Upload folder using huggingface_hub
Browse files- README.md +41 -0
- checkpoint-1569/config.json +54 -0
- checkpoint-1569/model.safetensors +3 -0
- checkpoint-1569/optimizer.pt +3 -0
- checkpoint-1569/rng_state.pth +3 -0
- checkpoint-1569/scheduler.pt +3 -0
- checkpoint-1569/trainer_state.json +530 -0
- checkpoint-1569/training_args.bin +3 -0
- config.json +54 -0
- model.safetensors +3 -0
- preprocessor_config.json +22 -0
- runs/Oct18_06-24-24_07b4c6376f8e/events.out.tfevents.1729232666.07b4c6376f8e.21206.0 +2 -2
- runs/Oct18_06-24-24_07b4c6376f8e/events.out.tfevents.1729233657.07b4c6376f8e.21206.1 +3 -0
- training_args.bin +3 -0
- training_params.json +29 -0
README.md
ADDED
|
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
|
| 2 |
+
---
|
| 3 |
+
tags:
|
| 4 |
+
- autotrain
|
| 5 |
+
- image-classification
|
| 6 |
+
base_model: microsoft/resnet-152
|
| 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: 0.369663268327713
|
| 22 |
+
|
| 23 |
+
f1_macro: 0.6843075887364951
|
| 24 |
+
|
| 25 |
+
f1_micro: 0.858508604206501
|
| 26 |
+
|
| 27 |
+
f1_weighted: 0.8303295709630173
|
| 28 |
+
|
| 29 |
+
precision_macro: 0.8204154992433914
|
| 30 |
+
|
| 31 |
+
precision_micro: 0.858508604206501
|
| 32 |
+
|
| 33 |
+
precision_weighted: 0.882137838723129
|
| 34 |
+
|
| 35 |
+
recall_macro: 0.7169578798305077
|
| 36 |
+
|
| 37 |
+
recall_micro: 0.858508604206501
|
| 38 |
+
|
| 39 |
+
recall_weighted: 0.858508604206501
|
| 40 |
+
|
| 41 |
+
accuracy: 0.858508604206501
|
checkpoint-1569/config.json
ADDED
|
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "microsoft/resnet-152",
|
| 3 |
+
"_num_labels": 4,
|
| 4 |
+
"architectures": [
|
| 5 |
+
"ResNetForImageClassification"
|
| 6 |
+
],
|
| 7 |
+
"depths": [
|
| 8 |
+
3,
|
| 9 |
+
8,
|
| 10 |
+
36,
|
| 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": "Common_Rust",
|
| 25 |
+
"1": "Gray_Leaf_Spot",
|
| 26 |
+
"2": "Healthy_Leaf",
|
| 27 |
+
"3": "Northern_Leaf_Blight"
|
| 28 |
+
},
|
| 29 |
+
"label2id": {
|
| 30 |
+
"Common_Rust": 0,
|
| 31 |
+
"Gray_Leaf_Spot": 1,
|
| 32 |
+
"Healthy_Leaf": 2,
|
| 33 |
+
"Northern_Leaf_Blight": 3
|
| 34 |
+
},
|
| 35 |
+
"layer_type": "bottleneck",
|
| 36 |
+
"model_type": "resnet",
|
| 37 |
+
"num_channels": 3,
|
| 38 |
+
"out_features": [
|
| 39 |
+
"stage4"
|
| 40 |
+
],
|
| 41 |
+
"out_indices": [
|
| 42 |
+
4
|
| 43 |
+
],
|
| 44 |
+
"problem_type": "single_label_classification",
|
| 45 |
+
"stage_names": [
|
| 46 |
+
"stem",
|
| 47 |
+
"stage1",
|
| 48 |
+
"stage2",
|
| 49 |
+
"stage3",
|
| 50 |
+
"stage4"
|
| 51 |
+
],
|
| 52 |
+
"torch_dtype": "float32",
|
| 53 |
+
"transformers_version": "4.45.0"
|
| 54 |
+
}
|
checkpoint-1569/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:645576a82568b0eef5352984eca080ea05a70ae94011f53978ab703b27247fd2
|
| 3 |
+
size 233338200
|
checkpoint-1569/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a8ea98e5edc2439025f95974b346faa0020d650fde8fcdc440f991bcf46bda26
|
| 3 |
+
size 465609611
|
checkpoint-1569/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ddc2ba2f53d47f9e93f59b943a5c2285c82191f107608aa0970d651697f4fdce
|
| 3 |
+
size 14244
|
checkpoint-1569/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bede44975d1f7de145427b3d6a115ba78bce06803261b20f85aa5bb4e7f3b03c
|
| 3 |
+
size 1064
|
checkpoint-1569/trainer_state.json
