Upload folder using huggingface_hub
Browse files- README.md +37 -0
- checkpoint-32/config.json +46 -0
- checkpoint-32/model.safetensors +3 -0
- checkpoint-32/optimizer.pt +3 -0
- checkpoint-32/preprocessor_config.json +23 -0
- checkpoint-32/rng_state.pth +3 -0
- checkpoint-32/scheduler.pt +3 -0
- checkpoint-32/trainer_state.json +53 -0
- checkpoint-32/training_args.bin +3 -0
- checkpoint-4688/config.json +46 -0
- checkpoint-4688/model.safetensors +3 -0
- checkpoint-4688/optimizer.pt +3 -0
- checkpoint-4688/preprocessor_config.json +23 -0
- checkpoint-4688/rng_state.pth +3 -0
- checkpoint-4688/scheduler.pt +3 -0
- checkpoint-4688/trainer_state.json +116 -0
- checkpoint-4688/training_args.bin +3 -0
- checkpoint-8752/config.json +46 -0
- checkpoint-8752/model.safetensors +3 -0
- checkpoint-8752/optimizer.pt +3 -0
- checkpoint-8752/preprocessor_config.json +23 -0
- checkpoint-8752/rng_state.pth +3 -0
- checkpoint-8752/scheduler.pt +3 -0
- checkpoint-8752/trainer_state.json +192 -0
- checkpoint-8752/training_args.bin +3 -0
- checkpoint-9376/config.json +46 -0
- checkpoint-9376/model.safetensors +3 -0
- checkpoint-9376/optimizer.pt +3 -0
- checkpoint-9376/preprocessor_config.json +23 -0
- checkpoint-9376/rng_state.pth +3 -0
- checkpoint-9376/scheduler.pt +3 -0
- checkpoint-9376/trainer_state.json +199 -0
- checkpoint-9376/training_args.bin +3 -0
- config.json +46 -0
- model.safetensors +3 -0
- preprocessor_config.json +23 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
metrics:
|
| 4 |
+
- accuracy
|
| 5 |
+
- f1
|
| 6 |
+
base_model:
|
| 7 |
+
- google/vit-base-patch16-224-in21k
|
| 8 |
+
pipeline_tag: image-classification
|
| 9 |
+
library_name: transformers
|
| 10 |
+
datasets:
|
| 11 |
+
- nateraw/fairface
|
| 12 |
+
---
|
| 13 |
+
Detects age group with about 59% accuracy based on an image.
|
| 14 |
+
|
| 15 |
+
See https://www.kaggle.com/code/dima806/age-group-image-classification-vit for details.
|
| 16 |
+
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
```
|
| 20 |
+
Classification report:
|
| 21 |
+
|
| 22 |
+
precision recall f1-score support
|
| 23 |
+
|
| 24 |
+
0-2 0.7803 0.7500 0.7649 180
|
| 25 |
+
3-9 0.7998 0.7998 0.7998 1249
|
| 26 |
+
10-19 0.5361 0.4236 0.4733 1086
|
| 27 |
+
20-29 0.6402 0.7221 0.6787 3026
|
| 28 |
+
30-39 0.4935 0.5083 0.5008 2099
|
| 29 |
+
40-49 0.4848 0.4386 0.4606 1238
|
| 30 |
+
50-59 0.5000 0.4814 0.4905 725
|
| 31 |
+
60-69 0.4497 0.4685 0.4589 286
|
| 32 |
+
more than 70 0.6897 0.1802 0.2857 111
|
| 33 |
+
|
| 34 |
+
accuracy 0.5892 10000
|
| 35 |
+
macro avg 0.5971 0.5303 0.5459 10000
|
| 36 |
+
weighted avg 0.5863 0.5892 0.5844 10000
|
| 37 |
+
```
|
checkpoint-32/config.json
ADDED
|
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": "0-2",
|
| 13 |
+
"1": "3-9",
|
| 14 |
+
"2": "10-19",
|
| 15 |
+
"3": "20-29",
|
| 16 |
+
"4": "30-39",
|
| 17 |
+
"5": "40-49",
|
| 18 |
+
"6": "50-59",
|
| 19 |
+
"7": "60-69",
|
| 20 |
+
"8": "more than 70"
|
| 21 |
+
},
|
| 22 |
+
"image_size": 224,
|
| 23 |
+
"initializer_range": 0.02,
|
| 24 |
+
"intermediate_size": 3072,
|
| 25 |
+
"label2id": {
|
| 26 |
+
"0-2": 0,
|
| 27 |
+
"10-19": 2,
|
| 28 |
+
"20-29": 3,
|
| 29 |
+
"3-9": 1,
|
| 30 |
+
"30-39": 4,
|
| 31 |
+
"40-49": 5,
|
| 32 |
+
"50-59": 6,
|
| 33 |
+
"60-69": 7,
|
| 34 |
+
"more than 70": 8
|
| 35 |
+
},
|
| 36 |
+
"layer_norm_eps": 1e-12,
|
| 37 |
+
"model_type": "vit",
|
| 38 |
+
"num_attention_heads": 12,
|
| 39 |
+
"num_channels": 3,
|
| 40 |
+
"num_hidden_layers": 12,
|
| 41 |
+
"patch_size": 16,
|
| 42 |
+
"problem_type": "single_label_classification",
|
| 43 |
+
"qkv_bias": true,
|
| 44 |
+
"torch_dtype": "float32",
|
| 45 |
+
"transformers_version": "4.47.0"
|
| 46 |
+
}
|
checkpoint-32/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8c2e34c076a38920a0faa6bd6d28ab3c256de02211af98588a84de50a3fcbf61
|
| 3 |
+
size 343245508
|
