Upload folder using huggingface_hub
Browse files- checkpoint-1200/config.json +40 -0
- checkpoint-1200/optimizer.pt +3 -0
- checkpoint-1200/preprocessor_config.json +22 -0
- checkpoint-1200/pytorch_model.bin +3 -0
- checkpoint-1200/rng_state.pth +3 -0
- checkpoint-1200/scheduler.pt +3 -0
- checkpoint-1200/trainer_state.json +931 -0
- checkpoint-1200/training_args.bin +3 -0
- config.json +40 -0
- preprocessor_config.json +22 -0
- pytorch_model.bin +3 -0
- training_args.bin +3 -0
checkpoint-1200/config.json
ADDED
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "google/vit-base-patch16-224-in21k",
|
3 |
+
"architectures": [
|
4 |
+
"ViTForImageClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.0,
|
7 |
+
"encoder_stride": 16,
|
8 |
+
"hidden_act": "gelu",
|
9 |
+
"hidden_dropout_prob": 0.0,
|
10 |
+
"hidden_size": 768,
|
11 |
+
"id2label": {
|
12 |
+
"0": "blue_jellyfish",
|
13 |
+
"1": "barrel_jellyfish",
|
14 |
+
"2": "mauve_stinger_jellyfish",
|
15 |
+
"3": "Moon_jellyfish",
|
16 |
+
"4": "compass_jellyfish",
|
17 |
+
"5": "lions_mane_jellyfish"
|
18 |
+
},
|
19 |
+
"image_size": 224,
|
20 |
+
"initializer_range": 0.02,
|
21 |
+
"intermediate_size": 3072,
|
22 |
+
"label2id": {
|
23 |
+
"Moon_jellyfish": 3,
|
24 |
+
"barrel_jellyfish": 1,
|
25 |
+
"blue_jellyfish": 0,
|
26 |
+
"compass_jellyfish": 4,
|
27 |
+
"lions_mane_jellyfish": 5,
|
28 |
+
"mauve_stinger_jellyfish": 2
|
29 |
+
},
|
30 |
+
"layer_norm_eps": 1e-12,
|
31 |
+
"model_type": "vit",
|
32 |
+
"num_attention_heads": 12,
|
33 |
+
"num_channels": 3,
|
34 |
+
"num_hidden_layers": 12,
|
35 |
+
"patch_size": 16,
|
36 |
+
"problem_type": "single_label_classification",
|
37 |
+
"qkv_bias": true,
|
38 |
+
"torch_dtype": "float32",
|
39 |
+
"transformers_version": "4.34.1"
|
40 |
+
}
|
checkpoint-1200/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5f3fc63acdd710b6c2eb3e822c64d935415732f2aa7b1cc36c108bc7f7ddd21e
|
3 |
+
size 686593029
|
checkpoint-1200/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 |
+
0.5,
|
7 |
+
0.5,
|
8 |
+
0.5
|
9 |
+
],
|
10 |
+
"image_processor_type": "ViTImageProcessor",
|
11 |
+
"image_std": [
|
12 |
+
0.5,
|
13 |
+
0.5,
|
14 |
+
0.5
|
15 |
+
],
|
16 |
+
"resample": 2,
|
17 |
+
"rescale_factor": 0.00392156862745098,
|
18 |
+
"size": {
|
19 |
+
"height": 224,
|
20 |
+
"width": 224
|
21 |
+
}
|
22 |
+
}
|
checkpoint-1200/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1c9b83da3579395b4535b7fcc3edcca10fe7318386f18f860ef9102bf5e322aa
|
3 |
+
size 343281005
|
checkpoint-1200/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:86f698bb359919186b3f2f4ac7958b7109201544f78ccb810f6d8350b928aec5
|
3 |
+
size 14575
|
checkpoint-1200/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f19269de4ad7ef86993de2849ebd6c05cb5562a9d775951b8b3c39e6fac66d41
|
3 |
+
size 627
|
checkpoint-1200/trainer_state.json
ADDED
@@ -0,0 +1,931 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.2559128701686859,
|
3 |
+
"best_model_checkpoint": "jellyfish_types_image_detection/checkpoint-1200",
|
4 |
+
"epoch": 100.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 1200,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 1.0,
|
13 |
+
"eval_accuracy": 0.13333333333333333,
|
14 |
+
"eval_loss": 1.8037762641906738,
|
15 |
+
"eval_runtime": 1.4668,
|
16 |
+
"eval_samples_per_second": 122.716,
|
17 |
+
"eval_steps_per_second": 4.091,
|
18 |
+
"step": 12
|
19 |
+
},
|
20 |
+
{
|
21 |
+
"epoch": 2.0,
|
22 |
+
"eval_accuracy": 0.16666666666666666,
|
23 |
+
"eval_loss": 1.7964667081832886,
|
24 |
+
"eval_runtime": 1.4537,
|
25 |
+
"eval_samples_per_second": 123.818,
|
26 |
+
"eval_steps_per_second": 4.127,
|
27 |
+
"step": 24
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 3.0,
|
31 |
+
"eval_accuracy": 0.2111111111111111,
|
32 |
+
"eval_loss": 1.7842199802398682,
|
33 |
+
"eval_runtime": 1.4821,
|
34 |
+
"eval_samples_per_second": 121.449,
|
35 |
+
"eval_steps_per_second": 4.048,
|
36 |
+
"step": 36
|
37 |
+
},
|
38 |
+
{
|
39 |
+
"epoch": 4.0,
|
40 |
+
"eval_accuracy": 0.3277777777777778,
|
41 |
+
"eval_loss": 1.7650824785232544,
|
42 |
+
"eval_runtime": 1.453,
|
43 |
+
"eval_samples_per_second": 123.884,
|
44 |
+
"eval_steps_per_second": 4.129,
