End of training
Browse files- README.md +117 -0
- all_results.json +12 -0
- config.json +60 -0
- eval_results.json +8 -0
- model.safetensors +3 -0
- preprocessor_config.json +22 -0
- runs/Oct12_17-58-48_DESKTOP-SKBE9FB/events.out.tfevents.1728777529.DESKTOP-SKBE9FB.14652.0 +3 -0
- runs/Oct12_17-58-48_DESKTOP-SKBE9FB/events.out.tfevents.1728777886.DESKTOP-SKBE9FB.14652.1 +3 -0
- train_results.json +7 -0
- trainer_state.json +510 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,117 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: microsoft/swinv2-tiny-patch4-window8-256
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
datasets:
|
| 7 |
+
- imagefolder
|
| 8 |
+
metrics:
|
| 9 |
+
- accuracy
|
| 10 |
+
model-index:
|
| 11 |
+
- name: swinv2-tiny-patch4-window8-256-Diabetic-Retinopathy
|
| 12 |
+
results:
|
| 13 |
+
- task:
|
| 14 |
+
name: Image Classification
|
| 15 |
+
type: image-classification
|
| 16 |
+
dataset:
|
| 17 |
+
name: imagefolder
|
| 18 |
+
type: imagefolder
|
| 19 |
+
config: default
|
| 20 |
+
split: validation
|
| 21 |
+
args: default
|
| 22 |
+
metrics:
|
| 23 |
+
- name: Accuracy
|
| 24 |
+
type: accuracy
|
| 25 |
+
value: 0.8090909090909091
|
| 26 |
+
---
|
| 27 |
+
|
| 28 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 29 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 30 |
+
|
| 31 |
+
# swinv2-tiny-patch4-window8-256-Diabetic-Retinopathy
|
| 32 |
+
|
| 33 |
+
This model is a fine-tuned version of [microsoft/swinv2-tiny-patch4-window8-256](https://huggingface.co/microsoft/swinv2-tiny-patch4-window8-256) on the imagefolder dataset.
|
| 34 |
+
It achieves the following results on the evaluation set:
|
| 35 |
+
- Loss: 0.5203
|
| 36 |
+
- Accuracy: 0.8091
|
| 37 |
+
|
| 38 |
+
## Model description
|
| 39 |
+
|
| 40 |
+
More information needed
|
| 41 |
+
|
| 42 |
+
## Intended uses & limitations
|
| 43 |
+
|
| 44 |
+
More information needed
|
| 45 |
+
|
| 46 |
+
## Training and evaluation data
|
| 47 |
+
|
| 48 |
+
More information needed
|
| 49 |
+
|
| 50 |
+
## Training procedure
|
| 51 |
+
|
| 52 |
+
### Training hyperparameters
|
| 53 |
+
|
| 54 |
+
The following hyperparameters were used during training:
|
| 55 |
+
- learning_rate: 5e-05
|
| 56 |
+
- train_batch_size: 32
|
| 57 |
+
- eval_batch_size: 32
|
| 58 |
+
- seed: 42
|
| 59 |
+
- gradient_accumulation_steps: 4
|
| 60 |
+
- total_train_batch_size: 128
|
| 61 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 62 |
+
- lr_scheduler_type: linear
|
| 63 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 64 |
+
- num_epochs: 40
|
| 65 |
+
|
| 66 |
+
### Training results
|
| 67 |
+
|
| 68 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 69 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 70 |
+
| No log | 1.0 | 5 | 1.6054 | 0.4909 |
|
| 71 |
+
| 1.6039 | 2.0 | 10 | 1.5774 | 0.4909 |
|
| 72 |
+
| 1.6039 | 3.0 | 15 | 1.4627 | 0.4909 |
|
| 73 |
+
| 1.4766 | 4.0 | 20 | 1.3211 | 0.4909 |
|
| 74 |
+
| 1.4766 | 5.0 | 25 | 1.2294 | 0.4909 |
|
| 75 |
+
| 1.2308 | 6.0 | 30 | 1.0657 | 0.4909 |
|
| 76 |
+
| 1.2308 | 7.0 | 35 | 0.9504 | 0.6545 |
|
