Commit
•
c6e9748
1
Parent(s):
fa51f3f
Upload folder using huggingface_hub
Browse files- README.md +42 -0
- checkpoint-190/config.json +56 -0
- checkpoint-190/model.safetensors +3 -0
- checkpoint-190/optimizer.pt +3 -0
- checkpoint-190/rng_state.pth +3 -0
- checkpoint-190/scheduler.pt +3 -0
- checkpoint-190/trainer_state.json +1341 -0
- checkpoint-190/training_args.bin +3 -0
- config.json +56 -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 |
+
- tosullivan/autotrain-data-weapon_1
|
| 15 |
+
---
|
| 16 |
+
|
| 17 |
+
# Model Trained Using AutoTrain
|
| 18 |
+
|
| 19 |
+
- Problem type: Image Classification
|
| 20 |
+
|
| 21 |
+
## Validation Metricsg
|
| 22 |
+
loss: 0.8072579503059387
|
| 23 |
+
|
| 24 |
+
f1_macro: 0.608552036199095
|
| 25 |
+
|
| 26 |
+
f1_micro: 0.717948717948718
|
| 27 |
+
|
| 28 |
+
f1_weighted: 0.6738484743009631
|
| 29 |
+
|
| 30 |
+
precision_macro: 0.5864285714285714
|
| 31 |
+
|
| 32 |
+
precision_micro: 0.717948717948718
|
| 33 |
+
|
| 34 |
+
precision_weighted: 0.6695970695970695
|
| 35 |
+
|
| 36 |
+
recall_macro: 0.6633333333333333
|
| 37 |
+
|
| 38 |
+
recall_micro: 0.717948717948718
|
| 39 |
+
|
| 40 |
+
recall_weighted: 0.717948717948718
|
| 41 |
+
|
| 42 |
+
accuracy: 0.717948717948718
|
checkpoint-190/config.json
ADDED
|
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "microsoft/resnet-50",
|
| 3 |
+
"_num_labels": 5,
|
| 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": "9K111 Fagot",
|
| 25 |
+
"1": "9K115-2 Metis-M",
|
| 26 |
+
"2": "9M113 Konkurs",
|
| 27 |
+
"3": "9M133 Kornet",
|
| 28 |
+
"4": "BGM-71 TOW"
|
| 29 |
+
},
|
| 30 |
+
"label2id": {
|
| 31 |
+
"9K111 Fagot": 0,
|
| 32 |
+
"9K115-2 Metis-M": 1,
|
| 33 |
+
"9M113 Konkurs": 2,
|
| 34 |
+
"9M133 Kornet": 3,
|
| 35 |
+
"BGM-71 TOW": 4
|
| 36 |
+
},
|
| 37 |
+
"layer_type": "bottleneck",
|
| 38 |
+
"model_type": "resnet",
|
| 39 |
+
"num_channels": 3,
|
| 40 |
+
"out_features": [
|
| 41 |
+
"stage4"
|
| 42 |
+
],
|
| 43 |
+
"out_indices": [
|
| 44 |
+
4
|
| 45 |
+
],
|
| 46 |
+
"problem_type": "single_label_classification",
|
| 47 |
+
"stage_names": [
|
| 48 |
+
"stem",
|
| 49 |
+
"stage1",
|
| 50 |
+
"stage2",
|
| 51 |
+
"stage3",
|
| 52 |
+
"stage4"
|
| 53 |
+
],
|
| 54 |
+
"torch_dtype": "float32",
|
| 55 |
+
"transformers_version": "4.36.1"
|
| 56 |
+
}
|
checkpoint-190/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c4e5595afb95ccd017d4e243d490ccbec395c785588dce4134683b536ca83a9d
|
| 3 |
+
size 94327540
|
checkpoint-190/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5b27a23a5f51ef2806fc09615183254e5cec9be6aed699f9cbc2c2998a43fec6
|
| 3 |
+
size 188281658
|
checkpoint-190/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:51cee84f3ca5cfe5a5541387d6ef4ab09b1764a511afd8555d247c7214819ca6
|
| 3 |
+
size 14244
|
checkpoint-190/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0a883c947c9738c67d68824c2e6ce3bc42d2b7d7d66bcfcd7ab1e83c29baf123
|
| 3 |
+
size 1064
|
checkpoint-190/trainer_state.json
ADDED
|
@@ -0,0 +1,1341 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.8072579503059387,
|
| 3 |
+
"best_model_checkpoint": "/tmp/model/checkpoint-190",
|
| 4 |
+
"epoch": 10.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 190,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.05,
|
| 13 |
+
"learning_rate": 5.263157894736843e-06,
|
| 14 |
+
"loss": 1.6094,
|
| 15 |
+
"step": 1
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.11,
|
| 19 |
+
"learning_rate": 1.0526315789473686e-05,
|
| 20 |
+
"loss": 1.6094,
|
| 21 |
+
"step": 2
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.16,
|
| 25 |
+
"learning_rate": 1.5789473684210526e-05,
|
| 26 |
+
"loss": 1.6096,
|
| 27 |
+
"step": 3
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.21,
|
| 31 |
+
"learning_rate": 2.1052631578947372e-05,
|
| 32 |
+
"loss": 1.6089,
|
| 33 |
+
"step": 4
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.26,
|
| 37 |
+
"learning_rate": 2.6315789473684212e-05,
|
| 38 |
+
"loss": 1.6085,
|
| 39 |
+
"step": 5
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.32,
|
| 43 |
+
"learning_rate": 3.157894736842105e-05,
|
| 44 |
+
"loss": 1.6068,
|
| 45 |
+
"step": 6
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.37,
|
| 49 |
+
"learning_rate": 3.68421052631579e-05,
|
| 50 |
+
"loss": 1.6105,
|
| 51 |
+
"step": 7
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.42,
|
| 55 |
+
"learning_rate": 4.2105263157894745e-05,
|
| 56 |
+
"loss": 1.6058,
|
| 57 |
+
"step": 8
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.47,
|
| 61 |
+
"learning_rate": 4.736842105263158e-05,
|
| 62 |
+
"loss": 1.6108,
|
| 63 |
+
"step": 9
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.53,
|
| 67 |
+
"learning_rate": 5.2631578947368424e-05,
|
| 68 |
+
"loss": 1.6079,
|
| 69 |
+
"step": 10
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.58,
|
| 73 |
+
"learning_rate": 5.7894736842105274e-05,
|
| 74 |
+
"loss": 1.6044,
|
| 75 |
+
"step": 11
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.63,
|
| 79 |
+
"learning_rate": 6.31578947368421e-05,
|
| 80 |
+
"loss": 1.6069,
|
| 81 |
+
"step": 12
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.68,
|
| 85 |
+
"learning_rate": 6.842105263157895e-05,
|
| 86 |
+
"loss": 1.6007,
|
| 87 |
+
"step": 13
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.74,
|
| 91 |
+
"learning_rate": 7.36842105263158e-05,
|
| 92 |
+
"loss": 1.6083,
|
| 93 |
+
"step": 14
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.79,
|
| 97 |
+
"learning_rate": 7.894736842105263e-05,
|
| 98 |
+
"loss": 1.6077,
|
| 99 |
+
