Commit
·
b9fec44
1
Parent(s):
0c8e7cf
Upload folder using huggingface_hub
Browse files- .gitignore +1 -0
- checkpoint-100/config.json +82 -0
- checkpoint-100/optimizer.pt +3 -0
- checkpoint-100/pytorch_model.bin +3 -0
- checkpoint-100/rng_state.pth +3 -0
- checkpoint-100/scheduler.pt +3 -0
- checkpoint-100/trainer_state.json +711 -0
- checkpoint-100/training_args.bin +3 -0
- checkpoint-60/config.json +82 -0
- checkpoint-60/optimizer.pt +3 -0
- checkpoint-60/pytorch_model.bin +3 -0
- checkpoint-60/rng_state.pth +3 -0
- checkpoint-60/scheduler.pt +3 -0
- checkpoint-60/trainer_state.json +433 -0
- checkpoint-60/training_args.bin +3 -0
- checkpoint-80/config.json +82 -0
- checkpoint-80/optimizer.pt +3 -0
- checkpoint-80/pytorch_model.bin +3 -0
- checkpoint-80/rng_state.pth +3 -0
- checkpoint-80/scheduler.pt +3 -0
- checkpoint-80/trainer_state.json +572 -0
- checkpoint-80/training_args.bin +3 -0
- config.json +82 -0
- preprocessor_config.json +23 -0
- pytorch_model.bin +3 -0
- runs/Jul11_16-48-07_8bd8190397e4/events.out.tfevents.1689094148.8bd8190397e4.5988.2 +3 -0
- training_args.bin +3 -0
.gitignore
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
checkpoint-*/
|
checkpoint-100/config.json
ADDED
|
@@ -0,0 +1,82 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "nvidia/mit-b2",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"SegformerForSemanticSegmentation"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.0,
|
| 7 |
+
"classifier_dropout_prob": 0.1,
|
| 8 |
+
"decoder_hidden_size": 768,
|
| 9 |
+
"depths": [
|
| 10 |
+
3,
|
| 11 |
+
4,
|
| 12 |
+
6,
|
| 13 |
+
3
|
| 14 |
+
],
|
| 15 |
+
"downsampling_rates": [
|
| 16 |
+
1,
|
| 17 |
+
4,
|
| 18 |
+
8,
|
| 19 |
+
16
|
| 20 |
+
],
|
| 21 |
+
"drop_path_rate": 0.1,
|
| 22 |
+
"hidden_act": "gelu",
|
| 23 |
+
"hidden_dropout_prob": 0.0,
|
| 24 |
+
"hidden_sizes": [
|
| 25 |
+
64,
|
| 26 |
+
128,
|
| 27 |
+
320,
|
| 28 |
+
512
|
| 29 |
+
],
|
| 30 |
+
"id2label": {
|
| 31 |
+
"0": "unlabeled",
|
| 32 |
+
"1": "dress",
|
| 33 |
+
"2": "mannequin",
|
| 34 |
+
"3": "background"
|
| 35 |
+
},
|
| 36 |
+
"image_size": 224,
|
| 37 |
+
"initializer_range": 0.02,
|
| 38 |
+
"label2id": {
|
| 39 |
+
"background": 3,
|
| 40 |
+
"dress": 1,
|
| 41 |
+
"mannequin": 2,
|
| 42 |
+
"unlabeled": 0
|
| 43 |
+
},
|
| 44 |
+
"layer_norm_eps": 1e-06,
|
| 45 |
+
"mlp_ratios": [
|
| 46 |
+
4,
|
| 47 |
+
4,
|
| 48 |
+
4,
|
| 49 |
+
4
|
| 50 |
+
],
|
| 51 |
+
"model_type": "segformer",
|
| 52 |
+
"num_attention_heads": [
|
| 53 |
+
1,
|
| 54 |
+
2,
|
| 55 |
+
5,
|
| 56 |
+
8
|
| 57 |
+
],
|
| 58 |
+
"num_channels": 3,
|
| 59 |
+
"num_encoder_blocks": 4,
|
| 60 |
+
"patch_sizes": [
|
| 61 |
+
7,
|
| 62 |
+
3,
|
| 63 |
+
3,
|
| 64 |
+
3
|
| 65 |
+
],
|
| 66 |
+
"reshape_last_stage": true,
|
| 67 |
+
"semantic_loss_ignore_index": 255,
|
| 68 |
+
"sr_ratios": [
|
| 69 |
+
8,
|
| 70 |
+
4,
|
| 71 |
+
2,
|
| 72 |
+
1
|
| 73 |
+
],
|
| 74 |
+
"strides": [
|
| 75 |
+
4,
|
| 76 |
+
2,
|
| 77 |
+
2,
|
| 78 |
+
2
|
| 79 |
+
],
|
| 80 |
+
"torch_dtype": "float32",
|
| 81 |
+
"transformers_version": "4.30.2"
|
| 82 |
+
}
|
checkpoint-100/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f1d59077416470f3a7bea7ad287501ec60d243efc8f291f85da0927191afbc6b
|
| 3 |
+
size 219007813
|
checkpoint-100/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7da41d5b1aefeb2cd38a865f93164f5f577426ffdf376820e0b6cfc631cff98d
|
| 3 |
+
size 109530621
|
checkpoint-100/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0610c415b71c6e3ceb9a1d51bb33d8077c89e29c29285c65c10d8776191b9ab8
|
| 3 |
+
size 13553
|
checkpoint-100/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8c998fb10f80c7c4827ff405961c397b8e5495d774ee15e3e638763d5189a548
|
| 3 |
+
size 627
|
checkpoint-100/trainer_state.json
ADDED
|
@@ -0,0 +1,711 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.04383450374007225,
|
| 3 |
+
"best_model_checkpoint": "./output/checkpoint-100",
|
| 4 |
+
"epoch": 50.0,
|
| 5 |
+
"global_step": 100,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.5,
|
| 12 |
+
"learning_rate": 5.94e-05,
|
| 13 |
+
"loss": 1.3812,
|
| 14 |
+
"step": 1
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 1.0,
|
| 18 |
+
"learning_rate": 5.88e-05,
|
| 19 |
+
"loss": 1.2124,
|
| 20 |
+
"step": 2
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 1.5,
|
| 24 |
+
"learning_rate": 5.82e-05,
|
| 25 |
+
"loss": 1.1456,
|
| 26 |
+
"step": 3
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 2.0,
|
| 30 |
+
"learning_rate": 5.76e-05,
|
| 31 |
+
"loss": 0.9318,
|
| 32 |
+
"step": 4
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 2.5,
|
| 36 |
+
"learning_rate": 5.6999999999999996e-05,
|
| 37 |
+
"loss": 0.8013,
|
| 38 |
+
"step": 5
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 3.0,
|
| 42 |
+
"learning_rate": 5.6399999999999995e-05,
|
| 43 |
+
"loss": 0.8656,
|
| 44 |
+
"step": 6
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 3.5,
|
| 48 |
+
"learning_rate": 5.58e-05,
|
| 49 |
+
"loss": 0.7525,
|
| 50 |
+
"step": 7
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 4.0,
|
| 54 |
+
"learning_rate": 5.520000000000001e-05,
|
| 55 |
+
"loss": 0.6735,
|
| 56 |
+
"step": 8
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 4.5,
|
| 60 |
+
"learning_rate": 5.4600000000000006e-05,
|
| 61 |
+
"loss": 0.5719,
|
| 62 |
+
"step": 9
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 5.0,
|
| 66 |
+
"learning_rate": 5.4000000000000005e-05,
|
| 67 |
+
"loss": 0.5665,
|
| 68 |
+
"step": 10
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 5.5,
|
| 72 |
+
"learning_rate": 5.3400000000000004e-05,
|
| 73 |
+
"loss": 0.5482,
|
| 74 |
+
"step": 11
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 6.0,
|
| 78 |
+
"learning_rate": 5.28e-05,
|
| 79 |
+
"loss": 0.3563,
|
| 80 |
+
"step": 12
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 6.5,
|
| 84 |
+
"learning_rate": 5.22e-05,
|
| 85 |
+
"loss": 0.3161,
|
| 86 |
+
"step": 13
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 7.0,
|
| 90 |
+
"learning_rate": 5.16e-05,
|
| 91 |
+
"loss": 0.3794,
|
| 92 |
+
"step": 14
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 7.5,
|
| 96 |
+
"learning_rate": 5.1e-05,
|
| 97 |
+
"loss": 0.322,
|
| 98 |
+
"step": 15
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 8.0,
|
| 102 |
+
"learning_rate": 5.04e-05,
|
| 103 |
+
"loss": 0.294,
|
| 104 |
+
"step": 16
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 8.5,
|
| 108 |
+
"learning_rate": 4.98e-05,
|
| 109 |
+
"loss": 0.2514,
|
| 110 |
+
"step": 17
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 9.0,
|
| 114 |
+
"learning_rate": 4.9199999999999997e-05,
|
| 115 |
+
"loss": 0.2338,
|
| 116 |
+
"step": 18
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 9.5,
|
| 120 |
+
"learning_rate": 4.86e-05,
|
| 121 |
+
"loss": 0.3549,
|
| 122 |
+
"step": 19
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 10.0,
|
| 126 |
+
"learning_rate": 4.8e-05,
|
| 127 |
+
"loss": 0.1691,
|
| 128 |
+
"step": 20
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 10.0,
|
| 132 |
+
"eval_accuracy_background": 0.988144527098831,
|
| 133 |
+
"eval_accuracy_dress": 0.991687871077184,
|
| 134 |
+
"eval_accuracy_mannequin": 0.4888352444176222,
|
| 135 |
+
"eval_accuracy_unlabeled": NaN,
|
| 136 |
+
"eval_iou_background": 0.9844285968374425,
|
| 137 |
+
"eval_iou_dress": 0.8830148780303603,
|
| 138 |
+
"eval_iou_mannequin": 0.3854389721627409,
|
| 139 |
+
"eval_iou_unlabeled": NaN,
|
| 140 |
+
"eval_loss": 0.43675652146339417,
