Training in progress, step 80
Browse files- checkpoint-80/config.json +80 -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 +632 -0
- checkpoint-80/training_args.bin +3 -0
- pytorch_model.bin +1 -1
- runs/Feb05_23-09-17_robolidar/events.out.tfevents.1707196164.robolidar.781259.0 +2 -2
checkpoint-80/config.json
ADDED
|
@@ -0,0 +1,80 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "nvidia/mit-b5",
|
| 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 |
+
6,
|
| 12 |
+
40,
|
| 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": "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": 6,
|
| 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-80/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d5b06467e932d8a772711bf25704d319c24887b61510d6c4d7200a80e512033b
|
| 3 |
+
size 677530431
|
checkpoint-80/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a1b440e78c9f741b2f1eba95eb6f325659282b46ce007ca08af37faa519c39a7
|
| 3 |
+
size 338834121
|
checkpoint-80/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cf1a9d08b8f2647a6ce0c407b33f2111d88572cf492dc685feed24c570648abd
|
| 3 |
+
size 14575
|
checkpoint-80/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2552a53307f86a6c86f6de8593fe7db5436a046ef0c42488381a7de82a9a5642
|
| 3 |
+
size 627
|
checkpoint-80/trainer_state.json
ADDED
|
@@ -0,0 +1,632 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.32469046115875244,
|
| 3 |
+
"best_model_checkpoint": "/robodata/smodak/Projects/nspl/scripts/terrainseg/training/models/safety-utcustom-train-SF-RGBD-b5/checkpoint-80",
|
| 4 |
+
"epoch": 7.2727272727272725,
|
| 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": 0.09,
|
| 12 |
+
"learning_rate": 7.272727272727273e-08,
|
| 13 |
+
"loss": 0.8005,
|
| 14 |
+
"step": 1
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.18,
|
| 18 |
+
"learning_rate": 1.4545454545454545e-07,
|
| 19 |
+
"loss": 0.7952,
|
| 20 |
+
"step": 2
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.27,
|
| 24 |
+
"learning_rate": 2.1818181818181815e-07,
|
| 25 |
+
"loss": 0.7806,
|
| 26 |
+
"step": 3
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.36,
|
| 30 |
+
"learning_rate": 2.909090909090909e-07,
|
| 31 |
+
"loss": 0.7985,
|
| 32 |
+
"step": 4
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.45,
|
| 36 |
+
"learning_rate": 3.636363636363636e-07,
|
| 37 |
+
"loss": 0.7916,
|
| 38 |
+
"step": 5
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.55,
|
| 42 |
+
"learning_rate": 4.363636363636363e-07,
|
| 43 |
+
"loss": 0.7885,
|
| 44 |
+
"step": 6
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.64,
|
| 48 |
+
"learning_rate": 5.090909090909091e-07,
|
| 49 |
+
"loss": 0.7869,
|
| 50 |
+
"step": 7
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.73,
|
| 54 |
+
"learning_rate": 5.818181818181818e-07,
|
| 55 |
+
"loss": 0.7871,
|
| 56 |
+
"step": 8
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.82,
|
| 60 |
+
"learning_rate": 6.545454545454546e-07,
|
| 61 |
+