ADDED
|
@@ -0,0 +1,530 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.369663268327713,
|
| 3 |
+
"best_model_checkpoint": "v-mdd-2000-150/checkpoint-1569",
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 1569,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.04780114722753346,
|
| 13 |
+
"grad_norm": 24.8793888092041,
|
| 14 |
+
"learning_rate": 6.687898089171975e-06,
|
| 15 |
+
"loss": 1.391,
|
| 16 |
+
"step": 25
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.09560229445506692,
|
| 20 |
+
"grad_norm": 13.04520034790039,
|
| 21 |
+
"learning_rate": 1.464968152866242e-05,
|
| 22 |
+
"loss": 1.3907,
|
| 23 |
+
"step": 50
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.14340344168260039,
|
| 27 |
+
"grad_norm": 12.42558765411377,
|
| 28 |
+
"learning_rate": 2.261146496815287e-05,
|
| 29 |
+
"loss": 1.3641,
|
| 30 |
+
"step": 75
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.19120458891013384,
|
| 34 |
+
"grad_norm": 40.01886749267578,
|
| 35 |
+
"learning_rate": 3.057324840764331e-05,
|
| 36 |
+
"loss": 1.3144,
|
| 37 |
+
"step": 100
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.2390057361376673,
|
| 41 |
+
"grad_norm": 16.6850528717041,
|
| 42 |
+
"learning_rate": 3.8535031847133766e-05,
|
| 43 |
+
"loss": 1.2513,
|
| 44 |
+
"step": 125
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.28680688336520077,
|
| 48 |
+
"grad_norm": 20.78025245666504,
|
| 49 |
+
"learning_rate": 4.617834394904459e-05,
|
| 50 |
+
"loss": 1.139,
|
| 51 |
+
"step": 150
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.33460803059273425,
|
| 55 |
+
"grad_norm": 56.91587448120117,
|
| 56 |
+
"learning_rate": 4.9575070821529744e-05,
|
| 57 |
+
"loss": 1.0721,
|
| 58 |
+
"step": 175
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.3824091778202677,
|
| 62 |
+
"grad_norm": 27.284250259399414,
|
| 63 |
+
"learning_rate": 4.868980169971671e-05,
|
| 64 |
+
"loss": 1.0102,
|
| 65 |
+
"step": 200
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.43021032504780116,
|
| 69 |
+
"grad_norm": 18.555421829223633,
|
| 70 |
+
"learning_rate": 4.7804532577903685e-05,
|
| 71 |
+
"loss": 0.9647,
|
| 72 |
+
"step": 225
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.4780114722753346,
|
| 76 |
+
"grad_norm": 17.996288299560547,
|
| 77 |
+
"learning_rate": 4.691926345609066e-05,
|
| 78 |
+
"loss": 0.8751,
|
| 79 |
+
"step": 250
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.5258126195028681,
|
| 83 |
+
"grad_norm": 16.214096069335938,
|
| 84 |
+
"learning_rate": 4.6033994334277626e-05,
|
| 85 |
+
"loss": 0.7932,
|
| 86 |
+
"step": 275
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.5736137667304015,
|
| 90 |
+
"grad_norm": 12.805717468261719,
|
| 91 |
+
"learning_rate": 4.514872521246459e-05,
|
| 92 |
+
"loss": 0.8325,
|
| 93 |
+
"step": 300
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.621414913957935,
|
| 97 |
+
"grad_norm": 9.800782203674316,
|
| 98 |
+
"learning_rate": 4.426345609065156e-05,
|
| 99 |
+
"loss": 0.6662,
|
| 100 |
+
"step": 325
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.6692160611854685,
|
| 104 |
+
"grad_norm": 63.53221893310547,
|
| 105 |
+
"learning_rate": 4.337818696883853e-05,
|
| 106 |
+
"loss": 0.6896,
|
| 107 |
+
"step": 350
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.7170172084130019,
