Upload folder using huggingface_hub
Browse files- README.md +42 -0
- checkpoint-112/config.json +52 -0
- checkpoint-112/model.safetensors +3 -0
- checkpoint-112/optimizer.pt +3 -0
- checkpoint-112/rng_state.pth +3 -0
- checkpoint-112/scheduler.pt +3 -0
- checkpoint-112/trainer_state.json +765 -0
- checkpoint-112/training_args.bin +3 -0
- config.json +52 -0
- model.safetensors +3 -0
- preprocessor_config.json +22 -0
- training_args.bin +3 -0
- training_params.json +29 -0
README.md
ADDED
|
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
- xxhwjzx/autotrain-data-autotrain-9f2g9-xg0d2
|
| 15 |
+
---
|
| 16 |
+
|
| 17 |
+
# Model Trained Using AutoTrain
|
| 18 |
+
|
| 19 |
+
- Problem type: Image Classification
|
| 20 |
+
|
| 21 |
+
## Validation Metricsg
|
| 22 |
+
loss: 1.0950939655303955
|
| 23 |
+
|
| 24 |
+
f1_macro: 0.14814814814814817
|
| 25 |
+
|
| 26 |
+
f1_micro: 0.2857142857142857
|
| 27 |
+
|
| 28 |
+
f1_weighted: 0.126984126984127
|
| 29 |
+
|
| 30 |
+
precision_macro: 0.09523809523809523
|
| 31 |
+
|
| 32 |
+
precision_micro: 0.2857142857142857
|
| 33 |
+
|
| 34 |
+
precision_weighted: 0.08163265306122448
|
| 35 |
+
|
| 36 |
+
recall_macro: 0.3333333333333333
|
| 37 |
+
|
| 38 |
+
recall_micro: 0.2857142857142857
|
| 39 |
+
|
| 40 |
+
recall_weighted: 0.2857142857142857
|
| 41 |
+
|
| 42 |
+
accuracy: 0.2857142857142857
|
checkpoint-112/config.json
ADDED
|
@@ -0,0 +1,52 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "microsoft/resnet-50",
|
| 3 |
+
"_num_labels": 3,
|
| 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": "BJ",
|
| 25 |
+
"1": "NG",
|
| 26 |
+
"2": "OK"
|
| 27 |
+
},
|
| 28 |
+
"label2id": {
|
| 29 |
+
"BJ": 0,
|
| 30 |
+
"NG": 1,
|
| 31 |
+
"OK": 2
|
| 32 |
+
},
|
| 33 |
+
"layer_type": "bottleneck",
|
| 34 |
+
"model_type": "resnet",
|
| 35 |
+
"num_channels": 3,
|
| 36 |
+
"out_features": [
|
| 37 |
+
"stage4"
|
| 38 |
+
],
|
| 39 |
+
"out_indices": [
|
| 40 |
+
4
|
| 41 |
+
],
|
| 42 |
+
"problem_type": "single_label_classification",
|
| 43 |
+
"stage_names": [
|
| 44 |
+
"stem",
|
| 45 |
+
"stage1",
|
| 46 |
+
"stage2",
|
| 47 |
+
"stage3",
|
| 48 |
+
"stage4"
|
| 49 |
+
],
|
| 50 |
+
"torch_dtype": "float32",
|
| 51 |
+
"transformers_version": "4.36.1"
|
| 52 |
+
}
|
checkpoint-112/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8e0117cd25e066e6ca36dc9c2706a92b1f5ca7f6531956aaa864d522a85a6369
|
| 3 |
+
size 94311148
|
checkpoint-112/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c44bb07987ae269c93ea7b16e0d6f7e3d6b2f023aa2bdf9b98a6712404914baa
|
| 3 |
+
size 188244410
|
checkpoint-112/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:97663954d990e82f5018c78991197813c9f1f900354c8dd749e4d3ff6fd473bd
|
| 3 |
+
size 13990
|
checkpoint-112/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bd77e6e54da4956d70d32e91b8b222447d8ef84e8b7694c97c84cb916fa13fc4
|
| 3 |
+
size 1064
|
checkpoint-112/trainer_state.json
ADDED
|
@@ -0,0 +1,765 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 1.0950939655303955,
|
| 3 |
+
"best_model_checkpoint": "/tmp/model/checkpoint-112",
|
| 4 |
+
"epoch": 4.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 112,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.04,
|
| 13 |
+
"learning_rate": 3.5714285714285714e-06,
|
| 14 |
+
"loss": 1.0986,
|
| 15 |
+
"step": 1
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.07,