"loss": 0.7895,
|
| 62 |
+
"step": 9
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.91,
|
| 66 |
+
"learning_rate": 7.272727272727272e-07,
|
| 67 |
+
"loss": 0.789,
|
| 68 |
+
"step": 10
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.91,
|
| 72 |
+
"eval_accuracy_safe": 0.020290978060994367,
|
| 73 |
+
"eval_accuracy_unlabeled": NaN,
|
| 74 |
+
"eval_accuracy_unsafe": 0.8956518586322223,
|
| 75 |
+
"eval_iou_safe": 0.009542102362547317,
|
| 76 |
+
"eval_iou_unlabeled": 0.0,
|
| 77 |
+
"eval_iou_unsafe": 0.872225496966486,
|
| 78 |
+
"eval_loss": 0.9554787278175354,
|
| 79 |
+
"eval_mean_accuracy": 0.4579714183466083,
|
| 80 |
+
"eval_mean_iou": 0.29392253310967775,
|
| 81 |
+
"eval_overall_accuracy": 0.8697951017920651,
|
| 82 |
+
"eval_runtime": 10.4712,
|
| 83 |
+
"eval_samples_per_second": 6.399,
|
| 84 |
+
"eval_steps_per_second": 0.478,
|
| 85 |
+
"step": 10
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"epoch": 1.0,
|
| 89 |
+
"learning_rate": 8e-07,
|
| 90 |
+
"loss": 0.7808,
|
| 91 |
+
"step": 11
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"epoch": 1.09,
|
| 95 |
+
"learning_rate": 8.727272727272726e-07,
|
| 96 |
+
"loss": 0.7854,
|
| 97 |
+
"step": 12
|
| 98 |
+
},
|
| 99 |
+
{
|
| 100 |
+
"epoch": 1.18,
|
| 101 |
+
"learning_rate": 9.454545454545454e-07,
|
| 102 |
+
"loss": 0.7698,
|
| 103 |
+
"step": 13
|
| 104 |
+
},
|
| 105 |
+
{
|
| 106 |
+
"epoch": 1.27,
|
| 107 |
+
"learning_rate": 1.0181818181818181e-06,
|
| 108 |
+
"loss": 0.7788,
|
| 109 |
+
"step": 14
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 1.36,
|
| 113 |
+
"learning_rate": 1.0909090909090908e-06,
|
| 114 |
+
"loss": 0.7783,
|
| 115 |
+
"step": 15
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 1.45,
|
| 119 |
+
"learning_rate": 1.1636363636363636e-06,
|
| 120 |
+
"loss": 0.7696,
|
| 121 |
+
"step": 16
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 1.55,
|
| 125 |
+
"learning_rate": 1.2363636363636363e-06,
|
| 126 |
+
"loss": 0.7638,
|
| 127 |
+
"step": 17
|
| 128 |
+
},
|
| 129 |
+
{
|
| 130 |
+
"epoch": 1.64,
|
| 131 |
+
"learning_rate": 1.3090909090909091e-06,
|
| 132 |
+
"loss": 0.7611,
|
| 133 |
+
"step": 18
|
| 134 |
+
},
|
| 135 |
+
{
|
| 136 |
+
"epoch": 1.73,
|
| 137 |
+
"learning_rate": 1.3818181818181818e-06,
|
| 138 |
+
"loss": 0.7597,
|
| 139 |
+
"step": 19
|
| 140 |
+
},
|
| 141 |
+
{
|
| 142 |
+
"epoch": 1.82,
|
| 143 |
+
"learning_rate": 1.4545454545454544e-06,
|
| 144 |
+
"loss": 0.7579,
|
| 145 |
+
"step": 20
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 1.82,
|
| 149 |
+
"eval_accuracy_safe": 0.011667264197131082,
|
| 150 |
+
"eval_accuracy_unlabeled": NaN,
|
| 151 |
+
"eval_accuracy_unsafe": 0.9614483463212281,
|
| 152 |
+
"eval_iou_safe": 0.006852036536648151,
|
| 153 |
+
"eval_iou_unlabeled": 0.0,
|
| 154 |
+
"eval_iou_unsafe": 0.9338335778122896,
|
| 155 |
+
"eval_loss": 0.8321800827980042,
|
| 156 |
+
"eval_mean_accuracy": 0.4865578052591796,
|
| 157 |
+
"eval_mean_iou": 0.3135618714496459,
