End of training
Browse files- README.md +61 -0
- all_results.json +16 -0
- config.json +65 -0
- eval_results.json +10 -0
- model.safetensors +3 -0
- preprocessor_config.json +22 -0
- runs/Nov13_19-50-32_d01704b0a29d/events.out.tfevents.1699905032.d01704b0a29d.625.0 +3 -0
- runs/Nov13_19-50-32_d01704b0a29d/events.out.tfevents.1699906160.d01704b0a29d.625.1 +3 -0
- train_results.json +8 -0
- trainer_state.json +880 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: microsoft/resnet-50
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
model-index:
|
| 7 |
+
- name: resnet-50-finetuned-combinedSpiders
|
| 8 |
+
results: []
|
| 9 |
+
---
|
| 10 |
+
|
| 11 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 12 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 13 |
+
|
| 14 |
+
# resnet-50-finetuned-combinedSpiders
|
| 15 |
+
|
| 16 |
+
This model is a fine-tuned version of [microsoft/resnet-50](https://huggingface.co/microsoft/resnet-50) on an unknown dataset.
|
| 17 |
+
It achieves the following results on the evaluation set:
|
| 18 |
+
- eval_loss: 0.3794
|
| 19 |
+
- eval_accuracy: 0.8996
|
| 20 |
+
- eval_precision: 0.8983
|
| 21 |
+
- eval_recall: 0.8934
|
| 22 |
+
- eval_f1: 0.8943
|
| 23 |
+
- eval_runtime: 14.9052
|
| 24 |
+
- eval_samples_per_second: 181.145
|
| 25 |
+
- eval_steps_per_second: 11.338
|
| 26 |
+
- step: 0
|
| 27 |
+
|
| 28 |
+
## Model description
|
| 29 |
+
|
| 30 |
+
More information needed
|
| 31 |
+
|
| 32 |
+
## Intended uses & limitations
|
| 33 |
+
|
| 34 |
+
More information needed
|
| 35 |
+
|
| 36 |
+
## Training and evaluation data
|
| 37 |
+
|
| 38 |
+
More information needed
|
| 39 |
+
|
| 40 |
+
## Training procedure
|
| 41 |
+
|
| 42 |
+
### Training hyperparameters
|
| 43 |
+
|
| 44 |
+
The following hyperparameters were used during training:
|
| 45 |
+
- learning_rate: 5e-05
|
| 46 |
+
- train_batch_size: 16
|
| 47 |
+
- eval_batch_size: 16
|
| 48 |
+
- seed: 42
|
| 49 |
+
- gradient_accumulation_steps: 4
|
| 50 |
+
- total_train_batch_size: 64
|
| 51 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 52 |
+
- lr_scheduler_type: linear
|
| 53 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 54 |
+
- num_epochs: 4
|
| 55 |
+
|
| 56 |
+
### Framework versions
|
| 57 |
+
|
| 58 |
+
- Transformers 4.35.0
|
| 59 |
+
- Pytorch 2.1.0+cu118
|
| 60 |
+
- Datasets 2.14.6
|
| 61 |
+
- Tokenizers 0.14.1
|
all_results.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.99,
|
| 3 |
+
"eval_accuracy": 0.8996296296296297,
|
| 4 |
+
"eval_f1": 0.894271485857943,
|
| 5 |
+
"eval_loss": 0.379376620054245,
|
| 6 |
+
"eval_precision": 0.8983431695901203,
|
| 7 |
+
"eval_recall": 0.8933698002925257,
|
| 8 |
+
"eval_runtime": 14.9052,
|
| 9 |
+
"eval_samples_per_second": 181.145,
|
| 10 |
+
"eval_steps_per_second": 11.338,
|
| 11 |
+
"total_flos": 1.8332979581807493e+18,
|
| 12 |
+
"train_loss": 1.1345372907485736,
|
| 13 |
+
"train_runtime": 1112.1938,
|
| 14 |
+
"train_samples_per_second": 77.684,
|
| 15 |
+
"train_steps_per_second": 1.212
|
| 16 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,65 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": "annual crop",
|
| 24 |
+
"1": "forest",
|
| 25 |
+
"2": "herbaceous vegetation",
|
| 26 |
+
"3": "highway",
|
| 27 |
+
"4": "industrial",
|
| 28 |
+
"5": "pasture",
|
| 29 |
+
"6": "permanent crop",
|
| 30 |
+
"7": "residential",
|
| 31 |
+
"8": "river",
|
| 32 |
+
"9": "sea or lake"
|
| 33 |
+
},
|
| 34 |
+
"label2id": {
|
| 35 |
+
"annual crop": 0,
|
| 36 |
+
"forest": 1,
|
| 37 |
+
"herbaceous vegetation": 2,
|
| 38 |
+
"highway": 3,
|
| 39 |
+
"industrial": 4,
|
| 40 |
+
"pasture": 5,
|
| 41 |
+
"permanent crop": 6,
|
| 42 |
+
"residential": 7,
|
| 43 |
+
"river": 8,
|
| 44 |
+
"sea or lake": 9
|
| 45 |
+
},
|
| 46 |
+
