Commit
•
b37ddc1
1
Parent(s):
99f116b
End of training
Browse files- .ipynb_checkpoints/README-checkpoint.md +77 -0
- .ipynb_checkpoints/all_results-checkpoint.json +8 -0
- .ipynb_checkpoints/config-checkpoint.json +64 -0
- .ipynb_checkpoints/train_results-checkpoint.json +8 -0
- .ipynb_checkpoints/trainer_state-checkpoint.json +220 -0
- all_results.json +13 -0
- eval_results.json +8 -0
- train_results.json +8 -0
- trainer_state.json +220 -0
.ipynb_checkpoints/README-checkpoint.md
ADDED
|
@@ -0,0 +1,77 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
datasets:
|
| 6 |
+
- image_folder
|
| 7 |
+
metrics:
|
| 8 |
+
- accuracy
|
| 9 |
+
model-index:
|
| 10 |
+
- name: swin-tiny-patch4-window7-224-finetuned-eurosat
|
| 11 |
+
results:
|
| 12 |
+
- task:
|
| 13 |
+
name: Image Classification
|
| 14 |
+
type: image-classification
|
| 15 |
+
dataset:
|
| 16 |
+
name: image_folder
|
| 17 |
+
type: image_folder
|
| 18 |
+
args: default
|
| 19 |
+
metrics:
|
| 20 |
+
- name: Accuracy
|
| 21 |
+
type: accuracy
|
| 22 |
+
value: 0.9688888888888889
|
| 23 |
+
---
|
| 24 |
+
|
| 25 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 26 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 27 |
+
|
| 28 |
+
# swin-tiny-patch4-window7-224-finetuned-eurosat
|
| 29 |
+
|
| 30 |
+
This model is a fine-tuned version of [microsoft/swin-tiny-patch4-window7-224](https://huggingface.co/microsoft/swin-tiny-patch4-window7-224) on the image_folder dataset.
|
| 31 |
+
It achieves the following results on the evaluation set:
|
| 32 |
+
- Loss: 0.0866
|
| 33 |
+
- Accuracy: 0.9689
|
| 34 |
+
|
| 35 |
+
## Model description
|
| 36 |
+
|
| 37 |
+
More information needed
|
| 38 |
+
|
| 39 |
+
## Intended uses & limitations
|
| 40 |
+
|
| 41 |
+
More information needed
|
| 42 |
+
|
| 43 |
+
## Training and evaluation data
|
| 44 |
+
|
| 45 |
+
More information needed
|
| 46 |
+
|
| 47 |
+
## Training procedure
|
| 48 |
+
|
| 49 |
+
### Training hyperparameters
|
| 50 |
+
|
| 51 |
+
The following hyperparameters were used during training:
|
| 52 |
+
- learning_rate: 5e-05
|
| 53 |
+
- train_batch_size: 64
|
| 54 |
+
- eval_batch_size: 64
|
| 55 |
+
- seed: 42
|
| 56 |
+
- gradient_accumulation_steps: 4
|
| 57 |
+
- total_train_batch_size: 256
|
| 58 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 59 |
+
- lr_scheduler_type: linear
|
| 60 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 61 |
+
- num_epochs: 3
|
| 62 |
+
|
| 63 |
+
### Training results
|
| 64 |
+
|
| 65 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 66 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 67 |
+
| 0.3046 | 1.0 | 95 | 0.1547 | 0.9452 |
|
| 68 |
+
| 0.191 | 2.0 | 190 | 0.1161 | 0.9559 |
|
| 69 |
+
| 0.1701 | 3.0 | 285 | 0.0866 | 0.9689 |
|
| 70 |
+
|
| 71 |
+
|
| 72 |
+
### Framework versions
|
| 73 |
+
|
| 74 |
+
- Transformers 4.19.2
|
| 75 |
+
- Pytorch 1.11.0
|
| 76 |
+
- Datasets 2.2.2
|
| 77 |
+
- Tokenizers 0.12.1
|
.ipynb_checkpoints/all_results-checkpoint.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"total_flos": 1.8124066505760768e+18,
|
| 4 |
+
"train_loss": 0.3941639829100224,
|
| 5 |
+
