Training in progress, step 40
Browse files- checkpoint-40/config.json +80 -0
- checkpoint-40/optimizer.pt +3 -0
- checkpoint-40/pytorch_model.bin +3 -0
- checkpoint-40/rng_state.pth +3 -0
- checkpoint-40/scheduler.pt +3 -0
- checkpoint-40/trainer_state.json +324 -0
- checkpoint-40/training_args.bin +3 -0
- config.json +80 -0
- pytorch_model.bin +3 -0
- runs/Feb06_02-59-17_robovision.csres.utexas.edu/events.out.tfevents.1707209963.robovision.csres.utexas.edu.1658684.0 +3 -0
- training_args.bin +3 -0
checkpoint-40/config.json
ADDED
|
@@ -0,0 +1,80 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "nvidia/mit-b0",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"SegformerForSemanticSegmentation"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.0,
|
| 7 |
+
"classifier_dropout_prob": 0.1,
|
| 8 |
+
"decoder_hidden_size": 256,
|
| 9 |
+
"depths": [
|
| 10 |
+
2,
|
| 11 |
+
2,
|
| 12 |
+
2,
|
| 13 |
+
2
|
| 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 |
+
32,
|
| 26 |
+
64,
|
| 27 |
+
160,
|
| 28 |
+
256
|
| 29 |
+
],
|
| 30 |
+
"id2label": {
|
| 31 |
+
"0": "unlabeled",
|
| 32 |
+
"1": "safe",
|
| 33 |
+
"2": "unsafe"
|
| 34 |
+
},
|
| 35 |
+
"image_size": 224,
|
| 36 |
+
"initializer_range": 0.02,
|
| 37 |
+
"label2id": {
|
| 38 |
+
"safe": 1,
|
| 39 |
+
"unlabeled": 0,
|
| 40 |
+
"unsafe": 2
|
| 41 |
+
},
|
| 42 |
+
"layer_norm_eps": 1e-06,
|
| 43 |
+
"mlp_ratios": [
|
| 44 |
+
4,
|
| 45 |
+
4,
|
| 46 |
+
4,
|
| 47 |
+
4
|
| 48 |
+
],
|
| 49 |
+
"model_type": "segformer",
|
| 50 |
+
"num_attention_heads": [
|
| 51 |
+
1,
|
| 52 |
+
2,
|
| 53 |
+
5,
|
| 54 |
+
8
|
| 55 |
+
],
|
| 56 |
+
"num_channels": 3,
|
| 57 |
+
"num_encoder_blocks": 4,
|
| 58 |
+
"patch_sizes": [
|
| 59 |
+
7,
|
| 60 |
+
3,
|
| 61 |
+
3,
|
| 62 |
+
3
|
| 63 |
+
],
|
| 64 |
+
"reshape_last_stage": true,
|
| 65 |
+
"semantic_loss_ignore_index": 255,
|
| 66 |
+
"sr_ratios": [
|
| 67 |
+
8,
|
| 68 |
+
4,
|
| 69 |
+
2,
|
| 70 |
+
1
|
| 71 |
+
],
|
| 72 |
+
"strides": [
|
| 73 |
+
4,
|
| 74 |
+
2,
|
| 75 |
+
2,
|
| 76 |
+
2
|
| 77 |
+
],
|
| 78 |
+
"torch_dtype": "float32",
|
| 79 |
+
"transformers_version": "4.30.2"
|
| 80 |
+
}
|
checkpoint-40/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ba0505b98d428f7f5d03ffd69aa086ecbd11ce506c0ba7acfd5e56f6dc1bfbfc
|
| 3 |
+
size 29838853
|
checkpoint-40/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:08605b63118cd35227e16af31386d759e6f85b111ed2cd236aafe8b343ef6b51
|
| 3 |
+
size 14932813
|
checkpoint-40/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:13d35a3f686a8199c1f12ea412db4b0fa420e3d79b06da4fb3ed9ed5ea62d2ed
|
| 3 |
+
size 14575
|
checkpoint-40/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e2895218501d856bd4db6117caf5e3c897ff63d38ee40988f3e62d4405b3e69
|
| 3 |
+
size 627
|
checkpoint-40/trainer_state.json
ADDED
|
@@ -0,0 +1,324 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 1.135031819343567,
