End of training
Browse files- README.md +96 -0
- all_results.json +12 -0
- config.json +56 -0
- eval_results.json +8 -0
- model.safetensors +3 -0
- preprocessor_config.json +22 -0
- runs/Dec28_18-44-20_MacBook-Pro-de-Max-2.local/events.out.tfevents.1703785531.MacBook-Pro-de-Max-2.local.34768.0 +3 -0
- runs/Dec28_18-44-20_MacBook-Pro-de-Max-2.local/events.out.tfevents.1703786843.MacBook-Pro-de-Max-2.local.34768.1 +3 -0
- train_results.json +7 -0
- trainer_state.json +333 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,96 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: microsoft/swinv2-tiny-patch4-window8-256
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
datasets:
|
7 |
+
- imagefolder
|
8 |
+
metrics:
|
9 |
+
- accuracy
|
10 |
+
model-index:
|
11 |
+
- name: swinv2-tiny-patch4-window8-256-finetuned-gardner-icm-max
|
12 |
+
results:
|
13 |
+
- task:
|
14 |
+
name: Image Classification
|
15 |
+
type: image-classification
|
16 |
+
dataset:
|
17 |
+
name: imagefolder
|
18 |
+
type: imagefolder
|
19 |
+
config: default
|
20 |
+
split: train
|
21 |
+
args: default
|
22 |
+
metrics:
|
23 |
+
- name: Accuracy
|
24 |
+
type: accuracy
|
25 |
+
value: 0.6428571428571429
|
26 |
+
---
|
27 |
+
|
28 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
29 |
+
should probably proofread and complete it, then remove this comment. -->
|
30 |
+
|
31 |
+
# swinv2-tiny-patch4-window8-256-finetuned-gardner-icm-max
|
32 |
+
|
33 |
+
This model is a fine-tuned version of [microsoft/swinv2-tiny-patch4-window8-256](https://huggingface.co/microsoft/swinv2-tiny-patch4-window8-256) on the imagefolder dataset.
|
34 |
+
It achieves the following results on the evaluation set:
|
35 |
+
- Loss: 1.0741
|
36 |
+
- Accuracy: 0.6429
|
37 |
+
|
38 |
+
## Model description
|
39 |
+
|
40 |
+
More information needed
|
41 |
+
|
42 |
+
## Intended uses & limitations
|
43 |
+
|
44 |
+
More information needed
|
45 |
+
|
46 |
+
## Training and evaluation data
|
47 |
+
|
48 |
+
More information needed
|
49 |
+
|
50 |
+
## Training procedure
|
51 |
+
|
52 |
+
### Training hyperparameters
|
53 |
+
|
54 |
+
The following hyperparameters were used during training:
|
55 |
+
- learning_rate: 5e-05
|
56 |
+
- train_batch_size: 32
|
57 |
+
- eval_batch_size: 32
|
58 |
+
- seed: 42
|
59 |
+
- gradient_accumulation_steps: 4
|
60 |
+
- total_train_batch_size: 128
|
61 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
62 |
+
- lr_scheduler_type: linear
|
63 |
+
- lr_scheduler_warmup_ratio: 0.1
|
64 |
+
- num_epochs: 20
|
65 |
+
|
66 |
+
### Training results
|
67 |
+
|
68 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
69 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
70 |
+
| 1.0925 | 0.94 | 11 | 1.0631 | 0.7952 |
|
71 |
+
| 0.9552 | 1.96 | 23 | 0.6336 | 0.7952 |
|
72 |
+
| 0.6566 | 2.98 | 35 | 0.5356 | 0.7952 |