|
| 158 |
+
"eval_overall_accuracy": 0.9333933360541045,
|
| 159 |
+
"eval_runtime": 11.8686,
|
| 160 |
+
"eval_samples_per_second": 5.645,
|
| 161 |
+
"eval_steps_per_second": 0.421,
|
| 162 |
+
"step": 20
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 1.91,
|
| 166 |
+
"learning_rate": 1.5272727272727273e-06,
|
| 167 |
+
"loss": 0.7626,
|
| 168 |
+
"step": 21
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 2.0,
|
| 172 |
+
"learning_rate": 1.6e-06,
|
| 173 |
+
"loss": 0.7399,
|
| 174 |
+
"step": 22
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 2.09,
|
| 178 |
+
"learning_rate": 1.6727272727272726e-06,
|
| 179 |
+
"loss": 0.7658,
|
| 180 |
+
"step": 23
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 2.18,
|
| 184 |
+
"learning_rate": 1.7454545454545452e-06,
|
| 185 |
+
"loss": 0.7404,
|
| 186 |
+
"step": 24
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 2.27,
|
| 190 |
+
"learning_rate": 1.818181818181818e-06,
|
| 191 |
+
"loss": 0.742,
|
| 192 |
+
"step": 25
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 2.36,
|
| 196 |
+
"learning_rate": 1.8909090909090907e-06,
|
| 197 |
+
"loss": 0.721,
|
| 198 |
+
"step": 26
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 2.45,
|
| 202 |
+
"learning_rate": 1.9636363636363636e-06,
|
| 203 |
+
"loss": 0.7222,
|
| 204 |
+
"step": 27
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 2.55,
|
| 208 |
+
"learning_rate": 2.0363636363636362e-06,
|
| 209 |
+
"loss": 0.7358,
|
| 210 |
+
"step": 28
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 2.64,
|
| 214 |
+
"learning_rate": 2.109090909090909e-06,
|
| 215 |
+
"loss": 0.7427,
|
| 216 |
+
"step": 29
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 2.73,
|
| 220 |
+
"learning_rate": 2.1818181818181815e-06,
|
| 221 |
+
"loss": 0.7103,
|
| 222 |
+
"step": 30
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 2.73,
|
| 226 |
+
"eval_accuracy_safe": 0.005111776747198353,
|
| 227 |
+
"eval_accuracy_unlabeled": NaN,
|
| 228 |
+
"eval_accuracy_unsafe": 0.9893036287919527,
|
| 229 |
+
"eval_iou_safe": 0.004283838202726343,
|
| 230 |
+
"eval_iou_unlabeled": 0.0,
|
| 231 |
+
"eval_iou_unsafe": 0.9604181920132638,
|
| 232 |
+
"eval_loss": 0.6728952527046204,
|
| 233 |
+
"eval_mean_accuracy": 0.4972077027695755,
|
| 234 |
+
"eval_mean_iou": 0.32156734340533005,
|
| 235 |
+
"eval_overall_accuracy": 0.96023217955632,
|
| 236 |
+
"eval_runtime": 12.232,
|
| 237 |
+
"eval_samples_per_second": 5.477,
|
| 238 |
+
"eval_steps_per_second": 0.409,
|
| 239 |
+
"step": 30
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 2.82,
|
| 243 |
+
"learning_rate": 2.254545454545454e-06,
|
| 244 |
+
"loss": 0.7102,
|
| 245 |
+
"step": 31
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 2.91,
|
| 249 |
+
"learning_rate": 2.3272727272727272e-06,
|
| 250 |
+
"loss": 0.7035,
|
| 251 |
+
"step": 32
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 3.0,
|
| 255 |
+
"learning_rate": 2.4e-06,
|
| 256 |
+
