Training in progress, epoch 5, checkpoint
Browse files- checkpoint-535/config.json +69 -0
- checkpoint-535/model.safetensors +3 -0
- checkpoint-535/optimizer.pt +3 -0
- checkpoint-535/preprocessor_config.json +47 -0
- checkpoint-535/rng_state.pth +3 -0
- checkpoint-535/scheduler.pt +3 -0
- checkpoint-535/trainer_state.json +340 -0
- checkpoint-535/training_args.bin +3 -0
checkpoint-535/config.json
ADDED
|
@@ -0,0 +1,69 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "microsoft/conditional-detr-resnet-50",
|
| 3 |
+
"activation_dropout": 0.0,
|
| 4 |
+
"activation_function": "relu",
|
| 5 |
+
"architectures": [
|
| 6 |
+
"ConditionalDetrForObjectDetection"
|
| 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": 2,
|
| 24 |
+
"cls_loss_coefficient": 2,
|
| 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 |
+
"focal_alpha": 0.25,
|
| 38 |
+
"giou_cost": 2,
|
| 39 |
+
"giou_loss_coefficient": 2,
|
| 40 |
+
"id2label": {
|
| 41 |
+
"0": "Coverall",
|
| 42 |
+
"1": "Face_Shield",
|
| 43 |
+
"2": "Gloves",
|
| 44 |
+
"3": "Goggles",
|
| 45 |
+
"4": "Mask"
|
| 46 |
+
},
|
| 47 |
+
"init_std": 0.02,
|
| 48 |
+
"init_xavier_std": 1.0,
|
| 49 |
+
"is_encoder_decoder": true,
|
| 50 |
+
"label2id": {
|
| 51 |
+
"Coverall": 0,
|
| 52 |
+
"Face_Shield": 1,
|
| 53 |
+
"Gloves": 2,
|
| 54 |
+
"Goggles": 3,
|
| 55 |
+
"Mask": 4
|
| 56 |
+
},
|
| 57 |
+
"mask_loss_coefficient": 1,
|
| 58 |
+
"max_position_embeddings": 1024,
|
| 59 |
+
"model_type": "conditional_detr",
|
| 60 |
+
"num_channels": 3,
|
| 61 |
+
"num_hidden_layers": 6,
|
| 62 |
+
"num_queries": 300,
|
| 63 |
+
"position_embedding_type": "sine",
|
| 64 |
+
"scale_embedding": false,
|
| 65 |
+
"torch_dtype": "float32",
|
| 66 |
+
"transformers_version": "4.42.0.dev0",
|
| 67 |
+
"use_pretrained_backbone": true,
|
| 68 |
+
"use_timm_backbone": true
|
| 69 |
+
}
|
checkpoint-535/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b39311a457b4000680a589d4e2309f7aa7625ff5748bc83e74188fd774033f3c
|
| 3 |
+
size 174079796
|
checkpoint-535/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:54430a5b39632bf4eaa8cc2f1e8fc8311713d856a22e1b18b3d46d31bcec682c
|
| 3 |
+
size 345687577
|
checkpoint-535/preprocessor_config.json
ADDED
|
@@ -0,0 +1,47 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_valid_processor_keys": [
|
| 3 |
+
"images",
|
| 4 |
+
"annotations",
|
| 5 |
+
"return_segmentation_masks",
|
| 6 |
+
"masks_path",
|
| 7 |
+
"do_resize",
|
| 8 |
+
"size",
|
| 9 |
+
"resample",
|
| 10 |
+
"do_rescale",
|
| 11 |
+
"rescale_factor",
|
| 12 |
+
"do_normalize",
|
| 13 |
+
"do_convert_annotations",
|
| 14 |
+
"image_mean",
|
| 15 |
+
"image_std",
|
| 16 |
+
"do_pad",
|
| 17 |
+
"pad_size",
|
| 18 |
+