|
73 |
+
| 0.5686 | 4.0 | 47 | 0.5150 | 0.7952 |
|
74 |
+
| 0.5703 | 4.94 | 58 | 0.5129 | 0.7952 |
|
75 |
+
| 0.5726 | 5.96 | 70 | 0.5154 | 0.7952 |
|
76 |
+
| 0.5482 | 6.98 | 82 | 0.5142 | 0.7952 |
|
77 |
+
| 0.568 | 8.0 | 94 | 0.5109 | 0.7952 |
|
78 |
+
| 0.5245 | 8.94 | 105 | 0.5134 | 0.7952 |
|
79 |
+
| 0.5979 | 9.96 | 117 | 0.5238 | 0.7952 |
|
80 |
+
| 0.5442 | 10.98 | 129 | 0.5076 | 0.7952 |
|
81 |
+
| 0.545 | 12.0 | 141 | 0.5062 | 0.7952 |
|
82 |
+
| 0.5514 | 12.94 | 152 | 0.5013 | 0.7952 |
|
83 |
+
| 0.5377 | 13.96 | 164 | 0.5045 | 0.7952 |
|
84 |
+
| 0.5282 | 14.98 | 176 | 0.5038 | 0.7952 |
|
85 |
+
| 0.5389 | 16.0 | 188 | 0.4994 | 0.7952 |
|
86 |
+
| 0.5039 | 16.94 | 199 | 0.4996 | 0.7952 |
|
87 |
+
| 0.5348 | 17.96 | 211 | 0.4940 | 0.7952 |
|
88 |
+
| 0.5426 | 18.72 | 220 | 0.4947 | 0.7952 |
|
89 |
+
|
90 |
+
|
91 |
+
### Framework versions
|
92 |
+
|
93 |
+
- Transformers 4.36.2
|
94 |
+
- Pytorch 2.1.2
|
95 |
+
- Datasets 2.16.0
|
96 |
+
- Tokenizers 0.15.0
|
all_results.json
ADDED
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 18.72,
|
3 |
+
"eval_accuracy": 0.6428571428571429,
|
4 |
+
"eval_loss": 1.0741071701049805,
|
5 |
+
"eval_runtime": 4.5667,
|
6 |
+
"eval_samples_per_second": 52.116,
|
7 |
+
"eval_steps_per_second": 1.752,
|
8 |
+
"train_loss": 0.595783019065857,
|
9 |
+
"train_runtime": 1248.9487,
|
10 |
+
"train_samples_per_second": 23.796,
|
11 |
+
"train_steps_per_second": 0.176
|
12 |
+
}
|
config.json
ADDED
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "microsoft/swinv2-tiny-patch4-window8-256",
|
3 |
+
"architectures": [
|
4 |
+
"Swinv2ForImageClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.0,
|
7 |
+
"depths": [
|
8 |
+
2,
|
9 |
+
2,
|
10 |
+
6,
|
11 |
+
2
|
12 |
+
],
|
13 |
+
"drop_path_rate": 0.1,
|
14 |
+
"embed_dim": 96,
|
15 |
+
"encoder_stride": 32,
|
16 |
+
"hidden_act": "gelu",
|
17 |
+
"hidden_dropout_prob": 0.0,
|
18 |
+
"hidden_size": 768,
|
19 |
+
"id2label": {
|
20 |
+
"0": "0",
|
21 |
+
"1": "1",
|
22 |
+
"2": "2"
|
23 |
+
},
|
24 |
+
"image_size": 256,
|
25 |
+
"initializer_range": 0.02,
|
26 |
+
"label2id": {
|
27 |
+
"0": 0,
|
28 |
+
"1": 1,
|
29 |
+
"2": 2
|
30 |
+
},
|
31 |
+
"layer_norm_eps": 1e-05,
|
32 |
+
"mlp_ratio": 4.0,
|
33 |
+
"model_type": "swinv2",
|
34 |
+
"num_channels": 3,
|
35 |
+
"num_heads": [
|
36 |
+
3,
|
37 |
+
6,
|
38 |
+
12,
|
39 |
+
24
|
40 |
+
],
|
41 |
+
"num_layers": 4,
|
42 |
+
"patch_size": 4,
|
43 |
+
"path_norm": true,
|
44 |
+
"pretrained_window_sizes": [
|
45 |
+
0,
|
46 |
+
0,
|
47 |
+
0,
|
48 |
+
0
|
49 |
+
],
|
50 |
+
"problem_type": "single_label_classification",
|
51 |
+
"qkv_bias": true,
|
52 |
+
"torch_dtype": "float32",
|
53 |
+
"transformers_version": "4.36.2",
|
54 |
+
"use_absolute_embeddings": false,
|
55 |
+
"window_size": 8
|
56 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 18.72,
