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/Feb12_06-53-01_robovision.csres.utexas.edu/events.out.tfevents.1707742388.robovision.csres.utexas.edu.2756623.0 +2 -2
checkpoint-80/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": 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:cf3658f21ff80b90b341a69e028c1e964bbd53d3c0da20ccddf0e41cb5fb5fcf
|
| 3 |
+
size 29876485
|
checkpoint-80/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3fe2c8f7bb76b694833eb7072e649a39e879cc8ef2eb77e9eb09aeecaadedef5
|
| 3 |
+
size 14951629
|
checkpoint-80/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e142622719e232eb12d7b433f8592aba5196ab4d7b70ff2447c2807d90abb4c0
|
| 3 |
+
size 14575
|
checkpoint-80/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:72309fbb9c0e0b33e1a7229aacda154ec1e83c11c826f24c2336ab33c98b0251
|
| 3 |
+
size 627
|
checkpoint-80/trainer_state.json
ADDED
|
@@ -0,0 +1,632 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.3478124737739563,
|
| 3 |
+
"best_model_checkpoint": "/robodata/smodak/Projects/nspl/scripts/terrainseg/training/models/dropoff-utcustom-train-SF-RGBD-b0_7/checkpoint-80",
|
| 4 |
+
"epoch": 40.0,
|
| 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": 0.5,
|
| 12 |
+
"learning_rate": 6.666666666666667e-06,
|
| 13 |
+
"loss": 1.0264,
|
| 14 |
+
"step": 1
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 1.0,
|
| 18 |
+
"learning_rate": 1.3333333333333333e-05,
|
| 19 |
+
"loss": 1.0249,
|
| 20 |
+
"step": 2
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 1.5,
|
| 24 |
+
"learning_rate": 2e-05,
|
| 25 |
+
"loss": 1.0219,
|
| 26 |
+
"step": 3
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 2.0,
|
| 30 |
+
"learning_rate": 2.6666666666666667e-05,
|
| 31 |
+
"loss": 1.0261,
|
| 32 |
+
"step": 4
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 2.5,
|
| 36 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 37 |
+
"loss": 1.0043,
|
| 38 |
+
"step": 5
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 3.0,
|
| 42 |
+
"learning_rate": 4e-05,
|
| 43 |
+
"loss": 0.9882,
|
| 44 |
+
"step": 6
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 3.5,
|
| 48 |
+
"learning_rate": 4.666666666666667e-05,
|
| 49 |
+
"loss": 0.9908,
|
| 50 |
+
"step": 7
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 4.0,
|
| 54 |
+
"learning_rate": 5.333333333333333e-05,
|
| 55 |
+
"loss": 0.9709,
|
| 56 |
+
"step": 8
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 4.5,
|
| 60 |
+
"learning_rate": 6.000000000000001e-05,
|
| 61 |
+
"loss": 0.961,
|
| 62 |
+
"step": 9
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 5.0,
|
| 66 |
+
"learning_rate": 6.666666666666667e-05,
|
| 67 |
+
"loss": 0.9508,
|
| 68 |
+
"step": 10
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 5.0,
|
| 72 |
+
"eval_accuracy_dropoff": 0.19369710314456753,
|
| 73 |
+
"eval_accuracy_undropoff": 0.9010801242217483,
|
| 74 |
+
"eval_accuracy_unlabeled": NaN,
|
| 75 |
+
"eval_iou_dropoff": 0.06049444267748618,
|
| 76 |
+
"eval_iou_undropoff": 0.8706257192603624,
|
| 77 |
+
"eval_iou_unlabeled": 0.0,
|
| 78 |
+
"eval_loss": 1.026282548904419,
|
| 79 |
+
"eval_mean_accuracy": 0.5473886136831579,
|
| 80 |
+
"eval_mean_iou": 0.31037338731261616,
|
| 81 |
+
"eval_overall_accuracy": 0.8716676712036133,
|
| 82 |
+
"eval_runtime": 2.7665,
|
| 83 |
+
"eval_samples_per_second": 7.229,
|
| 84 |
+
"eval_steps_per_second": 0.723,
|
| 85 |
+
"step": 10