"layer_type": "bottleneck",
|
| 47 |
+
"model_type": "resnet",
|
| 48 |
+
"num_channels": 3,
|
| 49 |
+
"out_features": [
|
| 50 |
+
"stage4"
|
| 51 |
+
],
|
| 52 |
+
"out_indices": [
|
| 53 |
+
4
|
| 54 |
+
],
|
| 55 |
+
"problem_type": "single_label_classification",
|
| 56 |
+
"stage_names": [
|
| 57 |
+
"stem",
|
| 58 |
+
"stage1",
|
| 59 |
+
"stage2",
|
| 60 |
+
"stage3",
|
| 61 |
+
"stage4"
|
| 62 |
+
],
|
| 63 |
+
"torch_dtype": "float32",
|
| 64 |
+
"transformers_version": "4.35.0"
|
| 65 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"eval_accuracy": 0.8996296296296297,
|
| 3 |
+
"eval_f1": 0.894271485857943,
|
| 4 |
+
"eval_loss": 0.379376620054245,
|
| 5 |
+
"eval_precision": 0.8983431695901203,
|
| 6 |
+
"eval_recall": 0.8933698002925257,
|
| 7 |
+
"eval_runtime": 14.9052,
|
| 8 |
+
"eval_samples_per_second": 181.145,
|
| 9 |
+
"eval_steps_per_second": 11.338
|
| 10 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d6d4b20265dd4e5e74dcb81e8d3f6de5ebe97a827e7374b8bf3bbc8cc149d6d6
|
| 3 |
+
size 94368544
|
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/Nov13_19-50-32_d01704b0a29d/events.out.tfevents.1699905032.d01704b0a29d.625.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:20cfd35552df19e0b03a69e507505efae76c09a5aef48604522d8cb318cfba0c
|
| 3 |
+
size 27996
|
runs/Nov13_19-50-32_d01704b0a29d/events.out.tfevents.1699906160.d01704b0a29d.625.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d9d8000e2f12341736975e0bd98ee5eb13a03a98853f48f879186ea27d4342a7
|
| 3 |
+
size 486
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.99,
|
| 3 |
+
"total_flos": 1.8332979581807493e+18,
|
| 4 |
+
"train_loss": 1.1345372907485736,
|
| 5 |
+
"train_runtime": 1112.1938,
|
| 6 |
+
"train_samples_per_second": 77.684,
|
| 7 |
+
"train_steps_per_second": 1.212
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,880 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.8974074074074074,
|
| 3 |
+
"best_model_checkpoint": "resnet-50-finetuned-combinedSpiders/checkpoint-1348",
|
| 4 |
+
"epoch": 3.9940740740740743,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 1348,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.03,
|
| 13 |
+
"learning_rate": 3.7037037037037037e-06,
|
| 14 |
+
"loss": 2.3139,
|
| 15 |
+
"step": 10
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.06,
|
| 19 |
+
"learning_rate": 7.4074074074074075e-06,
|
| 20 |
+
"loss": 2.3199,
|
| 21 |
+
"step": 20
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.09,
|
| 25 |
+
"learning_rate": 1.1111111111111112e-05,
|
| 26 |
+
"loss": 2.3141,
|
| 27 |
+
"step": 30
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.12,
|
| 31 |
+
"learning_rate": 1.4814814814814815e-05,
|
| 32 |
+
"loss": 2.3051,
|
| 33 |
+
"step": 40
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.15,
|
| 37 |
+
"learning_rate": 1.8518518518518518e-05,
|
| 38 |
+
"loss": 2.3055,
|
| 39 |
+
"step": 50
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.18,
|
| 43 |
+
"learning_rate": 2.2222222222222223e-05,
|
| 44 |
+
"loss": 2.2966,
|
| 45 |
+
"step": 60
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.21,
|
| 49 |
+
"learning_rate": 2.5925925925925925e-05,
|
| 50 |
+
"loss": 2.2891,
|
| 51 |
+
"step": 70
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.24,
|
| 55 |
+
"learning_rate": 2.962962962962963e-05,
|
| 56 |
+
"loss": 2.2871,
|
| 57 |
+
"step": 80
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.27,
|
| 61 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 62 |
+
"loss": 2.2767,
|
| 63 |
+
"step": 90
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.3,
|
| 67 |
+
"learning_rate": 3.7037037037037037e-05,
|
| 68 |
+
"loss": 2.2604,
|
| 69 |
+
"step": 100
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.33,
|
| 73 |
+