|
3 |
+
"eval_accuracy": 0.6428571428571429,
|
4 |
+
"eval_loss": 1.0741071701049805,
|
5 |
+
"eval_runtime": 4.5667,
|
6 |
+
"eval_samples_per_second": 52.116,
|
7 |
+
"eval_steps_per_second": 1.752
|
8 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:65be09d36da40c6d8dfe6ffbb404e735f5bb14937d77df09ec924f331ce7c977
|
3 |
+
size 110353212
|
preprocessor_config.json
ADDED
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"do_normalize": true,
|
3 |
+
"do_rescale": true,
|
4 |
+
"do_resize": true,
|
5 |
+
"image_mean": [
|
6 |
+
0.485,
|
7 |
+
0.456,
|
8 |
+
0.406
|
9 |
+
],
|
10 |
+
"image_processor_type": "ViTImageProcessor",
|
11 |
+
"image_std": [
|
12 |
+
0.229,
|
13 |
+
0.224,
|
14 |
+
0.225
|
15 |
+
],
|
16 |
+
"resample": 3,
|
17 |
+
"rescale_factor": 0.00392156862745098,
|
18 |
+
"size": {
|
19 |
+
"height": 256,
|
20 |
+
"width": 256
|
21 |
+
}
|
22 |
+
}
|
runs/Dec28_18-44-20_MacBook-Pro-de-Max-2.local/events.out.tfevents.1703785531.MacBook-Pro-de-Max-2.local.34768.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0aa379bd3a1e87cf0c81a8e1f4a21b8c1a7218b943676e2bbe60f853d919ec61
|
3 |
+
size 14628
|
runs/Dec28_18-44-20_MacBook-Pro-de-Max-2.local/events.out.tfevents.1703786843.MacBook-Pro-de-Max-2.local.34768.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:90d4c26f538e46a898ce2b0b614a742811d2aa098be294e09a4d8ee16576d145
|
3 |
+
size 734
|
train_results.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 18.72,
|
3 |
+
"train_loss": 0.595783019065857,
|
4 |
+
"train_runtime": 1248.9487,
|
5 |
+
"train_samples_per_second": 23.796,
|
6 |
+
"train_steps_per_second": 0.176
|
7 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,333 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.7951807228915663,
|
3 |
+
"best_model_checkpoint": "swinv2-tiny-patch4-window8-256-finetuned-gardner-icm-max/checkpoint-11",
|
4 |
+
"epoch": 18.72340425531915,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 220,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.85,
|
13 |
+
"learning_rate": 2.272727272727273e-05,
|
14 |
+
"loss": 1.0925,
|
15 |
+
"step": 10
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 0.94,
|
19 |
+
"eval_accuracy": 0.7951807228915663,
|
20 |
+
"eval_loss": 1.0630700588226318,
|
21 |
+
"eval_runtime": 8.4566,
|
22 |
+
"eval_samples_per_second": 19.63,
|
23 |
+
"eval_steps_per_second": 0.71,
|
24 |
+
"step": 11
|
25 |
+
},
|
26 |
+
{
|
27 |
+
"epoch": 1.7,
|
28 |
+
"learning_rate": 4.545454545454546e-05,
|
29 |
+
"loss": 0.9552,
|
30 |
+
"step": 20
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 1.96,
|
34 |
+
"eval_accuracy": 0.7951807228915663,
|
35 |
+
"eval_loss": 0.633553683757782,
|
36 |
+
"eval_runtime": 2.9014,
|
37 |
+
"eval_samples_per_second": 57.213,
|
38 |
+
"eval_steps_per_second": 2.068,
|
39 |
+
"step": 23
