Commit
·
ea4787b
1
Parent(s):
ba01c26
Upload folder using huggingface_hub
Browse files- README.md +32 -0
- checkpoint-9004/config.json +33 -0
- checkpoint-9004/optimizer.pt +3 -0
- checkpoint-9004/pytorch_model.bin +3 -0
- checkpoint-9004/rng_state.pth +3 -0
- checkpoint-9004/scheduler.pt +3 -0
- checkpoint-9004/trainer_state.json +1151 -0
- checkpoint-9004/training_args.bin +3 -0
- config.json +33 -0
- preprocessor_config.json +22 -0
- pytorch_model.bin +3 -0
- runs/Sep02_09-12-58_c3f9c2116fca/events.out.tfevents.1693645986.c3f9c2116fca.859.0 +3 -0
- runs/Sep02_09-15-13_c3f9c2116fca/events.out.tfevents.1693646116.c3f9c2116fca.896.0 +3 -0
- runs/Sep02_10-08-26_c3f9c2116fca/events.out.tfevents.1693649310.c3f9c2116fca.1017.0 +3 -0
- runs/Sep02_10-08-26_c3f9c2116fca/events.out.tfevents.1693653026.c3f9c2116fca.1017.1 +3 -0
- training_args.bin +3 -0
- training_params.json +28 -0
README.md
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
|
| 2 |
+
---
|
| 3 |
+
tags:
|
| 4 |
+
- autotrain
|
| 5 |
+
- image-classification
|
| 6 |
+
widget:
|
| 7 |
+
- src: https://huggingface.co/datasets/mishig/sample_images/resolve/main/tiger.jpg
|
| 8 |
+
example_title: Tiger
|
| 9 |
+
- src: https://huggingface.co/datasets/mishig/sample_images/resolve/main/teapot.jpg
|
| 10 |
+
example_title: Teapot
|
| 11 |
+
- src: https://huggingface.co/datasets/mishig/sample_images/resolve/main/palace.jpg
|
| 12 |
+
example_title: Palace
|
| 13 |
+
datasets:
|
| 14 |
+
- KhalfounMehdi/mura_dataset_processed_224px_train_val
|
| 15 |
+
---
|
| 16 |
+
|
| 17 |
+
# Model Trained Using AutoTrain
|
| 18 |
+
|
| 19 |
+
- Problem type: Image Classification
|
| 20 |
+
|
| 21 |
+
## Validation Metricsg
|
| 22 |
+
loss: 0.5185230374336243
|
| 23 |
+
|
| 24 |
+
f1: 0.8211164615658998
|
| 25 |
+
|
| 26 |
+
precision: 0.7175810473815462
|
| 27 |
+
|
| 28 |
+
recall: 0.9595664860358483
|
| 29 |
+
|
| 30 |
+
auc: 0.7988417458585272
|
| 31 |
+
|
| 32 |
+
accuracy: 0.749312671832042
|
checkpoint-9004/config.json
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "KhalfounMehdi/mura_vit_224",
|
| 3 |
+
"_num_labels": 2,
|
| 4 |
+
"architectures": [
|
| 5 |
+
"ViTForImageClassification"
|
| 6 |
+
],
|
| 7 |
+
"attention_probs_dropout_prob": 0.0,
|
| 8 |
+
"encoder_stride": 16,
|
| 9 |
+
"hidden_act": "gelu",
|
| 10 |
+
"hidden_dropout_prob": 0.0,
|
| 11 |
+
"hidden_size": 768,
|
| 12 |
+
"id2label": {
|
| 13 |
+
"0": "abnormal",
|
| 14 |
+
"1": "normal"
|
| 15 |
+
},
|
| 16 |
+
"image_size": 224,
|
| 17 |
+
"initializer_range": 0.02,
|
| 18 |
+
"intermediate_size": 3072,
|
| 19 |
+
"label2id": {
|
| 20 |
+
"abnormal": 0,
|
| 21 |
+
"normal": 1
|
| 22 |
+
},
|
| 23 |
+
"layer_norm_eps": 1e-12,
|
| 24 |
+
"model_type": "vit",
|
| 25 |
+
"num_attention_heads": 12,
|
| 26 |
+
"num_channels": 3,
|
| 27 |
+
"num_hidden_layers": 12,
|
| 28 |
+
"patch_size": 16,
|
| 29 |
+
"problem_type": "single_label_classification",
|
| 30 |
+
"qkv_bias": true,
|
| 31 |
+
"torch_dtype": "float32",
|
| 32 |
+
"transformers_version": "4.33.0.dev0"
|
| 33 |
+
}
|
checkpoint-9004/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7c81da075e723bf5519fea4723570d6eb6b03368e09e5cb06228e67d270d3e48
|
| 3 |
+
size 686568453
|
checkpoint-9004/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2aa275df102c4055478fea67c20c37edd7e84655990d4ee849cbdb9ccc94661d
|
| 3 |
+
size 343268717
|
checkpoint-9004/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7e8205b22b996108d5f57e6682d0098afe796b461ca684cc0709bb34b69b7f95
|
| 3 |
+
size 14575
|
checkpoint-9004/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1530d91dbb1b9f747eb3bca6652f400232a7acfb40404ed33fdb28f80b731494
|
| 3 |
+
size 627
|
checkpoint-9004/trainer_state.json
ADDED
|
@@ -0,0 +1,1151 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.5185230374336243,
|
| 3 |
+
"best_model_checkpoint": "mura_vit_224_10ep/checkpoint-9004",
|
| 4 |
+
"epoch": 4.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 9004,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.02,
|
| 13 |
+
"learning_rate": 2.221235006663705e-06,
|
| 14 |
+
"loss": 0.501,
|
| 15 |
+
"step": 50
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.04,
|
| 19 |
+
"learning_rate": 4.44247001332741e-06,
|
| 20 |
+
"loss": 0.4777,
|
| 21 |
+
"step": 100
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.07,
|
| 25 |
+
"learning_rate": 6.663705019991115e-06,
|
| 26 |
+
"loss": 0.4847,
|
| 27 |
+
"step": 150
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.09,
|
| 31 |
+
"learning_rate": 8.88494002665482e-06,
|
| 32 |
+
"loss": 0.4587,
|
| 33 |
+
"step": 200
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.11,
|
| 37 |
+
"learning_rate": 1.1106175033318526e-05,
|
| 38 |
+
"loss": 0.4898,
|
| 39 |
+
"step": 250
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.13,
|
| 43 |
+
"learning_rate": 1.332741003998223e-05,
|
| 44 |
+
"loss": 0.5003,
|
| 45 |
+
"step": 300
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.16,