|
45 |
+
"step": 48
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 5.0,
|
49 |
+
"eval_accuracy": 0.48333333333333334,
|
50 |
+
"eval_loss": 1.7318922281265259,
|
51 |
+
"eval_runtime": 1.4666,
|
52 |
+
"eval_samples_per_second": 122.73,
|
53 |
+
"eval_steps_per_second": 4.091,
|
54 |
+
"step": 60
|
55 |
+
},
|
56 |
+
{
|
57 |
+
"epoch": 6.0,
|
58 |
+
"eval_accuracy": 0.5222222222222223,
|
59 |
+
"eval_loss": 1.6917558908462524,
|
60 |
+
"eval_runtime": 1.4921,
|
61 |
+
"eval_samples_per_second": 120.632,
|
62 |
+
"eval_steps_per_second": 4.021,
|
63 |
+
"step": 72
|
64 |
+
},
|
65 |
+
{
|
66 |
+
"epoch": 7.0,
|
67 |
+
"eval_accuracy": 0.6111111111111112,
|
68 |
+
"eval_loss": 1.6543385982513428,
|
69 |
+
"eval_runtime": 1.4653,
|
70 |
+
"eval_samples_per_second": 122.838,
|
71 |
+
"eval_steps_per_second": 4.095,
|
72 |
+
"step": 84
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 8.0,
|
76 |
+
"eval_accuracy": 0.6666666666666666,
|
77 |
+
"eval_loss": 1.6152613162994385,
|
78 |
+
"eval_runtime": 1.4815,
|
79 |
+
"eval_samples_per_second": 121.5,
|
80 |
+
"eval_steps_per_second": 4.05,
|
81 |
+
"step": 96
|
82 |
+
},
|
83 |
+
{
|
84 |
+
"epoch": 9.0,
|
85 |
+
"eval_accuracy": 0.6944444444444444,
|
86 |
+
"eval_loss": 1.5774973630905151,
|
87 |
+
"eval_runtime": 1.4589,
|
88 |
+
"eval_samples_per_second": 123.383,
|
89 |
+
"eval_steps_per_second": 4.113,
|
90 |
+
"step": 108
|
91 |
+
},
|
92 |
+
{
|
93 |
+
"epoch": 10.0,
|
94 |
+
"eval_accuracy": 0.7222222222222222,
|
95 |
+
"eval_loss": 1.537232756614685,
|
96 |
+
"eval_runtime": 1.4581,
|
97 |
+
"eval_samples_per_second": 123.449,
|
98 |
+
"eval_steps_per_second": 4.115,
|
99 |
+
"step": 120
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"epoch": 11.0,
|
103 |
+
"eval_accuracy": 0.7611111111111111,
|
104 |
+
"eval_loss": 1.493251919746399,
|
105 |
+
"eval_runtime": 1.4506,
|
106 |
+
"eval_samples_per_second": 124.088,
|
107 |
+
"eval_steps_per_second": 4.136,
|
108 |
+
"step": 132
|
109 |
+
},
|
110 |
+
{
|
111 |
+
"epoch": 12.0,
|
112 |
+
"eval_accuracy": 0.8055555555555556,
|
113 |
+
"eval_loss": 1.4493757486343384,
|
114 |
+
"eval_runtime": 1.4446,
|
115 |
+
"eval_samples_per_second": 124.603,
|
116 |
+
"eval_steps_per_second": 4.153,
|
117 |
+
"step": 144
|
118 |
+
},
|
119 |
+
{
|
120 |
+
"epoch": 13.0,
|
121 |
+
"eval_accuracy": 0.8277777777777777,
|
122 |
+
"eval_loss": 1.4047116041183472,
|
123 |
+
"eval_runtime": 1.4571,
|
124 |
+
"eval_samples_per_second": 123.531,
|
125 |
+
"eval_steps_per_second": 4.118,
|
126 |
+
"step": 156
|
127 |
+
},
|
128 |
+
{
|
129 |
+
"epoch": 14.0,
|
130 |
+
"eval_accuracy": 0.8444444444444444,
|
131 |
+
"eval_loss": 1.361648440361023,
|
132 |
+
"eval_runtime": 1.4881,
|
133 |
+
"eval_samples_per_second": 120.957,
|
134 |
+
"eval_steps_per_second": 4.032,
|
135 |
+
"step": 168
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 15.0,
|
139 |
+
"eval_accuracy": 0.8611111111111112,
|
140 |
+
"eval_loss": 1.3176687955856323,
|
141 |
+
"eval_runtime": 1.4475,
|
142 |
+
"eval_samples_per_second": 124.356,
|
143 |
+
"eval_steps_per_second": 4.145,
|
144 |
+
"step": 180
|
145 |
+
},
|
146 |
+
{
|
147 |
+
"epoch": 16.0,
|
148 |
+
"eval_accuracy": 0.8722222222222222,
|
149 |
+
"eval_loss": 1.274472951889038,
|
150 |
+
"eval_runtime": 1.4847,
|
151 |
+
"eval_samples_per_second": 121.233,
|
152 |
+
"eval_steps_per_second": 4.041,
|
153 |
+
"step": 192
|
154 |
+
},
|
155 |
+
{
|
156 |
+
"epoch": 17.0,
|
157 |
+
"eval_accuracy": 0.8833333333333333,
|
158 |
+
"eval_loss": 1.2312456369400024,
|
159 |
+
"eval_runtime": 1.4418,
|
160 |
+
"eval_samples_per_second": 124.848,
|
161 |
+
"eval_steps_per_second": 4.162,
|
162 |
+
"step": 204
|
163 |
+
},
|
164 |
+
{
|
165 |
+
"epoch": 18.0,
|
166 |
+
"eval_accuracy": 0.8944444444444445,
|
167 |
+
"eval_loss": 1.188086748123169,
|
168 |
+
"eval_runtime": 1.464,
|
169 |
+
"eval_samples_per_second": 122.954,
|
170 |
+
"eval_steps_per_second": 4.098,
|
171 |
+
"step": 216
|
172 |
+
},
|
173 |
+
{
|
174 |
+
"epoch": 19.0,
|
175 |
+
"eval_accuracy": 0.9,
|
176 |
+
"eval_loss": 1.1461745500564575,
|
177 |
+
"eval_runtime": 1.493,
|
178 |
+
"eval_samples_per_second": 120.56,
|