"format",
|
| 19 |
+
"return_tensors",
|
| 20 |
+
"data_format",
|
| 21 |
+
"input_data_format"
|
| 22 |
+
],
|
| 23 |
+
"do_convert_annotations": true,
|
| 24 |
+
"do_normalize": true,
|
| 25 |
+
"do_pad": false,
|
| 26 |
+
"do_rescale": true,
|
| 27 |
+
"do_resize": false,
|
| 28 |
+
"format": "coco_detection",
|
| 29 |
+
"image_mean": [
|
| 30 |
+
0.485,
|
| 31 |
+
0.456,
|
| 32 |
+
0.406
|
| 33 |
+
],
|
| 34 |
+
"image_processor_type": "ConditionalDetrImageProcessor",
|
| 35 |
+
"image_std": [
|
| 36 |
+
0.229,
|
| 37 |
+
0.224,
|
| 38 |
+
0.225
|
| 39 |
+
],
|
| 40 |
+
"pad_size": null,
|
| 41 |
+
"resample": 2,
|
| 42 |
+
"rescale_factor": 0.00392156862745098,
|
| 43 |
+
"size": {
|
| 44 |
+
"longest_edge": 1333,
|
| 45 |
+
"shortest_edge": 800
|
| 46 |
+
}
|
| 47 |
+
}
|
checkpoint-535/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2a392b92abb441aca4c13e112d8e65c63f0a787044db3944e07d73ca395700c3
|
| 3 |
+
size 13990
|
checkpoint-535/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ff5026637c4bd3aa4963f3c9e1c74828911a22462e969a6ee3b6eea8b6e70288
|
| 3 |
+
size 1064
|
checkpoint-535/trainer_state.json
ADDED
|
@@ -0,0 +1,340 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.0177,
|
| 3 |
+
"best_model_checkpoint": "test_detr_finetuned_cppe5/checkpoint-535",
|
| 4 |
+
"epoch": 5.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 535,
|
| 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 |
+
"step": 107,
|
| 14 |
+
"train_loss": 3.0001344680786133,
|
| 15 |
+
"train_map": 0.0047,
|
| 16 |
+
"train_map_50": 0.0176,
|
| 17 |
+
"train_map_75": 0.0014,
|
| 18 |
+
"train_map_Coverall": 0.0232,
|
| 19 |
+
"train_map_Face_Shield": 0.0,
|
| 20 |
+
"train_map_Gloves": 0.0001,
|
| 21 |
+
"train_map_Goggles": 0.0,
|
| 22 |
+
"train_map_Mask": 0.0004,
|
| 23 |
+
"train_map_large": 0.0049,
|
| 24 |
+
"train_map_medium": 0.0002,
|
| 25 |
+
"train_map_small": 0.0016,
|
| 26 |
+
"train_mar_1": 0.0108,
|
| 27 |
+
"train_mar_10": 0.0458,
|
| 28 |
+
"train_mar_100": 0.0837,
|
| 29 |
+
"train_mar_100_Coverall": 0.3473,
|
| 30 |
+
"train_mar_100_Face_Shield": 0.0,
|
| 31 |
+
"train_mar_100_Gloves": 0.0145,
|
| 32 |
+
"train_mar_100_Goggles": 0.0,
|
| 33 |
+
"train_mar_100_Mask": 0.0567,
|
| 34 |
+
"train_mar_large": 0.0731,
|
| 35 |
+
"train_mar_medium": 0.0246,
|
| 36 |
+
"train_mar_small": 0.0013,
|
| 37 |
+
"train_runtime": 83.8338,
|
| 38 |
+
"train_samples_per_second": 10.139,
|
| 39 |
+
"train_steps_per_second": 1.276
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 1.0,
|
| 43 |
+
"eval_loss": 3.0698611736297607,
|
| 44 |
+
"eval_map": 0.0038,
|
| 45 |
+
"eval_map_50": 0.0126,
|
| 46 |
+
"eval_map_75": 0.0008,
|
| 47 |
+
"eval_map_Coverall": 0.0183,