| 77 |
+
| 1.017 | 8.0 | 40 | 0.8463 | 0.7364 |
|
| 78 |
+
| 1.017 | 9.0 | 45 | 0.7463 | 0.7455 |
|
| 79 |
+
| 0.8345 | 10.0 | 50 | 0.6948 | 0.7455 |
|
| 80 |
+
| 0.8345 | 11.0 | 55 | 0.6460 | 0.7545 |
|
| 81 |
+
| 0.7594 | 12.0 | 60 | 0.6403 | 0.7545 |
|
| 82 |
+
| 0.7594 | 13.0 | 65 | 0.6319 | 0.7545 |
|
| 83 |
+
| 0.7228 | 14.0 | 70 | 0.5999 | 0.7455 |
|
| 84 |
+
| 0.7228 | 15.0 | 75 | 0.5922 | 0.7545 |
|
| 85 |
+
| 0.6851 | 16.0 | 80 | 0.5955 | 0.7636 |
|
| 86 |
+
| 0.6851 | 17.0 | 85 | 0.5731 | 0.7545 |
|
| 87 |
+
| 0.6549 | 18.0 | 90 | 0.5603 | 0.7818 |
|
| 88 |
+
| 0.6549 | 19.0 | 95 | 0.5386 | 0.7818 |
|
| 89 |
+
| 0.643 | 20.0 | 100 | 0.5424 | 0.7727 |
|
| 90 |
+
| 0.643 | 21.0 | 105 | 0.5295 | 0.7909 |
|
| 91 |
+
| 0.5951 | 22.0 | 110 | 0.5203 | 0.8091 |
|
| 92 |
+
| 0.5951 | 23.0 | 115 | 0.5162 | 0.7909 |
|
| 93 |
+
| 0.5913 | 24.0 | 120 | 0.5095 | 0.7818 |
|
| 94 |
+
| 0.5913 | 25.0 | 125 | 0.5140 | 0.7909 |
|
| 95 |
+
| 0.5462 | 26.0 | 130 | 0.5167 | 0.7636 |
|
| 96 |
+
| 0.5462 | 27.0 | 135 | 0.4943 | 0.7909 |
|
| 97 |
+
| 0.5538 | 28.0 | 140 | 0.4844 | 0.7636 |
|
| 98 |
+
| 0.5538 | 29.0 | 145 | 0.4821 | 0.7727 |
|
| 99 |
+
| 0.5497 | 30.0 | 150 | 0.4952 | 0.7727 |
|
| 100 |
+
| 0.5497 | 31.0 | 155 | 0.4995 | 0.7818 |
|
| 101 |
+
| 0.4923 | 32.0 | 160 | 0.4910 | 0.7727 |
|
| 102 |
+
| 0.4923 | 33.0 | 165 | 0.5029 | 0.7818 |
|
| 103 |
+
| 0.5228 | 34.0 | 170 | 0.5083 | 0.7818 |
|
| 104 |
+
| 0.5228 | 35.0 | 175 | 0.4984 | 0.7909 |
|
| 105 |
+
| 0.4986 | 36.0 | 180 | 0.4914 | 0.7909 |
|
| 106 |
+
| 0.4986 | 37.0 | 185 | 0.4926 | 0.7909 |
|
| 107 |
+
| 0.5154 | 38.0 | 190 | 0.4915 | 0.8 |
|
| 108 |
+
| 0.5154 | 39.0 | 195 | 0.4886 | 0.8 |
|
| 109 |
+
| 0.5081 | 40.0 | 200 | 0.4875 | 0.8 |
|
| 110 |
+
|
| 111 |
+
|
| 112 |
+
### Framework versions
|
| 113 |
+
|
| 114 |
+
- Transformers 4.36.2
|
| 115 |
+
- Pytorch 2.1.2+cu118
|
| 116 |
+
- Datasets 2.16.1
|
| 117 |
+
- Tokenizers 0.15.0
|
all_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 40.0,
|
| 3 |
+
"eval_accuracy": 0.8090909090909091,
|
| 4 |
+
"eval_loss": 0.5203222036361694,
|
| 5 |
+
"eval_runtime": 0.6076,
|
| 6 |
+
"eval_samples_per_second": 181.031,
|
| 7 |
+
"eval_steps_per_second": 6.583,
|
| 8 |
+
"train_loss": 0.750064127445221,
|
| 9 |
+
"train_runtime": 356.9379,
|
| 10 |
+
"train_samples_per_second": 69.816,
|
| 11 |
+
"train_steps_per_second": 0.56
|
| 12 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "microsoft/swinv2-tiny-patch4-window8-256",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"Swinv2ForImageClassification"
|
| 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": "Mild",
|
| 21 |
+
"1": "Moderate",
|
| 22 |
+
"2": "No_DR",
|
| 23 |
+
"3": "Proliferate_DR",
|
| 24 |
+
"4": "Severe"
|
| 25 |
+
},
|
| 26 |
+
"image_size": 256,
|
| 27 |
+
"initializer_range": 0.02,
|
| 28 |
+
"label2id": {
|
| 29 |
+
"Mild": 0,
|
| 30 |
+
"Moderate": 1,
|
| 31 |
+
"No_DR": 2,
|
| 32 |
+
"Proliferate_DR": 3,
|
| 33 |
+
"Severe": 4
|
| 34 |
+
},
|
| 35 |
+
"layer_norm_eps": 1e-05,
|
| 36 |
+
"mlp_ratio": 4.0,
|
| 37 |
+
"model_type": "swinv2",
|
| 38 |
+