179 |
+
"eval_steps_per_second": 4.019,
|
180 |
+
"step": 228
|
181 |
+
},
|
182 |
+
{
|
183 |
+
"epoch": 20.0,
|
184 |
+
"eval_accuracy": 0.9055555555555556,
|
185 |
+
"eval_loss": 1.1037755012512207,
|
186 |
+
"eval_runtime": 1.4858,
|
187 |
+
"eval_samples_per_second": 121.149,
|
188 |
+
"eval_steps_per_second": 4.038,
|
189 |
+
"step": 240
|
190 |
+
},
|
191 |
+
{
|
192 |
+
"epoch": 21.0,
|
193 |
+
"eval_accuracy": 0.9222222222222223,
|
194 |
+
"eval_loss": 1.0644763708114624,
|
195 |
+
"eval_runtime": 1.457,
|
196 |
+
"eval_samples_per_second": 123.54,
|
197 |
+
"eval_steps_per_second": 4.118,
|
198 |
+
"step": 252
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 22.0,
|
202 |
+
"eval_accuracy": 0.9222222222222223,
|
203 |
+
"eval_loss": 1.0271453857421875,
|
204 |
+
"eval_runtime": 1.4687,
|
205 |
+
"eval_samples_per_second": 122.558,
|
206 |
+
"eval_steps_per_second": 4.085,
|
207 |
+
"step": 264
|
208 |
+
},
|
209 |
+
{
|
210 |
+
"epoch": 23.0,
|
211 |
+
"eval_accuracy": 0.9222222222222223,
|
212 |
+
"eval_loss": 0.9920065999031067,
|
213 |
+
"eval_runtime": 1.4756,
|
214 |
+
"eval_samples_per_second": 121.987,
|
215 |
+
"eval_steps_per_second": 4.066,
|
216 |
+
"step": 276
|
217 |
+
},
|
218 |
+
{
|
219 |
+
"epoch": 24.0,
|
220 |
+
"eval_accuracy": 0.9277777777777778,
|
221 |
+
"eval_loss": 0.9561882615089417,
|
222 |
+
"eval_runtime": 1.4526,
|
223 |
+
"eval_samples_per_second": 123.915,
|
224 |
+
"eval_steps_per_second": 4.13,
|
225 |
+
"step": 288
|
226 |
+
},
|
227 |
+
{
|
228 |
+
"epoch": 25.0,
|
229 |
+
"eval_accuracy": 0.9277777777777778,
|
230 |
+
"eval_loss": 0.9198849201202393,
|
231 |
+
"eval_runtime": 1.4722,
|
232 |
+
"eval_samples_per_second": 122.266,
|
233 |
+
"eval_steps_per_second": 4.076,
|
234 |
+
"step": 300
|
235 |
+
},
|
236 |
+
{
|
237 |
+
"epoch": 26.0,
|
238 |
+
"eval_accuracy": 0.9333333333333333,
|
239 |
+
"eval_loss": 0.8863067626953125,
|
240 |
+
"eval_runtime": 1.4638,
|
241 |
+
"eval_samples_per_second": 122.965,
|
242 |
+
"eval_steps_per_second": 4.099,
|
243 |
+
"step": 312
|
244 |
+
},
|
245 |
+
{
|
246 |
+
"epoch": 27.0,
|
247 |
+
"eval_accuracy": 0.9388888888888889,
|
248 |
+
"eval_loss": 0.854658842086792,
|
249 |
+
"eval_runtime": 1.4827,
|
250 |
+
"eval_samples_per_second": 121.397,
|
251 |
+
"eval_steps_per_second": 4.047,
|
252 |
+
"step": 324
|
253 |
+
},
|
254 |
+
{
|
255 |
+
"epoch": 28.0,
|
256 |
+
"eval_accuracy": 0.9388888888888889,
|
257 |
+
"eval_loss": 0.8234849572181702,
|
258 |
+
"eval_runtime": 1.4441,
|
259 |
+
"eval_samples_per_second": 124.642,
|
260 |
+
"eval_steps_per_second": 4.155,
|
261 |
+
"step": 336
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 29.0,
|
265 |
+
"eval_accuracy": 0.9444444444444444,
|
266 |
+
"eval_loss": 0.7938969731330872,
|
267 |
+
"eval_runtime": 1.4806,
|
268 |
+
"eval_samples_per_second": 121.571,
|
269 |
+
"eval_steps_per_second": 4.052,
|
270 |
+
"step": 348
|
271 |
+
},
|
272 |
+
{
|
273 |
+
"epoch": 30.0,
|
274 |
+
"eval_accuracy": 0.95,
|
275 |
+
"eval_loss": 0.7686691284179688,
|
276 |
+
"eval_runtime": 1.4728,
|
277 |
+
"eval_samples_per_second": 122.213,
|
278 |
+
"eval_steps_per_second": 4.074,
|
279 |
+
"step": 360
|
280 |
+
},
|
281 |
+
{
|
282 |
+
"epoch": 31.0,
|
283 |
+
"eval_accuracy": 0.9555555555555556,
|
284 |
+
"eval_loss": 0.7412105798721313,
|
285 |
+
"eval_runtime": 1.4756,
|
286 |
+
"eval_samples_per_second": 121.98,
|
287 |
+
"eval_steps_per_second": 4.066,
|
288 |
+
"step": 372
|
289 |
+
},
|
290 |
+
{
|
291 |
+
"epoch": 32.0,
|
292 |
+
"eval_accuracy": 0.9666666666666667,
|
293 |
+
"eval_loss": 0.7157594561576843,
|
294 |
+
"eval_runtime": 1.4492,
|
295 |
+
"eval_samples_per_second": 124.202,
|
296 |
+
"eval_steps_per_second": 4.14,
|
297 |
+
"step": 384
|
298 |
+
},
|
299 |
+
{
|
300 |
+
"epoch": 33.0,
|
301 |
+
"eval_accuracy": 0.9611111111111111,
|
302 |
+
"eval_loss": 0.6940791606903076,
|
303 |
+
"eval_runtime": 1.4692,
|
304 |
+
"eval_samples_per_second": 122.519,
|
305 |
+
"eval_steps_per_second": 4.084,
|
306 |
+
"step": 396
|
307 |
+
},
|
308 |
+
{
|
309 |
+
"epoch": 34.0,
|
310 |
+
"eval_accuracy": 0.9666666666666667,
|
311 |
+
"eval_loss": 0.6703041791915894,
|
312 |
+
