End of training

README.md

@@ -0,0 +1,82 @@
+---
+license: apache-2.0
+base_model: microsoft/conditional-detr-resnet-50
+tags:
+- generated_from_trainer
+model-index:
+- name: cdetr-mist1-brain-gt-tumors-8ah-6l
+  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. -->
+
+# cdetr-mist1-brain-gt-tumors-8ah-6l
+
+This model is a fine-tuned version of [microsoft/conditional-detr-resnet-50](https://huggingface.co/microsoft/conditional-detr-resnet-50) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.8917
+
+## 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: 1e-05
+- train_batch_size: 4
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 25
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 5.4149        | 1.0   | 115  | 4.3974          |
+| 3.9453        | 2.0   | 230  | 3.6520          |
+| 3.7269        | 3.0   | 345  | 3.7602          |
+| 3.5898        | 4.0   | 460  | 3.5671          |
+| 3.486         | 5.0   | 575  | 3.4912          |
+| 3.4073        | 6.0   | 690  | 3.4095          |
+| 3.4181        | 7.0   | 805  | 3.3183          |
+| 3.3603        | 8.0   | 920  | 3.1111          |
+| 3.2777        | 9.0   | 1035 | 3.1992          |
+| 3.2851        | 10.0  | 1150 | 3.3997          |
+| 3.266         | 11.0  | 1265 | 3.2861          |
+| 3.2803        | 12.0  | 1380 | 3.1813          |
+| 3.1733        | 13.0  | 1495 | 2.9838          |
+| 3.2094        | 14.0  | 1610 | 3.1175          |
+| 3.1718        | 15.0  | 1725 | 3.0064          |
+| 3.1303        | 16.0  | 1840 | 3.0869          |
+| 3.0897        | 17.0  | 1955 | 3.0306          |
+| 3.0233        | 18.0  | 2070 | 2.9479          |
+| 3.0156        | 19.0  | 2185 | 2.9145          |
+| 3.0277        | 20.0  | 2300 | 2.8919          |
+| 3.0847        | 21.0  | 2415 | 2.9321          |
+| 3.0333        | 22.0  | 2530 | 2.9128          |
+| 3.0126        | 23.0  | 2645 | 2.8627          |
+| 2.9701        | 24.0  | 2760 | 2.8686          |
+| 2.9964        | 25.0  | 2875 | 2.8917          |
+
+
+### Framework versions
+
+- Transformers 4.35.0
+- Pytorch 2.0.0
+- Datasets 2.1.0
+- Tokenizers 0.14.1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b0b6b763403d31e63d89d89cf243fb9a6875c2ce3f615e59eee8b92fe6494fcd
+oid sha256:9306ab9645deed1993e3c9a0d0284d7db695983873c6315f16eb6eade0183c4d
 size 173870884

trainer_state.json

@@ -0,0 +1,378 @@
+{
+  "best_metric": 2.8627383708953857,
+  "best_model_checkpoint": "cdetr-mist1-brain-gt-tumors-8ah-6l/checkpoint-2645",
+  "epoch": 25.0,
+  "eval_steps": 500,
+  "global_step": 2875,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 9.624347826086956e-06,
+      "loss": 5.4149,
+      "step": 115
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 4.397365093231201,
+      "eval_runtime": 5.8932,
+      "eval_samples_per_second": 6.787,
+      "eval_steps_per_second": 0.848,
+      "step": 115
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 9.231304347826087e-06,
+      "loss": 3.9453,
+      "step": 230
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 3.651952028274536,
+      "eval_runtime": 5.9289,
+      "eval_samples_per_second": 6.747,
+      "eval_steps_per_second": 0.843,
+      "step": 230
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 8.831304347826088e-06,
+      "loss": 3.7269,
+      "step": 345
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 3.7602438926696777,
+      "eval_runtime": 5.8799,
+      "eval_samples_per_second": 6.803,
+      "eval_steps_per_second": 0.85,
+      "step": 345
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 8.434782608695653e-06,
+      "loss": 3.5898,
+      "step": 460
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 3.5670828819274902,
+      "eval_runtime": 5.9645,
