Upload folder using huggingface_hub
Browse files- README.md +31 -0
- checkpoint-240/config.json +50 -0
- checkpoint-240/model.safetensors +3 -0
- checkpoint-240/optimizer.pt +3 -0
- checkpoint-240/rng_state.pth +3 -0
- checkpoint-240/scheduler.pt +3 -0
- checkpoint-240/trainer_state.json +2112 -0
- checkpoint-240/training_args.bin +3 -0
- config.json +50 -0
- model.safetensors +3 -0
- preprocessor_config.json +22 -0
- runs/Aug17_22-05-12_tufta/events.out.tfevents.1723946712.tufta.52761.0 +2 -2
- runs/Aug17_22-05-12_tufta/events.out.tfevents.1723947259.tufta.52761.1 +3 -0
- training_args.bin +3 -0
- training_params.json +29 -0
README.md
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
|
| 2 |
+
---
|
| 3 |
+
tags:
|
| 4 |
+
- autotrain
|
| 5 |
+
- image-classification
|
| 6 |
+
base_model: microsoft/resnet-50
|
| 7 |
+
widget:
|
| 8 |
+
- src: https://huggingface.co/datasets/mishig/sample_images/resolve/main/tiger.jpg
|
| 9 |
+
example_title: Tiger
|
| 10 |
+
- src: https://huggingface.co/datasets/mishig/sample_images/resolve/main/teapot.jpg
|
| 11 |
+
example_title: Teapot
|
| 12 |
+
- src: https://huggingface.co/datasets/mishig/sample_images/resolve/main/palace.jpg
|
| 13 |
+
example_title: Palace
|
| 14 |
+
---
|
| 15 |
+
|
| 16 |
+
# Model Trained Using AutoTrain
|
| 17 |
+
|
| 18 |
+
- Problem type: Image Classification
|
| 19 |
+
|
| 20 |
+
## Validation Metrics
|
| 21 |
+
loss: 0.5722106695175171
|
| 22 |
+
|
| 23 |
+
f1: 0.735632183908046
|
| 24 |
+
|
| 25 |
+
precision: 0.6037735849056604
|
| 26 |
+
|
| 27 |
+
recall: 0.9411764705882353
|
| 28 |
+
|
| 29 |
+
auc: 0.8161764705882353
|
| 30 |
+
|
| 31 |
+
accuracy: 0.6290322580645161
|
checkpoint-240/config.json
ADDED
|
@@ -0,0 +1,50 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "microsoft/resnet-50",
|
| 3 |
+
"_num_labels": 2,
|
| 4 |
+
"architectures": [
|
| 5 |
+
"ResNetForImageClassification"
|
| 6 |
+
],
|
| 7 |
+
"depths": [
|
| 8 |
+
3,
|
| 9 |
+
4,
|
| 10 |
+
6,
|
| 11 |
+
3
|
| 12 |
+
],
|
| 13 |
+
"downsample_in_bottleneck": false,
|
| 14 |
+
"downsample_in_first_stage": false,
|
| 15 |
+
"embedding_size": 64,
|
| 16 |
+
"hidden_act": "relu",
|
| 17 |
+
"hidden_sizes": [
|
| 18 |
+
256,
|
| 19 |
+
512,
|
| 20 |
+
1024,
|
| 21 |
+
2048
|
| 22 |
+
],
|
| 23 |
+
"id2label": {
|
| 24 |
+
"0": "no",
|
| 25 |
+
"1": "yes"
|
| 26 |
+
},
|
| 27 |
+
"label2id": {
|
| 28 |
+
"no": 0,
|
| 29 |
+
"yes": 1
|
| 30 |
+
},
|
| 31 |
+
"layer_type": "bottleneck",
|
| 32 |
+
"model_type": "resnet",
|
| 33 |
+
"num_channels": 3,
|
| 34 |
+
"out_features": [
|
| 35 |
+
"stage4"
|
| 36 |
+
],
|
| 37 |
+
"out_indices": [
|
| 38 |
+
4
|
| 39 |
+
],
|
| 40 |
+
"problem_type": "single_label_classification",
|
| 41 |
+
"stage_names": [
|
| 42 |
+
"stem",
|
| 43 |
+
"stage1",
|
| 44 |
+
"stage2",
|
| 45 |
+
"stage3",
|
| 46 |
+
"stage4"
|
| 47 |
+
],
|
| 48 |
+
"torch_dtype": "float32",
|
| 49 |
+
"transformers_version": "4.44.0"
|
| 50 |
+
}
|
checkpoint-240/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c6c6678a7274fb49e5b5ede268a85d8f38c72aeabf3712bc5b538679fb32de93
|
| 3 |
+
size 94302952
|
checkpoint-240/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:deb4fb7af6c00d51f2c142b480dfdc50f02749fe68e5ebc79c8f0c426541f447
|
| 3 |
+
size 188232506
|
checkpoint-240/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fa86a953624f05ce5c6d8e5f224346a30acee2db1d51b77d73c616b4eb1f610f
|
| 3 |
+
size 14244
|
checkpoint-240/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:31bd3a7c043a920fa9d42d76ca7177ae7305d5080d4499e4cc88437da95cab4c
|
| 3 |
+
size 1064
|
checkpoint-240/trainer_state.json
ADDED
|
@@ -0,0 +1,2112 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.5722106695175171,
|
| 3 |
+
"best_model_checkpoint": "prostate-mri-T2w-v02/checkpoint-240",
|
| 4 |
+
"epoch": 30.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 240,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.125,
|
| 13 |
+
"grad_norm": 5.07865571975708,
|
| 14 |
+
"learning_rate": 1.25e-06,
|
| 15 |
+
"loss": 0.6886,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.25,
|
| 20 |
+
"grad_norm": 3.828888177871704,
|
| 21 |
+
"learning_rate": 2.5e-06,
|
| 22 |
+
"loss": 0.6783,
|
| 23 |
+
"step": 2
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.375,
|
| 27 |
+
"grad_norm": 3.864379644393921,
|
| 28 |
+
"learning_rate": 3.75e-06,
|
| 29 |
+
"loss": 0.6866,
|
| 30 |
+
"step": 3
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.5,
|
| 34 |
+
"grad_norm": 4.327669620513916,
|
| 35 |
+
"learning_rate": 5e-06,
|
| 36 |
+
"loss": 0.6936,
|
| 37 |
+
"step": 4
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.625,
|
| 41 |
+
"grad_norm": 3.5544910430908203,
|
| 42 |
+
"learning_rate": 6.25e-06,
|
| 43 |
+
"loss": 0.7003,
|
| 44 |
+
"step": 5
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.75,
|
| 48 |
+
"grad_norm": 7.40487813949585,
|
| 49 |
+
"learning_rate": 7.5e-06,
|
| 50 |
+
"loss": 0.6924,
|
| 51 |
+
"step": 6
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.875,
|
| 55 |
+
"grad_norm": 5.0727972984313965,
|
| 56 |
+
"learning_rate": 8.75e-06,
|
| 57 |
+
"loss": 0.6835,
|
| 58 |
+
"step": 7
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 1.0,
|
| 62 |
+
"grad_norm": 5.4314188957214355,
|
| 63 |
+
"learning_rate": 1e-05,
|
| 64 |
+
"loss": 0.6976,
|
| 65 |
+
"step": 8
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 1.0,
|
| 69 |
+
"eval_accuracy": 0.41935483870967744,
|
| 70 |
+
"eval_auc": 0.3960084033613446,
|
| 71 |
+
"eval_f1": 0.55,
|
| 72 |
+
"eval_loss": 0.6989667415618896,
|
| 73 |
+
"eval_precision": 0.4782608695652174,
|
| 74 |
+
"eval_recall": 0.6470588235294118,
|
| 75 |
+
"eval_runtime": 1.0166,
|
| 76 |
+
"eval_samples_per_second": 60.987,
|
| 77 |
+
"eval_steps_per_second": 0.984,
|
| 78 |
+
"step": 8
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 1.125,
|
| 82 |
+
"grad_norm": 6.988642692565918,
|
| 83 |
+
"learning_rate": 1.125e-05,
|
| 84 |
+
"loss": 0.6868,
|
| 85 |
+
"step": 9
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"epoch": 1.25,
|
| 89 |
+
"grad_norm": 6.287717342376709,
|
| 90 |
+
"learning_rate": 1.25e-05,
|
| 91 |
+
"loss": 0.6914,
|
| 92 |
+
"step": 10
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 1.375,
|
| 96 |
+
"grad_norm": 4.172554016113281,
|
| 97 |
+
"learning_rate": 1.3750000000000002e-05,
|
| 98 |
+
"loss": 0.6914,
|
| 99 |
+
"step": 11
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 1.5,
|
| 103 |
+
"grad_norm": 4.629329681396484,
|
| 104 |
+
"learning_rate": 1.5e-05,
|
| 105 |
+
"loss": 0.6975,
|
| 106 |
+
"step": 12
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 1.625,
|
| 110 |
+
"grad_norm": 2.8630337715148926,
|
| 111 |
+
"learning_rate": 1.6250000000000002e-05,
|
| 112 |
+
"loss": 0.6849,
|
| 113 |
+
"step": 13
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 1.75,
|
| 117 |
+
"grad_norm": 4.219947338104248,
|
| 118 |
+
"learning_rate": 1.75e-05,
|
| 119 |
+
"loss": 0.6846,
|
| 120 |
+
"step": 14
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 1.875,
|
| 124 |
+
"grad_norm": 6.524469375610352,
|
| 125 |
+
"learning_rate": 1.8750000000000002e-05,
|
| 126 |
+
"loss": 0.6821,
|
| 127 |
+
"step": 15
|
| 128 |
+
},
|
| 129 |
+
{
|
| 130 |
+
"epoch": 2.0,
|
| 131 |
+
"grad_norm": 7.466086387634277,
|
| 132 |
+
"learning_rate": 2e-05,
|
| 133 |
+
"loss": 0.7024,
|
| 134 |
+
"step": 16
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 2.0,
|
| 138 |
+
"eval_accuracy": 0.45161290322580644,
|
| 139 |
+
"eval_auc": 0.4338235294117647,
|
| 140 |
+
"eval_f1": 0.5641025641025641,
|
| 141 |
+
"eval_loss": 0.6980215311050415,
|
| 142 |
+
"eval_precision": 0.5,
|
| 143 |
+
"eval_recall": 0.6470588235294118,
|
| 144 |
+
"eval_runtime": 0.9794,
|
| 145 |
+
"eval_samples_per_second": 63.306,
|
| 146 |
+
"eval_steps_per_second": 1.021,
|
| 147 |
+
"step": 16
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 2.125,
|
| 151 |
+
"grad_norm": 4.021885871887207,
|
| 152 |
+
"learning_rate": 2.125e-05,
|
| 153 |
+
"loss": 0.6912,
|
| 154 |
+
"step": 17
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 2.25,
|
| 158 |
+
"grad_norm": 4.557158946990967,
|
| 159 |
+
"learning_rate": 2.25e-05,
|
| 160 |
+
"loss": 0.6799,
|
| 161 |
+
"step": 18
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 2.375,
|
| 165 |
+
"grad_norm": 5.540194034576416,
|
| 166 |
+
"learning_rate": 2.375e-05,
|
| 167 |
+
"loss": 0.6875,
|
| 168 |
+
"step": 19
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 2.5,
|
| 172 |
+
"grad_norm": 4.831681251525879,
|
| 173 |
+
"learning_rate": 2.5e-05,
|
| 174 |
+
"loss": 0.6932,
|
| 175 |
+
"step": 20
|
| 176 |
+
},
|
| 177 |
+
{
|
| 178 |
+
"epoch": 2.625,
|
| 179 |
+
"grad_norm": 4.978184700012207,
|
| 180 |
+
"learning_rate": 2.625e-05,
|
| 181 |
+
"loss": 0.6936,
|
| 182 |
+
"step": 21
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 2.75,
|
| 186 |
+
"grad_norm": 5.5205183029174805,
|
| 187 |
+
"learning_rate": 2.7500000000000004e-05,
|
| 188 |
+
"loss": 0.6938,
|
| 189 |
+
"step": 22
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 2.875,
|
| 193 |
+