|
| 19 |
+
"learning_rate": 7.142857142857143e-06,
|
| 20 |
+
"loss": 1.0986,
|
| 21 |
+
"step": 2
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.11,
|
| 25 |
+
"learning_rate": 1.0714285714285714e-05,
|
| 26 |
+
"loss": 1.0988,
|
| 27 |
+
"step": 3
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.14,
|
| 31 |
+
"learning_rate": 1.4285714285714285e-05,
|
| 32 |
+
"loss": 1.0995,
|
| 33 |
+
"step": 4
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.18,
|
| 37 |
+
"learning_rate": 1.7857142857142855e-05,
|
| 38 |
+
"loss": 1.099,
|
| 39 |
+
"step": 5
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.21,
|
| 43 |
+
"learning_rate": 2.1428571428571428e-05,
|
| 44 |
+
"loss": 1.0999,
|
| 45 |
+
"step": 6
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.25,
|
| 49 |
+
"learning_rate": 2.5e-05,
|
| 50 |
+
"loss": 1.0976,
|
| 51 |
+
"step": 7
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.29,
|
| 55 |
+
"learning_rate": 2.857142857142857e-05,
|
| 56 |
+
"loss": 1.0999,
|
| 57 |
+
"step": 8
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.32,
|
| 61 |
+
"learning_rate": 3.214285714285714e-05,
|
| 62 |
+
"loss": 1.0993,
|
| 63 |
+
"step": 9
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.36,
|
| 67 |
+
"learning_rate": 3.571428571428571e-05,
|
| 68 |
+
"loss": 1.1003,
|
| 69 |
+
"step": 10
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.39,
|
| 73 |
+
"learning_rate": 3.928571428571428e-05,
|
| 74 |
+
"loss": 1.0971,
|
| 75 |
+
"step": 11
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.43,
|
| 79 |
+
"learning_rate": 4.2857142857142856e-05,
|
| 80 |
+
"loss": 1.096,
|
| 81 |
+
"step": 12
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.46,
|
| 85 |
+
"learning_rate": 4.642857142857143e-05,
|
| 86 |
+
"loss": 1.0932,
|
| 87 |
+
"step": 13
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.5,
|
| 91 |
+
"learning_rate": 5e-05,
|
| 92 |
+
"loss": 1.1029,
|
| 93 |
+
"step": 14
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.54,
|
| 97 |
+
"learning_rate": 5.357142857142857e-05,
|
| 98 |
+
"loss": 1.0879,
|
| 99 |
+
"step": 15
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.57,
|
| 103 |
+
"learning_rate": 5.714285714285714e-05,
|
| 104 |
+
"loss": 1.1036,
|
| 105 |
+
"step": 16
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.61,
|
| 109 |
+
"learning_rate": 6.0714285714285715e-05,
|
| 110 |
+
"loss": 1.1073,
|
| 111 |
+
"step": 17
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.64,
|
| 115 |
+
"learning_rate": 6.428571428571427e-05,
|
| 116 |
+
"loss": 1.1034,
|
| 117 |
+
"step": 18
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.68,
|
| 121 |
+
"learning_rate": 6.785714285714285e-05,
|
| 122 |
+
"loss": 1.1123,
|
| 123 |
+
"step": 19
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.71,
|
| 127 |
+
"learning_rate": 7.142857142857142e-05,
|
| 128 |
+
"loss": 1.1154,
|
| 129 |
+
"step": 20
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.75,
|
| 133 |
+
"learning_rate": 7.5e-05,
|
| 134 |
+
"loss": 1.102,
|
| 135 |
+
"step": 21
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.79,
|
| 139 |
+
"learning_rate": 7.857142857142857e-05,
|
| 140 |
+
"loss": 1.1162,
|
| 141 |
+
"step": 22
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.82,
|
| 145 |
+
"learning_rate": 8.214285714285714e-05,