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"epoch": 5.5,
|
| 89 |
+
"learning_rate": 7.333333333333333e-05,
|
| 90 |
+
"loss": 0.9292,
|
| 91 |
+
"step": 11
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"epoch": 6.0,
|
| 95 |
+
"learning_rate": 8e-05,
|
| 96 |
+
"loss": 0.9246,
|
| 97 |
+
"step": 12
|
| 98 |
+
},
|
| 99 |
+
{
|
| 100 |
+
"epoch": 6.5,
|
| 101 |
+
"learning_rate": 7.964912280701755e-05,
|
| 102 |
+
"loss": 0.9097,
|
| 103 |
+
"step": 13
|
| 104 |
+
},
|
| 105 |
+
{
|
| 106 |
+
"epoch": 7.0,
|
| 107 |
+
"learning_rate": 7.929824561403509e-05,
|
| 108 |
+
"loss": 0.8786,
|
| 109 |
+
"step": 14
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 7.5,
|
| 113 |
+
"learning_rate": 7.894736842105263e-05,
|
| 114 |
+
"loss": 0.8697,
|
| 115 |
+
"step": 15
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 8.0,
|
| 119 |
+
"learning_rate": 7.859649122807017e-05,
|
| 120 |
+
"loss": 0.8421,
|
| 121 |
+
"step": 16
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 8.5,
|
| 125 |
+
"learning_rate": 7.824561403508773e-05,
|
| 126 |
+
"loss": 0.8223,
|
| 127 |
+
"step": 17
|
| 128 |
+
},
|
| 129 |
+
{
|
| 130 |
+
"epoch": 9.0,
|
| 131 |
+
"learning_rate": 7.789473684210527e-05,
|
| 132 |
+
"loss": 0.8166,
|
| 133 |
+
"step": 18
|
| 134 |
+
},
|
| 135 |
+
{
|
| 136 |
+
"epoch": 9.5,
|
| 137 |
+
"learning_rate": 7.754385964912281e-05,
|
| 138 |
+
"loss": 0.7987,
|
| 139 |
+
"step": 19
|
| 140 |
+
},
|
| 141 |
+
{
|
| 142 |
+
"epoch": 10.0,
|
| 143 |
+
"learning_rate": 7.719298245614036e-05,
|
| 144 |
+
"loss": 0.7814,
|
| 145 |
+
"step": 20
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 10.0,
|
| 149 |
+
"eval_accuracy_dropoff": 0.09518566939608707,
|
| 150 |
+
"eval_accuracy_undropoff": 0.9726282293027602,
|
| 151 |
+
"eval_accuracy_unlabeled": NaN,
|
| 152 |
+
"eval_iou_dropoff": 0.05836274909643214,
|
| 153 |
+
"eval_iou_undropoff": 0.9358911019066932,
|
| 154 |
+
"eval_iou_unlabeled": NaN,
|
| 155 |
+
"eval_loss": 0.7567641139030457,
|
| 156 |
+
"eval_mean_accuracy": 0.5339069493494236,
|
| 157 |
+
"eval_mean_iou": 0.4971269255015627,
|
| 158 |
+
"eval_overall_accuracy": 0.9361448287963867,
|
| 159 |
+
"eval_runtime": 2.8406,
|
| 160 |
+
"eval_samples_per_second": 7.041,
|
| 161 |
+
"eval_steps_per_second": 0.704,
|
| 162 |
+
"step": 20
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 10.5,
|
| 166 |
+
"learning_rate": 7.68421052631579e-05,
|
| 167 |
+
"loss": 0.7775,
|
| 168 |
+
"step": 21
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 11.0,
|
| 172 |
+
"learning_rate": 7.649122807017544e-05,
|
| 173 |
+
"loss": 0.744,
|
| 174 |
+
"step": 22
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 11.5,
|
| 178 |
+
"learning_rate": 7.614035087719298e-05,
|
| 179 |
+
"loss": 0.7385,
|
| 180 |
+
"step": 23
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 12.0,
|
| 184 |
+
"learning_rate": 7.578947368421052e-05,
|
| 185 |
+
"loss": 0.7156,
|
| 186 |
+
"step": 24
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 12.5,
|
| 190 |
+
"learning_rate": 7.543859649122808e-05,
|
| 191 |
+
"loss": 0.7073,
|
| 192 |
+
"step": 25
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 13.0,
|
| 196 |
+
"learning_rate": 7.508771929824562e-05,
|
| 197 |
+
"loss": 0.6876,
|
| 198 |
+
"step": 26
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 13.5,
|
| 202 |
+
"learning_rate": 7.473684210526316e-05,
|
| 203 |
+
"loss": 0.68,