"step": 15
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.84,
|
| 103 |
+
"learning_rate": 8.421052631578949e-05,
|
| 104 |
+
"loss": 1.5968,
|
| 105 |
+
"step": 16
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.89,
|
| 109 |
+
"learning_rate": 8.947368421052632e-05,
|
| 110 |
+
"loss": 1.5903,
|
| 111 |
+
"step": 17
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.95,
|
| 115 |
+
"learning_rate": 9.473684210526316e-05,
|
| 116 |
+
"loss": 1.6045,
|
| 117 |
+
"step": 18
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 1.0,
|
| 121 |
+
"learning_rate": 0.0001,
|
| 122 |
+
"loss": 1.5974,
|
| 123 |
+
"step": 19
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 1.0,
|
| 127 |
+
"eval_accuracy": 0.3076923076923077,
|
| 128 |
+
"eval_f1_macro": 0.09411764705882353,
|
| 129 |
+
"eval_f1_micro": 0.3076923076923077,
|
| 130 |
+
"eval_f1_weighted": 0.14479638009049772,
|
| 131 |
+
"eval_loss": 1.5974059104919434,
|
| 132 |
+
"eval_precision_macro": 0.06153846153846154,
|
| 133 |
+
"eval_precision_micro": 0.3076923076923077,
|
| 134 |
+
"eval_precision_weighted": 0.09467455621301776,
|
| 135 |
+
"eval_recall_macro": 0.2,
|
| 136 |
+
"eval_recall_micro": 0.3076923076923077,
|
| 137 |
+
"eval_recall_weighted": 0.3076923076923077,
|
| 138 |
+
"eval_runtime": 0.2784,
|
| 139 |
+
"eval_samples_per_second": 140.073,
|
| 140 |
+
"eval_steps_per_second": 10.775,
|
| 141 |
+
"step": 19
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 1.05,
|
| 145 |
+
"learning_rate": 0.00010526315789473685,
|
| 146 |
+
"loss": 1.5782,
|
| 147 |
+
"step": 20
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 1.11,
|
| 151 |
+
"learning_rate": 0.00011052631578947368,
|
| 152 |
+
"loss": 1.5568,
|
| 153 |
+
"step": 21
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 1.16,
|
| 157 |
+
"learning_rate": 0.00011578947368421055,
|
| 158 |
+
"loss": 1.603,
|
| 159 |
+
"step": 22
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 1.21,
|
| 163 |
+
"learning_rate": 0.00011578947368421055,
|
| 164 |
+
"loss": 1.5393,
|
| 165 |
+
"step": 23
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 1.26,
|
| 169 |
+
"learning_rate": 0.00012105263157894738,
|
| 170 |
+
"loss": 1.5972,
|
| 171 |
+
"step": 24
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 1.32,
|
| 175 |
+
"learning_rate": 0.0001263157894736842,
|
| 176 |
+
"loss": 1.6077,
|
| 177 |
+
"step": 25
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 1.37,
|
| 181 |
+
"learning_rate": 0.00013157894736842105,
|
| 182 |
+
"loss": 1.5841,
|
| 183 |
+
"step": 26
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 1.42,
|
| 187 |
+
"learning_rate": 0.0001368421052631579,
|
| 188 |
+
"loss": 1.5846,
|
| 189 |
+
"step": 27
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 1.47,
|
| 193 |
+
"learning_rate": 0.00014210526315789476,
|
| 194 |
+
"loss": 1.5916,
|
| 195 |
+
"step": 28
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 1.53,
|
| 199 |
+
"learning_rate": 0.0001473684210526316,
|
| 200 |
+
"loss": 1.5476,
|
| 201 |
+
"step": 29
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 1.58,
|
| 205 |
+
"learning_rate": 0.00015263157894736842,
|
| 206 |
+
"loss": 1.6294,
|
| 207 |
+
"step": 30
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 1.63,
|
| 211 |
+
"learning_rate": 0.00015789473684210527,
|
| 212 |
+
"loss": 1.571,
|
| 213 |
+
"step": 31
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 1.68,
|
| 217 |
+
"learning_rate": 0.0001631578947368421,
|
| 218 |
+
"loss": 1.6475,
|
| 219 |
+
"step": 32
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 1.74,
|
| 223 |
+
"learning_rate": 0.00016842105263157898,
|
| 224 |
+
"loss": 1.5652,
|
| 225 |
+
"step": 33
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 1.79,
|
| 229 |
+
"learning_rate": 0.0001736842105263158,
|
| 230 |
+
"loss": 1.5198,
|
| 231 |
+
"step": 34
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 1.84,
|
| 235 |
+
"learning_rate": 0.00017894736842105264,
|
| 236 |
+
"loss": 1.5658,
|
| 237 |
+
"step": 35
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 1.89,
|
| 241 |
+
"learning_rate": 0.00018421052631578948,
|
| 242 |
+
"loss": 1.5823,
|
| 243 |
+
"step": 36
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 1.95,
|
| 247 |
+
"learning_rate": 0.00018947368421052632,
|
| 248 |
+
"loss": 1.5813,
|
| 249 |
+
"step": 37
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 2.0,
|
| 253 |
+
"learning_rate": 0.00019473684210526317,
|
| 254 |
+
"loss": 1.5338,
|
| 255 |
+
"step": 38
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 2.0,
|
| 259 |
+
"eval_accuracy": 0.3076923076923077,
|
| 260 |
+
"eval_f1_macro": 0.09411764705882353,
|
| 261 |
+
"eval_f1_micro": 0.3076923076923077,
|
| 262 |
+
"eval_f1_weighted": 0.14479638009049772,
|
| 263 |
+
"eval_loss": 1.571889877319336,
|
| 264 |
+
"eval_precision_macro": 0.06153846153846154,
|
| 265 |
+
"eval_precision_micro": 0.3076923076923077,
|
| 266 |
+
"eval_precision_weighted": 0.09467455621301776,
|
| 267 |
+
"eval_recall_macro": 0.2,
|
| 268 |
+
"eval_recall_micro": 0.3076923076923077,
|
| 269 |
+
"eval_recall_weighted": 0.3076923076923077,
|
| 270 |
+
"eval_runtime": 0.1048,
|
| 271 |
+
"eval_samples_per_second": 372.122,
|
| 272 |
+
"eval_steps_per_second": 28.625,
|
| 273 |
+
"step": 38
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 2.05,
|
| 277 |
+
"learning_rate": 0.0002,
|
| 278 |
+
"loss": 1.5117,
|
| 279 |
+
"step": 39
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 2.11,
|
| 283 |
+
"learning_rate": 0.00020526315789473685,
|
| 284 |
+
