Training in progress, step 500, checkpoint

checkpoint-500/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-500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff0eea6c1cc07664a4c9538ac0de5d17fe6cb1b17ff4fd8cdf2d5c3c459fdf70
+size 338562516

checkpoint-500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ccbec953ee7a40265ab7cdfa1324efecd42c37f874b555169f6fd5069b1540d9
+size 677518143

checkpoint-500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fcc2489f03f511ba5ce8943062cb38a3ed84fb8138474684a28cf59722314e9
+size 14575

checkpoint-500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9394b40358dc5185252cbb353c64c2116a46f256952593c353fc4f5a1fd4f7a5
+size 563

checkpoint-500/trainer_state.json

@@ -0,0 +1,57 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.08333333333333333,
+  "eval_steps": 500,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.08333333333333333,
+      "grad_norm": 10.64107608795166,
+      "learning_rate": 2.4999999999999998e-06,
+      "loss": 4.1627,
+      "step": 500
+    },
+    {
+      "epoch": 0.08333333333333333,
+      "eval_accuracy_background": 0.014990974836900402,
+      "eval_accuracy_double_plant": 0.09625850817128659,
+      "eval_accuracy_drydown": 0.11748866381009407,
+      "eval_accuracy_endrow": 0.019624906998737878,
+      "eval_accuracy_nutrient_deficiency": 0.39043216558572647,
+      "eval_accuracy_planter_skip": 0.03244089779472675,
+      "eval_accuracy_water": 0.4902746667077927,
+      "eval_accuracy_waterway": 0.37818186421979577,
+      "eval_accuracy_weed_cluster": 0.5157577782392276,
+      "eval_iou_background": 0.01485215844086368,
+      "eval_iou_double_plant": 0.025830652956995166,
+      "eval_iou_drydown": 0.09098524126821965,
+      "eval_iou_endrow": 0.011190399377301194,
+      "eval_iou_nutrient_deficiency": 0.16172838363740288,
+      "eval_iou_planter_skip": 0.007145844854739052,
+      "eval_iou_water": 0.052629358314533047,
+      "eval_iou_waterway": 0.008009602169192399,
+      "eval_iou_weed_cluster": 0.055193229922437775,
+      "eval_loss": 3.9555599689483643,
+      "eval_mean_accuracy": 0.22838338070714315,
+      "eval_mean_iou": 0.047507207882409426,
+      "eval_overall_accuracy": 0.09656532361323403,
+      "eval_runtime": 348.036,
+      "eval_samples_per_second": 8.166,
+      "eval_steps_per_second": 2.724,
+      "step": 500
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 120000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 20,
+  "save_steps": 500,
+  "total_flos": 7.98417862262784e+17,
+  "train_batch_size": 3,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a680a40140b6ca5fa47ac87d8120967d6766117ead261eaa84c073e1e9509b8
+size 4539