End of training
Browse files- README.md +97 -0
- all_results.json +18 -0
- config.json +55 -0
- eval_results.json +13 -0
- model.safetensors +3 -0
- preprocessor_config.json +22 -0
- train_results.json +8 -0
- trainer_state.json +726 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,97 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
license: apache-2.0
|
| 4 |
+
base_model: microsoft/resnet-50
|
| 5 |
+
tags:
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
metrics:
|
| 8 |
+
- precision
|
| 9 |
+
- recall
|
| 10 |
+
- f1
|
| 11 |
+
- accuracy
|
| 12 |
+
model-index:
|
| 13 |
+
- name: resnet-50-finetuned-barkley
|
| 14 |
+
results: []
|
| 15 |
+
---
|
| 16 |
+
|
| 17 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 18 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 19 |
+
|
| 20 |
+
# resnet-50-finetuned-barkley
|
| 21 |
+
|
| 22 |
+
This model is a fine-tuned version of [microsoft/resnet-50](https://huggingface.co/microsoft/resnet-50) on an unknown dataset.
|
| 23 |
+
It achieves the following results on the evaluation set:
|
| 24 |
+
- Loss: 0.9221
|
| 25 |
+
- Precision: 0.8780
|
| 26 |
+
- Recall: 0.8618
|
| 27 |
+
- F1: 0.8574
|
| 28 |
+
- Accuracy: 0.8744
|
| 29 |
+
- Top1 Accuracy: 0.8618
|
| 30 |
+
- Error Rate: 0.1256
|
| 31 |
+
|
| 32 |
+
## Model description
|
| 33 |
+
|
| 34 |
+
More information needed
|
| 35 |
+
|
| 36 |
+
## Intended uses & limitations
|
| 37 |
+
|
| 38 |
+
More information needed
|
| 39 |
+
|
| 40 |
+
## Training and evaluation data
|
| 41 |
+
|
| 42 |
+
More information needed
|
| 43 |
+
|
| 44 |
+
## Training procedure
|
| 45 |
+
|
| 46 |
+
### Training hyperparameters
|
| 47 |
+
|
| 48 |
+
The following hyperparameters were used during training:
|
| 49 |
+
- learning_rate: 0.0002
|
| 50 |
+
- train_batch_size: 32
|
| 51 |
+
- eval_batch_size: 32
|
| 52 |
+
- seed: 42
|
| 53 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 54 |
+
- lr_scheduler_type: cosine
|
| 55 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 56 |
+
- num_epochs: 30
|
| 57 |
+
- mixed_precision_training: Native AMP
|
| 58 |
+
|
| 59 |
+
### Training results
|
| 60 |
+
|
| 61 |
+
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | Top1 Accuracy | Error Rate |
|
| 62 |
+
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|:-------------:|:----------:|
|
| 63 |
+
| 1.6171 | 1.0 | 38 | 1.6195 | 0.0663 | 0.1513 | 0.0664 | 0.1738 | 0.1513 | 0.8262 |
|
| 64 |
+
| 1.6149 | 2.0 | 76 | 1.6160 | 0.2953 | 0.1579 | 0.0802 | 0.1785 | 0.1579 | 0.8215 |
|
| 65 |
+
| 1.6119 | 3.0 | 114 | 1.6112 | 0.0804 | 0.1579 | 0.0834 | 0.1772 | 0.1579 | 0.8228 |
|
| 66 |
+
| 1.6041 | 4.0 | 152 | 1.6015 | 0.4161 | 0.1974 | 0.1461 | 0.2155 | 0.1974 | 0.7845 |
|
| 67 |
+
| 1.5945 | 5.0 | 190 | 1.5895 | 0.4089 | 0.2895 | 0.2428 | 0.3092 | 0.2895 | 0.6908 |
|
| 68 |
+
| 1.5777 | 6.0 | 228 | 1.5710 | 0.5764 | 0.4408 | 0.3944 | 0.4663 | 0.4408 | 0.5337 |
|
| 69 |
+
| 1.561 | 7.0 | 266 | 1.5490 | 0.6013 | 0.4934 | 0.4516 | 0.5173 | 0.5 | 0.4827 |
|
| 70 |
+
| 1.536 | 8.0 | 304 | 1.5222 | 0.6377 | 0.5132 | 0.4711 | 0.5450 | 0.5132 | 0.4550 |
|
| 71 |
+
| 1.5081 | 9.0 | 342 | 1.4912 | 0.7595 | 0.5987 | 0.5869 | 0.6250 | 0.5987 | 0.3750 |
|
| 72 |
+
| 1.4756 | 10.0 | 380 | 1.4566 | 0.7579 | 0.6447 | 0.6293 | 0.6683 | 0.6447 | 0.3317 |
|
| 73 |
+
| 1.4387 | 11.0 | 418 | 1.4156 | 0.7914 | 0.6776 | 0.6692 | 0.6985 | 0.6776 | 0.3015 |
|
| 74 |
+
| 1.3993 | 12.0 | 456 | 1.3737 | 0.7997 | 0.6842 | 0.6732 | 0.7080 | 0.6842 | 0.2920 |
|
| 75 |
+
| 1.358 | 13.0 | 494 | 1.3288 | 0.8290 | 0.7039 | 0.7048 | 0.7232 | 0.7039 | 0.2768 |
|
| 76 |
+
| 1.3139 | 14.0 | 532 | 1.2806 | 0.8277 | 0.7434 | 0.7373 | 0.7592 | 0.75 | 0.2408 |
|
| 77 |
+
| 1.262 | 15.0 | 570 | 1.2345 | 0.8478 | 0.7697 | 0.7664 | 0.7829 | 0.7697 | 0.2171 |
|
| 78 |
+
| 1.2184 | 16.0 | 608 | 1.1887 | 0.8323 | 0.7697 | 0.7654 | 0.7818 | 0.7697 | 0.2182 |
|
| 79 |
+
| 1.1803 | 17.0 | 646 | 1.1408 | 0.8423 | 0.7763 | 0.7735 | 0.7931 | 0.7763 | 0.2069 |
|
| 80 |
+
| 1.1422 | 18.0 | 684 | 1.0966 | 0.8594 | 0.8158 | 0.8100 | 0.8317 | 0.8158 | 0.1683 |
|
| 81 |
+
| 1.1032 | 19.0 | 722 | 1.0587 | 0.8431 | 0.8026 | 0.7969 | 0.8145 | 0.8026 | 0.1855 |