"train_runtime": 487.9007,
|
| 6 |
+
"train_samples_per_second": 149.416,
|
| 7 |
+
"train_steps_per_second": 0.584
|
| 8 |
+
}
|
.ipynb_checkpoints/config-checkpoint.json
ADDED
|
@@ -0,0 +1,64 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "microsoft/swin-tiny-patch4-window7-224",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"SwinForImageClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.0,
|
| 7 |
+
"depths": [
|
| 8 |
+
2,
|
| 9 |
+
2,
|
| 10 |
+
6,
|
| 11 |
+
2
|
| 12 |
+
],
|
| 13 |
+
"drop_path_rate": 0.1,
|
| 14 |
+
"embed_dim": 96,
|
| 15 |
+
"encoder_stride": 32,
|
| 16 |
+
"hidden_act": "gelu",
|
| 17 |
+
"hidden_dropout_prob": 0.0,
|
| 18 |
+
"hidden_size": 768,
|
| 19 |
+
"id2label": {
|
| 20 |
+
"0": "AnnualCrop",
|
| 21 |
+
"1": "Forest",
|
| 22 |
+
"2": "HerbaceousVegetation",
|
| 23 |
+
"3": "Highway",
|
| 24 |
+
"4": "Industrial",
|
| 25 |
+
"5": "Pasture",
|
| 26 |
+
"6": "PermanentCrop",
|
| 27 |
+
"7": "Residential",
|
| 28 |
+
"8": "River",
|
| 29 |
+
"9": "SeaLake"
|
| 30 |
+
},
|
| 31 |
+
"image_size": 224,
|
| 32 |
+
"initializer_range": 0.02,
|
| 33 |
+
"label2id": {
|
| 34 |
+
"AnnualCrop": 0,
|
| 35 |
+
"Forest": 1,
|
| 36 |
+
"HerbaceousVegetation": 2,
|
| 37 |
+
"Highway": 3,
|
| 38 |
+
"Industrial": 4,
|
| 39 |
+
"Pasture": 5,
|
| 40 |
+
"PermanentCrop": 6,
|
| 41 |
+
"Residential": 7,
|
| 42 |
+
"River": 8,
|
| 43 |
+
"SeaLake": 9
|
| 44 |
+
},
|
| 45 |
+
"layer_norm_eps": 1e-05,
|
| 46 |
+
"mlp_ratio": 4.0,
|
| 47 |
+
"model_type": "swin",
|
| 48 |
+
"num_channels": 3,
|
| 49 |
+
"num_heads": [
|
| 50 |
+
3,
|
| 51 |
+
6,
|
| 52 |
+
12,
|
| 53 |
+
24
|
| 54 |
+
],
|
| 55 |
+
"num_layers": 4,
|
| 56 |
+
"patch_size": 4,
|
| 57 |
+
"path_norm": true,
|
| 58 |
+
"problem_type": "single_label_classification",
|
| 59 |
+
"qkv_bias": true,
|
| 60 |
+
"torch_dtype": "float32",
|
| 61 |
+
"transformers_version": "4.19.2",
|
| 62 |
+
"use_absolute_embeddings": false,
|
| 63 |
+
"window_size": 7
|
| 64 |
+
}
|
.ipynb_checkpoints/train_results-checkpoint.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"total_flos": 1.8124066505760768e+18,
|
| 4 |
+
"train_loss": 0.3941639829100224,
|
| 5 |
+
"train_runtime": 487.9007,
|
| 6 |
+
"train_samples_per_second": 149.416,
|
| 7 |
+
"train_steps_per_second": 0.584
|
| 8 |
+
}
|
.ipynb_checkpoints/trainer_state-checkpoint.json
ADDED
|
@@ -0,0 +1,220 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.9688888888888889,
|
| 3 |
+
"best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned-eurosat/checkpoint-285",
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"global_step": 285,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.11,
|
| 12 |
+
"learning_rate": 1.7241379310344828e-05,
|
| 13 |
+
"loss": 2.2089,
|
| 14 |
+
"step": 10
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.21,
|
| 18 |
+
"learning_rate": 3.4482758620689657e-05,
|
| 19 |
+
"loss": 1.769,
|
| 20 |
+
"step": 20
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.32,
|
| 24 |
+
"learning_rate": 4.9804687500000004e-05,
|
| 25 |
+
"loss": 0.9443,
|
| 26 |
+
"step": 30
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.42,
