Training in progress, epoch 1, checkpoint
Browse files- last-checkpoint/config.json +65 -0
- last-checkpoint/model.safetensors +3 -0
- last-checkpoint/optimizer.pt +3 -0
- last-checkpoint/preprocessor_config.json +29 -0
- last-checkpoint/rng_state.pth +3 -0
- last-checkpoint/scheduler.pt +3 -0
- last-checkpoint/trainer_state.json +171 -0
- last-checkpoint/training_args.bin +3 -0
last-checkpoint/config.json
ADDED
@@ -0,0 +1,65 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "facebook/detr-resnet-50",
|
3 |
+
"activation_dropout": 0.0,
|
4 |
+
"activation_function": "relu",
|
5 |
+
"architectures": [
|
6 |
+
"DetrForObjectDetection"
|
7 |
+
],
|
8 |
+
"attention_dropout": 0.0,
|
9 |
+
"auxiliary_loss": false,
|
10 |
+
"backbone": "resnet50",
|
11 |
+
"backbone_config": null,
|
12 |
+
"backbone_kwargs": {
|
13 |
+
"in_chans": 3,
|
14 |
+
"out_indices": [
|
15 |
+
1,
|
16 |
+
2,
|
17 |
+
3,
|
18 |
+
4
|
19 |
+
]
|
20 |
+
},
|
21 |
+
"bbox_cost": 5,
|
22 |
+
"bbox_loss_coefficient": 5,
|
23 |
+
"class_cost": 1,
|
24 |
+
"classifier_dropout": 0.0,
|
25 |
+
"d_model": 256,
|
26 |
+
"decoder_attention_heads": 8,
|
27 |
+
"decoder_ffn_dim": 2048,
|
28 |
+
"decoder_layerdrop": 0.0,
|
29 |
+
"decoder_layers": 6,
|
30 |
+
"dice_loss_coefficient": 1,
|
31 |
+
"dilation": false,
|
32 |
+
"dropout": 0.1,
|
33 |
+
"encoder_attention_heads": 8,
|
34 |
+
"encoder_ffn_dim": 2048,
|
35 |
+
"encoder_layerdrop": 0.0,
|
36 |
+
"encoder_layers": 6,
|
37 |
+
"eos_coefficient": 0.1,
|
38 |
+
"giou_cost": 2,
|
39 |
+
"giou_loss_coefficient": 2,
|
40 |
+
"id2label": {
|
41 |
+
"0": "chicken",
|
42 |
+
"1": "duck",
|
43 |
+
"2": "plant"
|
44 |
+
},
|
45 |
+
"init_std": 0.02,
|
46 |
+
"init_xavier_std": 1.0,
|
47 |
+
"is_encoder_decoder": true,
|
48 |
+
"label2id": {
|
49 |
+
"chicken": 0,
|
50 |
+
"duck": 1,
|
51 |
+
"plant": 2
|
52 |
+
},
|
53 |
+
"mask_loss_coefficient": 1,
|
54 |
+
"max_position_embeddings": 1024,
|
55 |
+
"model_type": "detr",
|
56 |
+
"num_channels": 3,
|
57 |
+
"num_hidden_layers": 6,
|
58 |
+
"num_queries": 100,
|
59 |
+
"position_embedding_type": "sine",
|
60 |
+
"scale_embedding": false,
|
61 |
+
"torch_dtype": "float32",
|
62 |
+
"transformers_version": "4.46.2",
|
63 |
+
"use_pretrained_backbone": true,
|
64 |
+
"use_timm_backbone": true
|
65 |
+
}
|
last-checkpoint/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ea51fcbfe25bbaa0958e2dd5e450d0362d2c687943f2f10a3723ad6e5b976bb7
|
3 |
+
size 166496880
|
last-checkpoint/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:10c6547b92e223346da6328ec91f8a52aecc0d286ee6c71ae433a37efd5bce61
|
3 |
+
size 330495866
|
last-checkpoint/preprocessor_config.json
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"do_convert_annotations": true,
|
3 |
+
"do_normalize": true,
|
4 |
+
"do_pad": true,
|
5 |
+
"do_rescale": true,
|
6 |
+
"do_resize": true,
|
7 |
+
"format": "coco_detection",
|
8 |
+
"image_mean": [
|
9 |
+
0.485,
|
10 |
