Commit
•
ecf467c
1
Parent(s):
9c74c3a
add model
Browse files- .gitignore +1 -0
- README.md +76 -0
- all_results.json +12 -0
- config.json +32 -0
- emissions.csv +2 -0
- eval_results.json +8 -0
- preprocessor_config.json +17 -0
- pytorch_model.bin +3 -0
- runs/Aug31_12-52-34_nate-gpu-2/1630414364.999114/events.out.tfevents.1630414364.nate-gpu-2.12898.1 +3 -0
- runs/Aug31_12-52-34_nate-gpu-2/events.out.tfevents.1630414364.nate-gpu-2.12898.0 +3 -0
- runs/Aug31_12-52-34_nate-gpu-2/events.out.tfevents.1630414491.nate-gpu-2.12898.2 +3 -0
- train_results.json +7 -0
- trainer_state.json +460 -0
- training_args.bin +3 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
README.md
ADDED
@@ -0,0 +1,76 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
datasets:
|
6 |
+
- beans
|
7 |
+
metrics:
|
8 |
+
- accuracy
|
9 |
+
model-index:
|
10 |
+
- name: vit-base-beans
|
11 |
+
results:
|
12 |
+
- task:
|
13 |
+
name: Image Classification
|
14 |
+
type: image-classification
|
15 |
+
dataset:
|
16 |
+
name: beans
|
17 |
+
type: beans
|
18 |
+
args: default
|
19 |
+
metrics:
|
20 |
+
- name: Accuracy
|
21 |
+
type: accuracy
|
22 |
+
value: 0.9774436090225563
|
23 |
+
---
|
24 |
+
|
25 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
26 |
+
should probably proofread and complete it, then remove this comment. -->
|
27 |
+
|
28 |
+
# vit-base-beans
|
29 |
+
|
30 |
+
This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the beans dataset.
|
31 |
+
It achieves the following results on the evaluation set:
|
32 |
+
- Loss: 0.0942
|
33 |
+
- Accuracy: 0.9774
|
34 |
+
|
35 |
+
## Model description
|
36 |
+
|
37 |
+
More information needed
|
38 |
+
|
39 |
+
## Intended uses & limitations
|
40 |
+
|
41 |
+
More information needed
|
42 |
+
|
43 |
+
## Training and evaluation data
|
44 |
+
|
45 |
+
More information needed
|
46 |
+
|
47 |
+
## Training procedure
|
48 |
+
|
49 |
+
### Training hyperparameters
|
50 |
+
|
51 |
+
The following hyperparameters were used during training:
|
52 |
+
- learning_rate: 2e-05
|
53 |
+
- train_batch_size: 8
|
54 |
+
- eval_batch_size: 8
|
55 |
+
- seed: 1337
|
56 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
57 |
+
- lr_scheduler_type: linear
|
58 |
+
- num_epochs: 5.0
|
59 |
+
|
60 |
+
### Training results
|
61 |
+
|
62 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
63 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
64 |
+
| 0.2809 | 1.0 | 130 | 0.2287 | 0.9699 |
|
65 |
+
| 0.1097 | 2.0 | 260 | 0.1676 | 0.9624 |
|
66 |
+
| 0.1027 | 3.0 | 390 | 0.0942 | 0.9774 |
|
67 |
+
| 0.0923 | 4.0 | 520 | 0.1104 | 0.9699 |
|
68 |
+
| 0.1726 | 5.0 | 650 | 0.1030 | 0.9699 |
|
69 |
+
|
70 |
+
|
71 |
+
### Framework versions
|
72 |
+
|
73 |
+
- Transformers 4.10.0.dev0
|
74 |
+
- Pytorch 1.9.0+cu102
|
75 |
+
- Datasets 1.11.1.dev0
|
76 |
+
- Tokenizers 0.10.3
|
all_results.json
ADDED
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 5.0,
|
3 |
+
"eval_accuracy": 0.9774436090225563,
|
4 |
+
"eval_loss": 0.09423530101776123,
|
5 |
+
"eval_runtime": 1.7062,
|
6 |
+