"learning_rate": 4.074074074074074e-05,
|
| 74 |
+
"loss": 2.254,
|
| 75 |
+
"step": 110
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.36,
|
| 79 |
+
"learning_rate": 4.4444444444444447e-05,
|
| 80 |
+
"loss": 2.2329,
|
| 81 |
+
"step": 120
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.39,
|
| 85 |
+
"learning_rate": 4.814814814814815e-05,
|
| 86 |
+
"loss": 2.2251,
|
| 87 |
+
"step": 130
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.41,
|
| 91 |
+
"learning_rate": 4.979389942291839e-05,
|
| 92 |
+
"loss": 2.2012,
|
| 93 |
+
"step": 140
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.44,
|
| 97 |
+
"learning_rate": 4.9381698268755155e-05,
|
| 98 |
+
"loss": 2.1776,
|
| 99 |
+
"step": 150
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.47,
|
| 103 |
+
"learning_rate": 4.896949711459192e-05,
|
| 104 |
+
"loss": 2.1594,
|
| 105 |
+
"step": 160
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.5,
|
| 109 |
+
"learning_rate": 4.8557295960428687e-05,
|
| 110 |
+
"loss": 2.1244,
|
| 111 |
+
"step": 170
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.53,
|
| 115 |
+
"learning_rate": 4.814509480626546e-05,
|
| 116 |
+
"loss": 2.0911,
|
| 117 |
+
"step": 180
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.56,
|
| 121 |
+
"learning_rate": 4.7732893652102225e-05,
|
| 122 |
+
"loss": 2.071,
|
| 123 |
+
"step": 190
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.59,
|
| 127 |
+
"learning_rate": 4.7320692497939e-05,
|
| 128 |
+
"loss": 2.0046,
|
| 129 |
+
"step": 200
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.62,
|
| 133 |
+
"learning_rate": 4.6908491343775764e-05,
|
| 134 |
+
"loss": 1.9742,
|
| 135 |
+
"step": 210
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.65,
|
| 139 |
+
"learning_rate": 4.649629018961254e-05,
|
| 140 |
+
"loss": 1.9107,
|
| 141 |
+
"step": 220
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.68,
|
| 145 |
+
"learning_rate": 4.60840890354493e-05,
|
| 146 |
+
"loss": 1.8838,
|
| 147 |
+
"step": 230
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 0.71,
|
| 151 |
+
"learning_rate": 4.567188788128607e-05,
|
| 152 |
+
"loss": 1.8305,
|
| 153 |
+
"step": 240
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.74,
|
| 157 |
+
"learning_rate": 4.525968672712284e-05,
|
| 158 |
+
"loss": 1.7924,
|
| 159 |
+
"step": 250
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.77,
|
| 163 |
+
"learning_rate": 4.484748557295961e-05,
|
| 164 |
+
"loss": 1.7411,
|
| 165 |
+
"step": 260
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.8,
|
| 169 |
+
"learning_rate": 4.443528441879637e-05,
|
| 170 |
+
"loss": 1.6658,
|
| 171 |
+
"step": 270
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.83,
|
| 175 |
+
"learning_rate": 4.402308326463314e-05,
|
| 176 |
+
"loss": 1.6818,
|
| 177 |
+
"step": 280
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.86,
|
| 181 |
+
"learning_rate": 4.361088211046991e-05,
|
| 182 |
+
"loss": 1.5883,
|
| 183 |
+
"step": 290
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 0.89,
|
| 187 |
+
"learning_rate": 4.319868095630668e-05,
|
| 188 |
+
"loss": 1.5316,
|
| 189 |
+
"step": 300
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.92,
|
| 193 |
+
"learning_rate": 4.278647980214345e-05,
|
| 194 |
+
"loss": 1.5345,
|
| 195 |
+
"step": 310
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.95,
|
| 199 |
+
"learning_rate": 4.2374278647980216e-05,
|
| 200 |
+
"loss": 1.4529,
|
| 201 |
+
"step": 320
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 0.98,
|
| 205 |
+
"learning_rate": 4.196207749381699e-05,
|
| 206 |
+
"loss": 1.4418,
|
| 207 |
+
"step": 330
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 1.0,
|
| 211 |
+
"eval_accuracy": 0.6692592592592592,
|
| 212 |
+
"eval_f1": 0.6056123000612204,
|
