Training in progress, step 2250, checkpoint

checkpoint-2250/config.json

@@ -0,0 +1,92 @@
+{
+  "_name_or_path": "nvidia/mit-b5",
+  "architectures": [
+    "SegformerForSemanticSegmentation"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "classifier_dropout_prob": 0.1,
+  "decoder_hidden_size": 768,
+  "depths": [
+    3,
+    6,
+    40,
+    3
+  ],
+  "downsampling_rates": [
+    1,
+    4,
+    8,
+    16
+  ],
+  "drop_path_rate": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_sizes": [
+    64,
+    128,
+    320,
+    512
+  ],
+  "id2label": {
+    "0": "background",
+    "1": "double_plant",
+    "2": "drydown",
+    "3": "endrow",
+    "4": "nutrient_deficiency",
+    "5": "planter_skip",
+    "6": "water",
+    "7": "waterway",
+    "8": "weed_cluster"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "label2id": {
+    "background": 0,
+    "double_plant": 1,
+    "drydown": 2,
+    "endrow": 3,
+    "nutrient_deficiency": 4,
+    "planter_skip": 5,
+    "water": 6,
+    "waterway": 7,
+    "weed_cluster": 8
+  },
+  "layer_norm_eps": 1e-06,
+  "mlp_ratios": [
+    4,
+    4,
+    4,
+    4
+  ],
+  "model_type": "segformer",
+  "num_attention_heads": [
+    1,
+    2,
+    5,
+    8
+  ],
+  "num_channels": 4,
+  "num_encoder_blocks": 4,
+  "patch_sizes": [
+    7,
+    3,
+    3,
+    3
+  ],
+  "reshape_last_stage": true,
+  "semantic_loss_ignore_index": 255,
+  "sr_ratios": [
+    8,
+    4,
+    2,
+    1
+  ],
+  "strides": [
+    4,
+    2,
+    2,
+    2
+  ],
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.2"
+}

checkpoint-2250/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13be523c751d92145168df3e98fff6700cedca57009100710b6d3fa8d3dc1e91
+size 338562516

checkpoint-2250/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a09a1b67607944945b72918db66bcb2cee6400655740e6f14324cda427c1be4
+size 677518143

checkpoint-2250/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84cc0bfa7e360e5546ece33084df378f335618c341ffc1c0a9f95c02214e3d9f
+size 14575

checkpoint-2250/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf1f7c7a656f5b4f50161665e99cd34b3d679de6b3c33b5ebfc9d9028d33dc83
+size 563

checkpoint-2250/trainer_state.json

@@ -0,0 +1,64 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.3266509433962264,
+  "eval_steps": 2250,
+  "global_step": 2250,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.589622641509434,
+      "grad_norm": 9.137022018432617,
+      "learning_rate": 2.9481132075471702e-05,
+      "loss": 2.8435,
+      "step": 1000
+    },
+    {
+      "epoch": 1.179245283018868,
+      "grad_norm": 6.052332401275635,
+      "learning_rate": 5.8962264150943403e-05,
+      "loss": 1.791,
+      "step": 2000
+    },
+    {
+      "epoch": 1.3266509433962264,
+      "eval_accuracy_background": 0.6658729859800179,
+      "eval_accuracy_double_plant": 0.44796971861142204,
+      "eval_accuracy_drydown": 0.838452272819733,
+      "eval_accuracy_endrow": 0.6564099936974693,
+      "eval_accuracy_nutrient_deficiency": 0.5255760511997533,
+      "eval_accuracy_planter_skip": 0.7062276764551357,
+      "eval_accuracy_water": 0.9873387227342924,
+      "eval_accuracy_waterway": 0.5770296385642565,
+      "eval_accuracy_weed_cluster": 0.4428120632960455,
+      "eval_iou_background": 0.5904190410028399,
+      "eval_iou_double_plant": 0.21713659970128166,
+      "eval_iou_drydown": 0.5191145408680865,
+      "eval_iou_endrow": 0.146705809299966,
+      "eval_iou_nutrient_deficiency": 0.3433700256479391,
+      "eval_iou_planter_skip": 0.19867844175237825,
+      "eval_iou_water": 0.3151796347651091,
+      "eval_iou_waterway": 0.17710299517028666,
+      "eval_iou_weed_cluster": 0.2871479144864637,
+      "eval_loss": 1.6307891607284546,
+      "eval_mean_accuracy": 0.6497432359286807,
+      "eval_mean_iou": 0.31053944474381673,
+      "eval_overall_accuracy": 0.6703095203666921,
+      "eval_runtime": 550.4413,
+      "eval_samples_per_second": 15.489,
+      "eval_steps_per_second": 0.485,
+      "step": 2250
+    }
+  ],
+  "logging_steps": 1000,
+  "max_steps": 33920,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 20,
+  "save_steps": 2250,
+  "total_flos": 3.831820232429037e+19,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-2250/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f718e0633b4eda2deeb786176aa261e6cae5f387b8ef2e8fb286f958ed2885d
+size 4539