|
| 141 |
+
"eval_mean_accuracy": 0.8228892141978791,
|
| 142 |
+
"eval_mean_iou": 0.7509608156768479,
|
| 143 |
+
"eval_overall_accuracy": 0.9821510314941406,
|
| 144 |
+
"eval_runtime": 1.9996,
|
| 145 |
+
"eval_samples_per_second": 0.5,
|
| 146 |
+
"eval_steps_per_second": 0.5,
|
| 147 |
+
"step": 20
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 10.5,
|
| 151 |
+
"learning_rate": 4.74e-05,
|
| 152 |
+
"loss": 0.138,
|
| 153 |
+
"step": 21
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 11.0,
|
| 157 |
+
"learning_rate": 4.6800000000000006e-05,
|
| 158 |
+
"loss": 0.188,
|
| 159 |
+
"step": 22
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 11.5,
|
| 163 |
+
"learning_rate": 4.6200000000000005e-05,
|
| 164 |
+
"loss": 0.1721,
|
| 165 |
+
"step": 23
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 12.0,
|
| 169 |
+
"learning_rate": 4.5600000000000004e-05,
|
| 170 |
+
"loss": 0.1189,
|
| 171 |
+
"step": 24
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 12.5,
|
| 175 |
+
"learning_rate": 4.5e-05,
|
| 176 |
+
"loss": 0.1652,
|
| 177 |
+
"step": 25
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 13.0,
|
| 181 |
+
"learning_rate": 4.44e-05,
|
| 182 |
+
"loss": 0.1086,
|
| 183 |
+
"step": 26
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 13.5,
|
| 187 |
+
"learning_rate": 4.38e-05,
|
| 188 |
+
"loss": 0.134,
|
| 189 |
+
"step": 27
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 14.0,
|
| 193 |
+
"learning_rate": 4.32e-05,
|
| 194 |
+
"loss": 0.0876,
|
| 195 |
+
"step": 28
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 14.5,
|
| 199 |
+
"learning_rate": 4.26e-05,
|
| 200 |
+
"loss": 0.1133,
|
| 201 |
+
"step": 29
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 15.0,
|
| 205 |
+
"learning_rate": 4.2e-05,
|
| 206 |
+
"loss": 0.1772,
|
| 207 |
+
"step": 30
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 15.5,
|
| 211 |
+
"learning_rate": 4.14e-05,
|
| 212 |
+
"loss": 0.0857,
|
| 213 |
+
"step": 31
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 16.0,
|
| 217 |
+
"learning_rate": 4.08e-05,
|
| 218 |
+
"loss": 0.0953,
|
| 219 |
+
"step": 32
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 16.5,
|
| 223 |
+
"learning_rate": 4.02e-05,
|
| 224 |
+
"loss": 0.0887,
|
| 225 |
+
"step": 33
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 17.0,
|
| 229 |
+
"learning_rate": 3.96e-05,
|
| 230 |
+
"loss": 0.0907,
|
| 231 |
+
"step": 34
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 17.5,
|
| 235 |
+
"learning_rate": 3.9e-05,
|
| 236 |
+
"loss": 0.0979,
|
| 237 |
+
"step": 35
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 18.0,
|
| 241 |
+
"learning_rate": 3.8400000000000005e-05,
|
| 242 |
+
"loss": 0.0798,
|
| 243 |
+
"step": 36
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 18.5,
|
| 247 |
+
"learning_rate": 3.7800000000000004e-05,
|
| 248 |
+
"loss": 0.0752,
|
| 249 |
+
"step": 37
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 19.0,
|
| 253 |
+
"learning_rate": 3.72e-05,
|
| 254 |
+
"loss": 0.0794,
|
| 255 |
+
"step": 38
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 19.5,
|
| 259 |
+
"learning_rate": 3.66e-05,
|
| 260 |
+
"loss": 0.1087,
|
| 261 |
+
"step": 39
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 20.0,
|
| 265 |
+
"learning_rate": 3.6e-05,
|
| 266 |
+
"loss": 0.0588,
|
| 267 |
+
"step": 40
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 20.0,
|
| 271 |
+
"eval_accuracy_background": 0.9961997874601488,
|
| 272 |
+
"eval_accuracy_dress": 0.9875742154368109,
|
| 273 |
+
"eval_accuracy_mannequin": 0.5470730235365118,
|
| 274 |
+
"eval_accuracy_unlabeled": NaN,
|
| 275 |
+
"eval_iou_background": 0.9908590466687525,
|
| 276 |
+
"eval_iou_dress": 0.9425645592163847,
|
| 277 |
+
"eval_iou_mannequin": 0.5024944567627494,
|
| 278 |
+
"eval_iou_unlabeled": NaN,
|
| 279 |
+
"eval_loss": 0.09112856537103653,
|
| 280 |
+
"eval_mean_accuracy": 0.8436156754778238,
|
| 281 |
+
"eval_mean_iou": 0.8119726875492955,
|
| 282 |
+
"eval_overall_accuracy": 0.98974609375,
|
| 283 |
+
"eval_runtime": 1.7988,
|
| 284 |
+
"eval_samples_per_second": 0.556,
|
| 285 |
+
"eval_steps_per_second": 0.556,
|
| 286 |
+
"step": 40
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 20.5,
|
| 290 |
+
"learning_rate": 3.54e-05,
|
| 291 |
+
"loss": 0.0618,
|
| 292 |
+
"step": 41
|
| 293 |
+
},
|
| 294 |
+
{
|
| 295 |
+
"epoch": 21.0,
|
| 296 |
+
"learning_rate": 3.48e-05,
|
| 297 |
+
"loss": 0.0688,
|
| 298 |
+
"step": 42
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"epoch": 21.5,
|
| 302 |
+
"learning_rate": 3.42e-05,
|
| 303 |
+
"loss": 0.0602,
|
| 304 |
+
"step": 43
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 22.0,
|
| 308 |
+
"learning_rate": 3.3600000000000004e-05,
|
| 309 |
+
"loss": 0.0644,
|
| 310 |
+
"step": 44
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 22.5,
|
| 314 |
+
"learning_rate": 3.3e-05,
|
| 315 |
+
"loss": 0.0695,
|
| 316 |
+
"step": 45
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 23.0,
|
| 320 |
+
"learning_rate": 3.24e-05,
|
| 321 |
+
"loss": 0.0711,
|
| 322 |
+
"step": 46
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 23.5,
|
| 326 |
+
"learning_rate": 3.18e-05,
|
| 327 |
+
"loss": 0.0574,
|
| 328 |
+
"step": 47
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 24.0,
|
| 332 |
+
"learning_rate": 3.12e-05,
|
| 333 |
+
"loss": 0.0688,
|
| 334 |
+
"step": 48
|
| 335 |
+
},
|
| 336 |
+
{
|
| 337 |
+
"epoch": 24.5,
|
| 338 |
+
"learning_rate": 3.06e-05,
|
| 339 |
+
"loss": 0.0552,
|
| 340 |
+
"step": 49
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 25.0,
|
| 344 |
+
"learning_rate": 3e-05,
|
| 345 |
+
"loss": 0.0564,
|
| 346 |
+
"step": 50
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 25.5,
|
| 350 |
+
"learning_rate": 2.94e-05,
|
| 351 |
+
"loss": 0.0645,
|
| 352 |
+
"step": 51
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 26.0,
|
| 356 |
+
"learning_rate": 2.88e-05,
|
| 357 |
+
"loss": 0.0552,
|
| 358 |
+
"step": 52
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"epoch": 26.5,
|
| 362 |
+
"learning_rate": 2.8199999999999998e-05,
|
| 363 |
+
"loss": 0.0596,
|
| 364 |
+
"step": 53
|
| 365 |
+
},
|
| 366 |
+
{
|
| 367 |
+
"epoch": 27.0,
|
| 368 |
+
"learning_rate": 2.7600000000000003e-05,
|
| 369 |
+
"loss": 0.0624,
|
| 370 |
+
"step": 54
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 27.5,
|
| 374 |
+
"learning_rate": 2.7000000000000002e-05,
|
| 375 |
+
"loss": 0.0641,
|
| 376 |
+
"step": 55
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 28.0,
|
| 380 |
+
"learning_rate": 2.64e-05,
|
| 381 |
+
"loss": 0.0495,
|
| 382 |
+
"step": 56
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 28.5,
|
| 386 |
+
"learning_rate": 2.58e-05,
|
| 387 |
+
"loss": 0.0458,
|
| 388 |
+
"step": 57
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 29.0,
|
| 392 |
+
"learning_rate": 2.52e-05,
|
| 393 |
+
"loss": 0.0583,
|
| 394 |
+
"step": 58
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 29.5,
|
| 398 |
+
"learning_rate": 2.4599999999999998e-05,
|
| 399 |
+
"loss": 0.0594,
|
| 400 |
+
"step": 59
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 30.0,
|
| 404 |
+
"learning_rate": 2.4e-05,
|
| 405 |
+
"loss": 0.0485,
|
| 406 |
+
"step": 60
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 30.0,
|
| 410 |
+
"eval_accuracy_background": 0.9971222104144527,
|
| 411 |
+
"eval_accuracy_dress": 0.9766751484308737,
|
| 412 |
+
"eval_accuracy_mannequin": 0.7314423657211828,
|
| 413 |
+