|
| 146 |
+
"loss": 1.1164,
|
| 147 |
+
"step": 23
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 0.86,
|
| 151 |
+
"learning_rate": 8.571428571428571e-05,
|
| 152 |
+
"loss": 1.0999,
|
| 153 |
+
"step": 24
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.89,
|
| 157 |
+
"learning_rate": 8.928571428571429e-05,
|
| 158 |
+
"loss": 1.083,
|
| 159 |
+
"step": 25
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.93,
|
| 163 |
+
"learning_rate": 9.285714285714286e-05,
|
| 164 |
+
"loss": 1.112,
|
| 165 |
+
"step": 26
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.96,
|
| 169 |
+
"learning_rate": 9.642857142857143e-05,
|
| 170 |
+
"loss": 1.086,
|
| 171 |
+
"step": 27
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 1.0,
|
| 175 |
+
"learning_rate": 0.0001,
|
| 176 |
+
"loss": 1.0991,
|
| 177 |
+
"step": 28
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 1.0,
|
| 181 |
+
"eval_accuracy": 0.2857142857142857,
|
| 182 |
+
"eval_f1_macro": 0.14814814814814817,
|
| 183 |
+
"eval_f1_micro": 0.2857142857142857,
|
| 184 |
+
"eval_f1_weighted": 0.126984126984127,
|
| 185 |
+
"eval_loss": 1.1046772003173828,
|
| 186 |
+
"eval_precision_macro": 0.09523809523809523,
|
| 187 |
+
"eval_precision_micro": 0.2857142857142857,
|
| 188 |
+
"eval_precision_weighted": 0.08163265306122448,
|
| 189 |
+
"eval_recall_macro": 0.3333333333333333,
|
| 190 |
+
"eval_recall_micro": 0.2857142857142857,
|
| 191 |
+
"eval_recall_weighted": 0.2857142857142857,
|
| 192 |
+
"eval_runtime": 1.0364,
|
| 193 |
+
"eval_samples_per_second": 6.754,
|
| 194 |
+
"eval_steps_per_second": 3.859,
|
| 195 |
+
"step": 28
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 1.04,
|
| 199 |
+
"learning_rate": 0.00010357142857142858,
|
| 200 |
+
"loss": 1.1119,
|
| 201 |
+
"step": 29
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 1.07,
|
| 205 |
+
"learning_rate": 0.00010714285714285714,
|
| 206 |
+
"loss": 1.0864,
|
| 207 |
+
"step": 30
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 1.11,
|
| 211 |
+
"learning_rate": 0.00011071428571428571,
|
| 212 |
+
"loss": 1.0979,
|
| 213 |
+
"step": 31
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 1.14,
|
| 217 |
+
"learning_rate": 0.00011428571428571428,
|
| 218 |
+
"loss": 1.0904,
|
| 219 |
+
"step": 32
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 1.18,
|
| 223 |
+
"learning_rate": 0.00011785714285714286,
|
| 224 |
+
"loss": 1.0861,
|
| 225 |
+
"step": 33
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 1.21,
|
| 229 |
+
"learning_rate": 0.00012142857142857143,
|
| 230 |
+
"loss": 1.1155,
|
| 231 |
+
"step": 34
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 1.25,
|
| 235 |
+
"learning_rate": 0.000125,
|
| 236 |
+
"loss": 1.0844,
|
| 237 |
+
"step": 35
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 1.29,
|
| 241 |
+
"learning_rate": 0.00012857142857142855,
|
| 242 |
+
"loss": 1.1182,
|
| 243 |
+
"step": 36
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 1.32,
|
| 247 |
+
"learning_rate": 0.00013214285714285715,
|
| 248 |
+
"loss": 1.1133,
|
| 249 |
+
"step": 37
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 1.36,
|
| 253 |
+
"learning_rate": 0.0001357142857142857,
|
| 254 |
+
"loss": 1.1152,
|
| 255 |
+
"step": 38
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 1.39,
|
| 259 |
+