"eval_runtime": 1.4885,
|
313 |
+
"eval_samples_per_second": 120.927,
|
314 |
+
"eval_steps_per_second": 4.031,
|
315 |
+
"step": 408
|
316 |
+
},
|
317 |
+
{
|
318 |
+
"epoch": 35.0,
|
319 |
+
"eval_accuracy": 0.9722222222222222,
|
320 |
+
"eval_loss": 0.6472752094268799,
|
321 |
+
"eval_runtime": 1.4555,
|
322 |
+
"eval_samples_per_second": 123.668,
|
323 |
+
"eval_steps_per_second": 4.122,
|
324 |
+
"step": 420
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"epoch": 36.0,
|
328 |
+
"eval_accuracy": 0.9722222222222222,
|
329 |
+
"eval_loss": 0.6263246536254883,
|
330 |
+
"eval_runtime": 1.4622,
|
331 |
+
"eval_samples_per_second": 123.1,
|
332 |
+
"eval_steps_per_second": 4.103,
|
333 |
+
"step": 432
|
334 |
+
},
|
335 |
+
{
|
336 |
+
"epoch": 37.0,
|
337 |
+
"eval_accuracy": 0.9777777777777777,
|
338 |
+
"eval_loss": 0.6071779131889343,
|
339 |
+
"eval_runtime": 1.4555,
|
340 |
+
"eval_samples_per_second": 123.673,
|
341 |
+
"eval_steps_per_second": 4.122,
|
342 |
+
"step": 444
|
343 |
+
},
|
344 |
+
{
|
345 |
+
"epoch": 38.0,
|
346 |
+
"eval_accuracy": 0.9777777777777777,
|
347 |
+
"eval_loss": 0.5879429578781128,
|
348 |
+
"eval_runtime": 1.4938,
|
349 |
+
"eval_samples_per_second": 120.501,
|
350 |
+
"eval_steps_per_second": 4.017,
|
351 |
+
"step": 456
|
352 |
+
},
|
353 |
+
{
|
354 |
+
"epoch": 39.0,
|
355 |
+
"eval_accuracy": 0.9777777777777777,
|
356 |
+
"eval_loss": 0.5692062377929688,
|
357 |
+
"eval_runtime": 1.4569,
|
358 |
+
"eval_samples_per_second": 123.554,
|
359 |
+
"eval_steps_per_second": 4.118,
|
360 |
+
"step": 468
|
361 |
+
},
|
362 |
+
{
|
363 |
+
"epoch": 40.0,
|
364 |
+
"eval_accuracy": 0.9833333333333333,
|
365 |
+
"eval_loss": 0.5512961745262146,
|
366 |
+
"eval_runtime": 1.4652,
|
367 |
+
"eval_samples_per_second": 122.849,
|
368 |
+
"eval_steps_per_second": 4.095,
|
369 |
+
"step": 480
|
370 |
+
},
|
371 |
+
{
|
372 |
+
"epoch": 41.0,
|
373 |
+
"eval_accuracy": 0.9833333333333333,
|
374 |
+
"eval_loss": 0.5354695916175842,
|
375 |
+
"eval_runtime": 1.4556,
|
376 |
+
"eval_samples_per_second": 123.659,
|
377 |
+
"eval_steps_per_second": 4.122,
|
378 |
+
"step": 492
|
379 |
+
},
|
380 |
+
{
|
381 |
+
"epoch": 41.67,
|
382 |
+
"learning_rate": 3.043478260869566e-06,
|
383 |
+
"loss": 1.0637,
|
384 |
+
"step": 500
|
385 |
+
},
|
386 |
+
{
|
387 |
+
"epoch": 42.0,
|
388 |
+
"eval_accuracy": 0.9833333333333333,
|
389 |
+
"eval_loss": 0.5195258259773254,
|
390 |
+
"eval_runtime": 1.4697,
|
391 |
+
"eval_samples_per_second": 122.474,
|
392 |
+
"eval_steps_per_second": 4.082,
|
393 |
+
"step": 504
|
394 |
+
},
|
395 |
+
{
|
396 |
+
"epoch": 43.0,
|
397 |
+
"eval_accuracy": 0.9833333333333333,
|
398 |
+
"eval_loss": 0.504427433013916,
|
399 |
+
"eval_runtime": 1.4758,
|
400 |
+
"eval_samples_per_second": 121.968,
|
401 |
+
"eval_steps_per_second": 4.066,
|
402 |
+
"step": 516
|
403 |
+
},
|
404 |
+
{
|
405 |
+
"epoch": 44.0,
|
406 |
+
"eval_accuracy": 0.9833333333333333,
|
407 |
+
"eval_loss": 0.4885842204093933,
|
408 |
+
"eval_runtime": 1.4505,
|
409 |
+
"eval_samples_per_second": 124.094,
|
410 |
+
"eval_steps_per_second": 4.136,
|
411 |
+
"step": 528
|
412 |
+
},
|
413 |
+
{
|
414 |
+
"epoch": 45.0,
|
415 |
+
"eval_accuracy": 0.9833333333333333,
|
416 |
+
"eval_loss": 0.476900577545166,
|
417 |
+
"eval_runtime": 1.458,
|
418 |
+
"eval_samples_per_second": 123.46,
|
419 |
+
"eval_steps_per_second": 4.115,
|
420 |
+
"step": 540
|
421 |
+
},
|
422 |
+
{
|
423 |
+
"epoch": 46.0,
|
424 |
+
"eval_accuracy": 0.9833333333333333,
|
425 |
+
"eval_loss": 0.46481671929359436,
|
426 |
+
"eval_runtime": 1.4536,
|
427 |
+
"eval_samples_per_second": 123.832,
|
428 |
+
"eval_steps_per_second": 4.128,
|
429 |
+
"step": 552
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"epoch": 47.0,
|
433 |
+
"eval_accuracy": 0.9833333333333333,
|
434 |
+
"eval_loss": 0.4519122242927551,
|
435 |
+
"eval_runtime": 1.4664,
|
436 |
+
"eval_samples_per_second": 122.75,
|
437 |
+
"eval_steps_per_second": 4.092,
|
438 |
+
"step": 564
|
439 |
+
},
|
440 |
+
{
|
441 |
+
"epoch": 48.0,
|
442 |
+
"eval_accuracy": 0.9833333333333333,
|
443 |
+
"eval_loss": 0.4407157003879547,
|
444 |
+
"eval_runtime": 1.4484,
|
445 |
+