"grad_norm": 3.865920066833496,
|
| 194 |
+
"learning_rate": 2.8749999999999997e-05,
|
| 195 |
+
"loss": 0.6843,
|
| 196 |
+
"step": 23
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 3.0,
|
| 200 |
+
"grad_norm": 4.337780952453613,
|
| 201 |
+
"learning_rate": 3e-05,
|
| 202 |
+
"loss": 0.6928,
|
| 203 |
+
"step": 24
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 3.0,
|
| 207 |
+
"eval_accuracy": 0.43548387096774194,
|
| 208 |
+
"eval_auc": 0.4495798319327731,
|
| 209 |
+
"eval_f1": 0.5569620253164557,
|
| 210 |
+
"eval_loss": 0.6971396803855896,
|
| 211 |
+
"eval_precision": 0.4888888888888889,
|
| 212 |
+
"eval_recall": 0.6470588235294118,
|
| 213 |
+
"eval_runtime": 0.9879,
|
| 214 |
+
"eval_samples_per_second": 62.76,
|
| 215 |
+
"eval_steps_per_second": 1.012,
|
| 216 |
+
"step": 24
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 3.125,
|
| 220 |
+
"grad_norm": 4.5307183265686035,
|
| 221 |
+
"learning_rate": 3.125e-05,
|
| 222 |
+
"loss": 0.6832,
|
| 223 |
+
"step": 25
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 3.25,
|
| 227 |
+
"grad_norm": 5.817195415496826,
|
| 228 |
+
"learning_rate": 3.2500000000000004e-05,
|
| 229 |
+
"loss": 0.6974,
|
| 230 |
+
"step": 26
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 3.375,
|
| 234 |
+
"grad_norm": 5.624639987945557,
|
| 235 |
+
"learning_rate": 3.375000000000001e-05,
|
| 236 |
+
"loss": 0.6887,
|
| 237 |
+
"step": 27
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 3.5,
|
| 241 |
+
"grad_norm": 3.9034228324890137,
|
| 242 |
+
"learning_rate": 3.5e-05,
|
| 243 |
+
"loss": 0.6785,
|
| 244 |
+
"step": 28
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"epoch": 3.625,
|
| 248 |
+
"grad_norm": 4.566128253936768,
|
| 249 |
+
"learning_rate": 3.625e-05,
|
| 250 |
+
"loss": 0.7015,
|
| 251 |
+
"step": 29
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 3.75,
|
| 255 |
+
"grad_norm": 6.583543300628662,
|
| 256 |
+
"learning_rate": 3.7500000000000003e-05,
|
| 257 |
+
"loss": 0.702,
|
| 258 |
+
"step": 30
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 3.875,
|
| 262 |
+
"grad_norm": 7.036752700805664,
|
| 263 |
+
"learning_rate": 3.875e-05,
|
| 264 |
+
"loss": 0.6927,
|
| 265 |
+
"step": 31
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 4.0,
|
| 269 |
+
"grad_norm": 5.107030868530273,
|
| 270 |
+
"learning_rate": 4e-05,
|
| 271 |
+
"loss": 0.6653,
|
| 272 |
+
"step": 32
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 4.0,
|
| 276 |
+
"eval_accuracy": 0.4838709677419355,
|
| 277 |
+
"eval_auc": 0.4852941176470588,
|
| 278 |
+
"eval_f1": 0.5675675675675675,
|
| 279 |
+
"eval_loss": 0.6967616677284241,
|
| 280 |
+
"eval_precision": 0.525,
|
| 281 |
+
"eval_recall": 0.6176470588235294,
|
| 282 |
+
"eval_runtime": 0.991,
|
| 283 |
+
"eval_samples_per_second": 62.566,
|
| 284 |
+
"eval_steps_per_second": 1.009,
|
| 285 |
+
"step": 32
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 4.125,
|
| 289 |
+
"grad_norm": 4.981570243835449,
|
| 290 |
+
"learning_rate": 4.125e-05,
|
| 291 |
+
"loss": 0.7017,
|
| 292 |
+
"step": 33
|
| 293 |
+
},
|
| 294 |
+
{
|
| 295 |
+
"epoch": 4.25,
|
| 296 |
+
"grad_norm": 3.622739315032959,
|
| 297 |
+
"learning_rate": 4.25e-05,
|
| 298 |
+
"loss": 0.6758,
|
| 299 |
+
"step": 34
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 4.375,
|
| 303 |
+
"grad_norm": 5.434995651245117,
|
| 304 |
+
"learning_rate": 4.375e-05,
|
| 305 |
+
"loss": 0.6968,
|
| 306 |
+
"step": 35
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 4.5,
|
| 310 |
+
"grad_norm": 4.017066955566406,
|
| 311 |
+
"learning_rate": 4.5e-05,
|
| 312 |
+
"loss": 0.683,
|
| 313 |
+
"step": 36
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 4.625,
|
| 317 |
+
"grad_norm": 4.787411689758301,
|
| 318 |
+
"learning_rate": 4.6250000000000006e-05,
|
| 319 |
+
"loss": 0.6764,
|
| 320 |
+
"step": 37
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 4.75,
|
| 324 |
+
"grad_norm": 4.249538421630859,
|
| 325 |
+
"learning_rate": 4.75e-05,
|
| 326 |
+
"loss": 0.6991,
|
| 327 |
+
"step": 38
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 4.875,
|
| 331 |
+
"grad_norm": 5.653696060180664,
|
| 332 |
+
"learning_rate": 4.875e-05,
|
| 333 |
+
"loss": 0.6885,
|
| 334 |
+
"step": 39
|
| 335 |
+
},
|
| 336 |
+
{
|
| 337 |
+
"epoch": 5.0,
|
| 338 |
+
"grad_norm": 5.200787544250488,
|
| 339 |
+
"learning_rate": 5e-05,
|
| 340 |
+
"loss": 0.6848,
|
| 341 |
+
"step": 40
|
| 342 |
+
},
|
| 343 |
+
{
|
| 344 |
+
"epoch": 5.0,
|
| 345 |
+
"eval_accuracy": 0.5161290322580645,
|
| 346 |
+
"eval_auc": 0.5399159663865546,
|
| 347 |
+
"eval_f1": 0.6511627906976745,
|
| 348 |
+
"eval_loss": 0.6903982758522034,
|
| 349 |
+
"eval_precision": 0.5384615384615384,
|
| 350 |
+
"eval_recall": 0.8235294117647058,
|
| 351 |
+
"eval_runtime": 1.005,
|
| 352 |
+
"eval_samples_per_second": 61.689,
|
| 353 |
+
"eval_steps_per_second": 0.995,
|
| 354 |
+
"step": 40
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 5.125,
|
| 358 |
+
"grad_norm": 4.032499313354492,
|
| 359 |
+
"learning_rate": 4.986111111111111e-05,
|
| 360 |
+
"loss": 0.6794,
|
| 361 |
+
"step": 41
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 5.25,
|
| 365 |
+
"grad_norm": 4.394955158233643,
|
| 366 |
+
"learning_rate": 4.972222222222223e-05,
|
| 367 |
+
"loss": 0.673,
|
| 368 |
+
"step": 42
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 5.375,
|
| 372 |
+
"grad_norm": 5.790032863616943,
|
| 373 |
+
"learning_rate": 4.958333333333334e-05,
|
| 374 |
+
"loss": 0.6969,
|
| 375 |
+
"step": 43
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 5.5,
|
| 379 |
+
"grad_norm": 4.156627178192139,
|
| 380 |
+
"learning_rate": 4.9444444444444446e-05,
|
| 381 |
+
"loss": 0.6853,
|
| 382 |
+
"step": 44
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 5.625,
|
| 386 |
+
"grad_norm": 3.0575897693634033,
|
| 387 |
+
"learning_rate": 4.930555555555556e-05,
|
| 388 |
+
"loss": 0.6755,
|
| 389 |
+
"step": 45
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 5.75,
|
| 393 |
+
"grad_norm": 4.219117641448975,
|
| 394 |
+
"learning_rate": 4.9166666666666665e-05,
|
| 395 |
+
"loss": 0.6826,
|
| 396 |
+
"step": 46
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 5.875,
|
| 400 |
+
"grad_norm": 3.935350179672241,
|
| 401 |
+
"learning_rate": 4.902777777777778e-05,
|
| 402 |
+
"loss": 0.6813,
|
| 403 |
+
"step": 47
|
| 404 |
+
},
|
| 405 |
+
{
|
| 406 |
+
"epoch": 6.0,
|
| 407 |
+
"grad_norm": 4.679253578186035,
|
| 408 |
+
"learning_rate": 4.888888888888889e-05,
|
| 409 |
+
"loss": 0.6667,
|
| 410 |
+
"step": 48
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 6.0,
|
| 414 |
+
"eval_accuracy": 0.5645161290322581,
|
| 415 |
+
"eval_auc": 0.5215336134453782,
|
| 416 |
+
"eval_f1": 0.6966292134831461,
|
| 417 |
+
"eval_loss": 0.6905871033668518,
|
| 418 |
+
"eval_precision": 0.5636363636363636,
|
| 419 |
+
"eval_recall": 0.9117647058823529,
|
| 420 |
+
"eval_runtime": 1.0097,
|
| 421 |
+
"eval_samples_per_second": 61.407,
|
| 422 |
+
"eval_steps_per_second": 0.99,
|
| 423 |
+
"step": 48
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 6.125,
|
| 427 |
+
"grad_norm": 4.561873912811279,
|
| 428 |
+
"learning_rate": 4.875e-05,
|
| 429 |
+
"loss": 0.6643,
|
| 430 |
+
"step": 49
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 6.25,
|
| 434 |
+
"grad_norm": 4.74534797668457,
|
| 435 |
+
"learning_rate": 4.8611111111111115e-05,
|
| 436 |
+
"loss": 0.6741,
|
| 437 |
+
"step": 50
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 6.375,
|
| 441 |
+
"grad_norm": 3.879701614379883,
|
| 442 |
+
"learning_rate": 4.8472222222222224e-05,
|
| 443 |
+
"loss": 0.6821,
|
| 444 |
+
"step": 51
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 6.5,
|
| 448 |
+
"grad_norm": 5.187071800231934,
|
| 449 |
+
"learning_rate": 4.8333333333333334e-05,
|
| 450 |
+
"loss": 0.6826,
|
| 451 |
+
"step": 52
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 6.625,
|
| 455 |
+
"grad_norm": 3.905057668685913,
|
| 456 |
+
"learning_rate": 4.819444444444445e-05,
|
| 457 |
+
"loss": 0.6708,
|
| 458 |
+
"step": 53
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 6.75,
|
| 462 |
+
"grad_norm": 4.2086567878723145,
|
| 463 |
+
"learning_rate": 4.805555555555556e-05,
|
| 464 |
+
"loss": 0.6796,
|
| 465 |
+
"step": 54
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 6.875,
|
| 469 |
+
"grad_norm": 3.0969605445861816,
|
| 470 |
+
"learning_rate": 4.791666666666667e-05,
|
| 471 |
+
"loss": 0.668,
|
| 472 |
+
"step": 55
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 7.0,
|
| 476 |
+
"grad_norm": 9.05994987487793,
|
| 477 |
+
"learning_rate": 4.7777777777777784e-05,
|
| 478 |
+
"loss": 0.7063,
|
| 479 |
+
"step": 56
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 7.0,
|
| 483 |
+
"eval_accuracy": 0.5483870967741935,
|
| 484 |
+
"eval_auc": 0.6186974789915967,
|
| 485 |
+
"eval_f1": 0.7021276595744681,
|
| 486 |
+
"eval_loss": 0.6794354915618896,
|
| 487 |
+
"eval_precision": 0.55,
|
| 488 |
+
"eval_recall": 0.9705882352941176,
|
| 489 |
+
"eval_runtime": 1.0085,
|
| 490 |
+
"eval_samples_per_second": 61.479,