|
| 204 |
+
"step": 27
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 14.0,
|
| 208 |
+
"learning_rate": 7.43859649122807e-05,
|
| 209 |
+
"loss": 0.6647,
|
| 210 |
+
"step": 28
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 14.5,
|
| 214 |
+
"learning_rate": 7.403508771929825e-05,
|
| 215 |
+
"loss": 0.656,
|
| 216 |
+
"step": 29
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 15.0,
|
| 220 |
+
"learning_rate": 7.368421052631579e-05,
|
| 221 |
+
"loss": 0.642,
|
| 222 |
+
"step": 30
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 15.0,
|
| 226 |
+
"eval_accuracy_dropoff": 0.10256657262781256,
|
| 227 |
+
"eval_accuracy_undropoff": 0.9861238615411099,
|
| 228 |
+
"eval_accuracy_unlabeled": NaN,
|
| 229 |
+
"eval_iou_dropoff": 0.07771069890623208,
|
| 230 |
+
"eval_iou_undropoff": 0.9491694411343236,
|
| 231 |
+
"eval_iou_unlabeled": NaN,
|
| 232 |
+
"eval_loss": 0.590660810470581,
|
| 233 |
+
"eval_mean_accuracy": 0.5443452170844613,
|
| 234 |
+
"eval_mean_iou": 0.5134400700202778,
|
| 235 |
+
"eval_overall_accuracy": 0.9493862152099609,
|
| 236 |
+
"eval_runtime": 2.7723,
|
| 237 |
+
"eval_samples_per_second": 7.214,
|
| 238 |
+
"eval_steps_per_second": 0.721,
|
| 239 |
+
"step": 30
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 15.5,
|
| 243 |
+
"learning_rate": 7.333333333333333e-05,
|
| 244 |
+
"loss": 0.6219,
|
| 245 |
+
"step": 31
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 16.0,
|
| 249 |
+
"learning_rate": 7.298245614035087e-05,
|
| 250 |
+
"loss": 0.6276,
|
| 251 |
+
"step": 32
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 16.5,
|
| 255 |
+
"learning_rate": 7.263157894736843e-05,
|
| 256 |
+
"loss": 0.5895,
|
| 257 |
+
"step": 33
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 17.0,
|
| 261 |
+
"learning_rate": 7.228070175438597e-05,
|
| 262 |
+
"loss": 0.5987,
|
| 263 |
+
"step": 34
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 17.5,
|
| 267 |
+
"learning_rate": 7.192982456140351e-05,
|
| 268 |
+
"loss": 0.578,
|
| 269 |
+
"step": 35
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 18.0,
|
| 273 |
+
"learning_rate": 7.157894736842105e-05,
|
| 274 |
+
"loss": 0.5622,
|
| 275 |
+
"step": 36
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 18.5,
|
| 279 |
+
"learning_rate": 7.12280701754386e-05,
|
| 280 |
+
"loss": 0.5411,
|
| 281 |
+
"step": 37
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 19.0,
|
| 285 |
+
"learning_rate": 7.087719298245614e-05,
|
| 286 |
+
"loss": 0.5512,
|
| 287 |
+
"step": 38
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 19.5,
|
| 291 |
+
"learning_rate": 7.052631578947368e-05,
|
| 292 |
+
"loss": 0.5536,
|
| 293 |
+
"step": 39
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 20.0,
|
| 297 |
+
"learning_rate": 7.017543859649124e-05,
|
| 298 |
+
"loss": 0.5118,
|
| 299 |
+
"step": 40
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 20.0,
|
| 303 |
+
"eval_accuracy_dropoff": 0.20064680382577582,
|
| 304 |
+
"eval_accuracy_undropoff": 0.9839122686389837,
|
| 305 |
+
"eval_accuracy_unlabeled": NaN,
|
| 306 |
+
"eval_iou_dropoff": 0.146396810999508,
|
| 307 |
+
"eval_iou_undropoff": 0.9509353469996961,
|
| 308 |
+
"eval_iou_unlabeled": 0.0,
|
| 309 |
+
"eval_loss": 0.48036208748817444,
|
| 310 |
+
"eval_mean_accuracy": 0.5922795362323798,
|
| 311 |
+
"eval_mean_iou": 0.3657773859997347,
|
| 312 |
+
"eval_overall_accuracy": 0.9513446807861328,
