Commit
•
9a1e2b3
1
Parent(s):
6b2ca73
End of training
Browse files- README.md +87 -0
- all_results.json +13 -0
- config.json +53 -0
- eval_results.json +8 -0
- model.safetensors +3 -0
- preprocessor_config.json +22 -0
- runs/Nov23_15-21-40_435ad433beae/events.out.tfevents.1700752973.435ad433beae.439.0 +3 -0
- runs/Nov23_15-21-40_435ad433beae/events.out.tfevents.1700753936.435ad433beae.439.1 +3 -0
- train_results.json +8 -0
- trainer_state.json +502 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,87 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: facebook/convnextv2-tiny-1k-224
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
datasets:
|
| 7 |
+
- beans
|
| 8 |
+
metrics:
|
| 9 |
+
- accuracy
|
| 10 |
+
model-index:
|
| 11 |
+
- name: convnextv2-tiny-1k-224-finetuned-beans
|
| 12 |
+
results:
|
| 13 |
+
- task:
|
| 14 |
+
name: Image Classification
|
| 15 |
+
type: image-classification
|
| 16 |
+
dataset:
|
| 17 |
+
name: beans
|
| 18 |
+
type: beans
|
| 19 |
+
config: default
|
| 20 |
+
split: validation
|
| 21 |
+
args: default
|
| 22 |
+
metrics:
|
| 23 |
+
- name: Accuracy
|
| 24 |
+
type: accuracy
|
| 25 |
+
value: 0.8120300751879699
|
| 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 |
+
# convnextv2-tiny-1k-224-finetuned-beans
|
| 32 |
+
|
| 33 |
+
This model is a fine-tuned version of [facebook/convnextv2-tiny-1k-224](https://huggingface.co/facebook/convnextv2-tiny-1k-224) on the beans dataset.
|
| 34 |
+
It achieves the following results on the evaluation set:
|
| 35 |
+
- Loss: 0.5389
|
| 36 |
+
- Accuracy: 0.8120
|
| 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: 4
|
| 57 |
+
- eval_batch_size: 4
|
| 58 |
+
- seed: 42
|
| 59 |
+
- gradient_accumulation_steps: 4
|
| 60 |
+
- total_train_batch_size: 16
|
| 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: 10
|
| 65 |
+
|
| 66 |
+
### Training results
|
| 67 |
+
|
| 68 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 69 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 70 |
+
| 0.2179 | 0.99 | 64 | 0.5407 | 0.7293 |
|
| 71 |
+
| 0.1033 | 1.99 | 129 | 0.6816 | 0.7068 |
|
| 72 |
+
| 0.0425 | 3.0 | 194 | 0.5600 | 0.7820 |
|
| 73 |
+
| 0.0017 | 4.0 | 259 | 0.6064 | 0.7444 |
|
| 74 |
+
| 0.0035 | 4.99 | 323 | 0.6192 | 0.7895 |
|
| 75 |
+
| 0.0005 | 5.99 | 388 | 0.5389 | 0.8120 |
|
| 76 |
+
| 0.0003 | 7.0 | 453 | 0.6144 | 0.7895 |
|
| 77 |
+
| 0.0002 | 8.0 | 518 | 0.6294 | 0.7895 |
|
| 78 |
+
| 0.0002 | 8.99 | 582 | 0.6324 | 0.7895 |
|
| 79 |
+
| 0.0002 | 9.88 | 640 | 0.6339 | 0.7895 |
|
| 80 |
+
|
| 81 |
+
|
| 82 |
+
### Framework versions
|
| 83 |
+
|
| 84 |
+
- Transformers 4.35.2
|
| 85 |
+
- Pytorch 2.1.0+cu118
|
| 86 |
+
- Datasets 2.15.0
|
| 87 |
+
- Tokenizers 0.15.0
|
all_results.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 9.88,
|
| 3 |
+
"eval_accuracy": 0.8120300751879699,
|
| 4 |
+
"eval_loss": 0.538909375667572,
|
| 5 |
+
"eval_runtime": 1.7053,
|
| 6 |
+
"eval_samples_per_second": 77.99,
|
| 7 |
+
"eval_steps_per_second": 19.937,
|
| 8 |
+
"total_flos": 1.2819370691970002e+18,
|
| 9 |
+
"train_loss": 0.08128333170207043,
|
| 10 |
+
"train_runtime": 961.2553,
|
| 11 |
+
"train_samples_per_second": 10.757,
|
| 12 |
+
"train_steps_per_second": 0.666
|
| 13 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,53 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": "angular_leaf_spot",
|
| 22 |
+