checkpoint-32/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ecf20baba72b0625f4b93c33924e6dbdc7864803fe84800ca6d7684d763d07c5
|
| 3 |
+
size 686611898
|
checkpoint-32/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 |
+
0.5,
|
| 8 |
+
0.5,
|
| 9 |
+
0.5
|
| 10 |
+
],
|
| 11 |
+
"image_processor_type": "ViTImageProcessor",
|
| 12 |
+
"image_std": [
|
| 13 |
+
0.5,
|
| 14 |
+
0.5,
|
| 15 |
+
0.5
|
| 16 |
+
],
|
| 17 |
+
"resample": 2,
|
| 18 |
+
"rescale_factor": 0.00392156862745098,
|
| 19 |
+
"size": {
|
| 20 |
+
"height": 224,
|
| 21 |
+
"width": 224
|
| 22 |
+
}
|
| 23 |
+
}
|
checkpoint-32/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6b3ee827a7a00012c0a116546df467feee35e70376d81a7a85b1a70eb90414d3
|
| 3 |
+
size 14244
|
checkpoint-32/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:56eec20d0c973eb7e7f22bff0d2cd051e8d4c98231e7961894dc75b33a3a36fe
|
| 3 |
+
size 1064
|
checkpoint-32/trainer_state.json
ADDED
|
@@ -0,0 +1,53 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 2.178948402404785,
|
| 3 |
+
"best_model_checkpoint": "fairface_age_image_detection/checkpoint-32",
|
| 4 |
+
"epoch": 2.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 32,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 1.0,
|
| 13 |
+
"eval_accuracy": 0.14,
|
| 14 |
+
"eval_loss": 2.1873559951782227,
|
| 15 |
+
"eval_model_preparation_time": 0.0047,
|
| 16 |
+
"eval_runtime": 8.2156,
|
| 17 |
+
"eval_samples_per_second": 12.172,
|
| 18 |
+
"eval_steps_per_second": 1.582,
|
| 19 |
+
"step": 16
|
| 20 |
+
},
|
| 21 |
+
{
|
| 22 |
+
"epoch": 2.0,
|
| 23 |
+
"eval_accuracy": 0.18,
|
| 24 |
+
"eval_loss": 2.178948402404785,
|
| 25 |
+
"eval_model_preparation_time": 0.0047,
|
| 26 |
+
"eval_runtime": 8.316,
|
| 27 |
+
"eval_samples_per_second": 12.025,
|
| 28 |
+
"eval_steps_per_second": 1.563,
|
| 29 |
+
"step": 32
|
| 30 |
+
}
|
| 31 |
+
],
|
| 32 |
+
"logging_steps": 500,
|
| 33 |
+
"max_steps": 32,
|
| 34 |
+
"num_input_tokens_seen": 0,
|
| 35 |
+
"num_train_epochs": 2,
|
| 36 |
+
"save_steps": 500,
|
| 37 |
+
"stateful_callbacks": {
|
| 38 |
+
"TrainerControl": {
|
| 39 |
+
"args": {
|
| 40 |
+
"should_epoch_stop": false,
|
| 41 |
+
"should_evaluate": false,
|
| 42 |
+
"should_log": false,
|
| 43 |
+
"should_save": true,
|
| 44 |
+
"should_training_stop": true
|
| 45 |
+
},
|
| 46 |
+
"attributes": {}
|
| 47 |
+
}
|
| 48 |
+
},
|
| 49 |
+
"total_flos": 7.7496851367936e+16,
|
| 50 |
+
"train_batch_size": 32,
|
| 51 |
+
"trial_name": null,
|
| 52 |
+
"trial_params": null
|
| 53 |
+
}
|
checkpoint-32/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:28ebf2b6dbb08045128c07625eb89924fd949f0c3794edd35784a5c320305df8
|
| 3 |
+
size 5304
|
checkpoint-4688/config.json
ADDED
|
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": "0-2",
|
| 13 |
+
"1": "3-9",
|
| 14 |
+
"2": "10-19",
|
| 15 |
+
"3": "20-29",
|
| 16 |
+
"4": "30-39",
|
| 17 |
+
"5": "40-49",
|
| 18 |
+
"6": "50-59",
|
| 19 |
+
"7": "60-69",
|
| 20 |
+
"8": "more than 70"
|
| 21 |
+
},
|
| 22 |
+
"image_size": 224,
|
| 23 |
+
"initializer_range": 0.02,
|
| 24 |
+
"intermediate_size": 3072,
|
| 25 |
+
"label2id": {
|
| 26 |
+
"0-2": 0,
|
| 27 |
+
"10-19": 2,
|
| 28 |
+
"20-29": 3,
|
| 29 |
+
"3-9": 1,
|
| 30 |
+
"30-39": 4,
|
| 31 |
+
"40-49": 5,
|
| 32 |
+
"50-59": 6,
|
| 33 |
+
"60-69": 7,
|
| 34 |
+
"more than 70": 8
|
| 35 |
+
},
|
| 36 |
+
"layer_norm_eps": 1e-12,
|
| 37 |
+
"model_type": "vit",
|
| 38 |
+
"num_attention_heads": 12,
|
| 39 |
+
"num_channels": 3,
|
| 40 |
+
"num_hidden_layers": 12,
|
| 41 |
+
"patch_size": 16,
|
| 42 |
+
"problem_type": "single_label_classification",
|
| 43 |
+
"qkv_bias": true,
|
| 44 |
+
"torch_dtype": "float32",
|
| 45 |
+
"transformers_version": "4.47.0"
|
| 46 |
+
}
|
checkpoint-4688/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1f6f3b28c3de06bcedbae8b985363f2df21de98524d8165e2c6cc7f998d98c57
|
| 3 |
+
size 343245508
|
