End of training
Browse files- README.md +82 -0
- all_results.json +18 -0
- config.json +57 -0
- eval_results.json +13 -0
- model.safetensors +3 -0
- preprocessor_config.json +22 -0
- train_results.json +8 -0
- trainer_state.json +301 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,82 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
license: apache-2.0
|
| 4 |
+
base_model: facebook/convnextv2-tiny-1k-224
|
| 5 |
+
tags:
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
metrics:
|
| 8 |
+
- precision
|
| 9 |
+
- recall
|
| 10 |
+
- f1
|
| 11 |
+
- accuracy
|
| 12 |
+
model-index:
|
| 13 |
+
- name: convnextv2-tiny-1k-224-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 |
+
# convnextv2-tiny-1k-224-finetuned-barkley
|
| 21 |
+
|
| 22 |
+
This model is a fine-tuned version of [facebook/convnextv2-tiny-1k-224](https://huggingface.co/facebook/convnextv2-tiny-1k-224) on an unknown dataset.
|
| 23 |
+
It achieves the following results on the evaluation set:
|
| 24 |
+
- Loss: 0.0083
|
| 25 |
+
- Precision: 1.0
|
| 26 |
+
- Recall: 1.0
|
| 27 |
+
- F1: 1.0
|
| 28 |
+
- Accuracy: 1.0
|
| 29 |
+
- Top1 Accuracy: 1.0
|
| 30 |
+
- Error Rate: 0.0
|
| 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: 5e-05
|
| 50 |
+
- train_batch_size: 8
|
| 51 |
+
- eval_batch_size: 8
|
| 52 |
+
- seed: 42
|
| 53 |
+
- gradient_accumulation_steps: 4
|
| 54 |
+
- total_train_batch_size: 32
|
| 55 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 56 |
+
- lr_scheduler_type: linear
|
| 57 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 58 |
+
- num_epochs: 30
|
| 59 |
+
- mixed_precision_training: Native AMP
|
| 60 |
+
|
| 61 |
+
### Training results
|
| 62 |
+
|
| 63 |
+
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | Top1 Accuracy | Error Rate |
|
| 64 |
+
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|:-------------:|:----------:|
|
| 65 |
+
| 1.4696 | 1.0 | 38 | 1.1807 | 0.7273 | 0.6513 | 0.6180 | 0.6768 | 0.6513 | 0.3232 |
|
| 66 |
+
| 0.7197 | 2.0 | 76 | 0.3719 | 0.9439 | 0.9408 | 0.9404 | 0.9434 | 0.9474 | 0.0566 |
|
| 67 |
+
| 0.2388 | 3.0 | 114 | 0.1489 | 0.9688 | 0.9671 | 0.9671 | 0.9716 | 0.9671 | 0.0284 |
|
| 68 |
+
| 0.1048 | 4.0 | 152 | 0.0730 | 0.9868 | 0.9868 | 0.9868 | 0.9878 | 0.9868 | 0.0122 |
|
| 69 |
+
| 0.1103 | 5.0 | 190 | 0.0288 | 0.9868 | 0.9868 | 0.9868 | 0.9878 | 0.9868 | 0.0122 |
|
| 70 |
+
| 0.072 | 6.0 | 228 | 0.0537 | 0.9877 | 0.9868 | 0.9869 | 0.9868 | 0.9868 | 0.0132 |
|
| 71 |
+
| 0.0248 | 7.0 | 266 | 0.0083 | 1.0 | 1.0 | 1.0 | 1.0 | 1.0 | 0.0 |
|
| 72 |
+
| 0.0371 | 8.0 | 304 | 0.0653 | 0.9819 | 0.9803 | 0.9802 | 0.9800 | 0.9803 | 0.0200 |
|
| 73 |
+
| 0.0626 | 9.0 | 342 | 0.2271 | 0.9545 | 0.9408 | 0.9404 | 0.95 | 0.9408 | 0.0500 |
|
| 74 |
+
| 0.07 | 10.0 | 380 | 0.0304 | 0.9936 | 0.9934 | 0.9934 | 0.9933 | 0.9934 | 0.0067 |
|
| 75 |
+
|
| 76 |
+
|
| 77 |
+
### Framework versions
|
| 78 |
+
|
| 79 |
+
- Transformers 4.44.2
|
| 80 |
+
- Pytorch 2.3.1+cu121
|
| 81 |
+
- Datasets 3.0.1
|
| 82 |
+
- Tokenizers 0.19.1
|
all_results.json
ADDED
|
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"eval_accuracy": 1.0,
|
| 4 |
+
"eval_error_rate": 0.0,
|
| 5 |
+
"eval_f1": 1.0,
|
| 6 |
+
"eval_loss": 0.008335741236805916,
|
| 7 |