| 213 |
+
"eval_loss": 1.2732560634613037,
|
| 214 |
+
"eval_precision": 0.6781768119793957,
|
| 215 |
+
"eval_recall": 0.6388902436275756,
|
| 216 |
+
"eval_runtime": 15.6445,
|
| 217 |
+
"eval_samples_per_second": 172.584,
|
| 218 |
+
"eval_steps_per_second": 10.803,
|
| 219 |
+
"step": 337
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 1.01,
|
| 223 |
+
"learning_rate": 4.1549876339653755e-05,
|
| 224 |
+
"loss": 1.4001,
|
| 225 |
+
"step": 340
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 1.04,
|
| 229 |
+
"learning_rate": 4.113767518549052e-05,
|
| 230 |
+
"loss": 1.3676,
|
| 231 |
+
"step": 350
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 1.07,
|
| 235 |
+
"learning_rate": 4.072547403132729e-05,
|
| 236 |
+
"loss": 1.3273,
|
| 237 |
+
"step": 360
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 1.1,
|
| 241 |
+
"learning_rate": 4.031327287716406e-05,
|
| 242 |
+
"loss": 1.3226,
|
| 243 |
+
"step": 370
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 1.13,
|
| 247 |
+
"learning_rate": 3.9901071723000826e-05,
|
| 248 |
+
"loss": 1.2902,
|
| 249 |
+
"step": 380
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 1.16,
|
| 253 |
+
"learning_rate": 3.948887056883759e-05,
|
| 254 |
+
"loss": 1.2565,
|
| 255 |
+
"step": 390
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 1.19,
|
| 259 |
+
"learning_rate": 3.907666941467436e-05,
|
| 260 |
+
"loss": 1.2411,
|
| 261 |
+
"step": 400
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 1.21,
|
| 265 |
+
"learning_rate": 3.866446826051113e-05,
|
| 266 |
+
"loss": 1.2337,
|
| 267 |
+
"step": 410
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 1.24,
|
| 271 |
+
"learning_rate": 3.82522671063479e-05,
|
| 272 |
+
"loss": 1.1719,
|
| 273 |
+
"step": 420
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 1.27,
|
| 277 |
+
"learning_rate": 3.784006595218467e-05,
|
| 278 |
+
"loss": 1.1746,
|
| 279 |
+
"step": 430
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 1.3,
|
| 283 |
+
"learning_rate": 3.7427864798021435e-05,
|
| 284 |
+
"loss": 1.1444,
|
| 285 |
+
"step": 440
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 1.33,
|
| 289 |
+
"learning_rate": 3.701566364385821e-05,
|
| 290 |
+
"loss": 1.1284,
|
| 291 |
+
"step": 450
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 1.36,
|
| 295 |
+
"learning_rate": 3.6603462489694974e-05,
|
| 296 |
+
"loss": 1.09,
|
| 297 |
+
"step": 460
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 1.39,
|
| 301 |
+
"learning_rate": 3.619126133553174e-05,
|
| 302 |
+
"loss": 1.1276,
|
| 303 |
+
"step": 470
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 1.42,
|
| 307 |
+
"learning_rate": 3.577906018136851e-05,
|
| 308 |
+
"loss": 1.0837,
|
| 309 |
+
"step": 480
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 1.45,
|
| 313 |
+
"learning_rate": 3.536685902720528e-05,
|
| 314 |
+
"loss": 1.0355,
|
| 315 |
+
"step": 490
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 1.48,
|
| 319 |
+
"learning_rate": 3.4954657873042044e-05,
|
| 320 |
+
"loss": 0.9847,
|
| 321 |
+
"step": 500
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 1.51,
|
| 325 |
+
"learning_rate": 3.454245671887881e-05,
|
| 326 |
+
"loss": 1.0393,
|
| 327 |
+
"step": 510
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 1.54,
|
| 331 |
+
"learning_rate": 3.413025556471558e-05,
|
| 332 |
+
"loss": 1.008,
|
| 333 |
+
"step": 520
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 1.57,
|
| 337 |
+
"learning_rate": 3.371805441055235e-05,
|
| 338 |
+
"loss": 0.977,
|
| 339 |
+
"step": 530
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 1.6,
|
| 343 |
+
"learning_rate": 3.330585325638912e-05,
|
| 344 |
+
"loss": 0.9954,
|
| 345 |
+
"step": 540
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 1.63,