|
| 313 |
+
"eval_runtime": 3.0452,
|
| 314 |
+
"eval_samples_per_second": 6.568,
|
| 315 |
+
"eval_steps_per_second": 0.657,
|
| 316 |
+
"step": 40
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 20.5,
|
| 320 |
+
"learning_rate": 6.982456140350878e-05,
|
| 321 |
+
"loss": 0.5335,
|
| 322 |
+
"step": 41
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 21.0,
|
| 326 |
+
"learning_rate": 6.947368421052632e-05,
|
| 327 |
+
"loss": 0.5013,
|
| 328 |
+
"step": 42
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 21.5,
|
| 332 |
+
"learning_rate": 6.912280701754386e-05,
|
| 333 |
+
"loss": 0.538,
|
| 334 |
+
"step": 43
|
| 335 |
+
},
|
| 336 |
+
{
|
| 337 |
+
"epoch": 22.0,
|
| 338 |
+
"learning_rate": 6.87719298245614e-05,
|
| 339 |
+
"loss": 0.5046,
|
| 340 |
+
"step": 44
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 22.5,
|
| 344 |
+
"learning_rate": 6.842105263157895e-05,
|
| 345 |
+
"loss": 0.4906,
|
| 346 |
+
"step": 45
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 23.0,
|
| 350 |
+
"learning_rate": 6.80701754385965e-05,
|
| 351 |
+
"loss": 0.4797,
|
| 352 |
+
"step": 46
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 23.5,
|
| 356 |
+
"learning_rate": 6.771929824561404e-05,
|
| 357 |
+
"loss": 0.492,
|
| 358 |
+
"step": 47
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"epoch": 24.0,
|
| 362 |
+
"learning_rate": 6.736842105263159e-05,
|
| 363 |
+
"loss": 0.4671,
|
| 364 |
+
"step": 48
|
| 365 |
+
},
|
| 366 |
+
{
|
| 367 |
+
"epoch": 24.5,
|
| 368 |
+
"learning_rate": 6.701754385964913e-05,
|
| 369 |
+
"loss": 0.477,
|
| 370 |
+
"step": 49
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 25.0,
|
| 374 |
+
"learning_rate": 6.666666666666667e-05,
|
| 375 |
+
"loss": 0.4581,
|
| 376 |
+
"step": 50
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 25.0,
|
| 380 |
+
"eval_accuracy_dropoff": 0.19300442670703458,
|
| 381 |
+
"eval_accuracy_undropoff": 0.9900139008156406,
|
| 382 |
+
"eval_accuracy_unlabeled": NaN,
|
| 383 |
+
"eval_iou_dropoff": 0.15784833444007998,
|
| 384 |
+
"eval_iou_undropoff": 0.9565325903664265,
|
| 385 |
+
"eval_iou_unlabeled": 0.0,
|
| 386 |
+
"eval_loss": 0.44047123193740845,
|
| 387 |
+
"eval_mean_accuracy": 0.5915091637613376,
|
| 388 |
+
"eval_mean_iou": 0.37146030826883547,
|
| 389 |
+
"eval_overall_accuracy": 0.9568748474121094,
|
| 390 |
+
"eval_runtime": 2.862,
|
| 391 |
+
"eval_samples_per_second": 6.988,
|
| 392 |
+
"eval_steps_per_second": 0.699,
|
| 393 |
+
"step": 50
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 25.5,
|
| 397 |
+
"learning_rate": 6.631578947368421e-05,
|
| 398 |
+
"loss": 0.451,
|
| 399 |
+
"step": 51
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 26.0,
|
| 403 |
+
"learning_rate": 6.596491228070175e-05,
|
| 404 |
+
"loss": 0.4583,
|
| 405 |
+
"step": 52
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 26.5,
|
| 409 |
+
"learning_rate": 6.561403508771931e-05,
|
| 410 |
+
"loss": 0.4437,
|
| 411 |
+
"step": 53
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 27.0,
|
| 415 |
+
"learning_rate": 6.526315789473685e-05,
|
| 416 |
+
"loss": 0.4363,
|
| 417 |
+
"step": 54
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 27.5,
|
| 421 |
+
"learning_rate": 6.49122807017544e-05,
|
| 422 |
+
"loss": 0.4311,
|
| 423 |
+
"step": 55
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 28.0,
|
| 427 |
+
"learning_rate": 6.456140350877194e-05,
|