+
"eval_precision": 1.0,
|
| 8 |
+
"eval_recall": 1.0,
|
| 9 |
+
"eval_runtime": 50.6937,
|
| 10 |
+
"eval_samples_per_second": 2.998,
|
| 11 |
+
"eval_steps_per_second": 0.375,
|
| 12 |
+
"eval_top1_accuracy": 1.0,
|
| 13 |
+
"total_flos": 3.060866577059021e+17,
|
| 14 |
+
"train_loss": 0.2909727611039814,
|
| 15 |
+
"train_runtime": 5060.0554,
|
| 16 |
+
"train_samples_per_second": 7.209,
|
| 17 |
+
"train_steps_per_second": 0.225
|
| 18 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "facebook/convnextv2-tiny-1k-224",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"ConvNextV2ForImageClassification"
|
| 5 |
+
],
|
| 6 |
+
"depths": [
|
| 7 |
+
3,
|
| 8 |
+
3,
|
| 9 |
+
9,
|
| 10 |
+
3
|
| 11 |
+
],
|
| 12 |
+
"drop_path_rate": 0.0,
|
| 13 |
+
"hidden_act": "gelu",
|
| 14 |
+
"hidden_sizes": [
|
| 15 |
+
96,
|
| 16 |
+
192,
|
| 17 |
+
384,
|
| 18 |
+
768
|
| 19 |
+
],
|
| 20 |
+
"id2label": {
|
| 21 |
+
"0": "Iinstia bijuga",
|
| 22 |
+
"1": "Mangifera indica",
|
| 23 |
+
"2": "Pterocarpus indicus",
|
| 24 |
+
"3": "Roystonea regia",
|
| 25 |
+
"4": "Tabebuia"
|
| 26 |
+
},
|
| 27 |
+
"image_size": 224,
|
| 28 |
+
"initializer_range": 0.02,
|
| 29 |
+
"label2id": {
|
| 30 |
+
"Iinstia bijuga": 0,
|
| 31 |
+
"Mangifera indica": 1,
|
| 32 |
+
"Pterocarpus indicus": 2,
|
| 33 |
+
"Roystonea regia": 3,
|
| 34 |
+
"Tabebuia": 4
|
| 35 |
+
},
|
| 36 |
+
"layer_norm_eps": 1e-12,
|
| 37 |
+
"model_type": "convnextv2",
|
| 38 |
+
"num_channels": 3,
|
| 39 |
+
"num_stages": 4,
|
| 40 |
+
"out_features": [
|
| 41 |
+
"stage4"
|
| 42 |
+
],
|
| 43 |
+
"out_indices": [
|
| 44 |
+
4
|
| 45 |
+
],
|
| 46 |
+
"patch_size": 4,
|
| 47 |
+
"problem_type": "single_label_classification",
|
| 48 |
+
"stage_names": [
|
| 49 |
+
"stem",
|
| 50 |
+
"stage1",
|
| 51 |
+
"stage2",
|
| 52 |
+
"stage3",
|
| 53 |
+
"stage4"
|
| 54 |
+
],
|
| 55 |
+
"torch_dtype": "float32",
|
| 56 |
+
"transformers_version": "4.44.2"
|
| 57 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"eval_accuracy": 1.0,
|
| 4 |
+
"eval_error_rate": 0.0,
|
| 5 |
+
"eval_f1": 1.0,
|
| 6 |
+
"eval_loss": 0.008335741236805916,
|
| 7 |
+
"eval_precision": 1.0,
|
| 8 |
+
"eval_recall": 1.0,
|
| 9 |
+
"eval_runtime": 50.6937,
|
| 10 |
+
"eval_samples_per_second": 2.998,
|
| 11 |
+
"eval_steps_per_second": 0.375,
|
| 12 |
+
"eval_top1_accuracy": 1.0
|
| 13 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e3a76b0e1711782aec90d90a1907cbd4c4c5b284eb64932b6f3e6635104548b7
|
| 3 |
+
size 111505052
|
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": 10.0,
|
| 3 |
+
"total_flos": 3.060866577059021e+17,
|
| 4 |
+
"train_loss": 0.2909727611039814,
|
| 5 |
+
"train_runtime": 5060.0554,
|
| 6 |
+
"train_samples_per_second": 7.209,
|
| 7 |
+
"train_steps_per_second": 0.225
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,301 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.008335741236805916,
|
| 3 |
+
"best_model_checkpoint": "convnextv2-tiny-1k-224-finetuned-barkley\\checkpoint-266",
|
| 4 |
+
"epoch": 10.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 380,
|
| 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": 0.3717105263157895
|
| 14 |
+
},
|
| 15 |
+
{
|
| 16 |
+
"epoch": 1.0,
|
| 17 |
+
"grad_norm": Infinity,