|
| 82 |
+
| 1.058 | 20.0 | 760 | 1.0289 | 0.8610 | 0.8355 | 0.8301 | 0.8487 | 0.8355 | 0.1513 |
|
| 83 |
+
| 1.0252 | 21.0 | 798 | 0.9918 | 0.8576 | 0.8421 | 0.8370 | 0.8534 | 0.8421 | 0.1466 |
|
| 84 |
+
| 1.002 | 22.0 | 836 | 0.9727 | 0.8677 | 0.8487 | 0.8435 | 0.8611 | 0.8487 | 0.1389 |
|
| 85 |
+
| 0.9812 | 23.0 | 874 | 0.9465 | 0.8795 | 0.8553 | 0.8497 | 0.8678 | 0.8553 | 0.1322 |
|
| 86 |
+
| 0.9636 | 24.0 | 912 | 0.9331 | 0.8820 | 0.8553 | 0.8485 | 0.8699 | 0.8553 | 0.1301 |
|
| 87 |
+
| 0.9591 | 25.0 | 950 | 0.9221 | 0.8780 | 0.8618 | 0.8574 | 0.8744 | 0.8618 | 0.1256 |
|
| 88 |
+
| 0.948 | 26.0 | 988 | 0.9158 | 0.8780 | 0.8618 | 0.8574 | 0.8744 | 0.8684 | 0.1256 |
|
| 89 |
+
| 0.9384 | 27.0 | 1026 | 0.9017 | 0.8685 | 0.8487 | 0.8431 | 0.8601 | 0.8487 | 0.1399 |
|
| 90 |
+
|
| 91 |
+
|
| 92 |
+
### Framework versions
|
| 93 |
+
|
| 94 |
+
- Transformers 4.45.2
|
| 95 |
+
- Pytorch 2.5.0+cu121
|
| 96 |
+
- Datasets 3.0.1
|
| 97 |
+
- Tokenizers 0.20.1
|
all_results.json
ADDED
|
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 27.0,
|
| 3 |
+
"eval_accuracy": 0.8743740573152337,
|
| 4 |
+
"eval_error_rate": 0.12562594268476635,
|
| 5 |
+
"eval_f1": 0.8573701550510042,
|
| 6 |
+
"eval_loss": 0.92206209897995,
|
| 7 |
+
"eval_precision": 0.877970723615921,
|
| 8 |
+
"eval_recall": 0.8618421052631579,
|
| 9 |
+
"eval_runtime": 25.6714,
|
| 10 |
+
"eval_samples_per_second": 5.921,
|
| 11 |
+
"eval_steps_per_second": 0.195,
|
| 12 |
+
"eval_top1_accuracy": 0.8618421052631579,
|
| 13 |
+
"total_flos": 6.9738304117683e+17,
|
| 14 |
+
"train_loss": 1.2960130829095375,
|
| 15 |
+
"train_runtime": 5177.2299,
|
| 16 |
+
"train_samples_per_second": 7.046,
|
| 17 |
+
"train_steps_per_second": 0.22
|
| 18 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "microsoft/resnet-50",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"ResNetForImageClassification"
|
| 5 |
+
],
|
| 6 |
+
"depths": [
|
| 7 |
+
3,
|
| 8 |
+
4,
|
| 9 |
+
6,
|
| 10 |
+
3
|
| 11 |
+
],
|
| 12 |
+
"downsample_in_bottleneck": false,
|
| 13 |
+
"downsample_in_first_stage": false,
|
| 14 |
+
"embedding_size": 64,
|
| 15 |
+
"hidden_act": "relu",
|
| 16 |
+
"hidden_sizes": [
|
| 17 |
+
256,
|
| 18 |
+
512,
|
| 19 |
+
1024,
|
| 20 |
+
2048
|
| 21 |
+
],
|
| 22 |
+
"id2label": {
|
| 23 |
+
"0": "Iinstia bijuga",
|
| 24 |
+
"1": "Mangifera indica",
|
| 25 |
+
"2": "Pterocarpus indicus",
|
| 26 |
+
"3": "Roystonea regia",
|
| 27 |
+
"4": "Tabebuia"
|
| 28 |
+
},
|
| 29 |
+
"label2id": {
|
| 30 |
+
"Iinstia bijuga": 0,
|
| 31 |
+
"Mangifera indica": 1,
|
| 32 |
+
"Pterocarpus indicus": 2,
|
| 33 |
+
"Roystonea regia": 3,
|
| 34 |
+
"Tabebuia": 4
|
| 35 |
+
},
|
| 36 |
+
"layer_type": "bottleneck",
|
| 37 |
+
"model_type": "resnet",
|
| 38 |
+
"num_channels": 3,
|
| 39 |
+
"out_features": [
|
| 40 |
+
"stage4"
|
| 41 |
+
],
|
| 42 |
+
"out_indices": [
|
| 43 |
+
4
|
| 44 |
+
],
|
| 45 |
+
"problem_type": "single_label_classification",
|
| 46 |
+
"stage_names": [
|
| 47 |
+
"stem",
|
| 48 |
+
"stage1",
|
| 49 |
+
"stage2",
|
| 50 |
+
"stage3",
|
| 51 |
+
"stage4"
|
| 52 |
+
],
|
| 53 |
+
"torch_dtype": "float32",
|
| 54 |
+
"transformers_version": "4.45.2"
|
| 55 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 27.0,
|
| 3 |
+
"eval_accuracy": 0.8743740573152337,
|
| 4 |
+
"eval_error_rate": 0.12562594268476635,
|
| 5 |
+
"eval_f1": 0.8573701550510042,
|
| 6 |
+
"eval_loss": 0.92206209897995,
|
| 7 |
+
"eval_precision": 0.877970723615921,
|
| 8 |
+
"eval_recall": 0.8618421052631579,
|
| 9 |
+
"eval_runtime": 25.6714,
|
| 10 |
+
"eval_samples_per_second": 5.921,
|
| 11 |
+
"eval_steps_per_second": 0.195,
|
| 12 |
+
"eval_top1_accuracy": 0.8618421052631579
|
| 13 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2c37f9ee1e794f5fcb4a63671450f0c9575850efd363d42801b4a1b34fd4054e
|
| 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 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 27.0,
|
| 3 |
+
"total_flos": 6.9738304117683e+17,
|
| 4 |
+
"train_loss": 1.2960130829095375,
|
| 5 |
+
"train_runtime": 5177.2299,
|
| 6 |
+
"train_samples_per_second": 7.046,
|
| 7 |
+
"train_steps_per_second": 0.22