|
| 49 |
+
"learning_rate": 1.5548645046645934e-05,
|
| 50 |
+
"loss": 0.4713,
|
| 51 |
+
"step": 350
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.18,
|
| 55 |
+
"learning_rate": 1.776988005330964e-05,
|
| 56 |
+
"loss": 0.5044,
|
| 57 |
+
"step": 400
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.2,
|
| 61 |
+
"learning_rate": 1.9991115059973345e-05,
|
| 62 |
+
"loss": 0.4841,
|
| 63 |
+
"step": 450
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.22,
|
| 67 |
+
"learning_rate": 2.2212350066637052e-05,
|
| 68 |
+
"loss": 0.4805,
|
| 69 |
+
"step": 500
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.24,
|
| 73 |
+
"learning_rate": 2.443358507330076e-05,
|
| 74 |
+
"loss": 0.4721,
|
| 75 |
+
"step": 550
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.27,
|
| 79 |
+
"learning_rate": 2.665482007996446e-05,
|
| 80 |
+
"loss": 0.5021,
|
| 81 |
+
"step": 600
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.29,
|
| 85 |
+
"learning_rate": 2.8876055086628167e-05,
|
| 86 |
+
"loss": 0.5348,
|
| 87 |
+
"step": 650
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.31,
|
| 91 |
+
"learning_rate": 3.109729009329187e-05,
|
| 92 |
+
"loss": 0.48,
|
| 93 |
+
"step": 700
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.33,
|
| 97 |
+
"learning_rate": 3.331852509995558e-05,
|
| 98 |
+
"loss": 0.5005,
|
| 99 |
+
"step": 750
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.36,
|
| 103 |
+
"learning_rate": 3.553976010661928e-05,
|
| 104 |
+
"loss": 0.4833,
|
| 105 |
+
"step": 800
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.38,
|
| 109 |
+
"learning_rate": 3.7760995113282985e-05,
|
| 110 |
+
"loss": 0.5251,
|
| 111 |
+
"step": 850
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.4,
|
| 115 |
+
"learning_rate": 3.998223011994669e-05,
|
| 116 |
+
"loss": 0.4782,
|
| 117 |
+
"step": 900
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.42,
|
| 121 |
+
"learning_rate": 4.22034651266104e-05,
|
| 122 |
+
"loss": 0.5145,
|
| 123 |
+
"step": 950
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.44,
|
| 127 |
+
"learning_rate": 4.4424700133274104e-05,
|
| 128 |
+
"loss": 0.4776,
|
| 129 |
+
"step": 1000
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.47,
|
| 133 |
+
"learning_rate": 4.664593513993781e-05,
|
| 134 |
+
"loss": 0.5021,
|
| 135 |
+
"step": 1050
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.49,
|
| 139 |
+
"learning_rate": 4.886717014660152e-05,
|
| 140 |
+
"loss": 0.4772,
|
| 141 |
+
"step": 1100
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.51,
|
| 145 |
+
"learning_rate": 5.1088405153265215e-05,
|
| 146 |
+
"loss": 0.5037,
|
| 147 |
+
"step": 1150
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 0.53,
|
| 151 |
+
"learning_rate": 5.330964015992892e-05,
|
| 152 |
+
"loss": 0.4697,
|
| 153 |
+
"step": 1200
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.56,
|
| 157 |
+
"learning_rate": 5.5530875166592636e-05,
|
| 158 |
+
"loss": 0.5098,
|
| 159 |
+
"step": 1250
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.58,
|
| 163 |
+
"learning_rate": 5.7752110173256333e-05,
|
| 164 |
+
"loss": 0.5352,
|
| 165 |
+
"step": 1300
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.6,
|
| 169 |
+
"learning_rate": 5.997334517992004e-05,
|
| 170 |
+
"loss": 0.5043,
|
| 171 |
+
"step": 1350
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.62,
|
| 175 |
+
"learning_rate": 6.219458018658373e-05,
|
| 176 |
+
"loss": 0.5291,
|
| 177 |
+
"step": 1400
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.64,
|
| 181 |
+
"learning_rate": 6.441581519324746e-05,
|
| 182 |
+
"loss": 0.494,
|
| 183 |
+
"step": 1450
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 0.67,
|
| 187 |
+
"learning_rate": 6.663705019991116e-05,
|
| 188 |
+
"loss": 0.5106,
|
| 189 |
+
"step": 1500
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.69,
|
| 193 |
+
"learning_rate": 6.885828520657485e-05,
|
| 194 |
+
"loss": 0.5239,
|
| 195 |
+
"step": 1550
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.71,
|
| 199 |
+
"learning_rate": 7.107952021323856e-05,
|
| 200 |
+
"loss": 0.5297,
|
| 201 |
+
"step": 1600
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 0.73,
|
| 205 |
+
"learning_rate": 7.330075521990227e-05,
|
| 206 |
+
"loss": 0.5363,
|
| 207 |
+
"step": 1650
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 0.76,
|
| 211 |
+
"learning_rate": 7.552199022656597e-05,
|
| 212 |
+
"loss": 0.4827,
|
| 213 |
+
"step": 1700
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.78,
|
| 217 |
+
"learning_rate": 7.774322523322968e-05,
|
| 218 |
+
"loss": 0.4679,
|
| 219 |
+
"step": 1750
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.8,
|
| 223 |
+
"learning_rate": 7.996446023989338e-05,
|
| 224 |
+
"loss": 0.5022,
|
| 225 |
+
"step": 1800
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 0.82,
|
| 229 |
+
"learning_rate": 8.218569524655709e-05,
|
| 230 |
+
"loss": 0.546,
|
| 231 |
+
"step": 1850