|
| 491 |
+
"eval_steps_per_second": 0.992,
|
| 492 |
+
"step": 56
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 7.125,
|
| 496 |
+
"grad_norm": 4.440723419189453,
|
| 497 |
+
"learning_rate": 4.7638888888888887e-05,
|
| 498 |
+
"loss": 0.6935,
|
| 499 |
+
"step": 57
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 7.25,
|
| 503 |
+
"grad_norm": 4.0728678703308105,
|
| 504 |
+
"learning_rate": 4.75e-05,
|
| 505 |
+
"loss": 0.6824,
|
| 506 |
+
"step": 58
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 7.375,
|
| 510 |
+
"grad_norm": 3.088693141937256,
|
| 511 |
+
"learning_rate": 4.736111111111111e-05,
|
| 512 |
+
"loss": 0.6808,
|
| 513 |
+
"step": 59
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 7.5,
|
| 517 |
+
"grad_norm": 3.818556547164917,
|
| 518 |
+
"learning_rate": 4.722222222222222e-05,
|
| 519 |
+
"loss": 0.6744,
|
| 520 |
+
"step": 60
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 7.625,
|
| 524 |
+
"grad_norm": 3.184988498687744,
|
| 525 |
+
"learning_rate": 4.708333333333334e-05,
|
| 526 |
+
"loss": 0.6768,
|
| 527 |
+
"step": 61
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 7.75,
|
| 531 |
+
"grad_norm": 4.454700946807861,
|
| 532 |
+
"learning_rate": 4.6944444444444446e-05,
|
| 533 |
+
"loss": 0.6506,
|
| 534 |
+
"step": 62
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 7.875,
|
| 538 |
+
"grad_norm": 4.876274108886719,
|
| 539 |
+
"learning_rate": 4.6805555555555556e-05,
|
| 540 |
+
"loss": 0.6422,
|
| 541 |
+
"step": 63
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 8.0,
|
| 545 |
+
"grad_norm": 5.91554069519043,
|
| 546 |
+
"learning_rate": 4.666666666666667e-05,
|
| 547 |
+
"loss": 0.6931,
|
| 548 |
+
"step": 64
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 8.0,
|
| 552 |
+
"eval_accuracy": 0.532258064516129,
|
| 553 |
+
"eval_auc": 0.6423319327731093,
|
| 554 |
+
"eval_f1": 0.6947368421052632,
|
| 555 |
+
"eval_loss": 0.6753401160240173,
|
| 556 |
+
"eval_precision": 0.5409836065573771,
|
| 557 |
+
"eval_recall": 0.9705882352941176,
|
| 558 |
+
"eval_runtime": 1.0222,
|
| 559 |
+
"eval_samples_per_second": 60.655,
|
| 560 |
+
"eval_steps_per_second": 0.978,
|
| 561 |
+
"step": 64
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 8.125,
|
| 565 |
+
"grad_norm": 4.071496486663818,
|
| 566 |
+
"learning_rate": 4.652777777777778e-05,
|
| 567 |
+
"loss": 0.6749,
|
| 568 |
+
"step": 65
|
| 569 |
+
},
|
| 570 |
+
{
|
| 571 |
+
"epoch": 8.25,
|
| 572 |
+
"grad_norm": 3.4611518383026123,
|
| 573 |
+
"learning_rate": 4.638888888888889e-05,
|
| 574 |
+
"loss": 0.6694,
|
| 575 |
+
"step": 66
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 8.375,
|
| 579 |
+
"grad_norm": 4.5895819664001465,
|
| 580 |
+
"learning_rate": 4.6250000000000006e-05,
|
| 581 |
+
"loss": 0.7015,
|
| 582 |
+
"step": 67
|
| 583 |
+
},
|
| 584 |
+
{
|
| 585 |
+
"epoch": 8.5,
|
| 586 |
+
"grad_norm": 4.686936855316162,
|
| 587 |
+
"learning_rate": 4.6111111111111115e-05,
|
| 588 |
+
"loss": 0.6787,
|
| 589 |
+
"step": 68
|
| 590 |
+
},
|
| 591 |
+
{
|
| 592 |
+
"epoch": 8.625,
|
| 593 |
+
"grad_norm": 3.401395320892334,
|
| 594 |
+
"learning_rate": 4.5972222222222225e-05,
|
| 595 |
+
"loss": 0.6926,
|
| 596 |
+
"step": 69
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 8.75,
|
| 600 |
+
"grad_norm": 3.536426544189453,
|
| 601 |
+
"learning_rate": 4.5833333333333334e-05,
|
| 602 |
+
"loss": 0.6627,
|
| 603 |
+
"step": 70
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 8.875,
|
| 607 |
+
"grad_norm": 3.778151750564575,
|
| 608 |
+
"learning_rate": 4.569444444444444e-05,
|
| 609 |
+
"loss": 0.6442,
|
| 610 |
+
"step": 71
|
| 611 |
+
},
|
| 612 |
+
{
|
| 613 |
+
"epoch": 9.0,
|
| 614 |
+
"grad_norm": 6.234261989593506,
|
| 615 |
+
"learning_rate": 4.555555555555556e-05,
|
| 616 |
+
"loss": 0.6523,
|
| 617 |
+
"step": 72
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 9.0,
|
| 621 |
+
"eval_accuracy": 0.5645161290322581,
|
| 622 |
+
"eval_auc": 0.7058823529411765,
|
| 623 |
+
"eval_f1": 0.7157894736842105,
|
| 624 |
+
"eval_loss": 0.6739227175712585,
|
| 625 |
+
"eval_precision": 0.5573770491803278,
|
| 626 |
+
"eval_recall": 1.0,
|
| 627 |
+
"eval_runtime": 1.0275,
|
| 628 |
+
"eval_samples_per_second": 60.343,
|
| 629 |
+
"eval_steps_per_second": 0.973,
|
| 630 |
+
"step": 72
|
| 631 |
+
},
|
| 632 |
+
{
|
| 633 |
+
"epoch": 9.125,
|
| 634 |
+
"grad_norm": 4.165038585662842,
|
| 635 |
+
"learning_rate": 4.541666666666667e-05,
|
| 636 |
+
"loss": 0.6514,
|
| 637 |
+
"step": 73
|
| 638 |
+
},
|
| 639 |
+
{
|
| 640 |
+
"epoch": 9.25,
|
| 641 |
+
"grad_norm": 3.8884994983673096,
|
| 642 |
+
"learning_rate": 4.527777777777778e-05,
|
| 643 |
+
"loss": 0.675,
|
| 644 |
+
"step": 74
|
| 645 |
+
},
|
| 646 |
+
{
|
| 647 |
+
"epoch": 9.375,
|
| 648 |
+
"grad_norm": 5.685192108154297,
|
| 649 |
+
"learning_rate": 4.5138888888888894e-05,
|
| 650 |
+
"loss": 0.6752,
|
| 651 |
+
"step": 75
|
| 652 |
+
},
|
| 653 |
+
{
|
| 654 |
+
"epoch": 9.5,
|
| 655 |
+
"grad_norm": 4.592513084411621,
|
| 656 |
+
"learning_rate": 4.5e-05,
|
| 657 |
+
"loss": 0.6677,
|
| 658 |
+
"step": 76
|
| 659 |
+
},
|
| 660 |
+
{
|
| 661 |
+
"epoch": 9.625,
|
| 662 |
+
"grad_norm": 5.494269371032715,
|
| 663 |
+
"learning_rate": 4.486111111111111e-05,
|
| 664 |
+
"loss": 0.6667,
|
| 665 |
+
"step": 77
|
| 666 |
+
},
|
| 667 |
+
{
|
| 668 |
+
"epoch": 9.75,
|
| 669 |
+
"grad_norm": 6.602809429168701,
|
| 670 |
+
"learning_rate": 4.472222222222223e-05,
|
| 671 |
+
"loss": 0.6628,
|
| 672 |
+
"step": 78
|
| 673 |
+
},
|
| 674 |
+
{
|
| 675 |
+
"epoch": 9.875,
|
| 676 |
+
"grad_norm": 3.7969062328338623,
|
| 677 |
+
"learning_rate": 4.458333333333334e-05,
|
| 678 |
+
"loss": 0.6672,
|
| 679 |
+
"step": 79
|
| 680 |
+
},
|
| 681 |
+
{
|
| 682 |
+
"epoch": 10.0,
|
| 683 |
+
"grad_norm": 5.1374335289001465,
|
| 684 |
+
"learning_rate": 4.4444444444444447e-05,
|
| 685 |
+
"loss": 0.7172,
|
| 686 |
+
"step": 80
|
| 687 |
+
},
|
| 688 |
+
{
|
| 689 |
+
"epoch": 10.0,
|
| 690 |
+
"eval_accuracy": 0.5645161290322581,
|
| 691 |
+
"eval_auc": 0.7053571428571429,
|
| 692 |
+
"eval_f1": 0.7157894736842105,
|
| 693 |
+
"eval_loss": 0.6663622856140137,
|
| 694 |
+
"eval_precision": 0.5573770491803278,
|
| 695 |
+
"eval_recall": 1.0,
|
| 696 |
+
"eval_runtime": 1.2564,
|
| 697 |
+
"eval_samples_per_second": 49.346,
|
| 698 |
+
"eval_steps_per_second": 0.796,
|
| 699 |
+
"step": 80
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 10.125,
|
| 703 |
+
"grad_norm": 3.1226301193237305,
|
| 704 |
+
"learning_rate": 4.4305555555555556e-05,
|
| 705 |
+
"loss": 0.7158,
|
| 706 |
+
"step": 81
|
| 707 |
+
},
|
| 708 |
+
{
|
| 709 |
+
"epoch": 10.25,
|
| 710 |
+
"grad_norm": 5.638371467590332,
|
| 711 |
+
"learning_rate": 4.4166666666666665e-05,
|
| 712 |
+
"loss": 0.6515,
|
| 713 |
+
"step": 82
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"epoch": 10.375,
|
| 717 |
+
"grad_norm": 4.971011638641357,
|
| 718 |
+
"learning_rate": 4.402777777777778e-05,
|
| 719 |
+
"loss": 0.6987,
|
| 720 |
+
"step": 83
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"epoch": 10.5,
|
| 724 |
+
"grad_norm": 4.76828145980835,
|
| 725 |
+
"learning_rate": 4.388888888888889e-05,
|
| 726 |
+
"loss": 0.688,
|
| 727 |
+
"step": 84
|
| 728 |
+
},
|
| 729 |
+
{
|
| 730 |
+
"epoch": 10.625,
|
| 731 |
+
"grad_norm": 5.02163028717041,
|
| 732 |
+
"learning_rate": 4.375e-05,
|
| 733 |
+
"loss": 0.6373,
|
| 734 |
+
"step": 85
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 10.75,
|
| 738 |
+
"grad_norm": 4.078597068786621,
|
| 739 |
+
"learning_rate": 4.3611111111111116e-05,
|
| 740 |
+
"loss": 0.6154,
|
| 741 |
+
"step": 86
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 10.875,
|
| 745 |
+
"grad_norm": 4.060718059539795,
|
| 746 |
+
"learning_rate": 4.3472222222222225e-05,
|
| 747 |
+
"loss": 0.6974,
|
| 748 |
+
"step": 87
|
| 749 |
+
},
|
| 750 |
+
{
|
| 751 |
+
"epoch": 11.0,
|
| 752 |
+
"grad_norm": 4.6225666999816895,
|
| 753 |
+
"learning_rate": 4.3333333333333334e-05,
|
| 754 |
+
"loss": 0.6635,
|
| 755 |
+
"step": 88
|
| 756 |
+
},
|
| 757 |
+
{
|
| 758 |
+
"epoch": 11.0,
|
| 759 |
+
"eval_accuracy": 0.5806451612903226,
|
| 760 |
+
"eval_auc": 0.6675420168067228,
|
| 761 |
+
"eval_f1": 0.723404255319149,
|
| 762 |
+
"eval_loss": 0.6652597188949585,
|
| 763 |
+
"eval_precision": 0.5666666666666667,
|
| 764 |
+
"eval_recall": 1.0,
|
| 765 |
+
"eval_runtime": 1.0222,
|
| 766 |
+
"eval_samples_per_second": 60.651,
|
| 767 |
+
"eval_steps_per_second": 0.978,
|
| 768 |
+
"step": 88
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 11.125,
|
| 772 |
+
"grad_norm": 4.226655006408691,
|
| 773 |
+
"learning_rate": 4.319444444444445e-05,
|
| 774 |
+
"loss": 0.6581,
|
| 775 |
+
"step": 89
|
| 776 |
+
},
|
| 777 |
+
{
|
| 778 |
+
"epoch": 11.25,
|
| 779 |
+
"grad_norm": 4.332324028015137,
|
| 780 |
+
"learning_rate": 4.305555555555556e-05,
|
| 781 |
+
"loss": 0.6258,
|
| 782 |
+
"step": 90
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"epoch": 11.375,
|
| 786 |
+
"grad_norm": 4.7362775802612305,
|
| 787 |
+
"learning_rate": 4.291666666666667e-05,