"num_channels": 3,
|
| 39 |
+
"num_heads": [
|
| 40 |
+
3,
|
| 41 |
+
6,
|
| 42 |
+
12,
|
| 43 |
+
24
|
| 44 |
+
],
|
| 45 |
+
"num_layers": 4,
|
| 46 |
+
"patch_size": 4,
|
| 47 |
+
"path_norm": true,
|
| 48 |
+
"pretrained_window_sizes": [
|
| 49 |
+
0,
|
| 50 |
+
0,
|
| 51 |
+
0,
|
| 52 |
+
0
|
| 53 |
+
],
|
| 54 |
+
"problem_type": "single_label_classification",
|
| 55 |
+
"qkv_bias": true,
|
| 56 |
+
"torch_dtype": "float32",
|
| 57 |
+
"transformers_version": "4.36.2",
|
| 58 |
+
"use_absolute_embeddings": false,
|
| 59 |
+
"window_size": 8
|
| 60 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 40.0,
|
| 3 |
+
"eval_accuracy": 0.8090909090909091,
|
| 4 |
+
"eval_loss": 0.5203222036361694,
|
| 5 |
+
"eval_runtime": 0.6076,
|
| 6 |
+
"eval_samples_per_second": 181.031,
|
| 7 |
+
"eval_steps_per_second": 6.583
|
| 8 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5c1f96515fab9dc9e7f57e7ccdd219306116ce8deddbbea81b330b3249533682
|
| 3 |
+
size 110359372
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_normalize": true,
|
| 3 |
+
"do_rescale": true,
|
| 4 |
+
"do_resize": true,
|
| 5 |
+
"image_mean": [
|
| 6 |
+
0.485,
|
| 7 |
+
0.456,
|
| 8 |
+
0.406
|
| 9 |
+
],
|
| 10 |
+
"image_processor_type": "ViTImageProcessor",
|
| 11 |
+
"image_std": [
|
| 12 |
+
0.229,
|
| 13 |
+
0.224,
|
| 14 |
+
0.225
|
| 15 |
+
],
|
| 16 |
+
"resample": 3,
|
| 17 |
+
"rescale_factor": 0.00392156862745098,
|
| 18 |
+
"size": {
|
| 19 |
+
"height": 256,
|
| 20 |
+
"width": 256
|
| 21 |
+
}
|
| 22 |
+
}
|
runs/Oct12_17-58-48_DESKTOP-SKBE9FB/events.out.tfevents.1728777529.DESKTOP-SKBE9FB.14652.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f9792bc671787aa2b7cce2e68160e97fc5dd15bbe2de4196ddceb48ac222355a
|
| 3 |
+
size 21112
|
runs/Oct12_17-58-48_DESKTOP-SKBE9FB/events.out.tfevents.1728777886.DESKTOP-SKBE9FB.14652.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0f2f25b487b50e2eae2515b87ceec72618266c72689d8ae66e6ecec54783027d
|
| 3 |
+
size 411
|
train_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 40.0,
|
| 3 |
+
"train_loss": 0.750064127445221,
|
| 4 |
+
"train_runtime": 356.9379,
|
| 5 |
+
"train_samples_per_second": 69.816,
|
| 6 |
+
"train_steps_per_second": 0.56
|
| 7 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,510 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.8090909090909091,
|
| 3 |
+
"best_model_checkpoint": "swinv2-tiny-patch4-window8-256-Diabetic-Retinopathy\\checkpoint-110",
|
| 4 |
+
"epoch": 40.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 200,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 1.0,
|
| 13 |
+
"eval_accuracy": 0.4909090909090909,
|
| 14 |
+
"eval_loss": 1.6053773164749146,
|
| 15 |
+
"eval_runtime": 1.1664,
|
| 16 |
+
"eval_samples_per_second": 94.304,
|
| 17 |
+
"eval_steps_per_second": 3.429,
|
| 18 |
+
"step": 5
|
| 19 |
+
},
|
| 20 |
+
{
|
| 21 |
+
"epoch": 2.0,
|
| 22 |
+
"learning_rate": 2.5e-05,
|
| 23 |
+
"loss": 1.6039,
|
| 24 |
+
"step": 10
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 2.0,
|
| 28 |
+
"eval_accuracy": 0.4909090909090909,
|
| 29 |
+
"eval_loss": 1.577444314956665,