"learning_rate": 0.0001392857142857143,
|
| 260 |
+
"loss": 1.1101,
|
| 261 |
+
"step": 39
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 1.43,
|
| 265 |
+
"learning_rate": 0.00014285714285714284,
|
| 266 |
+
"loss": 1.1064,
|
| 267 |
+
"step": 40
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 1.46,
|
| 271 |
+
"learning_rate": 0.00014642857142857144,
|
| 272 |
+
"loss": 1.1021,
|
| 273 |
+
"step": 41
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 1.5,
|
| 277 |
+
"learning_rate": 0.00015,
|
| 278 |
+
"loss": 1.1067,
|
| 279 |
+
"step": 42
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 1.54,
|
| 283 |
+
"learning_rate": 0.0001535714285714286,
|
| 284 |
+
"loss": 1.0951,
|
| 285 |
+
"step": 43
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 1.57,
|
| 289 |
+
"learning_rate": 0.00015714285714285713,
|
| 290 |
+
"loss": 1.0946,
|
| 291 |
+
"step": 44
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 1.61,
|
| 295 |
+
"learning_rate": 0.00016071428571428573,
|
| 296 |
+
"loss": 1.0972,
|
| 297 |
+
"step": 45
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 1.64,
|
| 301 |
+
"learning_rate": 0.00016428571428571428,
|
| 302 |
+
"loss": 1.1148,
|
| 303 |
+
"step": 46
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 1.68,
|
| 307 |
+
"learning_rate": 0.00016785714285714285,
|
| 308 |
+
"loss": 1.1223,
|
| 309 |
+
"step": 47
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 1.71,
|
| 313 |
+
"learning_rate": 0.00017142857142857143,
|
| 314 |
+
"loss": 1.0951,
|
| 315 |
+
"step": 48
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 1.75,
|
| 319 |
+
"learning_rate": 0.000175,
|
| 320 |
+
"loss": 1.1189,
|
| 321 |
+
"step": 49
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 1.79,
|
| 325 |
+
"learning_rate": 0.00017857142857142857,
|
| 326 |
+
"loss": 1.1219,
|
| 327 |
+
"step": 50
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 1.82,
|
| 331 |
+
"learning_rate": 0.00018214285714285714,
|
| 332 |
+
"loss": 1.0926,
|
| 333 |
+
"step": 51
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 1.86,
|
| 337 |
+
"learning_rate": 0.00018571428571428572,
|
| 338 |
+
"loss": 1.0903,
|
| 339 |
+
"step": 52
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 1.89,
|
| 343 |
+
"learning_rate": 0.0001892857142857143,
|
| 344 |
+
"loss": 1.093,
|
| 345 |
+
"step": 53
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 1.93,
|
| 349 |
+
"learning_rate": 0.00019285714285714286,
|
| 350 |
+
"loss": 1.1166,
|
| 351 |
+
"step": 54
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 1.96,
|
| 355 |
+
"learning_rate": 0.00019642857142857144,
|
| 356 |
+
"loss": 1.0854,
|
| 357 |
+
"step": 55
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 2.0,
|
| 361 |
+
"learning_rate": 0.0002,
|
| 362 |
+
"loss": 1.1161,
|
| 363 |
+
"step": 56
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 2.0,
|
| 367 |
+
"eval_accuracy": 0.2857142857142857,
|
| 368 |
+
"eval_f1_macro": 0.14814814814814817,
|
| 369 |
+
"eval_f1_micro": 0.2857142857142857,
|
| 370 |
+
"eval_f1_weighted": 0.126984126984127,
|
| 371 |
+
"eval_loss": 1.100687861442566,
|
| 372 |
+
"eval_precision_macro": 0.09523809523809523,
|
| 373 |
+
"eval_precision_micro": 0.2857142857142857,
|
| 374 |
+
"eval_precision_weighted": 0.08163265306122448,
|
| 375 |
+
"eval_recall_macro": 0.3333333333333333,