|
| 48 |
+
"eval_map_Face_Shield": 0.0,
|
| 49 |
+
"eval_map_Gloves": 0.0002,
|
| 50 |
+
"eval_map_Goggles": 0.0,
|
| 51 |
+
"eval_map_Mask": 0.0004,
|
| 52 |
+
"eval_map_large": 0.0044,
|
| 53 |
+
"eval_map_medium": 0.0002,
|
| 54 |
+
"eval_map_small": 0.0022,
|
| 55 |
+
"eval_mar_1": 0.0063,
|
| 56 |
+
"eval_mar_10": 0.0308,
|
| 57 |
+
"eval_mar_100": 0.0561,
|
| 58 |
+
"eval_mar_100_Coverall": 0.2185,
|
| 59 |
+
"eval_mar_100_Face_Shield": 0.0,
|
| 60 |
+
"eval_mar_100_Gloves": 0.0156,
|
| 61 |
+
"eval_mar_100_Goggles": 0.0,
|
| 62 |
+
"eval_mar_100_Mask": 0.0462,
|
| 63 |
+
"eval_mar_large": 0.05,
|
| 64 |
+
"eval_mar_medium": 0.0266,
|
| 65 |
+
"eval_mar_small": 0.0022,
|
| 66 |
+
"eval_runtime": 43.5223,
|
| 67 |
+
"eval_samples_per_second": 3.447,
|
| 68 |
+
"eval_steps_per_second": 0.437,
|
| 69 |
+
"step": 107
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 2.0,
|
| 73 |
+
"step": 214,
|
| 74 |
+
"train_loss": 2.964989423751831,
|
| 75 |
+
"train_map": 0.0073,
|
| 76 |
+
"train_map_50": 0.0272,
|
| 77 |
+
"train_map_75": 0.0018,
|
| 78 |
+
"train_map_Coverall": 0.0358,
|
| 79 |
+
"train_map_Face_Shield": 0.0,
|
| 80 |
+
"train_map_Gloves": 0.0002,
|
| 81 |
+
"train_map_Goggles": 0.0,
|
| 82 |
+
"train_map_Mask": 0.0005,
|
| 83 |
+
"train_map_large": 0.0075,
|
| 84 |
+
"train_map_medium": 0.0002,
|
| 85 |
+
"train_map_small": 0.0018,
|
| 86 |
+
"train_mar_1": 0.0107,
|
| 87 |
+
"train_mar_10": 0.045,
|
| 88 |
+
"train_mar_100": 0.0775,
|
| 89 |
+
"train_mar_100_Coverall": 0.2974,
|
| 90 |
+
"train_mar_100_Face_Shield": 0.0,
|
| 91 |
+
"train_mar_100_Gloves": 0.0302,
|
| 92 |
+
"train_mar_100_Goggles": 0.0,
|
| 93 |
+
"train_mar_100_Mask": 0.06,
|
| 94 |
+
"train_mar_large": 0.0627,
|
| 95 |
+
"train_mar_medium": 0.0311,
|
| 96 |
+
"train_mar_small": 0.0012,
|
| 97 |
+
"train_runtime": 86.7545,
|
| 98 |
+
"train_samples_per_second": 9.798,
|
| 99 |
+
"train_steps_per_second": 1.233
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 2.0,
|
| 103 |
+
"eval_loss": 3.0518693923950195,
|
| 104 |
+
"eval_map": 0.0042,
|
| 105 |
+
"eval_map_50": 0.0172,
|
| 106 |
+
"eval_map_75": 0.0009,
|
| 107 |
+
"eval_map_Coverall": 0.0203,
|
| 108 |
+
"eval_map_Face_Shield": 0.0,
|
| 109 |
+
"eval_map_Gloves": 0.0003,
|
| 110 |
+
"eval_map_Goggles": 0.0,
|
| 111 |
+
"eval_map_Mask": 0.0004,
|
| 112 |
+
"eval_map_large": 0.0046,
|
| 113 |
+
"eval_map_medium": 0.0003,
|
| 114 |
+
"eval_map_small": 0.0005,
|
| 115 |
+
"eval_mar_1": 0.0064,
|
| 116 |
+
"eval_mar_10": 0.0308,
|
| 117 |
+
"eval_mar_100": 0.0561,
|
| 118 |
+
"eval_mar_100_Coverall": 0.2045,
|
| 119 |
+
"eval_mar_100_Face_Shield": 0.0,
|
| 120 |
+
"eval_mar_100_Gloves": 0.0339,
|
| 121 |
+