"eval_accuracy_unlabeled": NaN,
|
| 414 |
+
"eval_iou_background": 0.9929183986183893,
|
| 415 |
+
"eval_iou_dress": 0.9522037542379889,
|
| 416 |
+
"eval_iou_mannequin": 0.6330634630451815,
|
| 417 |
+
"eval_iou_unlabeled": NaN,
|
| 418 |
+
"eval_loss": 0.057673919945955276,
|
| 419 |
+
"eval_mean_accuracy": 0.901746574855503,
|
| 420 |
+
"eval_mean_iou": 0.8593952053005198,
|
| 421 |
+
"eval_overall_accuracy": 0.9919242858886719,
|
| 422 |
+
"eval_runtime": 1.8206,
|
| 423 |
+
"eval_samples_per_second": 0.549,
|
| 424 |
+
"eval_steps_per_second": 0.549,
|
| 425 |
+
"step": 60
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 30.5,
|
| 429 |
+
"learning_rate": 2.3400000000000003e-05,
|
| 430 |
+
"loss": 0.0463,
|
| 431 |
+
"step": 61
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 31.0,
|
| 435 |
+
"learning_rate": 2.2800000000000002e-05,
|
| 436 |
+
"loss": 0.0549,
|
| 437 |
+
"step": 62
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 31.5,
|
| 441 |
+
"learning_rate": 2.22e-05,
|
| 442 |
+
"loss": 0.0433,
|
| 443 |
+
"step": 63
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 32.0,
|
| 447 |
+
"learning_rate": 2.16e-05,
|
| 448 |
+
"loss": 0.0503,
|
| 449 |
+
"step": 64
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 32.5,
|
| 453 |
+
"learning_rate": 2.1e-05,
|
| 454 |
+
"loss": 0.0474,
|
| 455 |
+
"step": 65
|
| 456 |
+
},
|
| 457 |
+
{
|
| 458 |
+
"epoch": 33.0,
|
| 459 |
+
"learning_rate": 2.04e-05,
|
| 460 |
+
"loss": 0.0441,
|
| 461 |
+
"step": 66
|
| 462 |
+
},
|
| 463 |
+
{
|
| 464 |
+
"epoch": 33.5,
|
| 465 |
+
"learning_rate": 1.98e-05,
|
| 466 |
+
"loss": 0.0399,
|
| 467 |
+
"step": 67
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 34.0,
|
| 471 |
+
"learning_rate": 1.9200000000000003e-05,
|
| 472 |
+
"loss": 0.051,
|
| 473 |
+
"step": 68
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 34.5,
|
| 477 |
+
"learning_rate": 1.86e-05,
|
| 478 |
+
"loss": 0.0449,
|
| 479 |
+
"step": 69
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 35.0,
|
| 483 |
+
"learning_rate": 1.8e-05,
|
| 484 |
+
"loss": 0.0438,
|
| 485 |
+
"step": 70
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 35.5,
|
| 489 |
+
"learning_rate": 1.74e-05,
|
| 490 |
+
"loss": 0.0505,
|
| 491 |
+
"step": 71
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"epoch": 36.0,
|
| 495 |
+
"learning_rate": 1.6800000000000002e-05,
|
| 496 |
+
"loss": 0.0457,
|
| 497 |
+
"step": 72
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 36.5,
|
| 501 |
+
"learning_rate": 1.62e-05,
|
| 502 |
+
"loss": 0.0374,
|
| 503 |
+
"step": 73
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 37.0,
|
| 507 |
+
"learning_rate": 1.56e-05,
|
| 508 |
+
"loss": 0.0429,
|
| 509 |
+
"step": 74
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 37.5,
|
| 513 |
+
"learning_rate": 1.5e-05,
|
| 514 |
+
"loss": 0.0535,
|
| 515 |
+
"step": 75
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 38.0,
|
| 519 |
+
"learning_rate": 1.44e-05,
|
| 520 |
+
"loss": 0.0426,
|
| 521 |
+
"step": 76
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 38.5,
|
| 525 |
+
"learning_rate": 1.3800000000000002e-05,
|
| 526 |
+
"loss": 0.039,
|
| 527 |
+
"step": 77
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 39.0,
|
| 531 |
+
"learning_rate": 1.32e-05,
|
| 532 |
+
"loss": 0.0434,
|
| 533 |
+
"step": 78
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 39.5,
|
| 537 |
+
"learning_rate": 1.26e-05,
|
| 538 |
+
"loss": 0.1033,
|
| 539 |
+
"step": 79
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 40.0,
|
| 543 |
+
"learning_rate": 1.2e-05,
|
| 544 |
+
"loss": 0.0374,
|
| 545 |
+
"step": 80
|
| 546 |
+
},
|
| 547 |
+
{
|
| 548 |
+
"epoch": 40.0,
|
| 549 |
+
"eval_accuracy_background": 0.9981806588735388,
|
| 550 |
+
"eval_accuracy_dress": 0.9714164546225615,
|
| 551 |
+
"eval_accuracy_mannequin": 0.7269161134580567,
|
| 552 |
+
"eval_accuracy_unlabeled": NaN,
|
| 553 |
+
"eval_iou_background": 0.993371095947781,
|
| 554 |
+
"eval_iou_dress": 0.9530268358643644,
|
| 555 |
+
"eval_iou_mannequin": 0.6463643681244969,
|
| 556 |
+
"eval_iou_unlabeled": NaN,
|
| 557 |
+
"eval_loss": 0.04460417479276657,
|
| 558 |
+
"eval_mean_accuracy": 0.8988377423180524,
|
| 559 |
+
"eval_mean_iou": 0.8642540999788807,
|
| 560 |
+
"eval_overall_accuracy": 0.9923439025878906,
|
| 561 |
+
"eval_runtime": 3.063,
|
| 562 |
+
"eval_samples_per_second": 0.326,
|
| 563 |
+
"eval_steps_per_second": 0.326,
|
| 564 |
+
"step": 80
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 40.5,
|
| 568 |
+
"learning_rate": 1.1400000000000001e-05,
|
| 569 |
+
"loss": 0.054,
|
| 570 |
+
"step": 81
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 41.0,
|
| 574 |
+
"learning_rate": 1.08e-05,
|
| 575 |
+
"loss": 0.0437,
|
| 576 |
+
"step": 82
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 41.5,
|
| 580 |
+
"learning_rate": 1.02e-05,
|
| 581 |
+
"loss": 0.0457,
|
| 582 |
+
"step": 83
|
| 583 |
+
},
|
| 584 |
+
{
|
| 585 |
+
"epoch": 42.0,
|
| 586 |
+
"learning_rate": 9.600000000000001e-06,
|
| 587 |
+
"loss": 0.0374,
|
| 588 |
+
"step": 84
|
| 589 |
+
},
|
| 590 |
+
{
|
| 591 |
+
"epoch": 42.5,
|
| 592 |
+
"learning_rate": 9e-06,
|
| 593 |
+
"loss": 0.044,
|
| 594 |
+
"step": 85
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 43.0,
|
| 598 |
+
"learning_rate": 8.400000000000001e-06,
|
| 599 |
+
"loss": 0.0376,
|
| 600 |
+
"step": 86
|
| 601 |
+
},
|
| 602 |
+
{
|
| 603 |
+
"epoch": 43.5,
|
| 604 |
+
"learning_rate": 7.8e-06,
|
| 605 |
+
"loss": 0.0414,
|
| 606 |
+
"step": 87
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 44.0,
|
| 610 |
+
"learning_rate": 7.2e-06,
|
| 611 |
+
"loss": 0.0376,
|
| 612 |
+
"step": 88
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 44.5,
|
| 616 |
+
"learning_rate": 6.6e-06,
|
| 617 |
+
"loss": 0.04,
|
| 618 |
+
"step": 89
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 45.0,
|
| 622 |
+
"learning_rate": 6e-06,
|
| 623 |
+
"loss": 0.0448,
|
| 624 |
+
"step": 90
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 45.5,
|
| 628 |
+
"learning_rate": 5.4e-06,
|
| 629 |
+
"loss": 0.0375,
|
| 630 |
+
"step": 91
|
| 631 |
+
},
|
| 632 |
+
{
|
| 633 |
+
"epoch": 46.0,
|
| 634 |
+
"learning_rate": 4.800000000000001e-06,
|
| 635 |
+
"loss": 0.0426,
|
| 636 |
+
"step": 92
|
| 637 |
+
},
|
| 638 |
+
{
|
| 639 |
+
"epoch": 46.5,
|
| 640 |
+
"learning_rate": 4.2000000000000004e-06,
|
| 641 |
+
"loss": 0.0391,
|
| 642 |
+
"step": 93
|
| 643 |
+
},
|
| 644 |
+
{
|
| 645 |
+
"epoch": 47.0,
|
| 646 |
+
"learning_rate": 3.6e-06,
|
| 647 |
+
"loss": 0.0525,
|
| 648 |
+
"step": 94
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 47.5,
|
| 652 |
+
"learning_rate": 3e-06,
|
| 653 |
+
"loss": 0.0407,
|
| 654 |
+
"step": 95
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 48.0,
|
| 658 |
+
"learning_rate": 2.4000000000000003e-06,
|
| 659 |
+
"loss": 0.044,
|
| 660 |
+
"step": 96
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 48.5,
|
| 664 |
+
"learning_rate": 1.8e-06,
|
| 665 |
+
"loss": 0.0355,
|
| 666 |
+
"step": 97
|
| 667 |
+
},
|
| 668 |
+
{
|
| 669 |
+
"epoch": 49.0,
|
| 670 |
+
"learning_rate": 1.2000000000000002e-06,
|
| 671 |
+
"loss": 0.0419,
|
| 672 |
+
"step": 98
|
| 673 |
+
},
|
| 674 |
+
{
|
| 675 |
+
"epoch": 49.5,
|
| 676 |
+
"learning_rate": 6.000000000000001e-07,
|
| 677 |
+
"loss": 0.0417,
|
| 678 |
+
"step": 99
|
| 679 |
+
},
|
| 680 |
+
{
|
| 681 |
+
"epoch": 50.0,
|
| 682 |
+
"learning_rate": 0.0,
|
| 683 |
+
"loss": 0.0412,
|
| 684 |
+
