Training in progress, step 200

README.md

@@ -0,0 +1,56 @@
+---
+license: other
+base_model: nvidia/mit-b0
+tags:
+- generated_from_trainer
+datasets:
+- scene_parse_150
+model-index:
+- name: Segments
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# Segments
+
+This model is a fine-tuned version of [nvidia/mit-b0](https://huggingface.co/nvidia/mit-b0) on the scene_parse_150 dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-05
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 16
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 20
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.33.0.dev0
+- Pytorch 2.0.1+cu117
+- Datasets 2.13.1
+- Tokenizers 0.13.3

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 20.0,
+    "total_flos": 1.9265685892890624e+17,
+    "train_loss": 2.621326805563534,
+    "train_runtime": 1247.0654,
+    "train_samples_per_second": 8.724,
+    "train_steps_per_second": 0.545
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37953f73bc52e471809b67b5a08dd65eb31d7d13a735a8e4edb4ab82f3e5b37d
+size 15036944

preprocessor_config.json

@@ -0,0 +1,23 @@
+{
+  "do_normalize": true,
+  "do_reduce_labels": false,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.485,
+    0.456,
+    0.406
+  ],
+  "image_processor_type": "SegformerImageProcessor",
+  "image_std": [
+    0.229,
+    0.224,
+    0.225
+  ],
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 512,
+    "width": 512
+  }
+}

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50245e368efb68c00597a3eb0110fd042a32dad741679194eb9cb27418c61750
+oid sha256:97f30e99b61c07013a85ef85bba1aaa488d12fb09f5aedc491fa1689221facb1
 size 15083917

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 20.0,
+    "total_flos": 1.9265685892890624e+17,
+    "train_loss": 2.621326805563534,
+    "train_runtime": 1247.0654,
+    "train_samples_per_second": 8.724,
+    "train_steps_per_second": 0.545
+}

trainer_state.json

@@ -0,0 +1,34 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 20.0,
+  "eval_steps": 500,
+  "global_step": 680,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 14.71,
+      "learning_rate": 1.323529411764706e-05,
+      "loss": 2.8344,
+      "step": 500
+    },
+    {
+      "epoch": 20.0,
+      "step": 680,
+      "total_flos": 1.9265685892890624e+17,
+      "train_loss": 2.621326805563534,
+      "train_runtime": 1247.0654,
+      "train_samples_per_second": 8.724,
+      "train_steps_per_second": 0.545
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 680,
+  "num_train_epochs": 20,
+  "save_steps": 200,
+  "total_flos": 1.9265685892890624e+17,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8cd16635afcbf26f711660aec95feebae4a02c1fc9b8ec435df39acab16f18b8
+oid sha256:1af9604a3906c57ddb8b7a2d27a78b0fb6d1d0c4666b15019a208ab218753f2e
 size 4155