"eval_samples_per_second": 124.273,
|
446 |
+
"eval_steps_per_second": 4.142,
|
447 |
+
"step": 576
|
448 |
+
},
|
449 |
+
{
|
450 |
+
"epoch": 49.0,
|
451 |
+
"eval_accuracy": 0.9833333333333333,
|
452 |
+
"eval_loss": 0.4315236508846283,
|
453 |
+
"eval_runtime": 1.477,
|
454 |
+
"eval_samples_per_second": 121.872,
|
455 |
+
"eval_steps_per_second": 4.062,
|
456 |
+
"step": 588
|
457 |
+
},
|
458 |
+
{
|
459 |
+
"epoch": 50.0,
|
460 |
+
"eval_accuracy": 0.9833333333333333,
|
461 |
+
"eval_loss": 0.4219152629375458,
|
462 |
+
"eval_runtime": 1.4877,
|
463 |
+
"eval_samples_per_second": 120.994,
|
464 |
+
"eval_steps_per_second": 4.033,
|
465 |
+
"step": 600
|
466 |
+
},
|
467 |
+
{
|
468 |
+
"epoch": 51.0,
|
469 |
+
"eval_accuracy": 0.9833333333333333,
|
470 |
+
"eval_loss": 0.4109198749065399,
|
471 |
+
"eval_runtime": 1.4732,
|
472 |
+
"eval_samples_per_second": 122.18,
|
473 |
+
"eval_steps_per_second": 4.073,
|
474 |
+
"step": 612
|
475 |
+
},
|
476 |
+
{
|
477 |
+
"epoch": 52.0,
|
478 |
+
"eval_accuracy": 0.9833333333333333,
|
479 |
+
"eval_loss": 0.40128326416015625,
|
480 |
+
"eval_runtime": 1.4657,
|
481 |
+
"eval_samples_per_second": 122.811,
|
482 |
+
"eval_steps_per_second": 4.094,
|
483 |
+
"step": 624
|
484 |
+
},
|
485 |
+
{
|
486 |
+
"epoch": 53.0,
|
487 |
+
"eval_accuracy": 0.9833333333333333,
|
488 |
+
"eval_loss": 0.3921063244342804,
|
489 |
+
"eval_runtime": 1.4551,
|
490 |
+
"eval_samples_per_second": 123.702,
|
491 |
+
"eval_steps_per_second": 4.123,
|
492 |
+
"step": 636
|
493 |
+
},
|
494 |
+
{
|
495 |
+
"epoch": 54.0,
|
496 |
+
"eval_accuracy": 0.9833333333333333,
|
497 |
+
"eval_loss": 0.3846009075641632,
|
498 |
+
"eval_runtime": 1.4672,
|
499 |
+
"eval_samples_per_second": 122.68,
|
500 |
+
"eval_steps_per_second": 4.089,
|
501 |
+
"step": 648
|
502 |
+
},
|
503 |
+
{
|
504 |
+
"epoch": 55.0,
|
505 |
+
"eval_accuracy": 0.9833333333333333,
|
506 |
+
"eval_loss": 0.3765101134777069,
|
507 |
+
"eval_runtime": 1.4497,
|
508 |
+
"eval_samples_per_second": 124.166,
|
509 |
+
"eval_steps_per_second": 4.139,
|
510 |
+
"step": 660
|
511 |
+
},
|
512 |
+
{
|
513 |
+
"epoch": 56.0,
|
514 |
+
"eval_accuracy": 0.9833333333333333,
|
515 |
+
"eval_loss": 0.36845535039901733,
|
516 |
+
"eval_runtime": 1.457,
|
517 |
+
"eval_samples_per_second": 123.539,
|
518 |
+
"eval_steps_per_second": 4.118,
|
519 |
+
"step": 672
|
520 |
+
},
|
521 |
+
{
|
522 |
+
"epoch": 57.0,
|
523 |
+
"eval_accuracy": 0.9944444444444445,
|
524 |
+
"eval_loss": 0.36152249574661255,
|
525 |
+
"eval_runtime": 1.4938,
|
526 |
+
"eval_samples_per_second": 120.499,
|
527 |
+
"eval_steps_per_second": 4.017,
|
528 |
+
"step": 684
|
529 |
+
},
|
530 |
+
{
|
531 |
+
"epoch": 58.0,
|
532 |
+
"eval_accuracy": 0.9944444444444445,
|
533 |
+
"eval_loss": 0.3548332154750824,
|
534 |
+
"eval_runtime": 1.4584,
|
535 |
+
"eval_samples_per_second": 123.426,
|
536 |
+
"eval_steps_per_second": 4.114,
|
537 |
+
"step": 696
|
538 |
+
},
|
539 |
+
{
|
540 |
+
"epoch": 59.0,
|
541 |
+
"eval_accuracy": 1.0,
|
542 |
+
"eval_loss": 0.347601056098938,
|
543 |
+
"eval_runtime": 1.4686,
|
544 |
+
"eval_samples_per_second": 122.568,
|
545 |
+
"eval_steps_per_second": 4.086,
|
546 |
+
"step": 708
|
547 |
+
},
|
548 |
+
{
|
549 |
+
"epoch": 60.0,
|
550 |
+
"eval_accuracy": 1.0,
|
551 |
+
"eval_loss": 0.34238797426223755,
|
552 |
+
"eval_runtime": 1.4606,
|
553 |
+
"eval_samples_per_second": 123.238,
|
554 |
+
"eval_steps_per_second": 4.108,
|
555 |
+
"step": 720
|
556 |
+
},
|
557 |
+
{
|
558 |
+
"epoch": 61.0,
|
559 |
+
"eval_accuracy": 0.9944444444444445,
|
560 |
+
"eval_loss": 0.3361431956291199,
|
561 |
+
"eval_runtime": 1.4646,
|
562 |
+
"eval_samples_per_second": 122.896,
|
563 |
+
"eval_steps_per_second": 4.097,
|
564 |
+
"step": 732
|
565 |
+
},
|
566 |
+
{
|
567 |
+
"epoch": 62.0,
|
568 |
+
"eval_accuracy": 1.0,
|
569 |
+
"eval_loss": 0.3294546604156494,
|
570 |
+
"eval_runtime": 1.455,
|
571 |
+
"eval_samples_per_second": 123.713,
|
572 |
+
"eval_steps_per_second": 4.124,
|
573 |
+
"step": 744
|
574 |
+
},
|
575 |
+
{
|
576 |
+
"epoch": 63.0,
|
577 |
+
"eval_accuracy": 1.0,
|
578 |
+
"eval_loss": 0.3248053193092346,
|
579 |
+
"eval_runtime": 1.4926,
|
580 |
+