"loss": 1.4995,
|
| 285 |
+
"step": 40
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 2.16,
|
| 289 |
+
"learning_rate": 0.0002105263157894737,
|
| 290 |
+
"loss": 1.6392,
|
| 291 |
+
"step": 41
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 2.21,
|
| 295 |
+
"learning_rate": 0.00021578947368421054,
|
| 296 |
+
"loss": 1.4529,
|
| 297 |
+
"step": 42
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 2.26,
|
| 301 |
+
"learning_rate": 0.00022105263157894735,
|
| 302 |
+
"loss": 1.5848,
|
| 303 |
+
"step": 43
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 2.32,
|
| 307 |
+
"learning_rate": 0.0002263157894736842,
|
| 308 |
+
"loss": 1.5591,
|
| 309 |
+
"step": 44
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 2.37,
|
| 313 |
+
"learning_rate": 0.0002315789473684211,
|
| 314 |
+
"loss": 1.5641,
|
| 315 |
+
"step": 45
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 2.42,
|
| 319 |
+
"learning_rate": 0.0002368421052631579,
|
| 320 |
+
"loss": 1.499,
|
| 321 |
+
"step": 46
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 2.47,
|
| 325 |
+
"learning_rate": 0.00024210526315789475,
|
| 326 |
+
"loss": 1.6476,
|
| 327 |
+
"step": 47
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 2.53,
|
| 331 |
+
"learning_rate": 0.0002473684210526316,
|
| 332 |
+
"loss": 1.4727,
|
| 333 |
+
"step": 48
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 2.58,
|
| 337 |
+
"learning_rate": 0.0002526315789473684,
|
| 338 |
+
"loss": 1.5519,
|
| 339 |
+
"step": 49
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 2.63,
|
| 343 |
+
"learning_rate": 0.0002578947368421053,
|
| 344 |
+
"loss": 1.5057,
|
| 345 |
+
"step": 50
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 2.68,
|
| 349 |
+
"learning_rate": 0.0002631578947368421,
|
| 350 |
+
"loss": 1.6801,
|
| 351 |
+
"step": 51
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 2.74,
|
| 355 |
+
"learning_rate": 0.00026842105263157897,
|
| 356 |
+
"loss": 1.5518,
|
| 357 |
+
"step": 52
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 2.79,
|
| 361 |
+
"learning_rate": 0.0002736842105263158,
|
| 362 |
+
"loss": 1.4608,
|
| 363 |
+
"step": 53
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 2.84,
|
| 367 |
+
"learning_rate": 0.0002789473684210526,
|
| 368 |
+
"loss": 1.5961,
|
| 369 |
+
"step": 54
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 2.89,
|
| 373 |
+
"learning_rate": 0.0002842105263157895,
|
| 374 |
+
"loss": 1.3564,
|
| 375 |
+
"step": 55
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 2.95,
|
| 379 |
+
"learning_rate": 0.00028947368421052634,
|
| 380 |
+
"loss": 1.5493,
|
| 381 |
+
"step": 56
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 3.0,
|
| 385 |
+
"learning_rate": 0.0002947368421052632,
|
| 386 |
+
"loss": 1.5723,
|
| 387 |
+
"step": 57
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 3.0,
|
| 391 |
+
"eval_accuracy": 0.3076923076923077,
|
| 392 |
+
"eval_f1_macro": 0.09411764705882353,
|
| 393 |
+
"eval_f1_micro": 0.3076923076923077,
|
| 394 |
+
"eval_f1_weighted": 0.14479638009049772,
|
| 395 |
+
"eval_loss": 1.5472002029418945,
|
| 396 |
+
"eval_precision_macro": 0.06153846153846154,
|
| 397 |
+
"eval_precision_micro": 0.3076923076923077,
|
| 398 |
+
"eval_precision_weighted": 0.09467455621301776,
|
| 399 |
+
"eval_recall_macro": 0.2,
|
| 400 |
+
"eval_recall_micro": 0.3076923076923077,
|
| 401 |
+
"eval_recall_weighted": 0.3076923076923077,
|
| 402 |
+
"eval_runtime": 0.1034,
|
| 403 |
+
"eval_samples_per_second": 377.243,
|
| 404 |
+
"eval_steps_per_second": 29.019,
|
| 405 |
+
"step": 57
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 3.05,
|
| 409 |
+
"learning_rate": 0.00030000000000000003,
|
| 410 |
+
"loss": 1.3807,
|
| 411 |
+
"step": 58
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 3.11,
|
| 415 |
+
"learning_rate": 0.00030526315789473684,
|
| 416 |
+
"loss": 1.4009,
|
| 417 |
+
"step": 59
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 3.16,
|
| 421 |
+
"learning_rate": 0.0003105263157894737,
|
| 422 |
+
"loss": 1.3475,
|
| 423 |
+
"step": 60
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 3.21,
|
| 427 |
+
"learning_rate": 0.00031578947368421053,
|
| 428 |
+
"loss": 1.4923,
|
| 429 |
+
"step": 61
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 3.26,
|
| 433 |
+
"learning_rate": 0.0003210526315789474,
|
| 434 |
+
"loss": 1.3802,
|
| 435 |
+
"step": 62
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 3.32,
|
| 439 |
+
"learning_rate": 0.0003263157894736842,
|
| 440 |
+
"loss": 1.4757,
|
| 441 |
+
"step": 63
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 3.37,
|
| 445 |
+
"learning_rate": 0.00033157894736842103,
|
| 446 |
+
"loss": 1.4177,
|
| 447 |
+
"step": 64
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 3.42,
|
| 451 |
+
"learning_rate": 0.00033684210526315796,
|
| 452 |
+
"loss": 1.7288,
|
| 453 |
+
"step": 65
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 3.47,
|
| 457 |
+
"learning_rate": 0.00034210526315789477,
|
| 458 |
+
"loss": 1.4219,
|
| 459 |
+
"step": 66
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 3.53,
|
| 463 |
+
"learning_rate": 0.0003473684210526316,
|
| 464 |
+
"loss": 1.6314,
|
| 465 |
+
"step": 67
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 3.58,
|
| 469 |
+
"learning_rate": 0.00035263157894736846,
|
| 470 |
+
"loss": 1.5195,
|
| 471 |
+
"step": 68
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 3.63,
|
| 475 |
+
"learning_rate": 0.0003578947368421053,
|
| 476 |
+
"loss": 1.4379,
|
| 477 |
+
"step": 69