|
| 376 |
+
"eval_recall_micro": 0.2857142857142857,
|
| 377 |
+
"eval_recall_weighted": 0.2857142857142857,
|
| 378 |
+
"eval_runtime": 0.8746,
|
| 379 |
+
"eval_samples_per_second": 8.004,
|
| 380 |
+
"eval_steps_per_second": 4.574,
|
| 381 |
+
"step": 56
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 2.04,
|
| 385 |
+
"learning_rate": 0.00020357142857142858,
|
| 386 |
+
"loss": 1.1051,
|
| 387 |
+
"step": 57
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 2.07,
|
| 391 |
+
"learning_rate": 0.00020714285714285716,
|
| 392 |
+
"loss": 1.106,
|
| 393 |
+
"step": 58
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 2.11,
|
| 397 |
+
"learning_rate": 0.00021071428571428573,
|
| 398 |
+
"loss": 1.1071,
|
| 399 |
+
"step": 59
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 2.14,
|
| 403 |
+
"learning_rate": 0.00021428571428571427,
|
| 404 |
+
"loss": 1.104,
|
| 405 |
+
"step": 60
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 2.18,
|
| 409 |
+
"learning_rate": 0.00021785714285714287,
|
| 410 |
+
"loss": 1.0954,
|
| 411 |
+
"step": 61
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 2.21,
|
| 415 |
+
"learning_rate": 0.00022142857142857142,
|
| 416 |
+
"loss": 1.1252,
|
| 417 |
+
"step": 62
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 2.25,
|
| 421 |
+
"learning_rate": 0.00022500000000000002,
|
| 422 |
+
"loss": 1.0935,
|
| 423 |
+
"step": 63
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 2.29,
|
| 427 |
+
"learning_rate": 0.00022857142857142857,
|
| 428 |
+
"loss": 1.0953,
|
| 429 |
+
"step": 64
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 2.32,
|
| 433 |
+
"learning_rate": 0.00023214285714285717,
|
| 434 |
+
"loss": 1.0697,
|
| 435 |
+
"step": 65
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 2.36,
|
| 439 |
+
"learning_rate": 0.0002357142857142857,
|
| 440 |
+
"loss": 1.1385,
|
| 441 |
+
"step": 66
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 2.39,
|
| 445 |
+
"learning_rate": 0.0002392857142857143,
|
| 446 |
+
"loss": 1.0618,
|
| 447 |
+
"step": 67
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 2.43,
|
| 451 |
+
"learning_rate": 0.00024285714285714286,
|
| 452 |
+
"loss": 1.1012,
|
| 453 |
+
"step": 68
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 2.46,
|
| 457 |
+
"learning_rate": 0.00024642857142857143,
|
| 458 |
+
"loss": 1.1554,
|
| 459 |
+
"step": 69
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 2.5,
|
| 463 |
+
"learning_rate": 0.00025,
|
| 464 |
+
"loss": 1.1472,
|
| 465 |
+
"step": 70
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 2.54,
|
| 469 |
+
"learning_rate": 0.0002535714285714286,
|
| 470 |
+
"loss": 1.0984,
|
| 471 |
+
"step": 71
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 2.57,
|
| 475 |
+
"learning_rate": 0.0002571428571428571,
|
| 476 |
+
"loss": 1.0957,
|
| 477 |
+
"step": 72
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 2.61,
|
| 481 |
+
"learning_rate": 0.0002607142857142857,
|
| 482 |
+
"loss": 1.0447,
|
| 483 |
+
"step": 73
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 2.64,
|
| 487 |
+
"learning_rate": 0.0002642857142857143,
|
| 488 |
+
"loss": 1.0864,
|
| 489 |
+
"step": 74
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 2.68,
|
| 493 |
+
"learning_rate": 0.00026785714285714287,
|
| 494 |
+
"loss": 1.0751,
|
| 495 |
+
