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/Feb12_06-10-30_robovision.csres.utexas.edu/events.out.tfevents.1707739845.robovision.csres.utexas.edu.2692127.0 +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": "dropoff",
|
| 33 |
+
"2": "undropoff"
|
| 34 |
+
},
|
| 35 |
+
"image_size": 224,
|
| 36 |
+
"initializer_range": 0.02,
|
| 37 |
+
"label2id": {
|
| 38 |
+
"dropoff": 1,
|
| 39 |
+
"undropoff": 2,
|
| 40 |
+
"unlabeled": 0
|
| 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 sha256:7859e3b129196783f3a4b989883b97c4308d2f409c6089ace11ef933b5a388a9
|
| 3 |
+
size 29838853
|
checkpoint-40/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4e75e92c72a179012b3b14833e0ba30583cd777bd6982d7f57f651d960683a5b
|
| 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:c301550081675e66a540685647726778557f949cb5ced37006a8b1363a534b82
|
| 3 |
+
size 14575
|
checkpoint-40/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d3ad3829ecfcd22bbfdce9baa6fad24f0ee1c52610efc15b889b35439745657e
|
| 3 |
+
size 627
|
checkpoint-40/trainer_state.json
ADDED
|
@@ -0,0 +1,324 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.5702608823776245,
|
| 3 |
+
"best_model_checkpoint": "/robodata/smodak/Projects/nspl/scripts/terrainseg/training/models/dropoff-utcustom-train-SF-RGB-b0_7/checkpoint-40",
|
| 4 |
+
"epoch": 13.333333333333334,
|
| 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": 0.33,
|
| 12 |
+
"learning_rate": 5e-06,
|
| 13 |
+
"loss": 1.2178,
|
| 14 |
+
"step": 1
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.67,
|
| 18 |
+
"learning_rate": 1e-05,
|
| 19 |
+
"loss": 1.2142,
|
| 20 |
+
"step": 2
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 1.0,
|
| 24 |
+
"learning_rate": 1.5e-05,
|
| 25 |
+
"loss": 1.2223,
|
| 26 |
+
"step": 3
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 1.33,
|
| 30 |
+
"learning_rate": 2e-05,
|
| 31 |
+
"loss": 1.208,
|
| 32 |
+
"step": 4
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 1.67,
|
| 36 |
+
"learning_rate": 2.5e-05,
|
| 37 |
+
"loss": 1.2072,
|
| 38 |
+
"step": 5
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 2.0,
|
| 42 |
+
"learning_rate": 3e-05,
|
| 43 |
+
"loss": 1.2015,
|
| 44 |
+
"step": 6
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 2.33,
|
| 48 |
+
"learning_rate": 3.5000000000000004e-05,
|
| 49 |
+
"loss": 1.1888,
|
| 50 |
+
"step": 7
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 2.67,
|
| 54 |
+
"learning_rate": 4e-05,
|
| 55 |
+
"loss": 1.1768,
|
| 56 |
+
"step": 8
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 3.0,
|
| 60 |
+
"learning_rate": 4.5e-05,
|
| 61 |
+
"loss": 1.1543,
|
| 62 |
+
"step": 9
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 3.33,
|
| 66 |
+
"learning_rate": 5e-05,
|
| 67 |
+
"loss": 1.1505,
|
| 68 |
+
"step": 10
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 3.33,
|
| 72 |
+
"eval_accuracy_dropoff": 0.9456199600248122,
|
| 73 |
+
"eval_accuracy_undropoff": 0.2616499186280552,
|
| 74 |
+
"eval_accuracy_unlabeled": NaN,
|
| 75 |
+
"eval_iou_dropoff": 0.07032648592680048,
|
| 76 |
+
"eval_iou_undropoff": 0.2615922132145178,
|
| 77 |
+
"eval_iou_unlabeled": 0.0,
|
| 78 |
+
"eval_loss": 1.1103304624557495,
|
| 79 |
+
"eval_mean_accuracy": 0.6036349393264338,
|
| 80 |
+
"eval_mean_iou": 0.11063956638043942,
|
| 81 |
+
"eval_overall_accuracy": 0.2919347127278646,
|
| 82 |
+
"eval_runtime": 1.7484,
|
| 83 |
+
"eval_samples_per_second": 8.579,
|
| 84 |
+
"eval_steps_per_second": 0.572,
|
| 85 |
+
"step": 10
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"epoch": 3.67,
|
| 89 |
+
"learning_rate": 5.500000000000001e-05,
|
| 90 |
+
"loss": 1.1405,
|
| 91 |
+
"step": 11
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"epoch": 4.0,
|
| 95 |
+
"learning_rate": 6e-05,
|
| 96 |
+
"loss": 1.1039,
|
| 97 |
+
"step": 12
|
| 98 |
+
},
|
| 99 |
+
