End of training

README.md

@@ -32,7 +32,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [microsoft/resnet-101](https://huggingface.co/microsoft/resnet-101) on the imagefolder dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0002
+- Loss: 0.0587
 - Accuracy: 1.0
 
 ## Model description

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 10.0,
+    "eval_accuracy": 1.0,
+    "eval_loss": 0.05872531235218048,
+    "eval_runtime": 28.1056,
+    "eval_samples_per_second": 10.496,
+    "eval_steps_per_second": 0.356,
+    "total_flos": 4.530059681107968e+17,
+    "train_loss": 0.2042137217959641,
+    "train_runtime": 3284.1143,
+    "train_samples_per_second": 3.593,
+    "train_steps_per_second": 0.113
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 10.0,
+    "eval_accuracy": 1.0,
+    "eval_loss": 0.05872531235218048,
+    "eval_runtime": 28.1056,
+    "eval_samples_per_second": 10.496,
+    "eval_steps_per_second": 0.356
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 10.0,
+    "total_flos": 4.530059681107968e+17,
+    "train_loss": 0.2042137217959641,
+    "train_runtime": 3284.1143,
+    "train_samples_per_second": 3.593,
+    "train_steps_per_second": 0.113
+}

trainer_state.json

@@ -0,0 +1,228 @@
+{
+  "best_metric": 1.0,
+  "best_model_checkpoint": "resnet-101-CivilEng11k_3Classes\\checkpoint-111",
+  "epoch": 10.0,
+  "eval_steps": 500,
+  "global_step": 370,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.00010810810810810812,
+      "loss": 1.0885,
+      "step": 20
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.43050847457627117,
+      "eval_loss": 0.8954569101333618,
+      "eval_runtime": 28.4852,
+      "eval_samples_per_second": 10.356,
+      "eval_steps_per_second": 0.351,
+      "step": 37
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 0.0001981981981981982,
+      "loss": 0.9813,
+      "step": 40
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 0.0001861861861861862,
+      "loss": 0.6832,
+      "step": 60
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.847457627118644,
+      "eval_loss": 0.49903005361557007,
+      "eval_runtime": 28.4228,
+      "eval_samples_per_second": 10.379,
+      "eval_steps_per_second": 0.352,
+      "step": 74
+    },
+    {
+      "epoch": 2.16,
+      "learning_rate": 0.0001741741741741742,
+      "loss": 0.541,
+      "step": 80
+    },
+    {
+      "epoch": 2.7,
+      "learning_rate": 0.00016216216216216218,
+      "loss": 0.2591,
+      "step": 100
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 1.0,
+      "eval_loss": 0.05872531235218048,
+      "eval_runtime": 29.0238,
+      "eval_samples_per_second": 10.164,
+      "eval_steps_per_second": 0.345,
+      "step": 111
+    },
+    {
+      "epoch": 3.24,
+      "learning_rate": 0.00015015015015015014,
+      "loss": 0.0814,
+      "step": 120
+    },
+    {
+      "epoch": 3.78,
+      "learning_rate": 0.00013813813813813813,
+      "loss": 0.024,
+      "step": 140
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 1.0,
+      "eval_loss": 0.0026093204505741596,
+      "eval_runtime": 29.0003,
+      "eval_samples_per_second": 10.172,
+      "eval_steps_per_second": 0.345,
+      "step": 148
+    },
+    {
+      "epoch": 4.32,
+      "learning_rate": 0.00012612612612612612,
+      "loss": 0.0386,
+      "step": 160
+    },
+    {
+      "epoch": 4.86,
+      "learning_rate": 0.00011411411411411413,
+      "loss": 0.005,
+      "step": 180
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 1.0,
+      "eval_loss": 0.0007084628450684249,
+      "eval_runtime": 28.7679,
+      "eval_samples_per_second": 10.254,
+      "eval_steps_per_second": 0.348,
+      "step": 185
+    },
+    {
+      "epoch": 5.41,
+      "learning_rate": 0.00010210210210210212,
+      "loss": 0.0197,
+      "step": 200
+    },
+    {
+      "epoch": 5.95,
+      "learning_rate": 9.009009009009009e-05,
+      "loss": 0.0121,
+      "step": 220
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 1.0,
+      "eval_loss": 0.000460774201201275,
+      "eval_runtime": 28.6565,
+      "eval_samples_per_second": 10.294,
+      "eval_steps_per_second": 0.349,
+      "step": 222
+    },
+    {
+      "epoch": 6.49,
+      "learning_rate": 7.807807807807808e-05,
+      "loss": 0.0214,
+      "step": 240
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 1.0,
+      "eval_loss": 0.00029981997795403004,
+      "eval_runtime": 28.7649,
+      "eval_samples_per_second": 10.256,
+      "eval_steps_per_second": 0.348,
+      "step": 259
+    },
+    {
+      "epoch": 7.03,
+      "learning_rate": 6.606606606606607e-05,
+      "loss": 0.0014,
+      "step": 260
+    },
+    {
+      "epoch": 7.57,
+      "learning_rate": 5.405405405405406e-05,
+      "loss": 0.0035,
+      "step": 280
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 1.0,
+      "eval_loss": 0.00022267199528869241,
+      "eval_runtime": 28.7621,
+      "eval_samples_per_second": 10.257,
+      "eval_steps_per_second": 0.348,
+      "step": 296
+    },
+    {
+      "epoch": 8.11,
+      "learning_rate": 4.204204204204204e-05,
+      "loss": 0.0054,
+      "step": 300
+    },
+    {
+      "epoch": 8.65,
+      "learning_rate": 3.0030030030030033e-05,
+      "loss": 0.0026,
+      "step": 320
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 1.0,
+      "eval_loss": 0.00019589992007240653,
+      "eval_runtime": 28.741,
+      "eval_samples_per_second": 10.264,
+      "eval_steps_per_second": 0.348,
+      "step": 333
+    },
+    {
+      "epoch": 9.19,
+      "learning_rate": 1.801801801801802e-05,
+      "loss": 0.0042,
+      "step": 340
+    },
+    {
+      "epoch": 9.73,
+      "learning_rate": 6.006006006006006e-06,
+      "loss": 0.0054,
+      "step": 360
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 1.0,
+      "eval_loss": 0.00018292466120328754,
+      "eval_runtime": 29.0295,
+      "eval_samples_per_second": 10.162,
+      "eval_steps_per_second": 0.344,
+      "step": 370
+    },
+    {
+      "epoch": 10.0,
+      "step": 370,
+      "total_flos": 4.530059681107968e+17,
+      "train_loss": 0.2042137217959641,
+      "train_runtime": 3284.1143,
+      "train_samples_per_second": 3.593,
+      "train_steps_per_second": 0.113
+    }
+  ],
+  "logging_steps": 20,
+  "max_steps": 370,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 4.530059681107968e+17,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}