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/Feb07_22-15-06_robovision.csres.utexas.edu/events.out.tfevents.1707365713.robovision.csres.utexas.edu.742362.0 +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": 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-80/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ad0db0fe74a86ae9f1fb766f40bf95f9f70eb66851543bdd1d003ee09d77ba76
|
| 3 |
+
size 677455103
|
checkpoint-80/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e4e73a15398e3b1dbf67a446dceb98a21dc84a7f59f69771a09b646761b706f0
|
| 3 |
+
size 338796489
|
checkpoint-80/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1e8f8d8944ad581893f04d1331c217a77c71c3b803a68490e3e047f95dab4e4d
|
| 3 |
+
size 14575
|
checkpoint-80/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:743aead8b79a67257c91584f3c344e1eba3504f44f1a1f1cdaae63dfe41fcaf4
|
| 3 |
+
size 627
|
checkpoint-80/trainer_state.json
ADDED
|
@@ -0,0 +1,632 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.8647122979164124,
|
| 3 |
+
"best_model_checkpoint": "/robodata/smodak/Projects/nspl/scripts/terrainseg/training/models/safety-utcustom-train-SF-RGB-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": 1.764705882352941e-07,
|
| 13 |
+
"loss": 1.2293,
|
| 14 |
+
"step": 1
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.18,
|
| 18 |
+
"learning_rate": 3.529411764705882e-07,
|
| 19 |
+
"loss": 1.2349,
|
| 20 |
+
"step": 2
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.27,
|
| 24 |
+
"learning_rate": 5.294117647058824e-07,
|
| 25 |
+
"loss": 1.2357,
|
| 26 |
+
"step": 3
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.36,
|
| 30 |
+
"learning_rate": 7.058823529411765e-07,
|
| 31 |
+
"loss": 1.2242,
|
| 32 |
+
"step": 4
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.45,
|
| 36 |
+
"learning_rate": 8.823529411764706e-07,
|
| 37 |
+
"loss": 1.2247,
|
| 38 |
+
"step": 5
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.55,
|
| 42 |
+
"learning_rate": 1.0588235294117648e-06,
|
| 43 |
+
"loss": 1.227,
|
| 44 |
+
"step": 6
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.64,
|
| 48 |
+
"learning_rate": 1.2352941176470588e-06,
|
| 49 |
+
"loss": 1.2292,
|
| 50 |
+
"step": 7
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.73,
|
| 54 |
+
"learning_rate": 1.411764705882353e-06,
|
| 55 |
+
"loss": 1.2257,
|
| 56 |
+
"step": 8
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.82,
|
| 60 |
+
"learning_rate": 1.5882352941176472e-06,
|
| 61 |
+
"loss": 1.2173,
|
| 62 |
+
"step": 9
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.91,
|
| 66 |
+
"learning_rate": 1.7647058823529412e-06,
|
| 67 |
+
"loss": 1.2239,
|
| 68 |
+
"step": 10
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.91,
|
| 72 |
+
"eval_accuracy_safe": 0.39920432072351303,
|
| 73 |
+
"eval_accuracy_unlabeled": NaN,
|
| 74 |
+
"eval_accuracy_unsafe": 0.29510386893492613,
|
| 75 |
+
"eval_iou_safe": 0.031418797454432365,
|
| 76 |
+
"eval_iou_unlabeled": 0.0,
|
| 77 |
+
"eval_iou_unsafe": 0.29392505413655395,
|
| 78 |
+
"eval_loss": 1.1102662086486816,
|
| 79 |
+
"eval_mean_accuracy": 0.34715409482921955,
|
| 80 |
+
"eval_mean_iou": 0.10844795053032878,
|
| 81 |
+
"eval_overall_accuracy": 0.2981788293639226,
|
| 82 |
+
"eval_runtime": 9.3061,
|
| 83 |
+
"eval_samples_per_second": 7.2,
|
| 84 |
+
"eval_steps_per_second": 0.537,
|
| 85 |
+
"step": 10
