loss": 0.0023,
335
+ "step": 530
336
+ },
337
+ {
338
+ "epoch": 0.3,
339
+ "learning_rate": 0.0001396078431372549,
340
+ "loss": 0.0021,
341
+ "step": 540
342
+ },
343
+ {
344
+ "epoch": 0.31,
345
+ "learning_rate": 0.0001384873949579832,
346
+ "loss": 0.0021,
347
+ "step": 550
348
+ },
349
+ {
350
+ "epoch": 0.31,
351
+ "learning_rate": 0.0001373669467787115,
352
+ "loss": 0.2876,
353
+ "step": 560
354
+ },
355
+ {
356
+ "epoch": 0.32,
357
+ "learning_rate": 0.00013624649859943978,
358
+ "loss": 0.0036,
359
+ "step": 570
360
+ },
361
+ {
362
+ "epoch": 0.32,
363
+ "learning_rate": 0.00013512605042016807,
364
+ "loss": 0.0026,
365
+ "step": 580
366
+ },
367
+ {
368
+ "epoch": 0.33,
369
+ "learning_rate": 0.00013400560224089634,
370
+ "loss": 0.0432,
371
+ "step": 590
372
+ },
373
+ {
374
+ "epoch": 0.34,
375
+ "learning_rate": 0.00013288515406162466,
376
+ "loss": 0.033,
377
+ "step": 600
378
+ },
379
+ {
380
+ "epoch": 0.34,
381
+ "learning_rate": 0.00013176470588235296,
382
+ "loss": 0.0048,
383
+ "step": 610
384
+ },
385
+ {
386
+ "epoch": 0.35,
387
+ "learning_rate": 0.00013064425770308125,
388
+ "loss": 0.0027,
389
+ "step": 620
390
+ },
391
+ {
392
+ "epoch": 0.35,
393
+ "learning_rate": 0.00012952380952380954,
394
+ "loss": 0.0021,
395
+ "step": 630
396
+ },
397
+ {
398
+ "epoch": 0.36,
399
+ "learning_rate": 0.00012840336134453784,
400
+ "loss": 0.0019,
401
+ "step": 640
402
+ },
403
+ {
404
+ "epoch": 0.36,
405
+ "learning_rate": 0.0001272829131652661,
406
+ "loss": 0.0018,
407
+ "step": 650
408
+ },
409
+ {
410
+ "epoch": 0.37,
411
+ "learning_rate": 0.0001261624649859944,
412
+ "loss": 0.0408,
413
+ "step": 660
414
+ },
415
+ {
416
+ "epoch": 0.38,
417
+ "learning_rate": 0.0001250420168067227,
418
+ "loss": 0.0105,
419
+ "step": 670
420
+ },
421
+ {
422
+ "epoch": 0.38,
423
+ "learning_rate": 0.000123921568627451,
424
+ "loss": 0.0023,
425
+ "step": 680
426
+ },
427
+ {
428
+ "epoch": 0.39,
429
+ "learning_rate": 0.00012280112044817928,
430
+ "loss": 0.0018,
431
+ "step": 690
432
+ },
433
+ {
434
+ "epoch": 0.39,
435
+ "learning_rate": 0.00012168067226890756,
436
+ "loss": 0.0247,
437
+ "step": 700
438
+ },
439
+ {
440
+ "epoch": 0.4,
441
+ "learning_rate": 0.00012056022408963586,
442
+ "loss": 0.0328,
443
+ "step": 710
444
+ },
445
+ {
446
+ "epoch": 0.4,
447
+ "learning_rate": 0.00011943977591036415,
448
+ "loss": 0.0081,
449
+ "step": 720
450
+ },
451
+ {
452
+ "epoch": 0.41,
453
+ "learning_rate": 0.00011831932773109244,
454
+ "loss": 0.0024,
455
+ "step": 730
456
+ },
457
+ {
458
+ "epoch": 0.41,
459
+ "learning_rate": 0.00011719887955182074,
460
+ "loss": 0.0018,
461
+ "step": 740
462
+ },
463
+ {
464
+ "epoch": 0.42,
465
+ "learning_rate": 0.00011607843137254903,
466
+ "loss": 0.0073,
467
+ "step": 750
468
+ },
469
+ {
470
+ "epoch": 0.43,
471
+ "learning_rate": 0.00011495798319327731,
472
+ "loss": 0.0015,
473
+ "step": 760
474
+ },
475
+ {
476
+ "epoch": 0.43,
477
+ "learning_rate": 0.0001138375350140056,
478
+ "loss": 0.0302,
479
+ "step": 770
480
+ },
481
+ {
482
+ "epoch": 0.44,
483
+ "learning_rate": 0.0001127170868347339,
484
+ "loss": 0.046,
485
+ "step": 780
486
+ },
487
+ {
488
+ "epoch": 0.44,
489
+ "learning_rate": 0.0001115966386554622,
490
+ "loss": 0.0306,
491
+ "step": 790
492
+ },
493
+ {
494
+ "epoch": 0.45,
495
+ "learning_rate": 0.00011047619047619049,
496
+ "loss": 0.0014,
497
+ "step": 800
498
+ },
499
+ {
500
+ "epoch": 0.45,
501
+ "learning_rate": 0.00010935574229691876,
502
+ "loss": 0.0149,
503