|
| 788 |
+
"loss": 0.6826,
|
| 789 |
+
"step": 91
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 11.5,
|
| 793 |
+
"grad_norm": 3.910616874694824,
|
| 794 |
+
"learning_rate": 4.277777777777778e-05,
|
| 795 |
+
"loss": 0.6767,
|
| 796 |
+
"step": 92
|
| 797 |
+
},
|
| 798 |
+
{
|
| 799 |
+
"epoch": 11.625,
|
| 800 |
+
"grad_norm": 3.6902244091033936,
|
| 801 |
+
"learning_rate": 4.263888888888889e-05,
|
| 802 |
+
"loss": 0.6954,
|
| 803 |
+
"step": 93
|
| 804 |
+
},
|
| 805 |
+
{
|
| 806 |
+
"epoch": 11.75,
|
| 807 |
+
"grad_norm": 6.192240238189697,
|
| 808 |
+
"learning_rate": 4.25e-05,
|
| 809 |
+
"loss": 0.6512,
|
| 810 |
+
"step": 94
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"epoch": 11.875,
|
| 814 |
+
"grad_norm": 5.220276832580566,
|
| 815 |
+
"learning_rate": 4.236111111111111e-05,
|
| 816 |
+
"loss": 0.6326,
|
| 817 |
+
"step": 95
|
| 818 |
+
},
|
| 819 |
+
{
|
| 820 |
+
"epoch": 12.0,
|
| 821 |
+
"grad_norm": 5.584306716918945,
|
| 822 |
+
"learning_rate": 4.222222222222222e-05,
|
| 823 |
+
"loss": 0.7,
|
| 824 |
+
"step": 96
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 12.0,
|
| 828 |
+
"eval_accuracy": 0.5645161290322581,
|
| 829 |
+
"eval_auc": 0.6523109243697479,
|
| 830 |
+
"eval_f1": 0.7096774193548387,
|
| 831 |
+
"eval_loss": 0.6655430197715759,
|
| 832 |
+
"eval_precision": 0.559322033898305,
|
| 833 |
+
"eval_recall": 0.9705882352941176,
|
| 834 |
+
"eval_runtime": 1.0537,
|
| 835 |
+
"eval_samples_per_second": 58.841,
|
| 836 |
+
"eval_steps_per_second": 0.949,
|
| 837 |
+
"step": 96
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 12.125,
|
| 841 |
+
"grad_norm": 4.439757347106934,
|
| 842 |
+
"learning_rate": 4.208333333333334e-05,
|
| 843 |
+
"loss": 0.6559,
|
| 844 |
+
"step": 97
|
| 845 |
+
},
|
| 846 |
+
{
|
| 847 |
+
"epoch": 12.25,
|
| 848 |
+
"grad_norm": 5.144546031951904,
|
| 849 |
+
"learning_rate": 4.194444444444445e-05,
|
| 850 |
+
"loss": 0.6865,
|
| 851 |
+
"step": 98
|
| 852 |
+
},
|
| 853 |
+
{
|
| 854 |
+
"epoch": 12.375,
|
| 855 |
+
"grad_norm": 3.6267988681793213,
|
| 856 |
+
"learning_rate": 4.1805555555555556e-05,
|
| 857 |
+
"loss": 0.6373,
|
| 858 |
+
"step": 99
|
| 859 |
+
},
|
| 860 |
+
{
|
| 861 |
+
"epoch": 12.5,
|
| 862 |
+
"grad_norm": 5.765615940093994,
|
| 863 |
+
"learning_rate": 4.166666666666667e-05,
|
| 864 |
+
"loss": 0.6611,
|
| 865 |
+
"step": 100
|
| 866 |
+
},
|
| 867 |
+
{
|
| 868 |
+
"epoch": 12.625,
|
| 869 |
+
"grad_norm": 3.467578172683716,
|
| 870 |
+
"learning_rate": 4.152777777777778e-05,
|
| 871 |
+
"loss": 0.6743,
|
| 872 |
+
"step": 101
|
| 873 |
+
},
|
| 874 |
+
{
|
| 875 |
+
"epoch": 12.75,
|
| 876 |
+
"grad_norm": 5.960920333862305,
|
| 877 |
+
"learning_rate": 4.138888888888889e-05,
|
| 878 |
+
"loss": 0.6453,
|
| 879 |
+
"step": 102
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 12.875,
|
| 883 |
+
"grad_norm": 4.811793804168701,
|
| 884 |
+
"learning_rate": 4.125e-05,
|
| 885 |
+
"loss": 0.6481,
|
| 886 |
+
"step": 103
|
| 887 |
+
},
|
| 888 |
+
{
|
| 889 |
+
"epoch": 13.0,
|
| 890 |
+
"grad_norm": 6.307322025299072,
|
| 891 |
+
"learning_rate": 4.111111111111111e-05,
|
| 892 |
+
"loss": 0.6378,
|
| 893 |
+
"step": 104
|
| 894 |
+
},
|
| 895 |
+
{
|
| 896 |
+
"epoch": 13.0,
|
| 897 |
+
"eval_accuracy": 0.5161290322580645,
|
| 898 |
+
"eval_auc": 0.7253151260504203,
|
| 899 |
+
"eval_f1": 0.6808510638297872,
|
| 900 |
+
"eval_loss": 0.6621407866477966,
|
| 901 |
+
"eval_precision": 0.5333333333333333,
|
| 902 |
+
"eval_recall": 0.9411764705882353,
|
| 903 |
+
"eval_runtime": 1.051,
|
| 904 |
+
"eval_samples_per_second": 58.993,
|
| 905 |
+
"eval_steps_per_second": 0.952,
|
| 906 |
+
"step": 104
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 13.125,
|
| 910 |
+
"grad_norm": 3.2586889266967773,
|
| 911 |
+
"learning_rate": 4.0972222222222225e-05,
|
| 912 |
+
"loss": 0.6345,
|
| 913 |
+
"step": 105
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 13.25,
|
| 917 |
+
"grad_norm": 4.068896293640137,
|
| 918 |
+
"learning_rate": 4.0833333333333334e-05,
|
| 919 |
+
"loss": 0.6684,
|
| 920 |
+
"step": 106
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 13.375,
|
| 924 |
+
"grad_norm": 4.019279956817627,
|
| 925 |
+
"learning_rate": 4.0694444444444444e-05,
|
| 926 |
+
"loss": 0.6707,
|
| 927 |
+
"step": 107
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 13.5,
|
| 931 |
+
"grad_norm": 11.265647888183594,
|
| 932 |
+
"learning_rate": 4.055555555555556e-05,
|
| 933 |
+
"loss": 0.6451,
|
| 934 |
+
"step": 108
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 13.625,
|
| 938 |
+
"grad_norm": 3.7474427223205566,
|
| 939 |
+
"learning_rate": 4.041666666666667e-05,
|
| 940 |
+
"loss": 0.6574,
|
| 941 |
+
"step": 109
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 13.75,
|
| 945 |
+
"grad_norm": 3.5386738777160645,
|
| 946 |
+
"learning_rate": 4.027777777777778e-05,
|
| 947 |
+
"loss": 0.6499,
|
| 948 |
+
"step": 110
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 13.875,
|
| 952 |
+
"grad_norm": 4.487296104431152,
|
| 953 |
+
"learning_rate": 4.0138888888888894e-05,
|
| 954 |
+
"loss": 0.635,
|
| 955 |
+
"step": 111
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 14.0,
|
| 959 |
+
"grad_norm": 5.318592071533203,
|
| 960 |
+
"learning_rate": 4e-05,
|
| 961 |
+
"loss": 0.6661,
|
| 962 |
+
"step": 112
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 14.0,
|
| 966 |
+
"eval_accuracy": 0.5161290322580645,
|
| 967 |
+
"eval_auc": 0.7878151260504201,
|
| 968 |
+
"eval_f1": 0.6808510638297872,
|
| 969 |
+
"eval_loss": 0.6499494910240173,
|
| 970 |
+
"eval_precision": 0.5333333333333333,
|
| 971 |
+
"eval_recall": 0.9411764705882353,
|
| 972 |
+
"eval_runtime": 1.0543,
|
| 973 |
+
"eval_samples_per_second": 58.809,
|
| 974 |
+
"eval_steps_per_second": 0.949,
|
| 975 |
+
"step": 112
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 14.125,
|
| 979 |
+
"grad_norm": 4.820748329162598,
|
| 980 |
+
"learning_rate": 3.986111111111111e-05,
|
| 981 |
+
"loss": 0.6658,
|
| 982 |
+
"step": 113
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 14.25,
|
| 986 |
+
"grad_norm": 5.010680198669434,
|
| 987 |
+
"learning_rate": 3.972222222222222e-05,
|
| 988 |
+
"loss": 0.6368,
|
| 989 |
+
"step": 114
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 14.375,
|
| 993 |
+
"grad_norm": 4.729431629180908,
|
| 994 |
+
"learning_rate": 3.958333333333333e-05,
|
| 995 |
+
"loss": 0.6401,
|
| 996 |
+
"step": 115
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 14.5,
|
| 1000 |
+
"grad_norm": 3.62618088722229,
|
| 1001 |
+
"learning_rate": 3.944444444444445e-05,
|
| 1002 |
+
"loss": 0.6284,
|
| 1003 |
+
"step": 116
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 14.625,
|
| 1007 |
+
"grad_norm": 3.4717531204223633,
|
| 1008 |
+
"learning_rate": 3.9305555555555556e-05,
|
| 1009 |
+
"loss": 0.6988,
|
| 1010 |
+
"step": 117
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 14.75,
|
| 1014 |
+
"grad_norm": 5.191429615020752,
|
| 1015 |
+
"learning_rate": 3.9166666666666665e-05,
|
| 1016 |
+
"loss": 0.6581,
|
| 1017 |
+
"step": 118
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 14.875,
|
| 1021 |
+
"grad_norm": 4.230731964111328,
|
| 1022 |
+
"learning_rate": 3.902777777777778e-05,
|
| 1023 |
+
"loss": 0.6275,
|
| 1024 |
+
"step": 119
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 15.0,
|
| 1028 |
+
"grad_norm": 4.9688591957092285,
|
| 1029 |
+
"learning_rate": 3.888888888888889e-05,
|
| 1030 |
+
"loss": 0.6995,
|
| 1031 |
+
"step": 120
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 15.0,
|
| 1035 |
+
"eval_accuracy": 0.5645161290322581,
|
| 1036 |
+
"eval_auc": 0.7689075630252101,
|
| 1037 |
+
"eval_f1": 0.7157894736842105,
|
| 1038 |
+
"eval_loss": 0.6420426964759827,
|
| 1039 |
+
"eval_precision": 0.5573770491803278,
|
| 1040 |
+
"eval_recall": 1.0,
|
| 1041 |
+
"eval_runtime": 1.9681,
|
| 1042 |
+
"eval_samples_per_second": 31.502,
|
| 1043 |
+
"eval_steps_per_second": 0.508,
|
| 1044 |
+
"step": 120
|
| 1045 |
+
},
|
| 1046 |
+
{
|
| 1047 |
+
"epoch": 15.125,
|
| 1048 |
+
"grad_norm": 5.159355163574219,
|
| 1049 |
+
"learning_rate": 3.875e-05,
|
| 1050 |
+
"loss": 0.6519,
|
| 1051 |
+
"step": 121
|
| 1052 |
+
},
|
| 1053 |
+
{
|
| 1054 |
+
"epoch": 15.25,
|
| 1055 |
+
"grad_norm": 4.40577507019043,
|
| 1056 |
+
"learning_rate": 3.8611111111111116e-05,
|
| 1057 |
+
"loss": 0.6403,
|
| 1058 |
+
"step": 122
|
| 1059 |
+
},
|
| 1060 |
+
{
|
| 1061 |
+
"epoch": 15.375,
|
| 1062 |
+
"grad_norm": 4.472173690795898,
|
| 1063 |
+
"learning_rate": 3.8472222222222225e-05,
|
| 1064 |
+
"loss": 0.631,
|
| 1065 |
+
"step": 123
|
| 1066 |
+
},
|
| 1067 |
+
{
|
| 1068 |
+
"epoch": 15.5,
|
| 1069 |
+
"grad_norm": 4.416353702545166,
|
| 1070 |
+
"learning_rate": 3.8333333333333334e-05,
|
| 1071 |
+
"loss": 0.6754,
|
| 1072 |
+
"step": 124
|
| 1073 |
+
},
|
| 1074 |
+
{
|
| 1075 |
+
"epoch": 15.625,
|
| 1076 |
+
"grad_norm": 4.293478965759277,
|
| 1077 |
+
"learning_rate": 3.8194444444444444e-05,
|
| 1078 |
+
"loss": 0.6077,
|
| 1079 |
+
"step": 125
|
| 1080 |
+
},
|
| 1081 |
+
{
|
| 1082 |
+