"step": 100
|
| 685 |
+
},
|
| 686 |
+
{
|
| 687 |
+
"epoch": 50.0,
|
| 688 |
+
"eval_accuracy_background": 0.9986142401700319,
|
| 689 |
+
"eval_accuracy_dress": 0.9680237489397795,
|
| 690 |
+
"eval_accuracy_mannequin": 0.7175618587809294,
|
| 691 |
+
"eval_accuracy_unlabeled": NaN,
|
| 692 |
+
"eval_iou_background": 0.9932857529427682,
|
| 693 |
+
"eval_iou_dress": 0.9535864978902954,
|
| 694 |
+
"eval_iou_mannequin": 0.6407976286715171,
|
| 695 |
+
"eval_iou_unlabeled": NaN,
|
| 696 |
+
"eval_loss": 0.04383450374007225,
|
| 697 |
+
"eval_mean_accuracy": 0.8947332826302469,
|
| 698 |
+
"eval_mean_iou": 0.8625566265015269,
|
| 699 |
+
"eval_overall_accuracy": 0.9923095703125,
|
| 700 |
+
"eval_runtime": 1.9723,
|
| 701 |
+
"eval_samples_per_second": 0.507,
|
| 702 |
+
"eval_steps_per_second": 0.507,
|
| 703 |
+
"step": 100
|
| 704 |
+
}
|
| 705 |
+
],
|
| 706 |
+
"max_steps": 100,
|
| 707 |
+
"num_train_epochs": 50,
|
| 708 |
+
"total_flos": 2.581041512448e+16,
|
| 709 |
+
"trial_name": null,
|
| 710 |
+
"trial_params": null
|
| 711 |
+
}
|
checkpoint-100/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:db41b5b7dd1b4e7919196c94cd48fefe27753a561d95db18671d26e224301078
|
| 3 |
+
size 3963
|
checkpoint-60/config.json
ADDED
|
@@ -0,0 +1,82 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "nvidia/mit-b2",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"SegformerForSemanticSegmentation"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.0,
|
| 7 |
+
"classifier_dropout_prob": 0.1,
|
| 8 |
+
"decoder_hidden_size": 768,
|
| 9 |
+
"depths": [
|
| 10 |
+
3,
|
| 11 |
+
4,
|
| 12 |
+
6,
|
| 13 |
+
3
|
| 14 |
+
],
|
| 15 |
+
"downsampling_rates": [
|
| 16 |
+
1,
|
| 17 |
+
4,
|
| 18 |
+
8,
|
| 19 |
+
16
|
| 20 |
+
],
|
| 21 |
+
"drop_path_rate": 0.1,
|
| 22 |
+
"hidden_act": "gelu",
|
| 23 |
+
"hidden_dropout_prob": 0.0,
|
| 24 |
+
"hidden_sizes": [
|
| 25 |
+
64,
|
| 26 |
+
128,
|
| 27 |
+
320,
|
| 28 |
+
512
|
| 29 |
+
],
|
| 30 |
+
"id2label": {
|
| 31 |
+
"0": "unlabeled",
|
| 32 |
+
"1": "dress",
|
| 33 |
+
"2": "mannequin",
|
| 34 |
+
"3": "background"
|
| 35 |
+
},
|
| 36 |
+
"image_size": 224,
|
| 37 |
+
"initializer_range": 0.02,
|
| 38 |
+
"label2id": {
|
| 39 |
+
"background": 3,
|
| 40 |
+
"dress": 1,
|
| 41 |
+
"mannequin": 2,
|
| 42 |
+
"unlabeled": 0
|
| 43 |
+
},
|
| 44 |
+
"layer_norm_eps": 1e-06,
|
| 45 |
+
"mlp_ratios": [
|
| 46 |
+
4,
|
| 47 |
+
4,
|
| 48 |
+
4,
|
| 49 |
+
4
|
| 50 |
+
],
|
| 51 |
+
"model_type": "segformer",
|
| 52 |
+
"num_attention_heads": [
|
| 53 |
+
1,
|
| 54 |
+
2,
|
| 55 |
+
5,
|
| 56 |
+
8
|
| 57 |
+
],
|
| 58 |
+
"num_channels": 3,
|
| 59 |
+
"num_encoder_blocks": 4,
|
| 60 |
+
"patch_sizes": [
|
| 61 |
+
7,
|
| 62 |
+
3,
|
| 63 |
+
3,
|
| 64 |
+
3
|
| 65 |
+
],
|
| 66 |
+
"reshape_last_stage": true,
|
| 67 |
+
"semantic_loss_ignore_index": 255,
|
| 68 |
+
"sr_ratios": [
|
| 69 |
+
8,
|
| 70 |
+
4,
|
| 71 |
+
2,
|
| 72 |
+
1
|
| 73 |
+
],
|
| 74 |
+
"strides": [
|
| 75 |
+
4,
|
| 76 |
+
2,
|
| 77 |
+
2,
|
| 78 |
+
2
|
| 79 |
+
],
|
| 80 |
+
"torch_dtype": "float32",
|
| 81 |
+
"transformers_version": "4.30.2"
|
| 82 |
+
}
|
checkpoint-60/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:79a7263146e37a556d8d50715cb75915930947b65cd97d09849740bc5c11b561
|
| 3 |
+
size 219007813
|
checkpoint-60/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b7e9757808ea67033e87cc18581c13115d28ea8cca92c6a00eb157bdbe850421
|
| 3 |
+
size 109530621
|
checkpoint-60/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c91950f363ce2ef93e9b6c78d3152bb63681a747d759e355df047c654677b0bf
|
| 3 |
+
size 13553
|
checkpoint-60/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f09ddb2c3d9412d0881ed2644f5f9995b7fe91790a51dd235dda201e28b89d0c
|
| 3 |
+
size 627
|
checkpoint-60/trainer_state.json
ADDED
|
@@ -0,0 +1,433 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.057673919945955276,
|
| 3 |
+
"best_model_checkpoint": "./output/checkpoint-60",
|
| 4 |
+
"epoch": 30.0,
|
| 5 |
+
"global_step": 60,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.5,
|
| 12 |
+
"learning_rate": 5.94e-05,
|
| 13 |
+
"loss": 1.3812,
|
| 14 |
+
"step": 1
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 1.0,
|
| 18 |
+
"learning_rate": 5.88e-05,
|
| 19 |
+
"loss": 1.2124,
|
| 20 |
+
"step": 2
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 1.5,
|
| 24 |
+
"learning_rate": 5.82e-05,
|
| 25 |
+
"loss": 1.1456,
|
| 26 |
+
"step": 3
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 2.0,
|
| 30 |
+
"learning_rate": 5.76e-05,
|
| 31 |
+
"loss": 0.9318,
|
| 32 |
+
"step": 4
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 2.5,
|
| 36 |
+
"learning_rate": 5.6999999999999996e-05,
|
| 37 |
+
"loss": 0.8013,
|
| 38 |
+
"step": 5
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 3.0,
|
| 42 |
+
"learning_rate": 5.6399999999999995e-05,
|
| 43 |
+
"loss": 0.8656,
|
| 44 |
+
"step": 6
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 3.5,
|
| 48 |
+
"learning_rate": 5.58e-05,
|
| 49 |
+
"loss": 0.7525,
|
| 50 |
+
"step": 7
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 4.0,
|
| 54 |
+
"learning_rate": 5.520000000000001e-05,
|
| 55 |
+
"loss": 0.6735,
|
| 56 |
+
"step": 8
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 4.5,
|
| 60 |
+
"learning_rate": 5.4600000000000006e-05,
|
| 61 |
+
"loss": 0.5719,
|
| 62 |
+
"step": 9
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 5.0,
|
| 66 |
+
"learning_rate": 5.4000000000000005e-05,
|
| 67 |
+
"loss": 0.5665,
|
| 68 |
+
"step": 10
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 5.5,
|
| 72 |
+
"learning_rate": 5.3400000000000004e-05,
|
| 73 |
+
"loss": 0.5482,
|
| 74 |
+
"step": 11
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 6.0,
|
| 78 |
+
"learning_rate": 5.28e-05,
|
| 79 |
+
"loss": 0.3563,
|
| 80 |
+
"step": 12
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 6.5,
|
| 84 |
+
"learning_rate": 5.22e-05,
|
| 85 |
+
"loss": 0.3161,
|
| 86 |
+
"step": 13
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 7.0,
|
| 90 |
+
"learning_rate": 5.16e-05,
|
| 91 |
+
"loss": 0.3794,
|
| 92 |
+
"step": 14
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 7.5,
|
| 96 |
+
"learning_rate": 5.1e-05,
|
| 97 |
+
"loss": 0.322,
|
| 98 |
+
"step": 15
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 8.0,
|
| 102 |
+
"learning_rate": 5.04e-05,
|
| 103 |
+
"loss": 0.294,
|
| 104 |
+
"step": 16
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 8.5,
|
| 108 |
+
"learning_rate": 4.98e-05,
|
| 109 |
+
"loss": 0.2514,
|
| 110 |
+
"step": 17
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 9.0,
|
| 114 |
+
"learning_rate": 4.9199999999999997e-05,
|
| 115 |
+
"loss": 0.2338,
|
| 116 |
+
"step": 18
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 9.5,
|
| 120 |
+
"learning_rate": 4.86e-05,
|
| 121 |
+
"loss": 0.3549,
|
| 122 |
+
"step": 19
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 10.0,
|
| 126 |
+
"learning_rate": 4.8e-05,
|
| 127 |
+
"loss": 0.1691,
|
| 128 |
+
"step": 20
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 10.0,
|
| 132 |
+
"eval_accuracy_background": 0.988144527098831,
|
| 133 |
+
"eval_accuracy_dress": 0.991687871077184,
|
| 134 |
+
"eval_accuracy_mannequin": 0.4888352444176222,
|
| 135 |
+
"eval_accuracy_unlabeled": NaN,
|
| 136 |
+
"eval_iou_background": 0.9844285968374425,
|
| 137 |
+
"eval_iou_dress": 0.8830148780303603,
|
| 138 |
+
"eval_iou_mannequin": 0.3854389721627409,
|
| 139 |
+
"eval_iou_unlabeled": NaN,
|
| 140 |
+