+      "eval_samples_per_second": 6.706,
+      "eval_steps_per_second": 0.838,
+      "step": 460
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 8.034782608695652e-06,
+      "loss": 3.486,
+      "step": 575
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 3.4911675453186035,
+      "eval_runtime": 5.9241,
+      "eval_samples_per_second": 6.752,
+      "eval_steps_per_second": 0.844,
+      "step": 575
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 7.634782608695653e-06,
+      "loss": 3.4073,
+      "step": 690
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 3.409463405609131,
+      "eval_runtime": 5.8302,
+      "eval_samples_per_second": 6.861,
+      "eval_steps_per_second": 0.858,
+      "step": 690
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 7.234782608695653e-06,
+      "loss": 3.4181,
+      "step": 805
+    },
+    {
+      "epoch": 7.0,
+      "eval_loss": 3.3183083534240723,
+      "eval_runtime": 5.8894,
+      "eval_samples_per_second": 6.792,
+      "eval_steps_per_second": 0.849,
+      "step": 805
+    },
+    {
+      "epoch": 8.0,
+      "learning_rate": 6.834782608695653e-06,
+      "loss": 3.3603,
+      "step": 920
+    },
+    {
+      "epoch": 8.0,
+      "eval_loss": 3.1111273765563965,
+      "eval_runtime": 5.9175,
+      "eval_samples_per_second": 6.76,
+      "eval_steps_per_second": 0.845,
+      "step": 920
+    },
+    {
+      "epoch": 9.0,
+      "learning_rate": 6.434782608695652e-06,
+      "loss": 3.2777,
+      "step": 1035
+    },
+    {
+      "epoch": 9.0,
+      "eval_loss": 3.1992499828338623,
+      "eval_runtime": 5.9275,
+      "eval_samples_per_second": 6.748,
+      "eval_steps_per_second": 0.844,
+      "step": 1035
+    },
+    {
+      "epoch": 10.0,
+      "learning_rate": 6.034782608695653e-06,
+      "loss": 3.2851,
+      "step": 1150
+    },
+    {
+      "epoch": 10.0,
+      "eval_loss": 3.3997130393981934,
+      "eval_runtime": 5.8939,
+      "eval_samples_per_second": 6.787,
+      "eval_steps_per_second": 0.848,
+      "step": 1150
+    },
+    {
+      "epoch": 11.0,
+      "learning_rate": 5.634782608695652e-06,
+      "loss": 3.266,
+      "step": 1265
+    },
+    {
+      "epoch": 11.0,
+      "eval_loss": 3.286081314086914,
+      "eval_runtime": 6.1287,
+      "eval_samples_per_second": 6.527,
+      "eval_steps_per_second": 0.816,
+      "step": 1265
+    },
+    {
+      "epoch": 12.0,
+      "learning_rate": 5.234782608695652e-06,
+      "loss": 3.2803,
+      "step": 1380
+    },
+    {
+      "epoch": 12.0,
+      "eval_loss": 3.18131947517395,
+      "eval_runtime": 6.1123,
+      "eval_samples_per_second": 6.544,
+      "eval_steps_per_second": 0.818,
+      "step": 1380
+    },
+    {
+      "epoch": 13.0,
+      "learning_rate": 4.834782608695652e-06,
+      "loss": 3.1733,
+      "step": 1495
+    },
+    {
+      "epoch": 13.0,
+      "eval_loss": 2.9837594032287598,
+      "eval_runtime": 5.925,
+      "eval_samples_per_second": 6.751,
+      "eval_steps_per_second": 0.844,
+      "step": 1495
+    },
+    {
+      "epoch": 14.0,
+      "learning_rate": 4.434782608695653e-06,
+      "loss": 3.2094,
+      "step": 1610
+    },
+    {
+      "epoch": 14.0,
+      "eval_loss": 3.1175174713134766,
+      "eval_runtime": 5.9137,
+      "eval_samples_per_second": 6.764,
+      "eval_steps_per_second": 0.845,
+      "step": 1610
+    },
+    {
+      "epoch": 15.0,
+      "learning_rate": 4.034782608695652e-06,
+      "loss": 3.1718,
+      "step": 1725
+    },
+    {
+      "epoch": 15.0,
+      "eval_loss": 3.0063586235046387,
+      "eval_runtime": 5.9077,
+      "eval_samples_per_second": 6.771,
+      "eval_steps_per_second": 0.846,
+      "step": 1725
+    },
+    {
+      "epoch": 16.0,
