Training in progress, epoch 1

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 5.0,
+    "eval_accuracy": 0.9878511769172361,
+    "eval_loss": 0.11460567265748978,
+    "eval_runtime": 15.6306,
+    "eval_samples_per_second": 252.774,
+    "eval_steps_per_second": 7.933,
+    "train_loss": 1.611847831170086,
+    "train_runtime": 1076.3578,
+    "train_samples_per_second": 146.829,
+    "train_steps_per_second": 1.147
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 5.0,
+    "eval_accuracy": 0.9878511769172361,
+    "eval_loss": 0.11460567265748978,
+    "eval_runtime": 15.6306,
+    "eval_samples_per_second": 252.774,
+    "eval_steps_per_second": 7.933
+}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c2f596bd069f05c47342108b52cf07a6255f11d2c919ec2ef900eb6077025aa
+oid sha256:e5d159c0cddceaeadd183d6b7785512baae125c57fc086b4b646ad58d42e56ca
 size 111687116

runs/Sep12_04-51-29_gilbreth-k001.rcac.purdue.edu/events.out.tfevents.1726132186.gilbreth-k001.rcac.purdue.edu.9384.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:631276fa8f7462c440ad9cd3ad9a890322cb1b4a16d4539174ea0af1571dde94
+size 363

runs/Sep12_05-49-33_gilbreth-k001.rcac.purdue.edu/events.out.tfevents.1726134573.gilbreth-k001.rcac.purdue.edu.17127.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c84a3f112a5a712241afa401423a6f83b92f51e746a280fbee0e101dab66b433
+size 22102

train_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 5.0,
+    "train_loss": 1.611847831170086,
+    "train_runtime": 1076.3578,
+    "train_samples_per_second": 146.829,
+    "train_steps_per_second": 1.147
+}

trainer_state.json

@@ -0,0 +1,159 @@
+{
+  "best_metric": 0.9878511769172361,
+  "best_model_checkpoint": "microsoft/swin-original-5/checkpoint-1235",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 1235,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.4,
+      "grad_norm": 6.132917404174805,
+      "learning_rate": 4.032258064516129e-05,
+      "loss": 6.0671,
+      "step": 100
+    },
+    {
+      "epoch": 0.81,
+      "grad_norm": 14.785033226013184,
+      "learning_rate": 4.657965796579658e-05,
+      "loss": 4.7997,
+      "step": 200
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6183244748165021,
+      "eval_loss": 2.255305290222168,
+      "eval_runtime": 16.6534,
+      "eval_samples_per_second": 237.248,
+      "eval_steps_per_second": 7.446,
+      "step": 247
+    },
+    {
+      "epoch": 1.21,
+      "grad_norm": 22.028240203857422,
+      "learning_rate": 4.207920792079208e-05,
+      "loss": 2.7224,
+      "step": 300
+    },
+    {
+      "epoch": 1.62,
+      "grad_norm": 16.01068115234375,
+      "learning_rate": 3.757875787578758e-05,
+      "loss": 1.6045,
+      "step": 400
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9519109086307264,
+      "eval_loss": 0.4502609968185425,
+      "eval_runtime": 16.0354,
+      "eval_samples_per_second": 246.393,
+      "eval_steps_per_second": 7.733,
+      "step": 494
+    },
+    {
+      "epoch": 2.02,
+      "grad_norm": 13.010788917541504,
+      "learning_rate": 3.307830783078308e-05,
+      "loss": 1.0508,
+      "step": 500
+    },
+    {
+      "epoch": 2.43,
+      "grad_norm": 12.1071138381958,
+      "learning_rate": 2.857785778577858e-05,
+      "loss": 0.7845,
+      "step": 600
+    },
+    {
+      "epoch": 2.83,
+      "grad_norm": 14.280351638793945,
+      "learning_rate": 2.4077407740774077e-05,
+      "loss": 0.6279,
+      "step": 700
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.970640344216654,
+      "eval_loss": 0.21980240941047668,
+      "eval_runtime": 15.8459,
+      "eval_samples_per_second": 249.339,
+      "eval_steps_per_second": 7.825,
+      "step": 741
+    },
+    {
+      "epoch": 3.24,
+      "grad_norm": 11.046144485473633,
+      "learning_rate": 1.9576957695769578e-05,
+      "loss": 0.5078,
+      "step": 800
+    },
+    {
+      "epoch": 3.64,
+      "grad_norm": 11.497967720031738,
+      "learning_rate": 1.5076507650765076e-05,
+      "loss": 0.4804,
+      "step": 900
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.9835484687420906,
+      "eval_loss": 0.13504138588905334,
+      "eval_runtime": 15.977,
+      "eval_samples_per_second": 247.293,
+      "eval_steps_per_second": 7.761,
+      "step": 988
+    },
+    {
+      "epoch": 4.05,
+      "grad_norm": 7.521940231323242,
+      "learning_rate": 1.0576057605760577e-05,
+      "loss": 0.4149,
+      "step": 1000
+    },
+    {
+      "epoch": 4.45,
+      "grad_norm": 8.31807804107666,
+      "learning_rate": 6.075607560756076e-06,
+      "loss": 0.3718,
+      "step": 1100
+    },
+    {
+      "epoch": 4.86,
+      "grad_norm": 10.554880142211914,
+      "learning_rate": 1.5751575157515752e-06,
+      "loss": 0.36,
+      "step": 1200
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.9878511769172361,
+      "eval_loss": 0.11460567265748978,
+      "eval_runtime": 15.924,
+      "eval_samples_per_second": 248.116,
+      "eval_steps_per_second": 7.787,
+      "step": 1235
+    },
+    {
+      "epoch": 5.0,
+      "step": 1235,
+      "total_flos": 3.9762075857301504e+18,
+      "train_loss": 1.611847831170086,
+      "train_runtime": 1076.3578,
+      "train_samples_per_second": 146.829,
+      "train_steps_per_second": 1.147
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 1235,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 3.9762075857301504e+18,
+  "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 sha256:4fc700bdfd8ef9d84c3870cd5e31869d9182b0da65fb2b1a635638f4cd2dc10c
+oid sha256:894b7256f178a42a7a42412c0c3f0ef1afcc04cbc5cbabadd7c3882a8552447f
 size 4984