"eval_mar_100_Goggles": 0.0,
|
| 122 |
+
"eval_mar_100_Mask": 0.0422,
|
| 123 |
+
"eval_mar_large": 0.0468,
|
| 124 |
+
"eval_mar_medium": 0.0333,
|
| 125 |
+
"eval_mar_small": 0.0004,
|
| 126 |
+
"eval_runtime": 41.1994,
|
| 127 |
+
"eval_samples_per_second": 3.641,
|
| 128 |
+
"eval_steps_per_second": 0.461,
|
| 129 |
+
"step": 214
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 3.0,
|
| 133 |
+
"step": 321,
|
| 134 |
+
"train_loss": 2.9912493228912354,
|
| 135 |
+
"train_map": 0.0034,
|
| 136 |
+
"train_map_50": 0.0129,
|
| 137 |
+
"train_map_75": 0.0014,
|
| 138 |
+
"train_map_Coverall": 0.0166,
|
| 139 |
+
"train_map_Face_Shield": 0.0003,
|
| 140 |
+
"train_map_Gloves": 0.0,
|
| 141 |
+
"train_map_Goggles": 0.0,
|
| 142 |
+
"train_map_Mask": 0.0003,
|
| 143 |
+
"train_map_large": 0.0039,
|
| 144 |
+
"train_map_medium": 0.0001,
|
| 145 |
+
"train_map_small": 0.0028,
|
| 146 |
+
"train_mar_1": 0.0112,
|
| 147 |
+
"train_mar_10": 0.0458,
|
| 148 |
+
"train_mar_100": 0.0675,
|
| 149 |
+
"train_mar_100_Coverall": 0.2772,
|
| 150 |
+
"train_mar_100_Face_Shield": 0.004,
|
| 151 |
+
"train_mar_100_Gloves": 0.014,
|
| 152 |
+
"train_mar_100_Goggles": 0.0,
|
| 153 |
+
"train_mar_100_Mask": 0.0425,
|
| 154 |
+
"train_mar_large": 0.0589,
|
| 155 |
+
"train_mar_medium": 0.02,
|
| 156 |
+
"train_mar_small": 0.0021,
|
| 157 |
+
"train_runtime": 80.1813,
|
| 158 |
+
"train_samples_per_second": 10.601,
|
| 159 |
+
"train_steps_per_second": 1.334
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 3.0,
|
| 163 |
+
"eval_loss": 3.0276060104370117,
|
| 164 |
+
"eval_map": 0.0029,
|
| 165 |
+
"eval_map_50": 0.0113,
|
| 166 |
+
"eval_map_75": 0.0007,
|
| 167 |
+
"eval_map_Coverall": 0.0137,
|
| 168 |
+
"eval_map_Face_Shield": 0.0003,
|
| 169 |
+
"eval_map_Gloves": 0.0,
|
| 170 |
+
"eval_map_Goggles": 0.0,
|
| 171 |
+
"eval_map_Mask": 0.0003,
|
| 172 |
+
"eval_map_large": 0.0031,
|
| 173 |
+
"eval_map_medium": 0.0002,
|
| 174 |
+
"eval_map_small": 0.001,
|
| 175 |
+
"eval_mar_1": 0.0057,
|
| 176 |
+
"eval_mar_10": 0.0326,
|
| 177 |
+
"eval_mar_100": 0.0506,
|
| 178 |
+
"eval_mar_100_Coverall": 0.2108,
|
| 179 |
+
"eval_mar_100_Face_Shield": 0.0063,
|
| 180 |
+
"eval_mar_100_Gloves": 0.0058,
|
| 181 |
+
"eval_mar_100_Goggles": 0.0,
|
| 182 |
+
"eval_mar_100_Mask": 0.0302,
|
| 183 |
+
"eval_mar_large": 0.0482,
|
| 184 |
+
"eval_mar_medium": 0.0184,
|
| 185 |
+
"eval_mar_small": 0.0009,
|
| 186 |
+
"eval_runtime": 49.8337,
|
| 187 |
+
"eval_samples_per_second": 3.01,
|
| 188 |
+
"eval_steps_per_second": 0.381,
|
| 189 |
+
"step": 321
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 4.0,
|
| 193 |
+
"step": 428,
|
| 194 |
+
"train_loss": 2.774980068206787,
|
| 195 |
+