|
| 3 |
+
"best_model_checkpoint": "/robodata/smodak/Projects/nspl/scripts/terrainseg/training/models/safety-utcustom-train-SF-RGB-b0/checkpoint-40",
|
| 4 |
+
"epoch": 4.0,
|
| 5 |
+
"global_step": 40,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.1,
|
| 12 |
+
"learning_rate": 1.5e-07,
|
| 13 |
+
"loss": 1.207,
|
| 14 |
+
"step": 1
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.2,
|
| 18 |
+
"learning_rate": 3e-07,
|
| 19 |
+
"loss": 1.2091,
|
| 20 |
+
"step": 2
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.3,
|
| 24 |
+
"learning_rate": 4.5000000000000003e-07,
|
| 25 |
+
"loss": 1.2064,
|
| 26 |
+
"step": 3
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.4,
|
| 30 |
+
"learning_rate": 6e-07,
|
| 31 |
+
"loss": 1.2111,
|
| 32 |
+
"step": 4
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.5,
|
| 36 |
+
"learning_rate": 7.5e-07,
|
| 37 |
+
"loss": 1.2054,
|
| 38 |
+
"step": 5
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.6,
|
| 42 |
+
"learning_rate": 9.000000000000001e-07,
|
| 43 |
+
"loss": 1.2113,
|
| 44 |
+
"step": 6
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.7,
|
| 48 |
+
"learning_rate": 1.0500000000000001e-06,
|
| 49 |
+
"loss": 1.2112,
|
| 50 |
+
"step": 7
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.8,
|
| 54 |
+
"learning_rate": 1.2e-06,
|
| 55 |
+
"loss": 1.2149,
|
| 56 |
+
"step": 8
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.9,
|
| 60 |
+
"learning_rate": 1.35e-06,
|
| 61 |
+
"loss": 1.2028,
|
| 62 |
+
"step": 9
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 1.0,
|
| 66 |
+
"learning_rate": 1.5e-06,
|
| 67 |
+
"loss": 1.2069,
|
| 68 |
+
"step": 10
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 1.0,
|
| 72 |
+
"eval_accuracy_safe": 0.6266745309385854,
|
| 73 |
+
"eval_accuracy_unlabeled": NaN,
|
| 74 |
+
"eval_accuracy_unsafe": 0.09601107572341809,
|
| 75 |
+
"eval_iou_safe": 0.026090091061736383,
|
| 76 |
+
"eval_iou_unlabeled": 0.0,
|
| 77 |
+
"eval_iou_unsafe": 0.09583941787515647,
|
| 78 |
+
"eval_loss": 1.1287050247192383,
|
| 79 |
+
"eval_mean_accuracy": 0.3613428033310017,
|
| 80 |
+
"eval_mean_iou": 0.04064316964563095,
|
| 81 |
+
"eval_overall_accuracy": 0.11168602331360775,
|
| 82 |
+
"eval_runtime": 9.0643,
|
| 83 |
+
"eval_samples_per_second": 7.392,
|
| 84 |
+
"eval_steps_per_second": 0.552,
|
| 85 |
+
"step": 10
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"epoch": 1.1,
|
| 89 |
+
"learning_rate": 1.6499999999999999e-06,
|
| 90 |
+
"loss": 1.2039,
|
| 91 |
+
"step": 11
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"epoch": 1.2,
|
| 95 |
+
"learning_rate": 1.8000000000000001e-06,
|
| 96 |
+
"loss": 1.2092,
|
| 97 |
+
"step": 12
|
| 98 |
+
},
|
| 99 |
+
{
|
| 100 |
+
"epoch": 1.3,
|
| 101 |
+
"learning_rate": 1.95e-06,
|
| 102 |
+
"loss": 1.2029,
|
| 103 |
+
"step": 13
|
| 104 |
+
},
|
| 105 |
+
{
|
| 106 |
+
"epoch": 1.4,
|
