Training in progress, epoch 0

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 9.68421052631579,
+    "eval_accuracy": 0.9458388375165125,
+    "eval_loss": 0.16089674830436707,
+    "eval_runtime": 3.23,
+    "eval_samples_per_second": 234.366,
+    "eval_steps_per_second": 7.43,
+    "total_flos": 7.291573574754632e+17,
+    "train_loss": 0.36814911676489787,
+    "train_runtime": 310.0803,
+    "train_samples_per_second": 97.652,
+    "train_steps_per_second": 0.742
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 9.68421052631579,
+    "eval_accuracy": 0.9458388375165125,
+    "eval_loss": 0.16089674830436707,
+    "eval_runtime": 3.23,
+    "eval_samples_per_second": 234.366,
+    "eval_steps_per_second": 7.43
+}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d189ce29e944736feb43166613897f62cf10b1fe78813f43431b64fcafad5e1
+oid sha256:5cf20d304c66e8fdd5708eec8a650d0bcf03f6c9c60f1098c965300b6401966a
 size 110355136

runs/Jun10_05-09-42_e6d590d50f6e/events.out.tfevents.1717996510.e6d590d50f6e.461.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de740fb9bc7d59f022442ef6d16734081e79c7b144f185739939bee019c53a6f
+size 411

runs/Jun10_05-18-58_e6d590d50f6e/events.out.tfevents.1717996738.e6d590d50f6e.461.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:169d77b57817ac0545a193c1e6b0020b467f2807d09cf3ce9aa64ec821291315
+size 6066

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 9.68421052631579,
+    "total_flos": 7.291573574754632e+17,
+    "train_loss": 0.36814911676489787,
+    "train_runtime": 310.0803,
+    "train_samples_per_second": 97.652,
+    "train_steps_per_second": 0.742
+}