"eval_samples_per_second": 77.951,
|
7 |
+
"eval_steps_per_second": 9.964,
|
8 |
+
"train_loss": 0.23702784006412211,
|
9 |
+
"train_runtime": 124.7505,
|
10 |
+
"train_samples_per_second": 41.443,
|
11 |
+
"train_steps_per_second": 5.21
|
12 |
+
}
|
config.json
ADDED
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "google/vit-base-patch16-224-in21k",
|
3 |
+
"architectures": [
|
4 |
+
"ViTForImageClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.0,
|
7 |
+
"finetuning_task": "image-classification",
|
8 |
+
"hidden_act": "gelu",
|
9 |
+
"hidden_dropout_prob": 0.0,
|
10 |
+
"hidden_size": 768,
|
11 |
+
"id2label": {
|
12 |
+
"0": "angular_leaf_spot",
|
13 |
+
"1": "bean_rust",
|
14 |
+
"2": "healthy"
|
15 |
+
},
|
16 |
+
"image_size": 224,
|
17 |
+
"initializer_range": 0.02,
|
18 |
+
"intermediate_size": 3072,
|
19 |
+
"label2id": {
|
20 |
+
"angular_leaf_spot": "0",
|
21 |
+
"bean_rust": "1",
|
22 |
+
"healthy": "2"
|
23 |
+
},
|
24 |
+
"layer_norm_eps": 1e-12,
|
25 |
+
"model_type": "vit",
|
26 |
+
"num_attention_heads": 12,
|
27 |
+
"num_channels": 3,
|
28 |
+
"num_hidden_layers": 12,
|
29 |
+
"patch_size": 16,
|
30 |
+
"torch_dtype": "float32",
|
31 |
+
"transformers_version": "4.10.0.dev0"
|
32 |
+
}
|
emissions.csv
ADDED
@@ -0,0 +1,2 @@
|
|
|
|
|
|
|
1 |
+
timestamp,experiment_id,project_name,duration,emissions,energy_consumed,country_name,country_iso_code,region,on_cloud,cloud_provider,cloud_region
|
2 |
+
2021-08-31T12:54:49,a4449492-67ee-4738-a85d-5ac4861bcb29,codecarbon,124.76043105125427,0.005462426324374648,0.009645817277723201,USA,USA,Iowa,Y,gcp,us-central1
|
eval_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 5.0,
|
3 |
+
"eval_accuracy": 0.9774436090225563,
|
4 |
+
"eval_loss": 0.09423530101776123,
|
5 |
+
"eval_runtime": 1.7062,
|
6 |
+
"eval_samples_per_second": 77.951,
|
7 |
+
"eval_steps_per_second": 9.964
|
8 |
+
}
|
preprocessor_config.json
ADDED
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"do_normalize": true,
|
3 |
+
"do_resize": true,
|
4 |
+
"feature_extractor_type": "ViTFeatureExtractor",
|
5 |
+
"image_mean": [
|
6 |
+
0.5,
|
7 |
+
0.5,
|
8 |
+
0.5
|
9 |
+
],
|
10 |
+
"image_std": [
|
11 |
+
0.5,
|
12 |
+
0.5,
|
13 |
+
0.5
|
14 |
+
],
|
15 |
+
"resample": 2,
|
16 |
+
"size": 224
|
17 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fc443b145fcc3a09cf07eb28b94e9a989ec3f0e8f7255e1fa08c0953ed4bae91
|
3 |
+
size 343282929
|
runs/Aug31_12-52-34_nate-gpu-2/1630414364.999114/events.out.tfevents.1630414364.nate-gpu-2.12898.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0518be0bbb187145974df13bed88d402be8eb609cabf1527c4a09df057b7a1ef
|
3 |
+
size 4216
|
runs/Aug31_12-52-34_nate-gpu-2/events.out.tfevents.1630414364.nate-gpu-2.12898.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d838680fe881c3f25f235ece74982927b314f580b29d1224c44a3df042bd64b4
|
3 |
+
size 15187
|
runs/Aug31_12-52-34_nate-gpu-2/events.out.tfevents.1630414491.nate-gpu-2.12898.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8aaee3d3e039b4a6e840ad05b41b11c749918c7925d1c19fa4524e0423d179d7
|
3 |
+