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 0.84,
|
| 235 |
+
"learning_rate": 8.44069302532208e-05,
|
| 236 |
+
"loss": 0.5214,
|
| 237 |
+
"step": 1900
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 0.87,
|
| 241 |
+
"learning_rate": 8.66281652598845e-05,
|
| 242 |
+
"loss": 0.5249,
|
| 243 |
+
"step": 1950
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 0.89,
|
| 247 |
+
"learning_rate": 8.884940026654821e-05,
|
| 248 |
+
"loss": 0.4825,
|
| 249 |
+
"step": 2000
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 0.91,
|
| 253 |
+
"learning_rate": 9.107063527321192e-05,
|
| 254 |
+
"loss": 0.508,
|
| 255 |
+
"step": 2050
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.93,
|
| 259 |
+
"learning_rate": 9.329187027987562e-05,
|
| 260 |
+
"loss": 0.541,
|
| 261 |
+
"step": 2100
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.96,
|
| 265 |
+
"learning_rate": 9.551310528653931e-05,
|
| 266 |
+
"loss": 0.5459,
|
| 267 |
+
"step": 2150
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 0.98,
|
| 271 |
+
"learning_rate": 9.773434029320304e-05,
|
| 272 |
+
"loss": 0.5086,
|
| 273 |
+
"step": 2200
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 1.0,
|
| 277 |
+
"learning_rate": 9.995557529986673e-05,
|
| 278 |
+
"loss": 0.499,
|
| 279 |
+
"step": 2250
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 1.0,
|
| 283 |
+
"eval_accuracy": 0.7555611097225694,
|
| 284 |
+
"eval_auc": 0.8084199669129719,
|
| 285 |
+
"eval_f1": 0.8114880493446416,
|
| 286 |
+
"eval_loss": 0.5284907817840576,
|
| 287 |
+
"eval_precision": 0.7547508067407673,
|
| 288 |
+
"eval_recall": 0.8774489370571071,
|
| 289 |
+
"eval_runtime": 41.4612,
|
| 290 |
+
"eval_samples_per_second": 96.5,
|
| 291 |
+
"eval_steps_per_second": 3.039,
|
| 292 |
+
"step": 2251
|
| 293 |
+
},
|
| 294 |
+
{
|
| 295 |
+
"epoch": 1.02,
|
| 296 |
+
"learning_rate": 0.00010217681030653043,
|
| 297 |
+
"loss": 0.5376,
|
| 298 |
+
"step": 2300
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"epoch": 1.04,
|
| 302 |
+
"learning_rate": 0.00010439804531319415,
|
| 303 |
+
"loss": 0.5448,
|
| 304 |
+
"step": 2350
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 1.07,
|
| 308 |
+
"learning_rate": 0.00010661928031985784,
|
| 309 |
+
"loss": 0.5191,
|
| 310 |
+
"step": 2400
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 1.09,
|
| 314 |
+
"learning_rate": 0.00010884051532652155,
|
| 315 |
+
"loss": 0.5306,
|
| 316 |
+
"step": 2450
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 1.11,
|
| 320 |
+
"learning_rate": 0.00011106175033318527,
|
| 321 |
+
"loss": 0.5159,
|
| 322 |
+
"step": 2500
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 1.13,
|
| 326 |
+
"learning_rate": 0.00011328298533984896,
|
| 327 |
+
"loss": 0.522,
|
| 328 |
+
"step": 2550
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 1.16,
|
| 332 |
+
"learning_rate": 0.00011550422034651267,
|
| 333 |
+
"loss": 0.5133,
|
| 334 |
+
"step": 2600
|
| 335 |
+
},
|
| 336 |
+
{
|
| 337 |
+
"epoch": 1.18,
|
| 338 |
+
"learning_rate": 0.00011772545535317636,
|
| 339 |
+
"loss": 0.5307,
|
| 340 |
+
"step": 2650
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 1.2,
|
| 344 |
+
"learning_rate": 0.00011994669035984007,
|
| 345 |
+
"loss": 0.529,
|
| 346 |
+
"step": 2700
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 1.22,
|
| 350 |
+
"learning_rate": 0.00012216792536650379,
|
| 351 |
+
"loss": 0.5238,
|
| 352 |
+
"step": 2750
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 1.24,
|
| 356 |
+
"learning_rate": 0.00012438916037316747,
|
| 357 |
+
"loss": 0.5174,
|
| 358 |
+
"step": 2800
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"epoch": 1.27,
|
| 362 |
+
"learning_rate": 0.00012661039537983118,
|
| 363 |
+
"loss": 0.5835,
|
| 364 |
+
"step": 2850
|
| 365 |
+
},
|
| 366 |
+
{
|
| 367 |
+
"epoch": 1.29,
|
| 368 |
+
"learning_rate": 0.00012883163038649492,
|
| 369 |
+
"loss": 0.5497,
|
| 370 |
+
"step": 2900
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 1.31,
|
| 374 |
+
"learning_rate": 0.0001310528653931586,
|
| 375 |
+
"loss": 0.5509,
|
| 376 |
+
"step": 2950
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 1.33,
|
| 380 |
+
"learning_rate": 0.0001332741003998223,
|
| 381 |
+
"loss": 0.5461,
|
| 382 |
+
"step": 3000
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 1.35,
|
| 386 |
+
"learning_rate": 0.00013549533540648602,
|
| 387 |
+
"loss": 0.5155,
|
| 388 |
+
"step": 3050
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 1.38,
|
| 392 |
+
"learning_rate": 0.0001377165704131497,
|
| 393 |
+
"loss": 0.5315,
|
| 394 |
+
"step": 3100
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 1.4,
|
| 398 |
+
"learning_rate": 0.00013993780541981342,
|
| 399 |
+
"loss": 0.552,
|
| 400 |
+
"step": 3150
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 1.42,
|
| 404 |
+
"learning_rate": 0.00014215904042647713,
|
| 405 |
+
"loss": 0.5293,
|
| 406 |
+
"step": 3200