"loss": 0.6845,
|
| 257 |
+
"step": 33
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 3.09,
|
| 261 |
+
"learning_rate": 2.4727272727272725e-06,
|
| 262 |
+
"loss": 0.6932,
|
| 263 |
+
"step": 34
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 3.18,
|
| 267 |
+
"learning_rate": 2.545454545454545e-06,
|
| 268 |
+
"loss": 0.6848,
|
| 269 |
+
"step": 35
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 3.27,
|
| 273 |
+
"learning_rate": 2.6181818181818183e-06,
|
| 274 |
+
"loss": 0.6816,
|
| 275 |
+
"step": 36
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 3.36,
|
| 279 |
+
"learning_rate": 2.690909090909091e-06,
|
| 280 |
+
"loss": 0.6617,
|
| 281 |
+
"step": 37
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 3.45,
|
| 285 |
+
"learning_rate": 2.7636363636363635e-06,
|
| 286 |
+
"loss": 0.6924,
|
| 287 |
+
"step": 38
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 3.55,
|
| 291 |
+
"learning_rate": 2.836363636363636e-06,
|
| 292 |
+
"loss": 0.6775,
|
| 293 |
+
"step": 39
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 3.64,
|
| 297 |
+
"learning_rate": 2.909090909090909e-06,
|
| 298 |
+
"loss": 0.676,
|
| 299 |
+
"step": 40
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 3.64,
|
| 303 |
+
"eval_accuracy_safe": 0.0021453271190165035,
|
| 304 |
+
"eval_accuracy_unlabeled": NaN,
|
| 305 |
+
"eval_accuracy_unsafe": 0.9968958945126286,
|
| 306 |
+
"eval_iou_safe": 0.0020376330502982305,
|
| 307 |
+
"eval_iou_unlabeled": 0.0,
|
| 308 |
+
"eval_iou_unsafe": 0.9675401930395611,
|
| 309 |
+
"eval_loss": 0.5335736274719238,
|
| 310 |
+
"eval_mean_accuracy": 0.49952061081582255,
|
| 311 |
+
"eval_mean_iou": 0.32319260869661975,
|
| 312 |
+
"eval_overall_accuracy": 0.9675125577556554,
|
| 313 |
+
"eval_runtime": 10.8655,
|
| 314 |
+
"eval_samples_per_second": 6.166,
|
| 315 |
+
"eval_steps_per_second": 0.46,
|
| 316 |
+
"step": 40
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 3.73,
|
| 320 |
+
"learning_rate": 2.981818181818182e-06,
|
| 321 |
+
"loss": 0.6708,
|
| 322 |
+
"step": 41
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 3.82,
|
| 326 |
+
"learning_rate": 3.0545454545454546e-06,
|
| 327 |
+
"loss": 0.6587,
|
| 328 |
+
"step": 42
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 3.91,
|
| 332 |
+
"learning_rate": 3.127272727272727e-06,
|
| 333 |
+
"loss": 0.6511,
|
| 334 |
+
"step": 43
|
| 335 |
+
},
|
| 336 |
+
{
|
| 337 |
+
"epoch": 4.0,
|
| 338 |
+
"learning_rate": 3.2e-06,
|
| 339 |
+
"loss": 0.6533,
|
| 340 |
+
"step": 44
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 4.09,
|
| 344 |
+
"learning_rate": 3.272727272727273e-06,
|
| 345 |
+
"loss": 0.6371,
|
| 346 |
+
"step": 45
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 4.18,
|
| 350 |
+
"learning_rate": 3.345454545454545e-06,
|
| 351 |
+
"loss": 0.6289,
|
| 352 |
+
"step": 46
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 4.27,
|
| 356 |
+
"learning_rate": 3.418181818181818e-06,
|
| 357 |
+
"loss": 0.6143,