|
| 30 |
+
"learning_rate": 4.78515625e-05,
|
| 31 |
+
"loss": 0.5303,
|
| 32 |
+
"step": 40
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.53,
|
| 36 |
+
"learning_rate": 4.58984375e-05,
|
| 37 |
+
"loss": 0.4221,
|
| 38 |
+
"step": 50
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.63,
|
| 42 |
+
"learning_rate": 4.3945312500000005e-05,
|
| 43 |
+
"loss": 0.3781,
|
| 44 |
+
"step": 60
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.74,
|
| 48 |
+
"learning_rate": 4.1992187500000003e-05,
|
| 49 |
+
"loss": 0.3348,
|
| 50 |
+
"step": 70
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.84,
|
| 54 |
+
"learning_rate": 4.00390625e-05,
|
| 55 |
+
"loss": 0.3034,
|
| 56 |
+
"step": 80
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.95,
|
| 60 |
+
"learning_rate": 3.80859375e-05,
|
| 61 |
+
"loss": 0.3046,
|
| 62 |
+
"step": 90
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 1.0,
|
| 66 |
+
"eval_accuracy": 0.9451851851851852,
|
| 67 |
+
"eval_loss": 0.15470224618911743,
|
| 68 |
+
"eval_runtime": 10.7878,
|
| 69 |
+
"eval_samples_per_second": 250.283,
|
| 70 |
+
"eval_steps_per_second": 3.986,
|
| 71 |
+
"step": 95
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"epoch": 1.05,
|
| 75 |
+
"learning_rate": 3.6132812500000005e-05,
|
| 76 |
+
"loss": 0.2883,
|
| 77 |
+
"step": 100
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"epoch": 1.16,
|
| 81 |
+
"learning_rate": 3.41796875e-05,
|
| 82 |
+
"loss": 0.2784,
|
| 83 |
+
"step": 110
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 1.26,
|
| 87 |
+
"learning_rate": 3.22265625e-05,
|
| 88 |
+
"loss": 0.2677,
|
| 89 |
+
"step": 120
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 1.37,
|
| 93 |
+
"learning_rate": 3.02734375e-05,
|
| 94 |
+
"loss": 0.2631,
|
| 95 |
+
"step": 130
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 1.47,
|
| 99 |
+
"learning_rate": 2.83203125e-05,
|
| 100 |
+
"loss": 0.2293,
|
| 101 |
+
"step": 140
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 1.58,
|
| 105 |
+
"learning_rate": 2.63671875e-05,
|
| 106 |
+
"loss": 0.2219,
|
| 107 |
+
"step": 150
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 1.68,
|
| 111 |
+
"learning_rate": 2.44140625e-05,
|
| 112 |
+
"loss": 0.2059,
|
| 113 |
+
"step": 160
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 1.79,
|
| 117 |
+
"learning_rate": 2.24609375e-05,
|
| 118 |
+
"loss": 0.2308,
|
| 119 |
+
"step": 170
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 1.89,
|
| 123 |
+
"learning_rate": 2.05078125e-05,
|
| 124 |
+
"loss": 0.1977,
|
| 125 |
+
"step": 180
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 2.0,
|
| 129 |
+
"learning_rate": 1.85546875e-05,
|
| 130 |
+
"loss": 0.191,
|
| 131 |
+
"step": 190
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 2.0,
|
| 135 |
+
"eval_accuracy": 0.955925925925926,
|
| 136 |
+
"eval_loss": 0.11611586064100266,
|
| 137 |
+
"eval_runtime": 8.8072,
|
| 138 |
+
"eval_samples_per_second": 306.569,
|
| 139 |
+
"eval_steps_per_second": 4.882,
|
| 140 |
+
"step": 190
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 2.11,
|