"eval_samples_per_second": 120.594,
|
581 |
+
"eval_steps_per_second": 4.02,
|
582 |
+
"step": 756
|
583 |
+
},
|
584 |
+
{
|
585 |
+
"epoch": 64.0,
|
586 |
+
"eval_accuracy": 1.0,
|
587 |
+
"eval_loss": 0.321612685918808,
|
588 |
+
"eval_runtime": 1.5011,
|
589 |
+
"eval_samples_per_second": 119.908,
|
590 |
+
"eval_steps_per_second": 3.997,
|
591 |
+
"step": 768
|
592 |
+
},
|
593 |
+
{
|
594 |
+
"epoch": 65.0,
|
595 |
+
"eval_accuracy": 1.0,
|
596 |
+
"eval_loss": 0.31790634989738464,
|
597 |
+
"eval_runtime": 1.4912,
|
598 |
+
"eval_samples_per_second": 120.707,
|
599 |
+
"eval_steps_per_second": 4.024,
|
600 |
+
"step": 780
|
601 |
+
},
|
602 |
+
{
|
603 |
+
"epoch": 66.0,
|
604 |
+
"eval_accuracy": 1.0,
|
605 |
+
"eval_loss": 0.3131932020187378,
|
606 |
+
"eval_runtime": 1.4769,
|
607 |
+
"eval_samples_per_second": 121.876,
|
608 |
+
"eval_steps_per_second": 4.063,
|
609 |
+
"step": 792
|
610 |
+
},
|
611 |
+
{
|
612 |
+
"epoch": 67.0,
|
613 |
+
"eval_accuracy": 1.0,
|
614 |
+
"eval_loss": 0.30861523747444153,
|
615 |
+
"eval_runtime": 1.4543,
|
616 |
+
"eval_samples_per_second": 123.77,
|
617 |
+
"eval_steps_per_second": 4.126,
|
618 |
+
"step": 804
|
619 |
+
},
|
620 |
+
{
|
621 |
+
"epoch": 68.0,
|
622 |
+
"eval_accuracy": 1.0,
|
623 |
+
"eval_loss": 0.30537351965904236,
|
624 |
+
"eval_runtime": 1.4584,
|
625 |
+
"eval_samples_per_second": 123.426,
|
626 |
+
"eval_steps_per_second": 4.114,
|
627 |
+
"step": 816
|
628 |
+
},
|
629 |
+
{
|
630 |
+
"epoch": 69.0,
|
631 |
+
"eval_accuracy": 1.0,
|
632 |
+
"eval_loss": 0.3011786639690399,
|
633 |
+
"eval_runtime": 1.5201,
|
634 |
+
"eval_samples_per_second": 118.412,
|
635 |
+
"eval_steps_per_second": 3.947,
|
636 |
+
"step": 828
|
637 |
+
},
|
638 |
+
{
|
639 |
+
"epoch": 70.0,
|
640 |
+
"eval_accuracy": 1.0,
|
641 |
+
"eval_loss": 0.2988120913505554,
|
642 |
+
"eval_runtime": 1.5115,
|
643 |
+
"eval_samples_per_second": 119.089,
|
644 |
+
"eval_steps_per_second": 3.97,
|
645 |
+
"step": 840
|
646 |
+
},
|
647 |
+
{
|
648 |
+
"epoch": 71.0,
|
649 |
+
"eval_accuracy": 1.0,
|
650 |
+
"eval_loss": 0.29593294858932495,
|
651 |
+
"eval_runtime": 1.5429,
|
652 |
+
"eval_samples_per_second": 116.664,
|
653 |
+
"eval_steps_per_second": 3.889,
|
654 |
+
"step": 852
|
655 |
+
},
|
656 |
+
{
|
657 |
+
"epoch": 72.0,
|
658 |
+
"eval_accuracy": 1.0,
|
659 |
+
"eval_loss": 0.2927241027355194,
|
660 |
+
"eval_runtime": 1.5079,
|
661 |
+
"eval_samples_per_second": 119.375,
|
662 |
+
"eval_steps_per_second": 3.979,
|
663 |
+
"step": 864
|
664 |
+
},
|
665 |
+
{
|
666 |
+
"epoch": 73.0,
|
667 |
+
"eval_accuracy": 1.0,
|
668 |
+
"eval_loss": 0.28996163606643677,
|
669 |
+
"eval_runtime": 1.4668,
|
670 |
+
"eval_samples_per_second": 122.719,
|
671 |
+
"eval_steps_per_second": 4.091,
|
672 |
+
"step": 876
|
673 |
+
},
|
674 |
+
{
|
675 |
+
"epoch": 74.0,
|
676 |
+
"eval_accuracy": 1.0,
|
677 |
+
"eval_loss": 0.2871484160423279,
|
678 |
+
"eval_runtime": 1.4881,
|
679 |
+
"eval_samples_per_second": 120.96,
|
680 |
+
"eval_steps_per_second": 4.032,
|
681 |
+
"step": 888
|
682 |
+
},
|
683 |
+
{
|
684 |
+
"epoch": 75.0,
|
685 |
+
"eval_accuracy": 1.0,
|
686 |
+
"eval_loss": 0.28433895111083984,
|
687 |
+
"eval_runtime": 1.4634,
|
688 |
+
"eval_samples_per_second": 122.997,
|
689 |
+
"eval_steps_per_second": 4.1,
|
690 |
+
"step": 900
|
691 |
+
},
|
692 |
+
{
|
693 |
+
"epoch": 76.0,
|
694 |
+
"eval_accuracy": 1.0,
|
695 |
+
"eval_loss": 0.28165823221206665,
|
696 |
+
"eval_runtime": 1.5021,
|
697 |
+
"eval_samples_per_second": 119.83,
|
698 |
+
"eval_steps_per_second": 3.994,
|
699 |
+
"step": 912
|
700 |
+
},
|
701 |
+
{
|
702 |
+
"epoch": 77.0,
|
703 |
+
"eval_accuracy": 1.0,
|
704 |
+
"eval_loss": 0.28015318512916565,
|
705 |
+
"eval_runtime": 1.4568,
|
706 |
+
"eval_samples_per_second": 123.561,
|
707 |
+
"eval_steps_per_second": 4.119,
|
708 |
+
"step": 924
|
709 |
+
},
|
710 |
+
{
|
711 |
+
"epoch": 78.0,
|
712 |
+
"eval_accuracy": 1.0,
|
713 |
+
"eval_loss": 0.2770257890224457,
|
714 |
+
"eval_runtime": 1.5064,
|
715 |
+
"eval_samples_per_second": 119.488,
|
716 |
+
"eval_steps_per_second": 3.983,
|
717 |
+
"step": 936
|
718 |
+
},
|
719 |
+
{
|
720 |
+
"epoch": 79.0,
|
721 |
+