+ "step": 810
504
+ },
505
+ {
506
+ "epoch": 0.46,
507
+ "learning_rate": 0.00010823529411764706,
508
+ "loss": 0.0092,
509
+ "step": 820
510
+ },
511
+ {
512
+ "epoch": 0.46,
513
+ "learning_rate": 0.00010711484593837536,
514
+ "loss": 0.0069,
515
+ "step": 830
516
+ },
517
+ {
518
+ "epoch": 0.47,
519
+ "learning_rate": 0.00010599439775910365,
520
+ "loss": 0.0013,
521
+ "step": 840
522
+ },
523
+ {
524
+ "epoch": 0.48,
525
+ "learning_rate": 0.00010487394957983194,
526
+ "loss": 0.0017,
527
+ "step": 850
528
+ },
529
+ {
530
+ "epoch": 0.48,
531
+ "learning_rate": 0.00010375350140056024,
532
+ "loss": 0.0013,
533
+ "step": 860
534
+ },
535
+ {
536
+ "epoch": 0.49,
537
+ "learning_rate": 0.0001026330532212885,
538
+ "loss": 0.0175,
539
+ "step": 870
540
+ },
541
+ {
542
+ "epoch": 0.49,
543
+ "learning_rate": 0.0001015126050420168,
544
+ "loss": 0.0029,
545
+ "step": 880
546
+ },
547
+ {
548
+ "epoch": 0.5,
549
+ "learning_rate": 0.00010039215686274511,
550
+ "loss": 0.0023,
551
+ "step": 890
552
+ },
553
+ {
554
+ "epoch": 0.5,
555
+ "learning_rate": 9.92717086834734e-05,
556
+ "loss": 0.0018,
557
+ "step": 900
558
+ },
559
+ {
560
+ "epoch": 0.51,
561
+ "learning_rate": 9.815126050420168e-05,
562
+ "loss": 0.001,
563
+ "step": 910
564
+ },
565
+ {
566
+ "epoch": 0.52,
567
+ "learning_rate": 9.703081232492998e-05,
568
+ "loss": 0.0911,
569
+ "step": 920
570
+ },
571
+ {
572
+ "epoch": 0.52,
573
+ "learning_rate": 9.591036414565827e-05,
574
+ "loss": 0.0011,
575
+ "step": 930
576
+ },
577
+ {
578
+ "epoch": 0.53,
579
+ "learning_rate": 9.478991596638655e-05,
580
+ "loss": 0.0013,
581
+ "step": 940
582
+ },
583
+ {
584
+ "epoch": 0.53,
585
+ "learning_rate": 9.366946778711484e-05,
586
+ "loss": 0.0283,
587
+ "step": 950
588
+ },
589
+ {
590
+ "epoch": 0.54,
591
+ "learning_rate": 9.254901960784315e-05,
592
+ "loss": 0.0011,
593
+ "step": 960
594
+ },
595
+ {
596
+ "epoch": 0.54,
597
+ "learning_rate": 9.142857142857143e-05,
598
+ "loss": 0.0028,
599
+ "step": 970
600
+ },
601
+ {
602
+ "epoch": 0.55,
603
+ "learning_rate": 9.030812324929973e-05,
604
+ "loss": 0.0011,
605
+ "step": 980
606
+ },
607
+ {
608
+ "epoch": 0.55,
609
+ "learning_rate": 8.918767507002802e-05,
610
+ "loss": 0.001,
611
+ "step": 990
612
+ },
613
+ {
614
+ "epoch": 0.56,
615
+ "learning_rate": 8.80672268907563e-05,
616
+ "loss": 0.0186,
617
+ "step": 1000
618
+ },
619
+ {
620
+ "epoch": 0.56,
621
+ "eval_f1": 0.9990915697674418,
622
+ "eval_loss": 0.011647290550172329,
623
+ "eval_runtime": 81.5953,
624
+ "eval_samples_per_second": 69.244,
625
+ "eval_steps_per_second": 8.665,
626
+ "step": 1000
627
+ }
628
+ ],
629
+ "max_steps": 1785,
630
+ "num_train_epochs": 1,
631
+ "total_flos": 1.239871833833472e+18,
632
+ "trial_name": null,
633
+ "trial_params": null
634
+ }
checkpoint-1000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39f257e82f28143d7ff7b116edd3fbbc7443cda81b679e766139180799cfb6e4
3
+ size 3375
config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/vit-base-patch16-224-in21k",
3
+ "architectures": [
4
+ "ViTForImageClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.0,
7
+ "encoder_stride": 16,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.0,
10
+ "hidden_size": 768,
11
+ "id2label": {
12
+ "0": "ticket",
13
+ "1": "no_ticket"
14
+ },
15
+ "image_size": 224,
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 3072,
18
+ "label2id": {
19
+ "no_ticket": "1",
20
+ "ticket": "0"
21
+ },
22
+ "layer_norm_eps": 1e-12,
23
+ "model_type": "vit",
