Training in progress, step 500, checkpoint
Browse files- checkpoint-500/config.json +62 -0
- checkpoint-500/model.safetensors +3 -0
- checkpoint-500/optimizer.pt +3 -0
- checkpoint-500/preprocessor_config.json +26 -0
- checkpoint-500/rng_state.pth +3 -0
- checkpoint-500/scheduler.pt +3 -0
- checkpoint-500/trainer_state.json +48 -0
- checkpoint-500/training_args.bin +3 -0
checkpoint-500/config.json
ADDED
@@ -0,0 +1,62 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "facebook/detr-resnet-50-dc5",
|
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 |
+
"output_stride": 16
|
21 |
+
},
|
22 |
+
"bbox_cost": 5,
|
23 |
+
"bbox_loss_coefficient": 5,
|
24 |
+
"class_cost": 1,
|
25 |
+
"classifier_dropout": 0.0,
|
26 |
+
"d_model": 256,
|
27 |
+
"decoder_attention_heads": 8,
|
28 |
+
"decoder_ffn_dim": 2048,
|
29 |
+
"decoder_layerdrop": 0.0,
|
30 |
+
"decoder_layers": 6,
|
31 |
+
"dice_loss_coefficient": 1,
|
32 |
+
"dilation": true,
|
33 |
+
"dropout": 0.1,
|
34 |
+
"encoder_attention_heads": 8,
|
35 |
+
"encoder_ffn_dim": 2048,
|
36 |
+
"encoder_layerdrop": 0.0,
|
37 |
+
"encoder_layers": 6,
|
38 |
+
"eos_coefficient": 0.1,
|
39 |
+
"giou_cost": 2,
|
40 |
+
"giou_loss_coefficient": 2,
|
41 |
+
"id2label": {
|
42 |
+
"0": "segment"
|
43 |
+
},
|
44 |
+
"init_std": 0.02,
|
45 |
+
"init_xavier_std": 1.0,
|
46 |
+
"is_encoder_decoder": true,
|
47 |
+
"label2id": {
|
48 |
+
"segment": 0
|
49 |
+
},
|
50 |
+
"mask_loss_coefficient": 1,
|
51 |
+
"max_position_embeddings": 1024,
|
52 |
+
"model_type": "detr",
|
53 |
+
"num_channels": 3,
|
54 |
+
"num_hidden_layers": 6,
|
55 |
+
"num_queries": 99,
|
56 |
+
"position_embedding_type": "sine",
|
57 |
+
"scale_embedding": false,
|
58 |
+
"torch_dtype": "float32",
|
59 |
+
"transformers_version": "4.44.2",
|
60 |
+
"use_pretrained_backbone": true,
|
61 |
+
"use_timm_backbone": true
|
62 |
+
}
|
checkpoint-500/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c77b5fb70cb66f90e774f6c1183454f515ea4701033085661ad3f2a8760a4180
|
3 |
+
size 166493800
|
checkpoint-500/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:baf9efacb34779dfc8fc6eee18ae3ce192dcc8ff9ac4ab244ea025014e9b6d07
|
3 |
+
size 330489722
|
checkpoint-500/preprocessor_config.json
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": null,
|
20 |
+
"resample": 2,
|
21 |
+
"rescale_factor": 0.00392156862745098,
|
22 |
+
"size": {
|
23 |
+
"longest_edge": 1333,
|
24 |
+
"shortest_edge": 800
|
25 |
+
}
|
26 |
+
}
|
checkpoint-500/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0357edbfb94fe715e92cdb404a66fc50cb8a164bb59b1193cd65efe7e41d3b13
|
3 |
+
size 14308
|
checkpoint-500/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:31fbc968dbee05bf9e95ad636c30189a20cf0cb17218e3a27fc5d103e4d8dbdc
|
3 |
+
size 1064
|
checkpoint-500/trainer_state.json
ADDED
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 7.6923076923076925,
|
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": 7.6923076923076925,
|
13 |
+
"grad_norm": 103.745361328125,
|
14 |
+
"learning_rate": 9.950700000000001e-06,
|
15 |
+
"loss": 3.7724,
|
16 |
+
"step": 500
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 7.6923076923076925,
|
20 |
+
"eval_loss": 4.843122959136963,
|
21 |
+
"eval_runtime": 12.2345,
|
22 |
+
"eval_samples_per_second": 10.707,
|
23 |
+
"eval_steps_per_second": 1.39,
|
24 |
+
"step": 500
|
25 |
+
}
|
26 |
+
],
|
27 |
+
"logging_steps": 500,
|
28 |
+
"max_steps": 100000,
|
29 |
+
"num_input_tokens_seen": 0,
|
30 |
+
"num_train_epochs": 1539,
|
31 |
+
"save_steps": 500,
|
32 |
+
"stateful_callbacks": {
|
33 |
+
"TrainerControl": {
|
34 |
+
"args": {
|
35 |
+
"should_epoch_stop": false,
|
36 |
+
"should_evaluate": false,
|
37 |
+
"should_log": false,
|
38 |
+
"should_save": true,
|
39 |
+
"should_training_stop": false
|
40 |
+
},
|
41 |
+
"attributes": {}
|
42 |
+
}
|
43 |
+
},
|
44 |
+
"total_flos": 1.91121583104e+18,
|
45 |
+
"train_batch_size": 8,
|
46 |
+
"trial_name": null,
|
47 |
+
"trial_params": null
|
48 |
+
}
|
checkpoint-500/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fd8cbf8e5e80b0b1d79922b7e15316817f1dd7309fcbaf2357bcb937829fb959
|
3 |
+
size 5304
|