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 2.55,
|
43 |
+
"learning_rate": 4.797979797979798e-05,
|
44 |
+
"loss": 0.6566,
|
45 |
+
"step": 30
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 2.98,
|
49 |
+
"eval_accuracy": 0.7951807228915663,
|
50 |
+
"eval_loss": 0.5356065630912781,
|
51 |
+
"eval_runtime": 2.9308,
|
52 |
+
"eval_samples_per_second": 56.639,
|
53 |
+
"eval_steps_per_second": 2.047,
|
54 |
+
"step": 35
|
55 |
+
},
|
56 |
+
{
|
57 |
+
"epoch": 3.4,
|
58 |
+
"learning_rate": 4.545454545454546e-05,
|
59 |
+
"loss": 0.5686,
|
60 |
+
"step": 40
|
61 |
+
},
|
62 |
+
{
|
63 |
+
"epoch": 4.0,
|
64 |
+
"eval_accuracy": 0.7951807228915663,
|
65 |
+
"eval_loss": 0.5150089263916016,
|
66 |
+
"eval_runtime": 3.1556,
|
67 |
+
"eval_samples_per_second": 52.605,
|
68 |
+
"eval_steps_per_second": 1.901,
|
69 |
+
"step": 47
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 4.26,
|
73 |
+
"learning_rate": 4.292929292929293e-05,
|
74 |
+
"loss": 0.5703,
|
75 |
+
"step": 50
|
76 |
+
},
|
77 |
+
{
|
78 |
+
"epoch": 4.94,
|
79 |
+
"eval_accuracy": 0.7951807228915663,
|
80 |
+
"eval_loss": 0.5129297971725464,
|
81 |
+
"eval_runtime": 2.9359,
|
82 |
+
"eval_samples_per_second": 56.542,
|
83 |
+
"eval_steps_per_second": 2.044,
|
84 |
+
"step": 58
|
85 |
+
},
|
86 |
+
{
|
87 |
+
"epoch": 5.11,
|
88 |
+
"learning_rate": 4.0404040404040405e-05,
|
89 |
+
"loss": 0.5361,
|
90 |
+
"step": 60
|
91 |
+
},
|
92 |
+
{
|
93 |
+
"epoch": 5.96,
|
94 |
+
"learning_rate": 3.787878787878788e-05,
|
95 |
+
"loss": 0.5726,
|
96 |
+
"step": 70
|
97 |
+
},
|
98 |
+
{
|
99 |
+
"epoch": 5.96,
|
100 |
+
"eval_accuracy": 0.7951807228915663,
|
101 |
+
"eval_loss": 0.5154421925544739,
|
102 |
+
"eval_runtime": 2.9132,
|
103 |
+
"eval_samples_per_second": 56.982,
|
104 |
+
"eval_steps_per_second": 2.06,
|
105 |
+
"step": 70
|
106 |
+
},
|
107 |
+
{
|
108 |
+
"epoch": 6.81,
|
109 |
+
"learning_rate": 3.535353535353535e-05,
|
110 |
+
"loss": 0.5482,
|
111 |
+
"step": 80
|
112 |
+
},
|
113 |
+
{
|
114 |
+
"epoch": 6.98,
|
115 |
+
"eval_accuracy": 0.7951807228915663,
|
116 |
+
"eval_loss": 0.5141979455947876,
|
117 |
+
"eval_runtime": 2.9168,
|
118 |
+
"eval_samples_per_second": 56.912,
|
119 |
+
"eval_steps_per_second": 2.057,
|
120 |
+
"step": 82
|
121 |
+
},
|
122 |
+
{
|
123 |
+
"epoch": 7.66,
|
124 |
+
"learning_rate": 3.282828282828283e-05,
|
125 |
+
"loss": 0.568,
|
126 |
+
"step": 90
|
127 |
+
},
|
128 |
+
{
|
129 |
+
"epoch": 8.0,
|
130 |
+
"eval_accuracy": 0.7951807228915663,
|
131 |
+
"eval_loss": 0.5108516812324524,
|
132 |
+
"eval_runtime": 2.9147,
|
133 |
+
"eval_samples_per_second": 56.952,
|
134 |
+
"eval_steps_per_second": 2.059,
|
135 |
+
"step": 94
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 8.51,
|
139 |
+
"learning_rate": 3.0303030303030306e-05,
|
140 |
+
"loss": 0.5245,
|
141 |
+
"step": 100