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"epoch": 1.0,
|
| 89 |
+
"learning_rate": 1.9411764705882353e-06,
|
| 90 |
+
"loss": 1.221,
|
| 91 |
+
"step": 11
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"epoch": 1.09,
|
| 95 |
+
"learning_rate": 2.1176470588235296e-06,
|
| 96 |
+
"loss": 1.2149,
|
| 97 |
+
"step": 12
|
| 98 |
+
},
|
| 99 |
+
{
|
| 100 |
+
"epoch": 1.18,
|
| 101 |
+
"learning_rate": 2.2941176470588234e-06,
|
| 102 |
+
"loss": 1.2197,
|
| 103 |
+
"step": 13
|
| 104 |
+
},
|
| 105 |
+
{
|
| 106 |
+
"epoch": 1.27,
|
| 107 |
+
"learning_rate": 2.4705882352941177e-06,
|
| 108 |
+
"loss": 1.2064,
|
| 109 |
+
"step": 14
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 1.36,
|
| 113 |
+
"learning_rate": 2.647058823529412e-06,
|
| 114 |
+
"loss": 1.2042,
|
| 115 |
+
"step": 15
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 1.45,
|
| 119 |
+
"learning_rate": 2.823529411764706e-06,
|
| 120 |
+
"loss": 1.2046,
|
| 121 |
+
"step": 16
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 1.55,
|
| 125 |
+
"learning_rate": 3e-06,
|
| 126 |
+
"loss": 1.2054,
|
| 127 |
+
"step": 17
|
| 128 |
+
},
|
| 129 |
+
{
|
| 130 |
+
"epoch": 1.64,
|
| 131 |
+
"learning_rate": 2.990415335463259e-06,
|
| 132 |
+
"loss": 1.2002,
|
| 133 |
+
"step": 18
|
| 134 |
+
},
|
| 135 |
+
{
|
| 136 |
+
"epoch": 1.73,
|
| 137 |
+
"learning_rate": 2.9808306709265177e-06,
|
| 138 |
+
"loss": 1.1982,
|
| 139 |
+
"step": 19
|
| 140 |
+
},
|
| 141 |
+
{
|
| 142 |
+
"epoch": 1.82,
|
| 143 |
+
"learning_rate": 2.9712460063897764e-06,
|
| 144 |
+
"loss": 1.1948,
|
| 145 |
+
"step": 20
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 1.82,
|
| 149 |
+
"eval_accuracy_safe": 0.5218599774094934,
|
| 150 |
+
"eval_accuracy_unlabeled": NaN,
|
| 151 |
+
"eval_accuracy_unsafe": 0.3705393407485172,
|
| 152 |
+
"eval_iou_safe": 0.0439841259320199,
|
| 153 |
+
"eval_iou_unlabeled": 0.0,
|
| 154 |
+
"eval_iou_unsafe": 0.36893471456827454,
|
| 155 |
+
"eval_loss": 1.0963102579116821,
|
| 156 |
+
"eval_mean_accuracy": 0.4461996590790053,
|
| 157 |
+
"eval_mean_iou": 0.13763961350009815,
|
| 158 |
+
"eval_overall_accuracy": 0.37500910972481344,
|
| 159 |
+
"eval_runtime": 8.3942,
|
| 160 |
+
"eval_samples_per_second": 7.982,
|
| 161 |
+
"eval_steps_per_second": 0.596,
|
| 162 |
+
"step": 20
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 1.91,
|
| 166 |
+
"learning_rate": 2.9616613418530352e-06,
|
| 167 |
+
"loss": 1.1776,
|
| 168 |
+
"step": 21
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 2.0,
|
| 172 |
+
"learning_rate": 2.952076677316294e-06,
|
| 173 |
+
"loss": 1.1936,
|
| 174 |
+
"step": 22
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 2.09,
|
| 178 |
+
"learning_rate": 2.942492012779553e-06,
|
| 179 |
+
"loss": 1.1664,
|
| 180 |
+
"step": 23
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 2.18,
|
| 184 |
+
"learning_rate": 2.9329073482428116e-06,
|
| 185 |
+
"loss": 1.1809,
|
| 186 |
+
"step": 24
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 2.27,
|
| 190 |
+
"learning_rate": 2.9233226837060704e-06,
|
| 191 |
+
"loss": 1.1731,
|
| 192 |
+
"step": 25
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 2.36,
|
| 196 |
+
"learning_rate": 2.913738019169329e-06,
|
| 197 |
+
"loss": 1.1794,
|
| 198 |
+
"step": 26
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 2.45,
|
| 202 |
+
"learning_rate": 2.904153354632588e-06,
|
| 203 |
+
"loss": 1.1684,