|
| 349 |
+
"learning_rate": 3.289365210222589e-05,
|
| 350 |
+
"loss": 0.9811,
|
| 351 |
+
"step": 550
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 1.66,
|
| 355 |
+
"learning_rate": 3.248145094806266e-05,
|
| 356 |
+
"loss": 1.0519,
|
| 357 |
+
"step": 560
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 1.69,
|
| 361 |
+
"learning_rate": 3.2069249793899426e-05,
|
| 362 |
+
"loss": 0.9764,
|
| 363 |
+
"step": 570
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 1.72,
|
| 367 |
+
"learning_rate": 3.165704863973619e-05,
|
| 368 |
+
"loss": 0.9426,
|
| 369 |
+
"step": 580
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 1.75,
|
| 373 |
+
"learning_rate": 3.124484748557296e-05,
|
| 374 |
+
"loss": 0.9598,
|
| 375 |
+
"step": 590
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 1.78,
|
| 379 |
+
"learning_rate": 3.083264633140973e-05,
|
| 380 |
+
"loss": 0.9344,
|
| 381 |
+
"step": 600
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 1.81,
|
| 385 |
+
"learning_rate": 3.0420445177246497e-05,
|
| 386 |
+
"loss": 0.9049,
|
| 387 |
+
"step": 610
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 1.84,
|
| 391 |
+
"learning_rate": 3.0008244023083266e-05,
|
| 392 |
+
"loss": 0.8284,
|
| 393 |
+
"step": 620
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 1.87,
|
| 397 |
+
"learning_rate": 2.9596042868920032e-05,
|
| 398 |
+
"loss": 0.9119,
|
| 399 |
+
"step": 630
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 1.9,
|
| 403 |
+
"learning_rate": 2.9183841714756805e-05,
|
| 404 |
+
"loss": 0.8489,
|
| 405 |
+
"step": 640
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 1.93,
|
| 409 |
+
"learning_rate": 2.877164056059357e-05,
|
| 410 |
+
"loss": 0.8227,
|
| 411 |
+
"step": 650
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 1.96,
|
| 415 |
+
"learning_rate": 2.8359439406430337e-05,
|
| 416 |
+
"loss": 0.8788,
|
| 417 |
+
"step": 660
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 1.99,
|
| 421 |
+
"learning_rate": 2.7947238252267106e-05,
|
| 422 |
+
"loss": 0.9058,
|
| 423 |
+
"step": 670
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 2.0,
|
| 427 |
+
"eval_accuracy": 0.8525925925925926,
|
| 428 |
+
"eval_f1": 0.8410753034302768,
|
| 429 |
+
"eval_loss": 0.5913922786712646,
|
| 430 |
+
"eval_precision": 0.8467806416477608,
|
| 431 |
+
"eval_recall": 0.840061365110396,
|
| 432 |
+
"eval_runtime": 14.4146,
|
| 433 |
+
"eval_samples_per_second": 187.31,
|
| 434 |
+
"eval_steps_per_second": 11.724,
|
| 435 |
+
"step": 675
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 2.01,
|
| 439 |
+
"learning_rate": 2.753503709810388e-05,
|
| 440 |
+
"loss": 0.8246,
|
| 441 |
+
"step": 680
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 2.04,
|
| 445 |
+
"learning_rate": 2.7122835943940645e-05,
|
| 446 |
+
"loss": 0.8661,
|
| 447 |
+
"step": 690
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 2.07,
|
| 451 |
+
"learning_rate": 2.671063478977741e-05,
|
| 452 |
+
"loss": 0.9393,
|
| 453 |
+
"step": 700
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 2.1,
|
| 457 |
+
"learning_rate": 2.6298433635614183e-05,
|
| 458 |
+
"loss": 0.8919,
|
| 459 |
+
"step": 710
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 2.13,
|
| 463 |
+
"learning_rate": 2.588623248145095e-05,
|
| 464 |
+
"loss": 0.8454,
|
| 465 |
+
"step": 720
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 2.16,
|
| 469 |
+
"learning_rate": 2.547403132728772e-05,
|
| 470 |
+
"loss": 0.8213,
|
| 471 |
+
"step": 730
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 2.19,
|
| 475 |
+
"learning_rate": 2.5061830173124485e-05,
|
| 476 |
+
"loss": 0.8213,
|
| 477 |
+
"step": 740
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 2.22,
|
| 481 |
+
"learning_rate": 2.4649629018961254e-05,
|