|
| 30 |
+
"eval_runtime": 0.6246,
|
| 31 |
+
"eval_samples_per_second": 176.117,
|
| 32 |
+
"eval_steps_per_second": 6.404,
|
| 33 |
+
"step": 10
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 3.0,
|
| 37 |
+
"eval_accuracy": 0.4909090909090909,
|
| 38 |
+
"eval_loss": 1.4627095460891724,
|
| 39 |
+
"eval_runtime": 0.6237,
|
| 40 |
+
"eval_samples_per_second": 176.372,
|
| 41 |
+
"eval_steps_per_second": 6.414,
|
| 42 |
+
"step": 15
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 4.0,
|
| 46 |
+
"learning_rate": 5e-05,
|
| 47 |
+
"loss": 1.4766,
|
| 48 |
+
"step": 20
|
| 49 |
+
},
|
| 50 |
+
{
|
| 51 |
+
"epoch": 4.0,
|
| 52 |
+
"eval_accuracy": 0.4909090909090909,
|
| 53 |
+
"eval_loss": 1.3211016654968262,
|
| 54 |
+
"eval_runtime": 0.5963,
|
| 55 |
+
"eval_samples_per_second": 184.459,
|
| 56 |
+
"eval_steps_per_second": 6.708,
|
| 57 |
+
"step": 20
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 5.0,
|
| 61 |
+
"eval_accuracy": 0.4909090909090909,
|
| 62 |
+
"eval_loss": 1.2294203042984009,
|
| 63 |
+
"eval_runtime": 0.6045,
|
| 64 |
+
"eval_samples_per_second": 181.978,
|
| 65 |
+
"eval_steps_per_second": 6.617,
|
| 66 |
+
"step": 25
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 6.0,
|
| 70 |
+
"learning_rate": 4.722222222222222e-05,
|
| 71 |
+
"loss": 1.2308,
|
| 72 |
+
"step": 30
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 6.0,
|
| 76 |
+
"eval_accuracy": 0.4909090909090909,
|
| 77 |
+
"eval_loss": 1.0656994581222534,
|
| 78 |
+
"eval_runtime": 0.6274,
|
| 79 |
+
"eval_samples_per_second": 175.336,
|
| 80 |
+
"eval_steps_per_second": 6.376,
|
| 81 |
+
"step": 30
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 7.0,
|
| 85 |
+
"eval_accuracy": 0.6545454545454545,
|
| 86 |
+
"eval_loss": 0.9504080414772034,
|
| 87 |
+
"eval_runtime": 0.6116,
|
| 88 |
+
"eval_samples_per_second": 179.842,
|
| 89 |
+
"eval_steps_per_second": 6.54,
|
| 90 |
+
"step": 35
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 8.0,
|
| 94 |
+
"learning_rate": 4.4444444444444447e-05,
|
| 95 |
+
"loss": 1.017,
|
| 96 |
+
"step": 40
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 8.0,
|
| 100 |
+
"eval_accuracy": 0.7363636363636363,
|
| 101 |
+
"eval_loss": 0.8463379740715027,
|
| 102 |
+
"eval_runtime": 0.6133,
|
| 103 |
+
"eval_samples_per_second": 179.362,
|
| 104 |
+
"eval_steps_per_second": 6.522,
|
| 105 |
+
"step": 40
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 9.0,
|
| 109 |
+
"eval_accuracy": 0.7454545454545455,
|
| 110 |
+
"eval_loss": 0.7462926506996155,
|
| 111 |
+
"eval_runtime": 0.6373,
|
| 112 |
+
"eval_samples_per_second": 172.596,
|
| 113 |
+
"eval_steps_per_second": 6.276,
|
| 114 |
+
"step": 45
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 10.0,
|
| 118 |
+
"learning_rate": 4.166666666666667e-05,
|
| 119 |
+
"loss": 0.8345,
|
| 120 |
+
"step": 50
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 10.0,
|
| 124 |
+
"eval_accuracy": 0.7454545454545455,
|
| 125 |
+
"eval_loss": 0.6947882771492004,
|
| 126 |
+
"eval_runtime": 0.6097,
|
| 127 |
+
"eval_samples_per_second": 180.42,