checkpoint-4688/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8791320f4d583baaa89f9cc262a7a6bbf539b9f9a9e4914e6837a32bd47a7d98
|
| 3 |
+
size 686611898
|
checkpoint-4688/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 |
+
0.5,
|
| 8 |
+
0.5,
|
| 9 |
+
0.5
|
| 10 |
+
],
|
| 11 |
+
"image_processor_type": "ViTImageProcessor",
|
| 12 |
+
"image_std": [
|
| 13 |
+
0.5,
|
| 14 |
+
0.5,
|
| 15 |
+
0.5
|
| 16 |
+
],
|
| 17 |
+
"resample": 2,
|
| 18 |
+
"rescale_factor": 0.00392156862745098,
|
| 19 |
+
"size": {
|
| 20 |
+
"height": 224,
|
| 21 |
+
"width": 224
|
| 22 |
+
}
|
| 23 |
+
}
|
checkpoint-4688/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6b3ee827a7a00012c0a116546df467feee35e70376d81a7a85b1a70eb90414d3
|
| 3 |
+
size 14244
|
checkpoint-4688/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b93e187257ca6fe0f5b0bc88b5e29ad4936be1b98b0acb5f887bb184be713f3d
|
| 3 |
+
size 1064
|
checkpoint-4688/trainer_state.json
ADDED
|
@@ -0,0 +1,116 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 1.233594298362732,
|
| 3 |
+
"best_model_checkpoint": "fairface_age_image_detection/checkpoint-4688",
|
| 4 |
+
"epoch": 2.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 4688,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.21331058020477817,
|
| 13 |
+
"grad_norm": 1.7164175510406494,
|
| 14 |
+
"learning_rate": 2.2574385510996123e-06,
|
| 15 |
+
"loss": 1.945,
|
| 16 |
+
"step": 500
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.42662116040955633,
|
| 20 |
+
"grad_norm": 1.979918360710144,
|
| 21 |
+
"learning_rate": 1.9879258300991807e-06,
|
| 22 |
+
"loss": 1.5803,
|
| 23 |
+
"step": 1000
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.6399317406143344,
|
| 27 |
+
"grad_norm": 2.0418295860290527,
|
| 28 |
+
"learning_rate": 1.7184131090987496e-06,
|
| 29 |
+
"loss": 1.4368,
|
| 30 |
+
"step": 1500
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.8532423208191127,
|
| 34 |
+
"grad_norm": 2.872443199157715,
|
| 35 |
+
"learning_rate": 1.4489003880983182e-06,
|
| 36 |
+
"loss": 1.3531,
|
| 37 |
+
"step": 2000
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 1.0,
|
| 41 |
+
"eval_accuracy": 0.5275,
|
| 42 |
+
"eval_loss": 1.3043227195739746,
|
| 43 |
+
"eval_model_preparation_time": 0.0035,
|
| 44 |
+
"eval_runtime": 894.9363,
|
| 45 |
+
"eval_samples_per_second": 11.174,
|
| 46 |
+
"eval_steps_per_second": 1.397,
|
| 47 |
+
"step": 2344
|
| 48 |
+
},
|
| 49 |
+
{
|
| 50 |
+
"epoch": 1.0665529010238908,
|
| 51 |
+
"grad_norm": 4.807504177093506,
|
| 52 |
+
"learning_rate": 1.179387667097887e-06,
|
| 53 |
+
"loss": 1.3097,
|
| 54 |
+
"step": 2500
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 1.2798634812286689,
|
| 58 |
+
"grad_norm": 6.204404830932617,
|
| 59 |
+
"learning_rate": 9.098749460974558e-07,
|
| 60 |
+
"loss": 1.2671,
|
| 61 |
+
"step": 3000
|
| 62 |
+
},
|
| 63 |
+
{
|
| 64 |
+
"epoch": 1.493174061433447,
|
| 65 |
+
"grad_norm": 6.795459270477295,
|
| 66 |
+
"learning_rate": 6.403622250970247e-07,
|
| 67 |
+
"loss": 1.2428,
|
| 68 |
+
"step": 3500
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 1.7064846416382253,
|
| 72 |
+
"grad_norm": 3.4942402839660645,
|
| 73 |
+
"learning_rate": 3.708495040965934e-07,
|
| 74 |
+
"loss": 1.2307,
|
| 75 |
+
"step": 4000
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 1.9197952218430034,
|
| 79 |
+
"grad_norm": 3.384183406829834,
|
| 80 |
+
"learning_rate": 1.0133678309616215e-07,
|
| 81 |
+
"loss": 1.2214,
|
| 82 |
+
"step": 4500
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 2.0,
|
| 86 |
+
"eval_accuracy": 0.5385,
|
| 87 |
+
"eval_loss": 1.233594298362732,
|
| 88 |
+
"eval_model_preparation_time": 0.0035,
|
| 89 |
+
"eval_runtime": 903.6391,
|
| 90 |
+
"eval_samples_per_second": 11.066,
|
| 91 |
+
"eval_steps_per_second": 1.383,
|
| 92 |
+
"step": 4688
|
| 93 |
+
}
|
| 94 |
+
],
|
| 95 |
+
"logging_steps": 500,
|
| 96 |
+
"max_steps": 4688,
|