"eval_accuracy": 1.0,
|
722 |
+
"eval_loss": 0.27566105127334595,
|
723 |
+
"eval_runtime": 1.4625,
|
724 |
+
"eval_samples_per_second": 123.078,
|
725 |
+
"eval_steps_per_second": 4.103,
|
726 |
+
"step": 948
|
727 |
+
},
|
728 |
+
{
|
729 |
+
"epoch": 80.0,
|
730 |
+
"eval_accuracy": 1.0,
|
731 |
+
"eval_loss": 0.2737778425216675,
|
732 |
+
"eval_runtime": 1.4797,
|
733 |
+
"eval_samples_per_second": 121.65,
|
734 |
+
"eval_steps_per_second": 4.055,
|
735 |
+
"step": 960
|
736 |
+
},
|
737 |
+
{
|
738 |
+
"epoch": 81.0,
|
739 |
+
"eval_accuracy": 1.0,
|
740 |
+
"eval_loss": 0.2718334197998047,
|
741 |
+
"eval_runtime": 1.4696,
|
742 |
+
"eval_samples_per_second": 122.481,
|
743 |
+
"eval_steps_per_second": 4.083,
|
744 |
+
"step": 972
|
745 |
+
},
|
746 |
+
{
|
747 |
+
"epoch": 82.0,
|
748 |
+
"eval_accuracy": 1.0,
|
749 |
+
"eval_loss": 0.26975783705711365,
|
750 |
+
"eval_runtime": 1.4687,
|
751 |
+
"eval_samples_per_second": 122.558,
|
752 |
+
"eval_steps_per_second": 4.085,
|
753 |
+
"step": 984
|
754 |
+
},
|
755 |
+
{
|
756 |
+
"epoch": 83.0,
|
757 |
+
"eval_accuracy": 1.0,
|
758 |
+
"eval_loss": 0.26791912317276,
|
759 |
+
"eval_runtime": 1.4639,
|
760 |
+
"eval_samples_per_second": 122.956,
|
761 |
+
"eval_steps_per_second": 4.099,
|
762 |
+
"step": 996
|
763 |
+
},
|
764 |
+
{
|
765 |
+
"epoch": 83.33,
|
766 |
+
"learning_rate": 8.695652173913044e-07,
|
767 |
+
"loss": 0.2932,
|
768 |
+
"step": 1000
|
769 |
+
},
|
770 |
+
{
|
771 |
+
"epoch": 84.0,
|
772 |
+
"eval_accuracy": 1.0,
|
773 |
+
"eval_loss": 0.26642781496047974,
|
774 |
+
"eval_runtime": 1.4634,
|
775 |
+
"eval_samples_per_second": 122.998,
|
776 |
+
"eval_steps_per_second": 4.1,
|
777 |
+
"step": 1008
|
778 |
+
},
|
779 |
+
{
|
780 |
+
"epoch": 85.0,
|
781 |
+
"eval_accuracy": 1.0,
|
782 |
+
"eval_loss": 0.26537179946899414,
|
783 |
+
"eval_runtime": 1.4911,
|
784 |
+
"eval_samples_per_second": 120.716,
|
785 |
+
"eval_steps_per_second": 4.024,
|
786 |
+
"step": 1020
|
787 |
+
},
|
788 |
+
{
|
789 |
+
"epoch": 86.0,
|
790 |
+
"eval_accuracy": 1.0,
|
791 |
+
"eval_loss": 0.2642461061477661,
|
792 |
+
"eval_runtime": 1.4853,
|
793 |
+
"eval_samples_per_second": 121.185,
|
794 |
+
"eval_steps_per_second": 4.04,
|
795 |
+
"step": 1032
|
796 |
+
},
|
797 |
+
{
|
798 |
+
"epoch": 87.0,
|
799 |
+
"eval_accuracy": 1.0,
|
800 |
+
"eval_loss": 0.26312384009361267,
|
801 |
+
"eval_runtime": 1.4683,
|
802 |
+
"eval_samples_per_second": 122.595,
|
803 |
+
"eval_steps_per_second": 4.086,
|
804 |
+
"step": 1044
|
805 |
+
},
|
806 |
+
{
|
807 |
+
"epoch": 88.0,
|
808 |
+
"eval_accuracy": 1.0,
|
809 |
+
"eval_loss": 0.26201656460762024,
|
810 |
+
"eval_runtime": 1.4595,
|
811 |
+
"eval_samples_per_second": 123.329,
|
812 |
+
"eval_steps_per_second": 4.111,
|
813 |
+
"step": 1056
|
814 |
+
},
|
815 |
+
{
|
816 |
+
"epoch": 89.0,
|
817 |
+
"eval_accuracy": 1.0,
|
818 |
+
"eval_loss": 0.2606281042098999,
|
819 |
+
"eval_runtime": 1.4847,
|
820 |
+
"eval_samples_per_second": 121.236,
|
821 |
+
"eval_steps_per_second": 4.041,
|
822 |
+
"step": 1068
|
823 |
+
},
|
824 |
+
{
|
825 |
+
"epoch": 90.0,
|
826 |
+
"eval_accuracy": 1.0,
|
827 |
+
"eval_loss": 0.2599017918109894,
|
828 |
+
"eval_runtime": 1.4956,
|
829 |
+
"eval_samples_per_second": 120.351,
|
830 |
+
"eval_steps_per_second": 4.012,
|
831 |
+
"step": 1080
|
832 |
+
},
|
833 |
+
{
|
834 |
+
"epoch": 91.0,
|
835 |
+
"eval_accuracy": 1.0,
|
836 |
+
"eval_loss": 0.259151428937912,
|
837 |
+
"eval_runtime": 1.5175,
|
838 |
+
"eval_samples_per_second": 118.618,
|
839 |
+
"eval_steps_per_second": 3.954,
|
840 |
+
"step": 1092
|
841 |
+
},
|
842 |
+
{
|
843 |
+
"epoch": 92.0,
|
844 |
+
"eval_accuracy": 1.0,
|
845 |
+
"eval_loss": 0.25827452540397644,
|
846 |
+
"eval_runtime": 1.4933,
|
847 |
+
"eval_samples_per_second": 120.542,
|
848 |
+
"eval_steps_per_second": 4.018,
|
849 |
+
"step": 1104
|
850 |
+
},
|
851 |
+
{
|
852 |
+
"epoch": 93.0,
|
853 |
+
"eval_accuracy": 1.0,
|
854 |
+
"eval_loss": 0.25780928134918213,
|
855 |
+
"eval_runtime": 1.4766,
|
856 |
+
"eval_samples_per_second": 121.898,
|
857 |
+
"eval_steps_per_second": 4.063,
|
858 |
+
"step": 1116
|
859 |
+
},
|
860 |
+
{
|
861 |
+
"epoch": 94.0,
|
862 |
+