"step": 75
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 2.71,
|
| 499 |
+
"learning_rate": 0.0002714285714285714,
|
| 500 |
+
"loss": 1.179,
|
| 501 |
+
"step": 76
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 2.75,
|
| 505 |
+
"learning_rate": 0.000275,
|
| 506 |
+
"loss": 1.0559,
|
| 507 |
+
"step": 77
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 2.79,
|
| 511 |
+
"learning_rate": 0.0002785714285714286,
|
| 512 |
+
"loss": 1.1938,
|
| 513 |
+
"step": 78
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 2.82,
|
| 517 |
+
"learning_rate": 0.00028214285714285716,
|
| 518 |
+
"loss": 1.0462,
|
| 519 |
+
"step": 79
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 2.86,
|
| 523 |
+
"learning_rate": 0.0002857142857142857,
|
| 524 |
+
"loss": 1.207,
|
| 525 |
+
"step": 80
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 2.89,
|
| 529 |
+
"learning_rate": 0.0002892857142857143,
|
| 530 |
+
"loss": 1.0474,
|
| 531 |
+
"step": 81
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 2.93,
|
| 535 |
+
"learning_rate": 0.0002928571428571429,
|
| 536 |
+
"loss": 1.1944,
|
| 537 |
+
"step": 82
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 2.96,
|
| 541 |
+
"learning_rate": 0.00029642857142857145,
|
| 542 |
+
"loss": 1.0709,
|
| 543 |
+
"step": 83
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 3.0,
|
| 547 |
+
"learning_rate": 0.0003,
|
| 548 |
+
"loss": 1.0382,
|
| 549 |
+
"step": 84
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 3.0,
|
| 553 |
+
"eval_accuracy": 0.2857142857142857,
|
| 554 |
+
"eval_f1_macro": 0.14814814814814817,
|
| 555 |
+
"eval_f1_micro": 0.2857142857142857,
|
| 556 |
+
"eval_f1_weighted": 0.126984126984127,
|
| 557 |
+
"eval_loss": 1.0976771116256714,
|
| 558 |
+
"eval_precision_macro": 0.09523809523809523,
|
| 559 |
+
"eval_precision_micro": 0.2857142857142857,
|
| 560 |
+
"eval_precision_weighted": 0.08163265306122448,
|
| 561 |
+
"eval_recall_macro": 0.3333333333333333,
|
| 562 |
+
"eval_recall_micro": 0.2857142857142857,
|
| 563 |
+
"eval_recall_weighted": 0.2857142857142857,
|
| 564 |
+
"eval_runtime": 0.9461,
|
| 565 |
+
"eval_samples_per_second": 7.398,
|
| 566 |
+
"eval_steps_per_second": 4.228,
|
| 567 |
+
"step": 84
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 3.04,
|
| 571 |
+
"learning_rate": 0.00030357142857142855,
|
| 572 |
+
"loss": 1.2095,
|
| 573 |
+
"step": 85
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 3.07,
|
| 577 |
+
"learning_rate": 0.0003071428571428572,
|
| 578 |
+
"loss": 1.0712,
|
| 579 |
+
"step": 86
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 3.11,
|
| 583 |
+
"learning_rate": 0.00031071428571428575,
|
| 584 |
+
"loss": 0.9957,
|
| 585 |
+
"step": 87
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 3.14,
|
| 589 |
+
"learning_rate": 0.00031428571428571427,
|
| 590 |
+
"loss": 1.2297,
|
| 591 |
+
"step": 88
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 3.18,
|
| 595 |
+
"learning_rate": 0.00031785714285714284,
|
| 596 |
+
"loss": 1.2472,
|
| 597 |
+
"step": 89
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 3.21,
|
| 601 |
+
"learning_rate": 0.00032142857142857147,
|
| 602 |
+
"loss": 1.2194,
|
| 603 |
+
"step": 90
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 3.25,
|
| 607 |
+
"learning_rate": 0.00032500000000000004,
|
| 608 |
+