| 97 |
+
"num_input_tokens_seen": 0,
|
| 98 |
+
"num_train_epochs": 2,
|
| 99 |
+
"save_steps": 500,
|
| 100 |
+
"stateful_callbacks": {
|
| 101 |
+
"TrainerControl": {
|
| 102 |
+
"args": {
|
| 103 |
+
"should_epoch_stop": false,
|
| 104 |
+
"should_evaluate": false,
|
| 105 |
+
"should_log": false,
|
| 106 |
+
"should_save": true,
|
| 107 |
+
"should_training_stop": true
|
| 108 |
+
},
|
| 109 |
+
"attributes": {}
|
| 110 |
+
}
|
| 111 |
+
},
|
| 112 |
+
"total_flos": 1.16245277051904e+19,
|
| 113 |
+
"train_batch_size": 32,
|
| 114 |
+
"trial_name": null,
|
| 115 |
+
"trial_params": null
|
| 116 |
+
}
|
checkpoint-4688/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:28ebf2b6dbb08045128c07625eb89924fd949f0c3794edd35784a5c320305df8
|
| 3 |
+
size 5304
|
checkpoint-8752/config.json
ADDED
|
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": "0-2",
|
| 13 |
+
"1": "3-9",
|
| 14 |
+
"2": "10-19",
|
| 15 |
+
"3": "20-29",
|
| 16 |
+
"4": "30-39",
|
| 17 |
+
"5": "40-49",
|
| 18 |
+
"6": "50-59",
|
| 19 |
+
"7": "60-69",
|
| 20 |
+
"8": "more than 70"
|
| 21 |
+
},
|
| 22 |
+
"image_size": 224,
|
| 23 |
+
"initializer_range": 0.02,
|
| 24 |
+
"intermediate_size": 3072,
|
| 25 |
+
"label2id": {
|
| 26 |
+
"0-2": 0,
|
| 27 |
+
"10-19": 2,
|
| 28 |
+
"20-29": 3,
|
| 29 |
+
"3-9": 1,
|
| 30 |
+
"30-39": 4,
|
| 31 |
+
"40-49": 5,
|
| 32 |
+
"50-59": 6,
|
| 33 |
+
"60-69": 7,
|
| 34 |
+
"more than 70": 8
|
| 35 |
+
},
|
| 36 |
+
"layer_norm_eps": 1e-12,
|
| 37 |
+
"model_type": "vit",
|
| 38 |
+
"num_attention_heads": 12,
|
| 39 |
+
"num_channels": 3,
|
| 40 |
+
"num_hidden_layers": 12,
|
| 41 |
+
"patch_size": 16,
|
| 42 |
+
"problem_type": "single_label_classification",
|
| 43 |
+
"qkv_bias": true,
|
| 44 |
+
"torch_dtype": "float32",
|
| 45 |
+
"transformers_version": "4.47.0"
|
| 46 |
+
}
|
checkpoint-8752/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cd3a725b1119d48b89118403515c77428316605407f871bbc7bba7fb50b32305
|
| 3 |
+
size 343245508
|
checkpoint-8752/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:087e51816b138512d362a1022cf69ae38505cd21144fa8057f954593880b9011
|
| 3 |
+
size 686611898
|
checkpoint-8752/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 |
+
0.5,
|
| 8 |
+
0.5,
|
| 9 |
+
0.5
|
| 10 |
+
],
|
| 11 |
+
"image_processor_type": "ViTImageProcessor",
|
| 12 |
+
"image_std": [
|
| 13 |
+
0.5,
|
| 14 |
+
0.5,
|
| 15 |
+
0.5
|
| 16 |
+
],
|
| 17 |
+
"resample": 2,
|
| 18 |
+
"rescale_factor": 0.00392156862745098,
|
| 19 |
+
"size": {
|
| 20 |
+
"height": 224,
|
| 21 |
+
"width": 224
|
| 22 |
+
}
|
| 23 |
+
}
|
checkpoint-8752/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:48ee9b73399c28d7e668360bf1d5a4d11095c4738bf96c13f7bb6fbff59f8ccb
|
| 3 |
+
size 14244
|
checkpoint-8752/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:197fc8dcfe2b6e4805b14a2ff8529c35795cc2f0491c4b5a6bd2783753725f19
|
| 3 |
+
size 1064
|
checkpoint-8752/trainer_state.json
ADDED
|
@@ -0,0 +1,192 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 1.0447938442230225,
|
| 3 |
+
"best_model_checkpoint": "fairface_age_image_detection/checkpoint-8752",
|
| 4 |
+
"epoch": 4.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 8752,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.22851919561243145,
|
| 13 |
+
"grad_norm": 2.228593587875366,
|
| 14 |
+
"learning_rate": 3.7931509997701674e-06,
|
| 15 |
+
"loss": 1.8122,
|
| 16 |
+
"step": 500
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.4570383912248629,
|
| 20 |
+
"grad_norm": 3.4612433910369873,
|
| 21 |
+
"learning_rate": 3.5633187772925763e-06,
|
| 22 |
+
"loss": 1.4177,
|
| 23 |
+
"step": 1000
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.6855575868372943,
|
| 27 |
+
"grad_norm": 5.7468061447143555,
|
| 28 |
+
"learning_rate": 3.333486554814985e-06,
|
| 29 |
+
"loss": 1.3017,
|
| 30 |
+
"step": 1500
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.9140767824497258,