|
| 111 |
+
"grad_norm": 3.3974146842956543,
|
| 112 |
+
"learning_rate": 4.24929178470255e-05,
|
| 113 |
+
"loss": 0.6671,
|
| 114 |
+
"step": 375
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.7648183556405354,
|
| 118 |
+
"grad_norm": 20.420568466186523,
|
| 119 |
+
"learning_rate": 4.160764872521247e-05,
|
| 120 |
+
"loss": 0.6681,
|
| 121 |
+
"step": 400
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.8126195028680688,
|
| 125 |
+
"grad_norm": 29.39402198791504,
|
| 126 |
+
"learning_rate": 4.0722379603399435e-05,
|
| 127 |
+
"loss": 0.7249,
|
| 128 |
+
"step": 425
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.8604206500956023,
|
| 132 |
+
"grad_norm": 2.5485928058624268,
|
| 133 |
+
"learning_rate": 3.98371104815864e-05,
|
| 134 |
+
"loss": 0.5976,
|
| 135 |
+
"step": 450
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.9082217973231358,
|
| 139 |
+
"grad_norm": 20.10879135131836,
|
| 140 |
+
"learning_rate": 3.895184135977337e-05,
|
| 141 |
+
"loss": 0.7261,
|
| 142 |
+
"step": 475
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.9560229445506692,
|
| 146 |
+
"grad_norm": 20.019594192504883,
|
| 147 |
+
"learning_rate": 3.806657223796034e-05,
|
| 148 |
+
"loss": 0.6267,
|
| 149 |
+
"step": 500
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 1.0,
|
| 153 |
+
"eval_accuracy": 0.7160611854684512,
|
| 154 |
+
"eval_f1_macro": 0.37856670758190913,
|
| 155 |
+
"eval_f1_micro": 0.7160611854684512,
|
| 156 |
+
"eval_f1_weighted": 0.6476372575798962,
|
| 157 |
+
"eval_loss": 0.59242182970047,
|
| 158 |
+
"eval_precision_macro": 0.33835803984515156,
|
| 159 |
+
"eval_precision_micro": 0.7160611854684512,
|
| 160 |
+
"eval_precision_weighted": 0.6202676864244742,
|
| 161 |
+
"eval_recall_macro": 0.47908837692380324,
|
| 162 |
+
"eval_recall_micro": 0.7160611854684512,
|
| 163 |
+
"eval_recall_weighted": 0.7160611854684512,
|
| 164 |
+
"eval_runtime": 47.1589,
|
| 165 |
+
"eval_samples_per_second": 22.18,
|
| 166 |
+
"eval_steps_per_second": 1.4,
|
| 167 |
+
"step": 523
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 1.0038240917782026,
|
| 171 |
+
"grad_norm": 52.7318229675293,
|
| 172 |
+
"learning_rate": 3.718130311614731e-05,
|
| 173 |
+
"loss": 0.7421,
|
| 174 |
+
"step": 525
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 1.0516252390057361,
|
| 178 |
+
"grad_norm": 7.203369617462158,
|
| 179 |
+
"learning_rate": 3.629603399433428e-05,
|
| 180 |
+
"loss": 0.6477,
|
| 181 |
+
"step": 550
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 1.0994263862332696,
|
| 185 |
+
"grad_norm": 3.6017909049987793,
|
| 186 |
+
"learning_rate": 3.5410764872521244e-05,
|
| 187 |
+
"loss": 0.5586,
|
| 188 |
+
"step": 575
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 1.147227533460803,
|
| 192 |
+
"grad_norm": 52.35728073120117,
|
| 193 |
+
"learning_rate": 3.452549575070821e-05,
|
| 194 |
+
"loss": 0.5506,
|
| 195 |
+
"step": 600
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 1.1950286806883366,
|
| 199 |
+
"grad_norm": 3.721095085144043,
|
| 200 |
+
"learning_rate": 3.364022662889519e-05,
|
| 201 |
+
"loss": 0.5279,
|
| 202 |
+
"step": 625
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 1.24282982791587,
|
| 206 |
+
"grad_norm": 4.125187397003174,
|
| 207 |
+