"epoch": 15.75,
|
| 1083 |
+
"grad_norm": 6.2308573722839355,
|
| 1084 |
+
"learning_rate": 3.805555555555555e-05,
|
| 1085 |
+
"loss": 0.6856,
|
| 1086 |
+
"step": 126
|
| 1087 |
+
},
|
| 1088 |
+
{
|
| 1089 |
+
"epoch": 15.875,
|
| 1090 |
+
"grad_norm": 5.293476581573486,
|
| 1091 |
+
"learning_rate": 3.791666666666667e-05,
|
| 1092 |
+
"loss": 0.6651,
|
| 1093 |
+
"step": 127
|
| 1094 |
+
},
|
| 1095 |
+
{
|
| 1096 |
+
"epoch": 16.0,
|
| 1097 |
+
"grad_norm": 4.858785629272461,
|
| 1098 |
+
"learning_rate": 3.777777777777778e-05,
|
| 1099 |
+
"loss": 0.667,
|
| 1100 |
+
"step": 128
|
| 1101 |
+
},
|
| 1102 |
+
{
|
| 1103 |
+
"epoch": 16.0,
|
| 1104 |
+
"eval_accuracy": 0.6129032258064516,
|
| 1105 |
+
"eval_auc": 0.8224789915966386,
|
| 1106 |
+
"eval_f1": 0.7391304347826086,
|
| 1107 |
+
"eval_loss": 0.6401523947715759,
|
| 1108 |
+
"eval_precision": 0.5862068965517241,
|
| 1109 |
+
"eval_recall": 1.0,
|
| 1110 |
+
"eval_runtime": 1.899,
|
| 1111 |
+
"eval_samples_per_second": 32.648,
|
| 1112 |
+
"eval_steps_per_second": 0.527,
|
| 1113 |
+
"step": 128
|
| 1114 |
+
},
|
| 1115 |
+
{
|
| 1116 |
+
"epoch": 16.125,
|
| 1117 |
+
"grad_norm": 5.453197002410889,
|
| 1118 |
+
"learning_rate": 3.763888888888889e-05,
|
| 1119 |
+
"loss": 0.6408,
|
| 1120 |
+
"step": 129
|
| 1121 |
+
},
|
| 1122 |
+
{
|
| 1123 |
+
"epoch": 16.25,
|
| 1124 |
+
"grad_norm": 3.673980951309204,
|
| 1125 |
+
"learning_rate": 3.7500000000000003e-05,
|
| 1126 |
+
"loss": 0.6495,
|
| 1127 |
+
"step": 130
|
| 1128 |
+
},
|
| 1129 |
+
{
|
| 1130 |
+
"epoch": 16.375,
|
| 1131 |
+
"grad_norm": 4.425279140472412,
|
| 1132 |
+
"learning_rate": 3.736111111111111e-05,
|
| 1133 |
+
"loss": 0.7037,
|
| 1134 |
+
"step": 131
|
| 1135 |
+
},
|
| 1136 |
+
{
|
| 1137 |
+
"epoch": 16.5,
|
| 1138 |
+
"grad_norm": 6.135858535766602,
|
| 1139 |
+
"learning_rate": 3.722222222222222e-05,
|
| 1140 |
+
"loss": 0.6355,
|
| 1141 |
+
"step": 132
|
| 1142 |
+
},
|
| 1143 |
+
{
|
| 1144 |
+
"epoch": 16.625,
|
| 1145 |
+
"grad_norm": 5.035116195678711,
|
| 1146 |
+
"learning_rate": 3.708333333333334e-05,
|
| 1147 |
+
"loss": 0.6258,
|
| 1148 |
+
"step": 133
|
| 1149 |
+
},
|
| 1150 |
+
{
|
| 1151 |
+
"epoch": 16.75,
|
| 1152 |
+
"grad_norm": 5.022816181182861,
|
| 1153 |
+
"learning_rate": 3.694444444444445e-05,
|
| 1154 |
+
"loss": 0.6282,
|
| 1155 |
+
"step": 134
|
| 1156 |
+
},
|
| 1157 |
+
{
|
| 1158 |
+
"epoch": 16.875,
|
| 1159 |
+
"grad_norm": 5.77787446975708,
|
| 1160 |
+
"learning_rate": 3.6805555555555556e-05,
|
| 1161 |
+
"loss": 0.6772,
|
| 1162 |
+
"step": 135
|
| 1163 |
+
},
|
| 1164 |
+
{
|
| 1165 |
+
"epoch": 17.0,
|
| 1166 |
+
"grad_norm": 4.462384223937988,
|
| 1167 |
+
"learning_rate": 3.6666666666666666e-05,
|
| 1168 |
+
"loss": 0.6323,
|
| 1169 |
+
"step": 136
|
| 1170 |
+
},
|
| 1171 |
+
{
|
| 1172 |
+
"epoch": 17.0,
|
| 1173 |
+
"eval_accuracy": 0.5967741935483871,
|
| 1174 |
+
"eval_auc": 0.8067226890756303,
|
| 1175 |
+
"eval_f1": 0.7252747252747253,
|
| 1176 |
+
"eval_loss": 0.636435329914093,
|
| 1177 |
+
"eval_precision": 0.5789473684210527,
|
| 1178 |
+
"eval_recall": 0.9705882352941176,
|
| 1179 |
+
"eval_runtime": 2.1248,
|
| 1180 |
+
"eval_samples_per_second": 29.18,
|
| 1181 |
+
"eval_steps_per_second": 0.471,
|
| 1182 |
+
"step": 136
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 17.125,
|
| 1186 |
+
"grad_norm": 5.69638204574585,
|
| 1187 |
+
"learning_rate": 3.6527777777777775e-05,
|
| 1188 |
+
"loss": 0.7483,
|
| 1189 |
+
"step": 137
|
| 1190 |
+
},
|
| 1191 |
+
{
|
| 1192 |
+
"epoch": 17.25,
|
| 1193 |
+
"grad_norm": 5.035621643066406,
|
| 1194 |
+
"learning_rate": 3.638888888888889e-05,
|
| 1195 |
+
"loss": 0.582,
|
| 1196 |
+
"step": 138
|
| 1197 |
+
},
|
| 1198 |
+
{
|
| 1199 |
+
"epoch": 17.375,
|
| 1200 |
+
"grad_norm": 4.352199554443359,
|
| 1201 |
+
"learning_rate": 3.625e-05,
|
| 1202 |
+
"loss": 0.6365,
|
| 1203 |
+
"step": 139
|
| 1204 |
+
},
|
| 1205 |
+
{
|
| 1206 |
+
"epoch": 17.5,
|
| 1207 |
+
"grad_norm": 3.4610562324523926,
|
| 1208 |
+
"learning_rate": 3.611111111111111e-05,
|
| 1209 |
+
"loss": 0.6649,
|
| 1210 |
+
"step": 140
|
| 1211 |
+
},
|
| 1212 |
+
{
|
| 1213 |
+
"epoch": 17.625,
|
| 1214 |
+
"grad_norm": 3.9347448348999023,
|
| 1215 |
+
"learning_rate": 3.5972222222222225e-05,
|
| 1216 |
+
"loss": 0.6237,
|
| 1217 |
+
"step": 141
|
| 1218 |
+
},
|
| 1219 |
+
{
|
| 1220 |
+
"epoch": 17.75,
|
| 1221 |
+
"grad_norm": 5.365068435668945,
|
| 1222 |
+
"learning_rate": 3.5833333333333335e-05,
|
| 1223 |
+
"loss": 0.663,
|
| 1224 |
+
"step": 142
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 17.875,
|
| 1228 |
+
"grad_norm": 3.5667879581451416,
|
| 1229 |
+
"learning_rate": 3.5694444444444444e-05,
|
| 1230 |
+
"loss": 0.6276,
|
| 1231 |
+
"step": 143
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 18.0,
|
| 1235 |
+
"grad_norm": 5.399511337280273,
|
| 1236 |
+
"learning_rate": 3.555555555555556e-05,
|
| 1237 |
+
"loss": 0.6042,
|
| 1238 |
+
"step": 144
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 18.0,
|
| 1242 |
+
"eval_accuracy": 0.5645161290322581,
|
| 1243 |
+
"eval_auc": 0.7668067226890757,
|
| 1244 |
+
"eval_f1": 0.7157894736842105,
|
| 1245 |
+
"eval_loss": 0.6346396803855896,
|
| 1246 |
+
"eval_precision": 0.5573770491803278,
|
| 1247 |
+
"eval_recall": 1.0,
|
| 1248 |
+
"eval_runtime": 1.8426,
|
| 1249 |
+
"eval_samples_per_second": 33.647,
|
| 1250 |
+
"eval_steps_per_second": 0.543,
|
| 1251 |
+
"step": 144
|
| 1252 |
+
},
|
| 1253 |
+
{
|
| 1254 |
+
"epoch": 18.125,
|
| 1255 |
+
"grad_norm": 6.267144680023193,
|
| 1256 |
+
"learning_rate": 3.541666666666667e-05,
|
| 1257 |
+
"loss": 0.637,
|
| 1258 |
+
"step": 145
|
| 1259 |
+
},
|
| 1260 |
+
{
|
| 1261 |
+
"epoch": 18.25,
|
| 1262 |
+
"grad_norm": 5.8084893226623535,
|
| 1263 |
+
"learning_rate": 3.527777777777778e-05,
|
| 1264 |
+
"loss": 0.6969,
|
| 1265 |
+
"step": 146
|
| 1266 |
+
},
|
| 1267 |
+
{
|
| 1268 |
+
"epoch": 18.375,
|
| 1269 |
+
"grad_norm": 4.974161148071289,
|
| 1270 |
+
"learning_rate": 3.513888888888889e-05,
|
| 1271 |
+
"loss": 0.6304,
|
| 1272 |
+
"step": 147
|
| 1273 |
+
},
|
| 1274 |
+
{
|
| 1275 |
+
"epoch": 18.5,
|
| 1276 |
+
"grad_norm": 3.7128164768218994,
|
| 1277 |
+
"learning_rate": 3.5e-05,
|
| 1278 |
+
"loss": 0.6409,
|
| 1279 |
+
"step": 148
|
| 1280 |
+
},
|
| 1281 |
+
{
|
| 1282 |
+
"epoch": 18.625,
|
| 1283 |
+
"grad_norm": 3.934004306793213,
|
| 1284 |
+
"learning_rate": 3.486111111111111e-05,
|
| 1285 |
+
"loss": 0.6731,
|
| 1286 |
+
"step": 149
|
| 1287 |
+
},
|
| 1288 |
+
{
|
| 1289 |
+
"epoch": 18.75,
|
| 1290 |
+
"grad_norm": 3.6201493740081787,
|
| 1291 |
+
"learning_rate": 3.472222222222222e-05,
|
| 1292 |
+
"loss": 0.6151,
|
| 1293 |
+
"step": 150
|
| 1294 |
+
},
|
| 1295 |
+
{
|
| 1296 |
+
"epoch": 18.875,
|
| 1297 |
+
"grad_norm": 4.2509846687316895,
|
| 1298 |
+
"learning_rate": 3.458333333333333e-05,
|
| 1299 |
+
"loss": 0.6355,
|
| 1300 |
+
"step": 151
|
| 1301 |
+
},
|
| 1302 |
+
{
|
| 1303 |
+
"epoch": 19.0,
|
| 1304 |
+
"grad_norm": 5.550896167755127,
|
| 1305 |
+
"learning_rate": 3.444444444444445e-05,
|
| 1306 |
+
"loss": 0.6246,
|
| 1307 |
+
"step": 152
|
| 1308 |
+
},
|
| 1309 |
+
{
|
| 1310 |
+
"epoch": 19.0,
|
| 1311 |
+
"eval_accuracy": 0.6129032258064516,
|
| 1312 |
+
"eval_auc": 0.7956932773109244,
|
| 1313 |
+
"eval_f1": 0.7333333333333333,
|
| 1314 |
+
"eval_loss": 0.6221962571144104,
|
| 1315 |
+
"eval_precision": 0.5892857142857143,
|
| 1316 |
+
"eval_recall": 0.9705882352941176,
|
| 1317 |
+
"eval_runtime": 1.8313,
|
| 1318 |
+
"eval_samples_per_second": 33.856,
|
| 1319 |
+
"eval_steps_per_second": 0.546,
|
| 1320 |
+
"step": 152
|
| 1321 |
+
},
|
| 1322 |
+
{
|
| 1323 |
+
"epoch": 19.125,
|
| 1324 |
+
"grad_norm": 6.814294338226318,
|
| 1325 |
+
"learning_rate": 3.430555555555556e-05,
|
| 1326 |
+
"loss": 0.6481,
|
| 1327 |
+
"step": 153
|
| 1328 |
+
},
|
| 1329 |
+
{
|
| 1330 |
+
"epoch": 19.25,
|
| 1331 |
+
"grad_norm": 4.457539081573486,
|
| 1332 |
+
"learning_rate": 3.4166666666666666e-05,
|
| 1333 |
+
"loss": 0.6304,
|
| 1334 |
+
"step": 154
|
| 1335 |
+
},
|
| 1336 |
+
{
|
| 1337 |
+
"epoch": 19.375,
|
| 1338 |
+
"grad_norm": 6.537652015686035,
|
| 1339 |
+
"learning_rate": 3.402777777777778e-05,
|
| 1340 |
+
"loss": 0.6383,
|
| 1341 |
+
"step": 155
|
| 1342 |
+
},
|
| 1343 |
+
{
|
| 1344 |
+
"epoch": 19.5,
|
| 1345 |
+
"grad_norm": 4.554441452026367,
|
| 1346 |
+
"learning_rate": 3.388888888888889e-05,
|
| 1347 |
+
"loss": 0.6493,
|
| 1348 |
+
"step": 156
|
| 1349 |
+
},
|
| 1350 |
+
{
|
| 1351 |
+
"epoch": 19.625,
|
| 1352 |
+
"grad_norm": 4.500042915344238,
|
| 1353 |
+
"learning_rate": 3.375000000000001e-05,
|
| 1354 |
+
"loss": 0.6182,
|
| 1355 |
+
"step": 157
|
| 1356 |
+
},
|
| 1357 |
+
{
|
| 1358 |
+
"epoch": 19.75,
|
| 1359 |
+
"grad_norm": 3.971832752227783,
|
| 1360 |
+
"learning_rate": 3.3611111111111116e-05,
|
| 1361 |
+
"loss": 0.6368,
|
| 1362 |
+
"step": 158
|
| 1363 |
+
},
|
| 1364 |
+
{
|
| 1365 |
+
"epoch": 19.875,
|
| 1366 |
+
"grad_norm": 4.7569379806518555,
|
| 1367 |
+
"learning_rate": 3.347222222222222e-05,
|
| 1368 |
+
"loss": 0.6299,
|
| 1369 |
+
"step": 159