size 363
|
train_results.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 5.0,
|
3 |
+
"train_loss": 0.23702784006412211,
|
4 |
+
"train_runtime": 124.7505,
|
5 |
+
"train_samples_per_second": 41.443,
|
6 |
+
"train_steps_per_second": 5.21
|
7 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,460 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.09423530101776123,
|
3 |
+
"best_model_checkpoint": "./beans_outputs/checkpoint-390",
|
4 |
+
"epoch": 5.0,
|
5 |
+
"global_step": 650,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.08,
|
12 |
+
"learning_rate": 1.9692307692307696e-05,
|
13 |
+
"loss": 1.0801,
|
14 |
+
"step": 10
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.15,
|
18 |
+
"learning_rate": 1.9384615384615386e-05,
|
19 |
+
"loss": 1.0047,
|
20 |
+
"step": 20
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.23,
|
24 |
+
"learning_rate": 1.907692307692308e-05,
|
25 |
+
"loss": 0.9106,
|
26 |
+
"step": 30
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 0.31,
|
30 |
+
"learning_rate": 1.876923076923077e-05,
|
31 |
+
"loss": 0.7891,
|
32 |
+
"step": 40
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 0.38,
|
36 |
+
"learning_rate": 1.8461538461538465e-05,
|
37 |
+
"loss": 0.7158,
|
38 |
+
"step": 50
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 0.46,
|
42 |
+
"learning_rate": 1.8153846153846155e-05,
|
43 |
+
"loss": 0.6401,
|
44 |
+
"step": 60
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.54,
|
48 |
+
"learning_rate": 1.784615384615385e-05,
|
49 |
+
"loss": 0.5135,
|
50 |
+
"step": 70
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 0.62,
|
54 |
+
"learning_rate": 1.753846153846154e-05,
|
55 |
+
"loss": 0.4501,
|
56 |
+
"step": 80
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 0.69,
|
60 |
+
"learning_rate": 1.7230769230769234e-05,
|
61 |
+
"loss": 0.4603,
|
62 |
+
"step": 90
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 0.77,
|
66 |
+
"learning_rate": 1.6923076923076924e-05,
|
67 |
+
"loss": 0.2978,
|
68 |
+
"step": 100
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 0.85,
|
72 |
+
"learning_rate": 1.6615384615384618e-05,
|
73 |
+
"loss": 0.3313,
|
74 |
+
"step": 110
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 0.92,
|
78 |
+
"learning_rate": 1.630769230769231e-05,
|
79 |
+
"loss": 0.3273,
|
80 |
+
"step": 120
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 1.0,
|
84 |
+
"learning_rate": 1.6000000000000003e-05,
|
85 |
+
"loss": 0.2809,
|
86 |
+
"step": 130
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 1.0,
|
90 |
+
"eval_accuracy": 0.9699248120300752,
|
91 |
+
"eval_loss": 0.2287006974220276,
|
92 |
+
"eval_runtime": 1.6228,
|
93 |
+
"eval_samples_per_second": 81.958,
|
94 |
+
"eval_steps_per_second": 10.476,
|
95 |
+
"step": 130
|
96 |
+
},
|
97 |
+
{
|
98 |
+
"epoch": 1.08,
|
99 |
+
"learning_rate": 1.5692307692307693e-05,
|
100 |
+
"loss": 0.2246,
|
101 |
+
"step": 140
|
102 |
+
},
|
103 |
+
{
|
104 |
+
"epoch": 1.15,
|
105 |
+
"learning_rate": 1.5384615384615387e-05,
|
106 |
+
"loss": 0.184,
|