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,726 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.8743740573152337,
|
| 3 |
+
"best_model_checkpoint": "resnet-50-finetuned-barkley\\checkpoint-950",
|
| 4 |
+
"epoch": 27.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 1026,
|
| 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 |
+
"train_accuracy": 0.16611842105263158
|
| 14 |
+
},
|
| 15 |
+
{
|
| 16 |
+
"epoch": 1.0,
|
| 17 |
+
"grad_norm": 1.3611191511154175,
|
| 18 |
+
"learning_rate": 1.3823166234831842e-06,
|
| 19 |
+
"loss": 1.6171,
|
| 20 |
+
"step": 38
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 1.0,
|
| 24 |
+
"eval_accuracy": 0.17376068376068377,
|
| 25 |
+
"eval_error_rate": 0.8262393162393162,
|
| 26 |
+
"eval_f1": 0.06643250805361339,
|
| 27 |
+
"eval_loss": 1.619532585144043,
|
| 28 |
+
"eval_precision": 0.06626276231021362,
|
| 29 |
+
"eval_recall": 0.1513157894736842,
|
| 30 |
+
"eval_runtime": 26.7886,
|
| 31 |
+
"eval_samples_per_second": 5.674,
|
| 32 |
+
"eval_steps_per_second": 0.187,
|
| 33 |
+
"eval_top1_accuracy": 0.1513157894736842,
|
| 34 |
+
"step": 38
|
| 35 |
+
},
|
| 36 |
+
{
|
| 37 |
+
"epoch": 2.0,
|
| 38 |
+
"train_accuracy": 0.15862573099415206
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 2.0,
|
| 42 |
+
"grad_norm": 1.6634056568145752,
|
| 43 |
+
"learning_rate": 3.058622191852561e-06,
|
| 44 |
+
"loss": 1.6149,
|
| 45 |
+
"step": 76
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 2.0,
|
| 49 |
+
"eval_accuracy": 0.17853192559074912,
|
| 50 |
+
"eval_error_rate": 0.8214680744092508,
|
| 51 |
+
"eval_f1": 0.08020327273951958,
|
| 52 |
+
"eval_loss": 1.6160310506820679,
|
| 53 |
+
"eval_precision": 0.29525518341307816,
|
| 54 |
+
"eval_recall": 0.15789473684210525,
|
| 55 |
+
"eval_runtime": 26.6794,
|
| 56 |
+
"eval_samples_per_second": 5.697,
|
| 57 |
+
"eval_steps_per_second": 0.187,
|
| 58 |
+
"eval_top1_accuracy": 0.15789473684210525,
|
| 59 |
+
"step": 76
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 3.0,
|
| 63 |
+
"train_accuracy": 0.1783625730994152
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 3.0,
|
| 67 |
+
"grad_norm": 1.5223407745361328,
|
| 68 |
+
"learning_rate": 5.625554080420859e-06,
|
| 69 |
+
"loss": 1.6119,
|
| 70 |
+
"step": 114
|
| 71 |
+
},
|
| 72 |
+
{
|
| 73 |
+
"epoch": 3.0,
|
| 74 |
+
"eval_accuracy": 0.1771794871794872,
|
| 75 |
+
"eval_error_rate": 0.8228205128205128,
|
| 76 |
+
"eval_f1": 0.08341165413533834,
|
| 77 |
+
"eval_loss": 1.6111546754837036,
|
| 78 |
+
"eval_precision": 0.08044783010156971,
|
| 79 |
+
"eval_recall": 0.15789473684210525,
|
| 80 |
+
"eval_runtime": 26.2938,
|
| 81 |
+
"eval_samples_per_second": 5.781,
|
| 82 |
+
"eval_steps_per_second": 0.19,
|
| 83 |
+
"eval_top1_accuracy": 0.15789473684210525,
|
| 84 |
+
"step": 114
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 4.0,
|
| 88 |
+
"train_accuracy": 0.20833333333333334
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 4.0,
|
| 92 |
+
"grad_norm": 1.3961833715438843,
|
| 93 |
+
"learning_rate": 8.771702474591739e-06,
|
| 94 |
+
"loss": 1.6041,
|
| 95 |
+
"step": 152
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 4.0,
|
| 99 |
+
"eval_accuracy": 0.21552538964303675,
|
| 100 |
+
"eval_error_rate": 0.7844746103569633,
|
| 101 |
+
"eval_f1": 0.14610577502522265,
|
| 102 |
+
"eval_loss": 1.6015431880950928,
|
| 103 |
+
"eval_precision": 0.4161313363641264,
|
| 104 |
+
"eval_recall": 0.19736842105263158,
|
| 105 |
+
"eval_runtime": 28.8611,
|
| 106 |
+
"eval_samples_per_second": 5.267,
|
| 107 |
+
"eval_steps_per_second": 0.173,
|
| 108 |
+
"eval_top1_accuracy": 0.19736842105263158,
|
| 109 |
+
"step": 152
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 5.0,
|
| 113 |
+
"train_accuracy": 0.24926900584795322
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 5.0,
|
| 117 |
+
"grad_norm": 1.5497902631759644,
|
| 118 |
+
"learning_rate": 1.2115389351475484e-05,
|
| 119 |
+
"loss": 1.5945,
|
| 120 |
+
"step": 190
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 5.0,
|
| 124 |
+
"eval_accuracy": 0.30917043740573147,
|
| 125 |
+
"eval_error_rate": 0.6908295625942685,