24
+ "num_attention_heads": 12,
25
+ "num_channels": 3,
26
+ "num_hidden_layers": 12,
27
+ "patch_size": 16,
28
+ "problem_type": "single_label_classification",
29
+ "qkv_bias": true,
30
+ "torch_dtype": "float32",
31
+ "transformers_version": "4.21.2"
32
+ }
eval_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "eval_f1": 0.9990915697674418,
4
+ "eval_loss": 0.011647290550172329,
5
+ "eval_runtime": 80.9842,
6
+ "eval_samples_per_second": 69.767,
7
+ "eval_steps_per_second": 8.73
8
+ }
preprocessor_config.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_normalize": true,
3
+ "do_resize": true,
4
+ "feature_extractor_type": "ViTFeatureExtractor",
5
+ "image_mean": [
6
+ 0.5,
7
+ 0.5,
8
+ 0.5
9
+ ],
10
+ "image_std": [
11
+ 0.5,
12
+ 0.5,
13
+ 0.5
14
+ ],
15
+ "resample": 2,
16
+ "size": 224
17
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26d3e6dbcc4e0e19350f8de8fef0ef9aef02adb2dfecc0b3eb7fc3d771081dc8
3
+ size 343266993
runs/Aug26_11-54-12_ip-172-31-14-234/1661514854.9900718/events.out.tfevents.1661514854.ip-172-31-14-234.6104.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1728b5368ffb3904fbdd162a30ab36646150bc8ace64908d9f84d93f2a42cbd1
3
+ size 5441
runs/Aug26_11-54-12_ip-172-31-14-234/events.out.tfevents.1661514854.ip-172-31-14-234.6104.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59569ae7590517431a9938e62b50d1c3464e53a537caa0657c4724197841a9a8
3
+ size 3675
runs/Aug26_12-04-24_ip-172-31-14-234/1661515473.6557944/events.out.tfevents.1661515473.ip-172-31-14-234.6104.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f8fae6aee0ac50da08604463b94cf2b22e5bcb65672722051b2db6903fe09e1
3
+ size 5441
runs/Aug26_12-04-24_ip-172-31-14-234/events.out.tfevents.1661515473.ip-172-31-14-234.6104.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c325e2492c8a2c125cfff3c479d6334fda6397b7a32ebb5902e0ac3c0223fb6f
3
+ size 3675
runs/Aug26_12-05-14_ip-172-31-14-234/1661515514.976626/events.out.tfevents.1661515514.ip-172-31-14-234.6104.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5cc0c62b787cd5b53df2f0917b901e75e1cb823a3b1398af02478b39e4fb1e44
3
+ size 5441
runs/Aug26_12-05-14_ip-172-31-14-234/events.out.tfevents.1661515514.ip-172-31-14-234.6104.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:372c0780704f65f6bf80ad17d822c62344812a3ed2c1033872f85312925a24ff
3
+ size 4137
runs/Aug26_12-05-49_ip-172-31-14-234/1661515550.0803146/events.out.tfevents.1661515550.ip-172-31-14-234.6104.7 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2eec1acf456644439fea911a4e9591bd2bc38caf33339f257aaf0a7974a22a60
3
+ size 5441
runs/Aug26_12-05-49_ip-172-31-14-234/events.out.tfevents.1661515550.ip-172-31-14-234.6104.6 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e5e31c7842864c4bafceb25baa837d6477f253313a802bd041745aa9d4ac762
3
+ size 5215
runs/Aug26_12-06-57_ip-172-31-14-234/1661515618.0554335/events.out.tfevents.1661515618.ip-172-31-14-234.6104.9 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:892324738dafb781e702eb2d2ea3912bd2f17e787ce791a36bcbc630606c0f3d
3
+ size 5441
runs/Aug26_12-06-57_ip-172-31-14-234/events.out.tfevents.1661515618.ip-172-31-14-234.6104.8 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e53319c49a5680115e3a62abcb944a8b5ea8dba8f3daa47c417126bbed64ec85
3
+ size 7090
runs/Aug26_12-10-06_ip-172-31-14-234/1661515810.9488475/events.out.tfevents.1661515810.ip-172-31-14-234.6104.11 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11b8df9fda357b19cb52434f6c2ba63abc8b4a358f1443269c701588ec8ae566
3