|
| 204 |
+
"step": 27
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 2.55,
|
| 208 |
+
"learning_rate": 2.8945686900958468e-06,
|
| 209 |
+
"loss": 1.1594,
|
| 210 |
+
"step": 28
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 2.64,
|
| 214 |
+
"learning_rate": 2.884984025559105e-06,
|
| 215 |
+
"loss": 1.146,
|
| 216 |
+
"step": 29
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 2.73,
|
| 220 |
+
"learning_rate": 2.8753993610223644e-06,
|
| 221 |
+
"loss": 1.1661,
|
| 222 |
+
"step": 30
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 2.73,
|
| 226 |
+
"eval_accuracy_safe": 0.5863200218966003,
|
| 227 |
+
"eval_accuracy_unlabeled": NaN,
|
| 228 |
+
"eval_accuracy_unsafe": 0.49882181393718666,
|
| 229 |
+
"eval_iou_safe": 0.06472096392925002,
|
| 230 |
+
"eval_iou_unlabeled": 0.0,
|
| 231 |
+
"eval_iou_unsafe": 0.49613792944888824,
|
| 232 |
+
"eval_loss": 1.0516184568405151,
|
| 233 |
+
"eval_mean_accuracy": 0.5425709179168935,
|
| 234 |
+
"eval_mean_iou": 0.1869529644593794,
|
| 235 |
+
"eval_overall_accuracy": 0.5014063707038537,
|
| 236 |
+
"eval_runtime": 9.3615,
|
| 237 |
+
"eval_samples_per_second": 7.157,
|
| 238 |
+
"eval_steps_per_second": 0.534,
|
| 239 |
+
"step": 30
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 2.82,
|
| 243 |
+
"learning_rate": 2.865814696485623e-06,
|
| 244 |
+
"loss": 1.153,
|
| 245 |
+
"step": 31
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 2.91,
|
| 249 |
+
"learning_rate": 2.856230031948882e-06,
|
| 250 |
+
"loss": 1.149,
|
| 251 |
+
"step": 32
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 3.0,
|
| 255 |
+
"learning_rate": 2.8466453674121407e-06,
|
| 256 |
+
"loss": 1.164,
|
| 257 |
+
"step": 33
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 3.09,
|
| 261 |
+
"learning_rate": 2.8370607028753995e-06,
|
| 262 |
+
"loss": 1.1479,
|
| 263 |
+
"step": 34
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 3.18,
|
| 267 |
+
"learning_rate": 2.8274760383386583e-06,
|
| 268 |
+
"loss": 1.1428,
|
| 269 |
+
"step": 35
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 3.27,
|
| 273 |
+
"learning_rate": 2.817891373801917e-06,
|
| 274 |
+
"loss": 1.1398,
|
| 275 |
+
"step": 36
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 3.36,
|
| 279 |
+
"learning_rate": 2.8083067092651755e-06,
|
| 280 |
+
"loss": 1.1415,
|
| 281 |
+
"step": 37
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 3.45,
|
| 285 |
+
"learning_rate": 2.7987220447284347e-06,
|
| 286 |
+
"loss": 1.1146,
|
| 287 |
+
"step": 38
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 3.55,
|
| 291 |
+
"learning_rate": 2.7891373801916935e-06,
|
| 292 |
+
"loss": 1.1234,
|
| 293 |
+
"step": 39
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 3.64,
|
| 297 |
+
"learning_rate": 2.7795527156549523e-06,
|
| 298 |
+
"loss": 1.1112,
|
| 299 |
+
"step": 40
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 3.64,
|
| 303 |
+
"eval_accuracy_safe": 0.5458517893146133,
|
| 304 |
+
"eval_accuracy_unlabeled": NaN,
|
| 305 |
+
"eval_accuracy_unsafe": 0.5794390867479824,
|
| 306 |
+
"eval_iou_safe": 0.0899865428032596,
|
| 307 |
+
"eval_iou_unlabeled": 0.0,
|
| 308 |
+
"eval_iou_unsafe": 0.5753581085678546,
|
| 309 |
+
"eval_loss": 1.0047743320465088,
|
| 310 |
+
"eval_mean_accuracy": 0.5626454380312979,
|
| 311 |
+
"eval_mean_iou": 0.22178155045703807,
|
| 312 |
+
"eval_overall_accuracy": 0.5784469718363747,