|
| 126 |
+
"eval_f1": 0.24280704310495774,
|
| 127 |
+
"eval_loss": 1.5894904136657715,
|
| 128 |
+
"eval_precision": 0.40893317853457173,
|
| 129 |
+
"eval_recall": 0.2894736842105263,
|
| 130 |
+
"eval_runtime": 27.1975,
|
| 131 |
+
"eval_samples_per_second": 5.589,
|
| 132 |
+
"eval_steps_per_second": 0.184,
|
| 133 |
+
"eval_top1_accuracy": 0.2894736842105263,
|
| 134 |
+
"step": 190
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 6.0,
|
| 138 |
+
"train_accuracy": 0.33260233918128657
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 6.0,
|
| 142 |
+
"grad_norm": 1.6292859315872192,
|
| 143 |
+
"learning_rate": 1.5250972116877936e-05,
|
| 144 |
+
"loss": 1.5777,
|
| 145 |
+
"step": 228
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 6.0,
|
| 149 |
+
"eval_accuracy": 0.4663499245852186,
|
| 150 |
+
"eval_error_rate": 0.5336500754147814,
|
| 151 |
+
"eval_f1": 0.39436167836929775,
|
| 152 |
+
"eval_loss": 1.5709806680679321,
|
| 153 |
+
"eval_precision": 0.5764411027568922,
|
| 154 |
+
"eval_recall": 0.4407894736842105,
|
| 155 |
+
"eval_runtime": 26.1121,
|
| 156 |
+
"eval_samples_per_second": 5.821,
|
| 157 |
+
"eval_steps_per_second": 0.191,
|
| 158 |
+
"eval_top1_accuracy": 0.4407894736842105,
|
| 159 |
+
"step": 228
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 7.0,
|
| 163 |
+
"train_accuracy": 0.4093567251461988
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 7.0,
|
| 167 |
+
"grad_norm": 1.4761221408843994,
|
| 168 |
+
"learning_rate": 1.7798054527340503e-05,
|
| 169 |
+
"loss": 1.561,
|
| 170 |
+
"step": 266
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 7.0,
|
| 174 |
+
"eval_accuracy": 0.5173303167420814,
|
| 175 |
+
"eval_error_rate": 0.4826696832579186,
|
| 176 |
+
"eval_f1": 0.45158707610515547,
|
| 177 |
+
"eval_loss": 1.5490015745162964,
|
| 178 |
+
"eval_precision": 0.6013273211996122,
|
| 179 |
+
"eval_recall": 0.4934210526315789,
|
| 180 |
+
"eval_runtime": 27.8381,
|
| 181 |
+
"eval_samples_per_second": 5.46,
|
| 182 |
+
"eval_steps_per_second": 0.18,
|
| 183 |
+
"eval_top1_accuracy": 0.5,
|
| 184 |
+
"step": 266
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 8.0,
|
| 188 |
+
"train_accuracy": 0.47733918128654973
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 8.0,
|
| 192 |
+
"grad_norm": 1.691532850265503,
|
| 193 |
+
"learning_rate": 1.9447634826822778e-05,
|
| 194 |
+
"loss": 1.536,
|
| 195 |
+
"step": 304
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 8.0,
|
| 199 |
+
"eval_accuracy": 0.5450075414781297,
|
| 200 |
+
"eval_error_rate": 0.4549924585218703,
|
| 201 |
+
"eval_f1": 0.4711077818086626,
|
| 202 |
+
"eval_loss": 1.5221654176712036,
|
| 203 |
+
"eval_precision": 0.63772879167616,
|
| 204 |
+
"eval_recall": 0.5131578947368421,
|
| 205 |
+
"eval_runtime": 26.2831,
|
| 206 |
+
"eval_samples_per_second": 5.783,
|
| 207 |
+
"eval_steps_per_second": 0.19,
|
| 208 |
+
"eval_top1_accuracy": 0.5131578947368421,
|
| 209 |
+
"step": 304
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 9.0,
|
| 213 |
+
"train_accuracy": 0.5372807017543859
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 9.0,
|
| 217 |
+
"grad_norm": 1.69563889503479,
|
| 218 |
+
"learning_rate": 1.9999922507143676e-05,
|
| 219 |
+
"loss": 1.5081,
|
| 220 |
+
"step": 342
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 9.0,
|
| 224 |
+
"eval_accuracy": 0.625032679738562,
|
| 225 |
+
"eval_error_rate": 0.374967320261438,
|
| 226 |
+
"eval_f1": 0.5868892868172693,
|
| 227 |
+
"eval_loss": 1.4911595582962036,
|
| 228 |
+
"eval_precision": 0.7594769272604533,
|
| 229 |
+
"eval_recall": 0.5986842105263158,
|
| 230 |
+
"eval_runtime": 27.44,
|
| 231 |
+
"eval_samples_per_second": 5.539,
|
| 232 |
+
"eval_steps_per_second": 0.182,
|
| 233 |
+
"eval_top1_accuracy": 0.5986842105263158,
|
| 234 |
+
"step": 342
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 10.0,
|
| 238 |
+
"train_accuracy": 0.5957602339181286
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 10.0,
|
| 242 |
+
"grad_norm": 1.694950819015503,
|
| 243 |
+
"learning_rate": 1.9882364575351117e-05,
|
| 244 |
+
"loss": 1.4756,
|
| 245 |
+
"step": 380