| 144 |
+
"learning_rate": 1.66015625e-05,
|
| 145 |
+
"loss": 0.1861,
|
| 146 |
+
"step": 200
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 2.21,
|
| 150 |
+
"learning_rate": 1.4648437500000001e-05,
|
| 151 |
+
"loss": 0.1912,
|
| 152 |
+
"step": 210
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 2.32,
|
| 156 |
+
"learning_rate": 1.2695312500000001e-05,
|
| 157 |
+
"loss": 0.1704,
|
| 158 |
+
"step": 220
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 2.42,
|
| 162 |
+
"learning_rate": 1.0742187500000001e-05,
|
| 163 |
+
"loss": 0.1792,
|
| 164 |
+
"step": 230
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 2.53,
|
| 168 |
+
"learning_rate": 8.789062500000001e-06,
|
| 169 |
+
"loss": 0.178,
|
| 170 |
+
"step": 240
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 2.63,
|
| 174 |
+
"learning_rate": 6.8359375e-06,
|
| 175 |
+
"loss": 0.1685,
|
| 176 |
+
"step": 250
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 2.74,
|
| 180 |
+
"learning_rate": 4.8828125e-06,
|
| 181 |
+
"loss": 0.1596,
|
| 182 |
+
"step": 260
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 2.84,
|
| 186 |
+
"learning_rate": 2.9296875e-06,
|
| 187 |
+
"loss": 0.1769,
|
| 188 |
+
"step": 270
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 2.95,
|
| 192 |
+
"learning_rate": 9.765625e-07,
|
| 193 |
+
"loss": 0.1701,
|
| 194 |
+
"step": 280
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 3.0,
|
| 198 |
+
"eval_accuracy": 0.9688888888888889,
|
| 199 |
+
"eval_loss": 0.08657249808311462,
|
| 200 |
+
"eval_runtime": 9.1811,
|
| 201 |
+
"eval_samples_per_second": 294.083,
|
| 202 |
+
"eval_steps_per_second": 4.684,
|
| 203 |
+
"step": 285
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 3.0,
|
| 207 |
+
"step": 285,
|
| 208 |
+
"total_flos": 1.8124066505760768e+18,
|
| 209 |
+
"train_loss": 0.3941639829100224,
|
| 210 |
+
"train_runtime": 487.9007,
|
| 211 |
+
"train_samples_per_second": 149.416,
|
| 212 |
+
"train_steps_per_second": 0.584
|
| 213 |
+
}
|
| 214 |
+
],
|
| 215 |
+
"max_steps": 285,
|
| 216 |
+
"num_train_epochs": 3,
|
| 217 |
+
"total_flos": 1.8124066505760768e+18,
|
| 218 |
+
"trial_name": null,
|
| 219 |
+
"trial_params": null
|
| 220 |
+
}
|
all_results.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"eval_accuracy": 0.9688888888888889,
|
| 4 |
+
"eval_loss": 0.08657249808311462,
|
| 5 |
+
"eval_runtime": 9.4322,
|
| 6 |
+
"eval_samples_per_second": 286.255,
|
| 7 |
+
"eval_steps_per_second": 4.559,
|
| 8 |
+
"total_flos": 1.8124066505760768e+18,
|
| 9 |
+
"train_loss": 0.3941639829100224,
|
| 10 |
+
"train_runtime": 487.9007,
|
| 11 |
+
"train_samples_per_second": 149.416,
|
| 12 |
+
"train_steps_per_second": 0.584
|
| 13 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"eval_accuracy": 0.9688888888888889,
|
| 4 |
+
"eval_loss": 0.08657249808311462,
|
| 5 |
+
"eval_runtime": 9.4322,
|
| 6 |
+
"eval_samples_per_second": 286.255,
|
| 7 |
+
"eval_steps_per_second": 4.559
|
| 8 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"total_flos": 1.8124066505760768e+18,
|
| 4 |
+
"train_loss": 0.3941639829100224,
|
| 5 |
+
"train_runtime": 487.9007,