|
| 18 |
+
"learning_rate": 1.5789473684210526e-05,
|
| 19 |
+
"loss": 1.4696,
|
| 20 |
+
"step": 38
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 1.0,
|
| 24 |
+
"eval_accuracy": 0.6768426344896932,
|
| 25 |
+
"eval_error_rate": 0.3231573655103068,
|
| 26 |
+
"eval_f1": 0.6179742198967869,
|
| 27 |
+
"eval_loss": 1.1806769371032715,
|
| 28 |
+
"eval_precision": 0.7272665779298716,
|
| 29 |
+
"eval_recall": 0.6513157894736842,
|
| 30 |
+
"eval_runtime": 39.4866,
|
| 31 |
+
"eval_samples_per_second": 3.849,
|
| 32 |
+
"eval_steps_per_second": 0.481,
|
| 33 |
+
"eval_top1_accuracy": 0.6513157894736842,
|
| 34 |
+
"step": 38
|
| 35 |
+
},
|
| 36 |
+
{
|
| 37 |
+
"epoch": 2.0,
|
| 38 |
+
"train_accuracy": 0.8472222222222222
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 2.0,
|
| 42 |
+
"grad_norm": 13.038293838500977,
|
| 43 |
+
"learning_rate": 3.24561403508772e-05,
|
| 44 |
+
"loss": 0.7197,
|
| 45 |
+
"step": 76
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 2.0,
|
| 49 |
+
"eval_accuracy": 0.9434188034188035,
|
| 50 |
+
"eval_error_rate": 0.056581196581196536,
|
| 51 |
+
"eval_f1": 0.9403973173646983,
|
| 52 |
+
"eval_loss": 0.3719189167022705,
|
| 53 |
+
"eval_precision": 0.9439213320792268,
|
| 54 |
+
"eval_recall": 0.9407894736842105,
|
| 55 |
+
"eval_runtime": 25.8579,
|
| 56 |
+
"eval_samples_per_second": 5.878,
|
| 57 |
+
"eval_steps_per_second": 0.735,
|
| 58 |
+
"eval_top1_accuracy": 0.9473684210526315,
|
| 59 |
+
"step": 76
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 3.0,
|
| 63 |
+
"train_accuracy": 0.9429824561403509
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 3.0,
|
| 67 |
+
"grad_norm": 18.88597297668457,
|
| 68 |
+
"learning_rate": 4.868421052631579e-05,
|
| 69 |
+
"loss": 0.2388,
|
| 70 |
+
"step": 114
|
| 71 |
+
},
|
| 72 |
+
{
|
| 73 |
+
"epoch": 3.0,
|
| 74 |
+
"eval_accuracy": 0.9715686274509803,
|
| 75 |
+
"eval_error_rate": 0.02843137254901973,
|
| 76 |
+
"eval_f1": 0.9670619516200449,
|
| 77 |
+
"eval_loss": 0.14889617264270782,
|
| 78 |
+
"eval_precision": 0.9687561893444246,
|
| 79 |
+
"eval_recall": 0.9671052631578947,
|
| 80 |
+
"eval_runtime": 56.7711,
|
| 81 |
+
"eval_samples_per_second": 2.677,
|
| 82 |
+
"eval_steps_per_second": 0.335,
|
| 83 |
+
"eval_top1_accuracy": 0.9671052631578947,
|
| 84 |
+
"step": 114
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 4.0,
|
| 88 |
+
"train_accuracy": 0.9758771929824561
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 4.0,
|
| 92 |
+
"grad_norm": 20.039169311523438,
|
| 93 |
+
"learning_rate": 4.834307992202729e-05,
|
| 94 |
+
"loss": 0.1048,
|
| 95 |
+
"step": 152
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 4.0,
|
| 99 |
+
"eval_accuracy": 0.9877777777777779,
|
| 100 |
+
"eval_error_rate": 0.012222222222222134,
|
| 101 |
+
"eval_f1": 0.9868421052631579,
|
| 102 |
+
"eval_loss": 0.07301948219537735,
|
| 103 |
+
"eval_precision": 0.9868421052631579,
|
| 104 |
+
"eval_recall": 0.9868421052631579,
|
| 105 |
+
"eval_runtime": 57.9769,
|
| 106 |
+
"eval_samples_per_second": 2.622,
|
| 107 |
+
"eval_steps_per_second": 0.328,
|
| 108 |
+
"eval_top1_accuracy": 0.9868421052631579,
|
| 109 |
+
"step": 152
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 5.0,