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 10.0,
|
| 249 |
+
"eval_accuracy": 0.6683459024635495,
|
| 250 |
+
"eval_error_rate": 0.3316540975364505,
|
| 251 |
+
"eval_f1": 0.6293044227869377,
|
| 252 |
+
"eval_loss": 1.4565558433532715,
|
| 253 |
+
"eval_precision": 0.7578870575407971,
|
| 254 |
+
"eval_recall": 0.6447368421052632,
|
| 255 |
+
"eval_runtime": 25.8912,
|
| 256 |
+
"eval_samples_per_second": 5.871,
|
| 257 |
+
"eval_steps_per_second": 0.193,
|
| 258 |
+
"eval_top1_accuracy": 0.6447368421052632,
|
| 259 |
+
"step": 380
|
| 260 |
+
},
|
| 261 |
+
{
|
| 262 |
+
"epoch": 11.0,
|
| 263 |
+
"train_accuracy": 0.6111111111111112
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 11.0,
|
| 267 |
+
"grad_norm": 1.591986894607544,
|
| 268 |
+
"learning_rate": 1.9544051842595e-05,
|
| 269 |
+
"loss": 1.4387,
|
| 270 |
+
"step": 418
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 11.0,
|
| 274 |
+
"eval_accuracy": 0.698541980894922,
|
| 275 |
+
"eval_error_rate": 0.30145801910507797,
|
| 276 |
+
"eval_f1": 0.6692242337767512,
|
| 277 |
+
"eval_loss": 1.4155722856521606,
|
| 278 |
+
"eval_precision": 0.7913987173816895,
|
| 279 |
+
"eval_recall": 0.6776315789473685,
|
| 280 |
+
"eval_runtime": 26.7774,
|
| 281 |
+
"eval_samples_per_second": 5.676,
|
| 282 |
+
"eval_steps_per_second": 0.187,
|
| 283 |
+
"eval_top1_accuracy": 0.6776315789473685,
|
| 284 |
+
"step": 418
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 12.0,
|
| 288 |
+
"train_accuracy": 0.6469298245614035
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 12.0,
|
| 292 |
+
"grad_norm": 1.8263485431671143,
|
| 293 |
+
"learning_rate": 1.9009692640269474e-05,
|
| 294 |
+
"loss": 1.3993,
|
| 295 |
+
"step": 456
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 12.0,
|
| 299 |
+
"eval_accuracy": 0.7080442433383609,
|
| 300 |
+
"eval_error_rate": 0.2919557566616391,
|
| 301 |
+
"eval_f1": 0.6731791852575238,
|
| 302 |
+
"eval_loss": 1.3737214803695679,
|
| 303 |
+
"eval_precision": 0.7997336700204268,
|
| 304 |
+
"eval_recall": 0.6842105263157895,
|
| 305 |
+
"eval_runtime": 25.8778,
|
| 306 |
+
"eval_samples_per_second": 5.874,
|
| 307 |
+
"eval_steps_per_second": 0.193,
|
| 308 |
+
"eval_top1_accuracy": 0.6842105263157895,
|
| 309 |
+
"step": 456
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 13.0,
|
| 313 |
+
"train_accuracy": 0.6527777777777778
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 13.0,
|
| 317 |
+
"grad_norm": 1.8651676177978516,
|
| 318 |
+
"learning_rate": 1.826239469360898e-05,
|
| 319 |
+
"loss": 1.358,
|
| 320 |
+
"step": 494
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 13.0,
|
| 324 |
+
"eval_accuracy": 0.7232277526395173,
|
| 325 |
+
"eval_error_rate": 0.27677224736048267,
|
| 326 |
+
"eval_f1": 0.7048030719072474,
|
| 327 |
+
"eval_loss": 1.3288253545761108,
|
| 328 |
+
"eval_precision": 0.8290264820356354,
|
| 329 |
+
"eval_recall": 0.7039473684210527,
|
| 330 |
+
"eval_runtime": 26.9677,
|
| 331 |
+
"eval_samples_per_second": 5.636,
|
| 332 |
+
"eval_steps_per_second": 0.185,
|
| 333 |
+
"eval_top1_accuracy": 0.7039473684210527,
|
| 334 |
+
"step": 494
|
| 335 |
+
},
|
| 336 |
+
{
|
| 337 |
+
"epoch": 14.0,
|
| 338 |
+
"train_accuracy": 0.7017543859649122
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 14.0,
|
| 342 |
+
"grad_norm": 2.0590460300445557,
|
| 343 |
+
"learning_rate": 1.733052939622339e-05,
|
| 344 |
+
"loss": 1.3139,
|
| 345 |
+
"step": 532
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 14.0,
|
| 349 |
+
"eval_accuracy": 0.7592207139265963,
|
| 350 |
+
"eval_error_rate": 0.2407792860734037,
|
| 351 |
+
"eval_f1": 0.7373063276167947,
|
| 352 |
+
"eval_loss": 1.2805979251861572,
|
| 353 |
+
"eval_precision": 0.8276704808408175,
|
| 354 |
+
"eval_recall": 0.743421052631579,
|
| 355 |
+
"eval_runtime": 24.8464,
|
| 356 |
+
"eval_samples_per_second": 6.118,
|
| 357 |
+
"eval_steps_per_second": 0.201,
|
| 358 |
+
"eval_top1_accuracy": 0.75,
|
| 359 |
+
"step": 532
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 15.0,
|
| 363 |
+
"train_accuracy": 0.7185672514619883
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 15.0,