|
| 128 |
+
"eval_steps_per_second": 6.561,
|
| 129 |
+
"step": 50
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 11.0,
|
| 133 |
+
"eval_accuracy": 0.7545454545454545,
|
| 134 |
+
"eval_loss": 0.6460423469543457,
|
| 135 |
+
"eval_runtime": 0.6052,
|
| 136 |
+
"eval_samples_per_second": 181.744,
|
| 137 |
+
"eval_steps_per_second": 6.609,
|
| 138 |
+
"step": 55
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 12.0,
|
| 142 |
+
"learning_rate": 3.888888888888889e-05,
|
| 143 |
+
"loss": 0.7594,
|
| 144 |
+
"step": 60
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 12.0,
|
| 148 |
+
"eval_accuracy": 0.7545454545454545,
|
| 149 |
+
"eval_loss": 0.6403194069862366,
|
| 150 |
+
"eval_runtime": 0.6016,
|
| 151 |
+
"eval_samples_per_second": 182.831,
|
| 152 |
+
"eval_steps_per_second": 6.648,
|
| 153 |
+
"step": 60
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 13.0,
|
| 157 |
+
"eval_accuracy": 0.7545454545454545,
|
| 158 |
+
"eval_loss": 0.631945788860321,
|
| 159 |
+
"eval_runtime": 0.6046,
|
| 160 |
+
"eval_samples_per_second": 181.926,
|
| 161 |
+
"eval_steps_per_second": 6.615,
|
| 162 |
+
"step": 65
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 14.0,
|
| 166 |
+
"learning_rate": 3.611111111111111e-05,
|
| 167 |
+
"loss": 0.7228,
|
| 168 |
+
"step": 70
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 14.0,
|
| 172 |
+
"eval_accuracy": 0.7454545454545455,
|
| 173 |
+
"eval_loss": 0.5999094843864441,
|
| 174 |
+
"eval_runtime": 0.6056,
|
| 175 |
+
"eval_samples_per_second": 181.624,
|
| 176 |
+
"eval_steps_per_second": 6.605,
|
| 177 |
+
"step": 70
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 15.0,
|
| 181 |
+
"eval_accuracy": 0.7545454545454545,
|
| 182 |
+
"eval_loss": 0.5922093391418457,
|
| 183 |
+
"eval_runtime": 0.5972,
|
| 184 |
+
"eval_samples_per_second": 184.202,
|
| 185 |
+
"eval_steps_per_second": 6.698,
|
| 186 |
+
"step": 75
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 16.0,
|
| 190 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 191 |
+
"loss": 0.6851,
|
| 192 |
+
"step": 80
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 16.0,
|
| 196 |
+
"eval_accuracy": 0.7636363636363637,
|
| 197 |
+
"eval_loss": 0.5955119132995605,
|
| 198 |
+
"eval_runtime": 0.6011,
|
| 199 |
+
"eval_samples_per_second": 182.985,
|
| 200 |
+
"eval_steps_per_second": 6.654,
|
| 201 |
+
"step": 80
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 17.0,
|
| 205 |
+
"eval_accuracy": 0.7545454545454545,
|
| 206 |
+
"eval_loss": 0.573071300983429,
|
| 207 |
+
"eval_runtime": 0.6051,
|
| 208 |
+
"eval_samples_per_second": 181.777,
|
| 209 |
+
"eval_steps_per_second": 6.61,
|
| 210 |
+
"step": 85
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 18.0,
|
| 214 |
+
"learning_rate": 3.055555555555556e-05,
|
| 215 |
+
"loss": 0.6549,
|
| 216 |
+
"step": 90
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 18.0,
|
| 220 |
+
"eval_accuracy": 0.7818181818181819,
|
| 221 |
+
"eval_loss": 0.5602535605430603,
|
| 222 |
+
"eval_runtime": 0.7062,
|
| 223 |
+
"eval_samples_per_second": 155.768,
|
| 224 |