107 |
+
"step": 150
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 1.23,
|
111 |
+
"learning_rate": 1.5076923076923078e-05,
|
112 |
+
"loss": 0.2474,
|
113 |
+
"step": 160
|
114 |
+
},
|
115 |
+
{
|
116 |
+
"epoch": 1.31,
|
117 |
+
"learning_rate": 1.4769230769230772e-05,
|
118 |
+
"loss": 0.2246,
|
119 |
+
"step": 170
|
120 |
+
},
|
121 |
+
{
|
122 |
+
"epoch": 1.38,
|
123 |
+
"learning_rate": 1.4461538461538462e-05,
|
124 |
+
"loss": 0.1846,
|
125 |
+
"step": 180
|
126 |
+
},
|
127 |
+
{
|
128 |
+
"epoch": 1.46,
|
129 |
+
"learning_rate": 1.4153846153846156e-05,
|
130 |
+
"loss": 0.2743,
|
131 |
+
"step": 190
|
132 |
+
},
|
133 |
+
{
|
134 |
+
"epoch": 1.54,
|
135 |
+
"learning_rate": 1.3846153846153847e-05,
|
136 |
+
"loss": 0.1205,
|
137 |
+
"step": 200
|
138 |
+
},
|
139 |
+
{
|
140 |
+
"epoch": 1.62,
|
141 |
+
"learning_rate": 1.353846153846154e-05,
|
142 |
+
"loss": 0.249,
|
143 |
+
"step": 210
|
144 |
+
},
|
145 |
+
{
|
146 |
+
"epoch": 1.69,
|
147 |
+
"learning_rate": 1.3230769230769231e-05,
|
148 |
+
"loss": 0.1794,
|
149 |
+
"step": 220
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 1.77,
|
153 |
+
"learning_rate": 1.2923076923076925e-05,
|
154 |
+
"loss": 0.0964,
|
155 |
+
"step": 230
|
156 |
+
},
|
157 |
+
{
|
158 |
+
"epoch": 1.85,
|
159 |
+
"learning_rate": 1.2615384615384616e-05,
|
160 |
+
"loss": 0.2207,
|
161 |
+
"step": 240
|
162 |
+
},
|
163 |
+
{
|
164 |
+
"epoch": 1.92,
|
165 |
+
"learning_rate": 1.230769230769231e-05,
|
166 |
+
"loss": 0.167,
|
167 |
+
"step": 250
|
168 |
+
},
|
169 |
+
{
|
170 |
+
"epoch": 2.0,
|
171 |
+
"learning_rate": 1.2e-05,
|
172 |
+
"loss": 0.1097,
|
173 |
+
"step": 260
|
174 |
+
},
|
175 |
+
{
|
176 |
+
"epoch": 2.0,
|
177 |
+
"eval_accuracy": 0.9624060150375939,
|
178 |
+
"eval_loss": 0.1675739735364914,
|
179 |
+
"eval_runtime": 1.6333,
|
180 |
+
"eval_samples_per_second": 81.431,
|
181 |
+
"eval_steps_per_second": 10.408,
|
182 |
+
"step": 260
|
183 |
+
},
|
184 |
+
{
|
185 |
+
"epoch": 2.08,
|
186 |
+
"learning_rate": 1.1692307692307694e-05,
|
187 |
+
"loss": 0.1882,
|
188 |
+
"step": 270
|
189 |
+
},
|
190 |
+
{
|
191 |
+
"epoch": 2.15,
|
192 |
+
"learning_rate": 1.1384615384615385e-05,
|
193 |
+
"loss": 0.1248,
|
194 |
+
"step": 280
|
195 |
+
},
|
196 |
+
{
|
197 |
+
"epoch": 2.23,
|
198 |
+
"learning_rate": 1.1076923076923079e-05,
|
199 |
+
"loss": 0.1261,
|
200 |
+
"step": 290
|
201 |
+
},
|
202 |
+
{
|
203 |
+
"epoch": 2.31,
|
204 |
+
"learning_rate": 1.076923076923077e-05,
|
205 |
+
"loss": 0.1816,
|
206 |
+
"step": 300
|
207 |
+
},
|
208 |
+
{
|
209 |
+
"epoch": 2.38,
|
210 |
+
"learning_rate": 1.0461538461538463e-05,
|
211 |
+
"loss": 0.1997,
|
212 |
+
"step": 310
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 2.46,
|
216 |
+
"learning_rate": 1.0153846153846154e-05,
|
217 |
+
"loss": 0.0846,
|
218 |
+
"step": 320
|
219 |
+
},
|
220 |
+
{
|
221 |
+
"epoch": 2.54,
|
222 |
+
"learning_rate": 9.846153846153848e-06,
|
223 |
+
"loss": 0.2028,
|
224 |
+
"step": 330
|
225 |
+
},
|
226 |
+
{
|
227 |
+
"epoch": 2.62,
|
228 |
+