|
| 367 |
+
"grad_norm": 2.4823436737060547,
|
| 368 |
+
"learning_rate": 1.6234913078995263e-05,
|
| 369 |
+
"loss": 1.262,
|
| 370 |
+
"step": 570
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 15.0,
|
| 374 |
+
"eval_accuracy": 0.7828808446455506,
|
| 375 |
+
"eval_error_rate": 0.21711915535444937,
|
| 376 |
+
"eval_f1": 0.7664102924938837,
|
| 377 |
+
"eval_loss": 1.2344970703125,
|
| 378 |
+
"eval_precision": 0.8477553968860445,
|
| 379 |
+
"eval_recall": 0.7697368421052632,
|
| 380 |
+
"eval_runtime": 26.3117,
|
| 381 |
+
"eval_samples_per_second": 5.777,
|
| 382 |
+
"eval_steps_per_second": 0.19,
|
| 383 |
+
"eval_top1_accuracy": 0.7697368421052632,
|
| 384 |
+
"step": 570
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 16.0,
|
| 388 |
+
"train_accuracy": 0.7236842105263158
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 16.0,
|
| 392 |
+
"grad_norm": 2.0972795486450195,
|
| 393 |
+
"learning_rate": 1.5000020000000002e-05,
|
| 394 |
+
"loss": 1.2184,
|
| 395 |
+
"step": 608
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 16.0,
|
| 399 |
+
"eval_accuracy": 0.7817697335344395,
|
| 400 |
+
"eval_error_rate": 0.21823026646556054,
|
| 401 |
+
"eval_f1": 0.7654284912445182,
|
| 402 |
+
"eval_loss": 1.1887174844741821,
|
| 403 |
+
"eval_precision": 0.8322669418644651,
|
| 404 |
+
"eval_recall": 0.7697368421052632,
|
| 405 |
+
"eval_runtime": 25.3816,
|
| 406 |
+
"eval_samples_per_second": 5.989,
|
| 407 |
+
"eval_steps_per_second": 0.197,
|
| 408 |
+
"eval_top1_accuracy": 0.7697368421052632,
|
| 409 |
+
"step": 608
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 17.0,
|
| 413 |
+
"train_accuracy": 0.7448830409356725
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 17.0,
|
| 417 |
+
"grad_norm": 1.9592589139938354,
|
| 418 |
+
"learning_rate": 1.365343563002298e-05,
|
| 419 |
+
"loss": 1.1803,
|
| 420 |
+
"step": 646
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 17.0,
|
| 424 |
+
"eval_accuracy": 0.7930819507290096,
|
| 425 |
+
"eval_error_rate": 0.20691804927099045,
|
| 426 |
+
"eval_f1": 0.773531629357028,
|
| 427 |
+
"eval_loss": 1.1408498287200928,
|
| 428 |
+
"eval_precision": 0.8423109913821989,
|
| 429 |
+
"eval_recall": 0.7763157894736842,
|
| 430 |
+
"eval_runtime": 26.1892,
|
| 431 |
+
"eval_samples_per_second": 5.804,
|
| 432 |
+
"eval_steps_per_second": 0.191,
|
| 433 |
+
"eval_top1_accuracy": 0.7763157894736842,
|
| 434 |
+
"step": 646
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 18.0,
|
| 438 |
+
"train_accuracy": 0.7580409356725146
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 18.0,
|
| 442 |
+
"grad_norm": 2.348762035369873,
|
| 443 |
+
"learning_rate": 1.2225240438725788e-05,
|
| 444 |
+
"loss": 1.1422,
|
| 445 |
+
"step": 684
|
| 446 |
+
},
|
| 447 |
+
{
|
| 448 |
+
"epoch": 18.0,
|
| 449 |
+
"eval_accuracy": 0.83166918049271,
|
| 450 |
+
"eval_error_rate": 0.16833081950729,
|
| 451 |
+
"eval_f1": 0.810022076785411,
|
| 452 |
+
"eval_loss": 1.096580147743225,
|
| 453 |
+
"eval_precision": 0.8594414607948442,
|
| 454 |
+
"eval_recall": 0.8157894736842105,
|
| 455 |
+
"eval_runtime": 25.0285,
|
| 456 |
+
"eval_samples_per_second": 6.073,
|
| 457 |
+
"eval_steps_per_second": 0.2,
|
| 458 |
+
"eval_top1_accuracy": 0.8157894736842105,
|
| 459 |
+
"step": 684
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 19.0,
|
| 463 |
+
"train_accuracy": 0.7733918128654971
|
| 464 |
+
},
|
| 465 |
+
{
|
| 466 |
+
"epoch": 19.0,
|
| 467 |
+
"grad_norm": 2.2395124435424805,
|
| 468 |
+
"learning_rate": 1.0747337946660503e-05,
|
| 469 |
+
"loss": 1.1032,
|
| 470 |
+
"step": 722
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 19.0,
|
| 474 |
+
"eval_accuracy": 0.8144746103569632,
|
| 475 |
+
"eval_error_rate": 0.18552538964303678,
|
| 476 |
+
"eval_f1": 0.7968691491574786,
|
| 477 |
+
"eval_loss": 1.0586965084075928,
|
| 478 |
+
"eval_precision": 0.8430972766845342,
|
| 479 |
+
"eval_recall": 0.8026315789473685,
|
| 480 |
+
"eval_runtime": 25.4802,
|
| 481 |
+
"eval_samples_per_second": 5.965,
|
| 482 |
+
"eval_steps_per_second": 0.196,
|
| 483 |
+
"eval_top1_accuracy": 0.8026315789473685,
|
| 484 |
+