"loss": 1.0032,
|
| 609 |
+
"step": 91
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 3.29,
|
| 613 |
+
"learning_rate": 0.00032857142857142856,
|
| 614 |
+
"loss": 1.0049,
|
| 615 |
+
"step": 92
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 3.32,
|
| 619 |
+
"learning_rate": 0.00033214285714285713,
|
| 620 |
+
"loss": 1.075,
|
| 621 |
+
"step": 93
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 3.36,
|
| 625 |
+
"learning_rate": 0.0003357142857142857,
|
| 626 |
+
"loss": 1.0702,
|
| 627 |
+
"step": 94
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 3.39,
|
| 631 |
+
"learning_rate": 0.00033928571428571433,
|
| 632 |
+
"loss": 1.0675,
|
| 633 |
+
"step": 95
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 3.43,
|
| 637 |
+
"learning_rate": 0.00034285714285714285,
|
| 638 |
+
"loss": 1.0613,
|
| 639 |
+
"step": 96
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 3.46,
|
| 643 |
+
"learning_rate": 0.0003464285714285714,
|
| 644 |
+
"loss": 1.2716,
|
| 645 |
+
"step": 97
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 3.5,
|
| 649 |
+
"learning_rate": 0.00035,
|
| 650 |
+
"loss": 0.9875,
|
| 651 |
+
"step": 98
|
| 652 |
+
},
|
| 653 |
+
{
|
| 654 |
+
"epoch": 3.54,
|
| 655 |
+
"learning_rate": 0.0003535714285714286,
|
| 656 |
+
"loss": 1.2666,
|
| 657 |
+
"step": 99
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 3.57,
|
| 661 |
+
"learning_rate": 0.00035714285714285714,
|
| 662 |
+
"loss": 1.0338,
|
| 663 |
+
"step": 100
|
| 664 |
+
},
|
| 665 |
+
{
|
| 666 |
+
"epoch": 3.61,
|
| 667 |
+
"learning_rate": 0.0003607142857142857,
|
| 668 |
+
"loss": 1.0024,
|
| 669 |
+
"step": 101
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 3.64,
|
| 673 |
+
"learning_rate": 0.0003642857142857143,
|
| 674 |
+
"loss": 1.3218,
|
| 675 |
+
"step": 102
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 3.68,
|
| 679 |
+
"learning_rate": 0.0003678571428571429,
|
| 680 |
+
"loss": 1.0089,
|
| 681 |
+
"step": 103
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 3.71,
|
| 685 |
+
"learning_rate": 0.00037142857142857143,
|
| 686 |
+
"loss": 1.0051,
|
| 687 |
+
"step": 104
|
| 688 |
+
},
|
| 689 |
+
{
|
| 690 |
+
"epoch": 3.75,
|
| 691 |
+
"learning_rate": 0.000375,
|
| 692 |
+
"loss": 1.0034,
|
| 693 |
+
"step": 105
|
| 694 |
+
},
|
| 695 |
+
{
|
| 696 |
+
"epoch": 3.79,
|
| 697 |
+
"learning_rate": 0.0003785714285714286,
|
| 698 |
+
"loss": 1.0045,
|
| 699 |
+
"step": 106
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 3.82,
|
| 703 |
+
"learning_rate": 0.0003821428571428571,
|
| 704 |
+
"loss": 1.0025,
|
| 705 |
+
"step": 107
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 3.86,
|
| 709 |
+
"learning_rate": 0.0003857142857142857,
|
| 710 |
+
"loss": 0.9845,
|
| 711 |
+
"step": 108
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 3.89,
|
| 715 |
+
"learning_rate": 0.0003892857142857143,
|
| 716 |
+
"loss": 0.9621,
|
| 717 |
+
"step": 109
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 3.93,
|
| 721 |
+
"learning_rate": 0.0003928571428571429,
|
| 722 |
+
"loss": 0.9943,
|
| 723 |
+
"step": 110
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 3.96,
|
| 727 |
+
"learning_rate": 0.0003964285714285714,
|
| 728 |
+
"loss": 1.4232,
|
| 729 |
+
"step": 111
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 4.0,
|
| 733 |
+
"learning_rate": 0.0004,