| 107 |
+
"learning_rate": 2.1000000000000002e-06,
|
| 108 |
+
"loss": 1.206,
|
| 109 |
+
"step": 14
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 1.5,
|
| 113 |
+
"learning_rate": 2.25e-06,
|
| 114 |
+
"loss": 1.203,
|
| 115 |
+
"step": 15
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 1.6,
|
| 119 |
+
"learning_rate": 2.4e-06,
|
| 120 |
+
"loss": 1.2048,
|
| 121 |
+
"step": 16
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 1.7,
|
| 125 |
+
"learning_rate": 2.55e-06,
|
| 126 |
+
"loss": 1.2063,
|
| 127 |
+
"step": 17
|
| 128 |
+
},
|
| 129 |
+
{
|
| 130 |
+
"epoch": 1.8,
|
| 131 |
+
"learning_rate": 2.7e-06,
|
| 132 |
+
"loss": 1.1991,
|
| 133 |
+
"step": 18
|
| 134 |
+
},
|
| 135 |
+
{
|
| 136 |
+
"epoch": 1.9,
|
| 137 |
+
"learning_rate": 2.85e-06,
|
| 138 |
+
"loss": 1.1998,
|
| 139 |
+
"step": 19
|
| 140 |
+
},
|
| 141 |
+
{
|
| 142 |
+
"epoch": 2.0,
|
| 143 |
+
"learning_rate": 3e-06,
|
| 144 |
+
"loss": 1.196,
|
| 145 |
+
"step": 20
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 2.0,
|
| 149 |
+
"eval_accuracy_safe": 0.6836885748320168,
|
| 150 |
+
"eval_accuracy_unlabeled": NaN,
|
| 151 |
+
"eval_accuracy_unsafe": 0.11050988668363446,
|
| 152 |
+
"eval_iou_safe": 0.02896514993488335,
|
| 153 |
+
"eval_iou_unlabeled": 0.0,
|
| 154 |
+
"eval_iou_unsafe": 0.11038771755966317,
|
| 155 |
+
"eval_loss": 1.1407982110977173,
|
| 156 |
+
"eval_mean_accuracy": 0.39709923075782566,
|
| 157 |
+
"eval_mean_iou": 0.04645095583151551,
|
| 158 |
+
"eval_overall_accuracy": 0.1274406660848589,
|
| 159 |
+
"eval_runtime": 8.0076,
|
| 160 |
+
"eval_samples_per_second": 8.367,
|
| 161 |
+
"eval_steps_per_second": 0.624,
|
| 162 |
+
"step": 20
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 2.1,
|
| 166 |
+
"learning_rate": 3.15e-06,
|
| 167 |
+
"loss": 1.1935,
|
| 168 |
+
"step": 21
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 2.2,
|
| 172 |
+
"learning_rate": 3.2999999999999997e-06,
|
| 173 |
+
"loss": 1.1985,
|
| 174 |
+
"step": 22
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 2.3,
|
| 178 |
+
"learning_rate": 3.4500000000000004e-06,
|
| 179 |
+
"loss": 1.2026,
|
| 180 |
+
"step": 23
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 2.4,
|
| 184 |
+
"learning_rate": 3.6000000000000003e-06,
|
| 185 |
+
"loss": 1.1999,
|
| 186 |
+
"step": 24
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 2.5,
|
| 190 |
+
"learning_rate": 3.75e-06,
|
| 191 |
+
"loss": 1.194,
|
| 192 |
+
"step": 25
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 2.6,
|
| 196 |
+
"learning_rate": 3.9e-06,
|
| 197 |
+
"loss": 1.1856,
|
| 198 |
+
"step": 26
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 2.7,
|
| 202 |
+
"learning_rate": 4.05e-06,
|
| 203 |
+
"loss": 1.1875,
|
| 204 |
+
"step": 27
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 2.8,
|
| 208 |
+
"learning_rate": 4.2000000000000004e-06,
|
| 209 |
+
"loss": 1.1881,
