Training in progress, epoch 0

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 8.0,
+    "total_flos": 1.9019421639416218e+17,
+    "train_loss": 2.6748404184977215,
+    "train_runtime": 2549.9123,
+    "train_samples_per_second": 3.749,
+    "train_steps_per_second": 0.012
+}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25adb1edd66215e1b4d731172fa87a7a4bb17ee0eb7d6015e40489d246080efb
+oid sha256:42758b103584d7cd49e63d3200625149d08137738e98ac59919396a9c4543afe
 size 110398208

runs/Jun27_07-26-45_c34ae8869574/events.out.tfevents.1719473207.c34ae8869574

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d648d825f11a0f482c52834586004804142e6de17315cfdd8187a4cc50b09eab
+size 6361

runs/Jun27_07-36-11_c34ae8869574/events.out.tfevents.1719473776.c34ae8869574

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e771d4fc84d7ef0510c2f960aa174702843210a2b72ac09e24b62452a3811b55
+size 7810

runs/Jun27_08-42-01_c3df91dfd599/events.out.tfevents.1719477728.c3df91dfd599

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2df81a7c4b1e1c5ef573f25786ff8164f9a2ae8763c0e33d957af5a9dbcd851e
+size 6361

runs/Jun27_08-47-10_c3df91dfd599/events.out.tfevents.1719478034.c3df91dfd599

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b27dfcc0f4bc79894355421baa1e1b5f0306303b969d23024ae16878488efec0
+size 8273

runs/Jun27_10-04-20_79e23ecbe329/events.out.tfevents.1719482662.79e23ecbe329

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5c54d33a013507f6b06a4f04ca62301966108b0db4420afd425e0e14f9597ea
+size 8224

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 8.0,
+    "total_flos": 1.9019421639416218e+17,
+    "train_loss": 2.6748404184977215,
+    "train_runtime": 2549.9123,
+    "train_samples_per_second": 3.749,
+    "train_steps_per_second": 0.012
+}

trainer_state.json

@@ -0,0 +1,135 @@
+{
+  "best_metric": 0.30022075055187636,
+  "best_model_checkpoint": "swin-tiny-patch4-window7-224-category-classification/checkpoint-26",
+  "epoch": 8.0,
+  "eval_steps": 500,
+  "global_step": 30,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.8,
+      "eval_accuracy": 0.05518763796909492,
+      "eval_loss": 3.007758617401123,
+      "eval_runtime": 188.9532,
+      "eval_samples_per_second": 4.795,
+      "eval_steps_per_second": 0.079,
+      "step": 3
+    },
+    {
+      "epoch": 1.8666666666666667,
+      "eval_accuracy": 0.1280353200883002,
+      "eval_loss": 2.8865292072296143,
+      "eval_runtime": 166.273,
+      "eval_samples_per_second": 5.449,
+      "eval_steps_per_second": 0.09,
+      "step": 7
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 4.288784980773926,
+      "learning_rate": 3.7037037037037037e-05,
+      "loss": 2.9474,
+      "step": 10
+    },
+    {
+      "epoch": 2.9333333333333336,
+      "eval_accuracy": 0.19646799116997793,
+      "eval_loss": 2.7917754650115967,
+      "eval_runtime": 156.11,
+      "eval_samples_per_second": 5.804,
+      "eval_steps_per_second": 0.096,
+      "step": 11
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.23620309050772628,
+      "eval_loss": 2.694143056869507,
+      "eval_runtime": 155.6836,
+      "eval_samples_per_second": 5.819,
+      "eval_steps_per_second": 0.096,
+      "step": 15
+    },
+    {
+      "epoch": 4.8,
+      "eval_accuracy": 0.2582781456953642,
+      "eval_loss": 2.628232002258301,
+      "eval_runtime": 148.8415,
+      "eval_samples_per_second": 6.087,
+      "eval_steps_per_second": 0.101,
+      "step": 18
+    },
+    {
+      "epoch": 5.333333333333333,
+      "grad_norm": 4.339354515075684,
+      "learning_rate": 1.8518518518518518e-05,
+      "loss": 2.645,
+      "step": 20
+    },
+    {
+      "epoch": 5.866666666666667,
+      "eval_accuracy": 0.282560706401766,
+      "eval_loss": 2.5581247806549072,
+      "eval_runtime": 155.1024,
+      "eval_samples_per_second": 5.841,
+      "eval_steps_per_second": 0.097,
+      "step": 22
+    },
+    {
+      "epoch": 6.933333333333334,
+      "eval_accuracy": 0.30022075055187636,
+      "eval_loss": 2.515105962753296,
+      "eval_runtime": 149.6803,
+      "eval_samples_per_second": 6.053,
+      "eval_steps_per_second": 0.1,
+      "step": 26
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 4.57526159286499,
+      "learning_rate": 0.0,
+      "loss": 2.4321,
+      "step": 30
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.2980132450331126,
+      "eval_loss": 2.4982221126556396,
+      "eval_runtime": 169.9225,
+      "eval_samples_per_second": 5.332,
+      "eval_steps_per_second": 0.088,
+      "step": 30
+    },
+    {
+      "epoch": 8.0,
+      "step": 30,
+      "total_flos": 1.9019421639416218e+17,
+      "train_loss": 2.6748404184977215,
+      "train_runtime": 2549.9123,
+      "train_samples_per_second": 3.749,
+      "train_steps_per_second": 0.012
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 30,
+  "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": 1.9019421639416218e+17,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e5163abb6b92fa6e78aff6612725e85119767ac2a5b4d32eb6967c07c80cc20
+oid sha256:8f70c68887969d626f0f5fbfe9b053bb1874e07deaf580b932ca8af4ac3c26a5
 size 4731