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 3.68,
|
| 481 |
+
"learning_rate": 0.00036315789473684214,
|
| 482 |
+
"loss": 1.6594,
|
| 483 |
+
"step": 70
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 3.74,
|
| 487 |
+
"learning_rate": 0.00036842105263157896,
|
| 488 |
+
"loss": 1.5372,
|
| 489 |
+
"step": 71
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 3.79,
|
| 493 |
+
"learning_rate": 0.0003736842105263158,
|
| 494 |
+
"loss": 1.6277,
|
| 495 |
+
"step": 72
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 3.84,
|
| 499 |
+
"learning_rate": 0.00037894736842105265,
|
| 500 |
+
"loss": 1.3156,
|
| 501 |
+
"step": 73
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 3.89,
|
| 505 |
+
"learning_rate": 0.00038421052631578946,
|
| 506 |
+
"loss": 1.7242,
|
| 507 |
+
"step": 74
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 3.95,
|
| 511 |
+
"learning_rate": 0.00038947368421052633,
|
| 512 |
+
"loss": 1.4844,
|
| 513 |
+
"step": 75
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 4.0,
|
| 517 |
+
"learning_rate": 0.0003947368421052632,
|
| 518 |
+
"loss": 1.4152,
|
| 519 |
+
"step": 76
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 4.0,
|
| 523 |
+
"eval_accuracy": 0.3076923076923077,
|
| 524 |
+
"eval_f1_macro": 0.09411764705882353,
|
| 525 |
+
"eval_f1_micro": 0.3076923076923077,
|
| 526 |
+
"eval_f1_weighted": 0.14479638009049772,
|
| 527 |
+
"eval_loss": 1.4960436820983887,
|
| 528 |
+
"eval_precision_macro": 0.06153846153846154,
|
| 529 |
+
"eval_precision_micro": 0.3076923076923077,
|
| 530 |
+
"eval_precision_weighted": 0.09467455621301776,
|
| 531 |
+
"eval_recall_macro": 0.2,
|
| 532 |
+
"eval_recall_micro": 0.3076923076923077,
|
| 533 |
+
"eval_recall_weighted": 0.3076923076923077,
|
| 534 |
+
"eval_runtime": 0.1073,
|
| 535 |
+
"eval_samples_per_second": 363.387,
|
| 536 |
+
"eval_steps_per_second": 27.953,
|
| 537 |
+
"step": 76
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 4.05,
|
| 541 |
+
"learning_rate": 0.0004,
|
| 542 |
+
"loss": 1.2319,
|
| 543 |
+
"step": 77
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 4.11,
|
| 547 |
+
"learning_rate": 0.0004052631578947369,
|
| 548 |
+
"loss": 1.5189,
|
| 549 |
+
"step": 78
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 4.16,
|
| 553 |
+
"learning_rate": 0.0004105263157894737,
|
| 554 |
+
"loss": 1.5146,
|
| 555 |
+
"step": 79
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 4.21,
|
| 559 |
+
"learning_rate": 0.0004157894736842105,
|
| 560 |
+
"loss": 1.4695,
|
| 561 |
+
"step": 80
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 4.26,
|
| 565 |
+
"learning_rate": 0.0004210526315789474,
|
| 566 |
+
"loss": 1.343,
|
| 567 |
+
"step": 81
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 4.32,
|
| 571 |
+
"learning_rate": 0.0004263157894736842,
|
| 572 |
+
"loss": 1.4702,
|
| 573 |
+
"step": 82
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 4.37,
|
| 577 |
+
"learning_rate": 0.0004315789473684211,
|
| 578 |
+
"loss": 1.6262,
|
| 579 |
+
"step": 83
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 4.42,
|
| 583 |
+
"learning_rate": 0.0004368421052631579,
|
| 584 |
+
"loss": 1.5298,
|
| 585 |
+
"step": 84
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 4.47,
|
| 589 |
+
"learning_rate": 0.0004421052631578947,
|
| 590 |
+
"loss": 1.2922,
|
| 591 |
+
"step": 85
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 4.53,
|
| 595 |
+
"learning_rate": 0.0004473684210526316,
|
| 596 |
+
"loss": 1.2764,
|
| 597 |
+
"step": 86
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 4.58,
|
| 601 |
+
"learning_rate": 0.0004526315789473684,
|
| 602 |
+
"loss": 1.2834,
|
| 603 |
+
"step": 87
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 4.63,
|
| 607 |
+
"learning_rate": 0.00045789473684210527,
|
| 608 |
+
"loss": 1.3713,
|
| 609 |
+
"step": 88
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 4.68,
|
| 613 |
+
"learning_rate": 0.0004631578947368422,
|
| 614 |
+
"loss": 1.5645,
|
| 615 |
+
"step": 89
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 4.74,
|
| 619 |
+
"learning_rate": 0.000468421052631579,
|
| 620 |
+
"loss": 1.3019,
|
| 621 |
+
"step": 90
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 4.79,
|
| 625 |
+
"learning_rate": 0.0004736842105263158,
|
| 626 |
+
"loss": 1.3534,
|
| 627 |
+
"step": 91
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 4.84,
|
| 631 |
+
"learning_rate": 0.0004789473684210527,
|
| 632 |
+
"loss": 1.4572,
|
| 633 |
+
"step": 92
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 4.89,
|
| 637 |
+
"learning_rate": 0.0004842105263157895,
|
| 638 |
+
"loss": 1.5372,
|
| 639 |
+
"step": 93
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 4.95,
|
| 643 |
+
"learning_rate": 0.0004894736842105264,
|
| 644 |
+
"loss": 1.4614,
|
| 645 |
+
"step": 94
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 5.0,
|
| 649 |
+
"learning_rate": 0.0004947368421052632,
|
| 650 |
+
"loss": 1.214,
|
| 651 |
+
"step": 95
|
| 652 |
+
},
|
| 653 |
+
{
|
| 654 |
+
"epoch": 5.0,
|
| 655 |
+
"eval_accuracy": 0.41025641025641024,
|
| 656 |
+
"eval_f1_macro": 0.21165501165501163,
|
| 657 |
+
"eval_f1_micro": 0.41025641025641024,
|
| 658 |
+
"eval_f1_weighted": 0.29765106688183607,
|
| 659 |
+
"eval_loss": 1.392277717590332,
|
| 660 |
+
"eval_precision_macro": 0.17407407407407408,
|
| 661 |
+
"eval_precision_micro": 0.41025641025641024,
|
| 662 |
+
"eval_precision_weighted": 0.24216524216524218,
|
| 663 |
+
"eval_recall_macro": 0.2866666666666667,
|
| 664 |
+
"eval_recall_micro": 0.41025641025641024,
|
| 665 |
+