|
| 1370 |
+
},
|
| 1371 |
+
{
|
| 1372 |
+
"epoch": 20.0,
|
| 1373 |
+
"grad_norm": 5.7485527992248535,
|
| 1374 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 1375 |
+
"loss": 0.7056,
|
| 1376 |
+
"step": 160
|
| 1377 |
+
},
|
| 1378 |
+
{
|
| 1379 |
+
"epoch": 20.0,
|
| 1380 |
+
"eval_accuracy": 0.5967741935483871,
|
| 1381 |
+
"eval_auc": 0.8140756302521008,
|
| 1382 |
+
"eval_f1": 0.7252747252747253,
|
| 1383 |
+
"eval_loss": 0.6149352788925171,
|
| 1384 |
+
"eval_precision": 0.5789473684210527,
|
| 1385 |
+
"eval_recall": 0.9705882352941176,
|
| 1386 |
+
"eval_runtime": 1.8264,
|
| 1387 |
+
"eval_samples_per_second": 33.946,
|
| 1388 |
+
"eval_steps_per_second": 0.548,
|
| 1389 |
+
"step": 160
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 20.125,
|
| 1393 |
+
"grad_norm": 6.883080005645752,
|
| 1394 |
+
"learning_rate": 3.3194444444444444e-05,
|
| 1395 |
+
"loss": 0.6857,
|
| 1396 |
+
"step": 161
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 20.25,
|
| 1400 |
+
"grad_norm": 5.485716819763184,
|
| 1401 |
+
"learning_rate": 3.3055555555555553e-05,
|
| 1402 |
+
"loss": 0.689,
|
| 1403 |
+
"step": 162
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 20.375,
|
| 1407 |
+
"grad_norm": 4.644085884094238,
|
| 1408 |
+
"learning_rate": 3.291666666666667e-05,
|
| 1409 |
+
"loss": 0.5933,
|
| 1410 |
+
"step": 163
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"epoch": 20.5,
|
| 1414 |
+
"grad_norm": 4.706975936889648,
|
| 1415 |
+
"learning_rate": 3.277777777777778e-05,
|
| 1416 |
+
"loss": 0.6278,
|
| 1417 |
+
"step": 164
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 20.625,
|
| 1421 |
+
"grad_norm": 8.53987979888916,
|
| 1422 |
+
"learning_rate": 3.263888888888889e-05,
|
| 1423 |
+
"loss": 0.5889,
|
| 1424 |
+
"step": 165
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 20.75,
|
| 1428 |
+
"grad_norm": 5.014941215515137,
|
| 1429 |
+
"learning_rate": 3.2500000000000004e-05,
|
| 1430 |
+
"loss": 0.6179,
|
| 1431 |
+
"step": 166
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 20.875,
|
| 1435 |
+
"grad_norm": 5.296703338623047,
|
| 1436 |
+
"learning_rate": 3.236111111111111e-05,
|
| 1437 |
+
"loss": 0.6346,
|
| 1438 |
+
"step": 167
|
| 1439 |
+
},
|
| 1440 |
+
{
|
| 1441 |
+
"epoch": 21.0,
|
| 1442 |
+
"grad_norm": 6.87127685546875,
|
| 1443 |
+
"learning_rate": 3.222222222222223e-05,
|
| 1444 |
+
"loss": 0.6363,
|
| 1445 |
+
"step": 168
|
| 1446 |
+
},
|
| 1447 |
+
{
|
| 1448 |
+
"epoch": 21.0,
|
| 1449 |
+
"eval_accuracy": 0.6451612903225806,
|
| 1450 |
+
"eval_auc": 0.8188025210084033,
|
| 1451 |
+
"eval_f1": 0.7555555555555555,
|
| 1452 |
+
"eval_loss": 0.6101309061050415,
|
| 1453 |
+
"eval_precision": 0.6071428571428571,
|
| 1454 |
+
"eval_recall": 1.0,
|
| 1455 |
+
"eval_runtime": 1.8384,
|
| 1456 |
+
"eval_samples_per_second": 33.725,
|
| 1457 |
+
"eval_steps_per_second": 0.544,
|
| 1458 |
+
"step": 168
|
| 1459 |
+
},
|
| 1460 |
+
{
|
| 1461 |
+
"epoch": 21.125,
|
| 1462 |
+
"grad_norm": 3.649150848388672,
|
| 1463 |
+
"learning_rate": 3.208333333333334e-05,
|
| 1464 |
+
"loss": 0.5961,
|
| 1465 |
+
"step": 169
|
| 1466 |
+
},
|
| 1467 |
+
{
|
| 1468 |
+
"epoch": 21.25,
|
| 1469 |
+
"grad_norm": 5.5340962409973145,
|
| 1470 |
+
"learning_rate": 3.194444444444444e-05,
|
| 1471 |
+
"loss": 0.658,
|
| 1472 |
+
"step": 170
|
| 1473 |
+
},
|
| 1474 |
+
{
|
| 1475 |
+
"epoch": 21.375,
|
| 1476 |
+
"grad_norm": 4.7374396324157715,
|
| 1477 |
+
"learning_rate": 3.180555555555556e-05,
|
| 1478 |
+
"loss": 0.6595,
|
| 1479 |
+
"step": 171
|
| 1480 |
+
},
|
| 1481 |
+
{
|
| 1482 |
+
"epoch": 21.5,
|
| 1483 |
+
"grad_norm": 5.9304280281066895,
|
| 1484 |
+
"learning_rate": 3.1666666666666666e-05,
|
| 1485 |
+
"loss": 0.6111,
|
| 1486 |
+
"step": 172
|
| 1487 |
+
},
|
| 1488 |
+
{
|
| 1489 |
+
"epoch": 21.625,
|
| 1490 |
+
"grad_norm": 4.608835697174072,
|
| 1491 |
+
"learning_rate": 3.1527777777777775e-05,
|
| 1492 |
+
"loss": 0.6172,
|
| 1493 |
+
"step": 173
|
| 1494 |
+
},
|
| 1495 |
+
{
|
| 1496 |
+
"epoch": 21.75,
|
| 1497 |
+
"grad_norm": 6.680834770202637,
|
| 1498 |
+
"learning_rate": 3.138888888888889e-05,
|
| 1499 |
+
"loss": 0.6245,
|
| 1500 |
+
"step": 174
|
| 1501 |
+
},
|
| 1502 |
+
{
|
| 1503 |
+
"epoch": 21.875,
|
| 1504 |
+
"grad_norm": 4.915333271026611,
|
| 1505 |
+
"learning_rate": 3.125e-05,
|
| 1506 |
+
"loss": 0.6208,
|
| 1507 |
+
"step": 175
|
| 1508 |
+
},
|
| 1509 |
+
{
|
| 1510 |
+
"epoch": 22.0,
|
| 1511 |
+
"grad_norm": 6.438394546508789,
|
| 1512 |
+
"learning_rate": 3.111111111111111e-05,
|
| 1513 |
+
"loss": 0.6096,
|
| 1514 |
+
"step": 176
|
| 1515 |
+
},
|
| 1516 |
+
{
|
| 1517 |
+
"epoch": 22.0,
|
| 1518 |
+
"eval_accuracy": 0.6129032258064516,
|
| 1519 |
+
"eval_auc": 0.8403361344537815,
|
| 1520 |
+
"eval_f1": 0.7333333333333333,
|
| 1521 |
+
"eval_loss": 0.6029170751571655,
|
| 1522 |
+
"eval_precision": 0.5892857142857143,
|
| 1523 |
+
"eval_recall": 0.9705882352941176,
|
| 1524 |
+
"eval_runtime": 1.8387,
|
| 1525 |
+
"eval_samples_per_second": 33.72,
|
| 1526 |
+
"eval_steps_per_second": 0.544,
|
| 1527 |
+
"step": 176
|
| 1528 |
+
},
|
| 1529 |
+
{
|
| 1530 |
+
"epoch": 22.125,
|
| 1531 |
+
"grad_norm": 4.041502952575684,
|
| 1532 |
+
"learning_rate": 3.0972222222222226e-05,
|
| 1533 |
+
"loss": 0.6492,
|
| 1534 |
+
"step": 177
|
| 1535 |
+
},
|
| 1536 |
+
{
|
| 1537 |
+
"epoch": 22.25,
|
| 1538 |
+
"grad_norm": 4.550416946411133,
|
| 1539 |
+
"learning_rate": 3.0833333333333335e-05,
|
| 1540 |
+
"loss": 0.5992,
|
| 1541 |
+
"step": 178
|
| 1542 |
+
},
|
| 1543 |
+
{
|
| 1544 |
+
"epoch": 22.375,
|
| 1545 |
+
"grad_norm": 4.022625923156738,
|
| 1546 |
+
"learning_rate": 3.069444444444445e-05,
|
| 1547 |
+
"loss": 0.6154,
|
| 1548 |
+
"step": 179
|
| 1549 |
+
},
|
| 1550 |
+
{
|
| 1551 |
+
"epoch": 22.5,
|
| 1552 |
+
"grad_norm": 6.600803375244141,
|
| 1553 |
+
"learning_rate": 3.055555555555556e-05,
|
| 1554 |
+
"loss": 0.6168,
|
| 1555 |
+
"step": 180
|
| 1556 |
+
},
|
| 1557 |
+
{
|
| 1558 |
+
"epoch": 22.625,
|
| 1559 |
+
"grad_norm": 5.327729225158691,
|
| 1560 |
+
"learning_rate": 3.0416666666666666e-05,
|
| 1561 |
+
"loss": 0.6605,
|
| 1562 |
+
"step": 181
|
| 1563 |
+
},
|
| 1564 |
+
{
|
| 1565 |
+
"epoch": 22.75,
|
| 1566 |
+
"grad_norm": 6.26377010345459,
|
| 1567 |
+
"learning_rate": 3.0277777777777776e-05,
|
| 1568 |
+
"loss": 0.6669,
|
| 1569 |
+
"step": 182
|
| 1570 |
+
},
|
| 1571 |
+
{
|
| 1572 |
+
"epoch": 22.875,
|
| 1573 |
+
"grad_norm": 6.820950508117676,
|
| 1574 |
+
"learning_rate": 3.0138888888888888e-05,
|
| 1575 |
+
"loss": 0.6306,
|
| 1576 |
+
"step": 183
|
| 1577 |
+
},
|
| 1578 |
+
{
|
| 1579 |
+
"epoch": 23.0,
|
| 1580 |
+
"grad_norm": 4.663633823394775,
|
| 1581 |
+
"learning_rate": 3e-05,
|
| 1582 |
+
"loss": 0.5631,
|
| 1583 |
+
"step": 184
|
| 1584 |
+
},
|
| 1585 |
+
{
|
| 1586 |
+
"epoch": 23.0,
|
| 1587 |
+
"eval_accuracy": 0.6129032258064516,
|
| 1588 |
+
"eval_auc": 0.8413865546218487,
|
| 1589 |
+
"eval_f1": 0.7391304347826086,
|
| 1590 |
+
"eval_loss": 0.6036572456359863,
|
| 1591 |
+
"eval_precision": 0.5862068965517241,
|
| 1592 |
+
"eval_recall": 1.0,
|
| 1593 |
+
"eval_runtime": 1.8201,
|
| 1594 |
+
"eval_samples_per_second": 34.064,
|
| 1595 |
+
"eval_steps_per_second": 0.549,
|
| 1596 |
+
"step": 184
|
| 1597 |
+
},
|
| 1598 |
+
{
|
| 1599 |
+
"epoch": 23.125,
|
| 1600 |
+
"grad_norm": 4.107852935791016,
|
| 1601 |
+
"learning_rate": 2.9861111111111113e-05,
|
| 1602 |
+
"loss": 0.5985,
|
| 1603 |
+
"step": 185
|
| 1604 |
+
},
|
| 1605 |
+
{
|
| 1606 |
+
"epoch": 23.25,
|
| 1607 |
+
"grad_norm": 3.9539260864257812,
|
| 1608 |
+
"learning_rate": 2.9722222222222223e-05,
|
| 1609 |
+
"loss": 0.5984,
|
| 1610 |
+
"step": 186
|
| 1611 |
+
},
|
| 1612 |
+
{
|
| 1613 |
+
"epoch": 23.375,
|
| 1614 |
+
"grad_norm": 4.034968376159668,
|
| 1615 |
+
"learning_rate": 2.9583333333333335e-05,
|
| 1616 |
+
"loss": 0.6806,
|
| 1617 |
+
"step": 187
|
| 1618 |
+
},
|
| 1619 |
+
{
|
| 1620 |
+
"epoch": 23.5,
|
| 1621 |
+
"grad_norm": 4.896390438079834,
|
| 1622 |
+
"learning_rate": 2.9444444444444448e-05,
|
| 1623 |
+
"loss": 0.6342,
|
| 1624 |
+
"step": 188
|
| 1625 |
+
},
|
| 1626 |
+
{
|
| 1627 |
+
"epoch": 23.625,
|
| 1628 |
+
"grad_norm": 4.502488136291504,
|
| 1629 |
+
"learning_rate": 2.9305555555555557e-05,
|
| 1630 |
+
"loss": 0.6412,
|
| 1631 |
+
"step": 189
|
| 1632 |
+
},
|
| 1633 |
+
{
|
| 1634 |
+
"epoch": 23.75,
|
| 1635 |
+
"grad_norm": 6.495486736297607,
|
| 1636 |
+
"learning_rate": 2.916666666666667e-05,
|
| 1637 |
+
"loss": 0.6085,
|
| 1638 |
+
"step": 190
|
| 1639 |
+
},
|
| 1640 |
+
{
|
| 1641 |
+
"epoch": 23.875,
|
| 1642 |
+
"grad_norm": 3.62249755859375,
|
| 1643 |
+
"learning_rate": 2.9027777777777782e-05,
|
| 1644 |
+
"loss": 0.5709,
|
| 1645 |
+
"step": 191
|
| 1646 |
+
},
|
| 1647 |
+
{
|
| 1648 |
+
"epoch": 24.0,
|
| 1649 |
+
"grad_norm": 6.480982780456543,
|
| 1650 |
+
"learning_rate": 2.8888888888888888e-05,
|
| 1651 |
+
"loss": 0.6514,
|
| 1652 |
+
"step": 192
|
| 1653 |
+
},
|
| 1654 |
+
{
|
| 1655 |
+
"epoch": 24.0,
|
| 1656 |
+
"eval_accuracy": 0.6129032258064516,
|
| 1657 |
+
"eval_auc": 0.8298319327731092,