|
| 113 |
+
"train_accuracy": 0.9685672514619883
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 5.0,
|
| 117 |
+
"grad_norm": 32.21807098388672,
|
| 118 |
+
"learning_rate": 4.6539961013645225e-05,
|
| 119 |
+
"loss": 0.1103,
|
| 120 |
+
"step": 190
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 5.0,
|
| 124 |
+
"eval_accuracy": 0.9877777777777779,
|
| 125 |
+
"eval_error_rate": 0.012222222222222134,
|
| 126 |
+
"eval_f1": 0.9868421052631579,
|
| 127 |
+
"eval_loss": 0.028847167268395424,
|
| 128 |
+
"eval_precision": 0.9868421052631579,
|
| 129 |
+
"eval_recall": 0.9868421052631579,
|
| 130 |
+
"eval_runtime": 55.6388,
|
| 131 |
+
"eval_samples_per_second": 2.732,
|
| 132 |
+
"eval_steps_per_second": 0.341,
|
| 133 |
+
"eval_top1_accuracy": 0.9868421052631579,
|
| 134 |
+
"step": 190
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 6.0,
|
| 138 |
+
"train_accuracy": 0.9824561403508771
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 6.0,
|
| 142 |
+
"grad_norm": 0.3600322902202606,
|
| 143 |
+
"learning_rate": 4.468810916179337e-05,
|
| 144 |
+
"loss": 0.072,
|
| 145 |
+
"step": 228
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 6.0,
|
| 149 |
+
"eval_accuracy": 0.9867521367521368,
|
| 150 |
+
"eval_error_rate": 0.0132478632478632,
|
| 151 |
+
"eval_f1": 0.986943499272542,
|
| 152 |
+
"eval_loss": 0.053720876574516296,
|
| 153 |
+
"eval_precision": 0.9876644736842105,
|
| 154 |
+
"eval_recall": 0.9868421052631579,
|
| 155 |
+
"eval_runtime": 58.3931,
|
| 156 |
+
"eval_samples_per_second": 2.603,
|
| 157 |
+
"eval_steps_per_second": 0.325,
|
| 158 |
+
"eval_top1_accuracy": 0.9868421052631579,
|
| 159 |
+
"step": 228
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 7.0,
|
| 163 |
+
"train_accuracy": 0.9919590643274854
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 7.0,
|
| 167 |
+
"grad_norm": 0.21095441281795502,
|
| 168 |
+
"learning_rate": 4.283625730994152e-05,
|
| 169 |
+
"loss": 0.0248,
|
| 170 |
+
"step": 266
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 7.0,
|
| 174 |
+
"eval_accuracy": 1.0,
|
| 175 |
+
"eval_error_rate": 0.0,
|
| 176 |
+
"eval_f1": 1.0,
|
| 177 |
+
"eval_loss": 0.008335741236805916,
|
| 178 |
+
"eval_precision": 1.0,
|
| 179 |
+
"eval_recall": 1.0,
|
| 180 |
+
"eval_runtime": 60.881,
|
| 181 |
+
"eval_samples_per_second": 2.497,
|
| 182 |
+
"eval_steps_per_second": 0.312,
|
| 183 |
+
"eval_top1_accuracy": 1.0,
|
| 184 |
+
"step": 266
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 8.0,
|
| 188 |
+
"train_accuracy": 0.9904970760233918
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 8.0,
|
| 192 |
+
"grad_norm": 65.39556121826172,
|
| 193 |
+
"learning_rate": 4.098440545808967e-05,
|
| 194 |
+
"loss": 0.0371,
|
| 195 |
+
"step": 304
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 8.0,
|
| 199 |
+
"eval_accuracy": 0.9800000000000001,
|
| 200 |
+
"eval_error_rate": 0.019999999999999907,
|
| 201 |
+
"eval_f1": 0.9801607428504544,
|
| 202 |
+
"eval_loss": 0.06527390331029892,
|
| 203 |
+
"eval_precision": 0.9818634423897581,
|
| 204 |
+
"eval_recall": 0.9802631578947368,
|
| 205 |
+
"eval_runtime": 54.5902,
|
| 206 |
+
"eval_samples_per_second": 2.784,
|
| 207 |
+