"eval_recall_weighted": 0.41025641025641024,
|
| 666 |
+
"eval_runtime": 0.1067,
|
| 667 |
+
"eval_samples_per_second": 365.557,
|
| 668 |
+
"eval_steps_per_second": 28.12,
|
| 669 |
+
"step": 95
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 5.05,
|
| 673 |
+
"learning_rate": 0.0005,
|
| 674 |
+
"loss": 1.1431,
|
| 675 |
+
"step": 96
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 5.11,
|
| 679 |
+
"learning_rate": 0.0005052631578947368,
|
| 680 |
+
"loss": 1.1986,
|
| 681 |
+
"step": 97
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 5.16,
|
| 685 |
+
"learning_rate": 0.0005105263157894738,
|
| 686 |
+
"loss": 1.3605,
|
| 687 |
+
"step": 98
|
| 688 |
+
},
|
| 689 |
+
{
|
| 690 |
+
"epoch": 5.21,
|
| 691 |
+
"learning_rate": 0.0005157894736842106,
|
| 692 |
+
"loss": 1.4709,
|
| 693 |
+
"step": 99
|
| 694 |
+
},
|
| 695 |
+
{
|
| 696 |
+
"epoch": 5.26,
|
| 697 |
+
"learning_rate": 0.0005210526315789474,
|
| 698 |
+
"loss": 1.4103,
|
| 699 |
+
"step": 100
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 5.32,
|
| 703 |
+
"learning_rate": 0.0005263157894736842,
|
| 704 |
+
"loss": 1.5161,
|
| 705 |
+
"step": 101
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 5.37,
|
| 709 |
+
"learning_rate": 0.000531578947368421,
|
| 710 |
+
"loss": 1.4339,
|
| 711 |
+
"step": 102
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 5.42,
|
| 715 |
+
"learning_rate": 0.0005368421052631579,
|
| 716 |
+
"loss": 1.2471,
|
| 717 |
+
"step": 103
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 5.47,
|
| 721 |
+
"learning_rate": 0.0005421052631578948,
|
| 722 |
+
"loss": 1.3335,
|
| 723 |
+
"step": 104
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 5.53,
|
| 727 |
+
"learning_rate": 0.0005473684210526316,
|
| 728 |
+
"loss": 1.1644,
|
| 729 |
+
"step": 105
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 5.58,
|
| 733 |
+
"learning_rate": 0.0005526315789473684,
|
| 734 |
+
"loss": 1.5695,
|
| 735 |
+
"step": 106
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 5.63,
|
| 739 |
+
"learning_rate": 0.0005578947368421052,
|
| 740 |
+
"loss": 1.099,
|
| 741 |
+
"step": 107
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 5.68,
|
| 745 |
+
"learning_rate": 0.0005631578947368421,
|
| 746 |
+
"loss": 1.3556,
|
| 747 |
+
"step": 108
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 5.74,
|
| 751 |
+
"learning_rate": 0.000568421052631579,
|
| 752 |
+
"loss": 1.4156,
|
| 753 |
+
"step": 109
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 5.79,
|
| 757 |
+
"learning_rate": 0.0005736842105263159,
|
| 758 |
+
"loss": 1.3777,
|
| 759 |
+
"step": 110
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 5.84,
|
| 763 |
+
"learning_rate": 0.0005789473684210527,
|
| 764 |
+
"loss": 1.8594,
|
| 765 |
+
"step": 111
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 5.89,
|
| 769 |
+
"learning_rate": 0.0005842105263157895,
|
| 770 |
+
"loss": 0.995,
|
| 771 |
+
"step": 112
|
| 772 |
+
},
|
| 773 |
+
{
|
| 774 |
+
"epoch": 5.95,
|
| 775 |
+
"learning_rate": 0.0005894736842105264,
|
| 776 |
+
"loss": 1.2018,
|
| 777 |
+
"step": 113
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 6.0,
|
| 781 |
+
"learning_rate": 0.0005947368421052632,
|
| 782 |
+
"loss": 0.9971,
|
| 783 |
+
"step": 114
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 6.0,
|
| 787 |
+
"eval_accuracy": 0.48717948717948717,
|
| 788 |
+
"eval_f1_macro": 0.33415204678362576,
|
| 789 |
+
"eval_f1_micro": 0.48717948717948717,
|
| 790 |
+
"eval_f1_weighted": 0.4098065677013045,
|
| 791 |
+
"eval_loss": 1.2535957098007202,
|
| 792 |
+
"eval_precision_macro": 0.35025641025641024,
|
| 793 |
+
"eval_precision_micro": 0.48717948717948717,
|
| 794 |
+
"eval_precision_weighted": 0.4003944773175543,
|
| 795 |
+
"eval_recall_macro": 0.3733333333333333,
|
| 796 |
+
"eval_recall_micro": 0.48717948717948717,
|
| 797 |
+
"eval_recall_weighted": 0.48717948717948717,
|
| 798 |
+
"eval_runtime": 0.1096,
|
| 799 |
+
"eval_samples_per_second": 355.926,
|
| 800 |
+
"eval_steps_per_second": 27.379,
|
| 801 |
+
"step": 114
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 6.05,
|
| 805 |
+
"learning_rate": 0.0006000000000000001,
|
| 806 |
+
"loss": 1.1295,
|
| 807 |
+
"step": 115
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 6.11,
|
| 811 |
+
"learning_rate": 0.0006052631578947369,
|
| 812 |
+
"loss": 1.4946,
|
| 813 |
+
"step": 116
|
| 814 |
+
},
|
| 815 |
+
{
|
| 816 |
+
"epoch": 6.16,
|
| 817 |
+
"learning_rate": 0.0006105263157894737,
|
| 818 |
+
"loss": 1.8178,
|
| 819 |
+
"step": 117
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 6.21,
|
| 823 |
+
"learning_rate": 0.0006157894736842106,
|
| 824 |
+
"loss": 1.1574,
|
| 825 |
+
"step": 118
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 6.26,
|
| 829 |
+
"learning_rate": 0.0006210526315789474,
|
| 830 |
+
"loss": 0.9329,
|
| 831 |
+
"step": 119
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 6.32,
|
| 835 |
+
"learning_rate": 0.0006263157894736842,
|
| 836 |
+
"loss": 1.2374,
|
| 837 |
+
"step": 120
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 6.37,
|
| 841 |
+
"learning_rate": 0.0006315789473684211,
|
| 842 |
+
"loss": 1.5585,
|
| 843 |
+
"step": 121
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 6.42,
|
| 847 |
+
"learning_rate": 0.0006368421052631579,
|
| 848 |
+
"loss": 1.0872,
|
| 849 |
+
"step": 122
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 6.47,
|
| 853 |
+
"learning_rate": 0.0006421052631578948,
|
| 854 |
+
"loss": 0.9432,
|
| 855 |
+
"step": 123
|
| 856 |
+
},
|
| 857 |
+
{
|