"1": "bean_rust",
|
| 23 |
+
"2": "healthy"
|
| 24 |
+
},
|
| 25 |
+
"image_size": 224,
|
| 26 |
+
"initializer_range": 0.02,
|
| 27 |
+
"label2id": {
|
| 28 |
+
"angular_leaf_spot": 0,
|
| 29 |
+
"bean_rust": 1,
|
| 30 |
+
"healthy": 2
|
| 31 |
+
},
|
| 32 |
+
"layer_norm_eps": 1e-12,
|
| 33 |
+
"model_type": "convnextv2",
|
| 34 |
+
"num_channels": 3,
|
| 35 |
+
"num_stages": 4,
|
| 36 |
+
"out_features": [
|
| 37 |
+
"stage4"
|
| 38 |
+
],
|
| 39 |
+
"out_indices": [
|
| 40 |
+
4
|
| 41 |
+
],
|
| 42 |
+
"patch_size": 4,
|
| 43 |
+
"problem_type": "single_label_classification",
|
| 44 |
+
"stage_names": [
|
| 45 |
+
"stem",
|
| 46 |
+
"stage1",
|
| 47 |
+
"stage2",
|
| 48 |
+
"stage3",
|
| 49 |
+
"stage4"
|
| 50 |
+
],
|
| 51 |
+
"torch_dtype": "float32",
|
| 52 |
+
"transformers_version": "4.35.2"
|
| 53 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 9.88,
|
| 3 |
+
"eval_accuracy": 0.8120300751879699,
|
| 4 |
+
"eval_loss": 0.538909375667572,
|
| 5 |
+
"eval_runtime": 1.7053,
|
| 6 |
+
"eval_samples_per_second": 77.99,
|
| 7 |
+
"eval_steps_per_second": 19.937
|
| 8 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1aa0a94e5c17b125bb5ca0132370bafb00f8ea69f675dba55cc76a06be4a67c3
|
| 3 |
+
size 111498892
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"crop_pct": 0.875,
|
| 3 |
+
"do_normalize": true,
|
| 4 |
+
"do_rescale": true,
|
| 5 |
+
"do_resize": true,
|
| 6 |
+
"image_mean": [
|
| 7 |
+
0.485,
|
| 8 |
+
0.456,
|
| 9 |
+
0.406
|
| 10 |
+
],
|
| 11 |
+
"image_processor_type": "ConvNextImageProcessor",
|
| 12 |
+
"image_std": [
|
| 13 |
+
0.229,
|
| 14 |
+
0.224,
|
| 15 |
+
0.225
|
| 16 |
+
],
|
| 17 |
+
"resample": 3,
|
| 18 |
+
"rescale_factor": 0.00392156862745098,
|
| 19 |
+
"size": {
|
| 20 |
+
"shortest_edge": 224
|
| 21 |
+
}
|
| 22 |
+
}
|
runs/Nov23_15-21-40_435ad433beae/events.out.tfevents.1700752973.435ad433beae.439.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8143ba9d66e2099c5693bf18c2b6a64609bb4501f54986b6ded2d53debc1f85e
|
| 3 |
+
size 18070
|
runs/Nov23_15-21-40_435ad433beae/events.out.tfevents.1700753936.435ad433beae.439.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8725883c4261bc2c2cc80e843a39cca064a63077009f3595a3b4eed656c6257a
|
| 3 |
+
size 411
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 9.88,
|
| 3 |
+
"total_flos": 1.2819370691970002e+18,
|
| 4 |
+
"train_loss": 0.08128333170207043,
|
| 5 |
+
"train_runtime": 961.2553,
|
| 6 |
+
"train_samples_per_second": 10.757,
|
| 7 |
+
"train_steps_per_second": 0.666
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,502 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.8120300751879699,
|
| 3 |
+
"best_model_checkpoint": "convnextv2-tiny-1k-224-finetuned-beans/checkpoint-388",
|
| 4 |
+
"epoch": 9.884169884169884,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 640,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.15,
|
| 13 |
+
"learning_rate": 7.8125e-06,
|
| 14 |
+
"loss": 1.0872,
|
| 15 |
+
"step": 10
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.31,
|
| 19 |
+
"learning_rate": 1.5625e-05,
|
| 20 |
+
"loss": 0.9814,
|
| 21 |
+
"step": 20
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.46,
|
| 25 |
+
"learning_rate": 2.34375e-05,
|
| 26 |
+
"loss": 0.7814,
|
| 27 |
+
"step": 30
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.62,
|
| 31 |
+
"learning_rate": 3.125e-05,
|
| 32 |