"learning_rate": 3.275495750708216e-05,
|
| 208 |
+
"loss": 0.6266,
|
| 209 |
+
"step": 650
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 1.2906309751434035,
|
| 213 |
+
"grad_norm": 15.054932594299316,
|
| 214 |
+
"learning_rate": 3.1869688385269126e-05,
|
| 215 |
+
"loss": 0.6104,
|
| 216 |
+
"step": 675
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 1.338432122370937,
|
| 220 |
+
"grad_norm": 12.489537239074707,
|
| 221 |
+
"learning_rate": 3.098441926345609e-05,
|
| 222 |
+
"loss": 0.6529,
|
| 223 |
+
"step": 700
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 1.3862332695984705,
|
| 227 |
+
"grad_norm": 7.253444671630859,
|
| 228 |
+
"learning_rate": 3.0099150141643063e-05,
|
| 229 |
+
"loss": 0.4816,
|
| 230 |
+
"step": 725
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 1.4340344168260037,
|
| 234 |
+
"grad_norm": 42.50492858886719,
|
| 235 |
+
"learning_rate": 2.921388101983003e-05,
|
| 236 |
+
"loss": 0.5376,
|
| 237 |
+
"step": 750
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 1.4818355640535372,
|
| 241 |
+
"grad_norm": 38.91421127319336,
|
| 242 |
+
"learning_rate": 2.8328611898017e-05,
|
| 243 |
+
"loss": 0.6558,
|
| 244 |
+
"step": 775
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"epoch": 1.5296367112810707,
|
| 248 |
+
"grad_norm": 10.420364379882812,
|
| 249 |
+
"learning_rate": 2.7443342776203968e-05,
|
| 250 |
+
"loss": 0.5679,
|
| 251 |
+
"step": 800
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 1.5774378585086042,
|
| 255 |
+
"grad_norm": 121.50483703613281,
|
| 256 |
+
"learning_rate": 2.6558073654390935e-05,
|
| 257 |
+
"loss": 0.6325,
|
| 258 |
+
"step": 825
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 1.6252390057361377,
|
| 262 |
+
"grad_norm": 29.850032806396484,
|
| 263 |
+
"learning_rate": 2.5672804532577905e-05,
|
| 264 |
+
"loss": 0.6696,
|
| 265 |
+
"step": 850
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 1.6730401529636711,
|
| 269 |
+
"grad_norm": 7.039335250854492,
|
| 270 |
+
"learning_rate": 2.4787535410764872e-05,
|
| 271 |
+
"loss": 0.5333,
|
| 272 |
+
"step": 875
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 1.7208413001912046,
|
| 276 |
+
"grad_norm": 18.278392791748047,
|
| 277 |
+
"learning_rate": 2.3902266288951843e-05,
|
| 278 |
+
"loss": 0.4725,
|
| 279 |
+
"step": 900
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 1.7686424474187379,
|
| 283 |
+
"grad_norm": 20.07522964477539,
|
| 284 |
+
"learning_rate": 2.3016997167138813e-05,
|
| 285 |
+
"loss": 0.532,
|
| 286 |
+
"step": 925
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 1.8164435946462714,
|
| 290 |
+
"grad_norm": 26.724767684936523,
|
| 291 |
+
"learning_rate": 2.213172804532578e-05,
|
| 292 |
+
"loss": 0.4835,
|
| 293 |
+
"step": 950
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 1.8642447418738048,
|
| 297 |
+
"grad_norm": 14.43714714050293,
|
| 298 |
+
"learning_rate": 2.124645892351275e-05,
|
| 299 |
+
"loss": 0.4511,
|
| 300 |
+
"step": 975
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 1.9120458891013383,
|
| 304 |
+
"grad_norm": 12.802144050598145,
|
| 305 |
+
"learning_rate": 2.0361189801699718e-05,
|
| 306 |
+
"loss": 0.4632,
|
| 307 |
+
"step": 1000
|
| 308 |
+
},
|
| 309 |
+
{
|
| 310 |
+
"epoch": 1.9598470363288718,
|
| 311 |
+
"grad_norm": 8.717876434326172,