"learning_rate": 9.53846153846154e-06,
|
229 |
+
"loss": 0.2454,
|
230 |
+
"step": 340
|
231 |
+
},
|
232 |
+
{
|
233 |
+
"epoch": 2.69,
|
234 |
+
"learning_rate": 9.230769230769232e-06,
|
235 |
+
"loss": 0.1636,
|
236 |
+
"step": 350
|
237 |
+
},
|
238 |
+
{
|
239 |
+
"epoch": 2.77,
|
240 |
+
"learning_rate": 8.923076923076925e-06,
|
241 |
+
"loss": 0.2061,
|
242 |
+
"step": 360
|
243 |
+
},
|
244 |
+
{
|
245 |
+
"epoch": 2.85,
|
246 |
+
"learning_rate": 8.615384615384617e-06,
|
247 |
+
"loss": 0.163,
|
248 |
+
"step": 370
|
249 |
+
},
|
250 |
+
{
|
251 |
+
"epoch": 2.92,
|
252 |
+
"learning_rate": 8.307692307692309e-06,
|
253 |
+
"loss": 0.0696,
|
254 |
+
"step": 380
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 3.0,
|
258 |
+
"learning_rate": 8.000000000000001e-06,
|
259 |
+
"loss": 0.1027,
|
260 |
+
"step": 390
|
261 |
+
},
|
262 |
+
{
|
263 |
+
"epoch": 3.0,
|
264 |
+
"eval_accuracy": 0.9774436090225563,
|
265 |
+
"eval_loss": 0.09423530101776123,
|
266 |
+
"eval_runtime": 1.6148,
|
267 |
+
"eval_samples_per_second": 82.363,
|
268 |
+
"eval_steps_per_second": 10.528,
|
269 |
+
"step": 390
|
270 |
+
},
|
271 |
+
{
|
272 |
+
"epoch": 3.08,
|
273 |
+
"learning_rate": 7.692307692307694e-06,
|
274 |
+
"loss": 0.1679,
|
275 |
+
"step": 400
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 3.15,
|
279 |
+
"learning_rate": 7.384615384615386e-06,
|
280 |
+
"loss": 0.1548,
|
281 |
+
"step": 410
|
282 |
+
},
|
283 |
+
{
|
284 |
+
"epoch": 3.23,
|
285 |
+
"learning_rate": 7.076923076923078e-06,
|
286 |
+
"loss": 0.1519,
|
287 |
+
"step": 420
|
288 |
+
},
|
289 |
+
{
|
290 |
+
"epoch": 3.31,
|
291 |
+
"learning_rate": 6.76923076923077e-06,
|
292 |
+
"loss": 0.0835,
|
293 |
+
"step": 430
|
294 |
+
},
|
295 |
+
{
|
296 |
+
"epoch": 3.38,
|
297 |
+
"learning_rate": 6.461538461538463e-06,
|
298 |
+
"loss": 0.2056,
|
299 |
+
"step": 440
|
300 |
+
},
|
301 |
+
{
|
302 |
+
"epoch": 3.46,
|
303 |
+
"learning_rate": 6.153846153846155e-06,
|
304 |
+
"loss": 0.1459,
|
305 |
+
"step": 450
|
306 |
+
},
|
307 |
+
{
|
308 |
+
"epoch": 3.54,
|
309 |
+
"learning_rate": 5.846153846153847e-06,
|
310 |
+
"loss": 0.1141,
|
311 |
+
"step": 460
|
312 |
+
},
|
313 |
+
{
|
314 |
+
"epoch": 3.62,
|
315 |
+
"learning_rate": 5.538461538461539e-06,
|
316 |
+
"loss": 0.0742,
|
317 |
+
"step": 470
|
318 |
+
},
|
319 |
+
{
|
320 |
+
"epoch": 3.69,
|
321 |
+
"learning_rate": 5.230769230769232e-06,
|
322 |
+
"loss": 0.1156,
|
323 |
+
"step": 480
|
324 |
+
},
|
325 |
+
{
|
326 |
+
"epoch": 3.77,
|
327 |
+
"learning_rate": 4.923076923076924e-06,
|
328 |
+
"loss": 0.1143,
|
329 |
+
"step": 490
|
330 |
+
},
|
331 |
+
{
|
332 |
+
"epoch": 3.85,
|
333 |
+
"learning_rate": 4.615384615384616e-06,
|
334 |
+
"loss": 0.0908,
|
335 |
+
"step": 500
|
336 |
+
},
|
337 |
+
{
|
338 |
+
"epoch": 3.92,
|
339 |
+
"learning_rate": 4.307692307692308e-06,
|
340 |
+
"loss": 0.0621,
|
341 |
+
"step": 510
|
342 |
+
},
|
343 |
+
{
|
344 |
+
"epoch": 4.0,
|
345 |
+
"learning_rate": 4.000000000000001e-06,
|
346 |
+
"loss": 0.0923,
|
347 |
+
"step": 520
|
348 |
+
},
|