+      "learning_rate": 3.6347826086956524e-06,
+      "loss": 3.1303,
+      "step": 1840
+    },
+    {
+      "epoch": 16.0,
+      "eval_loss": 3.086920738220215,
+      "eval_runtime": 5.9305,
+      "eval_samples_per_second": 6.745,
+      "eval_steps_per_second": 0.843,
+      "step": 1840
+    },
+    {
+      "epoch": 17.0,
+      "learning_rate": 3.2347826086956524e-06,
+      "loss": 3.0897,
+      "step": 1955
+    },
+    {
+      "epoch": 17.0,
+      "eval_loss": 3.0305533409118652,
+      "eval_runtime": 6.0975,
+      "eval_samples_per_second": 6.56,
+      "eval_steps_per_second": 0.82,
+      "step": 1955
+    },
+    {
+      "epoch": 18.0,
+      "learning_rate": 2.8347826086956525e-06,
+      "loss": 3.0233,
+      "step": 2070
+    },
+    {
+      "epoch": 18.0,
+      "eval_loss": 2.9478588104248047,
+      "eval_runtime": 5.9801,
+      "eval_samples_per_second": 6.689,
+      "eval_steps_per_second": 0.836,
+      "step": 2070
+    },
+    {
+      "epoch": 19.0,
+      "learning_rate": 2.4347826086956525e-06,
+      "loss": 3.0156,
+      "step": 2185
+    },
+    {
+      "epoch": 19.0,
+      "eval_loss": 2.914536952972412,
+      "eval_runtime": 6.0155,
+      "eval_samples_per_second": 6.649,
+      "eval_steps_per_second": 0.831,
+      "step": 2185
+    },
+    {
+      "epoch": 20.0,
+      "learning_rate": 2.0347826086956525e-06,
+      "loss": 3.0277,
+      "step": 2300
+    },
+    {
+      "epoch": 20.0,
+      "eval_loss": 2.891925811767578,
+      "eval_runtime": 6.058,
+      "eval_samples_per_second": 6.603,
+      "eval_steps_per_second": 0.825,
+      "step": 2300
+    },
+    {
+      "epoch": 21.0,
+      "learning_rate": 1.6382608695652176e-06,
+      "loss": 3.0847,
+      "step": 2415
+    },
+    {
+      "epoch": 21.0,
+      "eval_loss": 2.9321396350860596,
+      "eval_runtime": 6.1412,
+      "eval_samples_per_second": 6.513,
+      "eval_steps_per_second": 0.814,
+      "step": 2415
+    },
+    {
+      "epoch": 22.0,
+      "learning_rate": 1.2382608695652176e-06,
+      "loss": 3.0333,
+      "step": 2530
+    },
+    {
+      "epoch": 22.0,
+      "eval_loss": 2.91283917427063,
+      "eval_runtime": 6.139,
+      "eval_samples_per_second": 6.516,
+      "eval_steps_per_second": 0.814,
+      "step": 2530
+    },
+    {
+      "epoch": 23.0,
+      "learning_rate": 8.382608695652175e-07,
+      "loss": 3.0126,
+      "step": 2645
+    },
+    {
+      "epoch": 23.0,
+      "eval_loss": 2.8627383708953857,
+      "eval_runtime": 6.0565,
+      "eval_samples_per_second": 6.604,
+      "eval_steps_per_second": 0.826,
+      "step": 2645
+    },
+    {
+      "epoch": 24.0,
+      "learning_rate": 4.382608695652174e-07,
+      "loss": 2.9701,
+      "step": 2760
+    },
+    {
+      "epoch": 24.0,
+      "eval_loss": 2.868567705154419,
+      "eval_runtime": 6.0333,
+      "eval_samples_per_second": 6.63,
+      "eval_steps_per_second": 0.829,
+      "step": 2760
+    },
+    {
+      "epoch": 25.0,
+      "learning_rate": 3.82608695652174e-08,
+      "loss": 2.9964,
+      "step": 2875
+    },
+    {
+      "epoch": 25.0,
+      "eval_loss": 2.8917393684387207,
+      "eval_runtime": 6.0377,
+      "eval_samples_per_second": 6.625,
+      "eval_steps_per_second": 0.828,
+      "step": 2875
+    },
+    {
+      "epoch": 25.0,
+      "step": 2875,
+      "total_flos": 5.73883103808e+18,
+      "train_loss": 3.3358317977241847,
+      "train_runtime": 2483.4302,
+      "train_samples_per_second": 4.631,
+      "train_steps_per_second": 1.158
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2875,
+  "num_train_epochs": 25,
+  "save_steps": 500,
+  "total_flos": 5.73883103808e+18,
+  "trial_name": null,
+  "trial_params": null
+}