|
| 358 |
+
"step": 47
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"epoch": 4.36,
|
| 362 |
+
"learning_rate": 3.4909090909090904e-06,
|
| 363 |
+
"loss": 0.6047,
|
| 364 |
+
"step": 48
|
| 365 |
+
},
|
| 366 |
+
{
|
| 367 |
+
"epoch": 4.45,
|
| 368 |
+
"learning_rate": 3.5636363636363635e-06,
|
| 369 |
+
"loss": 0.6173,
|
| 370 |
+
"step": 49
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 4.55,
|
| 374 |
+
"learning_rate": 3.636363636363636e-06,
|
| 375 |
+
"loss": 0.5955,
|
| 376 |
+
"step": 50
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 4.55,
|
| 380 |
+
"eval_accuracy_safe": 0.00010023091661173242,
|
| 381 |
+
"eval_accuracy_unlabeled": NaN,
|
| 382 |
+
"eval_accuracy_unsafe": 0.9992954468465131,
|
| 383 |
+
"eval_iou_safe": 9.918496661090691e-05,
|
| 384 |
+
"eval_iou_unlabeled": 0.0,
|
| 385 |
+
"eval_iou_unsafe": 0.9697964694697941,
|
| 386 |
+
"eval_loss": 0.4440336227416992,
|
| 387 |
+
"eval_mean_accuracy": 0.4996978388815624,
|
| 388 |
+
"eval_mean_iou": 0.32329855147880165,
|
| 389 |
+
"eval_overall_accuracy": 0.96978082229842,
|
| 390 |
+
"eval_runtime": 10.7685,
|
| 391 |
+
"eval_samples_per_second": 6.222,
|
| 392 |
+
"eval_steps_per_second": 0.464,
|
| 393 |
+
"step": 50
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 4.64,
|
| 397 |
+
"learning_rate": 3.709090909090909e-06,
|
| 398 |
+
"loss": 0.6184,
|
| 399 |
+
"step": 51
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 4.73,
|
| 403 |
+
"learning_rate": 3.7818181818181815e-06,
|
| 404 |
+
"loss": 0.6059,
|
| 405 |
+
"step": 52
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 4.82,
|
| 409 |
+
"learning_rate": 3.8545454545454545e-06,
|
| 410 |
+
"loss": 0.5942,
|
| 411 |
+
"step": 53
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 4.91,
|
| 415 |
+
"learning_rate": 3.927272727272727e-06,
|
| 416 |
+
"loss": 0.5764,
|
| 417 |
+
"step": 54
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 5.0,
|
| 421 |
+
"learning_rate": 4e-06,
|
| 422 |
+
"loss": 0.5745,
|
| 423 |
+
"step": 55
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 5.09,
|
| 427 |
+
"learning_rate": 3.9961722488038276e-06,
|
| 428 |
+
"loss": 0.5496,
|
| 429 |
+
"step": 56
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 5.18,
|
| 433 |
+
"learning_rate": 3.992344497607655e-06,
|
| 434 |
+
"loss": 0.5785,
|
| 435 |
+
"step": 57
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 5.27,
|
| 439 |
+
"learning_rate": 3.988516746411483e-06,
|
| 440 |
+
"loss": 0.5468,
|
| 441 |
+
"step": 58
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 5.36,
|
| 445 |
+
"learning_rate": 3.984688995215311e-06,
|
| 446 |
+
"loss": 0.5697,
|
| 447 |
+
"step": 59
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 5.45,
|
| 451 |
+
"learning_rate": 3.980861244019139e-06,
|
| 452 |
+
"loss": 0.5691,
|
| 453 |
+
"step": 60
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 5.45,
|
| 457 |
+
"eval_accuracy_safe": 1.9275176271487e-05,
|
| 458 |
+