|
| 34 |
+
"grad_norm": 4.807565212249756,
|
| 35 |
+
"learning_rate": 3.1036543323373935e-06,
|
| 36 |
+
"loss": 1.2187,
|
| 37 |
+
"step": 2000
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 1.0,
|
| 41 |
+
"eval_accuracy": 0.5457,
|
| 42 |
+
"eval_loss": 1.1929566860198975,
|
| 43 |
+
"eval_model_preparation_time": 0.0035,
|
| 44 |
+
"eval_runtime": 876.5594,
|
| 45 |
+
"eval_samples_per_second": 11.408,
|
| 46 |
+
"eval_steps_per_second": 1.426,
|
| 47 |
+
"step": 2188
|
| 48 |
+
},
|
| 49 |
+
{
|
| 50 |
+
"epoch": 1.1425959780621573,
|
| 51 |
+
"grad_norm": 3.004606246948242,
|
| 52 |
+
"learning_rate": 2.873822109859802e-06,
|
| 53 |
+
"loss": 1.1713,
|
| 54 |
+
"step": 2500
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 1.3711151736745886,
|
| 58 |
+
"grad_norm": 4.531455039978027,
|
| 59 |
+
"learning_rate": 2.643989887382211e-06,
|
| 60 |
+
"loss": 1.1284,
|
| 61 |
+
"step": 3000
|
| 62 |
+
},
|
| 63 |
+
{
|
| 64 |
+
"epoch": 1.59963436928702,
|
| 65 |
+
"grad_norm": 3.8209729194641113,
|
| 66 |
+
"learning_rate": 2.4141576649046196e-06,
|
| 67 |
+
"loss": 1.105,
|
| 68 |
+
"step": 3500
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 1.8281535648994516,
|
| 72 |
+
"grad_norm": 3.4607913494110107,
|
| 73 |
+
"learning_rate": 2.184325442427028e-06,
|
| 74 |
+
"loss": 1.0773,
|
| 75 |
+
"step": 4000
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 2.0,
|
| 79 |
+
"eval_accuracy": 0.5754,
|
| 80 |
+
"eval_loss": 1.085502028465271,
|
| 81 |
+
"eval_model_preparation_time": 0.0035,
|
| 82 |
+
"eval_runtime": 892.4566,
|
| 83 |
+
"eval_samples_per_second": 11.205,
|
| 84 |
+
"eval_steps_per_second": 1.401,
|
| 85 |
+
"step": 4376
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"epoch": 2.056672760511883,
|
| 89 |
+
"grad_norm": 4.261874675750732,
|
| 90 |
+
"learning_rate": 1.954493219949437e-06,
|
| 91 |
+
"loss": 1.0657,
|
| 92 |
+
"step": 4500
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 2.2851919561243146,
|
| 96 |
+
"grad_norm": 3.815229654312134,
|
| 97 |
+
"learning_rate": 1.7246609974718455e-06,
|
| 98 |
+
"loss": 1.036,
|
| 99 |
+
"step": 5000
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 2.5137111517367456,
|
| 103 |
+
"grad_norm": 4.119363307952881,
|
| 104 |
+
"learning_rate": 1.494828774994254e-06,
|
| 105 |
+
"loss": 1.0255,
|
| 106 |
+
"step": 5500
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 2.742230347349177,
|
| 110 |
+
"grad_norm": 4.172023296356201,
|
| 111 |
+
"learning_rate": 1.2649965525166627e-06,
|
| 112 |
+
"loss": 1.0126,
|
| 113 |
+
"step": 6000
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 2.9707495429616086,
|
| 117 |
+
"grad_norm": 3.792961597442627,
|
| 118 |
+
"learning_rate": 1.0351643300390714e-06,
|
| 119 |
+
"loss": 1.008,
|
| 120 |
+
"step": 6500
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 3.0,
|
| 124 |
+
"eval_accuracy": 0.5792,
|
| 125 |
+
"eval_loss": 1.0549699068069458,
|
| 126 |
+
"eval_model_preparation_time": 0.0035,
|
| 127 |
+
"eval_runtime": 902.9283,
|
| 128 |
+
"eval_samples_per_second": 11.075,
|
| 129 |
+
"eval_steps_per_second": 1.384,
|
| 130 |
+
"step": 6564
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 3.19926873857404,
|
| 134 |
+
"grad_norm": 6.58300256729126,
|
| 135 |
+
"learning_rate": 8.053321075614801e-07,
|
| 136 |
+
"loss": 0.9923,
|
| 137 |
+
"step": 7000
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 3.4277879341864717,
|
| 141 |
+
"grad_norm": 7.9831223487854,
|
| 142 |
+
"learning_rate": 5.754998850838887e-07,
|
| 143 |
+
"loss": 0.9792,
|
| 144 |
+
"step": 7500
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 3.656307129798903,
|
| 148 |
+
"grad_norm": 6.074549198150635,
|
| 149 |
+
"learning_rate": 3.456676626062974e-07,
|
| 150 |
+
"loss": 0.9826,
|
| 151 |
+
"step": 8000
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 3.8848263254113347,