"eval_loss": 0.43675652146339417,
|
| 141 |
+
"eval_mean_accuracy": 0.8228892141978791,
|
| 142 |
+
"eval_mean_iou": 0.7509608156768479,
|
| 143 |
+
"eval_overall_accuracy": 0.9821510314941406,
|
| 144 |
+
"eval_runtime": 1.9996,
|
| 145 |
+
"eval_samples_per_second": 0.5,
|
| 146 |
+
"eval_steps_per_second": 0.5,
|
| 147 |
+
"step": 20
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 10.5,
|
| 151 |
+
"learning_rate": 4.74e-05,
|
| 152 |
+
"loss": 0.138,
|
| 153 |
+
"step": 21
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 11.0,
|
| 157 |
+
"learning_rate": 4.6800000000000006e-05,
|
| 158 |
+
"loss": 0.188,
|
| 159 |
+
"step": 22
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 11.5,
|
| 163 |
+
"learning_rate": 4.6200000000000005e-05,
|
| 164 |
+
"loss": 0.1721,
|
| 165 |
+
"step": 23
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 12.0,
|
| 169 |
+
"learning_rate": 4.5600000000000004e-05,
|
| 170 |
+
"loss": 0.1189,
|
| 171 |
+
"step": 24
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 12.5,
|
| 175 |
+
"learning_rate": 4.5e-05,
|
| 176 |
+
"loss": 0.1652,
|
| 177 |
+
"step": 25
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 13.0,
|
| 181 |
+
"learning_rate": 4.44e-05,
|
| 182 |
+
"loss": 0.1086,
|
| 183 |
+
"step": 26
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 13.5,
|
| 187 |
+
"learning_rate": 4.38e-05,
|
| 188 |
+
"loss": 0.134,
|
| 189 |
+
"step": 27
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 14.0,
|
| 193 |
+
"learning_rate": 4.32e-05,
|
| 194 |
+
"loss": 0.0876,
|
| 195 |
+
"step": 28
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 14.5,
|
| 199 |
+
"learning_rate": 4.26e-05,
|
| 200 |
+
"loss": 0.1133,
|
| 201 |
+
"step": 29
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 15.0,
|
| 205 |
+
"learning_rate": 4.2e-05,
|
| 206 |
+
"loss": 0.1772,
|
| 207 |
+
"step": 30
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 15.5,
|
| 211 |
+
"learning_rate": 4.14e-05,
|
| 212 |
+
"loss": 0.0857,
|
| 213 |
+
"step": 31
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 16.0,
|
| 217 |
+
"learning_rate": 4.08e-05,
|
| 218 |
+
"loss": 0.0953,
|
| 219 |
+
"step": 32
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 16.5,
|
| 223 |
+
"learning_rate": 4.02e-05,
|
| 224 |
+
"loss": 0.0887,
|
| 225 |
+
"step": 33
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 17.0,
|
| 229 |
+
"learning_rate": 3.96e-05,
|
| 230 |
+
"loss": 0.0907,
|
| 231 |
+
"step": 34
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 17.5,
|
| 235 |
+
"learning_rate": 3.9e-05,
|
| 236 |
+
"loss": 0.0979,
|
| 237 |
+
"step": 35
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 18.0,
|
| 241 |
+
"learning_rate": 3.8400000000000005e-05,
|
| 242 |
+
"loss": 0.0798,
|
| 243 |
+
"step": 36
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 18.5,
|
| 247 |
+
"learning_rate": 3.7800000000000004e-05,
|
| 248 |
+
"loss": 0.0752,
|
| 249 |
+
"step": 37
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 19.0,
|
| 253 |
+
"learning_rate": 3.72e-05,
|
| 254 |
+
"loss": 0.0794,
|
| 255 |
+
"step": 38
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 19.5,
|
| 259 |
+
"learning_rate": 3.66e-05,
|
| 260 |
+
"loss": 0.1087,
|
| 261 |
+
"step": 39
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 20.0,
|
| 265 |
+
"learning_rate": 3.6e-05,
|
| 266 |
+
"loss": 0.0588,
|
| 267 |
+
"step": 40
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 20.0,
|
| 271 |
+
"eval_accuracy_background": 0.9961997874601488,
|
| 272 |
+
"eval_accuracy_dress": 0.9875742154368109,
|
| 273 |
+
"eval_accuracy_mannequin": 0.5470730235365118,
|
| 274 |
+
"eval_accuracy_unlabeled": NaN,
|
| 275 |
+
"eval_iou_background": 0.9908590466687525,
|
| 276 |
+
"eval_iou_dress": 0.9425645592163847,
|
| 277 |
+
"eval_iou_mannequin": 0.5024944567627494,
|
| 278 |
+
"eval_iou_unlabeled": NaN,
|
| 279 |
+
"eval_loss": 0.09112856537103653,
|
| 280 |
+
"eval_mean_accuracy": 0.8436156754778238,
|
| 281 |
+
"eval_mean_iou": 0.8119726875492955,
|
| 282 |
+
"eval_overall_accuracy": 0.98974609375,
|
| 283 |
+
"eval_runtime": 1.7988,
|
| 284 |
+
"eval_samples_per_second": 0.556,
|
| 285 |
+
"eval_steps_per_second": 0.556,
|
| 286 |
+
"step": 40
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 20.5,
|
| 290 |
+
"learning_rate": 3.54e-05,
|
| 291 |
+
"loss": 0.0618,
|
| 292 |
+
"step": 41
|
| 293 |
+
},
|
| 294 |
+
{
|
| 295 |
+
"epoch": 21.0,
|
| 296 |
+
"learning_rate": 3.48e-05,
|
| 297 |
+
"loss": 0.0688,
|
| 298 |
+
"step": 42
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"epoch": 21.5,
|
| 302 |
+
"learning_rate": 3.42e-05,
|
| 303 |
+
"loss": 0.0602,
|
| 304 |
+
"step": 43
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 22.0,
|
| 308 |
+
"learning_rate": 3.3600000000000004e-05,
|
| 309 |
+
"loss": 0.0644,
|
| 310 |
+
"step": 44
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 22.5,
|
| 314 |
+
"learning_rate": 3.3e-05,
|
| 315 |
+
"loss": 0.0695,
|
| 316 |
+
"step": 45
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 23.0,
|
| 320 |
+
"learning_rate": 3.24e-05,
|
| 321 |
+
"loss": 0.0711,
|
| 322 |
+
"step": 46
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 23.5,
|
| 326 |
+
"learning_rate": 3.18e-05,
|
| 327 |
+
"loss": 0.0574,
|
| 328 |
+
"step": 47
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 24.0,
|
| 332 |
+
"learning_rate": 3.12e-05,
|
| 333 |
+
"loss": 0.0688,
|
| 334 |
+
"step": 48
|
| 335 |
+
},
|
| 336 |
+
{
|
| 337 |
+
"epoch": 24.5,
|
| 338 |
+
"learning_rate": 3.06e-05,
|
| 339 |
+
"loss": 0.0552,
|
| 340 |
+
"step": 49
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 25.0,
|
| 344 |
+
"learning_rate": 3e-05,
|
| 345 |
+
"loss": 0.0564,
|
| 346 |
+
"step": 50
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 25.5,
|
| 350 |
+
"learning_rate": 2.94e-05,
|
| 351 |
+
"loss": 0.0645,
|
| 352 |
+
"step": 51
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 26.0,
|
| 356 |
+
"learning_rate": 2.88e-05,
|
| 357 |
+
"loss": 0.0552,
|
| 358 |
+
"step": 52
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"epoch": 26.5,
|
| 362 |
+
"learning_rate": 2.8199999999999998e-05,
|
| 363 |
+
"loss": 0.0596,
|
| 364 |
+
"step": 53
|
| 365 |
+
},
|
| 366 |
+
{
|
| 367 |
+
"epoch": 27.0,
|
| 368 |
+
"learning_rate": 2.7600000000000003e-05,
|
| 369 |
+
"loss": 0.0624,
|
| 370 |
+
"step": 54
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 27.5,
|
| 374 |
+
"learning_rate": 2.7000000000000002e-05,
|
| 375 |
+
"loss": 0.0641,
|
| 376 |
+
"step": 55
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 28.0,
|
| 380 |
+
"learning_rate": 2.64e-05,
|
| 381 |
+
"loss": 0.0495,
|
| 382 |
+
"step": 56
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 28.5,
|
| 386 |
+
"learning_rate": 2.58e-05,
|
| 387 |
+
"loss": 0.0458,
|
| 388 |
+
"step": 57
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 29.0,
|
| 392 |
+
"learning_rate": 2.52e-05,
|
| 393 |
+
"loss": 0.0583,
|
| 394 |
+
"step": 58
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 29.5,
|
| 398 |
+
"learning_rate": 2.4599999999999998e-05,
|
| 399 |
+
"loss": 0.0594,
|
| 400 |
+
"step": 59
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 30.0,
|
| 404 |
+
"learning_rate": 2.4e-05,
|
| 405 |
+
"loss": 0.0485,
|
| 406 |
+
"step": 60
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 30.0,
|
| 410 |
+
"eval_accuracy_background": 0.9971222104144527,
|
| 411 |
+
"eval_accuracy_dress": 0.9766751484308737,
|
| 412 |
+
"eval_accuracy_mannequin": 0.7314423657211828,