"train_map": 0.0215,
|
| 196 |
+
"train_map_50": 0.0526,
|
| 197 |
+
"train_map_75": 0.0145,
|
| 198 |
+
"train_map_Coverall": 0.1068,
|
| 199 |
+
"train_map_Face_Shield": 0.0003,
|
| 200 |
+
"train_map_Gloves": 0.0001,
|
| 201 |
+
"train_map_Goggles": 0.0,
|
| 202 |
+
"train_map_Mask": 0.0003,
|
| 203 |
+
"train_map_large": 0.0226,
|
| 204 |
+
"train_map_medium": 0.0001,
|
| 205 |
+
"train_map_small": 0.0025,
|
| 206 |
+
"train_mar_1": 0.0295,
|
| 207 |
+
"train_mar_10": 0.08,
|
| 208 |
+
"train_mar_100": 0.106,
|
| 209 |
+
"train_mar_100_Coverall": 0.431,
|
| 210 |
+
"train_mar_100_Face_Shield": 0.0397,
|
| 211 |
+
"train_mar_100_Gloves": 0.0193,
|
| 212 |
+
"train_mar_100_Goggles": 0.0,
|
| 213 |
+
"train_mar_100_Mask": 0.0401,
|
| 214 |
+
"train_mar_large": 0.1015,
|
| 215 |
+
"train_mar_medium": 0.0255,
|
| 216 |
+
"train_mar_small": 0.005,
|
| 217 |
+
"train_runtime": 75.8168,
|
| 218 |
+
"train_samples_per_second": 11.211,
|
| 219 |
+
"train_steps_per_second": 1.411
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 4.0,
|
| 223 |
+
"eval_loss": 2.858452558517456,
|
| 224 |
+
"eval_map": 0.0149,
|
| 225 |
+
"eval_map_50": 0.0389,
|
| 226 |
+
"eval_map_75": 0.0106,
|
| 227 |
+
"eval_map_Coverall": 0.0739,
|
| 228 |
+
"eval_map_Face_Shield": 0.0001,
|
| 229 |
+
"eval_map_Gloves": 0.0,
|
| 230 |
+
"eval_map_Goggles": 0.0,
|
| 231 |
+
"eval_map_Mask": 0.0005,
|
| 232 |
+
"eval_map_large": 0.0169,
|
| 233 |
+
"eval_map_medium": 0.0001,
|
| 234 |
+
"eval_map_small": 0.003,
|
| 235 |
+
"eval_mar_1": 0.018,
|
| 236 |
+
"eval_mar_10": 0.051,
|
| 237 |
+
"eval_mar_100": 0.0751,
|
| 238 |
+
"eval_mar_100_Coverall": 0.3243,
|
| 239 |
+
"eval_mar_100_Face_Shield": 0.0063,
|
| 240 |
+
"eval_mar_100_Gloves": 0.0098,
|
| 241 |
+
"eval_mar_100_Goggles": 0.0,
|
| 242 |
+
"eval_mar_100_Mask": 0.0351,
|
| 243 |
+
"eval_mar_large": 0.0756,
|
| 244 |
+
"eval_mar_medium": 0.0173,
|
| 245 |
+
"eval_mar_small": 0.0055,
|
| 246 |
+
"eval_runtime": 39.8886,
|
| 247 |
+
"eval_samples_per_second": 3.76,
|
| 248 |
+
"eval_steps_per_second": 0.476,
|
| 249 |
+
"step": 428
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 4.672897196261682,
|
| 253 |
+
"grad_norm": 42.34880065917969,
|
| 254 |
+
"learning_rate": 4.97310930008156e-05,
|
| 255 |
+
"loss": 2.8744,
|
| 256 |
+
"step": 500
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 5.0,
|
| 260 |
+
"step": 535,
|
| 261 |
+
"train_loss": 2.7138683795928955,
|
| 262 |
+
"train_map": 0.0264,
|
| 263 |
+
"train_map_50": 0.0577,
|
| 264 |
+
"train_map_75": 0.0211,
|
| 265 |
+
"train_map_Coverall": 0.1315,
|
| 266 |
+
"train_map_Face_Shield": 0.0001,
|
| 267 |
+
"train_map_Gloves": 0.0001,
|
| 268 |
+
"train_map_Goggles": 0.0,