"eval_accuracy_unlabeled": NaN,
|
| 459 |
+
"eval_accuracy_unsafe": 0.9997433241696639,
|
| 460 |
+
"eval_iou_safe": 1.9217760285345306e-05,
|
| 461 |
+
"eval_iou_unlabeled": 0.0,
|
| 462 |
+
"eval_iou_unsafe": 0.9702130617813918,
|
| 463 |
+
"eval_loss": 0.38122960925102234,
|
| 464 |
+
"eval_mean_accuracy": 0.49988129967296774,
|
| 465 |
+
"eval_mean_iou": 0.3234107598472257,
|
| 466 |
+
"eval_overall_accuracy": 0.9702130787408174,
|
| 467 |
+
"eval_runtime": 11.2754,
|
| 468 |
+
"eval_samples_per_second": 5.942,
|
| 469 |
+
"eval_steps_per_second": 0.443,
|
| 470 |
+
"step": 60
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 5.55,
|
| 474 |
+
"learning_rate": 3.977033492822966e-06,
|
| 475 |
+
"loss": 0.5238,
|
| 476 |
+
"step": 61
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 5.64,
|
| 480 |
+
"learning_rate": 3.973205741626794e-06,
|
| 481 |
+
"loss": 0.5514,
|
| 482 |
+
"step": 62
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 5.73,
|
| 486 |
+
"learning_rate": 3.969377990430622e-06,
|
| 487 |
+
"loss": 0.5261,
|
| 488 |
+
"step": 63
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 5.82,
|
| 492 |
+
"learning_rate": 3.96555023923445e-06,
|
| 493 |
+
"loss": 0.5348,
|
| 494 |
+
"step": 64
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 5.91,
|
| 498 |
+
"learning_rate": 3.961722488038277e-06,
|
| 499 |
+
"loss": 0.5614,
|
| 500 |
+
"step": 65
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 6.0,
|
| 504 |
+
"learning_rate": 3.957894736842105e-06,
|
| 505 |
+
"loss": 0.5475,
|
| 506 |
+
"step": 66
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 6.09,
|
| 510 |
+
"learning_rate": 3.954066985645933e-06,
|
| 511 |
+
"loss": 0.5134,
|
| 512 |
+
"step": 67
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 6.18,
|
| 516 |
+
"learning_rate": 3.950239234449761e-06,
|
| 517 |
+
"loss": 0.5047,
|
| 518 |
+
"step": 68
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 6.27,
|
| 522 |
+
"learning_rate": 3.946411483253588e-06,
|
| 523 |
+
"loss": 0.4845,
|
| 524 |
+
"step": 69
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 6.36,
|
| 528 |
+
"learning_rate": 3.942583732057416e-06,
|
| 529 |
+
"loss": 0.5067,
|
| 530 |
+
"step": 70
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 6.36,
|
| 534 |
+
"eval_accuracy_safe": 0.0,
|
| 535 |
+
"eval_accuracy_unlabeled": NaN,
|
| 536 |
+
"eval_accuracy_unsafe": 0.999641064518858,
|
| 537 |
+
"eval_iou_safe": 0.0,
|
| 538 |
+
"eval_iou_unlabeled": 0.0,
|
| 539 |
+
"eval_iou_unsafe": 0.9701133255524892,
|
| 540 |
+
"eval_loss": 0.3590196967124939,
|
| 541 |
+
"eval_mean_accuracy": 0.499820532259429,
|
| 542 |
+
"eval_mean_iou": 0.3233711085174964,
|
| 543 |
+
"eval_overall_accuracy": 0.9701132703183303,
|
| 544 |
+
"eval_runtime": 10.8376,
|
| 545 |
+
"eval_samples_per_second": 6.182,
|
| 546 |
+
"eval_steps_per_second": 0.461,
|
| 547 |
+
"step": 70
|
| 548 |
+
},
|
| 549 |
+
{
|
| 550 |
+
"epoch": 6.45,
|
| 551 |
+
"learning_rate": 3.938755980861244e-06,