| 858 |
+
"epoch": 6.53,
|
| 859 |
+
"learning_rate": 0.0006473684210526316,
|
| 860 |
+
"loss": 1.2214,
|
| 861 |
+
"step": 124
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 6.58,
|
| 865 |
+
"learning_rate": 0.0006526315789473684,
|
| 866 |
+
"loss": 1.0156,
|
| 867 |
+
"step": 125
|
| 868 |
+
},
|
| 869 |
+
{
|
| 870 |
+
"epoch": 6.63,
|
| 871 |
+
"learning_rate": 0.0006578947368421052,
|
| 872 |
+
"loss": 1.2343,
|
| 873 |
+
"step": 126
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 6.68,
|
| 877 |
+
"learning_rate": 0.0006631578947368421,
|
| 878 |
+
"loss": 1.2906,
|
| 879 |
+
"step": 127
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 6.74,
|
| 883 |
+
"learning_rate": 0.000668421052631579,
|
| 884 |
+
"loss": 1.5074,
|
| 885 |
+
"step": 128
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 6.79,
|
| 889 |
+
"learning_rate": 0.0006736842105263159,
|
| 890 |
+
"loss": 1.0378,
|
| 891 |
+
"step": 129
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 6.84,
|
| 895 |
+
"learning_rate": 0.0006789473684210527,
|
| 896 |
+
"loss": 1.3764,
|
| 897 |
+
"step": 130
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 6.89,
|
| 901 |
+
"learning_rate": 0.0006842105263157895,
|
| 902 |
+
"loss": 0.9798,
|
| 903 |
+
"step": 131
|
| 904 |
+
},
|
| 905 |
+
{
|
| 906 |
+
"epoch": 6.95,
|
| 907 |
+
"learning_rate": 0.0006894736842105264,
|
| 908 |
+
"loss": 1.0204,
|
| 909 |
+
"step": 132
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"epoch": 7.0,
|
| 913 |
+
"learning_rate": 0.0006947368421052632,
|
| 914 |
+
"loss": 1.0225,
|
| 915 |
+
"step": 133
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 7.0,
|
| 919 |
+
"eval_accuracy": 0.6923076923076923,
|
| 920 |
+
"eval_f1_macro": 0.5685314685314686,
|
| 921 |
+
"eval_f1_micro": 0.6923076923076923,
|
| 922 |
+
"eval_f1_weighted": 0.6504691889307274,
|
| 923 |
+
"eval_loss": 1.1684703826904297,
|
| 924 |
+
"eval_precision_macro": 0.5473015873015872,
|
| 925 |
+
"eval_precision_micro": 0.6923076923076923,
|
| 926 |
+
"eval_precision_weighted": 0.6344322344322344,
|
| 927 |
+
"eval_recall_macro": 0.6142857142857142,
|
| 928 |
+
"eval_recall_micro": 0.6923076923076923,
|
| 929 |
+
"eval_recall_weighted": 0.6923076923076923,
|
| 930 |
+
"eval_runtime": 0.0989,
|
| 931 |
+
"eval_samples_per_second": 394.464,
|
| 932 |
+
"eval_steps_per_second": 30.343,
|
| 933 |
+
"step": 133
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 7.05,
|
| 937 |
+
"learning_rate": 0.0007000000000000001,
|
| 938 |
+
"loss": 0.8319,
|
| 939 |
+
"step": 134
|
| 940 |
+
},
|
| 941 |
+
{
|
| 942 |
+
"epoch": 7.11,
|
| 943 |
+
"learning_rate": 0.0007052631578947369,
|
| 944 |
+
"loss": 1.0276,
|
| 945 |
+
"step": 135
|
| 946 |
+
},
|
| 947 |
+
{
|
| 948 |
+
"epoch": 7.16,
|
| 949 |
+
"learning_rate": 0.0007105263157894737,
|
| 950 |
+
"loss": 0.9607,
|
| 951 |
+
"step": 136
|
| 952 |
+
},
|
| 953 |
+
{
|
| 954 |
+
"epoch": 7.21,
|
| 955 |
+
"learning_rate": 0.0007157894736842105,
|
| 956 |
+
"loss": 1.2387,
|
| 957 |
+
"step": 137
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 7.26,
|
| 961 |
+
"learning_rate": 0.0007210526315789474,
|
| 962 |
+
"loss": 1.2796,
|
| 963 |
+
"step": 138
|
| 964 |
+
},
|
| 965 |
+
{
|
| 966 |
+
"epoch": 7.32,
|
| 967 |
+
"learning_rate": 0.0007263157894736843,
|
| 968 |
+
"loss": 0.7215,
|
| 969 |
+
"step": 139
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 7.37,
|
| 973 |
+
"learning_rate": 0.0007315789473684211,
|
| 974 |
+
"loss": 1.0518,
|
| 975 |
+
"step": 140
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 7.42,
|
| 979 |
+
"learning_rate": 0.0007368421052631579,
|
| 980 |
+
"loss": 0.7813,
|
| 981 |
+
"step": 141
|
| 982 |
+
},
|
| 983 |
+
{
|
| 984 |
+
"epoch": 7.47,
|
| 985 |
+
"learning_rate": 0.0007421052631578947,
|
| 986 |
+
"loss": 1.0502,
|
| 987 |
+
"step": 142
|
| 988 |
+
},
|
| 989 |
+
{
|
| 990 |
+
"epoch": 7.53,
|
| 991 |
+
"learning_rate": 0.0007473684210526316,
|
| 992 |
+
"loss": 1.378,
|
| 993 |
+
"step": 143
|
| 994 |
+
},
|
| 995 |
+
{
|
| 996 |
+
"epoch": 7.58,
|
| 997 |
+
"learning_rate": 0.0007526315789473685,
|
| 998 |
+
"loss": 1.2363,
|
| 999 |
+
"step": 144
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 7.63,
|
| 1003 |
+
"learning_rate": 0.0007526315789473685,
|
| 1004 |
+
"loss": 1.4102,
|
| 1005 |
+
"step": 145
|
| 1006 |
+
},
|
| 1007 |
+
{
|
| 1008 |
+
"epoch": 7.68,
|
| 1009 |
+
"learning_rate": 0.0007578947368421053,
|
| 1010 |
+
"loss": 0.8184,
|
| 1011 |
+
"step": 146
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 7.74,
|
| 1015 |
+
"learning_rate": 0.0007631578947368421,
|
| 1016 |
+
"loss": 1.0921,
|
| 1017 |
+
"step": 147
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 7.79,
|
| 1021 |
+
"learning_rate": 0.0007684210526315789,
|
| 1022 |
+
"loss": 0.7126,
|
| 1023 |
+
"step": 148
|
| 1024 |
+
},
|
| 1025 |
+
{
|
| 1026 |
+
"epoch": 7.84,
|
| 1027 |
+
"learning_rate": 0.0007736842105263159,
|
| 1028 |
+
"loss": 1.0646,
|
| 1029 |
+
"step": 149
|
| 1030 |
+
},
|
| 1031 |
+
{
|
| 1032 |
+
"epoch": 7.89,
|
| 1033 |
+
"learning_rate": 0.0007789473684210527,
|
| 1034 |
+
"loss": 0.9532,
|
| 1035 |
+
"step": 150
|
| 1036 |
+
},
|
| 1037 |
+
{
|
| 1038 |
+
"epoch": 7.95,
|
| 1039 |
+
"learning_rate": 0.0007842105263157896,
|
| 1040 |
+
"loss": 0.7724,
|
| 1041 |
+
"step": 151
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 8.0,
|
| 1045 |
+
"learning_rate": 0.0007894736842105264,
|
| 1046 |
+
"loss": 0.8753,
|
| 1047 |
+
"step": 152
|
| 1048 |
+
},
|
| 1049 |
+
{
|
| 1050 |
+
"epoch": 8.0,
|
| 1051 |
+