|
| 155 |
+
"grad_norm": 6.298589706420898,
|
| 156 |
+
"learning_rate": 1.1583544012870603e-07,
|
| 157 |
+
"loss": 0.9858,
|
| 158 |
+
"step": 8500
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 4.0,
|
| 162 |
+
"eval_accuracy": 0.5809,
|
| 163 |
+
"eval_loss": 1.0447938442230225,
|
| 164 |
+
"eval_model_preparation_time": 0.0035,
|
| 165 |
+
"eval_runtime": 893.1973,
|
| 166 |
+
"eval_samples_per_second": 11.196,
|
| 167 |
+
"eval_steps_per_second": 1.399,
|
| 168 |
+
"step": 8752
|
| 169 |
+
}
|
| 170 |
+
],
|
| 171 |
+
"logging_steps": 500,
|
| 172 |
+
"max_steps": 8752,
|
| 173 |
+
"num_input_tokens_seen": 0,
|
| 174 |
+
"num_train_epochs": 4,
|
| 175 |
+
"save_steps": 500,
|
| 176 |
+
"stateful_callbacks": {
|
| 177 |
+
"TrainerControl": {
|
| 178 |
+
"args": {
|
| 179 |
+
"should_epoch_stop": false,
|
| 180 |
+
"should_evaluate": false,
|
| 181 |
+
"should_log": false,
|
| 182 |
+
"should_save": true,
|
| 183 |
+
"should_training_stop": true
|
| 184 |
+
},
|
| 185 |
+
"attributes": {}
|
| 186 |
+
}
|
| 187 |
+
},
|
| 188 |
+
"total_flos": 2.169911838302208e+19,
|
| 189 |
+
"train_batch_size": 32,
|
| 190 |
+
"trial_name": null,
|
| 191 |
+
"trial_params": null
|
| 192 |
+
}
|
checkpoint-8752/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e97ef976af56a6fd0395073925187744ad7c56829cffa99ff2332a90f94307b2
|
| 3 |
+
size 5304
|
checkpoint-9376/config.json
ADDED
|
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": "0-2",
|
| 13 |
+
"1": "3-9",
|
| 14 |
+
"2": "10-19",
|
| 15 |
+
"3": "20-29",
|
| 16 |
+
"4": "30-39",
|
| 17 |
+
"5": "40-49",
|
| 18 |
+
"6": "50-59",
|
| 19 |
+
"7": "60-69",
|
| 20 |
+
"8": "more than 70"
|
| 21 |
+
},
|
| 22 |
+
"image_size": 224,
|
| 23 |
+
"initializer_range": 0.02,
|
| 24 |
+
"intermediate_size": 3072,
|
| 25 |
+
"label2id": {
|
| 26 |
+
"0-2": 0,
|
| 27 |
+
"10-19": 2,
|
| 28 |
+
"20-29": 3,
|
| 29 |
+
"3-9": 1,
|
| 30 |
+
"30-39": 4,
|
| 31 |
+
"40-49": 5,
|
| 32 |
+
"50-59": 6,
|
| 33 |
+
"60-69": 7,
|
| 34 |
+
"more than 70": 8
|
| 35 |
+
},
|
| 36 |
+
"layer_norm_eps": 1e-12,
|
| 37 |
+
"model_type": "vit",
|
| 38 |
+
"num_attention_heads": 12,
|
| 39 |
+
"num_channels": 3,
|
| 40 |
+
"num_hidden_layers": 12,
|
| 41 |
+
"patch_size": 16,
|
| 42 |
+
"problem_type": "single_label_classification",
|
| 43 |
+
"qkv_bias": true,
|
| 44 |
+
"torch_dtype": "float32",
|
| 45 |
+
"transformers_version": "4.47.0"
|
| 46 |
+
}
|
checkpoint-9376/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1265d8e5a8a363a615898be873c224aebc6f310654bf23b1745da0975a7b7555
|
| 3 |
+
size 343245508
|
checkpoint-9376/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:db14e1baf0fce1ab79882476b9e400854724970e5adf6d8b17ef6d264fad3b22
|
| 3 |
+
size 686611898
|
checkpoint-9376/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 |
+
0.5,
|
| 8 |
+
0.5,
|
| 9 |
+
0.5
|
| 10 |
+
],
|
| 11 |
+
"image_processor_type": "ViTImageProcessor",
|
| 12 |
+
"image_std": [
|
| 13 |
+
0.5,
|
| 14 |
+
0.5,
|
| 15 |
+
0.5
|
| 16 |
+
],
|
| 17 |
+
"resample": 2,
|
| 18 |
+
"rescale_factor": 0.00392156862745098,
|
| 19 |
+
"size": {
|
| 20 |
+
"height": 224,
|
| 21 |
+
"width": 224
|
| 22 |
+
}
|
| 23 |
+
}
|
checkpoint-9376/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:48ee9b73399c28d7e668360bf1d5a4d11095c4738bf96c13f7bb6fbff59f8ccb
|
| 3 |
+
size 14244
|
checkpoint-9376/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:162830a25651b28da57d4375090a0500b22eb117bbfd79d4a2bf61dd85a56833
|
| 3 |
+
size 1064
|
checkpoint-9376/trainer_state.json
ADDED
|
@@ -0,0 +1,199 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 1.0019118785858154,
|
| 3 |
+
"best_model_checkpoint": "fairface_age_image_detection/checkpoint-9376",
|
| 4 |
+
"epoch": 4.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 9376,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.21331058020477817,
|
| 13 |
+
"grad_norm": 2.756800413131714,