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 1.44,
|
| 410 |
+
"learning_rate": 0.00014438027543314084,
|
| 411 |
+
"loss": 0.5443,
|
| 412 |
+
"step": 3250
|
| 413 |
+
},
|
| 414 |
+
{
|
| 415 |
+
"epoch": 1.47,
|
| 416 |
+
"learning_rate": 0.00014660151043980455,
|
| 417 |
+
"loss": 0.5472,
|
| 418 |
+
"step": 3300
|
| 419 |
+
},
|
| 420 |
+
{
|
| 421 |
+
"epoch": 1.49,
|
| 422 |
+
"learning_rate": 0.00014882274544646823,
|
| 423 |
+
"loss": 0.5381,
|
| 424 |
+
"step": 3350
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 1.51,
|
| 428 |
+
"learning_rate": 0.00015104398045313194,
|
| 429 |
+
"loss": 0.5528,
|
| 430 |
+
"step": 3400
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 1.53,
|
| 434 |
+
"learning_rate": 0.00015326521545979565,
|
| 435 |
+
"loss": 0.521,
|
| 436 |
+
"step": 3450
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 1.55,
|
| 440 |
+
"learning_rate": 0.00015548645046645936,
|
| 441 |
+
"loss": 0.5698,
|
| 442 |
+
"step": 3500
|
| 443 |
+
},
|
| 444 |
+
{
|
| 445 |
+
"epoch": 1.58,
|
| 446 |
+
"learning_rate": 0.00015770768547312307,
|
| 447 |
+
"loss": 0.5726,
|
| 448 |
+
"step": 3550
|
| 449 |
+
},
|
| 450 |
+
{
|
| 451 |
+
"epoch": 1.6,
|
| 452 |
+
"learning_rate": 0.00015992892047978676,
|
| 453 |
+
"loss": 0.5405,
|
| 454 |
+
"step": 3600
|
| 455 |
+
},
|
| 456 |
+
{
|
| 457 |
+
"epoch": 1.62,
|
| 458 |
+
"learning_rate": 0.00016215015548645047,
|
| 459 |
+
"loss": 0.5606,
|
| 460 |
+
"step": 3650
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 1.64,
|
| 464 |
+
"learning_rate": 0.00016437139049311418,
|
| 465 |
+
"loss": 0.5577,
|
| 466 |
+
"step": 3700
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 1.67,
|
| 470 |
+
"learning_rate": 0.0001665926254997779,
|
| 471 |
+
"loss": 0.5447,
|
| 472 |
+
"step": 3750
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 1.69,
|
| 476 |
+
"learning_rate": 0.0001688138605064416,
|
| 477 |
+
"loss": 0.5502,
|
| 478 |
+
"step": 3800
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 1.71,
|
| 482 |
+
"learning_rate": 0.0001710350955131053,
|
| 483 |
+
"loss": 0.5725,
|
| 484 |
+
"step": 3850
|
| 485 |
+
},
|
| 486 |
+
{
|
| 487 |
+
"epoch": 1.73,
|
| 488 |
+
"learning_rate": 0.000173256330519769,
|
| 489 |
+
"loss": 0.6174,
|
| 490 |
+
"step": 3900
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 1.75,
|
| 494 |
+
"learning_rate": 0.0001754775655264327,
|
| 495 |
+
"loss": 0.549,
|
| 496 |
+
"step": 3950
|
| 497 |
+
},
|
| 498 |
+
{
|
| 499 |
+
"epoch": 1.78,
|
| 500 |
+
"learning_rate": 0.00017769880053309641,
|
| 501 |
+
"loss": 0.562,
|
| 502 |
+
"step": 4000
|
| 503 |
+
},
|
| 504 |
+
{
|
| 505 |
+
"epoch": 1.8,
|
| 506 |
+
"learning_rate": 0.00017992003553976013,
|
| 507 |
+
"loss": 0.5602,
|
| 508 |
+
"step": 4050
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"epoch": 1.82,
|
| 512 |
+
"learning_rate": 0.00018214127054642384,
|
| 513 |
+
"loss": 0.568,
|
| 514 |
+
"step": 4100
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 1.84,
|
| 518 |
+
"learning_rate": 0.00018436250555308752,
|
| 519 |
+
"loss": 0.5753,
|
| 520 |
+
"step": 4150
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 1.87,
|
| 524 |
+
"learning_rate": 0.00018658374055975123,
|
| 525 |
+
"loss": 0.5262,
|
| 526 |
+
"step": 4200
|
| 527 |
+
},
|
| 528 |
+
{
|
| 529 |
+
"epoch": 1.89,
|
| 530 |
+
"learning_rate": 0.00018880497556641494,
|
| 531 |
+
"loss": 0.5467,
|
| 532 |
+
"step": 4250
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"epoch": 1.91,
|
| 536 |
+
"learning_rate": 0.00019102621057307862,
|
| 537 |
+
"loss": 0.5641,
|
| 538 |
+
"step": 4300
|
| 539 |
+
},
|
| 540 |
+
{
|
| 541 |
+
"epoch": 1.93,
|
| 542 |
+
"learning_rate": 0.00019324744557974233,
|
| 543 |
+
"loss": 0.5468,
|
| 544 |
+
"step": 4350
|
| 545 |
+
},
|
| 546 |
+
{
|
| 547 |
+
"epoch": 1.95,
|
| 548 |
+
"learning_rate": 0.00019546868058640607,
|
| 549 |
+
"loss": 0.5505,
|
| 550 |
+
"step": 4400
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 1.98,
|
| 554 |
+
"learning_rate": 0.00019768991559306976,
|
| 555 |
+
"loss": 0.5574,
|
| 556 |
+
"step": 4450
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 2.0,
|
| 560 |
+
"learning_rate": 0.00019991115059973347,
|
| 561 |
+
"loss": 0.5967,
|
| 562 |
+
"step": 4500
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 2.0,
|
| 566 |
+
"eval_accuracy": 0.7350662334416396,
|
| 567 |
+
"eval_auc": 0.7735341764853124,
|
| 568 |
+
"eval_f1": 0.8107142857142857,
|
| 569 |
+
"eval_loss": 0.538005530834198,
|
| 570 |
+
"eval_precision": 0.7091533895657607,
|
| 571 |
+
"eval_recall": 0.9462275948311797,
|
| 572 |
+
"eval_runtime": 41.5742,
|
| 573 |
+
"eval_samples_per_second": 96.237,
|
| 574 |
+
"eval_steps_per_second": 3.031,
|
| 575 |
+
"step": 4502
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 2.02,
|
| 579 |
+
"learning_rate": 0.00019976306826595587,
|
| 580 |
+
"loss": 0.5831,
|
| 581 |
+
"step": 4550
|
| 582 |
+
},
|
| 583 |
+
{
|
| 584 |
+
"epoch": 2.04,
|
| 585 |
+