+
0.456,
|
11 |
+
0.406
|
12 |
+
],
|
13 |
+
"image_processor_type": "DetrImageProcessor",
|
14 |
+
"image_std": [
|
15 |
+
0.229,
|
16 |
+
0.224,
|
17 |
+
0.225
|
18 |
+
],
|
19 |
+
"pad_size": {
|
20 |
+
"height": 480,
|
21 |
+
"width": 480
|
22 |
+
},
|
23 |
+
"resample": 2,
|
24 |
+
"rescale_factor": 0.00392156862745098,
|
25 |
+
"size": {
|
26 |
+
"height": 480,
|
27 |
+
"width": 480
|
28 |
+
}
|
29 |
+
}
|
last-checkpoint/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:80102c2ed7116fe515826ab6f9a361c705e0bd357c30f1258bdcf26128f862e8
|
3 |
+
size 14244
|
last-checkpoint/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7173c0fe85cede5b9a4816598dcc9e1616999a7e5656401e0a94269cd8bf4cd3
|
3 |
+
size 1064
|
last-checkpoint/trainer_state.json
ADDED
@@ -0,0 +1,171 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 1.3226262331008911,
|
3 |
+
"best_model_checkpoint": "chickens-composite-201616161616-150-epochs-wo-transform-metrics-test-shfld/checkpoint-500",
|
4 |
+
"epoch": 1.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 500,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.06,
|
13 |
+
"grad_norm": 47.82271957397461,
|
14 |
+
"learning_rate": 9.99999605215876e-06,
|
15 |
+
"loss": 2.2,
|
16 |
+
"step": 30
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.12,
|
20 |
+
"grad_norm": 84.58082580566406,
|
21 |
+
"learning_rate": 9.999984208641271e-06,
|
22 |
+
"loss": 2.0202,
|
23 |
+
"step": 60
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.18,
|
27 |
+
"grad_norm": 62.93268585205078,
|
28 |
+
"learning_rate": 9.999964469466236e-06,
|
29 |
+
"loss": 1.8138,
|
30 |
+
"step": 90
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.24,
|
34 |
+
"grad_norm": 58.002166748046875,
|
35 |
+
"learning_rate": 9.99993683466483e-06,
|
36 |
+
"loss": 1.7422,
|
37 |
+
"step": 120
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.3,
|
41 |
+
"grad_norm": 91.62603759765625,
|
42 |
+
"learning_rate": 9.999901304280686e-06,
|
43 |
+
"loss": 1.6313,
|
44 |
+
"step": 150
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.36,
|
48 |
+
"grad_norm": 59.092445373535156,
|
49 |
+
"learning_rate": 9.999857878369917e-06,
|
50 |
+
"loss": 1.6138,
|
51 |
+
"step": 180
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.42,
|
55 |
+
"grad_norm": 41.530330657958984,
|
56 |
+
"learning_rate": 9.999806557001092e-06,
|
57 |
+
"loss": 1.6983,
|
58 |
+
"step": 210
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.48,
|
62 |
+
"grad_norm": 38.27995681762695,
|
63 |
+
"learning_rate": 9.99974734025526e-06,
|
64 |
+
"loss": 1.5454,
|
65 |
+
"step": 240
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.54,
|
69 |
+
"grad_norm": 56.726383209228516,
|
70 |
+
"learning_rate": 9.99968022822593e-06,
|
71 |
+
"loss": 1.6066,
|
72 |
+
"step": 270
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.6,
|
76 |
+
"grad_norm": 46.108367919921875,
|
77 |
+
"learning_rate": 9.999605221019082e-06,