|
142 |
+
},
|
143 |
+
{
|
144 |
+
"epoch": 8.94,
|
145 |
+
"eval_accuracy": 0.7951807228915663,
|
146 |
+
"eval_loss": 0.5134214162826538,
|
147 |
+
"eval_runtime": 2.9007,
|
148 |
+
"eval_samples_per_second": 57.227,
|
149 |
+
"eval_steps_per_second": 2.068,
|
150 |
+
"step": 105
|
151 |
+
},
|
152 |
+
{
|
153 |
+
"epoch": 9.36,
|
154 |
+
"learning_rate": 2.777777777777778e-05,
|
155 |
+
"loss": 0.5979,
|
156 |
+
"step": 110
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 9.96,
|
160 |
+
"eval_accuracy": 0.7951807228915663,
|
161 |
+
"eval_loss": 0.5237765908241272,
|
162 |
+
"eval_runtime": 2.9436,
|
163 |
+
"eval_samples_per_second": 56.394,
|
164 |
+
"eval_steps_per_second": 2.038,
|
165 |
+
"step": 117
|
166 |
+
},
|
167 |
+
{
|
168 |
+
"epoch": 10.21,
|
169 |
+
"learning_rate": 2.5252525252525256e-05,
|
170 |
+
"loss": 0.5442,
|
171 |
+
"step": 120
|
172 |
+
},
|
173 |
+
{
|
174 |
+
"epoch": 10.98,
|
175 |
+
"eval_accuracy": 0.7951807228915663,
|
176 |
+
"eval_loss": 0.507612943649292,
|
177 |
+
"eval_runtime": 2.9562,
|
178 |
+
"eval_samples_per_second": 56.154,
|
179 |
+
"eval_steps_per_second": 2.03,
|
180 |
+
"step": 129
|
181 |
+
},
|
182 |
+
{
|
183 |
+
"epoch": 11.06,
|
184 |
+
"learning_rate": 2.272727272727273e-05,
|
185 |
+
"loss": 0.5451,
|
186 |
+
"step": 130
|
187 |
+
},
|
188 |
+
{
|
189 |
+
"epoch": 11.91,
|
190 |
+
"learning_rate": 2.0202020202020203e-05,
|
191 |
+
"loss": 0.545,
|
192 |
+
"step": 140
|
193 |
+
},
|
194 |
+
{
|
195 |
+
"epoch": 12.0,
|
196 |
+
"eval_accuracy": 0.7951807228915663,
|
197 |
+
"eval_loss": 0.5061953067779541,
|
198 |
+
"eval_runtime": 2.9818,
|
199 |
+
"eval_samples_per_second": 55.671,
|
200 |
+
"eval_steps_per_second": 2.012,
|
201 |
+
"step": 141
|
202 |
+
},
|
203 |
+
{
|
204 |
+
"epoch": 12.77,
|
205 |
+
"learning_rate": 1.7676767676767676e-05,
|
206 |
+
"loss": 0.5514,
|
207 |
+
"step": 150
|
208 |
+
},
|
209 |
+
{
|
210 |
+
"epoch": 12.94,
|
211 |
+
"eval_accuracy": 0.7951807228915663,
|
212 |
+
"eval_loss": 0.5012802481651306,
|
213 |
+
"eval_runtime": 3.0403,
|
214 |
+
"eval_samples_per_second": 54.599,
|
215 |
+
"eval_steps_per_second": 1.973,
|
216 |
+
"step": 152
|
217 |
+
},
|
218 |
+
{
|
219 |
+
"epoch": 13.62,
|
220 |
+
"learning_rate": 1.5151515151515153e-05,
|
221 |
+
"loss": 0.5377,
|
222 |
+
"step": 160
|
223 |
+
},
|
224 |
+
{
|
225 |
+
"epoch": 13.96,
|
226 |
+
"eval_accuracy": 0.7951807228915663,
|
227 |
+
"eval_loss": 0.5044662356376648,
|
228 |
+
"eval_runtime": 3.0226,
|
229 |
+
"eval_samples_per_second": 54.919,
|
230 |
+
"eval_steps_per_second": 1.985,
|
231 |
+
"step": 164
|
232 |
+
},
|
233 |
+
{
|
234 |
+
"epoch": 14.47,
|
235 |
+
"learning_rate": 1.2626262626262628e-05,
|
236 |
+
"loss": 0.5282,
|
237 |
+
"step": 170
|
238 |
+
},
|
239 |
+
{
|
240 |
+
"epoch": 14.98,
|
241 |
+
"eval_accuracy": 0.7951807228915663,