|
| 1658 |
+
"eval_f1": 0.7391304347826086,
|
| 1659 |
+
"eval_loss": 0.6017356514930725,
|
| 1660 |
+
"eval_precision": 0.5862068965517241,
|
| 1661 |
+
"eval_recall": 1.0,
|
| 1662 |
+
"eval_runtime": 1.8234,
|
| 1663 |
+
"eval_samples_per_second": 34.002,
|
| 1664 |
+
"eval_steps_per_second": 0.548,
|
| 1665 |
+
"step": 192
|
| 1666 |
+
},
|
| 1667 |
+
{
|
| 1668 |
+
"epoch": 24.125,
|
| 1669 |
+
"grad_norm": 3.940840244293213,
|
| 1670 |
+
"learning_rate": 2.8749999999999997e-05,
|
| 1671 |
+
"loss": 0.6404,
|
| 1672 |
+
"step": 193
|
| 1673 |
+
},
|
| 1674 |
+
{
|
| 1675 |
+
"epoch": 24.25,
|
| 1676 |
+
"grad_norm": 4.030274391174316,
|
| 1677 |
+
"learning_rate": 2.861111111111111e-05,
|
| 1678 |
+
"loss": 0.5729,
|
| 1679 |
+
"step": 194
|
| 1680 |
+
},
|
| 1681 |
+
{
|
| 1682 |
+
"epoch": 24.375,
|
| 1683 |
+
"grad_norm": 5.548068046569824,
|
| 1684 |
+
"learning_rate": 2.8472222222222223e-05,
|
| 1685 |
+
"loss": 0.6374,
|
| 1686 |
+
"step": 195
|
| 1687 |
+
},
|
| 1688 |
+
{
|
| 1689 |
+
"epoch": 24.5,
|
| 1690 |
+
"grad_norm": 4.947794437408447,
|
| 1691 |
+
"learning_rate": 2.8333333333333335e-05,
|
| 1692 |
+
"loss": 0.6271,
|
| 1693 |
+
"step": 196
|
| 1694 |
+
},
|
| 1695 |
+
{
|
| 1696 |
+
"epoch": 24.625,
|
| 1697 |
+
"grad_norm": 6.201533317565918,
|
| 1698 |
+
"learning_rate": 2.8194444444444445e-05,
|
| 1699 |
+
"loss": 0.6493,
|
| 1700 |
+
"step": 197
|
| 1701 |
+
},
|
| 1702 |
+
{
|
| 1703 |
+
"epoch": 24.75,
|
| 1704 |
+
"grad_norm": 4.74322509765625,
|
| 1705 |
+
"learning_rate": 2.8055555555555557e-05,
|
| 1706 |
+
"loss": 0.6461,
|
| 1707 |
+
"step": 198
|
| 1708 |
+
},
|
| 1709 |
+
{
|
| 1710 |
+
"epoch": 24.875,
|
| 1711 |
+
"grad_norm": 7.35964822769165,
|
| 1712 |
+
"learning_rate": 2.791666666666667e-05,
|
| 1713 |
+
"loss": 0.6208,
|
| 1714 |
+
"step": 199
|
| 1715 |
+
},
|
| 1716 |
+
{
|
| 1717 |
+
"epoch": 25.0,
|
| 1718 |
+
"grad_norm": 5.965765953063965,
|
| 1719 |
+
"learning_rate": 2.777777777777778e-05,
|
| 1720 |
+
"loss": 0.5818,
|
| 1721 |
+
"step": 200
|
| 1722 |
+
},
|
| 1723 |
+
{
|
| 1724 |
+
"epoch": 25.0,
|
| 1725 |
+
"eval_accuracy": 0.6290322580645161,
|
| 1726 |
+
"eval_auc": 0.8350840336134453,
|
| 1727 |
+
"eval_f1": 0.7472527472527473,
|
| 1728 |
+
"eval_loss": 0.5920096039772034,
|
| 1729 |
+
"eval_precision": 0.5964912280701754,
|
| 1730 |
+
"eval_recall": 1.0,
|
| 1731 |
+
"eval_runtime": 1.8063,
|
| 1732 |
+
"eval_samples_per_second": 34.324,
|
| 1733 |
+
"eval_steps_per_second": 0.554,
|
| 1734 |
+
"step": 200
|
| 1735 |
+
},
|
| 1736 |
+
{
|
| 1737 |
+
"epoch": 25.125,
|
| 1738 |
+
"grad_norm": 4.253195285797119,
|
| 1739 |
+
"learning_rate": 2.7638888888888892e-05,
|
| 1740 |
+
"loss": 0.5861,
|
| 1741 |
+
"step": 201
|
| 1742 |
+
},
|
| 1743 |
+
{
|
| 1744 |
+
"epoch": 25.25,
|
| 1745 |
+
"grad_norm": 6.890187740325928,
|
| 1746 |
+
"learning_rate": 2.7500000000000004e-05,
|
| 1747 |
+
"loss": 0.6664,
|
| 1748 |
+
"step": 202
|
| 1749 |
+
},
|
| 1750 |
+
{
|
| 1751 |
+
"epoch": 25.375,
|
| 1752 |
+
"grad_norm": 5.957720756530762,
|
| 1753 |
+
"learning_rate": 2.7361111111111114e-05,
|
| 1754 |
+
"loss": 0.5706,
|
| 1755 |
+
"step": 203
|
| 1756 |
+
},
|
| 1757 |
+
{
|
| 1758 |
+
"epoch": 25.5,
|
| 1759 |
+
"grad_norm": 4.830446243286133,
|
| 1760 |
+
"learning_rate": 2.7222222222222223e-05,
|
| 1761 |
+
"loss": 0.6379,
|
| 1762 |
+
"step": 204
|
| 1763 |
+
},
|
| 1764 |
+
{
|
| 1765 |
+
"epoch": 25.625,
|
| 1766 |
+
"grad_norm": 4.466456890106201,
|
| 1767 |
+
"learning_rate": 2.7083333333333332e-05,
|
| 1768 |
+
"loss": 0.6386,
|
| 1769 |
+
"step": 205
|
| 1770 |
+
},
|
| 1771 |
+
{
|
| 1772 |
+
"epoch": 25.75,
|
| 1773 |
+
"grad_norm": 3.843395948410034,
|
| 1774 |
+
"learning_rate": 2.6944444444444445e-05,
|
| 1775 |
+
"loss": 0.6142,
|
| 1776 |
+
"step": 206
|
| 1777 |
+
},
|
| 1778 |
+
{
|
| 1779 |
+
"epoch": 25.875,
|
| 1780 |
+
"grad_norm": 9.026485443115234,
|
| 1781 |
+
"learning_rate": 2.6805555555555557e-05,
|
| 1782 |
+
"loss": 0.6656,
|
| 1783 |
+
"step": 207
|
| 1784 |
+
},
|
| 1785 |
+
{
|
| 1786 |
+
"epoch": 26.0,
|
| 1787 |
+
"grad_norm": 5.378759860992432,
|
| 1788 |
+
"learning_rate": 2.6666666666666667e-05,
|
| 1789 |
+
"loss": 0.5598,
|
| 1790 |
+
"step": 208
|
| 1791 |
+
},
|
| 1792 |
+
{
|
| 1793 |
+
"epoch": 26.0,
|
| 1794 |
+
"eval_accuracy": 0.5967741935483871,
|
| 1795 |
+
"eval_auc": 0.8167016806722689,
|
| 1796 |
+
"eval_f1": 0.7252747252747253,
|
| 1797 |
+
"eval_loss": 0.5897570848464966,
|
| 1798 |
+
"eval_precision": 0.5789473684210527,
|
| 1799 |
+
"eval_recall": 0.9705882352941176,
|
| 1800 |
+
"eval_runtime": 1.8204,
|
| 1801 |
+
"eval_samples_per_second": 34.058,
|
| 1802 |
+
"eval_steps_per_second": 0.549,
|
| 1803 |
+
"step": 208
|
| 1804 |
+
},
|
| 1805 |
+
{
|
| 1806 |
+
"epoch": 26.125,
|
| 1807 |
+
"grad_norm": 6.285138130187988,
|
| 1808 |
+
"learning_rate": 2.652777777777778e-05,
|
| 1809 |
+
"loss": 0.5738,
|
| 1810 |
+
"step": 209
|
| 1811 |
+
},
|
| 1812 |
+
{
|
| 1813 |
+
"epoch": 26.25,
|
| 1814 |
+
"grad_norm": 5.52711296081543,
|
| 1815 |
+
"learning_rate": 2.6388888888888892e-05,
|
| 1816 |
+
"loss": 0.5979,
|
| 1817 |
+
"step": 210
|
| 1818 |
+
},
|
| 1819 |
+
{
|
| 1820 |
+
"epoch": 26.375,
|
| 1821 |
+
"grad_norm": 5.575936317443848,
|
| 1822 |
+
"learning_rate": 2.625e-05,
|
| 1823 |
+
"loss": 0.6169,
|
| 1824 |
+
"step": 211
|
| 1825 |
+
},
|
| 1826 |
+
{
|
| 1827 |
+
"epoch": 26.5,
|
| 1828 |
+
"grad_norm": 6.385137557983398,
|
| 1829 |
+
"learning_rate": 2.6111111111111114e-05,
|
| 1830 |
+
"loss": 0.629,
|
| 1831 |
+
"step": 212
|
| 1832 |
+
},
|
| 1833 |
+
{
|
| 1834 |
+
"epoch": 26.625,
|
| 1835 |
+
"grad_norm": 4.832798004150391,
|
| 1836 |
+
"learning_rate": 2.5972222222222226e-05,
|
| 1837 |
+
"loss": 0.635,
|
| 1838 |
+
"step": 213
|
| 1839 |
+
},
|
| 1840 |
+
{
|
| 1841 |
+
"epoch": 26.75,
|
| 1842 |
+
"grad_norm": 3.6846492290496826,
|
| 1843 |
+
"learning_rate": 2.5833333333333336e-05,
|
| 1844 |
+
"loss": 0.6198,
|
| 1845 |
+
"step": 214
|
| 1846 |
+
},
|
| 1847 |
+
{
|
| 1848 |
+
"epoch": 26.875,
|
| 1849 |
+
"grad_norm": 5.726068496704102,
|
| 1850 |
+
"learning_rate": 2.5694444444444445e-05,
|
| 1851 |
+
"loss": 0.6208,
|
| 1852 |
+
"step": 215
|
| 1853 |
+
},
|
| 1854 |
+
{
|
| 1855 |
+
"epoch": 27.0,
|
| 1856 |
+
"grad_norm": 6.713356971740723,
|
| 1857 |
+
"learning_rate": 2.5555555555555554e-05,
|
| 1858 |
+
"loss": 0.5799,
|
| 1859 |
+
"step": 216
|
| 1860 |
+
},
|
| 1861 |
+
{
|
| 1862 |
+
"epoch": 27.0,
|
| 1863 |
+
"eval_accuracy": 0.5967741935483871,
|
| 1864 |
+
"eval_auc": 0.8077731092436975,
|
| 1865 |
+
"eval_f1": 0.7252747252747253,
|
| 1866 |
+
"eval_loss": 0.5854727029800415,
|
| 1867 |
+
"eval_precision": 0.5789473684210527,
|
| 1868 |
+
"eval_recall": 0.9705882352941176,
|
| 1869 |
+
"eval_runtime": 1.8133,
|
| 1870 |
+
"eval_samples_per_second": 34.191,
|
| 1871 |
+
"eval_steps_per_second": 0.551,
|
| 1872 |
+
"step": 216
|
| 1873 |
+
},
|
| 1874 |
+
{
|
| 1875 |
+
"epoch": 27.125,
|
| 1876 |
+
"grad_norm": 6.116228103637695,
|
| 1877 |
+
"learning_rate": 2.5416666666666667e-05,
|
| 1878 |
+
"loss": 0.593,
|
| 1879 |
+
"step": 217
|
| 1880 |
+
},
|
| 1881 |
+
{
|
| 1882 |
+
"epoch": 27.25,
|
| 1883 |
+
"grad_norm": 4.514183521270752,
|
| 1884 |
+
"learning_rate": 2.527777777777778e-05,
|
| 1885 |
+
"loss": 0.6655,
|
| 1886 |
+
"step": 218
|
| 1887 |
+
},
|
| 1888 |
+
{
|
| 1889 |
+
"epoch": 27.375,
|
| 1890 |
+
"grad_norm": 3.4822494983673096,
|
| 1891 |
+
"learning_rate": 2.513888888888889e-05,
|
| 1892 |
+
"loss": 0.5884,
|
| 1893 |
+
"step": 219
|
| 1894 |
+
},
|
| 1895 |
+
{
|
| 1896 |
+
"epoch": 27.5,
|
| 1897 |
+
"grad_norm": 5.432756423950195,
|
| 1898 |
+
"learning_rate": 2.5e-05,
|
| 1899 |
+
"loss": 0.6722,
|
| 1900 |
+
"step": 220
|
| 1901 |
+
},
|
| 1902 |
+
{
|
| 1903 |
+
"epoch": 27.625,
|
| 1904 |
+
"grad_norm": 4.786170482635498,
|
| 1905 |
+
"learning_rate": 2.4861111111111114e-05,
|
| 1906 |
+
"loss": 0.6033,
|
| 1907 |
+
"step": 221
|
| 1908 |
+
},
|
| 1909 |
+
{
|
| 1910 |
+
"epoch": 27.75,
|
| 1911 |
+
"grad_norm": 4.8610968589782715,
|
| 1912 |
+
"learning_rate": 2.4722222222222223e-05,
|
| 1913 |
+
"loss": 0.5911,
|
| 1914 |
+
"step": 222
|
| 1915 |
+
},
|
| 1916 |
+
{
|
| 1917 |
+
"epoch": 27.875,
|
| 1918 |
+
"grad_norm": 6.39577579498291,
|
| 1919 |
+
"learning_rate": 2.4583333333333332e-05,
|
| 1920 |
+
"loss": 0.5838,
|
| 1921 |
+
"step": 223
|
| 1922 |
+
},
|
| 1923 |
+
{
|
| 1924 |
+
"epoch": 28.0,
|
| 1925 |
+
"grad_norm": 4.808637619018555,
|
| 1926 |
+
"learning_rate": 2.4444444444444445e-05,
|
| 1927 |
+
"loss": 0.5652,
|
| 1928 |
+
"step": 224
|
| 1929 |
+
},
|
| 1930 |
+
{
|
| 1931 |
+
"epoch": 28.0,
|
| 1932 |
+
"eval_accuracy": 0.6612903225806451,
|
| 1933 |
+
"eval_auc": 0.8103991596638656,
|
| 1934 |
+
"eval_f1": 0.7586206896551724,
|
| 1935 |
+
"eval_loss": 0.5821887254714966,
|
| 1936 |
+
"eval_precision": 0.6226415094339622,
|
| 1937 |
+
"eval_recall": 0.9705882352941176,
|
| 1938 |
+
"eval_runtime": 1.8137,
|
| 1939 |
+
"eval_samples_per_second": 34.184,
|
| 1940 |
+
"eval_steps_per_second": 0.551,
|
| 1941 |
+
"step": 224
|
| 1942 |
+