| 482 |
+
"loss": 0.7937,
|
| 483 |
+
"step": 750
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 2.25,
|
| 487 |
+
"learning_rate": 2.4237427864798023e-05,
|
| 488 |
+
"loss": 0.7901,
|
| 489 |
+
"step": 760
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 2.28,
|
| 493 |
+
"learning_rate": 2.382522671063479e-05,
|
| 494 |
+
"loss": 0.8005,
|
| 495 |
+
"step": 770
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 2.31,
|
| 499 |
+
"learning_rate": 2.341302555647156e-05,
|
| 500 |
+
"loss": 0.776,
|
| 501 |
+
"step": 780
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 2.34,
|
| 505 |
+
"learning_rate": 2.3000824402308328e-05,
|
| 506 |
+
"loss": 0.776,
|
| 507 |
+
"step": 790
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 2.37,
|
| 511 |
+
"learning_rate": 2.2588623248145097e-05,
|
| 512 |
+
"loss": 0.7684,
|
| 513 |
+
"step": 800
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 2.4,
|
| 517 |
+
"learning_rate": 2.2176422093981863e-05,
|
| 518 |
+
"loss": 0.7854,
|
| 519 |
+
"step": 810
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 2.43,
|
| 523 |
+
"learning_rate": 2.1764220939818633e-05,
|
| 524 |
+
"loss": 0.7608,
|
| 525 |
+
"step": 820
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 2.46,
|
| 529 |
+
"learning_rate": 2.13520197856554e-05,
|
| 530 |
+
"loss": 0.7563,
|
| 531 |
+
"step": 830
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 2.49,
|
| 535 |
+
"learning_rate": 2.093981863149217e-05,
|
| 536 |
+
"loss": 0.7836,
|
| 537 |
+
"step": 840
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 2.52,
|
| 541 |
+
"learning_rate": 2.0527617477328937e-05,
|
| 542 |
+
"loss": 0.7936,
|
| 543 |
+
"step": 850
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 2.55,
|
| 547 |
+
"learning_rate": 2.0115416323165706e-05,
|
| 548 |
+
"loss": 0.7693,
|
| 549 |
+
"step": 860
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 2.58,
|
| 553 |
+
"learning_rate": 1.9703215169002472e-05,
|
| 554 |
+
"loss": 0.8235,
|
| 555 |
+
"step": 870
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 2.61,
|
| 559 |
+
"learning_rate": 1.9291014014839242e-05,
|
| 560 |
+
"loss": 0.8423,
|
| 561 |
+
"step": 880
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 2.64,
|
| 565 |
+
"learning_rate": 1.887881286067601e-05,
|
| 566 |
+
"loss": 0.6937,
|
| 567 |
+
"step": 890
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 2.67,
|
| 571 |
+
"learning_rate": 1.846661170651278e-05,
|
| 572 |
+
"loss": 0.7325,
|
| 573 |
+
"step": 900
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 2.7,
|
| 577 |
+
"learning_rate": 1.805441055234955e-05,
|
| 578 |
+
"loss": 0.779,
|
| 579 |
+
"step": 910
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 2.73,
|
| 583 |
+
"learning_rate": 1.7642209398186316e-05,
|
| 584 |
+
"loss": 0.7278,
|
| 585 |
+
"step": 920
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 2.76,
|
| 589 |
+
"learning_rate": 1.7230008244023085e-05,
|
| 590 |
+
"loss": 0.6911,
|
| 591 |
+
"step": 930
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 2.79,
|
| 595 |
+
"learning_rate": 1.681780708985985e-05,
|
| 596 |
+
"loss": 0.7127,
|
| 597 |
+
"step": 940
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 2.81,
|
| 601 |
+
"learning_rate": 1.640560593569662e-05,
|
| 602 |
+
"loss": 0.7116,
|
| 603 |
+
"step": 950
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 2.84,
|
| 607 |
+
"learning_rate": 1.599340478153339e-05,
|
| 608 |
+
"loss": 0.76,
|
| 609 |
+
"step": 960
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 2.87,
|
| 613 |
+
"learning_rate": 1.558120362737016e-05,
|
| 614 |
+
"loss": 0.7644,
|
| 615 |
+
"step": 970
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 2.9,
|
| 619 |
+
"learning_rate": 1.5169002473206925e-05,
|
| 620 |
+