"learning_rate": 0.00019951626437632658,
|
| 586 |
+
"loss": 0.5602,
|
| 587 |
+
"step": 4600
|
| 588 |
+
},
|
| 589 |
+
{
|
| 590 |
+
"epoch": 2.07,
|
| 591 |
+
"learning_rate": 0.00019926946048669727,
|
| 592 |
+
"loss": 0.5629,
|
| 593 |
+
"step": 4650
|
| 594 |
+
},
|
| 595 |
+
{
|
| 596 |
+
"epoch": 2.09,
|
| 597 |
+
"learning_rate": 0.00019902265659706798,
|
| 598 |
+
"loss": 0.5841,
|
| 599 |
+
"step": 4700
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 2.11,
|
| 603 |
+
"learning_rate": 0.00019877585270743867,
|
| 604 |
+
"loss": 0.5748,
|
| 605 |
+
"step": 4750
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 2.13,
|
| 609 |
+
"learning_rate": 0.00019852904881780938,
|
| 610 |
+
"loss": 0.5731,
|
| 611 |
+
"step": 4800
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 2.15,
|
| 615 |
+
"learning_rate": 0.00019828224492818007,
|
| 616 |
+
"loss": 0.5691,
|
| 617 |
+
"step": 4850
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 2.18,
|
| 621 |
+
"learning_rate": 0.00019803544103855078,
|
| 622 |
+
"loss": 0.5793,
|
| 623 |
+
"step": 4900
|
| 624 |
+
},
|
| 625 |
+
{
|
| 626 |
+
"epoch": 2.2,
|
| 627 |
+
"learning_rate": 0.0001977886371489215,
|
| 628 |
+
"loss": 0.548,
|
| 629 |
+
"step": 4950
|
| 630 |
+
},
|
| 631 |
+
{
|
| 632 |
+
"epoch": 2.22,
|
| 633 |
+
"learning_rate": 0.00019754183325929218,
|
| 634 |
+
"loss": 0.5688,
|
| 635 |
+
"step": 5000
|
| 636 |
+
},
|
| 637 |
+
{
|
| 638 |
+
"epoch": 2.24,
|
| 639 |
+
"learning_rate": 0.00019729502936966287,
|
| 640 |
+
"loss": 0.5533,
|
| 641 |
+
"step": 5050
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 2.27,
|
| 645 |
+
"learning_rate": 0.00019704822548003356,
|
| 646 |
+
"loss": 0.5733,
|
| 647 |
+
"step": 5100
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 2.29,
|
| 651 |
+
"learning_rate": 0.00019680142159040427,
|
| 652 |
+
"loss": 0.5382,
|
| 653 |
+
"step": 5150
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 2.31,
|
| 657 |
+
"learning_rate": 0.00019655461770077496,
|
| 658 |
+
"loss": 0.5636,
|
| 659 |
+
"step": 5200
|
| 660 |
+
},
|
| 661 |
+
{
|
| 662 |
+
"epoch": 2.33,
|
| 663 |
+
"learning_rate": 0.00019630781381114567,
|
| 664 |
+
"loss": 0.5499,
|
| 665 |
+
"step": 5250
|
| 666 |
+
},
|
| 667 |
+
{
|
| 668 |
+
"epoch": 2.35,
|
| 669 |
+
"learning_rate": 0.00019606100992151636,
|
| 670 |
+
"loss": 0.5729,
|
| 671 |
+
"step": 5300
|
| 672 |
+
},
|
| 673 |
+
{
|
| 674 |
+
"epoch": 2.38,
|
| 675 |
+
"learning_rate": 0.00019581420603188707,
|
| 676 |
+
"loss": 0.5723,
|
| 677 |
+
"step": 5350
|
| 678 |
+
},
|
| 679 |
+
{
|
| 680 |
+
"epoch": 2.4,
|
| 681 |
+
"learning_rate": 0.00019556740214225776,
|
| 682 |
+
"loss": 0.5568,
|
| 683 |
+
"step": 5400
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 2.42,
|
| 687 |
+
"learning_rate": 0.00019532059825262847,
|
| 688 |
+
"loss": 0.5702,
|
| 689 |
+
"step": 5450
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 2.44,
|
| 693 |
+
"learning_rate": 0.00019507379436299916,
|
| 694 |
+
"loss": 0.5658,
|
| 695 |
+
"step": 5500
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 2.47,
|
| 699 |
+
"learning_rate": 0.00019482699047336987,
|
| 700 |
+
"loss": 0.5605,
|
| 701 |
+
"step": 5550
|
| 702 |
+
},
|
| 703 |
+
{
|
| 704 |
+
"epoch": 2.49,
|
| 705 |
+
"learning_rate": 0.0001945801865837406,
|
| 706 |
+
"loss": 0.6323,
|
| 707 |
+
"step": 5600
|
| 708 |
+
},
|
| 709 |
+
{
|
| 710 |
+
"epoch": 2.51,
|
| 711 |
+
"learning_rate": 0.00019433338269411128,
|
| 712 |
+
"loss": 0.6038,
|
| 713 |
+
"step": 5650
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"epoch": 2.53,
|
| 717 |
+
"learning_rate": 0.000194086578804482,
|
| 718 |
+
"loss": 0.5493,
|
| 719 |
+
"step": 5700
|
| 720 |
+
},
|
| 721 |
+
{
|
| 722 |
+
"epoch": 2.55,
|
| 723 |
+
"learning_rate": 0.00019383977491485265,
|
| 724 |
+
"loss": 0.585,
|
| 725 |
+
"step": 5750
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 2.58,
|
| 729 |
+
"learning_rate": 0.00019359297102522336,
|
| 730 |
+
"loss": 0.601,
|
| 731 |
+
"step": 5800
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 2.6,
|
| 735 |
+
"learning_rate": 0.00019334616713559405,
|
| 736 |
+
"loss": 0.5556,
|
| 737 |
+
"step": 5850
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 2.62,
|
| 741 |
+
"learning_rate": 0.00019309936324596476,
|
| 742 |
+
"loss": 0.5912,
|
| 743 |
+
"step": 5900
|
| 744 |
+
},
|
| 745 |
+
{
|
| 746 |
+
"epoch": 2.64,
|
| 747 |
+
"learning_rate": 0.00019285255935633545,
|
| 748 |
+
"loss": 0.5651,
|
| 749 |
+
"step": 5950
|
| 750 |
+
},
|
| 751 |
+
{
|
| 752 |
+
"epoch": 2.67,
|
| 753 |
+
"learning_rate": 0.00019260575546670616,
|
| 754 |
+
"loss": 0.5816,
|
| 755 |
+
"step": 6000
|
| 756 |
+
},
|
| 757 |
+
{
|
| 758 |
+
"epoch": 2.69,
|
| 759 |
+
"learning_rate": 0.00019235895157707685,
|
| 760 |
+
"loss": 0.5632,
|
| 761 |
+
"step": 6050
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 2.71,
|
| 765 |
+
"learning_rate": 0.00019211214768744756,
|
| 766 |
+