{
|
| 100 |
+
"epoch": 4.33,
|
| 101 |
+
"learning_rate": 6.500000000000001e-05,
|
| 102 |
+
"loss": 1.1211,
|
| 103 |
+
"step": 13
|
| 104 |
+
},
|
| 105 |
+
{
|
| 106 |
+
"epoch": 4.67,
|
| 107 |
+
"learning_rate": 7.000000000000001e-05,
|
| 108 |
+
"loss": 1.0914,
|
| 109 |
+
"step": 14
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 5.0,
|
| 113 |
+
"learning_rate": 7.500000000000001e-05,
|
| 114 |
+
"loss": 1.0583,
|
| 115 |
+
"step": 15
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 5.33,
|
| 119 |
+
"learning_rate": 8e-05,
|
| 120 |
+
"loss": 1.0527,
|
| 121 |
+
"step": 16
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 5.67,
|
| 125 |
+
"learning_rate": 8.5e-05,
|
| 126 |
+
"loss": 1.0227,
|
| 127 |
+
"step": 17
|
| 128 |
+
},
|
| 129 |
+
{
|
| 130 |
+
"epoch": 6.0,
|
| 131 |
+
"learning_rate": 9e-05,
|
| 132 |
+
"loss": 1.1078,
|
| 133 |
+
"step": 18
|
| 134 |
+
},
|
| 135 |
+
{
|
| 136 |
+
"epoch": 6.33,
|
| 137 |
+
"learning_rate": 8.973684210526316e-05,
|
| 138 |
+
"loss": 1.0001,
|
| 139 |
+
"step": 19
|
| 140 |
+
},
|
| 141 |
+
{
|
| 142 |
+
"epoch": 6.67,
|
| 143 |
+
"learning_rate": 8.947368421052632e-05,
|
| 144 |
+
"loss": 0.9635,
|
| 145 |
+
"step": 20
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 6.67,
|
| 149 |
+
"eval_accuracy_dropoff": 0.8177051025800078,
|
| 150 |
+
"eval_accuracy_undropoff": 0.8763050644323176,
|
| 151 |
+
"eval_accuracy_unlabeled": NaN,
|
| 152 |
+
"eval_iou_dropoff": 0.2434656953279978,
|
| 153 |
+
"eval_iou_undropoff": 0.8694137027963167,
|
| 154 |
+
"eval_iou_unlabeled": 0.0,
|
| 155 |
+
"eval_loss": 1.0114336013793945,
|
| 156 |
+
"eval_mean_accuracy": 0.8470050835061627,
|
| 157 |
+
"eval_mean_iou": 0.3709597993747715,
|
| 158 |
+
"eval_overall_accuracy": 0.8737103780110677,
|
| 159 |
+
"eval_runtime": 1.7139,
|
| 160 |
+
"eval_samples_per_second": 8.752,
|
| 161 |
+
"eval_steps_per_second": 0.583,
|
| 162 |
+
"step": 20
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 7.0,
|
| 166 |
+
"learning_rate": 8.921052631578948e-05,
|
| 167 |
+
"loss": 1.0405,
|
| 168 |
+
"step": 21
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 7.33,
|
| 172 |
+
"learning_rate": 8.894736842105263e-05,
|
| 173 |
+
"loss": 0.9095,
|
| 174 |
+
"step": 22
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 7.67,
|
| 178 |
+
"learning_rate": 8.86842105263158e-05,
|
| 179 |
+
"loss": 0.9104,
|
| 180 |
+
"step": 23
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 8.0,
|
| 184 |
+
"learning_rate": 8.842105263157894e-05,
|
| 185 |
+
"loss": 0.8736,
|
| 186 |
+
"step": 24
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 8.33,
|
| 190 |
+
"learning_rate": 8.815789473684211e-05,
|
| 191 |
+
"loss": 0.8849,
|
| 192 |
+
"step": 25
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 8.67,
|
| 196 |
+
"learning_rate": 8.789473684210527e-05,
|
| 197 |
+
"loss": 0.8143,
|
| 198 |
+
"step": 26
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 9.0,
|
| 202 |
+
"learning_rate": 8.763157894736843e-05,
|
| 203 |
+
"loss": 0.7846,
|
| 204 |
+
"step": 27
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 9.33,
|
| 208 |
+
"learning_rate": 8.736842105263158e-05,
|
| 209 |
+
"loss": 0.7748,
|
| 210 |
+
"step": 28
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 9.67,
|
| 214 |
+
"learning_rate": 8.710526315789474e-05,
|
| 215 |
+
"loss": 0.7513,
|
| 216 |
+
"step": 29
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 10.0,
|
| 220 |
+
"learning_rate": 8.68421052631579e-05,
|
| 221 |
+
"loss": 0.9358,
|
| 222 |
+
"step": 30
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 10.0,
|
| 226 |
+
"eval_accuracy_dropoff": 0.5848209157534404,
|
| 227 |
+
"eval_accuracy_undropoff": 0.9605968730608304,
|
| 228 |
+
"eval_accuracy_unlabeled": NaN,
|
| 229 |
+
"eval_iou_dropoff": 0.3193744373731639,
|
| 230 |
+
"eval_iou_undropoff": 0.9425019881457949,