"eval_accuracy": 0.717948717948718,
|
| 1052 |
+
"eval_f1_macro": 0.5992857142857144,
|
| 1053 |
+
"eval_f1_micro": 0.717948717948718,
|
| 1054 |
+
"eval_f1_weighted": 0.6808608058608059,
|
| 1055 |
+
"eval_loss": 1.0412697792053223,
|
| 1056 |
+
"eval_precision_macro": 0.5655555555555555,
|
| 1057 |
+
"eval_precision_micro": 0.717948717948718,
|
| 1058 |
+
"eval_precision_weighted": 0.6524216524216524,
|
| 1059 |
+
"eval_recall_macro": 0.6433333333333333,
|
| 1060 |
+
"eval_recall_micro": 0.717948717948718,
|
| 1061 |
+
"eval_recall_weighted": 0.717948717948718,
|
| 1062 |
+
"eval_runtime": 0.1034,
|
| 1063 |
+
"eval_samples_per_second": 377.218,
|
| 1064 |
+
"eval_steps_per_second": 29.017,
|
| 1065 |
+
"step": 152
|
| 1066 |
+
},
|
| 1067 |
+
{
|
| 1068 |
+
"epoch": 8.05,
|
| 1069 |
+
"learning_rate": 0.0007947368421052632,
|
| 1070 |
+
"loss": 0.6541,
|
| 1071 |
+
"step": 153
|
| 1072 |
+
},
|
| 1073 |
+
{
|
| 1074 |
+
"epoch": 8.11,
|
| 1075 |
+
"learning_rate": 0.0008,
|
| 1076 |
+
"loss": 1.2863,
|
| 1077 |
+
"step": 154
|
| 1078 |
+
},
|
| 1079 |
+
{
|
| 1080 |
+
"epoch": 8.16,
|
| 1081 |
+
"learning_rate": 0.0008052631578947369,
|
| 1082 |
+
"loss": 1.0602,
|
| 1083 |
+
"step": 155
|
| 1084 |
+
},
|
| 1085 |
+
{
|
| 1086 |
+
"epoch": 8.21,
|
| 1087 |
+
"learning_rate": 0.0008105263157894738,
|
| 1088 |
+
"loss": 1.2225,
|
| 1089 |
+
"step": 156
|
| 1090 |
+
},
|
| 1091 |
+
{
|
| 1092 |
+
"epoch": 8.26,
|
| 1093 |
+
"learning_rate": 0.0008157894736842106,
|
| 1094 |
+
"loss": 0.9046,
|
| 1095 |
+
"step": 157
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 8.32,
|
| 1099 |
+
"learning_rate": 0.0008210526315789474,
|
| 1100 |
+
"loss": 0.6939,
|
| 1101 |
+
"step": 158
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 8.37,
|
| 1105 |
+
"learning_rate": 0.0008263157894736842,
|
| 1106 |
+
"loss": 0.644,
|
| 1107 |
+
"step": 159
|
| 1108 |
+
},
|
| 1109 |
+
{
|
| 1110 |
+
"epoch": 8.42,
|
| 1111 |
+
"learning_rate": 0.000831578947368421,
|
| 1112 |
+
"loss": 0.9403,
|
| 1113 |
+
"step": 160
|
| 1114 |
+
},
|
| 1115 |
+
{
|
| 1116 |
+
"epoch": 8.47,
|
| 1117 |
+
"learning_rate": 0.000836842105263158,
|
| 1118 |
+
"loss": 0.5107,
|
| 1119 |
+
"step": 161
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 8.53,
|
| 1123 |
+
"learning_rate": 0.0008421052631578948,
|
| 1124 |
+
"loss": 1.0886,
|
| 1125 |
+
"step": 162
|
| 1126 |
+
},
|
| 1127 |
+
{
|
| 1128 |
+
"epoch": 8.58,
|
| 1129 |
+
"learning_rate": 0.0008473684210526316,
|
| 1130 |
+
"loss": 1.3385,
|
| 1131 |
+
"step": 163
|
| 1132 |
+
},
|
| 1133 |
+
{
|
| 1134 |
+
"epoch": 8.63,
|
| 1135 |
+
"learning_rate": 0.0008526315789473684,
|
| 1136 |
+
"loss": 1.2766,
|
| 1137 |
+
"step": 164
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 8.68,
|
| 1141 |
+
"learning_rate": 0.0008578947368421052,
|
| 1142 |
+
"loss": 0.6848,
|
| 1143 |
+
"step": 165
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 8.74,
|
| 1147 |
+
"learning_rate": 0.0008631578947368422,
|
| 1148 |
+
"loss": 0.9881,
|
| 1149 |
+
"step": 166
|
| 1150 |
+
},
|
| 1151 |
+
{
|
| 1152 |
+
"epoch": 8.79,
|
| 1153 |
+
"learning_rate": 0.000868421052631579,
|
| 1154 |
+
"loss": 0.6309,
|
| 1155 |
+
"step": 167
|
| 1156 |
+
},
|
| 1157 |
+
{
|
| 1158 |
+
"epoch": 8.84,
|
| 1159 |
+
"learning_rate": 0.0008736842105263158,
|
| 1160 |
+
"loss": 0.7585,
|
| 1161 |
+
"step": 168
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 8.89,
|
| 1165 |
+
"learning_rate": 0.0008789473684210526,
|
| 1166 |
+
"loss": 0.6653,
|
| 1167 |
+
"step": 169
|
| 1168 |
+
},
|
| 1169 |
+
{
|
| 1170 |
+
"epoch": 8.95,
|
| 1171 |
+
"learning_rate": 0.0008842105263157894,
|
| 1172 |
+
"loss": 1.0764,
|
| 1173 |
+
"step": 170
|
| 1174 |
+
},
|
| 1175 |
+
{
|
| 1176 |
+
"epoch": 9.0,
|
| 1177 |
+
"learning_rate": 0.0008894736842105263,
|
| 1178 |
+
"loss": 0.6241,
|
| 1179 |
+
"step": 171
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 9.0,
|
| 1183 |
+
"eval_accuracy": 0.7435897435897436,
|
| 1184 |
+
"eval_f1_macro": 0.6221158958001063,
|
| 1185 |
+
"eval_f1_micro": 0.7435897435897437,
|
| 1186 |
+
"eval_f1_weighted": 0.7144862934336619,
|
| 1187 |
+
"eval_loss": 0.9631038308143616,
|
| 1188 |
+
"eval_precision_macro": 0.6077777777777779,
|
| 1189 |
+
"eval_precision_micro": 0.7435897435897436,
|
| 1190 |
+
"eval_precision_weighted": 0.7235042735042736,
|
| 1191 |
+
"eval_recall_macro": 0.6766666666666666,
|
| 1192 |
+
"eval_recall_micro": 0.7435897435897436,
|
| 1193 |
+
"eval_recall_weighted": 0.7435897435897436,
|
| 1194 |
+
"eval_runtime": 0.1019,
|
| 1195 |
+
"eval_samples_per_second": 382.713,
|
| 1196 |
+
"eval_steps_per_second": 29.439,
|
| 1197 |
+
"step": 171
|
| 1198 |
+
},
|
| 1199 |
+
{
|
| 1200 |
+
"epoch": 9.05,
|
| 1201 |
+
"learning_rate": 0.0008947368421052632,
|
| 1202 |
+
"loss": 0.6013,
|
| 1203 |
+
"step": 172
|
| 1204 |
+
},
|
| 1205 |
+
{
|
| 1206 |
+
"epoch": 9.11,
|
| 1207 |
+
"learning_rate": 0.0009,
|
| 1208 |
+
"loss": 0.8411,
|
| 1209 |
+
"step": 173
|
| 1210 |
+
},
|
| 1211 |
+
{
|
| 1212 |
+
"epoch": 9.16,
|
| 1213 |
+
"learning_rate": 0.0009052631578947368,
|
| 1214 |
+
"loss": 0.9775,
|
| 1215 |
+
"step": 174
|
| 1216 |
+
},
|
| 1217 |
+
{
|
| 1218 |
+
"epoch": 9.21,
|
| 1219 |
+
"learning_rate": 0.0009105263157894736,
|
| 1220 |
+
"loss": 0.9363,
|
| 1221 |
+
"step": 175
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 9.26,
|
| 1225 |
+
"learning_rate": 0.0009157894736842105,
|
| 1226 |
+
"loss": 0.348,
|
| 1227 |
+
"step": 176
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 9.32,
|
| 1231 |
+
"learning_rate": 0.0009210526315789473,