|
| 313 |
+
"eval_runtime": 9.38,
|
| 314 |
+
"eval_samples_per_second": 7.143,
|
| 315 |
+
"eval_steps_per_second": 0.533,
|
| 316 |
+
"step": 40
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 3.73,
|
| 320 |
+
"learning_rate": 2.769968051118211e-06,
|
| 321 |
+
"loss": 1.1212,
|
| 322 |
+
"step": 41
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 3.82,
|
| 326 |
+
"learning_rate": 2.7603833865814694e-06,
|
| 327 |
+
"loss": 1.1117,
|
| 328 |
+
"step": 42
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 3.91,
|
| 332 |
+
"learning_rate": 2.7507987220447286e-06,
|
| 333 |
+
"loss": 1.1051,
|
| 334 |
+
"step": 43
|
| 335 |
+
},
|
| 336 |
+
{
|
| 337 |
+
"epoch": 4.0,
|
| 338 |
+
"learning_rate": 2.7412140575079874e-06,
|
| 339 |
+
"loss": 1.1382,
|
| 340 |
+
"step": 44
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 4.09,
|
| 344 |
+
"learning_rate": 2.731629392971246e-06,
|
| 345 |
+
"loss": 1.1075,
|
| 346 |
+
"step": 45
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 4.18,
|
| 350 |
+
"learning_rate": 2.722044728434505e-06,
|
| 351 |
+
"loss": 1.1096,
|
| 352 |
+
"step": 46
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 4.27,
|
| 356 |
+
"learning_rate": 2.7124600638977634e-06,
|
| 357 |
+
"loss": 1.0974,
|
| 358 |
+
"step": 47
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"epoch": 4.36,
|
| 362 |
+
"learning_rate": 2.7028753993610226e-06,
|
| 363 |
+
"loss": 1.0851,
|
| 364 |
+
"step": 48
|
| 365 |
+
},
|
| 366 |
+
{
|
| 367 |
+
"epoch": 4.45,
|
| 368 |
+
"learning_rate": 2.6932907348242814e-06,
|
| 369 |
+
"loss": 1.0851,
|
| 370 |
+
"step": 49
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 4.55,
|
| 374 |
+
"learning_rate": 2.6837060702875398e-06,
|
| 375 |
+
"loss": 1.0907,
|
| 376 |
+
"step": 50
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 4.55,
|
| 380 |
+
"eval_accuracy_safe": 0.5993018531154467,
|
| 381 |
+
"eval_accuracy_unlabeled": NaN,
|
| 382 |
+
"eval_accuracy_unsafe": 0.6366664738420048,
|
| 383 |
+
"eval_iou_safe": 0.10939424133801141,
|
| 384 |
+
"eval_iou_unlabeled": 0.0,
|
| 385 |
+
"eval_iou_unsafe": 0.6320960572783577,
|
| 386 |
+
"eval_loss": 0.9689871668815613,
|
| 387 |
+
"eval_mean_accuracy": 0.6179841634787258,
|
| 388 |
+
"eval_mean_iou": 0.24716343287212306,
|
| 389 |
+
"eval_overall_accuracy": 0.6355627828569554,
|
| 390 |
+
"eval_runtime": 9.8119,
|
| 391 |
+
"eval_samples_per_second": 6.828,
|
| 392 |
+
"eval_steps_per_second": 0.51,
|
| 393 |
+
"step": 50
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 4.64,
|
| 397 |
+
"learning_rate": 2.674121405750799e-06,
|
| 398 |
+
"loss": 1.0789,
|
| 399 |
+
"step": 51
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 4.73,
|
| 403 |
+
"learning_rate": 2.6645367412140573e-06,
|
| 404 |
+
"loss": 1.0566,
|
| 405 |
+
"step": 52
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 4.82,
|
| 409 |
+
"learning_rate": 2.654952076677316e-06,
|
| 410 |
+
"loss": 1.0718,
|
| 411 |
+
"step": 53
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 4.91,
|
| 415 |
+
"learning_rate": 2.6453674121405753e-06,
|
| 416 |
+
"loss": 1.0808,
|
| 417 |
+
"step": 54
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 5.0,
|
| 421 |
+
"learning_rate": 2.6357827476038337e-06,
|
| 422 |
+
"loss": 1.0808,
|
| 423 |
+
"step": 55
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 5.09,
|
| 427 |
+
"learning_rate": 2.626198083067093e-06,
