End of training

README.md

@@ -18,8 +18,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [microsoft/swin-base-patch4-window7-224](https://huggingface.co/microsoft/swin-base-patch4-window7-224) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.5821
-- F1: 0.6827
+- Loss: 0.5750
+- F1: 0.6892
 
 ## Model description
 

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 2.9888475836431225,
+    "eval_f1": 0.6891891891891891,
+    "eval_loss": 0.5749828815460205,
+    "eval_runtime": 42.4435,
+    "eval_samples_per_second": 50.561,
+    "eval_steps_per_second": 1.602,
+    "total_flos": 2.0116004863053496e+18,
+    "train_loss": 0.5923614676912032,
+    "train_runtime": 970.3607,
+    "train_samples_per_second": 26.532,
+    "train_steps_per_second": 0.207
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.9888475836431225,
+    "eval_f1": 0.6891891891891891,
+    "eval_loss": 0.5749828815460205,
+    "eval_runtime": 42.4435,
+    "eval_samples_per_second": 50.561,
+    "eval_steps_per_second": 1.602
+}

runs/Oct29_02-07-45_7291ebd579c4/events.out.tfevents.1730168697.7291ebd579c4.23.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4742ce2e1320dfd23e1c9b61933030df3ae2daca04d59a9d3c291ecd49a72f50
+size 405

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.9888475836431225,
+    "total_flos": 2.0116004863053496e+18,
+    "train_loss": 0.5923614676912032,
+    "train_runtime": 970.3607,
+    "train_samples_per_second": 26.532,
+    "train_steps_per_second": 0.207
+}

trainer_state.json

@@ -0,0 +1,209 @@
+{
+  "best_metric": 0.6891891891891891,
+  "best_model_checkpoint": "microsoft/swin-base-patch4-window7-224-finetuned-dsc/checkpoint-134",
+  "epoch": 2.9888475836431225,
+  "eval_steps": 500,
+  "global_step": 201,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.14869888475836432,
+      "grad_norm": 6.565695285797119,
+      "learning_rate": 2.380952380952381e-05,
+      "loss": 0.7083,
+      "step": 10
+    },
+    {
+      "epoch": 0.29739776951672864,
+      "grad_norm": 5.438655376434326,
+      "learning_rate": 4.761904761904762e-05,
+      "loss": 0.6693,
+      "step": 20
+    },
+    {
+      "epoch": 0.44609665427509293,
+      "grad_norm": 3.0724263191223145,
+      "learning_rate": 4.75e-05,
+      "loss": 0.6358,
+      "step": 30
+    },
+    {
+      "epoch": 0.5947955390334573,
+      "grad_norm": 3.94057559967041,
+      "learning_rate": 4.472222222222223e-05,
+      "loss": 0.6324,
+      "step": 40
+    },
+    {
+      "epoch": 0.7434944237918215,
+      "grad_norm": 3.166926383972168,
+      "learning_rate": 4.194444444444445e-05,
+      "loss": 0.6199,
+      "step": 50
+    },
+    {
+      "epoch": 0.8921933085501859,
+      "grad_norm": 5.67188835144043,
+      "learning_rate": 3.9166666666666665e-05,
+      "loss": 0.614,
+      "step": 60
+    },
+    {
+      "epoch": 0.9962825278810409,
+      "eval_f1": 0.684995340167754,
+      "eval_loss": 0.5885956287384033,
+      "eval_runtime": 42.0381,
+      "eval_samples_per_second": 51.049,
+      "eval_steps_per_second": 1.618,
+      "step": 67
+    },
+    {
+      "epoch": 1.0408921933085502,
+      "grad_norm": 5.284745693206787,
+      "learning_rate": 3.638888888888889e-05,
+      "loss": 0.614,
+      "step": 70
+    },
+    {
+      "epoch": 1.1895910780669146,
+      "grad_norm": 6.20527982711792,
+      "learning_rate": 3.3611111111111116e-05,
+      "loss": 0.5849,
+      "step": 80
+    },
+    {
+      "epoch": 1.3382899628252787,
+      "grad_norm": 3.855804681777954,
+      "learning_rate": 3.0833333333333335e-05,
+      "loss": 0.5679,
+      "step": 90
+    },
+    {
+      "epoch": 1.486988847583643,
+      "grad_norm": 2.7255961894989014,
+      "learning_rate": 2.8055555555555557e-05,
+      "loss": 0.5986,
+      "step": 100
+    },
+    {
+      "epoch": 1.6356877323420074,
+      "grad_norm": 2.572277545928955,
+      "learning_rate": 2.527777777777778e-05,
+      "loss": 0.5824,
+      "step": 110
+    },
+    {
+      "epoch": 1.7843866171003717,
+      "grad_norm": 4.312213897705078,
+      "learning_rate": 2.25e-05,
+      "loss": 0.5745,
+      "step": 120
+    },
+    {
+      "epoch": 1.933085501858736,
+      "grad_norm": 3.377645969390869,
+      "learning_rate": 1.9722222222222224e-05,
+      "loss": 0.5732,
+      "step": 130
+    },
+    {
+      "epoch": 1.9925650557620818,
+      "eval_f1": 0.6891891891891891,
+      "eval_loss": 0.5749828815460205,
+      "eval_runtime": 41.9409,
+      "eval_samples_per_second": 51.167,
+      "eval_steps_per_second": 1.621,
+      "step": 134
+    },
+    {
+      "epoch": 2.0817843866171004,
+      "grad_norm": 3.5765645503997803,
+      "learning_rate": 1.6944444444444446e-05,
+      "loss": 0.576,
+      "step": 140
+    },
+    {
+      "epoch": 2.2304832713754648,
+      "grad_norm": 3.370438814163208,
+      "learning_rate": 1.4166666666666668e-05,
+      "loss": 0.56,
+      "step": 150
+    },
+    {
+      "epoch": 2.379182156133829,
+      "grad_norm": 4.5592265129089355,
+      "learning_rate": 1.138888888888889e-05,
+      "loss": 0.5413,
+      "step": 160
+    },
+    {
+      "epoch": 2.5278810408921935,
+      "grad_norm": 2.81746506690979,
+      "learning_rate": 8.611111111111112e-06,
+      "loss": 0.5569,
+      "step": 170
+    },
+    {
+      "epoch": 2.6765799256505574,
+      "grad_norm": 3.472538471221924,
+      "learning_rate": 5.833333333333334e-06,
+      "loss": 0.551,
+      "step": 180
+    },
+    {
+      "epoch": 2.825278810408922,
+      "grad_norm": 3.6725478172302246,
+      "learning_rate": 3.0555555555555556e-06,
+      "loss": 0.5329,
+      "step": 190
+    },
+    {
+      "epoch": 2.973977695167286,
+      "grad_norm": 3.3126931190490723,
+      "learning_rate": 2.777777777777778e-07,
+      "loss": 0.5618,
+      "step": 200
+    },
+    {
+      "epoch": 2.9888475836431225,
+      "eval_f1": 0.6826654240447344,
+      "eval_loss": 0.5820640325546265,
+      "eval_runtime": 42.5373,
+      "eval_samples_per_second": 50.45,
+      "eval_steps_per_second": 1.599,
+      "step": 201
+    },
+    {
+      "epoch": 2.9888475836431225,
+      "step": 201,
+      "total_flos": 2.0116004863053496e+18,
+      "train_loss": 0.5923614676912032,
+      "train_runtime": 970.3607,
+      "train_samples_per_second": 26.532,
+      "train_steps_per_second": 0.207
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 201,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.0116004863053496e+18,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}