|
| 413 |
+
"eval_accuracy_unlabeled": NaN,
|
| 414 |
+
"eval_iou_background": 0.9929183986183893,
|
| 415 |
+
"eval_iou_dress": 0.9522037542379889,
|
| 416 |
+
"eval_iou_mannequin": 0.6330634630451815,
|
| 417 |
+
"eval_iou_unlabeled": NaN,
|
| 418 |
+
"eval_loss": 0.057673919945955276,
|
| 419 |
+
"eval_mean_accuracy": 0.901746574855503,
|
| 420 |
+
"eval_mean_iou": 0.8593952053005198,
|
| 421 |
+
"eval_overall_accuracy": 0.9919242858886719,
|
| 422 |
+
"eval_runtime": 1.8206,
|
| 423 |
+
"eval_samples_per_second": 0.549,
|
| 424 |
+
"eval_steps_per_second": 0.549,
|
| 425 |
+
"step": 60
|
| 426 |
+
}
|
| 427 |
+
],
|
| 428 |
+
"max_steps": 100,
|
| 429 |
+
"num_train_epochs": 50,
|
| 430 |
+
"total_flos": 1.5486249074688e+16,
|
| 431 |
+
"trial_name": null,
|
| 432 |
+
"trial_params": null
|
| 433 |
+
}
|
checkpoint-60/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:db41b5b7dd1b4e7919196c94cd48fefe27753a561d95db18671d26e224301078
|
| 3 |
+
size 3963
|
checkpoint-80/config.json
ADDED
|
@@ -0,0 +1,82 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "nvidia/mit-b2",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"SegformerForSemanticSegmentation"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.0,
|
| 7 |
+
"classifier_dropout_prob": 0.1,
|
| 8 |
+
"decoder_hidden_size": 768,
|
| 9 |
+
"depths": [
|
| 10 |
+
3,
|
| 11 |
+
4,
|
| 12 |
+
6,
|
| 13 |
+
3
|
| 14 |
+
],
|
| 15 |
+
"downsampling_rates": [
|
| 16 |
+
1,
|
| 17 |
+
4,
|
| 18 |
+
8,
|
| 19 |
+
16
|
| 20 |
+
],
|
| 21 |
+
"drop_path_rate": 0.1,
|
| 22 |
+
"hidden_act": "gelu",
|
| 23 |
+
"hidden_dropout_prob": 0.0,
|
| 24 |
+
"hidden_sizes": [
|
| 25 |
+
64,
|
| 26 |
+
128,
|
| 27 |
+
320,
|
| 28 |
+
512
|
| 29 |
+
],
|
| 30 |
+
"id2label": {
|
| 31 |
+
"0": "unlabeled",
|
| 32 |
+
"1": "dress",
|
| 33 |
+
"2": "mannequin",
|
| 34 |
+
"3": "background"
|
| 35 |
+
},
|
| 36 |
+
"image_size": 224,
|
| 37 |
+
"initializer_range": 0.02,
|
| 38 |
+
"label2id": {
|
| 39 |
+
"background": 3,
|
| 40 |
+
"dress": 1,
|
| 41 |
+
"mannequin": 2,
|
| 42 |
+
"unlabeled": 0
|
| 43 |
+
},
|
| 44 |
+
"layer_norm_eps": 1e-06,
|
| 45 |
+
"mlp_ratios": [
|
| 46 |
+
4,
|
| 47 |
+
4,
|
| 48 |
+
4,
|
| 49 |
+
4
|
| 50 |
+
],
|
| 51 |
+
"model_type": "segformer",
|
| 52 |
+
"num_attention_heads": [
|
| 53 |
+
1,
|
| 54 |
+
2,
|
| 55 |
+
5,
|
| 56 |
+
8
|
| 57 |
+
],
|
| 58 |
+
"num_channels": 3,
|
| 59 |
+
"num_encoder_blocks": 4,
|
| 60 |
+
"patch_sizes": [
|
| 61 |
+
7,
|
| 62 |
+
3,
|
| 63 |
+
3,
|
| 64 |
+
3
|
| 65 |
+
],
|
| 66 |
+
"reshape_last_stage": true,
|
| 67 |
+
"semantic_loss_ignore_index": 255,
|
| 68 |
+
"sr_ratios": [
|
| 69 |
+
8,
|
| 70 |
+
4,
|
| 71 |
+
2,
|
| 72 |
+
1
|
| 73 |
+
],
|
| 74 |
+
"strides": [
|
| 75 |
+
4,
|
| 76 |
+
2,
|
| 77 |
+
2,
|
| 78 |
+
2
|
| 79 |
+
],
|
| 80 |
+
"torch_dtype": "float32",
|
| 81 |
+
"transformers_version": "4.30.2"
|
| 82 |
+
}
|
checkpoint-80/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1634155829effbadbe7b4393eaedd51e1385c07655148ad1a8cc6eb38b2ade5f
|
| 3 |
+
size 219007813
|
checkpoint-80/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d09c58dcb6bbdf4c0f57b47b9b47a6831991e804dd2ed7868081cd1b5d59c046
|
| 3 |
+
size 109530621
|
checkpoint-80/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8a4863e1cf768e62a183007cd8a8fbb768e0520a71d8fc483f6c063b98ffedc1
|
| 3 |
+
size 13553
|
checkpoint-80/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0da22b4a1f2b8530d1d93383e33eae905337c89df2ceda985a613121069713c7
|
| 3 |
+
size 627
|
checkpoint-80/trainer_state.json
ADDED
|
@@ -0,0 +1,572 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.04460417479276657,
|
| 3 |
+
"best_model_checkpoint": "./output/checkpoint-80",
|
| 4 |
+
"epoch": 40.0,
|
| 5 |
+
"global_step": 80,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.5,
|
| 12 |
+
"learning_rate": 5.94e-05,
|
| 13 |
+
"loss": 1.3812,
|
| 14 |
+
"step": 1
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 1.0,
|
| 18 |
+
"learning_rate": 5.88e-05,
|
| 19 |
+
"loss": 1.2124,
|
| 20 |
+
"step": 2
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 1.5,
|
| 24 |
+
"learning_rate": 5.82e-05,
|
| 25 |
+
"loss": 1.1456,
|
| 26 |
+
"step": 3
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 2.0,
|
| 30 |
+
"learning_rate": 5.76e-05,
|
| 31 |
+
"loss": 0.9318,
|
| 32 |
+
"step": 4
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 2.5,
|
| 36 |
+
"learning_rate": 5.6999999999999996e-05,
|
| 37 |
+
"loss": 0.8013,
|
| 38 |
+
"step": 5
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 3.0,
|
| 42 |
+
"learning_rate": 5.6399999999999995e-05,
|
| 43 |
+
"loss": 0.8656,
|
| 44 |
+
"step": 6
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 3.5,
|
| 48 |
+
"learning_rate": 5.58e-05,
|
| 49 |
+
"loss": 0.7525,
|
| 50 |
+
"step": 7
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 4.0,
|
| 54 |
+
"learning_rate": 5.520000000000001e-05,
|
| 55 |
+
"loss": 0.6735,
|
| 56 |
+
"step": 8
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 4.5,
|
| 60 |
+
"learning_rate": 5.4600000000000006e-05,
|
| 61 |
+
"loss": 0.5719,
|
| 62 |
+
"step": 9
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 5.0,
|
| 66 |
+
"learning_rate": 5.4000000000000005e-05,
|
| 67 |
+
"loss": 0.5665,
|
| 68 |
+
"step": 10
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 5.5,
|
| 72 |
+
"learning_rate": 5.3400000000000004e-05,
|
| 73 |
+
"loss": 0.5482,
|
| 74 |
+
"step": 11
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 6.0,
|
| 78 |
+
"learning_rate": 5.28e-05,
|
| 79 |
+
"loss": 0.3563,
|
| 80 |
+
"step": 12
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 6.5,
|
| 84 |
+
"learning_rate": 5.22e-05,
|
| 85 |
+
"loss": 0.3161,
|
| 86 |
+
"step": 13
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 7.0,
|
| 90 |
+
"learning_rate": 5.16e-05,
|
| 91 |
+
"loss": 0.3794,
|
| 92 |
+
"step": 14
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 7.5,
|
| 96 |
+
"learning_rate": 5.1e-05,
|
| 97 |
+
"loss": 0.322,
|
| 98 |
+
"step": 15
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 8.0,
|
| 102 |
+
"learning_rate": 5.04e-05,
|
| 103 |
+
"loss": 0.294,
|
| 104 |
+
"step": 16
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 8.5,
|
| 108 |
+
"learning_rate": 4.98e-05,
|
| 109 |
+
"loss": 0.2514,
|
| 110 |
+
"step": 17
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 9.0,
|
| 114 |
+
"learning_rate": 4.9199999999999997e-05,
|
| 115 |
+
"loss": 0.2338,
|
| 116 |
+
"step": 18
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 9.5,
|
| 120 |
+
"learning_rate": 4.86e-05,
|
| 121 |
+
"loss": 0.3549,
|
| 122 |
+
"step": 19
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 10.0,
|
| 126 |
+
"learning_rate": 4.8e-05,
|
| 127 |
+
"loss": 0.1691,
|
| 128 |
+
"step": 20
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 10.0,
|
| 132 |
+
"eval_accuracy_background": 0.988144527098831,
|
| 133 |
+
"eval_accuracy_dress": 0.991687871077184,
|
| 134 |
+
"eval_accuracy_mannequin": 0.4888352444176222,
|
| 135 |
+
"eval_accuracy_unlabeled": NaN,
|
| 136 |
+
"eval_iou_background": 0.9844285968374425,
|
| 137 |
+
"eval_iou_dress": 0.8830148780303603,
|
| 138 |
+
"eval_iou_mannequin": 0.3854389721627409,
|
| 139 |
+
"eval_iou_unlabeled": NaN,
|
| 140 |
+
"eval_loss": 0.43675652146339417,
|
| 141 |
+
"eval_mean_accuracy": 0.8228892141978791,
|
| 142 |
+
"eval_mean_iou": 0.7509608156768479,
|
| 143 |
+
"eval_overall_accuracy": 0.9821510314941406,
|
| 144 |
+
"eval_runtime": 1.9996,
|