+
"eval_steps_per_second": 5.664,
|
| 225 |
+
"step": 90
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 19.0,
|
| 229 |
+
"eval_accuracy": 0.7818181818181819,
|
| 230 |
+
"eval_loss": 0.5386339426040649,
|
| 231 |
+
"eval_runtime": 0.6221,
|
| 232 |
+
"eval_samples_per_second": 176.809,
|
| 233 |
+
"eval_steps_per_second": 6.429,
|
| 234 |
+
"step": 95
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 20.0,
|
| 238 |
+
"learning_rate": 2.777777777777778e-05,
|
| 239 |
+
"loss": 0.643,
|
| 240 |
+
"step": 100
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 20.0,
|
| 244 |
+
"eval_accuracy": 0.7727272727272727,
|
| 245 |
+
"eval_loss": 0.5423626899719238,
|
| 246 |
+
"eval_runtime": 0.6072,
|
| 247 |
+
"eval_samples_per_second": 181.171,
|
| 248 |
+
"eval_steps_per_second": 6.588,
|
| 249 |
+
"step": 100
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 21.0,
|
| 253 |
+
"eval_accuracy": 0.7909090909090909,
|
| 254 |
+
"eval_loss": 0.5295349955558777,
|
| 255 |
+
"eval_runtime": 0.6772,
|
| 256 |
+
"eval_samples_per_second": 162.427,
|
| 257 |
+
"eval_steps_per_second": 5.906,
|
| 258 |
+
"step": 105
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 22.0,
|
| 262 |
+
"learning_rate": 2.5e-05,
|
| 263 |
+
"loss": 0.5951,
|
| 264 |
+
"step": 110
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 22.0,
|
| 268 |
+
"eval_accuracy": 0.8090909090909091,
|
| 269 |
+
"eval_loss": 0.5203222036361694,
|
| 270 |
+
"eval_runtime": 0.6067,
|
| 271 |
+
"eval_samples_per_second": 181.322,
|
| 272 |
+
"eval_steps_per_second": 6.594,
|
| 273 |
+
"step": 110
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 23.0,
|
| 277 |
+
"eval_accuracy": 0.7909090909090909,
|
| 278 |
+
"eval_loss": 0.516213059425354,
|
| 279 |
+
"eval_runtime": 0.6272,
|
| 280 |
+
"eval_samples_per_second": 175.393,
|
| 281 |
+
"eval_steps_per_second": 6.378,
|
| 282 |
+
"step": 115
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 24.0,
|
| 286 |
+
"learning_rate": 2.2222222222222223e-05,
|
| 287 |
+
"loss": 0.5913,
|
| 288 |
+
"step": 120
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 24.0,
|
| 292 |
+
"eval_accuracy": 0.7818181818181819,
|
| 293 |
+
"eval_loss": 0.5094789862632751,
|
| 294 |
+
"eval_runtime": 0.6677,
|
| 295 |
+
"eval_samples_per_second": 164.747,
|
| 296 |
+
"eval_steps_per_second": 5.991,
|
| 297 |
+
"step": 120
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 25.0,
|
| 301 |
+
"eval_accuracy": 0.7909090909090909,
|
| 302 |
+
"eval_loss": 0.5140318870544434,
|
| 303 |
+
"eval_runtime": 0.6572,
|
| 304 |
+
"eval_samples_per_second": 167.374,
|
| 305 |
+
"eval_steps_per_second": 6.086,
|
| 306 |
+
"step": 125
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 26.0,
|
| 310 |
+
"learning_rate": 1.9444444444444445e-05,
|
| 311 |
+
"loss": 0.5462,
|
| 312 |
+
"step": 130
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 26.0,
|
| 316 |
+
"eval_accuracy": 0.7636363636363637,
|
| 317 |
+
"eval_loss": 0.5167139768600464,
|
| 318 |
+
"eval_runtime": 0.7442,
|
| 319 |
+
"eval_samples_per_second": 147.801,
|
| 320 |
+
"eval_steps_per_second": 5.375,
