Evaluation on the test set completed on 2024_09_13.

README.md

@@ -0,0 +1,75 @@
+---
+license: apache-2.0
+base_model: microsoft/resnet-50
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: resnet-50-2024_09_13-batch-size32_epochs150_freeze
+  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. -->
+
+# resnet-50-2024_09_13-batch-size32_epochs150_freeze
+
+This model is a fine-tuned version of [microsoft/resnet-50](https://huggingface.co/microsoft/resnet-50) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: nan
+- F1 Micro: 0.0002
+- F1 Macro: 0.0002
+- Roc Auc: 0.4995
+- Accuracy: 0.0003
+- Learning Rate: 0.0001
+
+## 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: 0.001
+- train_batch_size: 32
+- eval_batch_size: 32
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 150
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | F1 Micro | F1 Macro | Roc Auc | Accuracy | Rate   |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|:-------:|:--------:|:------:|
+| No log        | 1.0   | 273  | nan             | 0.0      | 0.0      | 0.4995  | 0.0      | 0.001  |
+| 0.0           | 2.0   | 546  | nan             | 0.0003   | 0.0004   | 0.4993  | 0.0007   | 0.001  |
+| 0.0           | 3.0   | 819  | nan             | 0.0008   | 0.0010   | 0.4994  | 0.0017   | 0.001  |
+| 0.0           | 4.0   | 1092 | nan             | 0.0      | 0.0      | 0.4991  | 0.0      | 0.001  |
+| 0.0           | 5.0   | 1365 | nan             | 0.0005   | 0.0006   | 0.4994  | 0.0010   | 0.001  |
+| 0.0           | 6.0   | 1638 | nan             | 0.0002   | 0.0002   | 0.4993  | 0.0003   | 0.001  |
+| 0.0           | 7.0   | 1911 | nan             | 0.0      | 0.0      | 0.4993  | 0.0      | 0.0001 |
+| 0.0           | 8.0   | 2184 | nan             | 0.0002   | 0.0002   | 0.4993  | 0.0003   | 0.0001 |
+| 0.0           | 9.0   | 2457 | nan             | 0.0      | 0.0      | 0.4994  | 0.0      | 0.0001 |
+| 0.0           | 10.0  | 2730 | nan             | 0.0003   | 0.0004   | 0.4994  | 0.0007   | 0.0001 |
+| 0.0           | 11.0  | 3003 | nan             | 0.0      | 0.0      | 0.4994  | 0.0      | 0.0001 |
+
+
+### Framework versions
+
+- Transformers 4.41.1
+- Pytorch 2.3.0+cu121
+- Datasets 2.19.1
+- Tokenizers 0.19.1

all_results.json

@@ -0,0 +1,17 @@
+{
+    "epoch": 11.0,
+    "eval_accuracy": 0.00034602076124567473,
+    "eval_f1_macro": 0.0002346041055718475,
+    "eval_f1_micro": 0.00015795293002685197,
+    "eval_loss": NaN,
+    "eval_roc_auc": 0.49951383990145193,
+    "eval_runtime": 420.9492,
+    "eval_samples_per_second": 6.865,
+    "eval_steps_per_second": 0.216,
+    "learning_rate": 0.0001,
+    "total_flos": 1.09151596234231e+19,
+    "train_loss": 0.0,
+    "train_runtime": 18978.5009,
+    "train_samples_per_second": 68.888,
+    "train_steps_per_second": 2.158
+}

logs/events.out.tfevents.1726211111.datavisu2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a472b78238fc927f2d5d81899c3cb6db75396f543284060e274090e6bec08d4
-size 12580
+oid sha256:de833b5c3fa8ee2e547eaa3da26af08dd80d3672f6589245868fde77d737ca98
+size 14275

logs/events.out.tfevents.1726230522.datavisu2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:428cf977790a688a573d85efeae42c0dd9de9e76db0de8772420cd075a543ebe
+size 40

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d4c9245b0000abe7d5e316dd8c2f5e1c33bc7f4f29eb0c3cf8b863ed7961ab3
+oid sha256:0a56cc264c89bf5c7bf218605581418f30601d5599835dd576b71e7c1bb9eb67
 size 94540692

test_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 11.0,
+    "eval_accuracy": 0.00034602076124567473,
+    "eval_f1_macro": 0.0002346041055718475,
+    "eval_f1_micro": 0.00015795293002685197,
+    "eval_loss": NaN,
+    "eval_roc_auc": 0.49951383990145193,
+    "eval_runtime": 420.9492,
+    "eval_samples_per_second": 6.865,
+    "eval_steps_per_second": 0.216,
+    "learning_rate": 0.0001
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 11.0,
+    "learning_rate": 0.0001,
+    "total_flos": 1.09151596234231e+19,
+    "train_loss": 0.0,
+    "train_runtime": 18978.5009,
+    "train_samples_per_second": 68.888,
+    "train_steps_per_second": 2.158
+}