| 145 |
+
"eval_samples_per_second": 0.5,
|
| 146 |
+
"eval_steps_per_second": 0.5,
|
| 147 |
+
"step": 20
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 10.5,
|
| 151 |
+
"learning_rate": 4.74e-05,
|
| 152 |
+
"loss": 0.138,
|
| 153 |
+
"step": 21
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 11.0,
|
| 157 |
+
"learning_rate": 4.6800000000000006e-05,
|
| 158 |
+
"loss": 0.188,
|
| 159 |
+
"step": 22
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 11.5,
|
| 163 |
+
"learning_rate": 4.6200000000000005e-05,
|
| 164 |
+
"loss": 0.1721,
|
| 165 |
+
"step": 23
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 12.0,
|
| 169 |
+
"learning_rate": 4.5600000000000004e-05,
|
| 170 |
+
"loss": 0.1189,
|
| 171 |
+
"step": 24
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 12.5,
|
| 175 |
+
"learning_rate": 4.5e-05,
|
| 176 |
+
"loss": 0.1652,
|
| 177 |
+
"step": 25
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 13.0,
|
| 181 |
+
"learning_rate": 4.44e-05,
|
| 182 |
+
"loss": 0.1086,
|
| 183 |
+
"step": 26
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 13.5,
|
| 187 |
+
"learning_rate": 4.38e-05,
|
| 188 |
+
"loss": 0.134,
|
| 189 |
+
"step": 27
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 14.0,
|
| 193 |
+
"learning_rate": 4.32e-05,
|
| 194 |
+
"loss": 0.0876,
|
| 195 |
+
"step": 28
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 14.5,
|
| 199 |
+
"learning_rate": 4.26e-05,
|
| 200 |
+
"loss": 0.1133,
|
| 201 |
+
"step": 29
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 15.0,
|
| 205 |
+
"learning_rate": 4.2e-05,
|
| 206 |
+
"loss": 0.1772,
|
| 207 |
+
"step": 30
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 15.5,
|
| 211 |
+
"learning_rate": 4.14e-05,
|
| 212 |
+
"loss": 0.0857,
|
| 213 |
+
"step": 31
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 16.0,
|
| 217 |
+
"learning_rate": 4.08e-05,
|
| 218 |
+
"loss": 0.0953,
|
| 219 |
+
"step": 32
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 16.5,
|
| 223 |
+
"learning_rate": 4.02e-05,
|
| 224 |
+
"loss": 0.0887,
|
| 225 |
+
"step": 33
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 17.0,
|
| 229 |
+
"learning_rate": 3.96e-05,
|
| 230 |
+
"loss": 0.0907,
|
| 231 |
+
"step": 34
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 17.5,
|
| 235 |
+
"learning_rate": 3.9e-05,
|
| 236 |
+
"loss": 0.0979,
|
| 237 |
+
"step": 35
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 18.0,
|
| 241 |
+
"learning_rate": 3.8400000000000005e-05,
|
| 242 |
+
"loss": 0.0798,
|
| 243 |
+
"step": 36
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 18.5,
|
| 247 |
+
"learning_rate": 3.7800000000000004e-05,
|
| 248 |
+
"loss": 0.0752,
|
| 249 |
+
"step": 37
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 19.0,
|
| 253 |
+
"learning_rate": 3.72e-05,
|
| 254 |
+
"loss": 0.0794,
|
| 255 |
+
"step": 38
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 19.5,
|
| 259 |
+
"learning_rate": 3.66e-05,
|
| 260 |
+
"loss": 0.1087,
|
| 261 |
+
"step": 39
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 20.0,
|
| 265 |
+
"learning_rate": 3.6e-05,
|
| 266 |
+
"loss": 0.0588,
|
| 267 |
+
"step": 40
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 20.0,
|
| 271 |
+
"eval_accuracy_background": 0.9961997874601488,
|
| 272 |
+
"eval_accuracy_dress": 0.9875742154368109,
|
| 273 |
+
"eval_accuracy_mannequin": 0.5470730235365118,
|
| 274 |
+
"eval_accuracy_unlabeled": NaN,
|
| 275 |
+
"eval_iou_background": 0.9908590466687525,
|
| 276 |
+
"eval_iou_dress": 0.9425645592163847,
|
| 277 |
+
"eval_iou_mannequin": 0.5024944567627494,
|
| 278 |
+
"eval_iou_unlabeled": NaN,
|
| 279 |
+
"eval_loss": 0.09112856537103653,
|
| 280 |
+
"eval_mean_accuracy": 0.8436156754778238,
|
| 281 |
+
"eval_mean_iou": 0.8119726875492955,
|
| 282 |
+
"eval_overall_accuracy": 0.98974609375,
|
| 283 |
+
"eval_runtime": 1.7988,
|
| 284 |
+
"eval_samples_per_second": 0.556,
|
| 285 |
+
"eval_steps_per_second": 0.556,
|
| 286 |
+
"step": 40
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 20.5,
|
| 290 |
+
"learning_rate": 3.54e-05,
|
| 291 |
+
"loss": 0.0618,
|
| 292 |
+
"step": 41
|
| 293 |
+
},
|
| 294 |
+
{
|
| 295 |
+
"epoch": 21.0,
|
| 296 |
+
"learning_rate": 3.48e-05,
|
| 297 |
+
"loss": 0.0688,
|
| 298 |
+
"step": 42
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"epoch": 21.5,
|
| 302 |
+
"learning_rate": 3.42e-05,
|
| 303 |
+
"loss": 0.0602,
|
| 304 |
+
"step": 43
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 22.0,
|
| 308 |
+
"learning_rate": 3.3600000000000004e-05,
|
| 309 |
+
"loss": 0.0644,
|
| 310 |
+
"step": 44
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 22.5,
|
| 314 |
+
"learning_rate": 3.3e-05,
|
| 315 |
+
"loss": 0.0695,
|
| 316 |
+
"step": 45
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 23.0,
|
| 320 |
+
"learning_rate": 3.24e-05,
|
| 321 |
+
"loss": 0.0711,
|
| 322 |
+
"step": 46
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 23.5,
|
| 326 |
+
"learning_rate": 3.18e-05,
|
| 327 |
+
"loss": 0.0574,
|
| 328 |
+
"step": 47
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 24.0,
|
| 332 |
+
"learning_rate": 3.12e-05,
|
| 333 |
+
"loss": 0.0688,
|
| 334 |
+
"step": 48
|
| 335 |
+
},
|
| 336 |
+
{
|
| 337 |
+
"epoch": 24.5,
|
| 338 |
+
"learning_rate": 3.06e-05,
|
| 339 |
+
"loss": 0.0552,
|
| 340 |
+
"step": 49
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 25.0,
|
| 344 |
+
"learning_rate": 3e-05,
|
| 345 |
+
"loss": 0.0564,
|
| 346 |
+
"step": 50
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 25.5,
|
| 350 |
+
"learning_rate": 2.94e-05,
|
| 351 |
+
"loss": 0.0645,
|
| 352 |
+
"step": 51
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 26.0,
|
| 356 |
+
"learning_rate": 2.88e-05,
|
| 357 |
+
"loss": 0.0552,
|
| 358 |
+
"step": 52
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"epoch": 26.5,
|
| 362 |
+
"learning_rate": 2.8199999999999998e-05,
|
| 363 |
+
"loss": 0.0596,
|
| 364 |
+
"step": 53
|
| 365 |
+
},
|
| 366 |
+
{
|
| 367 |
+
"epoch": 27.0,
|
| 368 |
+
"learning_rate": 2.7600000000000003e-05,
|
| 369 |
+
"loss": 0.0624,
|
| 370 |
+
"step": 54
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 27.5,
|
| 374 |
+
"learning_rate": 2.7000000000000002e-05,
|
| 375 |
+
"loss": 0.0641,
|
| 376 |
+
"step": 55
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 28.0,
|
| 380 |
+
"learning_rate": 2.64e-05,
|
| 381 |
+
"loss": 0.0495,
|
| 382 |
+
"step": 56
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 28.5,
|
| 386 |
+
"learning_rate": 2.58e-05,
|
| 387 |
+
"loss": 0.0458,
|
| 388 |
+
"step": 57
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 29.0,
|
| 392 |
+
"learning_rate": 2.52e-05,
|
| 393 |
+
"loss": 0.0583,
|
| 394 |
+
"step": 58
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 29.5,
|
| 398 |
+
"learning_rate": 2.4599999999999998e-05,
|
| 399 |
+
"loss": 0.0594,
|
| 400 |
+
"step": 59
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 30.0,
|
| 404 |
+
"learning_rate": 2.4e-05,
|
| 405 |
+
"loss": 0.0485,
|
| 406 |
+
"step": 60
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 30.0,
|
| 410 |
+
"eval_accuracy_background": 0.9971222104144527,
|
| 411 |
+
"eval_accuracy_dress": 0.9766751484308737,
|
| 412 |
+
"eval_accuracy_mannequin": 0.7314423657211828,
|
| 413 |
+
"eval_accuracy_unlabeled": NaN,
|
| 414 |
+
"eval_iou_background": 0.9929183986183893,
|
| 415 |
+
"eval_iou_dress": 0.9522037542379889,
|
| 416 |
+
"eval_iou_mannequin": 0.6330634630451815,
|
| 417 |
+