|
| 321 |
+
"step": 130
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 27.0,
|
| 325 |
+
"eval_accuracy": 0.7909090909090909,
|
| 326 |
+
"eval_loss": 0.49426034092903137,
|
| 327 |
+
"eval_runtime": 0.6102,
|
| 328 |
+
"eval_samples_per_second": 180.278,
|
| 329 |
+
"eval_steps_per_second": 6.556,
|
| 330 |
+
"step": 135
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 28.0,
|
| 334 |
+
"learning_rate": 1.6666666666666667e-05,
|
| 335 |
+
"loss": 0.5538,
|
| 336 |
+
"step": 140
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 28.0,
|
| 340 |
+
"eval_accuracy": 0.7636363636363637,
|
| 341 |
+
"eval_loss": 0.4843919575214386,
|
| 342 |
+
"eval_runtime": 0.7542,
|
| 343 |
+
"eval_samples_per_second": 145.854,
|
| 344 |
+
"eval_steps_per_second": 5.304,
|
| 345 |
+
"step": 140
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 29.0,
|
| 349 |
+
"eval_accuracy": 0.7727272727272727,
|
| 350 |
+
"eval_loss": 0.4821490943431854,
|
| 351 |
+
"eval_runtime": 0.6238,
|
| 352 |
+
"eval_samples_per_second": 176.347,
|
| 353 |
+
"eval_steps_per_second": 6.413,
|
| 354 |
+
"step": 145
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 30.0,
|
| 358 |
+
"learning_rate": 1.388888888888889e-05,
|
| 359 |
+
"loss": 0.5497,
|
| 360 |
+
"step": 150
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 30.0,
|
| 364 |
+
"eval_accuracy": 0.7727272727272727,
|
| 365 |
+
"eval_loss": 0.49517491459846497,
|
| 366 |
+
"eval_runtime": 0.6867,
|
| 367 |
+
"eval_samples_per_second": 160.188,
|
| 368 |
+
"eval_steps_per_second": 5.825,
|
| 369 |
+
"step": 150
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 31.0,
|
| 373 |
+
"eval_accuracy": 0.7818181818181819,
|
| 374 |
+
"eval_loss": 0.499459445476532,
|
| 375 |
+
"eval_runtime": 0.6542,
|
| 376 |
+
"eval_samples_per_second": 168.144,
|
| 377 |
+
"eval_steps_per_second": 6.114,
|
| 378 |
+
"step": 155
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 32.0,
|
| 382 |
+
"learning_rate": 1.1111111111111112e-05,
|
| 383 |
+
"loss": 0.4923,
|
| 384 |
+
"step": 160
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 32.0,
|
| 388 |
+
"eval_accuracy": 0.7727272727272727,
|
| 389 |
+
"eval_loss": 0.4910464286804199,
|
| 390 |
+
"eval_runtime": 0.6079,
|
| 391 |
+
"eval_samples_per_second": 180.941,
|
| 392 |
+
"eval_steps_per_second": 6.58,
|
| 393 |
+
"step": 160
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 33.0,
|
| 397 |
+
"eval_accuracy": 0.7818181818181819,
|
| 398 |
+
"eval_loss": 0.5028622150421143,
|
| 399 |
+
"eval_runtime": 0.6106,
|
| 400 |
+
"eval_samples_per_second": 180.138,
|
| 401 |
+
"eval_steps_per_second": 6.55,
|
| 402 |
+
"step": 165
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 34.0,
|
| 406 |
+
"learning_rate": 8.333333333333334e-06,
|
| 407 |
+
"loss": 0.5228,
|
| 408 |
+
"step": 170
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 34.0,
|
| 412 |
+
"eval_accuracy": 0.7818181818181819,
|
| 413 |
+
"eval_loss": 0.5083434581756592,
|
| 414 |
+
"eval_runtime": 0.6097,
|
| 415 |
+
"eval_samples_per_second": 180.422,
|
| 416 |
+
"eval_steps_per_second": 6.561,