+
"loss": 0.4805,
|
| 33 |
+
"step": 40
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.77,
|
| 37 |
+
"learning_rate": 3.90625e-05,
|
| 38 |
+
"loss": 0.3533,
|
| 39 |
+
"step": 50
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.93,
|
| 43 |
+
"learning_rate": 4.6875e-05,
|
| 44 |
+
"loss": 0.2179,
|
| 45 |
+
"step": 60
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.99,
|
| 49 |
+
"eval_accuracy": 0.7293233082706767,
|
| 50 |
+
"eval_loss": 0.5406778454780579,
|
| 51 |
+
"eval_runtime": 1.5242,
|
| 52 |
+
"eval_samples_per_second": 87.261,
|
| 53 |
+
"eval_steps_per_second": 22.307,
|
| 54 |
+
"step": 64
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 1.08,
|
| 58 |
+
"learning_rate": 4.947916666666667e-05,
|
| 59 |
+
"loss": 0.1219,
|
| 60 |
+
"step": 70
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 1.24,
|
| 64 |
+
"learning_rate": 4.8611111111111115e-05,
|
| 65 |
+
"loss": 0.0905,
|
| 66 |
+
"step": 80
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 1.39,
|
| 70 |
+
"learning_rate": 4.774305555555556e-05,
|
| 71 |
+
"loss": 0.0584,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 1.54,
|
| 76 |
+
"learning_rate": 4.6875e-05,
|
| 77 |
+
"loss": 0.0654,
|
| 78 |
+
"step": 100
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 1.7,
|
| 82 |
+
"learning_rate": 4.6006944444444444e-05,
|
| 83 |
+
"loss": 0.132,
|
| 84 |
+
"step": 110
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 1.85,
|
| 88 |
+
"learning_rate": 4.5138888888888894e-05,
|
| 89 |
+
"loss": 0.1033,
|
| 90 |
+
"step": 120
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 1.99,
|
| 94 |
+
"eval_accuracy": 0.706766917293233,
|
| 95 |
+
"eval_loss": 0.6816055774688721,
|
| 96 |
+
"eval_runtime": 1.9031,
|
| 97 |
+
"eval_samples_per_second": 69.885,
|
| 98 |
+
"eval_steps_per_second": 17.865,
|
| 99 |
+
"step": 129
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 2.01,
|
| 103 |
+
"learning_rate": 4.4270833333333337e-05,
|
| 104 |
+
"loss": 0.088,
|
| 105 |
+
"step": 130
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 2.16,
|
| 109 |
+
"learning_rate": 4.340277777777778e-05,
|
| 110 |
+
"loss": 0.0408,
|
| 111 |
+
"step": 140
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 2.32,
|
| 115 |
+
"learning_rate": 4.253472222222222e-05,
|
| 116 |
+
"loss": 0.018,
|
| 117 |
+
"step": 150
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 2.47,
|
| 121 |
+
"learning_rate": 4.166666666666667e-05,
|
| 122 |
+
"loss": 0.0828,
|
| 123 |
+
"step": 160
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 2.63,
|
| 127 |
+
"learning_rate": 4.0798611111111115e-05,
|
| 128 |
+
"loss": 0.1316,
|
| 129 |
+
"step": 170
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 2.78,
|
| 133 |
+
"learning_rate": 3.993055555555556e-05,
|
| 134 |
+
"loss": 0.0105,
|
| 135 |
+
"step": 180
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 2.93,
|
| 139 |
+
"learning_rate": 3.90625e-05,
|
| 140 |
+
"loss": 0.0425,
|
| 141 |
+
"step": 190
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 3.0,
|
| 145 |
+
"eval_accuracy": 0.7819548872180451,
|
| 146 |
+
"eval_loss": 0.5600232481956482,
|
| 147 |
+
"eval_runtime": 1.5091,
|
| 148 |
+
"eval_samples_per_second": 88.131,
|
| 149 |
+
"eval_steps_per_second": 22.53,
|
| 150 |
+
"step": 194
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 3.09,
|
| 154 |
+