|
| 210 |
+
"step": 28
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 2.9,
|
| 214 |
+
"learning_rate": 4.35e-06,
|
| 215 |
+
"loss": 1.1845,
|
| 216 |
+
"step": 29
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 3.0,
|
| 220 |
+
"learning_rate": 4.5e-06,
|
| 221 |
+
"loss": 1.1866,
|
| 222 |
+
"step": 30
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 3.0,
|
| 226 |
+
"eval_accuracy_safe": 0.7519284813859622,
|
| 227 |
+
"eval_accuracy_unlabeled": NaN,
|
| 228 |
+
"eval_accuracy_unsafe": 0.16529459990427606,
|
| 229 |
+
"eval_iou_safe": 0.033480391113503524,
|
| 230 |
+
"eval_iou_unlabeled": 0.0,
|
| 231 |
+
"eval_iou_unsafe": 0.16518399491940172,
|
| 232 |
+
"eval_loss": 1.1440774202346802,
|
| 233 |
+
"eval_mean_accuracy": 0.45861154064511916,
|
| 234 |
+
"eval_mean_iou": 0.06622146201096842,
|
| 235 |
+
"eval_overall_accuracy": 0.1826228241422283,
|
| 236 |
+
"eval_runtime": 9.047,
|
| 237 |
+
"eval_samples_per_second": 7.406,
|
| 238 |
+
"eval_steps_per_second": 0.553,
|
| 239 |
+
"step": 30
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 3.1,
|
| 243 |
+
"learning_rate": 4.65e-06,
|
| 244 |
+
"loss": 1.182,
|
| 245 |
+
"step": 31
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 3.2,
|
| 249 |
+
"learning_rate": 4.8e-06,
|
| 250 |
+
"loss": 1.1875,
|
| 251 |
+
"step": 32
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 3.3,
|
| 255 |
+
"learning_rate": 4.950000000000001e-06,
|
| 256 |
+
"loss": 1.1818,
|
| 257 |
+
"step": 33
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 3.4,
|
| 261 |
+
"learning_rate": 5.1e-06,
|
| 262 |
+
"loss": 1.1865,
|
| 263 |
+
"step": 34
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 3.5,
|
| 267 |
+
"learning_rate": 5.2500000000000006e-06,
|
| 268 |
+
"loss": 1.1706,
|
| 269 |
+
"step": 35
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 3.6,
|
| 273 |
+
"learning_rate": 5.4e-06,
|
| 274 |
+
"loss": 1.1752,
|
| 275 |
+
"step": 36
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 3.7,
|
| 279 |
+
"learning_rate": 5.55e-06,
|
| 280 |
+
"loss": 1.1652,
|
| 281 |
+
"step": 37
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 3.8,
|
| 285 |
+
"learning_rate": 5.7e-06,
|
| 286 |
+
"loss": 1.1744,
|
| 287 |
+
"step": 38
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 3.9,
|
| 291 |
+
"learning_rate": 5.850000000000001e-06,
|
| 292 |
+
"loss": 1.1668,
|
| 293 |
+
"step": 39
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 4.0,
|
| 297 |
+
"learning_rate": 6e-06,
|
| 298 |
+
"loss": 1.1701,
|
| 299 |
+
"step": 40
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 4.0,
|
| 303 |
+
"eval_accuracy_safe": 0.8300989587549779,
|
| 304 |
+
"eval_accuracy_unlabeled": NaN,
|
| 305 |
+
"eval_accuracy_unsafe": 0.26378994565277974,
|
| 306 |
+
"eval_iou_safe": 0.040970127159922556,
|
| 307 |
+
"eval_iou_unlabeled": 0.0,
|
| 308 |
+
"eval_iou_unsafe": 0.2636823369166496,