"loss": 0.5904,
|
| 767 |
+
"step": 6100
|
| 768 |
+
},
|
| 769 |
+
{
|
| 770 |
+
"epoch": 2.73,
|
| 771 |
+
"learning_rate": 0.00019186534379781825,
|
| 772 |
+
"loss": 0.5578,
|
| 773 |
+
"step": 6150
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 2.75,
|
| 777 |
+
"learning_rate": 0.00019161853990818897,
|
| 778 |
+
"loss": 0.5435,
|
| 779 |
+
"step": 6200
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 2.78,
|
| 783 |
+
"learning_rate": 0.00019137173601855968,
|
| 784 |
+
"loss": 0.5392,
|
| 785 |
+
"step": 6250
|
| 786 |
+
},
|
| 787 |
+
{
|
| 788 |
+
"epoch": 2.8,
|
| 789 |
+
"learning_rate": 0.00019112493212893037,
|
| 790 |
+
"loss": 0.5517,
|
| 791 |
+
"step": 6300
|
| 792 |
+
},
|
| 793 |
+
{
|
| 794 |
+
"epoch": 2.82,
|
| 795 |
+
"learning_rate": 0.00019087812823930108,
|
| 796 |
+
"loss": 0.5339,
|
| 797 |
+
"step": 6350
|
| 798 |
+
},
|
| 799 |
+
{
|
| 800 |
+
"epoch": 2.84,
|
| 801 |
+
"learning_rate": 0.00019063132434967177,
|
| 802 |
+
"loss": 0.5683,
|
| 803 |
+
"step": 6400
|
| 804 |
+
},
|
| 805 |
+
{
|
| 806 |
+
"epoch": 2.87,
|
| 807 |
+
"learning_rate": 0.00019038452046004248,
|
| 808 |
+
"loss": 0.5847,
|
| 809 |
+
"step": 6450
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"epoch": 2.89,
|
| 813 |
+
"learning_rate": 0.00019013771657041314,
|
| 814 |
+
"loss": 0.5245,
|
| 815 |
+
"step": 6500
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 2.91,
|
| 819 |
+
"learning_rate": 0.00018989091268078385,
|
| 820 |
+
"loss": 0.5635,
|
| 821 |
+
"step": 6550
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 2.93,
|
| 825 |
+
"learning_rate": 0.00018964410879115454,
|
| 826 |
+
"loss": 0.6235,
|
| 827 |
+
"step": 6600
|
| 828 |
+
},
|
| 829 |
+
{
|
| 830 |
+
"epoch": 2.95,
|
| 831 |
+
"learning_rate": 0.00018939730490152525,
|
| 832 |
+
"loss": 0.6038,
|
| 833 |
+
"step": 6650
|
| 834 |
+
},
|
| 835 |
+
{
|
| 836 |
+
"epoch": 2.98,
|
| 837 |
+
"learning_rate": 0.00018915050101189594,
|
| 838 |
+
"loss": 0.5759,
|
| 839 |
+
"step": 6700
|
| 840 |
+
},
|
| 841 |
+
{
|
| 842 |
+
"epoch": 3.0,
|
| 843 |
+
"learning_rate": 0.00018890369712226666,
|
| 844 |
+
"loss": 0.5875,
|
| 845 |
+
"step": 6750
|
| 846 |
+
},
|
| 847 |
+
{
|
| 848 |
+
"epoch": 3.0,
|
| 849 |
+
"eval_accuracy": 0.7370657335666083,
|
| 850 |
+
"eval_auc": 0.7775605108037629,
|
| 851 |
+
"eval_f1": 0.7994662600076249,
|
| 852 |
+
"eval_loss": 0.5398992896080017,
|
| 853 |
+
"eval_precision": 0.7365648050579557,
|
| 854 |
+
"eval_recall": 0.8741142142559399,
|
| 855 |
+
"eval_runtime": 41.6653,
|
| 856 |
+
"eval_samples_per_second": 96.027,
|
| 857 |
+
"eval_steps_per_second": 3.024,
|
| 858 |
+
"step": 6753
|
| 859 |
+
},
|
| 860 |
+
{
|
| 861 |
+
"epoch": 3.02,
|
| 862 |
+
"learning_rate": 0.00018865689323263734,
|
| 863 |
+
"loss": 0.5611,
|
| 864 |
+
"step": 6800
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 3.04,
|
| 868 |
+
"learning_rate": 0.00018841008934300806,
|
| 869 |
+
"loss": 0.5595,
|
| 870 |
+
"step": 6850
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 3.07,
|
| 874 |
+
"learning_rate": 0.00018816328545337877,
|
| 875 |
+
"loss": 0.5751,
|
| 876 |
+
"step": 6900
|
| 877 |
+
},
|
| 878 |
+
{
|
| 879 |
+
"epoch": 3.09,
|
| 880 |
+
"learning_rate": 0.00018791648156374946,
|
| 881 |
+
"loss": 0.5193,
|
| 882 |
+
"step": 6950
|
| 883 |
+
},
|
| 884 |
+
{
|
| 885 |
+
"epoch": 3.11,
|
| 886 |
+
"learning_rate": 0.00018766967767412017,
|
| 887 |
+
"loss": 0.5819,
|
| 888 |
+
"step": 7000
|
| 889 |
+
},
|
| 890 |
+
{
|
| 891 |
+
"epoch": 3.13,
|
| 892 |
+
"learning_rate": 0.00018742287378449086,
|
| 893 |
+
"loss": 0.5787,
|
| 894 |
+
"step": 7050
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"epoch": 3.15,
|
| 898 |
+
"learning_rate": 0.00018717606989486157,
|
| 899 |
+
"loss": 0.5745,
|
| 900 |
+
"step": 7100
|
| 901 |
+
},
|
| 902 |
+
{
|
| 903 |
+
"epoch": 3.18,
|
| 904 |
+
"learning_rate": 0.00018692926600523226,
|
| 905 |
+
"loss": 0.547,
|
| 906 |
+
"step": 7150
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 3.2,
|
| 910 |
+
"learning_rate": 0.00018668246211560294,
|
| 911 |
+
"loss": 0.5815,
|
| 912 |
+
"step": 7200
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 3.22,
|
| 916 |
+
"learning_rate": 0.00018643565822597363,
|
| 917 |
+
"loss": 0.5959,
|
| 918 |
+
"step": 7250
|
| 919 |
+
},
|
| 920 |
+
{
|
| 921 |
+
"epoch": 3.24,
|
| 922 |
+
"learning_rate": 0.00018618885433634435,
|
| 923 |
+
"loss": 0.592,
|
| 924 |
+
"step": 7300
|
| 925 |
+
},
|
| 926 |
+
{
|
| 927 |
+
"epoch": 3.27,
|
| 928 |
+
"learning_rate": 0.00018594205044671503,
|
| 929 |
+
"loss": 0.5862,
|
| 930 |
+
"step": 7350
|
| 931 |
+
},
|
| 932 |
+
{
|
| 933 |
+
"epoch": 3.29,
|
| 934 |
+
"learning_rate": 0.00018569524655708575,
|
| 935 |
+
"loss": 0.5563,
|
| 936 |
+
"step": 7400
|
| 937 |
+
},
|
| 938 |
+
{
|
| 939 |
+
"epoch": 3.31,
|
| 940 |
+
"learning_rate": 0.00018544844266745643,
|
| 941 |
+
"loss": 0.579,
|
| 942 |
+
"step": 7450
|
| 943 |
+
},
|