|
78 |
+
"loss": 1.5964,
|
79 |
+
"step": 300
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.66,
|
83 |
+
"grad_norm": 45.66254806518555,
|
84 |
+
"learning_rate": 9.99952231875316e-06,
|
85 |
+
"loss": 1.5644,
|
86 |
+
"step": 330
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.72,
|
90 |
+
"grad_norm": 51.03472900390625,
|
91 |
+
"learning_rate": 9.999431521559081e-06,
|
92 |
+
"loss": 1.5523,
|
93 |
+
"step": 360
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.78,
|
97 |
+
"grad_norm": 40.366737365722656,
|
98 |
+
"learning_rate": 9.999332829580227e-06,
|
99 |
+
"loss": 1.5599,
|
100 |
+
"step": 390
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.84,
|
104 |
+
"grad_norm": 71.12183380126953,
|
105 |
+
"learning_rate": 9.999226242972445e-06,
|
106 |
+
"loss": 1.6338,
|
107 |
+
"step": 420
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.9,
|
111 |
+
"grad_norm": 80.18052673339844,
|
112 |
+
"learning_rate": 9.999111761904046e-06,
|
113 |
+
"loss": 1.4786,
|
114 |
+
"step": 450
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.96,
|
118 |
+
"grad_norm": 86.5920639038086,
|
119 |
+
"learning_rate": 9.998989386555815e-06,
|
120 |
+
"loss": 1.4551,
|
121 |
+
"step": 480
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 1.0,
|
125 |
+
"eval_loss": 1.3226262331008911,
|
126 |
+
"eval_map": 0.1944,
|
127 |
+
"eval_map_50": 0.2674,
|
128 |
+
"eval_map_75": 0.2295,
|
129 |
+
"eval_map_chicken": 0.0578,
|
130 |
+
"eval_map_duck": 0.0,
|
131 |
+
"eval_map_large": 0.2465,
|
132 |
+
"eval_map_medium": 0.1092,
|
133 |
+
"eval_map_plant": 0.5256,
|
134 |
+
"eval_map_small": 0.0337,
|
135 |
+
"eval_mar_1": 0.0876,
|
136 |
+
"eval_mar_10": 0.3262,
|
137 |
+
"eval_mar_100": 0.4233,
|
138 |
+
"eval_mar_100_chicken": 0.5155,
|
139 |
+
"eval_mar_100_duck": 0.0,
|
140 |
+
"eval_mar_100_plant": 0.7545,
|
141 |
+
"eval_mar_large": 0.4322,
|
142 |
+
"eval_mar_medium": 0.4015,
|
143 |
+
"eval_mar_small": 0.13,
|
144 |
+
"eval_runtime": 6.5542,
|
145 |
+
"eval_samples_per_second": 15.257,
|
146 |
+
"eval_steps_per_second": 1.983,
|
147 |
+
"step": 500
|
148 |
+
}
|
149 |
+
],
|
150 |
+
"logging_steps": 30,
|
151 |
+
"max_steps": 75000,
|
152 |
+
"num_input_tokens_seen": 0,
|
153 |
+
"num_train_epochs": 150,
|
154 |
+
"save_steps": 10,
|
155 |
+
"stateful_callbacks": {
|
156 |
+
"TrainerControl": {
|
157 |
+
"args": {
|
158 |
+
"should_epoch_stop": false,
|
159 |
+
"should_evaluate": false,
|
160 |
+
"should_log": false,
|
161 |
+
"should_save": true,
|
162 |
+
"should_training_stop": false
|
163 |
+
},
|
164 |
+
"attributes": {}
|
165 |
+
}
|
166 |
+
},
|
167 |
+
"total_flos": 1.720115564544e+17,
|
168 |
+
"train_batch_size": 2,
|
169 |
+
"trial_name": null,
|
170 |
+
"trial_params": null
|
171 |
+
}
|
last-checkpoint/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5a4c96bb26ca57b8b6f0b3371b901871160b2ec78fccef142940ba4f8399333b
|
3 |
+
size 5432
|