"step": 722
|
| 485 |
+
},
|
| 486 |
+
{
|
| 487 |
+
"epoch": 20.0,
|
| 488 |
+
"train_accuracy": 0.7850877192982456
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 20.0,
|
| 492 |
+
"grad_norm": 2.3096365928649902,
|
| 493 |
+
"learning_rate": 9.252742053339503e-06,
|
| 494 |
+
"loss": 1.058,
|
| 495 |
+
"step": 760
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 20.0,
|
| 499 |
+
"eval_accuracy": 0.8486626445449975,
|
| 500 |
+
"eval_error_rate": 0.1513373554550025,
|
| 501 |
+
"eval_f1": 0.8300500291649842,
|
| 502 |
+
"eval_loss": 1.0289386510849,
|
| 503 |
+
"eval_precision": 0.8609899749373433,
|
| 504 |
+
"eval_recall": 0.8355263157894737,
|
| 505 |
+
"eval_runtime": 27.6424,
|
| 506 |
+
"eval_samples_per_second": 5.499,
|
| 507 |
+
"eval_steps_per_second": 0.181,
|
| 508 |
+
"eval_top1_accuracy": 0.8355263157894737,
|
| 509 |
+
"step": 760
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 21.0,
|
| 513 |
+
"train_accuracy": 0.8084795321637427
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 21.0,
|
| 517 |
+
"grad_norm": 2.616567611694336,
|
| 518 |
+
"learning_rate": 7.774839561274216e-06,
|
| 519 |
+
"loss": 1.0252,
|
| 520 |
+
"step": 798
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 21.0,
|
| 524 |
+
"eval_accuracy": 0.8534338863750628,
|
| 525 |
+
"eval_error_rate": 0.1465661136249372,
|
| 526 |
+
"eval_f1": 0.8370304500033733,
|
| 527 |
+
"eval_loss": 0.9917795062065125,
|
| 528 |
+
"eval_precision": 0.8575724637681159,
|
| 529 |
+
"eval_recall": 0.8421052631578947,
|
| 530 |
+
"eval_runtime": 24.0656,
|
| 531 |
+
"eval_samples_per_second": 6.316,
|
| 532 |
+
"eval_steps_per_second": 0.208,
|
| 533 |
+
"eval_top1_accuracy": 0.8421052631578947,
|
| 534 |
+
"step": 798
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 22.0,
|
| 538 |
+
"train_accuracy": 0.814327485380117
|
| 539 |
+
},
|
| 540 |
+
{
|
| 541 |
+
"epoch": 22.0,
|
| 542 |
+
"grad_norm": 2.2312376499176025,
|
| 543 |
+
"learning_rate": 6.346644369977025e-06,
|
| 544 |
+
"loss": 1.002,
|
| 545 |
+
"step": 836
|
| 546 |
+
},
|
| 547 |
+
{
|
| 548 |
+
"epoch": 22.0,
|
| 549 |
+
"eval_accuracy": 0.8611261940673707,
|
| 550 |
+
"eval_error_rate": 0.13887380593262932,
|
| 551 |
+
"eval_f1": 0.8435398841932419,
|
| 552 |
+
"eval_loss": 0.9727317690849304,
|
| 553 |
+
"eval_precision": 0.8677232854864433,
|
| 554 |
+
"eval_recall": 0.8486842105263158,
|
| 555 |
+
"eval_runtime": 25.3651,
|
| 556 |
+
"eval_samples_per_second": 5.992,
|
| 557 |
+
"eval_steps_per_second": 0.197,
|
| 558 |
+
"eval_top1_accuracy": 0.8486842105263158,
|
| 559 |
+
"step": 836
|
| 560 |
+
},
|
| 561 |
+
{
|
| 562 |
+
"epoch": 23.0,
|
| 563 |
+
"train_accuracy": 0.8179824561403509
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 23.0,
|
| 567 |
+
"grad_norm": 2.2069149017333984,
|
| 568 |
+
"learning_rate": 5.000060000000003e-06,
|
| 569 |
+
"loss": 0.9812,
|
| 570 |
+
"step": 874
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 23.0,
|
| 574 |
+
"eval_accuracy": 0.8677928607340373,
|
| 575 |
+
"eval_error_rate": 0.13220713926596273,
|
| 576 |
+
"eval_f1": 0.8497099815147097,
|
| 577 |
+
"eval_loss": 0.9464592933654785,
|
| 578 |
+
"eval_precision": 0.8795061782362883,
|
| 579 |
+
"eval_recall": 0.8552631578947368,
|
| 580 |
+
"eval_runtime": 26.8567,
|
| 581 |
+
"eval_samples_per_second": 5.66,
|
| 582 |
+
"eval_steps_per_second": 0.186,
|
| 583 |
+
"eval_top1_accuracy": 0.8552631578947368,
|
| 584 |
+
"step": 874
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 24.0,
|
| 588 |
+
"train_accuracy": 0.8187134502923976
|
| 589 |
+
},
|
| 590 |
+
{
|
| 591 |
+
"epoch": 24.0,
|
| 592 |
+
"grad_norm": 2.32728910446167,
|
| 593 |
+
"learning_rate": 3.76516692100474e-06,
|
| 594 |
+
"loss": 0.9636,
|
| 595 |
+
"step": 912
|
| 596 |
+
},
|
| 597 |
+
{
|
| 598 |
+
"epoch": 24.0,
|
| 599 |
+
"eval_accuracy": 0.8699296128707893,
|
| 600 |
+
"eval_error_rate": 0.1300703871292107,
|
| 601 |
+
"eval_f1": 0.8485082765446309,
|
| 602 |
+
"eval_loss": 0.93310546875,
|
| 603 |
+
"eval_precision": 0.8820191260980734,
|
| 604 |
+
"eval_recall": 0.8552631578947368,
|
| 605 |
+
"eval_runtime": 27.6614,
|
| 606 |
+