| 944 |
+
{
|
| 945 |
+
"epoch": 3.33,
|
| 946 |
+
"learning_rate": 0.00018520163877782715,
|
| 947 |
+
"loss": 0.5721,
|
| 948 |
+
"step": 7500
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 3.35,
|
| 952 |
+
"learning_rate": 0.00018495483488819786,
|
| 953 |
+
"loss": 0.5642,
|
| 954 |
+
"step": 7550
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 3.38,
|
| 958 |
+
"learning_rate": 0.00018470803099856855,
|
| 959 |
+
"loss": 0.5534,
|
| 960 |
+
"step": 7600
|
| 961 |
+
},
|
| 962 |
+
{
|
| 963 |
+
"epoch": 3.4,
|
| 964 |
+
"learning_rate": 0.00018446122710893926,
|
| 965 |
+
"loss": 0.524,
|
| 966 |
+
"step": 7650
|
| 967 |
+
},
|
| 968 |
+
{
|
| 969 |
+
"epoch": 3.42,
|
| 970 |
+
"learning_rate": 0.00018421442321930995,
|
| 971 |
+
"loss": 0.568,
|
| 972 |
+
"step": 7700
|
| 973 |
+
},
|
| 974 |
+
{
|
| 975 |
+
"epoch": 3.44,
|
| 976 |
+
"learning_rate": 0.00018396761932968066,
|
| 977 |
+
"loss": 0.5789,
|
| 978 |
+
"step": 7750
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"epoch": 3.47,
|
| 982 |
+
"learning_rate": 0.00018372081544005135,
|
| 983 |
+
"loss": 0.5812,
|
| 984 |
+
"step": 7800
|
| 985 |
+
},
|
| 986 |
+
{
|
| 987 |
+
"epoch": 3.49,
|
| 988 |
+
"learning_rate": 0.00018347401155042206,
|
| 989 |
+
"loss": 0.5782,
|
| 990 |
+
"step": 7850
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 3.51,
|
| 994 |
+
"learning_rate": 0.00018322720766079272,
|
| 995 |
+
"loss": 0.5679,
|
| 996 |
+
"step": 7900
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 3.53,
|
| 1000 |
+
"learning_rate": 0.00018298040377116344,
|
| 1001 |
+
"loss": 0.5817,
|
| 1002 |
+
"step": 7950
|
| 1003 |
+
},
|
| 1004 |
+
{
|
| 1005 |
+
"epoch": 3.55,
|
| 1006 |
+
"learning_rate": 0.00018273359988153412,
|
| 1007 |
+
"loss": 0.5484,
|
| 1008 |
+
"step": 8000
|
| 1009 |
+
},
|
| 1010 |
+
{
|
| 1011 |
+
"epoch": 3.58,
|
| 1012 |
+
"learning_rate": 0.00018248679599190484,
|
| 1013 |
+
"loss": 0.5233,
|
| 1014 |
+
"step": 8050
|
| 1015 |
+
},
|
| 1016 |
+
{
|
| 1017 |
+
"epoch": 3.6,
|
| 1018 |
+
"learning_rate": 0.00018223999210227552,
|
| 1019 |
+
"loss": 0.535,
|
| 1020 |
+
"step": 8100
|
| 1021 |
+
},
|
| 1022 |
+
{
|
| 1023 |
+
"epoch": 3.62,
|
| 1024 |
+
"learning_rate": 0.00018199318821264624,
|
| 1025 |
+
"loss": 0.5825,
|
| 1026 |
+
"step": 8150
|
| 1027 |
+
},
|
| 1028 |
+
{
|
| 1029 |
+
"epoch": 3.64,
|
| 1030 |
+
"learning_rate": 0.00018174638432301695,
|
| 1031 |
+
"loss": 0.5487,
|
| 1032 |
+
"step": 8200
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 3.67,
|
| 1036 |
+
"learning_rate": 0.00018149958043338764,
|
| 1037 |
+
"loss": 0.548,
|
| 1038 |
+
"step": 8250
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 3.69,
|
| 1042 |
+
"learning_rate": 0.00018125277654375835,
|
| 1043 |
+
"loss": 0.5602,
|
| 1044 |
+
"step": 8300
|
| 1045 |
+
},
|
| 1046 |
+
{
|
| 1047 |
+
"epoch": 3.71,
|
| 1048 |
+
"learning_rate": 0.00018100597265412904,
|
| 1049 |
+
"loss": 0.5478,
|
| 1050 |
+
"step": 8350
|
| 1051 |
+
},
|
| 1052 |
+
{
|
| 1053 |
+
"epoch": 3.73,
|
| 1054 |
+
"learning_rate": 0.00018075916876449975,
|
| 1055 |
+
"loss": 0.5554,
|
| 1056 |
+
"step": 8400
|
| 1057 |
+
},
|
| 1058 |
+
{
|
| 1059 |
+
"epoch": 3.75,
|
| 1060 |
+
"learning_rate": 0.00018051236487487044,
|
| 1061 |
+
"loss": 0.5672,
|
| 1062 |
+
"step": 8450
|
| 1063 |
+
},
|
| 1064 |
+
{
|
| 1065 |
+
"epoch": 3.78,
|
| 1066 |
+
"learning_rate": 0.00018026556098524115,
|
| 1067 |
+
"loss": 0.5194,
|
| 1068 |
+
"step": 8500
|
| 1069 |
+
},
|
| 1070 |
+
{
|
| 1071 |
+
"epoch": 3.8,
|
| 1072 |
+
"learning_rate": 0.00018001875709561184,
|
| 1073 |
+
"loss": 0.5669,
|
| 1074 |
+
"step": 8550
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 3.82,
|
| 1078 |
+
"learning_rate": 0.00017977195320598253,
|
| 1079 |
+
"loss": 0.5767,
|
| 1080 |
+
"step": 8600
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 3.84,
|
| 1084 |
+
"learning_rate": 0.0001795251493163532,
|
| 1085 |
+
"loss": 0.5537,
|
| 1086 |
+
"step": 8650
|
| 1087 |
+
},
|
| 1088 |
+
{
|
| 1089 |
+
"epoch": 3.86,
|
| 1090 |
+
"learning_rate": 0.00017927834542672393,
|
| 1091 |
+
"loss": 0.5375,
|
| 1092 |
+
"step": 8700
|
| 1093 |
+
},
|
| 1094 |
+
{
|
| 1095 |
+
"epoch": 3.89,
|
| 1096 |
+
"learning_rate": 0.00017903154153709461,
|
| 1097 |
+
"loss": 0.572,
|
| 1098 |
+
"step": 8750
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 3.91,
|
| 1102 |
+
"learning_rate": 0.00017878473764746533,
|
| 1103 |
+
"loss": 0.5709,
|
| 1104 |
+
"step": 8800
|
| 1105 |
+
},
|
| 1106 |
+
{
|
| 1107 |
+
"epoch": 3.93,
|
| 1108 |
+
"learning_rate": 0.00017853793375783604,
|
| 1109 |
+
"loss": 0.5643,
|
| 1110 |
+
"step": 8850
|
| 1111 |
+
},
|
| 1112 |
+
{
|
| 1113 |
+
"epoch": 3.95,
|
| 1114 |
+
"learning_rate": 0.00017829112986820673,
|
| 1115 |
+
"loss": 0.544,
|
| 1116 |
+
"step": 8900
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 3.98,
|
| 1120 |
+
"learning_rate": 0.00017804432597857744,
|
| 1121 |
+
"loss": 0.5689,
|
| 1122 |
