Training in progress, epoch 0
Browse files- all_results.json +15 -0
- config.json +57 -0
- eval_results.json +10 -0
- preprocessor_config.json +22 -0
- pytorch_model.bin +3 -0
- train_results.json +7 -0
- trainer_state.json +106 -0
- training_args.bin +3 -0
all_results.json
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 4.8,
|
3 |
+
"eval_accuracy": 0.9,
|
4 |
+
"eval_f1": 0.8879710144927536,
|
5 |
+
"eval_loss": 0.4917445778846741,
|
6 |
+
"eval_precision": 0.9019841269841271,
|
7 |
+
"eval_recall": 0.888888888888889,
|
8 |
+
"eval_runtime": 2.8796,
|
9 |
+
"eval_samples_per_second": 17.363,
|
10 |
+
"eval_steps_per_second": 1.389,
|
11 |
+
"train_loss": 0.8048010190327962,
|
12 |
+
"train_runtime": 101.246,
|
13 |
+
"train_samples_per_second": 19.606,
|
14 |
+
"train_steps_per_second": 0.296
|
15 |
+
}
|
config.json
ADDED
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "facebook/convnextv2-tiny-22k-384",
|
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": "Araneus_diadematus",
|
22 |
+
"1": "Argiope_aurantia",
|
23 |
+
"2": "Misumena_vatia",
|
24 |
+
"3": "Phidippus_audax",
|
25 |
+
"4": "Salticus_scenicus"
|
26 |
+
},
|
27 |
+
"image_size": 224,
|
28 |
+
"initializer_range": 0.02,
|
29 |
+
"label2id": {
|
30 |
+
"Araneus_diadematus": 0,
|
31 |
+
"Argiope_aurantia": 1,
|
32 |
+
"Misumena_vatia": 2,
|
33 |
+
"Phidippus_audax": 3,
|
34 |
+
"Salticus_scenicus": 4
|
35 |
+
},
|
36 |
+
"layer_norm_eps": 1e-12,
|
37 |
+
"model_type": "convnextv2",
|
38 |
+
"num_channels": 3,
|
39 |
+
"num_stages": 4,
|
40 |
+
"out_features": [
|
41 |
+
"stage4"
|
42 |
+
],
|
43 |
+
"out_indices": [
|
44 |
+
4
|
45 |
+
],
|
46 |
+
"patch_size": 4,
|
47 |
+
"problem_type": "single_label_classification",
|
48 |
+
"stage_names": [
|
49 |
+
"stem",
|
50 |
+
"stage1",
|
51 |
+
"stage2",
|
52 |
+
"stage3",
|
53 |
+
"stage4"
|
54 |
+
],
|
55 |
+
"torch_dtype": "float32",
|
56 |
+
"transformers_version": "4.33.3"
|
57 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"eval_accuracy": 0.9,
|
3 |
+
"eval_f1": 0.8879710144927536,
|
4 |
+
"eval_loss": 0.4917445778846741,
|
5 |
+
"eval_precision": 0.9019841269841271,
|
6 |
+
"eval_recall": 0.888888888888889,
|
7 |
+
"eval_runtime": 2.8796,
|
8 |
+
"eval_samples_per_second": 17.363,
|
9 |
+
"eval_steps_per_second": 1.389
|
10 |
+
}
|
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": 384
|
21 |
+
}
|
22 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:530ab5a2fe34bde1848af8532dda84cbf75888e88874ef8f52e8397e7e0e0629
|
3 |
+
size 111550573
|
train_results.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 4.8,
|
3 |
+
"train_loss": 0.8048010190327962,
|
4 |
+
"train_runtime": 101.246,
|
5 |
+
"train_samples_per_second": 19.606,
|
6 |
+
"train_steps_per_second": 0.296
|
7 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,106 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.9,
|
3 |
+
"best_model_checkpoint": "convnextv2-tiny-22k-384-finetuned-zkdeng/t5spiders/checkpoint-18",
|
4 |
+
"epoch": 4.8,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 30,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.96,