"loss": 0.7876,
|
| 621 |
+
"step": 980
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 2.93,
|
| 625 |
+
"learning_rate": 1.4756801319043694e-05,
|
| 626 |
+
"loss": 0.6966,
|
| 627 |
+
"step": 990
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 2.96,
|
| 631 |
+
"learning_rate": 1.4344600164880462e-05,
|
| 632 |
+
"loss": 0.7425,
|
| 633 |
+
"step": 1000
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 2.99,
|
| 637 |
+
"learning_rate": 1.3932399010717231e-05,
|
| 638 |
+
"loss": 0.743,
|
| 639 |
+
"step": 1010
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 3.0,
|
| 643 |
+
"eval_accuracy": 0.8881481481481481,
|
| 644 |
+
"eval_f1": 0.8799732123735866,
|
| 645 |
+
"eval_loss": 0.4424385130405426,
|
| 646 |
+
"eval_precision": 0.8877465438754772,
|
| 647 |
+
"eval_recall": 0.8775775457617858,
|
| 648 |
+
"eval_runtime": 14.8388,
|
| 649 |
+
"eval_samples_per_second": 181.956,
|
| 650 |
+
"eval_steps_per_second": 11.389,
|
| 651 |
+
"step": 1012
|
| 652 |
+
},
|
| 653 |
+
{
|
| 654 |
+
"epoch": 3.02,
|
| 655 |
+
"learning_rate": 1.3520197856553999e-05,
|
| 656 |
+
"loss": 0.7802,
|
| 657 |
+
"step": 1020
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 3.05,
|
| 661 |
+
"learning_rate": 1.3107996702390768e-05,
|
| 662 |
+
"loss": 0.7482,
|
| 663 |
+
"step": 1030
|
| 664 |
+
},
|
| 665 |
+
{
|
| 666 |
+
"epoch": 3.08,
|
| 667 |
+
"learning_rate": 1.2695795548227534e-05,
|
| 668 |
+
"loss": 0.6815,
|
| 669 |
+
"step": 1040
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 3.11,
|
| 673 |
+
"learning_rate": 1.2283594394064305e-05,
|
| 674 |
+
"loss": 0.6821,
|
| 675 |
+
"step": 1050
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 3.14,
|
| 679 |
+
"learning_rate": 1.1871393239901073e-05,
|
| 680 |
+
"loss": 0.6976,
|
| 681 |
+
"step": 1060
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 3.17,
|
| 685 |
+
"learning_rate": 1.145919208573784e-05,
|
| 686 |
+
"loss": 0.7766,
|
| 687 |
+
"step": 1070
|
| 688 |
+
},
|
| 689 |
+
{
|
| 690 |
+
"epoch": 3.2,
|
| 691 |
+
"learning_rate": 1.104699093157461e-05,
|
| 692 |
+
"loss": 0.7489,
|
| 693 |
+
"step": 1080
|
| 694 |
+
},
|
| 695 |
+
{
|
| 696 |
+
"epoch": 3.23,
|
| 697 |
+
"learning_rate": 1.0634789777411378e-05,
|
| 698 |
+
"loss": 0.7489,
|
| 699 |
+
"step": 1090
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 3.26,
|
| 703 |
+
"learning_rate": 1.0222588623248145e-05,
|
| 704 |
+
"loss": 0.6568,
|
| 705 |
+
"step": 1100
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 3.29,
|
| 709 |
+
"learning_rate": 9.810387469084915e-06,
|
| 710 |
+
"loss": 0.7121,
|
| 711 |
+
"step": 1110
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 3.32,
|
| 715 |
+
"learning_rate": 9.398186314921682e-06,
|
| 716 |
+
"loss": 0.7013,
|
| 717 |
+
"step": 1120
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 3.35,
|
| 721 |
+
"learning_rate": 8.98598516075845e-06,
|
| 722 |
+
"loss": 0.667,
|
| 723 |
+
"step": 1130
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 3.38,
|
| 727 |
+
"learning_rate": 8.573784006595219e-06,
|
| 728 |
+
"loss": 0.715,
|
| 729 |
+
"step": 1140
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 3.41,
|
| 733 |
+
"learning_rate": 8.161582852431987e-06,
|
| 734 |
+
"loss": 0.6593,
|
| 735 |
+
"step": 1150
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 3.44,
|
| 739 |
+
"learning_rate": 7.749381698268756e-06,
|
| 740 |
+
"loss": 0.6886,
|
| 741 |
+
"step": 1160
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 3.47,
|
| 745 |
+
"learning_rate": 7.337180544105524e-06,
|
| 746 |
+
"loss": 0.712,
|
| 747 |
+
"step": 1170
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 3.5,
|
| 751 |
+
"learning_rate": 6.924979389942292e-06,
|
| 752 |
+
"loss": 0.752,
|
| 753 |
+
"step": 1180