|
| 14 |
+
"learning_rate": 5.710486811065838e-06,
|
| 15 |
+
"loss": 1.7206,
|
| 16 |
+
"step": 500
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.42662116040955633,
|
| 20 |
+
"grad_norm": 3.085395097732544,
|
| 21 |
+
"learning_rate": 5.3888054900278794e-06,
|
| 22 |
+
"loss": 1.3151,
|
| 23 |
+
"step": 1000
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.6399317406143344,
|
| 27 |
+
"grad_norm": 3.533961057662964,
|
| 28 |
+
"learning_rate": 5.067124168989921e-06,
|
| 29 |
+
"loss": 1.212,
|
| 30 |
+
"step": 1500
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.8532423208191127,
|
| 34 |
+
"grad_norm": 5.493643283843994,
|
| 35 |
+
"learning_rate": 4.745442847951962e-06,
|
| 36 |
+
"loss": 1.145,
|
| 37 |
+
"step": 2000
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 1.0,
|
| 41 |
+
"eval_accuracy": 0.5652,
|
| 42 |
+
"eval_loss": 1.115075707435608,
|
| 43 |
+
"eval_model_preparation_time": 0.0037,
|
| 44 |
+
"eval_runtime": 903.327,
|
| 45 |
+
"eval_samples_per_second": 11.07,
|
| 46 |
+
"eval_steps_per_second": 1.384,
|
| 47 |
+
"step": 2344
|
| 48 |
+
},
|
| 49 |
+
{
|
| 50 |
+
"epoch": 1.0665529010238908,
|
| 51 |
+
"grad_norm": 5.28899621963501,
|
| 52 |
+
"learning_rate": 4.423761526914004e-06,
|
| 53 |
+
"loss": 1.1006,
|
| 54 |
+
"step": 2500
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 1.2798634812286689,
|
| 58 |
+
"grad_norm": 6.52961540222168,
|
| 59 |
+
"learning_rate": 4.102080205876046e-06,
|
| 60 |
+
"loss": 1.0519,
|
| 61 |
+
"step": 3000
|
| 62 |
+
},
|
| 63 |
+
{
|
| 64 |
+
"epoch": 1.493174061433447,
|
| 65 |
+
"grad_norm": 10.652497291564941,
|
| 66 |
+
"learning_rate": 3.7803988848380875e-06,
|
| 67 |
+
"loss": 1.0292,
|
| 68 |
+
"step": 3500
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 1.7064846416382253,
|
| 72 |
+
"grad_norm": 5.245483875274658,
|
| 73 |
+
"learning_rate": 3.4587175638001284e-06,
|
| 74 |
+
"loss": 1.016,
|
| 75 |
+
"step": 4000
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 1.9197952218430034,
|
| 79 |
+
"grad_norm": 4.070522308349609,
|
| 80 |
+
"learning_rate": 3.1370362427621706e-06,
|
| 81 |
+
"loss": 1.0056,
|
| 82 |
+
"step": 4500
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 2.0,
|
| 86 |
+
"eval_accuracy": 0.5831,
|
| 87 |
+
"eval_loss": 1.030907392501831,
|
| 88 |
+
"eval_model_preparation_time": 0.0037,
|
| 89 |
+
"eval_runtime": 917.4025,
|
| 90 |
+
"eval_samples_per_second": 10.9,
|
| 91 |
+
"eval_steps_per_second": 1.363,
|
| 92 |
+
"step": 4688
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 2.1331058020477816,
|
| 96 |
+
"grad_norm": 6.568565845489502,
|
| 97 |
+
"learning_rate": 2.815354921724212e-06,
|
| 98 |
+
"loss": 0.9796,
|
| 99 |
+
"step": 5000
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 2.34641638225256,
|
| 103 |
+
"grad_norm": 10.742039680480957,
|
| 104 |
+
"learning_rate": 2.4936736006862537e-06,
|
| 105 |
+
"loss": 0.9587,
|
| 106 |
+
"step": 5500
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 2.5597269624573378,
|
| 110 |
+
"grad_norm": 4.3592424392700195,
|
| 111 |
+
"learning_rate": 2.171992279648295e-06,
|
| 112 |
+
"loss": 0.9455,
|
| 113 |
+
"step": 6000
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 2.773037542662116,
|
| 117 |
+
"grad_norm": 5.696556091308594,
|
| 118 |
+
"learning_rate": 1.8503109586103366e-06,
|
| 119 |
+
"loss": 0.9363,
|
| 120 |
+
"step": 6500
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 2.986348122866894,
|
| 124 |
+
"grad_norm": 5.746116638183594,
|
| 125 |
+
"learning_rate": 1.5286296375723786e-06,
|
| 126 |
+
"loss": 0.9347,
|
| 127 |
+
"step": 7000
|
| 128 |
+
},
|
| 129 |
+
{
|
| 130 |
+
"epoch": 3.0,
|
| 131 |
+
"eval_accuracy": 0.5883,
|
| 132 |
+
"eval_loss": 1.0057746171951294,
|
| 133 |
+
"eval_model_preparation_time": 0.0037,
|
| 134 |
+
"eval_runtime": 926.1536,
|
| 135 |
+
"eval_samples_per_second": 10.797,
|