|
| 1232 |
+
"loss": 0.7705,
|
| 1233 |
+
"step": 177
|
| 1234 |
+
},
|
| 1235 |
+
{
|
| 1236 |
+
"epoch": 9.37,
|
| 1237 |
+
"learning_rate": 0.0009263157894736844,
|
| 1238 |
+
"loss": 0.7397,
|
| 1239 |
+
"step": 178
|
| 1240 |
+
},
|
| 1241 |
+
{
|
| 1242 |
+
"epoch": 9.42,
|
| 1243 |
+
"learning_rate": 0.0009315789473684212,
|
| 1244 |
+
"loss": 0.3971,
|
| 1245 |
+
"step": 179
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"epoch": 9.47,
|
| 1249 |
+
"learning_rate": 0.000936842105263158,
|
| 1250 |
+
"loss": 1.4934,
|
| 1251 |
+
"step": 180
|
| 1252 |
+
},
|
| 1253 |
+
{
|
| 1254 |
+
"epoch": 9.53,
|
| 1255 |
+
"learning_rate": 0.0009421052631578948,
|
| 1256 |
+
"loss": 1.2191,
|
| 1257 |
+
"step": 181
|
| 1258 |
+
},
|
| 1259 |
+
{
|
| 1260 |
+
"epoch": 9.58,
|
| 1261 |
+
"learning_rate": 0.0009473684210526316,
|
| 1262 |
+
"loss": 1.3495,
|
| 1263 |
+
"step": 182
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 9.63,
|
| 1267 |
+
"learning_rate": 0.0009526315789473686,
|
| 1268 |
+
"loss": 1.2079,
|
| 1269 |
+
"step": 183
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 9.68,
|
| 1273 |
+
"learning_rate": 0.0009578947368421054,
|
| 1274 |
+
"loss": 0.9686,
|
| 1275 |
+
"step": 184
|
| 1276 |
+
},
|
| 1277 |
+
{
|
| 1278 |
+
"epoch": 9.74,
|
| 1279 |
+
"learning_rate": 0.0009631578947368422,
|
| 1280 |
+
"loss": 1.6675,
|
| 1281 |
+
"step": 185
|
| 1282 |
+
},
|
| 1283 |
+
{
|
| 1284 |
+
"epoch": 9.79,
|
| 1285 |
+
"learning_rate": 0.000968421052631579,
|
| 1286 |
+
"loss": 0.7272,
|
| 1287 |
+
"step": 186
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 9.84,
|
| 1291 |
+
"learning_rate": 0.0009736842105263158,
|
| 1292 |
+
"loss": 0.563,
|
| 1293 |
+
"step": 187
|
| 1294 |
+
},
|
| 1295 |
+
{
|
| 1296 |
+
"epoch": 9.89,
|
| 1297 |
+
"learning_rate": 0.0009789473684210528,
|
| 1298 |
+
"loss": 1.2433,
|
| 1299 |
+
"step": 188
|
| 1300 |
+
},
|
| 1301 |
+
{
|
| 1302 |
+
"epoch": 9.95,
|
| 1303 |
+
"learning_rate": 0.0009842105263157895,
|
| 1304 |
+
"loss": 1.353,
|
| 1305 |
+
"step": 189
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 10.0,
|
| 1309 |
+
"learning_rate": 0.0009894736842105264,
|
| 1310 |
+
"loss": 0.5994,
|
| 1311 |
+
"step": 190
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 10.0,
|
| 1315 |
+
"eval_accuracy": 0.717948717948718,
|
| 1316 |
+
"eval_f1_macro": 0.608552036199095,
|
| 1317 |
+
"eval_f1_micro": 0.717948717948718,
|
| 1318 |
+
"eval_f1_weighted": 0.6738484743009631,
|
| 1319 |
+
"eval_loss": 0.8072579503059387,
|
| 1320 |
+
"eval_precision_macro": 0.5864285714285714,
|
| 1321 |
+
"eval_precision_micro": 0.717948717948718,
|
| 1322 |
+
"eval_precision_weighted": 0.6695970695970695,
|
| 1323 |
+
"eval_recall_macro": 0.6633333333333333,
|
| 1324 |
+
"eval_recall_micro": 0.717948717948718,
|
| 1325 |
+
"eval_recall_weighted": 0.717948717948718,
|
| 1326 |
+
"eval_runtime": 0.1002,
|
| 1327 |
+
"eval_samples_per_second": 389.316,
|
| 1328 |
+
"eval_steps_per_second": 29.947,
|
| 1329 |
+
"step": 190
|
| 1330 |
+
}
|
| 1331 |
+
],
|
| 1332 |
+
"logging_steps": 1,
|
| 1333 |
+
"max_steps": 95000,
|
| 1334 |
+
"num_input_tokens_seen": 0,
|
| 1335 |
+
"num_train_epochs": 5000,
|
| 1336 |
+
"save_steps": 500,
|
| 1337 |
+
"total_flos": 3.228625190633472e+16,
|
| 1338 |
+
"train_batch_size": 8,
|
| 1339 |
+
"trial_name": null,
|
| 1340 |
+
"trial_params": null
|
| 1341 |
+
}
|
checkpoint-190/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:10528f68b86201216a8cf6dbea211415fe686bb19b7691eca86bd0f7c94d047b
|
| 3 |
+
size 4728
|
config.json
ADDED
|
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "microsoft/resnet-50",
|
| 3 |
+
"_num_labels": 5,
|
| 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": "9K111 Fagot",
|
| 25 |
+
"1": "9K115-2 Metis-M",
|
| 26 |
+
"2": "9M113 Konkurs",
|
| 27 |
+
"3": "9M133 Kornet",
|
| 28 |
+
"4": "BGM-71 TOW"
|
| 29 |
+
},
|
| 30 |
+
"label2id": {
|
| 31 |
+
"9K111 Fagot": 0,
|
| 32 |
+
"9K115-2 Metis-M": 1,
|
| 33 |
+
"9M113 Konkurs": 2,
|
| 34 |
+
"9M133 Kornet": 3,
|
| 35 |
+
"BGM-71 TOW": 4
|
| 36 |
+
},
|
| 37 |
+
"layer_type": "bottleneck",
|
| 38 |
+
"model_type": "resnet",
|
| 39 |
+
"num_channels": 3,
|
| 40 |
+
"out_features": [
|
| 41 |
+
"stage4"
|
| 42 |
+
],
|
| 43 |
+
"out_indices": [
|
| 44 |
+
4
|
| 45 |
+
],
|
| 46 |
+
"problem_type": "single_label_classification",
|
| 47 |
+
"stage_names": [
|
| 48 |
+
"stem",
|
| 49 |
+
"stage1",
|
| 50 |
+
"stage2",
|
| 51 |
+
"stage3",
|
| 52 |
+
"stage4"
|
| 53 |
+
],
|
| 54 |
+
"torch_dtype": "float32",
|
| 55 |
+
"transformers_version": "4.36.1"
|
| 56 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c4e5595afb95ccd017d4e243d490ccbec395c785588dce4134683b536ca83a9d
|
| 3 |
+
size 94327540
|
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 sha256:10528f68b86201216a8cf6dbea211415fe686bb19b7691eca86bd0f7c94d047b
|
| 3 |
+
size 4728
|
training_params.json
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"data_path": "tosullivan/autotrain-data-weapon_1",
|
| 3 |
+
"model": "microsoft/resnet-50",
|
| 4 |
+
"username": "tosullivan",
|
| 5 |
+
"lr": 0.05,
|
| 6 |
+
"epochs": 5000,
|
| 7 |
+
"batch_size": 8,
|
| 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": "fp16",
|
| 21 |
+
"save_total_limit": 1,
|
| 22 |
+
"save_strategy": "epoch",
|
| 23 |
+
"push_to_hub": true,
|
| 24 |
+
"repo_id": "tosullivan/weapon_1",
|
| 25 |
+
"evaluation_strategy": "epoch",
|
| 26 |
+
"image_column": "autotrain_image",
|
| 27 |
+
"target_column": "autotrain_label",
|
| 28 |
+
"log": "none"
|
| 29 |
+
}
|