|
| 312 |
+
"learning_rate": 1.9475920679886685e-05,
|
| 313 |
+
"loss": 0.481,
|
| 314 |
+
"step": 1025
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 2.0,
|
| 318 |
+
"eval_accuracy": 0.844168260038241,
|
| 319 |
+
"eval_f1_macro": 0.6551494818857037,
|
| 320 |
+
"eval_f1_micro": 0.844168260038241,
|
| 321 |
+
"eval_f1_weighted": 0.8158741281490736,
|
| 322 |
+
"eval_loss": 0.40430399775505066,
|
| 323 |
+
"eval_precision_macro": 0.7424475164964295,
|
| 324 |
+
"eval_precision_micro": 0.844168260038241,
|
| 325 |
+
"eval_precision_weighted": 0.8497777860209276,
|
| 326 |
+
"eval_recall_macro": 0.6970111110408359,
|
| 327 |
+
"eval_recall_micro": 0.844168260038241,
|
| 328 |
+
"eval_recall_weighted": 0.844168260038241,
|
| 329 |
+
"eval_runtime": 44.9693,
|
| 330 |
+
"eval_samples_per_second": 23.26,
|
| 331 |
+
"eval_steps_per_second": 1.468,
|
| 332 |
+
"step": 1046
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 2.0076481835564053,
|
| 336 |
+
"grad_norm": 3.963388681411743,
|
| 337 |
+
"learning_rate": 1.8590651558073655e-05,
|
| 338 |
+
"loss": 0.4624,
|
| 339 |
+
"step": 1050
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 2.0554493307839388,
|
| 343 |
+
"grad_norm": 37.179256439208984,
|
| 344 |
+
"learning_rate": 1.7705382436260622e-05,
|
| 345 |
+
"loss": 0.5283,
|
| 346 |
+
"step": 1075
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 2.1032504780114722,
|
| 350 |
+
"grad_norm": 14.825626373291016,
|
| 351 |
+
"learning_rate": 1.6820113314447596e-05,
|
| 352 |
+
"loss": 0.4486,
|
| 353 |
+
"step": 1100
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 2.1510516252390057,
|
| 357 |
+
"grad_norm": 11.206725120544434,
|
| 358 |
+
"learning_rate": 1.5934844192634563e-05,
|
| 359 |
+
"loss": 0.5357,
|
| 360 |
+
"step": 1125
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 2.198852772466539,
|
| 364 |
+
"grad_norm": 14.244481086730957,
|
| 365 |
+
"learning_rate": 1.5049575070821532e-05,
|
| 366 |
+
"loss": 0.3786,
|
| 367 |
+
"step": 1150
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 2.2466539196940727,
|
| 371 |
+
"grad_norm": 23.3243408203125,
|
| 372 |
+
"learning_rate": 1.41643059490085e-05,
|
| 373 |
+
"loss": 0.4675,
|
| 374 |
+
"step": 1175
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 2.294455066921606,
|
| 378 |
+
"grad_norm": 13.028168678283691,
|
| 379 |
+
"learning_rate": 1.3279036827195467e-05,
|
| 380 |
+
"loss": 0.5151,
|
| 381 |
+
"step": 1200
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 2.3422562141491396,
|
| 385 |
+
"grad_norm": 13.557563781738281,
|
| 386 |
+
"learning_rate": 1.2393767705382436e-05,
|
| 387 |
+
"loss": 0.4448,
|
| 388 |
+
"step": 1225
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 2.390057361376673,
|
| 392 |
+
"grad_norm": 5.000290870666504,
|
| 393 |
+
"learning_rate": 1.1508498583569407e-05,
|
| 394 |
+
"loss": 0.3802,
|
| 395 |
+
"step": 1250
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 2.4378585086042066,
|
| 399 |
+
"grad_norm": 25.394447326660156,
|
| 400 |
+
"learning_rate": 1.0623229461756375e-05,
|
| 401 |
+
"loss": 0.4251,
|
| 402 |
+
"step": 1275
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 2.48565965583174,
|
| 406 |
+
"grad_norm": 21.63365364074707,
|
| 407 |
+
"learning_rate": 9.737960339943342e-06,
|
| 408 |
+