|
242 |
+
"eval_loss": 0.5037835836410522,
|
243 |
+
"eval_runtime": 2.9367,
|
244 |
+
"eval_samples_per_second": 56.525,
|
245 |
+
"eval_steps_per_second": 2.043,
|
246 |
+
"step": 176
|
247 |
+
},
|
248 |
+
{
|
249 |
+
"epoch": 15.32,
|
250 |
+
"learning_rate": 1.0101010101010101e-05,
|
251 |
+
"loss": 0.5389,
|
252 |
+
"step": 180
|
253 |
+
},
|
254 |
+
{
|
255 |
+
"epoch": 16.0,
|
256 |
+
"eval_accuracy": 0.7951807228915663,
|
257 |
+
"eval_loss": 0.4994117021560669,
|
258 |
+
"eval_runtime": 2.9413,
|
259 |
+
"eval_samples_per_second": 56.437,
|
260 |
+
"eval_steps_per_second": 2.04,
|
261 |
+
"step": 188
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 16.17,
|
265 |
+
"learning_rate": 7.5757575757575764e-06,
|
266 |
+
"loss": 0.5039,
|
267 |
+
"step": 190
|
268 |
+
},
|
269 |
+
{
|
270 |
+
"epoch": 16.94,
|
271 |
+
"eval_accuracy": 0.7951807228915663,
|
272 |
+
"eval_loss": 0.49963268637657166,
|
273 |
+
"eval_runtime": 3.0102,
|
274 |
+
"eval_samples_per_second": 55.146,
|
275 |
+
"eval_steps_per_second": 1.993,
|
276 |
+
"step": 199
|
277 |
+
},
|
278 |
+
{
|
279 |
+
"epoch": 17.02,
|
280 |
+
"learning_rate": 5.050505050505051e-06,
|
281 |
+
"loss": 0.5449,
|
282 |
+
"step": 200
|
283 |
+
},
|
284 |
+
{
|
285 |
+
"epoch": 17.87,
|
286 |
+
"learning_rate": 2.5252525252525253e-06,
|
287 |
+
"loss": 0.5348,
|
288 |
+
"step": 210
|
289 |
+
},
|
290 |
+
{
|
291 |
+
"epoch": 17.96,
|
292 |
+
"eval_accuracy": 0.7951807228915663,
|
293 |
+
"eval_loss": 0.493960976600647,
|
294 |
+
"eval_runtime": 2.9022,
|
295 |
+
"eval_samples_per_second": 57.197,
|
296 |
+
"eval_steps_per_second": 2.067,
|
297 |
+
"step": 211
|
298 |
+
},
|
299 |
+
{
|
300 |
+
"epoch": 18.72,
|
301 |
+
"learning_rate": 0.0,
|
302 |
+
"loss": 0.5426,
|
303 |
+
"step": 220
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 18.72,
|
307 |
+
"eval_accuracy": 0.7951807228915663,
|
308 |
+
"eval_loss": 0.49473580718040466,
|
309 |
+
"eval_runtime": 2.8726,
|
310 |
+
"eval_samples_per_second": 57.787,
|
311 |
+
"eval_steps_per_second": 2.089,
|
312 |
+
"step": 220
|
313 |
+
},
|
314 |
+
{
|
315 |
+
"epoch": 18.72,
|
316 |
+
"step": 220,
|
317 |
+
"total_flos": 9.056508197685166e+17,
|
318 |
+
"train_loss": 0.595783019065857,
|
319 |
+
"train_runtime": 1248.9487,
|
320 |
+
"train_samples_per_second": 23.796,
|
321 |
+
"train_steps_per_second": 0.176
|
322 |
+
}
|
323 |
+
],
|
324 |
+
"logging_steps": 10,
|
325 |
+
"max_steps": 220,
|
326 |
+
"num_input_tokens_seen": 0,
|
327 |
+
"num_train_epochs": 20,
|
328 |
+
"save_steps": 500,
|
329 |
+
"total_flos": 9.056508197685166e+17,
|
330 |
+
"train_batch_size": 32,
|
331 |
+
"trial_name": null,
|
332 |
+
"trial_params": null
|
333 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:81e9c804b177a239e1066ec42d5a893c7bd6e29d0f1ad2294063020d5d452657
|
3 |
+
size 4792
|