"eval_iou_unlabeled": NaN,
|
| 418 |
+
"eval_loss": 0.057673919945955276,
|
| 419 |
+
"eval_mean_accuracy": 0.901746574855503,
|
| 420 |
+
"eval_mean_iou": 0.8593952053005198,
|
| 421 |
+
"eval_overall_accuracy": 0.9919242858886719,
|
| 422 |
+
"eval_runtime": 1.8206,
|
| 423 |
+
"eval_samples_per_second": 0.549,
|
| 424 |
+
"eval_steps_per_second": 0.549,
|
| 425 |
+
"step": 60
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 30.5,
|
| 429 |
+
"learning_rate": 2.3400000000000003e-05,
|
| 430 |
+
"loss": 0.0463,
|
| 431 |
+
"step": 61
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 31.0,
|
| 435 |
+
"learning_rate": 2.2800000000000002e-05,
|
| 436 |
+
"loss": 0.0549,
|
| 437 |
+
"step": 62
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 31.5,
|
| 441 |
+
"learning_rate": 2.22e-05,
|
| 442 |
+
"loss": 0.0433,
|
| 443 |
+
"step": 63
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 32.0,
|
| 447 |
+
"learning_rate": 2.16e-05,
|
| 448 |
+
"loss": 0.0503,
|
| 449 |
+
"step": 64
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 32.5,
|
| 453 |
+
"learning_rate": 2.1e-05,
|
| 454 |
+
"loss": 0.0474,
|
| 455 |
+
"step": 65
|
| 456 |
+
},
|
| 457 |
+
{
|
| 458 |
+
"epoch": 33.0,
|
| 459 |
+
"learning_rate": 2.04e-05,
|
| 460 |
+
"loss": 0.0441,
|
| 461 |
+
"step": 66
|
| 462 |
+
},
|
| 463 |
+
{
|
| 464 |
+
"epoch": 33.5,
|
| 465 |
+
"learning_rate": 1.98e-05,
|
| 466 |
+
"loss": 0.0399,
|
| 467 |
+
"step": 67
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 34.0,
|
| 471 |
+
"learning_rate": 1.9200000000000003e-05,
|
| 472 |
+
"loss": 0.051,
|
| 473 |
+
"step": 68
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 34.5,
|
| 477 |
+
"learning_rate": 1.86e-05,
|
| 478 |
+
"loss": 0.0449,
|
| 479 |
+
"step": 69
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 35.0,
|
| 483 |
+
"learning_rate": 1.8e-05,
|
| 484 |
+
"loss": 0.0438,
|
| 485 |
+
"step": 70
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 35.5,
|
| 489 |
+
"learning_rate": 1.74e-05,
|
| 490 |
+
"loss": 0.0505,
|
| 491 |
+
"step": 71
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"epoch": 36.0,
|
| 495 |
+
"learning_rate": 1.6800000000000002e-05,
|
| 496 |
+
"loss": 0.0457,
|
| 497 |
+
"step": 72
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 36.5,
|
| 501 |
+
"learning_rate": 1.62e-05,
|
| 502 |
+
"loss": 0.0374,
|
| 503 |
+
"step": 73
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 37.0,
|
| 507 |
+
"learning_rate": 1.56e-05,
|
| 508 |
+
"loss": 0.0429,
|
| 509 |
+
"step": 74
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 37.5,
|
| 513 |
+
"learning_rate": 1.5e-05,
|
| 514 |
+
"loss": 0.0535,
|
| 515 |
+
"step": 75
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 38.0,
|
| 519 |
+
"learning_rate": 1.44e-05,
|
| 520 |
+
"loss": 0.0426,
|
| 521 |
+
"step": 76
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 38.5,
|
| 525 |
+
"learning_rate": 1.3800000000000002e-05,
|
| 526 |
+
"loss": 0.039,
|
| 527 |
+
"step": 77
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 39.0,
|
| 531 |
+
"learning_rate": 1.32e-05,
|
| 532 |
+
"loss": 0.0434,
|
| 533 |
+
"step": 78
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 39.5,
|
| 537 |
+
"learning_rate": 1.26e-05,
|
| 538 |
+
"loss": 0.1033,
|
| 539 |
+
"step": 79
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 40.0,
|
| 543 |
+
"learning_rate": 1.2e-05,
|
| 544 |
+
"loss": 0.0374,
|
| 545 |
+
"step": 80
|
| 546 |
+
},
|
| 547 |
+
{
|
| 548 |
+
"epoch": 40.0,
|
| 549 |
+
"eval_accuracy_background": 0.9981806588735388,
|
| 550 |
+
"eval_accuracy_dress": 0.9714164546225615,
|
| 551 |
+
"eval_accuracy_mannequin": 0.7269161134580567,
|
| 552 |
+
"eval_accuracy_unlabeled": NaN,
|
| 553 |
+
"eval_iou_background": 0.993371095947781,
|
| 554 |
+
"eval_iou_dress": 0.9530268358643644,
|
| 555 |
+
"eval_iou_mannequin": 0.6463643681244969,
|
| 556 |
+
"eval_iou_unlabeled": NaN,
|
| 557 |
+
"eval_loss": 0.04460417479276657,
|
| 558 |
+
"eval_mean_accuracy": 0.8988377423180524,
|
| 559 |
+
"eval_mean_iou": 0.8642540999788807,
|
| 560 |
+
"eval_overall_accuracy": 0.9923439025878906,
|
| 561 |
+
"eval_runtime": 3.063,
|
| 562 |
+
"eval_samples_per_second": 0.326,
|
| 563 |
+
"eval_steps_per_second": 0.326,
|
| 564 |
+
"step": 80
|
| 565 |
+
}
|
| 566 |
+
],
|
| 567 |
+
"max_steps": 100,
|
| 568 |
+
"num_train_epochs": 50,
|
| 569 |
+
"total_flos": 2.0648332099584e+16,
|
| 570 |
+
"trial_name": null,
|
| 571 |
+
"trial_params": null
|
| 572 |
+
}
|
checkpoint-80/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:db41b5b7dd1b4e7919196c94cd48fefe27753a561d95db18671d26e224301078
|
| 3 |
+
size 3963
|
config.json
ADDED
|
@@ -0,0 +1,82 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "nvidia/mit-b2",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"SegformerForSemanticSegmentation"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.0,
|
| 7 |
+
"classifier_dropout_prob": 0.1,
|
| 8 |
+
"decoder_hidden_size": 768,
|
| 9 |
+
"depths": [
|
| 10 |
+
3,
|
| 11 |
+
4,
|
| 12 |
+
6,
|
| 13 |
+
3
|
| 14 |
+
],
|
| 15 |
+
"downsampling_rates": [
|
| 16 |
+
1,
|
| 17 |
+
4,
|
| 18 |
+
8,
|
| 19 |
+
16
|
| 20 |
+
],
|
| 21 |
+
"drop_path_rate": 0.1,
|
| 22 |
+
"hidden_act": "gelu",
|
| 23 |
+
"hidden_dropout_prob": 0.0,
|
| 24 |
+
"hidden_sizes": [
|
| 25 |
+
64,
|
| 26 |
+
128,
|
| 27 |
+
320,
|
| 28 |
+
512
|
| 29 |
+
],
|
| 30 |
+
"id2label": {
|
| 31 |
+
"0": "unlabeled",
|
| 32 |
+
"1": "dress",
|
| 33 |
+
"2": "mannequin",
|
| 34 |
+
"3": "background"
|
| 35 |
+
},
|
| 36 |
+
"image_size": 224,
|
| 37 |
+
"initializer_range": 0.02,
|
| 38 |
+
"label2id": {
|
| 39 |
+
"background": 3,
|
| 40 |
+
"dress": 1,
|
| 41 |
+
"mannequin": 2,
|
| 42 |
+
"unlabeled": 0
|
| 43 |
+
},
|
| 44 |
+
"layer_norm_eps": 1e-06,
|
| 45 |
+
"mlp_ratios": [
|
| 46 |
+
4,
|
| 47 |
+
4,
|
| 48 |
+
4,
|
| 49 |
+
4
|
| 50 |
+
],
|
| 51 |
+
"model_type": "segformer",
|
| 52 |
+
"num_attention_heads": [
|
| 53 |
+
1,
|
| 54 |
+
2,
|
| 55 |
+
5,
|
| 56 |
+
8
|
| 57 |
+
],
|
| 58 |
+
"num_channels": 3,
|
| 59 |
+
"num_encoder_blocks": 4,
|
| 60 |
+
"patch_sizes": [
|
| 61 |
+
7,
|
| 62 |
+
3,
|
| 63 |
+
3,
|
| 64 |
+
3
|
| 65 |
+
],
|
| 66 |
+
"reshape_last_stage": true,
|
| 67 |
+
"semantic_loss_ignore_index": 255,
|
| 68 |
+
"sr_ratios": [
|
| 69 |
+
8,
|
| 70 |
+
4,
|
| 71 |
+
2,
|
| 72 |
+
1
|
| 73 |
+
],
|
| 74 |
+
"strides": [
|
| 75 |
+
4,
|
| 76 |
+
2,
|
| 77 |
+
2,
|
| 78 |
+
2
|
| 79 |
+
],
|
| 80 |
+
"torch_dtype": "float32",
|
| 81 |
+
"transformers_version": "4.30.2"
|
| 82 |
+
}
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_normalize": true,
|
| 3 |
+
"do_reduce_labels": false,
|
| 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": "SegformerFeatureExtractor",
|
| 12 |
+
"image_std": [
|
| 13 |
+
0.229,
|
| 14 |
+
0.224,
|
| 15 |
+
0.225
|
| 16 |
+
],
|
| 17 |
+
"resample": 2,
|
| 18 |
+
"rescale_factor": 0.00392156862745098,
|
| 19 |
+
"size": {
|
| 20 |
+
"height": 512,
|
| 21 |
+
"width": 512
|
| 22 |
+
}
|
| 23 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7da41d5b1aefeb2cd38a865f93164f5f577426ffdf376820e0b6cfc631cff98d
|
| 3 |
+
size 109530621
|
runs/Jul11_16-48-07_8bd8190397e4/events.out.tfevents.1689094148.8bd8190397e4.5988.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e2fe303b600e029f69257f8abeff5a984614aa12a3646216f13b16ebaf762458
|
| 3 |
+
size 24781
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:db41b5b7dd1b4e7919196c94cd48fefe27753a561d95db18671d26e224301078
|
| 3 |
+
size 3963
|