trainer_state.json

@@ -0,0 +1,293 @@
+{
+  "best_metric": 0.9458388375165125,
+  "best_model_checkpoint": "swin-tiny-patch4-window7-224-finalterm/checkpoint-213",
+  "epoch": 9.68421052631579,
+  "eval_steps": 500,
+  "global_step": 230,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.42105263157894735,
+      "grad_norm": 4.606943607330322,
+      "learning_rate": 2.173913043478261e-05,
+      "loss": 1.8065,
+      "step": 10
+    },
+    {
+      "epoch": 0.8421052631578947,
+      "grad_norm": 4.823718547821045,
+      "learning_rate": 4.347826086956522e-05,
+      "loss": 1.3107,
+      "step": 20
+    },
+    {
+      "epoch": 0.968421052631579,
+      "eval_accuracy": 0.8348745046235139,
+      "eval_loss": 0.6132236123085022,
+      "eval_runtime": 3.1042,
+      "eval_samples_per_second": 243.862,
+      "eval_steps_per_second": 7.731,
+      "step": 23
+    },
+    {
+      "epoch": 1.263157894736842,
+      "grad_norm": 6.365540504455566,
+      "learning_rate": 4.830917874396135e-05,
+      "loss": 0.6282,
+      "step": 30
+    },
+    {
+      "epoch": 1.6842105263157894,
+      "grad_norm": 6.270587921142578,
+      "learning_rate": 4.589371980676328e-05,
+      "loss": 0.4128,
+      "step": 40
+    },
+    {
+      "epoch": 1.9789473684210526,
+      "eval_accuracy": 0.9233817701453104,
+      "eval_loss": 0.25043442845344543,
+      "eval_runtime": 3.103,
+      "eval_samples_per_second": 243.96,
+      "eval_steps_per_second": 7.735,
+      "step": 47
+    },
+    {
+      "epoch": 2.1052631578947367,
+      "grad_norm": 5.101744651794434,
+      "learning_rate": 4.347826086956522e-05,
+      "loss": 0.3978,
+      "step": 50
+    },
+    {
+      "epoch": 2.526315789473684,
+      "grad_norm": 7.869506359100342,
+      "learning_rate": 4.106280193236715e-05,
+      "loss": 0.2573,
+      "step": 60
+    },
+    {
+      "epoch": 2.9473684210526314,
+      "grad_norm": 5.02071475982666,
+      "learning_rate": 3.864734299516908e-05,
+      "loss": 0.3188,
+      "step": 70
+    },
+    {
+      "epoch": 2.9894736842105263,
+      "eval_accuracy": 0.9313077939233818,
+      "eval_loss": 0.20792996883392334,
+      "eval_runtime": 3.1416,
+      "eval_samples_per_second": 240.957,
+      "eval_steps_per_second": 7.639,
+      "step": 71
+    },
+    {
+      "epoch": 3.3684210526315788,
+      "grad_norm": 5.323513031005859,
+      "learning_rate": 3.6231884057971014e-05,
+      "loss": 0.2418,
+      "step": 80
+    },
+    {
+      "epoch": 3.7894736842105265,
+      "grad_norm": 5.30533504486084,
+      "learning_rate": 3.381642512077295e-05,
+      "loss": 0.2457,
+      "step": 90
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.9286657859973579,
+      "eval_loss": 0.19689106941223145,
+      "eval_runtime": 3.1441,
+      "eval_samples_per_second": 240.768,
+      "eval_steps_per_second": 7.633,
+      "step": 95
+    },
+    {
+      "epoch": 4.2105263157894735,
+      "grad_norm": 3.670581817626953,
+      "learning_rate": 3.140096618357488e-05,
+      "loss": 0.2736,
+      "step": 100
+    },
+    {
+      "epoch": 4.631578947368421,
+      "grad_norm": 3.689314365386963,
+      "learning_rate": 2.8985507246376814e-05,
+      "loss": 0.238,
+      "step": 110
+    },
+    {
+      "epoch": 4.968421052631579,
+      "eval_accuracy": 0.9379128137384413,
+      "eval_loss": 0.1951446682214737,
+      "eval_runtime": 3.1119,
+      "eval_samples_per_second": 243.263,
+      "eval_steps_per_second": 7.712,
+      "step": 118
+    },
+    {
+      "epoch": 5.052631578947368,
+      "grad_norm": 6.361433982849121,
+      "learning_rate": 2.6570048309178748e-05,
+      "loss": 0.248,
+      "step": 120
+    },
+    {
+      "epoch": 5.473684210526316,
+      "grad_norm": 4.373514652252197,
+      "learning_rate": 2.4154589371980676e-05,
+      "loss": 0.2051,
+      "step": 130
+    },
+    {
+      "epoch": 5.894736842105263,
+      "grad_norm": 4.400747776031494,
+      "learning_rate": 2.173913043478261e-05,
+      "loss": 0.2,
+      "step": 140
+    },
+    {
+      "epoch": 5.978947368421053,
+      "eval_accuracy": 0.9418758256274768,
+      "eval_loss": 0.17091834545135498,
+      "eval_runtime": 3.4141,
+      "eval_samples_per_second": 221.725,
+      "eval_steps_per_second": 7.03,
+      "step": 142
+    },
+    {
+      "epoch": 6.315789473684211,
+      "grad_norm": 4.114778518676758,
+      "learning_rate": 1.932367149758454e-05,
+      "loss": 0.1971,
+      "step": 150
+    },
+    {
+      "epoch": 6.7368421052631575,
+      "grad_norm": 5.723143577575684,
+      "learning_rate": 1.6908212560386476e-05,
+      "loss": 0.2037,
+      "step": 160
+    },
+    {
+      "epoch": 6.989473684210527,
+      "eval_accuracy": 0.9431968295904888,
+      "eval_loss": 0.17441698908805847,
+      "eval_runtime": 3.1436,
+      "eval_samples_per_second": 240.806,
+      "eval_steps_per_second": 7.635,
+      "step": 166
+    },
+    {
+      "epoch": 7.157894736842105,
+      "grad_norm": 5.644651412963867,
+      "learning_rate": 1.4492753623188407e-05,
+      "loss": 0.1939,
+      "step": 170
+    },
+    {
+      "epoch": 7.578947368421053,
+      "grad_norm": 5.06740665435791,
+      "learning_rate": 1.2077294685990338e-05,
+      "loss": 0.203,
+      "step": 180
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 3.859252452850342,
+      "learning_rate": 9.66183574879227e-06,
+      "loss": 0.1818,
+      "step": 190
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.9418758256274768,
+      "eval_loss": 0.16339561343193054,
+      "eval_runtime": 3.2688,
+      "eval_samples_per_second": 231.582,
+      "eval_steps_per_second": 7.342,
+      "step": 190
+    },
+    {
+      "epoch": 8.421052631578947,
+      "grad_norm": 6.130388259887695,
+      "learning_rate": 7.246376811594203e-06,
+      "loss": 0.1662,
+      "step": 200
+    },
+    {
+      "epoch": 8.842105263157894,
+      "grad_norm": 4.869731426239014,
+      "learning_rate": 4.830917874396135e-06,
+      "loss": 0.1838,
+      "step": 210
+    },
+    {
+      "epoch": 8.968421052631578,
+      "eval_accuracy": 0.9458388375165125,
+      "eval_loss": 0.16089674830436707,
+      "eval_runtime": 3.1248,
+      "eval_samples_per_second": 242.252,
+      "eval_steps_per_second": 7.68,
+      "step": 213
+    },
+    {
+      "epoch": 9.263157894736842,
+      "grad_norm": 4.596017837524414,
+      "learning_rate": 2.4154589371980677e-06,
+      "loss": 0.1765,
+      "step": 220
+    },
+    {
+      "epoch": 9.68421052631579,
+      "grad_norm": 4.615110397338867,
+      "learning_rate": 0.0,
+      "loss": 0.1769,
+      "step": 230
+    },
+    {
+      "epoch": 9.68421052631579,
+      "eval_accuracy": 0.9431968295904888,
+      "eval_loss": 0.1606564074754715,
+      "eval_runtime": 3.1146,
+      "eval_samples_per_second": 243.05,
+      "eval_steps_per_second": 7.706,
+      "step": 230
+    },
+    {
+      "epoch": 9.68421052631579,
+      "step": 230,
+      "total_flos": 7.291573574754632e+17,
+      "train_loss": 0.36814911676489787,
+      "train_runtime": 310.0803,
+      "train_samples_per_second": 97.652,
+      "train_steps_per_second": 0.742
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 230,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "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": 7.291573574754632e+17,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f564a6f6276d555999bcf389dd4ad383dc5eb864da88b73467d2a6a30ec18b4
+oid sha256:1c15880d116c87fabc94a6433b7602dbfaa1b68b6973fac4110c1538bc4b6ae3
 size 5176