+
"step": 8950
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 4.0,
|
| 1126 |
+
"learning_rate": 0.00017779752208894813,
|
| 1127 |
+
"loss": 0.5413,
|
| 1128 |
+
"step": 9000
|
| 1129 |
+
},
|
| 1130 |
+
{
|
| 1131 |
+
"epoch": 4.0,
|
| 1132 |
+
"eval_accuracy": 0.749312671832042,
|
| 1133 |
+
"eval_auc": 0.7988417458585272,
|
| 1134 |
+
"eval_f1": 0.8211164615658998,
|
| 1135 |
+
"eval_loss": 0.5185230374336243,
|
| 1136 |
+
"eval_precision": 0.7175810473815462,
|
| 1137 |
+
"eval_recall": 0.9595664860358483,
|
| 1138 |
+
"eval_runtime": 41.6672,
|
| 1139 |
+
"eval_samples_per_second": 96.023,
|
| 1140 |
+
"eval_steps_per_second": 3.024,
|
| 1141 |
+
"step": 9004
|
| 1142 |
+
}
|
| 1143 |
+
],
|
| 1144 |
+
"logging_steps": 50,
|
| 1145 |
+
"max_steps": 45020,
|
| 1146 |
+
"num_train_epochs": 20,
|
| 1147 |
+
"save_steps": 500,
|
| 1148 |
+
"total_flos": 1.1160086376335081e+19,
|
| 1149 |
+
"trial_name": null,
|
| 1150 |
+
"trial_params": null
|
| 1151 |
+
}
|
checkpoint-9004/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fadef8ae82ce160c2dbbd1209037da399f15640172741b0cda3900283d80d49e
|
| 3 |
+
size 4027
|
config.json
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "KhalfounMehdi/mura_vit_224",
|
| 3 |
+
"_num_labels": 2,
|
| 4 |
+
"architectures": [
|
| 5 |
+
"ViTForImageClassification"
|
| 6 |
+
],
|
| 7 |
+
"attention_probs_dropout_prob": 0.0,
|
| 8 |
+
"encoder_stride": 16,
|
| 9 |
+
"hidden_act": "gelu",
|
| 10 |
+
"hidden_dropout_prob": 0.0,
|
| 11 |
+
"hidden_size": 768,
|
| 12 |
+
"id2label": {
|
| 13 |
+
"0": "abnormal",
|
| 14 |
+
"1": "normal"
|
| 15 |
+
},
|
| 16 |
+
"image_size": 224,
|
| 17 |
+
"initializer_range": 0.02,
|
| 18 |
+
"intermediate_size": 3072,
|
| 19 |
+
"label2id": {
|
| 20 |
+
"abnormal": 0,
|
| 21 |
+
"normal": 1
|
| 22 |
+
},
|
| 23 |
+
"layer_norm_eps": 1e-12,
|
| 24 |
+
"model_type": "vit",
|
| 25 |
+
"num_attention_heads": 12,
|
| 26 |
+
"num_channels": 3,
|
| 27 |
+
"num_hidden_layers": 12,
|
| 28 |
+
"patch_size": 16,
|
| 29 |
+
"problem_type": "single_label_classification",
|
| 30 |
+
"qkv_bias": true,
|
| 31 |
+
"torch_dtype": "float32",
|
| 32 |
+
"transformers_version": "4.33.0.dev0"
|
| 33 |
+
}
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_normalize": true,
|
| 3 |
+
"do_rescale": true,
|
| 4 |
+
"do_resize": true,
|
| 5 |
+
"image_mean": [
|
| 6 |
+
0.5,
|
| 7 |
+
0.5,
|
| 8 |
+
0.5
|
| 9 |
+
],
|
| 10 |
+
"image_processor_type": "ViTImageProcessor",
|
| 11 |
+
"image_std": [
|
| 12 |
+
0.5,
|
| 13 |
+
0.5,
|
| 14 |
+
0.5
|
| 15 |
+
],
|
| 16 |
+
"resample": 2,
|
| 17 |
+
"rescale_factor": 0.00392156862745098,
|
| 18 |
+
"size": {
|
| 19 |
+
"height": 224,
|
| 20 |
+
"width": 224
|
| 21 |
+
}
|
| 22 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2aa275df102c4055478fea67c20c37edd7e84655990d4ee849cbdb9ccc94661d
|
| 3 |
+
size 343268717
|
runs/Sep02_09-12-58_c3f9c2116fca/events.out.tfevents.1693645986.c3f9c2116fca.859.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f020f440cb61a8cd27a02c770ed0b3d0b3b101c08602b20cd5960d8a19f3fae1
|
| 3 |
+
size 4273
|
runs/Sep02_09-15-13_c3f9c2116fca/events.out.tfevents.1693646116.c3f9c2116fca.896.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:130fc610594fc9cdd607b05b520355b800987bbd7b45eb9ecf79abba8af8899f
|
| 3 |
+
size 22507
|
runs/Sep02_10-08-26_c3f9c2116fca/events.out.tfevents.1693649310.c3f9c2116fca.1017.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4a2169c95aa17fca49578fcb5335a975b059cab3bcf51e0ac05343109a635ea7
|
| 3 |
+
size 34890
|
runs/Sep02_10-08-26_c3f9c2116fca/events.out.tfevents.1693653026.c3f9c2116fca.1017.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6792f7f413055a52bcfef66b26b3beba76f91f403beb457f2111e9af0fd334fb
|
| 3 |
+
size 607
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fadef8ae82ce160c2dbbd1209037da399f15640172741b0cda3900283d80d49e
|
| 3 |
+
size 4027
|
training_params.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"data_path": "KhalfounMehdi/mura_dataset_processed_224px_train_val",
|
| 3 |
+
"model_name": "KhalfounMehdi/mura_vit_224",
|
| 4 |
+
"lr": 0.0002,
|
| 5 |
+
"epochs": 20,
|
| 6 |
+
"batch_size": 16,
|
| 7 |
+
"warmup_ratio": 0.1,
|
| 8 |
+
"gradient_accumulation": 1,
|
| 9 |
+
"optimizer": "adamw_torch",
|
| 10 |
+
"scheduler": "linear",
|
| 11 |
+
"weight_decay": 0.0,
|
| 12 |
+
"max_grad_norm": 1.0,
|
| 13 |
+
"seed": 42,
|
| 14 |
+
"train_split": "train",
|
| 15 |
+
"valid_split": "validation",
|
| 16 |
+
"logging_steps": -1,
|
| 17 |
+
"project_name": "mura_vit_224_10ep",
|
| 18 |
+
"auto_find_batch_size": false,
|
| 19 |
+
"fp16": false,
|
| 20 |
+
"save_total_limit": 1,
|
| 21 |
+
"save_strategy": "epoch",
|
| 22 |
+
"token": null,
|
| 23 |
+
"push_to_hub": true,
|
| 24 |
+
"repo_id": "KhalfounMehdi/vit_musculoskeletal_abnormality_detection_mura_224px_16bs_20ep",
|
| 25 |
+
"evaluation_strategy": "epoch",
|
| 26 |
+
"image_column": "image",
|
| 27 |
+
"target_column": "label"
|
| 28 |
+
}
|