| 136 |
+
"eval_steps_per_second": 1.35,
|
| 137 |
+
"step": 7032
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 3.1996587030716723,
|
| 141 |
+
"grad_norm": 4.218583106994629,
|
| 142 |
+
"learning_rate": 1.20694831653442e-06,
|
| 143 |
+
"loss": 0.9035,
|
| 144 |
+
"step": 7500
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 3.4129692832764507,
|
| 148 |
+
"grad_norm": 6.724698543548584,
|
| 149 |
+
"learning_rate": 8.852669954964614e-07,
|
| 150 |
+
"loss": 0.9081,
|
| 151 |
+
"step": 8000
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 3.6262798634812285,
|
| 155 |
+
"grad_norm": 6.658480167388916,
|
| 156 |
+
"learning_rate": 5.635856744585031e-07,
|
| 157 |
+
"loss": 0.905,
|
| 158 |
+
"step": 8500
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 3.839590443686007,
|
| 162 |
+
"grad_norm": 4.382744789123535,
|
| 163 |
+
"learning_rate": 2.4190435342054474e-07,
|
| 164 |
+
"loss": 0.8969,
|
| 165 |
+
"step": 9000
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 4.0,
|
| 169 |
+
"eval_accuracy": 0.5892,
|
| 170 |
+
"eval_loss": 1.0019118785858154,
|
| 171 |
+
"eval_model_preparation_time": 0.0037,
|
| 172 |
+
"eval_runtime": 929.5968,
|
| 173 |
+
"eval_samples_per_second": 10.757,
|
| 174 |
+
"eval_steps_per_second": 1.345,
|
| 175 |
+
"step": 9376
|
| 176 |
+
}
|
| 177 |
+
],
|
| 178 |
+
"logging_steps": 500,
|
| 179 |
+
"max_steps": 9376,
|
| 180 |
+
"num_input_tokens_seen": 0,
|
| 181 |
+
"num_train_epochs": 4,
|
| 182 |
+
"save_steps": 500,
|
| 183 |
+
"stateful_callbacks": {
|
| 184 |
+
"TrainerControl": {
|
| 185 |
+
"args": {
|
| 186 |
+
"should_epoch_stop": false,
|
| 187 |
+
"should_evaluate": false,
|
| 188 |
+
"should_log": false,
|
| 189 |
+
"should_save": true,
|
| 190 |
+
"should_training_stop": true
|
| 191 |
+
},
|
| 192 |
+
"attributes": {}
|
| 193 |
+
}
|
| 194 |
+
},
|
| 195 |
+
"total_flos": 2.32490554103808e+19,
|
| 196 |
+
"train_batch_size": 32,
|
| 197 |
+
"trial_name": null,
|
| 198 |
+
"trial_params": null
|
| 199 |
+
}
|
checkpoint-9376/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5ba8df84fa27b6ce1aa5fc9dad74c0fa9ee6fdec46d72d1f00235b986d4684db
|
| 3 |
+
size 5304
|
config.json
ADDED
|
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": "0-2",
|
| 13 |
+
"1": "3-9",
|
| 14 |
+
"2": "10-19",
|
| 15 |
+
"3": "20-29",
|
| 16 |
+
"4": "30-39",
|
| 17 |
+
"5": "40-49",
|
| 18 |
+
"6": "50-59",
|
| 19 |
+
"7": "60-69",
|
| 20 |
+
"8": "more than 70"
|
| 21 |
+
},
|
| 22 |
+
"image_size": 224,
|
| 23 |
+
"initializer_range": 0.02,
|
| 24 |
+
"intermediate_size": 3072,
|
| 25 |
+
"label2id": {
|
| 26 |
+
"0-2": 0,
|
| 27 |
+
"10-19": 2,
|
| 28 |
+
"20-29": 3,
|
| 29 |
+
"3-9": 1,
|
| 30 |
+
"30-39": 4,
|
| 31 |
+
"40-49": 5,
|
| 32 |
+
"50-59": 6,
|
| 33 |
+
"60-69": 7,
|
| 34 |
+
"more than 70": 8
|
| 35 |
+
},
|
| 36 |
+
"layer_norm_eps": 1e-12,
|
| 37 |
+
"model_type": "vit",
|
| 38 |
+
"num_attention_heads": 12,
|
| 39 |
+
"num_channels": 3,
|
| 40 |
+
"num_hidden_layers": 12,
|
| 41 |
+
"patch_size": 16,
|
| 42 |
+
"problem_type": "single_label_classification",
|
| 43 |
+
"qkv_bias": true,
|
| 44 |
+
"torch_dtype": "float32",
|
| 45 |
+
"transformers_version": "4.47.0"
|
| 46 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1265d8e5a8a363a615898be873c224aebc6f310654bf23b1745da0975a7b7555
|
| 3 |
+
size 343245508
|
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 |
+
0.5,
|
| 8 |
+
0.5,
|
| 9 |
+
0.5
|
| 10 |
+
],
|
| 11 |
+
"image_processor_type": "ViTImageProcessor",
|
| 12 |
+
"image_std": [
|
| 13 |
+
0.5,
|
| 14 |
+
0.5,
|
| 15 |
+
0.5
|
| 16 |
+
],
|
| 17 |
+
"resample": 2,
|
| 18 |
+
"rescale_factor": 0.00392156862745098,
|
| 19 |
+
"size": {
|
| 20 |
+
"height": 224,
|
| 21 |
+
"width": 224
|
| 22 |
+
}
|
| 23 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5ba8df84fa27b6ce1aa5fc9dad74c0fa9ee6fdec46d72d1f00235b986d4684db
|
| 3 |
+
size 5304
|