|
| 6 |
+
"train_samples_per_second": 149.416,
|
| 7 |
+
"train_steps_per_second": 0.584
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,220 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.9688888888888889,
|
| 3 |
+
"best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned-eurosat/checkpoint-285",
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"global_step": 285,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.11,
|
| 12 |
+
"learning_rate": 1.7241379310344828e-05,
|
| 13 |
+
"loss": 2.2089,
|
| 14 |
+
"step": 10
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.21,
|
| 18 |
+
"learning_rate": 3.4482758620689657e-05,
|
| 19 |
+
"loss": 1.769,
|
| 20 |
+
"step": 20
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.32,
|
| 24 |
+
"learning_rate": 4.9804687500000004e-05,
|
| 25 |
+
"loss": 0.9443,
|
| 26 |
+
"step": 30
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.42,
|
| 30 |
+
"learning_rate": 4.78515625e-05,
|
| 31 |
+
"loss": 0.5303,
|
| 32 |
+
"step": 40
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.53,
|
| 36 |
+
"learning_rate": 4.58984375e-05,
|
| 37 |
+
"loss": 0.4221,
|
| 38 |
+
"step": 50
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.63,
|
| 42 |
+
"learning_rate": 4.3945312500000005e-05,
|
| 43 |
+
"loss": 0.3781,
|
| 44 |
+
"step": 60
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.74,
|
| 48 |
+
"learning_rate": 4.1992187500000003e-05,
|
| 49 |
+
"loss": 0.3348,
|
| 50 |
+
"step": 70
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.84,
|
| 54 |
+
"learning_rate": 4.00390625e-05,
|
| 55 |
+
"loss": 0.3034,
|
| 56 |
+
"step": 80
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.95,
|
| 60 |
+
"learning_rate": 3.80859375e-05,
|
| 61 |
+
"loss": 0.3046,
|
| 62 |
+
"step": 90
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 1.0,
|
| 66 |
+
"eval_accuracy": 0.9451851851851852,
|
| 67 |
+
"eval_loss": 0.15470224618911743,
|
| 68 |
+
"eval_runtime": 10.7878,
|
| 69 |
+
"eval_samples_per_second": 250.283,
|
| 70 |
+
"eval_steps_per_second": 3.986,
|
| 71 |
+
"step": 95
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"epoch": 1.05,
|
| 75 |
+
"learning_rate": 3.6132812500000005e-05,
|
| 76 |
+
"loss": 0.2883,
|
| 77 |
+
"step": 100
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"epoch": 1.16,
|
| 81 |
+
"learning_rate": 3.41796875e-05,
|
| 82 |
+
"loss": 0.2784,
|
| 83 |
+
"step": 110
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 1.26,
|
| 87 |
+
"learning_rate": 3.22265625e-05,
|
| 88 |
+
"loss": 0.2677,
|
| 89 |
+
"step": 120
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 1.37,
|
| 93 |
+
"learning_rate": 3.02734375e-05,
|
| 94 |
+
"loss": 0.2631,
|
| 95 |
+
"step": 130
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 1.47,
|
| 99 |
+
"learning_rate": 2.83203125e-05,
|
| 100 |
+
"loss": 0.2293,
|
| 101 |
+
"step": 140
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 1.58,
|
| 105 |
+
"learning_rate": 2.63671875e-05,
|
| 106 |
+
"loss": 0.2219,
|
| 107 |
+
"step": 150
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 1.68,
|
| 111 |
+