"eval_samples_per_second": 5.495,
|
| 607 |
+
"eval_steps_per_second": 0.181,
|
| 608 |
+
"eval_top1_accuracy": 0.8552631578947368,
|
| 609 |
+
"step": 912
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 25.0,
|
| 613 |
+
"train_accuracy": 0.8150584795321637
|
| 614 |
+
},
|
| 615 |
+
{
|
| 616 |
+
"epoch": 25.0,
|
| 617 |
+
"grad_norm": 2.2066571712493896,
|
| 618 |
+
"learning_rate": 2.6963844978948743e-06,
|
| 619 |
+
"loss": 0.9591,
|
| 620 |
+
"step": 950
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 25.0,
|
| 624 |
+
"eval_accuracy": 0.8743740573152337,
|
| 625 |
+
"eval_error_rate": 0.12562594268476635,
|
| 626 |
+
"eval_f1": 0.8573701550510042,
|
| 627 |
+
"eval_loss": 0.92206209897995,
|
| 628 |
+
"eval_precision": 0.877970723615921,
|
| 629 |
+
"eval_recall": 0.8618421052631579,
|
| 630 |
+
"eval_runtime": 26.1743,
|
| 631 |
+
"eval_samples_per_second": 5.807,
|
| 632 |
+
"eval_steps_per_second": 0.191,
|
| 633 |
+
"eval_top1_accuracy": 0.8618421052631579,
|
| 634 |
+
"step": 950
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 26.0,
|
| 638 |
+
"train_accuracy": 0.8194444444444444
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 26.0,
|
| 642 |
+
"grad_norm": 2.345517873764038,
|
| 643 |
+
"learning_rate": 1.75992615737436e-06,
|
| 644 |
+
"loss": 0.948,
|
| 645 |
+
"step": 988
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 26.0,
|
| 649 |
+
"eval_accuracy": 0.8743740573152337,
|
| 650 |
+
"eval_error_rate": 0.12562594268476635,
|
| 651 |
+
"eval_f1": 0.8573701550510042,
|
| 652 |
+
"eval_loss": 0.9158027768135071,
|
| 653 |
+
"eval_precision": 0.877970723615921,
|
| 654 |
+
"eval_recall": 0.8618421052631579,
|
| 655 |
+
"eval_runtime": 26.0018,
|
| 656 |
+
"eval_samples_per_second": 5.846,
|
| 657 |
+
"eval_steps_per_second": 0.192,
|
| 658 |
+
"eval_top1_accuracy": 0.868421052631579,
|
| 659 |
+
"step": 988
|
| 660 |
+
},
|
| 661 |
+
{
|
| 662 |
+
"epoch": 27.0,
|
| 663 |
+
"train_accuracy": 0.8201754385964912
|
| 664 |
+
},
|
| 665 |
+
{
|
| 666 |
+
"epoch": 27.0,
|
| 667 |
+
"grad_norm": 2.246762990951538,
|
| 668 |
+
"learning_rate": 1.0075383437198693e-06,
|
| 669 |
+
"loss": 0.9384,
|
| 670 |
+
"step": 1026
|
| 671 |
+
},
|
| 672 |
+
{
|
| 673 |
+
"epoch": 27.0,
|
| 674 |
+
"eval_accuracy": 0.8601005530417295,
|
| 675 |
+
"eval_error_rate": 0.1398994469582705,
|
| 676 |
+
"eval_f1": 0.8431034082329946,
|
| 677 |
+
"eval_loss": 0.901735782623291,
|
| 678 |
+
"eval_precision": 0.8684637995623307,
|
| 679 |
+
"eval_recall": 0.8486842105263158,
|
| 680 |
+
"eval_runtime": 25.9225,
|
| 681 |
+
"eval_samples_per_second": 5.864,
|
| 682 |
+
"eval_steps_per_second": 0.193,
|
| 683 |
+
"eval_top1_accuracy": 0.8486842105263158,
|
| 684 |
+
"step": 1026
|
| 685 |
+
},
|
| 686 |
+
{
|
| 687 |
+
"epoch": 27.0,
|
| 688 |
+
"step": 1026,
|
| 689 |
+
"total_flos": 6.9738304117683e+17,
|
| 690 |
+
"train_loss": 1.2960130829095375,
|
| 691 |
+
"train_runtime": 5177.2299,
|
| 692 |
+
"train_samples_per_second": 7.046,
|
| 693 |
+
"train_steps_per_second": 0.22
|
| 694 |
+
}
|
| 695 |
+
],
|
| 696 |
+
"logging_steps": 500,
|
| 697 |
+
"max_steps": 1140,
|
| 698 |
+
"num_input_tokens_seen": 0,
|
| 699 |
+
"num_train_epochs": 30,
|
| 700 |
+
"save_steps": 500,
|
| 701 |
+
"stateful_callbacks": {
|
| 702 |
+
"EarlyStoppingCallback": {
|
| 703 |
+
"args": {
|
| 704 |
+
"early_stopping_patience": 2,
|
| 705 |
+
"early_stopping_threshold": 0.0
|
| 706 |
+
},
|
| 707 |
+
"attributes": {
|
| 708 |
+
"early_stopping_patience_counter": 2
|
| 709 |
+
}
|
| 710 |
+
},
|
| 711 |
+
"TrainerControl": {
|
| 712 |
+
"args": {
|
| 713 |
+
"should_epoch_stop": false,
|
| 714 |
+
"should_evaluate": false,
|
| 715 |
+
"should_log": false,
|
| 716 |
+
"should_save": true,
|
| 717 |
+
"should_training_stop": true
|
| 718 |
+
},
|
| 719 |
+
"attributes": {}
|
| 720 |
+
}
|
| 721 |
+
},
|
| 722 |
+
"total_flos": 6.9738304117683e+17,
|
| 723 |
+
"train_batch_size": 32,
|
| 724 |
+
"trial_name": null,
|
| 725 |
+
"trial_params": null
|
| 726 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1260b76ac737c5c8e660b9ecd23bc303fdc0340adc4e3b91ce34f96f50eca543
|
| 3 |
+
size 5176
|