"loss": 0.4564,
|
| 409 |
+
"step": 1300
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 2.5334608030592736,
|
| 413 |
+
"grad_norm": 32.95785140991211,
|
| 414 |
+
"learning_rate": 8.852691218130311e-06,
|
| 415 |
+
"loss": 0.4532,
|
| 416 |
+
"step": 1325
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 2.581261950286807,
|
| 420 |
+
"grad_norm": 64.51441955566406,
|
| 421 |
+
"learning_rate": 7.967422096317281e-06,
|
| 422 |
+
"loss": 0.566,
|
| 423 |
+
"step": 1350
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 2.62906309751434,
|
| 427 |
+
"grad_norm": 42.481014251708984,
|
| 428 |
+
"learning_rate": 7.08215297450425e-06,
|
| 429 |
+
"loss": 0.403,
|
| 430 |
+
"step": 1375
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 2.676864244741874,
|
| 434 |
+
"grad_norm": 4.409757137298584,
|
| 435 |
+
"learning_rate": 6.196883852691218e-06,
|
| 436 |
+
"loss": 0.4463,
|
| 437 |
+
"step": 1400
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 2.724665391969407,
|
| 441 |
+
"grad_norm": 51.99477767944336,
|
| 442 |
+
"learning_rate": 5.347025495750709e-06,
|
| 443 |
+
"loss": 0.5211,
|
| 444 |
+
"step": 1425
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 2.772466539196941,
|
| 448 |
+
"grad_norm": 37.646881103515625,
|
| 449 |
+
"learning_rate": 4.461756373937677e-06,
|
| 450 |
+
"loss": 0.3393,
|
| 451 |
+
"step": 1450
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 2.820267686424474,
|
| 455 |
+
"grad_norm": 33.17749786376953,
|
| 456 |
+
"learning_rate": 3.576487252124646e-06,
|
| 457 |
+
"loss": 0.4809,
|
| 458 |
+
"step": 1475
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 2.8680688336520075,
|
| 462 |
+
"grad_norm": 16.174297332763672,
|
| 463 |
+
"learning_rate": 2.691218130311615e-06,
|
| 464 |
+
"loss": 0.4465,
|
| 465 |
+
"step": 1500
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 2.915869980879541,
|
| 469 |
+
"grad_norm": 88.04303741455078,
|
| 470 |
+
"learning_rate": 1.8059490084985835e-06,
|
| 471 |
+
"loss": 0.4669,
|
| 472 |
+
"step": 1525
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 2.9636711281070744,
|
| 476 |
+
"grad_norm": 6.651047229766846,
|
| 477 |
+
"learning_rate": 9.206798866855524e-07,
|
| 478 |
+
"loss": 0.4518,
|
| 479 |
+
"step": 1550
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 3.0,
|
| 483 |
+
"eval_accuracy": 0.858508604206501,
|
| 484 |
+
"eval_f1_macro": 0.6843075887364951,
|
| 485 |
+
"eval_f1_micro": 0.858508604206501,
|
| 486 |
+
"eval_f1_weighted": 0.8303295709630173,
|
| 487 |
+
"eval_loss": 0.369663268327713,
|
| 488 |
+
"eval_precision_macro": 0.8204154992433914,
|
| 489 |
+
"eval_precision_micro": 0.858508604206501,
|
| 490 |
+
"eval_precision_weighted": 0.882137838723129,
|
| 491 |
+
"eval_recall_macro": 0.7169578798305077,
|
| 492 |
+
"eval_recall_micro": 0.858508604206501,
|
| 493 |
+
"eval_recall_weighted": 0.858508604206501,
|
| 494 |
+
"eval_runtime": 44.9545,
|
| 495 |
+
"eval_samples_per_second": 23.268,
|
| 496 |
+
"eval_steps_per_second": 1.468,
|
| 497 |
+
"step": 1569
|
| 498 |
+
}
|
| 499 |
+
],
|
| 500 |
+
"logging_steps": 25,
|
| 501 |
+
"max_steps": 1569,
|
| 502 |
+
"num_input_tokens_seen": 0,
|
| 503 |
+
"num_train_epochs": 3,
|
| 504 |
+
"save_steps": 500,
|
| 505 |
+
"stateful_callbacks": {
|
| 506 |
+
"EarlyStoppingCallback": {
|