|
| 428 |
+
"loss": 1.0625,
|
| 429 |
+
"step": 56
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 5.18,
|
| 433 |
+
"learning_rate": 2.6166134185303517e-06,
|
| 434 |
+
"loss": 1.0508,
|
| 435 |
+
"step": 57
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 5.27,
|
| 439 |
+
"learning_rate": 2.60702875399361e-06,
|
| 440 |
+
"loss": 1.0521,
|
| 441 |
+
"step": 58
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 5.36,
|
| 445 |
+
"learning_rate": 2.5974440894568693e-06,
|
| 446 |
+
"loss": 1.052,
|
| 447 |
+
"step": 59
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 5.45,
|
| 451 |
+
"learning_rate": 2.5878594249201277e-06,
|
| 452 |
+
"loss": 1.047,
|
| 453 |
+
"step": 60
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 5.45,
|
| 457 |
+
"eval_accuracy_safe": 0.6691570194409427,
|
| 458 |
+
"eval_accuracy_unlabeled": NaN,
|
| 459 |
+
"eval_accuracy_unsafe": 0.669918812994849,
|
| 460 |
+
"eval_iou_safe": 0.11592410370525706,
|
| 461 |
+
"eval_iou_unlabeled": 0.0,
|
| 462 |
+
"eval_iou_unsafe": 0.6655783206367077,
|
| 463 |
+
"eval_loss": 0.9437160491943359,
|
| 464 |
+
"eval_mean_accuracy": 0.6695379162178958,
|
| 465 |
+
"eval_mean_iou": 0.2605008081139883,
|
| 466 |
+
"eval_overall_accuracy": 0.6698963108347423,
|
| 467 |
+
"eval_runtime": 9.3506,
|
| 468 |
+
"eval_samples_per_second": 7.165,
|
| 469 |
+
"eval_steps_per_second": 0.535,
|
| 470 |
+
"step": 60
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 5.55,
|
| 474 |
+
"learning_rate": 2.5782747603833865e-06,
|
| 475 |
+
"loss": 1.0456,
|
| 476 |
+
"step": 61
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 5.64,
|
| 480 |
+
"learning_rate": 2.5686900958466457e-06,
|
| 481 |
+
"loss": 1.0296,
|
| 482 |
+
"step": 62
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 5.73,
|
| 486 |
+
"learning_rate": 2.559105431309904e-06,
|
| 487 |
+
"loss": 1.0334,
|
| 488 |
+
"step": 63
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 5.82,
|
| 492 |
+
"learning_rate": 2.5495207667731633e-06,
|
| 493 |
+
"loss": 1.0525,
|
| 494 |
+
"step": 64
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 5.91,
|
| 498 |
+
"learning_rate": 2.5399361022364216e-06,
|
| 499 |
+
"loss": 1.0397,
|
| 500 |
+
"step": 65
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 6.0,
|
| 504 |
+
"learning_rate": 2.5303514376996804e-06,
|
| 505 |
+
"loss": 1.0575,
|
| 506 |
+
"step": 66
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 6.09,
|
| 510 |
+
"learning_rate": 2.5207667731629396e-06,
|
| 511 |
+
"loss": 1.0245,
|
| 512 |
+
"step": 67
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 6.18,
|
| 516 |
+
"learning_rate": 2.511182108626198e-06,
|
| 517 |
+
"loss": 1.0284,
|
| 518 |
+
"step": 68
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 6.27,
|
| 522 |
+
"learning_rate": 2.501597444089457e-06,
|
| 523 |
+
"loss": 1.0127,
|
| 524 |
+
"step": 69
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 6.36,
|
| 528 |
+
"learning_rate": 2.4920127795527156e-06,
|
| 529 |
+
"loss": 1.0112,
|
| 530 |
+
"step": 70
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 6.36,
|
| 534 |
+
"eval_accuracy_safe": 0.6673046750012529,
|
| 535 |
+
"eval_accuracy_unlabeled": NaN,
|
| 536 |
+
"eval_accuracy_unsafe": 0.718865515124044,
|
| 537 |
+
"eval_iou_safe": 0.13494764234639625,
|
| 538 |
+
"eval_iou_unlabeled": 0.0,
|
| 539 |
+
"eval_iou_unsafe": 0.7136723036690169,
|