|
| 552 |
+
"loss": 0.4808,
|
| 553 |
+
"step": 71
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"epoch": 6.55,
|
| 557 |
+
"learning_rate": 3.934928229665072e-06,
|
| 558 |
+
"loss": 0.5075,
|
| 559 |
+
"step": 72
|
| 560 |
+
},
|
| 561 |
+
{
|
| 562 |
+
"epoch": 6.64,
|
| 563 |
+
"learning_rate": 3.931100478468899e-06,
|
| 564 |
+
"loss": 0.5245,
|
| 565 |
+
"step": 73
|
| 566 |
+
},
|
| 567 |
+
{
|
| 568 |
+
"epoch": 6.73,
|
| 569 |
+
"learning_rate": 3.927272727272727e-06,
|
| 570 |
+
"loss": 0.4984,
|
| 571 |
+
"step": 74
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 6.82,
|
| 575 |
+
"learning_rate": 3.923444976076555e-06,
|
| 576 |
+
"loss": 0.483,
|
| 577 |
+
"step": 75
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 6.91,
|
| 581 |
+
"learning_rate": 3.919617224880383e-06,
|
| 582 |
+
"loss": 0.5161,
|
| 583 |
+
"step": 76
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 7.0,
|
| 587 |
+
"learning_rate": 3.9157894736842104e-06,
|
| 588 |
+
"loss": 0.4869,
|
| 589 |
+
"step": 77
|
| 590 |
+
},
|
| 591 |
+
{
|
| 592 |
+
"epoch": 7.09,
|
| 593 |
+
"learning_rate": 3.911961722488038e-06,
|
| 594 |
+
"loss": 0.4928,
|
| 595 |
+
"step": 78
|
| 596 |
+
},
|
| 597 |
+
{
|
| 598 |
+
"epoch": 7.18,
|
| 599 |
+
"learning_rate": 3.908133971291866e-06,
|
| 600 |
+
"loss": 0.4828,
|
| 601 |
+
"step": 79
|
| 602 |
+
},
|
| 603 |
+
{
|
| 604 |
+
"epoch": 7.27,
|
| 605 |
+
"learning_rate": 3.904306220095694e-06,
|
| 606 |
+
"loss": 0.4656,
|
| 607 |
+
"step": 80
|
| 608 |
+
},
|
| 609 |
+
{
|
| 610 |
+
"epoch": 7.27,
|
| 611 |
+
"eval_accuracy_safe": 0.0,
|
| 612 |
+
"eval_accuracy_unlabeled": NaN,
|
| 613 |
+
"eval_accuracy_unsafe": 0.999869403337525,
|
| 614 |
+
"eval_iou_safe": 0.0,
|
| 615 |
+
"eval_iou_unlabeled": 0.0,
|
| 616 |
+
"eval_iou_unsafe": 0.970334864374417,
|
| 617 |
+
"eval_loss": 0.32469046115875244,
|
| 618 |
+
"eval_mean_accuracy": 0.4999347016687625,
|
| 619 |
+
"eval_mean_iou": 0.32344495479147234,
|
| 620 |
+
"eval_overall_accuracy": 0.970334864374417,
|
| 621 |
+
"eval_runtime": 11.3252,
|
| 622 |
+
"eval_samples_per_second": 5.916,
|
| 623 |
+
"eval_steps_per_second": 0.441,
|
| 624 |
+
"step": 80
|
| 625 |
+
}
|
| 626 |
+
],
|
| 627 |
+
"max_steps": 1100,
|
| 628 |
+
"num_train_epochs": 100,
|
| 629 |
+
"total_flos": 8.966408307348603e+17,
|
| 630 |
+
"trial_name": null,
|
| 631 |
+
"trial_params": null
|
| 632 |
+
}
|
checkpoint-80/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e88955e6e4644e2a2ac452d82e4be1dbef3f3e51d5314588838187a999f14a95
|
| 3 |
+
size 4155
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 338834121
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a1b440e78c9f741b2f1eba95eb6f325659282b46ce007ca08af37faa519c39a7
|
| 3 |
size 338834121
|
runs/Feb05_23-09-17_robolidar/events.out.tfevents.1707196164.robolidar.781259.0
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d10f4e652996a883c38113af4a8ad3bbda2eb88c0f3a68e4f5a9630db68a3088
|
| 3 |
+
size 23194
|