| 428 |
+
"loss": 0.4346,
|
| 429 |
+
"step": 56
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 28.5,
|
| 433 |
+
"learning_rate": 6.421052631578948e-05,
|
| 434 |
+
"loss": 0.419,
|
| 435 |
+
"step": 57
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 29.0,
|
| 439 |
+
"learning_rate": 6.385964912280702e-05,
|
| 440 |
+
"loss": 0.4368,
|
| 441 |
+
"step": 58
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 29.5,
|
| 445 |
+
"learning_rate": 6.350877192982457e-05,
|
| 446 |
+
"loss": 0.4127,
|
| 447 |
+
"step": 59
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 30.0,
|
| 451 |
+
"learning_rate": 6.315789473684212e-05,
|
| 452 |
+
"loss": 0.4213,
|
| 453 |
+
"step": 60
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 30.0,
|
| 457 |
+
"eval_accuracy_dropoff": 0.23790453909493336,
|
| 458 |
+
"eval_accuracy_undropoff": 0.9892081112304063,
|
| 459 |
+
"eval_accuracy_unlabeled": NaN,
|
| 460 |
+
"eval_iou_dropoff": 0.19095414478964925,
|
| 461 |
+
"eval_iou_undropoff": 0.9575495596432145,
|
| 462 |
+
"eval_iou_unlabeled": 0.0,
|
| 463 |
+
"eval_loss": 0.4145582318305969,
|
| 464 |
+
"eval_mean_accuracy": 0.6135563251626699,
|
| 465 |
+
"eval_mean_iou": 0.38283456814428796,
|
| 466 |
+
"eval_overall_accuracy": 0.9579694747924805,
|
| 467 |
+
"eval_runtime": 2.9309,
|
| 468 |
+
"eval_samples_per_second": 6.824,
|
| 469 |
+
"eval_steps_per_second": 0.682,
|
| 470 |
+
"step": 60
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 30.5,
|
| 474 |
+
"learning_rate": 6.280701754385966e-05,
|
| 475 |
+
"loss": 0.4109,
|
| 476 |
+
"step": 61
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 31.0,
|
| 480 |
+
"learning_rate": 6.24561403508772e-05,
|
| 481 |
+
"loss": 0.3886,
|
| 482 |
+
"step": 62
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 31.5,
|
| 486 |
+
"learning_rate": 6.210526315789474e-05,
|
| 487 |
+
"loss": 0.4031,
|
| 488 |
+
"step": 63
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 32.0,
|
| 492 |
+
"learning_rate": 6.175438596491228e-05,
|
| 493 |
+
"loss": 0.3899,
|
| 494 |
+
"step": 64
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 32.5,
|
| 498 |
+
"learning_rate": 6.140350877192984e-05,
|
| 499 |
+
"loss": 0.3879,
|
| 500 |
+
"step": 65
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 33.0,
|
| 504 |
+
"learning_rate": 6.105263157894738e-05,
|
| 505 |
+
"loss": 0.3708,
|
| 506 |
+
"step": 66
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 33.5,
|
| 510 |
+
"learning_rate": 6.070175438596492e-05,
|
| 511 |
+
"loss": 0.382,
|
| 512 |
+
"step": 67
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 34.0,
|
| 516 |
+
"learning_rate": 6.035087719298246e-05,
|
| 517 |
+
"loss": 0.3716,
|
| 518 |
+
"step": 68
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 34.5,
|
| 522 |
+
"learning_rate": 6.000000000000001e-05,
|
| 523 |
+
"loss": 0.3808,
|
| 524 |
+
"step": 69
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 35.0,
|
| 528 |
+
"learning_rate": 5.964912280701755e-05,
|
| 529 |
+
"loss": 0.3571,
|
| 530 |
+
"step": 70
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 35.0,
|
| 534 |
+
"eval_accuracy_dropoff": 0.2473726461616092,
|
| 535 |
+
"eval_accuracy_undropoff": 0.9886681983766793,
|
| 536 |
+
"eval_accuracy_unlabeled": NaN,
|
| 537 |
+
"eval_iou_dropoff": 0.19633228600450728,
|
| 538 |
+
"eval_iou_undropoff": 0.9574076008382422,
|
| 539 |
+
"eval_iou_unlabeled": 0.0,
|
| 540 |
+