| 540 |
+
"eval_loss": 0.9084014892578125,
|
| 541 |
+
"eval_mean_accuracy": 0.6930850950626484,
|
| 542 |
+
"eval_mean_iou": 0.28287331533847104,
|
| 543 |
+
"eval_overall_accuracy": 0.7173424905805446,
|
| 544 |
+
"eval_runtime": 9.0845,
|
| 545 |
+
"eval_samples_per_second": 7.375,
|
| 546 |
+
"eval_steps_per_second": 0.55,
|
| 547 |
+
"step": 70
|
| 548 |
+
},
|
| 549 |
+
{
|
| 550 |
+
"epoch": 6.45,
|
| 551 |
+
"learning_rate": 2.4824281150159744e-06,
|
| 552 |
+
"loss": 1.0107,
|
| 553 |
+
"step": 71
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"epoch": 6.55,
|
| 557 |
+
"learning_rate": 2.4728434504792336e-06,
|
| 558 |
+
"loss": 1.0122,
|
| 559 |
+
"step": 72
|
| 560 |
+
},
|
| 561 |
+
{
|
| 562 |
+
"epoch": 6.64,
|
| 563 |
+
"learning_rate": 2.463258785942492e-06,
|
| 564 |
+
"loss": 1.0087,
|
| 565 |
+
"step": 73
|
| 566 |
+
},
|
| 567 |
+
{
|
| 568 |
+
"epoch": 6.73,
|
| 569 |
+
"learning_rate": 2.4536741214057507e-06,
|
| 570 |
+
"loss": 0.991,
|
| 571 |
+
"step": 74
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 6.82,
|
| 575 |
+
"learning_rate": 2.44408945686901e-06,
|
| 576 |
+
"loss": 1.0042,
|
| 577 |
+
"step": 75
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 6.91,
|
| 581 |
+
"learning_rate": 2.4345047923322683e-06,
|
| 582 |
+
"loss": 0.9788,
|
| 583 |
+
"step": 76
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 7.0,
|
| 587 |
+
"learning_rate": 2.424920127795527e-06,
|
| 588 |
+
"loss": 1.0371,
|
| 589 |
+
"step": 77
|
| 590 |
+
},
|
| 591 |
+
{
|
| 592 |
+
"epoch": 7.09,
|
| 593 |
+
"learning_rate": 2.415335463258786e-06,
|
| 594 |
+
"loss": 0.9884,
|
| 595 |
+
"step": 78
|
| 596 |
+
},
|
| 597 |
+
{
|
| 598 |
+
"epoch": 7.18,
|
| 599 |
+
"learning_rate": 2.4057507987220447e-06,
|
| 600 |
+
"loss": 0.9759,
|
| 601 |
+
"step": 79
|
| 602 |
+
},
|
| 603 |
+
{
|
| 604 |
+
"epoch": 7.27,
|
| 605 |
+
"learning_rate": 2.396166134185304e-06,
|
| 606 |
+
"loss": 0.9925,
|
| 607 |
+
"step": 80
|
| 608 |
+
},
|
| 609 |
+
{
|
| 610 |
+
"epoch": 7.27,
|
| 611 |
+
"eval_accuracy_safe": 0.6842282797676185,
|
| 612 |
+
"eval_accuracy_unlabeled": NaN,
|
| 613 |
+
"eval_accuracy_unsafe": 0.7664939888573942,
|
| 614 |
+
"eval_iou_safe": 0.14521835177647324,
|
| 615 |
+
"eval_iou_unlabeled": 0.0,
|
| 616 |
+
"eval_iou_unsafe": 0.7605469001045981,
|
| 617 |
+
"eval_loss": 0.8647122979164124,
|
| 618 |
+
"eval_mean_accuracy": 0.7253611343125064,
|
| 619 |
+
"eval_mean_iou": 0.3019217506270238,
|
| 620 |
+
"eval_overall_accuracy": 0.7640639917174382,
|
| 621 |
+
"eval_runtime": 9.9787,
|
| 622 |
+
"eval_samples_per_second": 6.714,
|
| 623 |
+
"eval_steps_per_second": 0.501,
|
| 624 |
+
"step": 80
|
| 625 |
+
}
|
| 626 |
+
],
|
| 627 |
+
"max_steps": 330,
|
| 628 |
+
"num_train_epochs": 30,
|
| 629 |
+
"total_flos": 4.482705625747292e+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 sha256:7f030ee6346022874816800d95eb680870a6f0608d7f7d70d11613eaa9ed9ab3
|
| 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 338796489
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e4e73a15398e3b1dbf67a446dceb98a21dc84a7f59f69771a09b646761b706f0
|
| 3 |
size 338796489
|
runs/Feb07_22-15-06_robovision.csres.utexas.edu/events.out.tfevents.1707365713.robovision.csres.utexas.edu.742362.0
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 sha256:1205e1c108e9a87497da904faf6379a2c8f1c59bd9c11b83e9b74c42ca51e204
|
| 3 |
+
size 23207
|