"eval_steps_per_second": 0.348,
|
| 208 |
+
"eval_top1_accuracy": 0.9802631578947368,
|
| 209 |
+
"step": 304
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 9.0,
|
| 213 |
+
"train_accuracy": 0.9846491228070176
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 9.0,
|
| 217 |
+
"grad_norm": 38.53361511230469,
|
| 218 |
+
"learning_rate": 3.9181286549707604e-05,
|
| 219 |
+
"loss": 0.0626,
|
| 220 |
+
"step": 342
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 9.0,
|
| 224 |
+
"eval_accuracy": 0.95,
|
| 225 |
+
"eval_error_rate": 0.050000000000000044,
|
| 226 |
+
"eval_f1": 0.9404217064400131,
|
| 227 |
+
"eval_loss": 0.22711969912052155,
|
| 228 |
+
"eval_precision": 0.9544534412955467,
|
| 229 |
+
"eval_recall": 0.9407894736842105,
|
| 230 |
+
"eval_runtime": 51.6016,
|
| 231 |
+
"eval_samples_per_second": 2.946,
|
| 232 |
+
"eval_steps_per_second": 0.368,
|
| 233 |
+
"eval_top1_accuracy": 0.9407894736842105,
|
| 234 |
+
"step": 342
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 10.0,
|
| 238 |
+
"train_accuracy": 0.9766081871345029
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 10.0,
|
| 242 |
+
"grad_norm": 0.2995816767215729,
|
| 243 |
+
"learning_rate": 3.7329434697855756e-05,
|
| 244 |
+
"loss": 0.07,
|
| 245 |
+
"step": 380
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 10.0,
|
| 249 |
+
"eval_accuracy": 0.9933333333333334,
|
| 250 |
+
"eval_error_rate": 0.006666666666666599,
|
| 251 |
+
"eval_f1": 0.9934103601236665,
|
| 252 |
+
"eval_loss": 0.030387282371520996,
|
| 253 |
+
"eval_precision": 0.9935988620199147,
|
| 254 |
+
"eval_recall": 0.993421052631579,
|
| 255 |
+
"eval_runtime": 52.2379,
|
| 256 |
+
"eval_samples_per_second": 2.91,
|
| 257 |
+
"eval_steps_per_second": 0.364,
|
| 258 |
+
"eval_top1_accuracy": 0.993421052631579,
|
| 259 |
+
"step": 380
|
| 260 |
+
},
|
| 261 |
+
{
|
| 262 |
+
"epoch": 10.0,
|
| 263 |
+
"step": 380,
|
| 264 |
+
"total_flos": 3.060866577059021e+17,
|
| 265 |
+
"train_loss": 0.2909727611039814,
|
| 266 |
+
"train_runtime": 5060.0554,
|
| 267 |
+
"train_samples_per_second": 7.209,
|
| 268 |
+
"train_steps_per_second": 0.225
|
| 269 |
+
}
|
| 270 |
+
],
|
| 271 |
+
"logging_steps": 10,
|
| 272 |
+
"max_steps": 1140,
|
| 273 |
+
"num_input_tokens_seen": 0,
|
| 274 |
+
"num_train_epochs": 30,
|
| 275 |
+
"save_steps": 500,
|
| 276 |
+
"stateful_callbacks": {
|
| 277 |
+
"EarlyStoppingCallback": {
|
| 278 |
+
"args": {
|
| 279 |
+
"early_stopping_patience": 3,
|
| 280 |
+
"early_stopping_threshold": 0.0
|
| 281 |
+
},
|
| 282 |
+
"attributes": {
|
| 283 |
+
"early_stopping_patience_counter": 0
|
| 284 |
+
}
|
| 285 |
+
},
|
| 286 |
+
"TrainerControl": {
|
| 287 |
+
"args": {
|
| 288 |
+
"should_epoch_stop": false,
|
| 289 |
+
"should_evaluate": false,
|
| 290 |
+
"should_log": false,
|
| 291 |
+
"should_save": true,
|
| 292 |
+
"should_training_stop": true
|
| 293 |
+
},
|
| 294 |
+
"attributes": {}
|
| 295 |
+
}
|
| 296 |
+
},
|
| 297 |
+
"total_flos": 3.060866577059021e+17,
|
| 298 |
+
"train_batch_size": 8,
|
| 299 |
+
"trial_name": null,
|
| 300 |
+
"trial_params": null
|
| 301 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:de756896046cbfdebae44572e838af135f99c09e1d5933136547d9ed49aea476
|
| 3 |
+
size 5176
|