"learning_rate": 3.8194444444444444e-05,
|
| 155 |
+
"loss": 0.0369,
|
| 156 |
+
"step": 200
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 3.24,
|
| 160 |
+
"learning_rate": 3.7326388888888893e-05,
|
| 161 |
+
"loss": 0.0354,
|
| 162 |
+
"step": 210
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 3.4,
|
| 166 |
+
"learning_rate": 3.6458333333333336e-05,
|
| 167 |
+
"loss": 0.0216,
|
| 168 |
+
"step": 220
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 3.55,
|
| 172 |
+
"learning_rate": 3.559027777777778e-05,
|
| 173 |
+
"loss": 0.0406,
|
| 174 |
+
"step": 230
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 3.71,
|
| 178 |
+
"learning_rate": 3.472222222222222e-05,
|
| 179 |
+
"loss": 0.0409,
|
| 180 |
+
"step": 240
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 3.86,
|
| 184 |
+
"learning_rate": 3.385416666666667e-05,
|
| 185 |
+
"loss": 0.0017,
|
| 186 |
+
"step": 250
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 4.0,
|
| 190 |
+
"eval_accuracy": 0.7443609022556391,
|
| 191 |
+
"eval_loss": 0.6063990592956543,
|
| 192 |
+
"eval_runtime": 1.484,
|
| 193 |
+
"eval_samples_per_second": 89.625,
|
| 194 |
+
"eval_steps_per_second": 22.912,
|
| 195 |
+
"step": 259
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 4.02,
|
| 199 |
+
"learning_rate": 3.2986111111111115e-05,
|
| 200 |
+
"loss": 0.0714,
|
| 201 |
+
"step": 260
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 4.17,
|
| 205 |
+
"learning_rate": 3.211805555555556e-05,
|
| 206 |
+
"loss": 0.025,
|
| 207 |
+
"step": 270
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 4.32,
|
| 211 |
+
"learning_rate": 3.125e-05,
|
| 212 |
+
"loss": 0.0007,
|
| 213 |
+
"step": 280
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 4.48,
|
| 217 |
+
"learning_rate": 3.0381944444444444e-05,
|
| 218 |
+
"loss": 0.0006,
|
| 219 |
+
"step": 290
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 4.63,
|
| 223 |
+
"learning_rate": 2.951388888888889e-05,
|
| 224 |
+
"loss": 0.0053,
|
| 225 |
+
"step": 300
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 4.79,
|
| 229 |
+
"learning_rate": 2.8645833333333333e-05,
|
| 230 |
+
"loss": 0.002,
|
| 231 |
+
"step": 310
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 4.94,
|
| 235 |
+
"learning_rate": 2.777777777777778e-05,
|
| 236 |
+
"loss": 0.0035,
|
| 237 |
+
"step": 320
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 4.99,
|
| 241 |
+
"eval_accuracy": 0.7894736842105263,
|
| 242 |
+
"eval_loss": 0.6192318201065063,
|
| 243 |
+
"eval_runtime": 1.8151,
|
| 244 |
+
"eval_samples_per_second": 73.275,
|
| 245 |
+
"eval_steps_per_second": 18.732,
|
| 246 |
+
"step": 323
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 5.1,
|
| 250 |
+
"learning_rate": 2.6909722222222222e-05,
|
| 251 |
+
"loss": 0.0005,
|
| 252 |
+
"step": 330
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 5.25,
|
| 256 |
+
"learning_rate": 2.604166666666667e-05,
|
| 257 |
+
"loss": 0.0004,
|
| 258 |
+
"step": 340
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 5.41,
|
| 262 |
+
"learning_rate": 2.517361111111111e-05,
|
| 263 |
+
"loss": 0.0005,
|
| 264 |
+
"step": 350
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 5.56,
|
| 268 |
+
"learning_rate": 2.4305555555555558e-05,
|
| 269 |
+
"loss": 0.0003,
|
| 270 |
+
"step": 360
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 5.71,
|