|
| 734 |
+
"loss": 1.4025,
|
| 735 |
+
"step": 112
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 4.0,
|
| 739 |
+
"eval_accuracy": 0.2857142857142857,
|
| 740 |
+
"eval_f1_macro": 0.14814814814814817,
|
| 741 |
+
"eval_f1_micro": 0.2857142857142857,
|
| 742 |
+
"eval_f1_weighted": 0.126984126984127,
|
| 743 |
+
"eval_loss": 1.0950939655303955,
|
| 744 |
+
"eval_precision_macro": 0.09523809523809523,
|
| 745 |
+
"eval_precision_micro": 0.2857142857142857,
|
| 746 |
+
"eval_precision_weighted": 0.08163265306122448,
|
| 747 |
+
"eval_recall_macro": 0.3333333333333333,
|
| 748 |
+
"eval_recall_micro": 0.2857142857142857,
|
| 749 |
+
"eval_recall_weighted": 0.2857142857142857,
|
| 750 |
+
"eval_runtime": 0.9362,
|
| 751 |
+
"eval_samples_per_second": 7.477,
|
| 752 |
+
"eval_steps_per_second": 4.273,
|
| 753 |
+
"step": 112
|
| 754 |
+
}
|
| 755 |
+
],
|
| 756 |
+
"logging_steps": 1,
|
| 757 |
+
"max_steps": 2800,
|
| 758 |
+
"num_input_tokens_seen": 0,
|
| 759 |
+
"num_train_epochs": 100,
|
| 760 |
+
"save_steps": 500,
|
| 761 |
+
"total_flos": 2378572450136064.0,
|
| 762 |
+
"train_batch_size": 1,
|
| 763 |
+
"trial_name": null,
|
| 764 |
+
"trial_params": null
|
| 765 |
+
}
|
checkpoint-112/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ad003ac43cbdcc5ba1d6de8813edc7c73ef3fb0b65cb16aa2f387f805fed31f6
|
| 3 |
+
size 4728
|
config.json
ADDED
|
@@ -0,0 +1,52 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "microsoft/resnet-50",
|
| 3 |
+
"_num_labels": 3,
|
| 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": "BJ",
|
| 25 |
+
"1": "NG",
|
| 26 |
+
"2": "OK"
|
| 27 |
+
},
|
| 28 |
+
"label2id": {
|
| 29 |
+
"BJ": 0,
|
| 30 |
+
"NG": 1,
|
| 31 |
+
"OK": 2
|
| 32 |
+
},
|
| 33 |
+
"layer_type": "bottleneck",
|
| 34 |
+
"model_type": "resnet",
|
| 35 |
+
"num_channels": 3,
|
| 36 |
+
"out_features": [
|
| 37 |
+
"stage4"
|
| 38 |
+
],
|
| 39 |
+
"out_indices": [
|
| 40 |
+
4
|
| 41 |
+
],
|
| 42 |
+
"problem_type": "single_label_classification",
|
| 43 |
+
"stage_names": [
|
| 44 |
+
"stem",
|
| 45 |
+
"stage1",
|
| 46 |
+
"stage2",
|
| 47 |
+
"stage3",
|
| 48 |
+
"stage4"
|
| 49 |
+
],
|
| 50 |
+
"torch_dtype": "float32",
|
| 51 |
+
"transformers_version": "4.36.1"
|
| 52 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8e0117cd25e066e6ca36dc9c2706a92b1f5ca7f6531956aaa864d522a85a6369
|
| 3 |
+
size 94311148
|
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 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ad003ac43cbdcc5ba1d6de8813edc7c73ef3fb0b65cb16aa2f387f805fed31f6
|
| 3 |
+
size 4728
|
training_params.json
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"data_path": "xxhwjzx/autotrain-data-autotrain-9f2g9-xg0d2",
|
| 3 |
+
"model": "microsoft/resnet-50",
|
| 4 |
+
"username": "xxhwjzx",
|
| 5 |
+
"lr": 0.001,
|
| 6 |
+
"epochs": 100,
|
| 7 |
+
"batch_size": 1,
|
| 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": "/tmp/model",
|
| 19 |
+
"auto_find_batch_size": false,
|
| 20 |
+
"mixed_precision": null,
|
| 21 |
+
"save_total_limit": 1,
|
| 22 |
+
"save_strategy": "epoch",
|
| 23 |
+
"push_to_hub": true,
|
| 24 |
+
"repo_id": "xxhwjzx/autotrain-9f2g9-xg0d2",
|
| 25 |
+
"evaluation_strategy": "epoch",
|
| 26 |
+
"image_column": "autotrain_image",
|
| 27 |
+
"target_column": "autotrain_label",
|
| 28 |
+
"log": "none"
|
| 29 |
+
}
|