trainer_state.json

@@ -0,0 +1,237 @@
+{
+  "best_metric": NaN,
+  "best_model_checkpoint": "/home/datawork-iot-nos/Seatizen/models/multilabel/fine_scale/resnet-50-2024_09_13-batch-size32_epochs150_freeze/checkpoint-273",
+  "epoch": 11.0,
+  "eval_steps": 500,
+  "global_step": 3003,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.0,
+      "eval_f1_macro": 0.0,
+      "eval_f1_micro": 0.0,
+      "eval_loss": NaN,
+      "eval_roc_auc": 0.499453523472468,
+      "eval_runtime": 431.8634,
+      "eval_samples_per_second": 6.683,
+      "eval_steps_per_second": 0.211,
+      "learning_rate": 0.001,
+      "step": 273
+    },
+    {
+      "epoch": 1.8315018315018317,
+      "grad_norm": NaN,
+      "learning_rate": 0.001,
+      "loss": 0.0,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.000693000693000693,
+      "eval_f1_macro": 0.00040576181781294376,
+      "eval_f1_micro": 0.00031409501374165687,
+      "eval_loss": NaN,
+      "eval_roc_auc": 0.4992791043687002,
+      "eval_runtime": 437.2143,
+      "eval_samples_per_second": 6.601,
+      "eval_steps_per_second": 0.208,
+      "learning_rate": 0.001,
+      "step": 546
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.0017325017325017325,
+      "eval_f1_macro": 0.0010049241282283187,
+      "eval_f1_micro": 0.0007850525985241011,
+      "eval_loss": NaN,
+      "eval_roc_auc": 0.4993980575804369,
+      "eval_runtime": 449.0005,
+      "eval_samples_per_second": 6.428,
+      "eval_steps_per_second": 0.203,
+      "learning_rate": 0.001,
+      "step": 819
+    },
+    {
+      "epoch": 3.663003663003663,
+      "grad_norm": NaN,
+      "learning_rate": 0.001,
+      "loss": 0.0,
+      "step": 1000
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.0,
+      "eval_f1_macro": 0.0,
+      "eval_f1_micro": 0.0,
+      "eval_loss": NaN,
+      "eval_roc_auc": 0.49914125117102115,
+      "eval_runtime": 438.2382,
+      "eval_samples_per_second": 6.585,
+      "eval_steps_per_second": 0.208,
+      "learning_rate": 0.001,
+      "step": 1092
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.0010395010395010396,
+      "eval_f1_macro": 0.0006430178973314757,
+      "eval_f1_micro": 0.00047177229124076113,
+      "eval_loss": NaN,
+      "eval_roc_auc": 0.4994358575523217,
+      "eval_runtime": 457.0913,
+      "eval_samples_per_second": 6.314,
+      "eval_steps_per_second": 0.199,
+      "learning_rate": 0.001,
+      "step": 1365
+    },
+    {
+      "epoch": 5.4945054945054945,
+      "grad_norm": NaN,
+      "learning_rate": 0.001,
+      "loss": 0.0,
+      "step": 1500
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.0003465003465003465,
+      "eval_f1_macro": 0.000206782464846981,
+      "eval_f1_micro": 0.00015712153350616704,
+      "eval_loss": NaN,
+      "eval_roc_auc": 0.49927198166285536,
+      "eval_runtime": 425.3309,
+      "eval_samples_per_second": 6.785,
+      "eval_steps_per_second": 0.214,
+      "learning_rate": 0.001,
+      "step": 1638
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.0,
+      "eval_f1_macro": 0.0,
+      "eval_f1_micro": 0.0,
+      "eval_loss": NaN,
+      "eval_roc_auc": 0.49929738732174456,
+      "eval_runtime": 423.0556,
+      "eval_samples_per_second": 6.822,
+      "eval_steps_per_second": 0.215,
+      "learning_rate": 0.0001,
+      "step": 1911
+    },
+    {
+      "epoch": 7.326007326007326,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001,
+      "loss": 0.0,
+      "step": 2000
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.0003465003465003465,
+      "eval_f1_macro": 0.0002061218179944347,
+      "eval_f1_micro": 0.00015710919088766695,
+      "eval_loss": NaN,
+      "eval_roc_auc": 0.49926547598990856,
+      "eval_runtime": 417.1408,
+      "eval_samples_per_second": 6.919,
+      "eval_steps_per_second": 0.218,
+      "learning_rate": 0.0001,
+      "step": 2184
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.0,
+      "eval_f1_macro": 0.0,
+      "eval_f1_micro": 0.0,
+      "eval_loss": NaN,
+      "eval_roc_auc": 0.49944051212657437,
+      "eval_runtime": 408.1598,
+      "eval_samples_per_second": 7.071,
+      "eval_steps_per_second": 0.223,
+      "learning_rate": 0.0001,
+      "step": 2457
+    },
+    {
+      "epoch": 9.157509157509157,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001,
+      "loss": 0.0,
+      "step": 2500
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.000693000693000693,
+      "eval_f1_macro": 0.0004230565838180856,
+      "eval_f1_micro": 0.00031441597233139445,
+      "eval_loss": NaN,
+      "eval_roc_auc": 0.49936367811700877,
+      "eval_runtime": 430.9669,
+      "eval_samples_per_second": 6.697,
+      "eval_steps_per_second": 0.211,
+      "learning_rate": 0.0001,
+      "step": 2730
+    },
+    {
+      "epoch": 10.989010989010989,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001,
+      "loss": 0.0,
+      "step": 3000
+    },
+    {
+      "epoch": 11.0,
+      "eval_accuracy": 0.0,
+      "eval_f1_macro": 0.0,
+      "eval_f1_micro": 0.0,
+      "eval_loss": NaN,
+      "eval_roc_auc": 0.49943400645362757,
+      "eval_runtime": 416.2683,
+      "eval_samples_per_second": 6.933,
+      "eval_steps_per_second": 0.219,
+      "learning_rate": 0.0001,
+      "step": 3003
+    },
+    {
+      "epoch": 11.0,
+      "learning_rate": 0.0001,
+      "step": 3003,
+      "total_flos": 1.09151596234231e+19,
+      "train_loss": 0.0,
+      "train_runtime": 18978.5009,
+      "train_samples_per_second": 68.888,
+      "train_steps_per_second": 2.158
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 40950,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 150,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 10,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.09151596234231e+19,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}