| 274 |
+
"learning_rate": 2.34375e-05,
|
| 275 |
+
"loss": 0.0199,
|
| 276 |
+
"step": 370
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 5.87,
|
| 280 |
+
"learning_rate": 2.2569444444444447e-05,
|
| 281 |
+
"loss": 0.0005,
|
| 282 |
+
"step": 380
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 5.99,
|
| 286 |
+
"eval_accuracy": 0.8120300751879699,
|
| 287 |
+
"eval_loss": 0.538909375667572,
|
| 288 |
+
"eval_runtime": 2.1559,
|
| 289 |
+
"eval_samples_per_second": 61.691,
|
| 290 |
+
"eval_steps_per_second": 15.771,
|
| 291 |
+
"step": 388
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 6.02,
|
| 295 |
+
"learning_rate": 2.170138888888889e-05,
|
| 296 |
+
"loss": 0.001,
|
| 297 |
+
"step": 390
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 6.18,
|
| 301 |
+
"learning_rate": 2.0833333333333336e-05,
|
| 302 |
+
"loss": 0.0003,
|
| 303 |
+
"step": 400
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 6.33,
|
| 307 |
+
"learning_rate": 1.996527777777778e-05,
|
| 308 |
+
"loss": 0.0003,
|
| 309 |
+
"step": 410
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 6.49,
|
| 313 |
+
"learning_rate": 1.9097222222222222e-05,
|
| 314 |
+
"loss": 0.0004,
|
| 315 |
+
"step": 420
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 6.64,
|
| 319 |
+
"learning_rate": 1.8229166666666668e-05,
|
| 320 |
+
"loss": 0.0003,
|
| 321 |
+
"step": 430
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 6.8,
|
| 325 |
+
"learning_rate": 1.736111111111111e-05,
|
| 326 |
+
"loss": 0.0003,
|
| 327 |
+
"step": 440
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 6.95,
|
| 331 |
+
"learning_rate": 1.6493055555555557e-05,
|
| 332 |
+
"loss": 0.0003,
|
| 333 |
+
"step": 450
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 7.0,
|
| 337 |
+
"eval_accuracy": 0.7894736842105263,
|
| 338 |
+
"eval_loss": 0.6144049763679504,
|
| 339 |
+
"eval_runtime": 1.5163,
|
| 340 |
+
"eval_samples_per_second": 87.716,
|
| 341 |
+
"eval_steps_per_second": 22.424,
|
| 342 |
+
"step": 453
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 7.1,
|
| 346 |
+
"learning_rate": 1.5625e-05,
|
| 347 |
+
"loss": 0.0003,
|
| 348 |
+
"step": 460
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"epoch": 7.26,
|
| 352 |
+
"learning_rate": 1.4756944444444445e-05,
|
| 353 |
+
"loss": 0.0002,
|
| 354 |
+
"step": 470
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 7.41,
|
| 358 |
+
"learning_rate": 1.388888888888889e-05,
|
| 359 |
+
"loss": 0.0002,
|
| 360 |
+
"step": 480
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 7.57,
|
| 364 |
+
"learning_rate": 1.3020833333333334e-05,
|
| 365 |
+
"loss": 0.0002,
|
| 366 |
+
"step": 490
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 7.72,
|
| 370 |
+
"learning_rate": 1.2152777777777779e-05,
|
| 371 |
+
"loss": 0.0003,
|
| 372 |
+
"step": 500
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 7.88,
|
| 376 |
+
"learning_rate": 1.1284722222222223e-05,
|
| 377 |
+
"loss": 0.0002,
|
| 378 |
+
"step": 510
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 8.0,
|
| 382 |
+
"eval_accuracy": 0.7894736842105263,
|
| 383 |
+
"eval_loss": 0.6294459104537964,
|
| 384 |
+
"eval_runtime": 1.5209,
|
| 385 |
+
"eval_samples_per_second": 87.448,
|
| 386 |
+
"eval_steps_per_second": 22.355,
|
| 387 |
+
"step": 518
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 8.03,
|
| 391 |
+