|
| 269 |
+
"train_map_Mask": 0.0004,
|
| 270 |
+
"train_map_large": 0.0278,
|
| 271 |
+
"train_map_medium": 0.0002,
|
| 272 |
+
"train_map_small": 0.0006,
|
| 273 |
+
"train_mar_1": 0.0329,
|
| 274 |
+
"train_mar_10": 0.0861,
|
| 275 |
+
"train_mar_100": 0.1129,
|
| 276 |
+
"train_mar_100_Coverall": 0.4616,
|
| 277 |
+
"train_mar_100_Face_Shield": 0.0175,
|
| 278 |
+
"train_mar_100_Gloves": 0.0374,
|
| 279 |
+
"train_mar_100_Goggles": 0.0,
|
| 280 |
+
"train_mar_100_Mask": 0.048,
|
| 281 |
+
"train_mar_large": 0.1028,
|
| 282 |
+
"train_mar_medium": 0.033,
|
| 283 |
+
"train_mar_small": 0.0004,
|
| 284 |
+
"train_runtime": 83.2574,
|
| 285 |
+
"train_samples_per_second": 10.209,
|
| 286 |
+
"train_steps_per_second": 1.285
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 5.0,
|
| 290 |
+
"eval_loss": 2.8448832035064697,
|
| 291 |
+
"eval_map": 0.0177,
|
| 292 |
+
"eval_map_50": 0.0404,
|
| 293 |
+
"eval_map_75": 0.0141,
|
| 294 |
+
"eval_map_Coverall": 0.0879,
|
| 295 |
+
"eval_map_Face_Shield": 0.0001,
|
| 296 |
+
"eval_map_Gloves": 0.0001,
|
| 297 |
+
"eval_map_Goggles": 0.0,
|
| 298 |
+
"eval_map_Mask": 0.0004,
|
| 299 |
+
"eval_map_large": 0.02,
|
| 300 |
+
"eval_map_medium": 0.0002,
|
| 301 |
+
"eval_map_small": 0.0,
|
| 302 |
+
"eval_mar_1": 0.0218,
|
| 303 |
+
"eval_mar_10": 0.0578,
|
| 304 |
+
"eval_mar_100": 0.0829,
|
| 305 |
+
"eval_mar_100_Coverall": 0.3347,
|
| 306 |
+
"eval_mar_100_Face_Shield": 0.0076,
|
| 307 |
+
"eval_mar_100_Gloves": 0.0263,
|
| 308 |
+
"eval_mar_100_Goggles": 0.0,
|
| 309 |
+
"eval_mar_100_Mask": 0.0458,
|
| 310 |
+
"eval_mar_large": 0.0793,
|
| 311 |
+
"eval_mar_medium": 0.0343,
|
| 312 |
+
"eval_mar_small": 0.0,
|
| 313 |
+
"eval_runtime": 40.7733,
|
| 314 |
+
"eval_samples_per_second": 3.679,
|
| 315 |
+
"eval_steps_per_second": 0.466,
|
| 316 |
+
"step": 535
|
| 317 |
+
}
|
| 318 |
+
],
|
| 319 |
+
"logging_steps": 500,
|
| 320 |
+
"max_steps": 10700,
|
| 321 |
+
"num_input_tokens_seen": 0,
|
| 322 |
+
"num_train_epochs": 100,
|
| 323 |
+
"save_steps": 500,
|
| 324 |
+
"stateful_callbacks": {
|
| 325 |
+
"TrainerControl": {
|
| 326 |
+
"args": {
|
| 327 |
+
"should_epoch_stop": false,
|
| 328 |
+
"should_evaluate": false,
|
| 329 |
+
"should_log": false,
|
| 330 |
+
"should_save": true,
|
| 331 |
+
"should_training_stop": false
|
| 332 |
+
},
|
| 333 |
+
"attributes": {}
|
| 334 |
+
}
|
| 335 |
+
},
|
| 336 |
+
"total_flos": 7.635321615744e+17,
|
| 337 |
+
"train_batch_size": 8,
|
| 338 |
+
"trial_name": null,
|
| 339 |
+
"trial_params": null
|
| 340 |
+
}
|
checkpoint-535/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dfb5b1b016fe6c9e411ad0aa21f5650b9f5bdfae6d91c31b103f2e514cbab6ff
|
| 3 |
+
size 5176
|