+ size 5441
runs/Aug26_12-10-06_ip-172-31-14-234/events.out.tfevents.1661515810.ip-172-31-14-234.6104.10 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8736706ae8295da766d0d070b8ffb8046797cbba5c9adc72f8931c01d7a3bb3c
3
+ size 15039
runs/Aug26_12-57-08_ip-172-31-14-234/1661518636.647917/events.out.tfevents.1661518636.ip-172-31-14-234.6104.13 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65d84c90381aca7003725f65e4348cfd876bf07ee755b991c84fead75f08b888
3
+ size 5441
runs/Aug26_12-57-08_ip-172-31-14-234/events.out.tfevents.1661518636.ip-172-31-14-234.6104.12 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65fda0f7059fbe30181554d5ca7a28f73390132577832c373a8f5fe8ae69460e
3
+ size 3677
runs/Aug26_12-58-28_ip-172-31-14-234/1661518713.4536793/events.out.tfevents.1661518713.ip-172-31-14-234.6104.15 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dbe6ee750f1fec77187e38ce5546743725b72603fa3dc47c67fd8cb997e074e6
3
+ size 5441
runs/Aug26_12-58-28_ip-172-31-14-234/events.out.tfevents.1661518713.ip-172-31-14-234.6104.14 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9857b5281628397dc9426536f29885b87408390dd421c68ce27ea949b9e3a88a
3
+ size 14945
runs/Aug26_13-38-52_ip-172-31-14-234/1661521155.816326/events.out.tfevents.1661521155.ip-172-31-14-234.6104.17 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9cbcb87dc6a397b84b81ad6b147ac50b5763aa8559913f761b5a2262faeabde
3
+ size 5441
runs/Aug26_13-38-52_ip-172-31-14-234/1661521180.6339931/events.out.tfevents.1661521180.ip-172-31-14-234.6104.19 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00b06b97b3e124905930256cde265f34135908c419c266023acb35e58e87a6a5
3
+ size 5441
runs/Aug26_13-38-52_ip-172-31-14-234/1661521190.0660818/events.out.tfevents.1661521190.ip-172-31-14-234.6104.21 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c629fe74a29161dcab5da151e11a373d7750ed68440a9495ed70e7100eed6b2f
3
+ size 5441
runs/Aug26_13-38-52_ip-172-31-14-234/events.out.tfevents.1661521155.ip-172-31-14-234.6104.16 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22f558fbe9bb2e3200235122b0911ceef716415fdba4e1db47897cddc045a5a2
3
+ size 3676
runs/Aug26_13-38-52_ip-172-31-14-234/events.out.tfevents.1661521180.ip-172-31-14-234.6104.18 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38cbc1855af468384d98b64c8c54d5765a34fa31ab3c05a8a735051d0daa8954
3
+ size 3676
runs/Aug26_13-38-52_ip-172-31-14-234/events.out.tfevents.1661521190.ip-172-31-14-234.6104.20 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f348fd17d44512473bc50f302e62b848c62be25051c9e0b35d3d23dbfef85457
3
+ size 3676
runs/Aug26_18-17-48_ip-172-31-14-234/1661537984.691932/events.out.tfevents.1661537984.ip-172-31-14-234.3094.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9a21559c9c23a953c8069659de490f94f649020c4ae6ded80c5818623160f60
3
+ size 5441
runs/Aug26_18-17-48_ip-172-31-14-234/events.out.tfevents.1661537984.ip-172-31-14-234.3094.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0e0fe1928f26fbbed2cffb855719a27823d5362972c80de466436ea4bd9d7fc
3
+ size 32891
runs/Aug26_18-17-48_ip-172-31-14-234/events.out.tfevents.1661538929.ip-172-31-14-234.3094.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59c135b9b5d23e0dc13aa5db883ba7639e7843c797f60fb8ac838dd665fcd3f6
3
+ size 357
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "total_flos": 2.2123963034966016e+18,
4
+ "train_loss": 0.019373888820827176,
5
+ "train_runtime": 828.3192,
6
+ "train_samples_per_second": 34.467,
7
+ "train_steps_per_second": 2.155
8
+ }