"learning_rate": 2.44140625e-05,
|
| 112 |
+
"loss": 0.2059,
|
| 113 |
+
"step": 160
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 1.79,
|
| 117 |
+
"learning_rate": 2.24609375e-05,
|
| 118 |
+
"loss": 0.2308,
|
| 119 |
+
"step": 170
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 1.89,
|
| 123 |
+
"learning_rate": 2.05078125e-05,
|
| 124 |
+
"loss": 0.1977,
|
| 125 |
+
"step": 180
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 2.0,
|
| 129 |
+
"learning_rate": 1.85546875e-05,
|
| 130 |
+
"loss": 0.191,
|
| 131 |
+
"step": 190
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 2.0,
|
| 135 |
+
"eval_accuracy": 0.955925925925926,
|
| 136 |
+
"eval_loss": 0.11611586064100266,
|
| 137 |
+
"eval_runtime": 8.8072,
|
| 138 |
+
"eval_samples_per_second": 306.569,
|
| 139 |
+
"eval_steps_per_second": 4.882,
|
| 140 |
+
"step": 190
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 2.11,
|
| 144 |
+
"learning_rate": 1.66015625e-05,
|
| 145 |
+
"loss": 0.1861,
|
| 146 |
+
"step": 200
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 2.21,
|
| 150 |
+
"learning_rate": 1.4648437500000001e-05,
|
| 151 |
+
"loss": 0.1912,
|
| 152 |
+
"step": 210
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 2.32,
|
| 156 |
+
"learning_rate": 1.2695312500000001e-05,
|
| 157 |
+
"loss": 0.1704,
|
| 158 |
+
"step": 220
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 2.42,
|
| 162 |
+
"learning_rate": 1.0742187500000001e-05,
|
| 163 |
+
"loss": 0.1792,
|
| 164 |
+
"step": 230
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 2.53,
|
| 168 |
+
"learning_rate": 8.789062500000001e-06,
|
| 169 |
+
"loss": 0.178,
|
| 170 |
+
"step": 240
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 2.63,
|
| 174 |
+
"learning_rate": 6.8359375e-06,
|
| 175 |
+
"loss": 0.1685,
|
| 176 |
+
"step": 250
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 2.74,
|
| 180 |
+
"learning_rate": 4.8828125e-06,
|
| 181 |
+
"loss": 0.1596,
|
| 182 |
+
"step": 260
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 2.84,
|
| 186 |
+
"learning_rate": 2.9296875e-06,
|
| 187 |
+
"loss": 0.1769,
|
| 188 |
+
"step": 270
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 2.95,
|
| 192 |
+
"learning_rate": 9.765625e-07,
|
| 193 |
+
"loss": 0.1701,
|
| 194 |
+
"step": 280
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 3.0,
|
| 198 |
+
"eval_accuracy": 0.9688888888888889,
|
| 199 |
+
"eval_loss": 0.08657249808311462,
|
| 200 |
+
"eval_runtime": 9.1811,
|
| 201 |
+
"eval_samples_per_second": 294.083,
|
| 202 |
+
"eval_steps_per_second": 4.684,
|
| 203 |
+
"step": 285
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 3.0,
|
| 207 |
+
"step": 285,
|
| 208 |
+
"total_flos": 1.8124066505760768e+18,
|
| 209 |
+
"train_loss": 0.3941639829100224,
|
| 210 |
+
"train_runtime": 487.9007,
|
| 211 |
+
"train_samples_per_second": 149.416,
|
| 212 |
+
"train_steps_per_second": 0.584
|
| 213 |
+
}
|
| 214 |
+
],
|
| 215 |
+
"max_steps": 285,
|
| 216 |
+
"num_train_epochs": 3,
|
| 217 |
+
"total_flos": 1.8124066505760768e+18,
|
| 218 |
+
"trial_name": null,
|
| 219 |
+
"trial_params": null
|
| 220 |
+
}
|