"learning_rate": 1.0416666666666668e-05,
|
| 392 |
+
"loss": 0.0002,
|
| 393 |
+
"step": 520
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 8.19,
|
| 397 |
+
"learning_rate": 9.548611111111111e-06,
|
| 398 |
+
"loss": 0.0002,
|
| 399 |
+
"step": 530
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 8.34,
|
| 403 |
+
"learning_rate": 8.680555555555556e-06,
|
| 404 |
+
"loss": 0.0002,
|
| 405 |
+
"step": 540
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 8.49,
|
| 409 |
+
"learning_rate": 7.8125e-06,
|
| 410 |
+
"loss": 0.0002,
|
| 411 |
+
"step": 550
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 8.65,
|
| 415 |
+
"learning_rate": 6.944444444444445e-06,
|
| 416 |
+
"loss": 0.0002,
|
| 417 |
+
"step": 560
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 8.8,
|
| 421 |
+
"learning_rate": 6.076388888888889e-06,
|
| 422 |
+
"loss": 0.0002,
|
| 423 |
+
"step": 570
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 8.96,
|
| 427 |
+
"learning_rate": 5.208333333333334e-06,
|
| 428 |
+
"loss": 0.0002,
|
| 429 |
+
"step": 580
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 8.99,
|
| 433 |
+
"eval_accuracy": 0.7894736842105263,
|
| 434 |
+
"eval_loss": 0.6324166059494019,
|
| 435 |
+
"eval_runtime": 2.0107,
|
| 436 |
+
"eval_samples_per_second": 66.147,
|
| 437 |
+
"eval_steps_per_second": 16.91,
|
| 438 |
+
"step": 582
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 9.11,
|
| 442 |
+
"learning_rate": 4.340277777777778e-06,
|
| 443 |
+
"loss": 0.0002,
|
| 444 |
+
"step": 590
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 9.27,
|
| 448 |
+
"learning_rate": 3.4722222222222224e-06,
|
| 449 |
+
"loss": 0.0002,
|
| 450 |
+
"step": 600
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 9.42,
|
| 454 |
+
"learning_rate": 2.604166666666667e-06,
|
| 455 |
+
"loss": 0.0002,
|
| 456 |
+
"step": 610
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 9.58,
|
| 460 |
+
"learning_rate": 1.7361111111111112e-06,
|
| 461 |
+
"loss": 0.0002,
|
| 462 |
+
"step": 620
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"epoch": 9.73,
|
| 466 |
+
"learning_rate": 8.680555555555556e-07,
|
| 467 |
+
"loss": 0.0002,
|
| 468 |
+
"step": 630
|
| 469 |
+
},
|
| 470 |
+
{
|
| 471 |
+
"epoch": 9.88,
|
| 472 |
+
"learning_rate": 0.0,
|
| 473 |
+
"loss": 0.0002,
|
| 474 |
+
"step": 640
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 9.88,
|
| 478 |
+
"eval_accuracy": 0.7894736842105263,
|
| 479 |
+
"eval_loss": 0.6338961124420166,
|
| 480 |
+
"eval_runtime": 1.9752,
|
| 481 |
+
"eval_samples_per_second": 67.334,
|
| 482 |
+
"eval_steps_per_second": 17.213,
|
| 483 |
+
"step": 640
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 9.88,
|
| 487 |
+
"step": 640,
|
| 488 |
+
"total_flos": 1.2819370691970002e+18,
|
| 489 |
+
"train_loss": 0.08128333170207043,
|
| 490 |
+
"train_runtime": 961.2553,
|
| 491 |
+
"train_samples_per_second": 10.757,
|
| 492 |
+
"train_steps_per_second": 0.666
|
| 493 |
+
}
|
| 494 |
+
],
|
| 495 |
+
"logging_steps": 10,
|
| 496 |
+
"max_steps": 640,
|
| 497 |
+
"num_train_epochs": 10,
|
| 498 |
+
"save_steps": 500,
|
| 499 |
+
"total_flos": 1.2819370691970002e+18,
|
| 500 |
+
"trial_name": null,
|
| 501 |
+
"trial_params": null
|
| 502 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:49856b37d6237cf06013dc0a351859ca2ad34d97f97391664b0fc505a68eb318
|
| 3 |
+
size 4600
|