|
13 |
+
"eval_accuracy": 0.68,
|
14 |
+
"eval_f1": 0.6750754604872251,
|
15 |
+
"eval_loss": 1.1803159713745117,
|
16 |
+
"eval_precision": 0.6789160839160839,
|
17 |
+
"eval_recall": 0.6868831168831169,
|
18 |
+
"eval_runtime": 3.3618,
|
19 |
+
"eval_samples_per_second": 14.873,
|
20 |
+
"eval_steps_per_second": 1.19,
|
21 |
+
"step": 6
|
22 |
+
},
|
23 |
+
{
|
24 |
+
"epoch": 1.6,
|
25 |
+
"learning_rate": 3.7037037037037037e-05,
|
26 |
+
"loss": 1.3235,
|
27 |
+
"step": 10
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 1.92,
|
31 |
+
"eval_accuracy": 0.84,
|
32 |
+
"eval_f1": 0.8387969924812031,
|
33 |
+
"eval_loss": 0.7862006425857544,
|
34 |
+
"eval_precision": 0.8603030303030303,
|
35 |
+
"eval_recall": 0.856969696969697,
|
36 |
+
"eval_runtime": 2.7831,
|
37 |
+
"eval_samples_per_second": 17.966,
|
38 |
+
"eval_steps_per_second": 1.437,
|
39 |
+
"step": 12
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 2.88,
|
43 |
+
"eval_accuracy": 0.9,
|
44 |
+
"eval_f1": 0.9023978919631095,
|
45 |
+
"eval_loss": 0.5749024748802185,
|
46 |
+
"eval_precision": 0.9034848484848486,
|
47 |
+
"eval_recall": 0.9103030303030304,
|
48 |
+
"eval_runtime": 2.6475,
|
49 |
+
"eval_samples_per_second": 18.886,
|
50 |
+
"eval_steps_per_second": 1.511,
|
51 |
+
"step": 18
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 3.2,
|
55 |
+
"learning_rate": 1.8518518518518518e-05,
|
56 |
+
"loss": 0.6609,
|
57 |
+
"step": 20
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"epoch": 4.0,
|
61 |
+
"eval_accuracy": 0.9,
|
62 |
+
"eval_f1": 0.9023978919631095,
|
63 |
+
"eval_loss": 0.47980964183807373,
|
64 |
+
"eval_precision": 0.9034848484848486,
|
65 |
+
"eval_recall": 0.9103030303030304,
|
66 |
+
"eval_runtime": 2.685,
|
67 |
+
"eval_samples_per_second": 18.622,
|
68 |
+
"eval_steps_per_second": 1.49,
|
69 |
+
"step": 25
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 4.8,
|
73 |
+
"learning_rate": 0.0,
|
74 |
+
"loss": 0.43,
|
75 |
+
"step": 30
|
76 |
+
},
|
77 |
+
{
|
78 |
+
"epoch": 4.8,
|
79 |
+
"eval_accuracy": 0.9,
|
80 |
+
"eval_f1": 0.9023978919631095,
|
81 |
+
"eval_loss": 0.46124908328056335,
|
82 |
+
"eval_precision": 0.9034848484848486,
|
83 |
+
"eval_recall": 0.9103030303030304,
|
84 |
+
"eval_runtime": 2.7597,
|
85 |
+
"eval_samples_per_second": 18.118,
|
86 |
+
"eval_steps_per_second": 1.449,
|
87 |
+
"step": 30
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"epoch": 4.8,
|
91 |
+
"step": 30,
|
92 |
+
"total_flos": 1.4114178534172262e+17,
|
93 |
+
"train_loss": 0.8048010190327962,
|
94 |
+
"train_runtime": 101.246,
|
95 |
+
"train_samples_per_second": 19.606,
|
96 |
+
"train_steps_per_second": 0.296
|
97 |
+
}
|
98 |
+
],
|
99 |
+
"logging_steps": 10,
|
100 |
+
"max_steps": 30,
|
101 |
+
"num_train_epochs": 5,
|
102 |
+
"save_steps": 500,
|
103 |
+
"total_flos": 1.4114178534172262e+17,
|
104 |
+
"trial_name": null,
|
105 |
+
"trial_params": null
|
106 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4ab3212533198c3de7e5dda4341f6ae79dafe0f3ee0a05e1d3c333c0f4df3a6a
|
3 |
+
size 4155
|