|
| 309 |
+
"eval_loss": 1.135031819343567,
|
| 310 |
+
"eval_mean_accuracy": 0.5469444522038788,
|
| 311 |
+
"eval_mean_iou": 0.10155082135885739,
|
| 312 |
+
"eval_overall_accuracy": 0.28051780586812036,
|
| 313 |
+
"eval_runtime": 9.2028,
|
| 314 |
+
"eval_samples_per_second": 7.28,
|
| 315 |
+
"eval_steps_per_second": 0.543,
|
| 316 |
+
"step": 40
|
| 317 |
+
}
|
| 318 |
+
],
|
| 319 |
+
"max_steps": 1200,
|
| 320 |
+
"num_train_epochs": 120,
|
| 321 |
+
"total_flos": 1.079796761100288e+16,
|
| 322 |
+
"trial_name": null,
|
| 323 |
+
"trial_params": null
|
| 324 |
+
}
|
checkpoint-40/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aa00751af1103d0c04af5b6d924f99fda1fc4fb7f319683e8f0485b9e1dc0273
|
| 3 |
+
size 4155
|
config.json
ADDED
|
@@ -0,0 +1,80 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "nvidia/mit-b0",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"SegformerForSemanticSegmentation"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.0,
|
| 7 |
+
"classifier_dropout_prob": 0.1,
|
| 8 |
+
"decoder_hidden_size": 256,
|
| 9 |
+
"depths": [
|
| 10 |
+
2,
|
| 11 |
+
2,
|
| 12 |
+
2,
|
| 13 |
+
2
|
| 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 |
+
32,
|
| 26 |
+
64,
|
| 27 |
+
160,
|
| 28 |
+
256
|
| 29 |
+
],
|
| 30 |
+
"id2label": {
|
| 31 |
+
"0": "unlabeled",
|
| 32 |
+
"1": "safe",
|
| 33 |
+
"2": "unsafe"
|
| 34 |
+
},
|
| 35 |
+
"image_size": 224,
|
| 36 |
+
"initializer_range": 0.02,
|
| 37 |
+
"label2id": {
|
| 38 |
+
"safe": 1,
|
| 39 |
+
"unlabeled": 0,
|
| 40 |
+
"unsafe": 2
|
| 41 |
+
},
|
| 42 |
+
"layer_norm_eps": 1e-06,
|
| 43 |
+
"mlp_ratios": [
|
| 44 |
+
4,
|
| 45 |
+
4,
|
| 46 |
+
4,
|
| 47 |
+
4
|
| 48 |
+
],
|
| 49 |
+
"model_type": "segformer",
|
| 50 |
+
"num_attention_heads": [
|
| 51 |
+
1,
|
| 52 |
+
2,
|
| 53 |
+
5,
|
| 54 |
+
8
|
| 55 |
+
],
|
| 56 |
+
"num_channels": 3,
|
| 57 |
+
"num_encoder_blocks": 4,
|
| 58 |
+
"patch_sizes": [
|
| 59 |
+
7,
|
| 60 |
+
3,
|
| 61 |
+
3,
|
| 62 |
+
3
|
| 63 |
+
],
|
| 64 |
+
"reshape_last_stage": true,
|
| 65 |
+
"semantic_loss_ignore_index": 255,
|
| 66 |
+
"sr_ratios": [
|
| 67 |
+
8,
|
| 68 |
+
4,
|
| 69 |
+
2,
|
| 70 |
+
1
|
| 71 |
+
],
|
| 72 |
+
"strides": [
|
| 73 |
+
4,
|
| 74 |
+
2,
|
| 75 |
+
2,
|
| 76 |
+
2
|
| 77 |
+
],
|
| 78 |
+
"torch_dtype": "float32",
|
| 79 |
+
"transformers_version": "4.30.2"
|
| 80 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:08605b63118cd35227e16af31386d759e6f85b111ed2cd236aafe8b343ef6b51
|
| 3 |
+
size 14932813
|
runs/Feb06_02-59-17_robovision.csres.utexas.edu/events.out.tfevents.1707209963.robovision.csres.utexas.edu.1658684.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d30d0d9ef61ff437e360aa139f0cf13d7c7815c5b6402d6cb1cb57708f2b2c0a
|
| 3 |
+
size 13978
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aa00751af1103d0c04af5b6d924f99fda1fc4fb7f319683e8f0485b9e1dc0273
|
| 3 |
+
size 4155
|