|
| 231 |
+
"eval_iou_unlabeled": 0.0,
|
| 232 |
+
"eval_loss": 0.8242360353469849,
|
| 233 |
+
"eval_mean_accuracy": 0.7727088944071354,
|
| 234 |
+
"eval_mean_iou": 0.42062547517298626,
|
| 235 |
+
"eval_overall_accuracy": 0.9439582824707031,
|
| 236 |
+
"eval_runtime": 1.7189,
|
| 237 |
+
"eval_samples_per_second": 8.726,
|
| 238 |
+
"eval_steps_per_second": 0.582,
|
| 239 |
+
"step": 30
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 10.33,
|
| 243 |
+
"learning_rate": 8.657894736842107e-05,
|
| 244 |
+
"loss": 0.7191,
|
| 245 |
+
"step": 31
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 10.67,
|
| 249 |
+
"learning_rate": 8.631578947368421e-05,
|
| 250 |
+
"loss": 0.73,
|
| 251 |
+
"step": 32
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 11.0,
|
| 255 |
+
"learning_rate": 8.605263157894737e-05,
|
| 256 |
+
"loss": 0.6168,
|
| 257 |
+
"step": 33
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 11.33,
|
| 261 |
+
"learning_rate": 8.578947368421054e-05,
|
| 262 |
+
"loss": 0.6559,
|
| 263 |
+
"step": 34
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 11.67,
|
| 267 |
+
"learning_rate": 8.552631578947369e-05,
|
| 268 |
+
"loss": 0.6277,
|
| 269 |
+
"step": 35
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 12.0,
|
| 273 |
+
"learning_rate": 8.526315789473684e-05,
|
| 274 |
+
"loss": 0.6168,
|
| 275 |
+
"step": 36
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 12.33,
|
| 279 |
+
"learning_rate": 8.5e-05,
|
| 280 |
+
"loss": 0.6095,
|
| 281 |
+
"step": 37
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 12.67,
|
| 285 |
+
"learning_rate": 8.473684210526316e-05,
|
| 286 |
+
"loss": 0.5927,
|
| 287 |
+
"step": 38
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 13.0,
|
| 291 |
+
"learning_rate": 8.447368421052632e-05,
|
| 292 |
+
"loss": 0.8162,
|
| 293 |
+
"step": 39
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 13.33,
|
| 297 |
+
"learning_rate": 8.421052631578948e-05,
|
| 298 |
+
"loss": 0.579,
|
| 299 |
+
"step": 40
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 13.33,
|
| 303 |
+
"eval_accuracy_dropoff": 0.5401589817814231,
|
| 304 |
+
"eval_accuracy_undropoff": 0.982923599779886,
|
| 305 |
+
"eval_accuracy_unlabeled": NaN,
|
| 306 |
+
"eval_iou_dropoff": 0.3951496002117638,
|
| 307 |
+
"eval_iou_undropoff": 0.9624271055937778,
|
| 308 |
+
"eval_iou_unlabeled": 0.0,
|
| 309 |
+
"eval_loss": 0.5702608823776245,
|
| 310 |
+
"eval_mean_accuracy": 0.7615412907806545,
|
| 311 |
+
"eval_mean_iou": 0.4525255686018472,
|
| 312 |
+
"eval_overall_accuracy": 0.9633188883463542,
|
| 313 |
+
"eval_runtime": 1.8153,
|
| 314 |
+
"eval_samples_per_second": 8.263,
|
| 315 |
+
"eval_steps_per_second": 0.551,
|
| 316 |
+
"step": 40
|
| 317 |
+
}
|
| 318 |
+
],
|
| 319 |
+
"max_steps": 360,
|
| 320 |
+
"num_train_epochs": 120,
|
| 321 |
+
"total_flos": 8028359035453440.0,
|
| 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 sha256:5b7857321965ab66eb6657636b1eae0c460a8508fd03e3aec44c53bb813616d2
|
| 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": "dropoff",
|
| 33 |
+
"2": "undropoff"
|
| 34 |
+
},
|
| 35 |
+
"image_size": 224,
|
| 36 |
+
"initializer_range": 0.02,
|
| 37 |
+
"label2id": {
|
| 38 |
+
"dropoff": 1,
|
| 39 |
+
"undropoff": 2,
|
| 40 |
+
"unlabeled": 0
|
| 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 sha256:4e75e92c72a179012b3b14833e0ba30583cd777bd6982d7f57f651d960683a5b
|
| 3 |
+
size 14932813
|
runs/Feb12_06-10-30_robovision.csres.utexas.edu/events.out.tfevents.1707739845.robovision.csres.utexas.edu.2692127.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:32e9e2c7d0a2b903c1549cffc35e13b13aeb91dada76c633340560114901a671
|
| 3 |
+
size 14052
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5b7857321965ab66eb6657636b1eae0c460a8508fd03e3aec44c53bb813616d2
|
| 3 |
+
size 4155
|