},
|
| 1943 |
+
{
|
| 1944 |
+
"epoch": 28.125,
|
| 1945 |
+
"grad_norm": 6.329916477203369,
|
| 1946 |
+
"learning_rate": 2.4305555555555558e-05,
|
| 1947 |
+
"loss": 0.6255,
|
| 1948 |
+
"step": 225
|
| 1949 |
+
},
|
| 1950 |
+
{
|
| 1951 |
+
"epoch": 28.25,
|
| 1952 |
+
"grad_norm": 6.513169765472412,
|
| 1953 |
+
"learning_rate": 2.4166666666666667e-05,
|
| 1954 |
+
"loss": 0.6316,
|
| 1955 |
+
"step": 226
|
| 1956 |
+
},
|
| 1957 |
+
{
|
| 1958 |
+
"epoch": 28.375,
|
| 1959 |
+
"grad_norm": 5.798919200897217,
|
| 1960 |
+
"learning_rate": 2.402777777777778e-05,
|
| 1961 |
+
"loss": 0.5832,
|
| 1962 |
+
"step": 227
|
| 1963 |
+
},
|
| 1964 |
+
{
|
| 1965 |
+
"epoch": 28.5,
|
| 1966 |
+
"grad_norm": 7.43931245803833,
|
| 1967 |
+
"learning_rate": 2.3888888888888892e-05,
|
| 1968 |
+
"loss": 0.6545,
|
| 1969 |
+
"step": 228
|
| 1970 |
+
},
|
| 1971 |
+
{
|
| 1972 |
+
"epoch": 28.625,
|
| 1973 |
+
"grad_norm": 11.239459037780762,
|
| 1974 |
+
"learning_rate": 2.375e-05,
|
| 1975 |
+
"loss": 0.6043,
|
| 1976 |
+
"step": 229
|
| 1977 |
+
},
|
| 1978 |
+
{
|
| 1979 |
+
"epoch": 28.75,
|
| 1980 |
+
"grad_norm": 8.446592330932617,
|
| 1981 |
+
"learning_rate": 2.361111111111111e-05,
|
| 1982 |
+
"loss": 0.6292,
|
| 1983 |
+
"step": 230
|
| 1984 |
+
},
|
| 1985 |
+
{
|
| 1986 |
+
"epoch": 28.875,
|
| 1987 |
+
"grad_norm": 4.742242336273193,
|
| 1988 |
+
"learning_rate": 2.3472222222222223e-05,
|
| 1989 |
+
"loss": 0.5746,
|
| 1990 |
+
"step": 231
|
| 1991 |
+
},
|
| 1992 |
+
{
|
| 1993 |
+
"epoch": 29.0,
|
| 1994 |
+
"grad_norm": 4.50292444229126,
|
| 1995 |
+
"learning_rate": 2.3333333333333336e-05,
|
| 1996 |
+
"loss": 0.5903,
|
| 1997 |
+
"step": 232
|
| 1998 |
+
},
|
| 1999 |
+
{
|
| 2000 |
+
"epoch": 29.0,
|
| 2001 |
+
"eval_accuracy": 0.6129032258064516,
|
| 2002 |
+
"eval_auc": 0.8235294117647058,
|
| 2003 |
+
"eval_f1": 0.7209302325581395,
|
| 2004 |
+
"eval_loss": 0.57861328125,
|
| 2005 |
+
"eval_precision": 0.5961538461538461,
|
| 2006 |
+
"eval_recall": 0.9117647058823529,
|
| 2007 |
+
"eval_runtime": 1.8119,
|
| 2008 |
+
"eval_samples_per_second": 34.219,
|
| 2009 |
+
"eval_steps_per_second": 0.552,
|
| 2010 |
+
"step": 232
|
| 2011 |
+
},
|
| 2012 |
+
{
|
| 2013 |
+
"epoch": 29.125,
|
| 2014 |
+
"grad_norm": 6.878953456878662,
|
| 2015 |
+
"learning_rate": 2.3194444444444445e-05,
|
| 2016 |
+
"loss": 0.6229,
|
| 2017 |
+
"step": 233
|
| 2018 |
+
},
|
| 2019 |
+
{
|
| 2020 |
+
"epoch": 29.25,
|
| 2021 |
+
"grad_norm": 7.358030319213867,
|
| 2022 |
+
"learning_rate": 2.3055555555555558e-05,
|
| 2023 |
+
"loss": 0.6111,
|
| 2024 |
+
"step": 234
|
| 2025 |
+
},
|
| 2026 |
+
{
|
| 2027 |
+
"epoch": 29.375,
|
| 2028 |
+
"grad_norm": 11.688603401184082,
|
| 2029 |
+
"learning_rate": 2.2916666666666667e-05,
|
| 2030 |
+
"loss": 0.6068,
|
| 2031 |
+
"step": 235
|
| 2032 |
+
},
|
| 2033 |
+
{
|
| 2034 |
+
"epoch": 29.5,
|
| 2035 |
+
"grad_norm": 5.618793487548828,
|
| 2036 |
+
"learning_rate": 2.277777777777778e-05,
|
| 2037 |
+
"loss": 0.6128,
|
| 2038 |
+
"step": 236
|
| 2039 |
+
},
|
| 2040 |
+
{
|
| 2041 |
+
"epoch": 29.625,
|
| 2042 |
+
"grad_norm": 4.052311897277832,
|
| 2043 |
+
"learning_rate": 2.263888888888889e-05,
|
| 2044 |
+
"loss": 0.5709,
|
| 2045 |
+
"step": 237
|
| 2046 |
+
},
|
| 2047 |
+
{
|
| 2048 |
+
"epoch": 29.75,
|
| 2049 |
+
"grad_norm": 7.0657958984375,
|
| 2050 |
+
"learning_rate": 2.25e-05,
|
| 2051 |
+
"loss": 0.639,
|
| 2052 |
+
"step": 238
|
| 2053 |
+
},
|
| 2054 |
+
{
|
| 2055 |
+
"epoch": 29.875,
|
| 2056 |
+
"grad_norm": 4.155570030212402,
|
| 2057 |
+
"learning_rate": 2.2361111111111114e-05,
|
| 2058 |
+
"loss": 0.6244,
|
| 2059 |
+
"step": 239
|
| 2060 |
+
},
|
| 2061 |
+
{
|
| 2062 |
+
"epoch": 30.0,
|
| 2063 |
+
"grad_norm": 8.205406188964844,
|
| 2064 |
+
"learning_rate": 2.2222222222222223e-05,
|
| 2065 |
+
"loss": 0.6824,
|
| 2066 |
+
"step": 240
|
| 2067 |
+
},
|
| 2068 |
+
{
|
| 2069 |
+
"epoch": 30.0,
|
| 2070 |
+
"eval_accuracy": 0.6290322580645161,
|
| 2071 |
+
"eval_auc": 0.8161764705882353,
|
| 2072 |
+
"eval_f1": 0.735632183908046,
|
| 2073 |
+
"eval_loss": 0.5722106695175171,
|
| 2074 |
+
"eval_precision": 0.6037735849056604,
|
| 2075 |
+
"eval_recall": 0.9411764705882353,
|
| 2076 |
+
"eval_runtime": 1.8211,
|
| 2077 |
+
"eval_samples_per_second": 34.045,
|
| 2078 |
+
"eval_steps_per_second": 0.549,
|
| 2079 |
+
"step": 240
|
| 2080 |
+
}
|
| 2081 |
+
],
|
| 2082 |
+
"logging_steps": 1,
|
| 2083 |
+
"max_steps": 400,
|
| 2084 |
+
"num_input_tokens_seen": 0,
|
| 2085 |
+
"num_train_epochs": 50,
|
| 2086 |
+
"save_steps": 500,
|
| 2087 |
+
"stateful_callbacks": {
|
| 2088 |
+
"EarlyStoppingCallback": {
|
| 2089 |
+
"args": {
|
| 2090 |
+
"early_stopping_patience": 15,
|
| 2091 |
+
"early_stopping_threshold": 0.01
|
| 2092 |
+
},
|
| 2093 |
+
"attributes": {
|
| 2094 |
+
"early_stopping_patience_counter": 0
|
| 2095 |
+
}
|
| 2096 |
+
},
|
| 2097 |
+
"TrainerControl": {
|
| 2098 |
+
"args": {
|
| 2099 |
+
"should_epoch_stop": false,
|
| 2100 |
+
"should_evaluate": false,
|
| 2101 |
+
"should_log": false,
|
| 2102 |
+
"should_save": true,
|
| 2103 |
+
"should_training_stop": false
|
| 2104 |
+
},
|
| 2105 |
+
"attributes": {}
|
| 2106 |
+
}
|
| 2107 |
+
},
|
| 2108 |
+
"total_flos": 1.567172772974592e+17,
|
| 2109 |
+
"train_batch_size": 32,
|
| 2110 |
+
"trial_name": null,
|
| 2111 |
+
"trial_params": null
|
| 2112 |
+
}
|
checkpoint-240/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:07f9f22c08f8a089d1b75ab2d8b38b2eb0436c03b91bd64a5366b1fe925e5c91
|
| 3 |
+
size 5176
|
config.json
ADDED
|
@@ -0,0 +1,50 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "microsoft/resnet-50",
|
| 3 |
+
"_num_labels": 2,
|
| 4 |
+
"architectures": [
|
| 5 |
+
"ResNetForImageClassification"
|
| 6 |
+
],
|
| 7 |
+
"depths": [
|
| 8 |
+
3,
|
| 9 |
+
4,
|
| 10 |
+
6,
|
| 11 |
+
3
|
| 12 |
+
],
|
| 13 |
+
"downsample_in_bottleneck": false,
|
| 14 |
+
"downsample_in_first_stage": false,
|
| 15 |
+
"embedding_size": 64,
|
| 16 |
+
"hidden_act": "relu",
|
| 17 |
+
"hidden_sizes": [
|
| 18 |
+
256,
|
| 19 |
+
512,
|
| 20 |
+
1024,
|
| 21 |
+
2048
|
| 22 |
+
],
|
| 23 |
+
"id2label": {
|
| 24 |
+
"0": "no",
|
| 25 |
+
"1": "yes"
|
| 26 |
+
},
|
| 27 |
+
"label2id": {
|
| 28 |
+
"no": 0,
|
| 29 |
+
"yes": 1
|
| 30 |
+
},
|
| 31 |
+
"layer_type": "bottleneck",
|
| 32 |
+
"model_type": "resnet",
|
| 33 |
+
"num_channels": 3,
|
| 34 |
+
"out_features": [
|
| 35 |
+
"stage4"
|
| 36 |
+
],
|
| 37 |
+
"out_indices": [
|
| 38 |
+
4
|
| 39 |
+
],
|
| 40 |
+
"problem_type": "single_label_classification",
|
| 41 |
+
"stage_names": [
|
| 42 |
+
"stem",
|
| 43 |
+
"stage1",
|
| 44 |
+
"stage2",
|
| 45 |
+
"stage3",
|
| 46 |
+
"stage4"
|
| 47 |
+
],
|
| 48 |
+
"torch_dtype": "float32",
|
| 49 |
+
"transformers_version": "4.44.0"
|
| 50 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c6c6678a7274fb49e5b5ede268a85d8f38c72aeabf3712bc5b538679fb32de93
|
| 3 |
+
size 94302952
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"crop_pct": 0.875,
|
| 3 |
+
"do_normalize": true,
|
| 4 |
+
"do_rescale": true,
|
| 5 |
+
"do_resize": true,
|
| 6 |
+
"image_mean": [
|
| 7 |
+
0.485,
|
| 8 |
+
0.456,
|
| 9 |
+
0.406
|
| 10 |
+
],
|
| 11 |
+
"image_processor_type": "ConvNextImageProcessor",
|
| 12 |
+
"image_std": [
|
| 13 |
+
0.229,
|
| 14 |
+
0.224,
|
| 15 |
+
0.225
|
| 16 |
+
],
|
| 17 |
+
"resample": 3,
|
| 18 |
+
"rescale_factor": 0.00392156862745098,
|
| 19 |
+
"size": {
|
| 20 |
+
"shortest_edge": 224
|
| 21 |
+
}
|
| 22 |
+
}
|
runs/Aug17_22-05-12_tufta/events.out.tfevents.1723946712.tufta.52761.0
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a7461136cffa83ab39bef08d49df5877dd06b42fdd8d30659323d31cb7789fbd
|
| 3 |
+
size 79750
|
runs/Aug17_22-05-12_tufta/events.out.tfevents.1723947259.tufta.52761.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2c932379217cded73d59f8dfc803b0f1d63242c4e5b4759208a29ed66297e8b9
|
| 3 |
+
size 607
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:07f9f22c08f8a089d1b75ab2d8b38b2eb0436c03b91bd64a5366b1fe925e5c91
|
| 3 |
+
size 5176
|
training_params.json
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"data_path": "prostate-mri-T2w-v02/autotrain-data",
|
| 3 |
+
"model": "microsoft/resnet-50",
|
| 4 |
+
"username": "Emilio407",
|
| 5 |
+
"lr": 5e-05,
|
| 6 |
+
"epochs": 50,
|
| 7 |
+
"batch_size": 32,
|
| 8 |
+
"warmup_ratio": 0.1,
|
| 9 |
+
"gradient_accumulation": 1,
|
| 10 |
+
"optimizer": "adamw_torch",
|
| 11 |
+
"scheduler": "linear",
|
| 12 |
+
"weight_decay": 0.0,
|
| 13 |
+
"max_grad_norm": 1.0,
|
| 14 |
+
"seed": 42,
|
| 15 |
+
"train_split": "train",
|
| 16 |
+
"valid_split": "validation",
|
| 17 |
+
"logging_steps": -1,
|
| 18 |
+
"project_name": "prostate-mri-T2w-v02",
|
| 19 |
+
"auto_find_batch_size": false,
|
| 20 |
+
"mixed_precision": "bf16",
|
| 21 |
+
"save_total_limit": 1,
|
| 22 |
+
"push_to_hub": true,
|
| 23 |
+
"eval_strategy": "epoch",
|
| 24 |
+
"image_column": "autotrain_image",
|
| 25 |
+
"target_column": "autotrain_label",
|
| 26 |
+
"log": "tensorboard",
|
| 27 |
+
"early_stopping_patience": 15,
|
| 28 |
+
"early_stopping_threshold": 0.01
|
| 29 |
+
}
|