349 |
+
{
|
350 |
+
"epoch": 4.0,
|
351 |
+
"eval_accuracy": 0.9699248120300752,
|
352 |
+
"eval_loss": 0.11044816672801971,
|
353 |
+
"eval_runtime": 1.6172,
|
354 |
+
"eval_samples_per_second": 82.239,
|
355 |
+
"eval_steps_per_second": 10.512,
|
356 |
+
"step": 520
|
357 |
+
},
|
358 |
+
{
|
359 |
+
"epoch": 4.08,
|
360 |
+
"learning_rate": 3.692307692307693e-06,
|
361 |
+
"loss": 0.1789,
|
362 |
+
"step": 530
|
363 |
+
},
|
364 |
+
{
|
365 |
+
"epoch": 4.15,
|
366 |
+
"learning_rate": 3.384615384615385e-06,
|
367 |
+
"loss": 0.1695,
|
368 |
+
"step": 540
|
369 |
+
},
|
370 |
+
{
|
371 |
+
"epoch": 4.23,
|
372 |
+
"learning_rate": 3.0769230769230774e-06,
|
373 |
+
"loss": 0.1273,
|
374 |
+
"step": 550
|
375 |
+
},
|
376 |
+
{
|
377 |
+
"epoch": 4.31,
|
378 |
+
"learning_rate": 2.7692307692307697e-06,
|
379 |
+
"loss": 0.0729,
|
380 |
+
"step": 560
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 4.38,
|
384 |
+
"learning_rate": 2.461538461538462e-06,
|
385 |
+
"loss": 0.0598,
|
386 |
+
"step": 570
|
387 |
+
},
|
388 |
+
{
|
389 |
+
"epoch": 4.46,
|
390 |
+
"learning_rate": 2.153846153846154e-06,
|
391 |
+
"loss": 0.0919,
|
392 |
+
"step": 580
|
393 |
+
},
|
394 |
+
{
|
395 |
+
"epoch": 4.54,
|
396 |
+
"learning_rate": 1.8461538461538465e-06,
|
397 |
+
"loss": 0.0685,
|
398 |
+
"step": 590
|
399 |
+
},
|
400 |
+
{
|
401 |
+
"epoch": 4.62,
|
402 |
+
"learning_rate": 1.5384615384615387e-06,
|
403 |
+
"loss": 0.088,
|
404 |
+
"step": 600
|
405 |
+
},
|
406 |
+
{
|
407 |
+
"epoch": 4.69,
|
408 |
+
"learning_rate": 1.230769230769231e-06,
|
409 |
+
"loss": 0.1753,
|
410 |
+
"step": 610
|
411 |
+
},
|
412 |
+
{
|
413 |
+
"epoch": 4.77,
|
414 |
+
"learning_rate": 9.230769230769232e-07,
|
415 |
+
"loss": 0.0791,
|
416 |
+
"step": 620
|
417 |
+
},
|
418 |
+
{
|
419 |
+
"epoch": 4.85,
|
420 |
+
"learning_rate": 6.153846153846155e-07,
|
421 |
+
"loss": 0.1131,
|
422 |
+
"step": 630
|
423 |
+
},
|
424 |
+
{
|
425 |
+
"epoch": 4.92,
|
426 |
+
"learning_rate": 3.0769230769230774e-07,
|
427 |
+
"loss": 0.0949,
|
428 |
+
"step": 640
|
429 |
+
},
|
430 |
+
{
|
431 |
+
"epoch": 5.0,
|
432 |
+
"learning_rate": 0.0,
|
433 |
+
"loss": 0.1726,
|
434 |
+
"step": 650
|
435 |
+
},
|
436 |
+
{
|
437 |
+
"epoch": 5.0,
|
438 |
+
"eval_accuracy": 0.9699248120300752,
|
439 |
+
"eval_loss": 0.10300374776124954,
|
440 |
+
"eval_runtime": 1.6531,
|
441 |
+
"eval_samples_per_second": 80.453,
|
442 |
+
"eval_steps_per_second": 10.284,
|
443 |
+
"step": 650
|
444 |
+
},
|
445 |
+
{
|
446 |
+
"epoch": 5.0,
|
447 |
+
"step": 650,
|
448 |
+
"total_flos": 0.0,
|
449 |
+
"train_loss": 0.23702784006412211,
|
450 |
+
"train_runtime": 124.7505,
|
451 |
+
"train_samples_per_second": 41.443,
|
452 |
+
"train_steps_per_second": 5.21
|
453 |
+
}
|
454 |
+
],
|
455 |
+
"max_steps": 650,
|
456 |
+
"num_train_epochs": 5,
|
457 |
+
"total_flos": 0.0,
|
458 |
+
"trial_name": null,
|
459 |
+
"trial_params": null
|
460 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dbfebeca32be1d102a71d29619d0db0783df335f73af946dd488cfac20c644ec
|
3 |
+
size 2671
|