"eval_loss": 0.375016450881958,
|
| 541 |
+
"eval_mean_accuracy": 0.6180204222691442,
|
| 542 |
+
"eval_mean_iou": 0.3845799622809165,
|
| 543 |
+
"eval_overall_accuracy": 0.9578456878662109,
|
| 544 |
+
"eval_runtime": 2.8583,
|
| 545 |
+
"eval_samples_per_second": 6.997,
|
| 546 |
+
"eval_steps_per_second": 0.7,
|
| 547 |
+
"step": 70
|
| 548 |
+
},
|
| 549 |
+
{
|
| 550 |
+
"epoch": 35.5,
|
| 551 |
+
"learning_rate": 5.929824561403509e-05,
|
| 552 |
+
"loss": 0.367,
|
| 553 |
+
"step": 71
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"epoch": 36.0,
|
| 557 |
+
"learning_rate": 5.8947368421052634e-05,
|
| 558 |
+
"loss": 0.3767,
|
| 559 |
+
"step": 72
|
| 560 |
+
},
|
| 561 |
+
{
|
| 562 |
+
"epoch": 36.5,
|
| 563 |
+
"learning_rate": 5.8596491228070176e-05,
|
| 564 |
+
"loss": 0.3713,
|
| 565 |
+
"step": 73
|
| 566 |
+
},
|
| 567 |
+
{
|
| 568 |
+
"epoch": 37.0,
|
| 569 |
+
"learning_rate": 5.8245614035087725e-05,
|
| 570 |
+
"loss": 0.3326,
|
| 571 |
+
"step": 74
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 37.5,
|
| 575 |
+
"learning_rate": 5.789473684210527e-05,
|
| 576 |
+
"loss": 0.348,
|
| 577 |
+
"step": 75
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 38.0,
|
| 581 |
+
"learning_rate": 5.7543859649122816e-05,
|
| 582 |
+
"loss": 0.3401,
|
| 583 |
+
"step": 76
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 38.5,
|
| 587 |
+
"learning_rate": 5.719298245614036e-05,
|
| 588 |
+
"loss": 0.3436,
|
| 589 |
+
"step": 77
|
| 590 |
+
},
|
| 591 |
+
{
|
| 592 |
+
"epoch": 39.0,
|
| 593 |
+
"learning_rate": 5.68421052631579e-05,
|
| 594 |
+
"loss": 0.3487,
|
| 595 |
+
"step": 78
|
| 596 |
+
},
|
| 597 |
+
{
|
| 598 |
+
"epoch": 39.5,
|
| 599 |
+
"learning_rate": 5.649122807017544e-05,
|
| 600 |
+
"loss": 0.3398,
|
| 601 |
+
"step": 79
|
| 602 |
+
},
|
| 603 |
+
{
|
| 604 |
+
"epoch": 40.0,
|
| 605 |
+
"learning_rate": 5.6140350877192984e-05,
|
| 606 |
+
"loss": 0.3205,
|
| 607 |
+
"step": 80
|
| 608 |
+
},
|
| 609 |
+
{
|
| 610 |
+
"epoch": 40.0,
|
| 611 |
+
"eval_accuracy_dropoff": 0.2522076194408129,
|
| 612 |
+
"eval_accuracy_undropoff": 0.9881893814485306,
|
| 613 |
+
"eval_accuracy_unlabeled": NaN,
|
| 614 |
+
"eval_iou_dropoff": 0.19823899733902547,
|
| 615 |
+
"eval_iou_undropoff": 0.9571383411399603,
|
| 616 |
+
"eval_iou_unlabeled": NaN,
|
| 617 |
+
"eval_loss": 0.3478124737739563,
|
| 618 |
+
"eval_mean_accuracy": 0.6201985004446717,
|
| 619 |
+
"eval_mean_iou": 0.5776886692394929,
|
| 620 |
+
"eval_overall_accuracy": 0.9575878143310547,
|
| 621 |
+
"eval_runtime": 2.8448,
|
| 622 |
+
"eval_samples_per_second": 7.03,
|
| 623 |
+
"eval_steps_per_second": 0.703,
|
| 624 |
+
"step": 80
|
| 625 |
+
}
|
| 626 |
+
],
|
| 627 |
+
"max_steps": 240,
|
| 628 |
+
"num_train_epochs": 120,
|
| 629 |
+
"total_flos": 4.071916553895936e+16,
|
| 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 sha256:8aac04d8cdad507b67b0cf9d85a115bd8b48759ff485068ff5a4f634035f8954
|
| 3 |
+
size 4219
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14951629
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3fe2c8f7bb76b694833eb7072e649a39e879cc8ef2eb77e9eb09aeecaadedef5
|
| 3 |
size 14951629
|
runs/Feb12_06-53-01_robovision.csres.utexas.edu/events.out.tfevents.1707742388.robovision.csres.utexas.edu.2756623.0
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:cd287dcb69b2f01c20b06cfeacde0ca68a586e14458163e4b98c365fa907fa12
|
| 3 |
+
size 23332
|