| 507 |
+
"args": {
|
| 508 |
+
"early_stopping_patience": 5,
|
| 509 |
+
"early_stopping_threshold": 0.01
|
| 510 |
+
},
|
| 511 |
+
"attributes": {
|
| 512 |
+
"early_stopping_patience_counter": 0
|
| 513 |
+
}
|
| 514 |
+
},
|
| 515 |
+
"TrainerControl": {
|
| 516 |
+
"args": {
|
| 517 |
+
"should_epoch_stop": false,
|
| 518 |
+
"should_evaluate": false,
|
| 519 |
+
"should_log": false,
|
| 520 |
+
"should_save": true,
|
| 521 |
+
"should_training_stop": true
|
| 522 |
+
},
|
| 523 |
+
"attributes": {}
|
| 524 |
+
}
|
| 525 |
+
},
|
| 526 |
+
"total_flos": 6.587712686117929e+17,
|
| 527 |
+
"train_batch_size": 8,
|
| 528 |
+
"trial_name": null,
|
| 529 |
+
"trial_params": null
|
| 530 |
+
}
|
checkpoint-1569/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:eca3a10d9a741565046f2876e2cfce87d38a02c28237ca2b935a06fa9964f373
|
| 3 |
+
size 5240
|
config.json
ADDED
|
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "microsoft/resnet-152",
|
| 3 |
+
"_num_labels": 4,
|
| 4 |
+
"architectures": [
|
| 5 |
+
"ResNetForImageClassification"
|
| 6 |
+
],
|
| 7 |
+
"depths": [
|
| 8 |
+
3,
|
| 9 |
+
8,
|
| 10 |
+
36,
|
| 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": "Common_Rust",
|
| 25 |
+
"1": "Gray_Leaf_Spot",
|
| 26 |
+
"2": "Healthy_Leaf",
|
| 27 |
+
"3": "Northern_Leaf_Blight"
|
| 28 |
+
},
|
| 29 |
+
"label2id": {
|
| 30 |
+
"Common_Rust": 0,
|
| 31 |
+
"Gray_Leaf_Spot": 1,
|
| 32 |
+
"Healthy_Leaf": 2,
|
| 33 |
+
"Northern_Leaf_Blight": 3
|
| 34 |
+
},
|
| 35 |
+
"layer_type": "bottleneck",
|
| 36 |
+
"model_type": "resnet",
|
| 37 |
+
"num_channels": 3,
|
| 38 |
+
"out_features": [
|
| 39 |
+
"stage4"
|
| 40 |
+
],
|
| 41 |
+
"out_indices": [
|
| 42 |
+
4
|
| 43 |
+
],
|
| 44 |
+
"problem_type": "single_label_classification",
|
| 45 |
+
"stage_names": [
|
| 46 |
+
"stem",
|
| 47 |
+
"stage1",
|
| 48 |
+
"stage2",
|
| 49 |
+
"stage3",
|
| 50 |
+
"stage4"
|
| 51 |
+
],
|
| 52 |
+
"torch_dtype": "float32",
|
| 53 |
+
"transformers_version": "4.45.0"
|
| 54 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:645576a82568b0eef5352984eca080ea05a70ae94011f53978ab703b27247fd2
|
| 3 |
+
size 233338200
|
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/Oct18_06-24-24_07b4c6376f8e/events.out.tfevents.1729232666.07b4c6376f8e.21206.0
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 sha256:8f37bdba438437302083a85a6dfee44a678c1d1b00cb2f80a993b2bb8f55ad0e
|
| 3 |
+
size 21102
|
runs/Oct18_06-24-24_07b4c6376f8e/events.out.tfevents.1729233657.07b4c6376f8e.21206.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d59d89550d685a293f8325fc5bdb7ef5d01b247313518cd75d78cd561a3c6b50
|
| 3 |
+
size 921
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:eca3a10d9a741565046f2876e2cfce87d38a02c28237ca2b935a06fa9964f373
|
| 3 |
+
size 5240
|
training_params.json
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"data_path": "v-mdd-2000-150/autotrain-data",
|
| 3 |
+
"model": "microsoft/resnet-152",
|
| 4 |
+
"username": "eligapris",
|
| 5 |
+
"lr": 5e-05,
|
| 6 |
+
"epochs": 3,
|
| 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": "v-mdd-2000-150",
|
| 19 |
+
"auto_find_batch_size": false,
|
| 20 |
+
"mixed_precision": "fp16",
|
| 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": 5,
|
| 28 |
+
"early_stopping_threshold": 0.01
|
| 29 |
+
}
|