|
| 417 |
+
"step": 170
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 35.0,
|
| 421 |
+
"eval_accuracy": 0.7909090909090909,
|
| 422 |
+
"eval_loss": 0.49842116236686707,
|
| 423 |
+
"eval_runtime": 0.6153,
|
| 424 |
+
"eval_samples_per_second": 178.786,
|
| 425 |
+
"eval_steps_per_second": 6.501,
|
| 426 |
+
"step": 175
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 36.0,
|
| 430 |
+
"learning_rate": 5.555555555555556e-06,
|
| 431 |
+
"loss": 0.4986,
|
| 432 |
+
"step": 180
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 36.0,
|
| 436 |
+
"eval_accuracy": 0.7909090909090909,
|
| 437 |
+
"eval_loss": 0.4914481043815613,
|
| 438 |
+
"eval_runtime": 0.6407,
|
| 439 |
+
"eval_samples_per_second": 171.693,
|
| 440 |
+
"eval_steps_per_second": 6.243,
|
| 441 |
+
"step": 180
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 37.0,
|
| 445 |
+
"eval_accuracy": 0.7909090909090909,
|
| 446 |
+
"eval_loss": 0.4926435649394989,
|
| 447 |
+
"eval_runtime": 0.6131,
|
| 448 |
+
"eval_samples_per_second": 179.402,
|
| 449 |
+
"eval_steps_per_second": 6.524,
|
| 450 |
+
"step": 185
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 38.0,
|
| 454 |
+
"learning_rate": 2.777777777777778e-06,
|
| 455 |
+
"loss": 0.5154,
|
| 456 |
+
"step": 190
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 38.0,
|
| 460 |
+
"eval_accuracy": 0.8,
|
| 461 |
+
"eval_loss": 0.49148377776145935,
|
| 462 |
+
"eval_runtime": 0.6154,
|
| 463 |
+
"eval_samples_per_second": 178.737,
|
| 464 |
+
"eval_steps_per_second": 6.5,
|
| 465 |
+
"step": 190
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 39.0,
|
| 469 |
+
"eval_accuracy": 0.8,
|
| 470 |
+
"eval_loss": 0.4885866641998291,
|
| 471 |
+
"eval_runtime": 0.636,
|
| 472 |
+
"eval_samples_per_second": 172.961,
|
| 473 |
+
"eval_steps_per_second": 6.289,
|
| 474 |
+
"step": 195
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 40.0,
|
| 478 |
+
"learning_rate": 0.0,
|
| 479 |
+
"loss": 0.5081,
|
| 480 |
+
"step": 200
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 40.0,
|
| 484 |
+
"eval_accuracy": 0.8,
|
| 485 |
+
"eval_loss": 0.48748189210891724,
|
| 486 |
+
"eval_runtime": 0.5972,
|
| 487 |
+
"eval_samples_per_second": 184.204,
|
| 488 |
+
"eval_steps_per_second": 6.698,
|
| 489 |
+
"step": 200
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 40.0,
|
| 493 |
+
"step": 200,
|
| 494 |
+
"total_flos": 8.108232849122918e+17,
|
| 495 |
+
"train_loss": 0.750064127445221,
|
| 496 |
+
"train_runtime": 356.9379,
|
| 497 |
+
"train_samples_per_second": 69.816,
|
| 498 |
+
"train_steps_per_second": 0.56
|
| 499 |
+
}
|
| 500 |
+
],
|
| 501 |
+
"logging_steps": 10,
|
| 502 |
+
"max_steps": 200,
|
| 503 |
+
"num_input_tokens_seen": 0,
|
| 504 |
+
"num_train_epochs": 40,
|
| 505 |
+
"save_steps": 500,
|
| 506 |
+
"total_flos": 8.108232849122918e+17,
|
| 507 |
+
"train_batch_size": 32,
|
| 508 |
+
"trial_name": null,
|
| 509 |
+
"trial_params": null
|
| 510 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1da300db61b98a7ddf001c7458ae82ed135715be936217a23a82db8c397b1644
|
| 3 |
+
size 4792
|