"eval_accuracy": 1.0,
|
863 |
+
"eval_loss": 0.2573579251766205,
|
864 |
+
"eval_runtime": 1.4712,
|
865 |
+
"eval_samples_per_second": 122.352,
|
866 |
+
"eval_steps_per_second": 4.078,
|
867 |
+
"step": 1128
|
868 |
+
},
|
869 |
+
{
|
870 |
+
"epoch": 95.0,
|
871 |
+
"eval_accuracy": 1.0,
|
872 |
+
"eval_loss": 0.2569742202758789,
|
873 |
+
"eval_runtime": 1.4809,
|
874 |
+
"eval_samples_per_second": 121.547,
|
875 |
+
"eval_steps_per_second": 4.052,
|
876 |
+
"step": 1140
|
877 |
+
},
|
878 |
+
{
|
879 |
+
"epoch": 96.0,
|
880 |
+
"eval_accuracy": 1.0,
|
881 |
+
"eval_loss": 0.25656217336654663,
|
882 |
+
"eval_runtime": 1.494,
|
883 |
+
"eval_samples_per_second": 120.482,
|
884 |
+
"eval_steps_per_second": 4.016,
|
885 |
+
"step": 1152
|
886 |
+
},
|
887 |
+
{
|
888 |
+
"epoch": 97.0,
|
889 |
+
"eval_accuracy": 1.0,
|
890 |
+
"eval_loss": 0.25618523359298706,
|
891 |
+
"eval_runtime": 1.4664,
|
892 |
+
"eval_samples_per_second": 122.748,
|
893 |
+
"eval_steps_per_second": 4.092,
|
894 |
+
"step": 1164
|
895 |
+
},
|
896 |
+
{
|
897 |
+
"epoch": 98.0,
|
898 |
+
"eval_accuracy": 1.0,
|
899 |
+
"eval_loss": 0.2560265362262726,
|
900 |
+
"eval_runtime": 1.4641,
|
901 |
+
"eval_samples_per_second": 122.941,
|
902 |
+
"eval_steps_per_second": 4.098,
|
903 |
+
"step": 1176
|
904 |
+
},
|
905 |
+
{
|
906 |
+
"epoch": 99.0,
|
907 |
+
"eval_accuracy": 1.0,
|
908 |
+
"eval_loss": 0.2559475004673004,
|
909 |
+
"eval_runtime": 1.462,
|
910 |
+
"eval_samples_per_second": 123.118,
|
911 |
+
"eval_steps_per_second": 4.104,
|
912 |
+
"step": 1188
|
913 |
+
},
|
914 |
+
{
|
915 |
+
"epoch": 100.0,
|
916 |
+
"eval_accuracy": 1.0,
|
917 |
+
"eval_loss": 0.2559128701686859,
|
918 |
+
"eval_runtime": 1.4715,
|
919 |
+
"eval_samples_per_second": 122.323,
|
920 |
+
"eval_steps_per_second": 4.077,
|
921 |
+
"step": 1200
|
922 |
+
}
|
923 |
+
],
|
924 |
+
"logging_steps": 500,
|
925 |
+
"max_steps": 1200,
|
926 |
+
"num_train_epochs": 100,
|
927 |
+
"save_steps": 500,
|
928 |
+
"total_flos": 5.57962327867392e+18,
|
929 |
+
"trial_name": null,
|
930 |
+
"trial_params": null
|
931 |
+
}
|
checkpoint-1200/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:031a7c8aed93814186c29423c7024491fbb7d91a2310f465580903f80fef8344
|
3 |
+
size 4027
|
config.json
ADDED
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "google/vit-base-patch16-224-in21k",
|
3 |
+
"architectures": [
|
4 |
+
"ViTForImageClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.0,
|
7 |
+
"encoder_stride": 16,
|
8 |
+
"hidden_act": "gelu",
|
9 |
+
"hidden_dropout_prob": 0.0,
|
10 |
+
"hidden_size": 768,
|
11 |
+
"id2label": {
|
12 |
+
"0": "blue_jellyfish",
|
13 |
+
"1": "barrel_jellyfish",
|
14 |
+
"2": "mauve_stinger_jellyfish",
|
15 |
+
"3": "Moon_jellyfish",
|
16 |
+
"4": "compass_jellyfish",
|
17 |
+
"5": "lions_mane_jellyfish"
|
18 |
+
},
|
19 |
+
"image_size": 224,
|
20 |
+
"initializer_range": 0.02,
|
21 |
+
"intermediate_size": 3072,
|
22 |
+
"label2id": {
|
23 |
+
"Moon_jellyfish": 3,
|
24 |
+
"barrel_jellyfish": 1,
|
25 |
+
"blue_jellyfish": 0,
|
26 |
+
"compass_jellyfish": 4,
|
27 |
+
"lions_mane_jellyfish": 5,
|
28 |
+
"mauve_stinger_jellyfish": 2
|
29 |
+
},
|
30 |
+
"layer_norm_eps": 1e-12,
|
31 |
+
"model_type": "vit",
|
32 |
+
"num_attention_heads": 12,
|
33 |
+
"num_channels": 3,
|
34 |
+
"num_hidden_layers": 12,
|
35 |
+
"patch_size": 16,
|
36 |
+
"problem_type": "single_label_classification",
|
37 |
+
"qkv_bias": true,
|
38 |
+
"torch_dtype": "float32",
|
39 |
+
"transformers_version": "4.34.1"
|
40 |
+
}
|
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 |
+
0.5,
|
7 |
+
0.5,
|
8 |
+
0.5
|
9 |
+
],
|
10 |
+
"image_processor_type": "ViTImageProcessor",
|
11 |
+
"image_std": [
|
12 |
+
0.5,
|
13 |
+
0.5,
|
14 |
+
0.5
|
15 |
+
],
|
16 |
+
"resample": 2,
|
17 |
+
"rescale_factor": 0.00392156862745098,
|
18 |
+
"size": {
|
19 |
+
"height": 224,
|
20 |
+
"width": 224
|
21 |
+
}
|
22 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1c9b83da3579395b4535b7fcc3edcca10fe7318386f18f860ef9102bf5e322aa
|
3 |
+
size 343281005
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:031a7c8aed93814186c29423c7024491fbb7d91a2310f465580903f80fef8344
|
3 |
+
size 4027
|