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 3.53,
|
| 757 |
+
"learning_rate": 6.51277823577906e-06,
|
| 758 |
+
"loss": 0.6274,
|
| 759 |
+
"step": 1190
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 3.56,
|
| 763 |
+
"learning_rate": 6.100577081615829e-06,
|
| 764 |
+
"loss": 0.698,
|
| 765 |
+
"step": 1200
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 3.59,
|
| 769 |
+
"learning_rate": 5.688375927452598e-06,
|
| 770 |
+
"loss": 0.7475,
|
| 771 |
+
"step": 1210
|
| 772 |
+
},
|
| 773 |
+
{
|
| 774 |
+
"epoch": 3.61,
|
| 775 |
+
"learning_rate": 5.276174773289365e-06,
|
| 776 |
+
"loss": 0.7261,
|
| 777 |
+
"step": 1220
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 3.64,
|
| 781 |
+
"learning_rate": 4.863973619126134e-06,
|
| 782 |
+
"loss": 0.6776,
|
| 783 |
+
"step": 1230
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 3.67,
|
| 787 |
+
"learning_rate": 4.451772464962902e-06,
|
| 788 |
+
"loss": 0.6548,
|
| 789 |
+
"step": 1240
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 3.7,
|
| 793 |
+
"learning_rate": 4.03957131079967e-06,
|
| 794 |
+
"loss": 0.6526,
|
| 795 |
+
"step": 1250
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 3.73,
|
| 799 |
+
"learning_rate": 3.6273701566364385e-06,
|
| 800 |
+
"loss": 0.6432,
|
| 801 |
+
"step": 1260
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 3.76,
|
| 805 |
+
"learning_rate": 3.215169002473207e-06,
|
| 806 |
+
"loss": 0.6769,
|
| 807 |
+
"step": 1270
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 3.79,
|
| 811 |
+
"learning_rate": 2.8029678483099755e-06,
|
| 812 |
+
"loss": 0.6966,
|
| 813 |
+
"step": 1280
|
| 814 |
+
},
|
| 815 |
+
{
|
| 816 |
+
"epoch": 3.82,
|
| 817 |
+
"learning_rate": 2.390766694146744e-06,
|
| 818 |
+
"loss": 0.662,
|
| 819 |
+
"step": 1290
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 3.85,
|
| 823 |
+
"learning_rate": 1.978565539983512e-06,
|
| 824 |
+
"loss": 0.6816,
|
| 825 |
+
"step": 1300
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 3.88,
|
| 829 |
+
"learning_rate": 1.5663643858202803e-06,
|
| 830 |
+
"loss": 0.6373,
|
| 831 |
+
"step": 1310
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 3.91,
|
| 835 |
+
"learning_rate": 1.1541632316570488e-06,
|
| 836 |
+
"loss": 0.6328,
|
| 837 |
+
"step": 1320
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 3.94,
|
| 841 |
+
"learning_rate": 7.419620774938171e-07,
|
| 842 |
+
"loss": 0.6925,
|
| 843 |
+
"step": 1330
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 3.97,
|
| 847 |
+
"learning_rate": 3.2976092333058533e-07,
|
| 848 |
+
"loss": 0.7272,
|
| 849 |
+
"step": 1340
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 3.99,
|
| 853 |
+
"eval_accuracy": 0.8974074074074074,
|
| 854 |
+
"eval_f1": 0.8910186753180345,
|
| 855 |
+
"eval_loss": 0.3921002447605133,
|
| 856 |
+
"eval_precision": 0.8937527021895239,
|
| 857 |
+
"eval_recall": 0.8899884876686517,
|
| 858 |
+
"eval_runtime": 14.7611,
|
| 859 |
+
"eval_samples_per_second": 182.913,
|
| 860 |
+
"eval_steps_per_second": 11.449,
|
| 861 |
+
"step": 1348
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 3.99,
|
| 865 |
+
"step": 1348,
|
| 866 |
+
"total_flos": 1.8332979581807493e+18,
|
| 867 |
+
"train_loss": 1.1345372907485736,
|
| 868 |
+
"train_runtime": 1112.1938,
|
| 869 |
+
"train_samples_per_second": 77.684,
|
| 870 |
+
"train_steps_per_second": 1.212
|
| 871 |
+
}
|
| 872 |
+
],
|
| 873 |
+
"logging_steps": 10,
|
| 874 |
+
"max_steps": 1348,
|
| 875 |
+
"num_train_epochs": 4,
|
| 876 |
+
"save_steps": 500,
|
| 877 |
+
"total_flos": 1.8332979581807493e+18,
|
| 878 |
+
"trial_name": null,
|
| 879 |
+
"trial_params": null
|
| 880 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1730a086082e0549a90b9b37204d2544c558a655e046ca2bc64ddde10a035b4f
|
| 3 |
+
size 4600
|