Training in progress, step 100

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 5.0,
+    "eval_loss": 0.07897982746362686,
+    "eval_runtime": 194.0605,
+    "eval_samples_per_second": 9.337,
+    "eval_steps_per_second": 0.294,
+    "total_flos": 7.020774259082035e+17,
+    "train_loss": 0.15416914590618067,
+    "train_runtime": 2897.051,
+    "train_samples_per_second": 3.148,
+    "train_steps_per_second": 0.098
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 5.0,
+    "eval_loss": 0.10813982784748077,
+    "eval_runtime": 24.5494,
+    "eval_samples_per_second": 9.247,
+    "eval_steps_per_second": 0.326
+}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a39344f88a60f42249fe9fac37bc91b0a813c0a2c85f3622b2cf7a3dcd0c96e
+oid sha256:ee8f751cdb7df86eb343179d7d295483a89b8d916b89e9b688a86d95d96f4a01
 size 343223968

runs/Jul12_16-00-05_REDLGLAUCORE01/events.out.tfevents.1720828147.REDLGLAUCORE01.162992.25

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28b88806201f7dd792a3de1b0ed35debf39e7b290bbfe5810cd744585e16cfba
+size 630

runs/Jul12_19-35-38_REDLGLAUCORE01/events.out.tfevents.1720838139.REDLGLAUCORE01.162992.27

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61025be7f3ab1dd73f61af2b6c5fdc7b955c10c77b81aa6043f75150b6d0638b
+size 7437

train_eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 5.0,
+    "eval_loss": 0.07897982746362686,
+    "eval_runtime": 194.0605,
+    "eval_samples_per_second": 9.337,
+    "eval_steps_per_second": 0.294
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 5.0,
+    "total_flos": 7.020774259082035e+17,
+    "train_loss": 0.15416914590618067,
+    "train_runtime": 2897.051,
+    "train_samples_per_second": 3.148,
+    "train_steps_per_second": 0.098
+}

trainer_state.json

@@ -0,0 +1,254 @@
+{
+  "best_metric": 0.10813982784748077,
+  "best_model_checkpoint": "/home/projects/Project - Fundus Photo Glaucoma Detection (AI)//model_results/vit-base-gpu/checkpoint-200",
+  "epoch": 5.0,
+  "eval_steps": 100,
+  "global_step": 285,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.17543859649122806,
+      "grad_norm": 1.040771245956421,
+      "learning_rate": 9.649122807017545e-06,
+      "loss": 0.6273,
+      "step": 10
+    },
+    {
+      "epoch": 0.3508771929824561,
+      "grad_norm": 2.329632520675659,
+      "learning_rate": 9.298245614035088e-06,
+      "loss": 0.5016,
+      "step": 20
+    },
+    {
+      "epoch": 0.5263157894736842,
+      "grad_norm": 1.6268341541290283,
+      "learning_rate": 8.947368421052632e-06,
+      "loss": 0.3763,
+      "step": 30
+    },
+    {
+      "epoch": 0.7017543859649122,
+      "grad_norm": 2.5890719890594482,
+      "learning_rate": 8.596491228070176e-06,
+      "loss": 0.2924,
+      "step": 40
+    },
+    {
+      "epoch": 0.8771929824561403,
+      "grad_norm": 0.7261876463890076,
+      "learning_rate": 8.24561403508772e-06,
+      "loss": 0.2481,
+      "step": 50
+    },
+    {
+      "epoch": 1.0526315789473684,
+      "grad_norm": 0.8194475769996643,
+      "learning_rate": 7.894736842105265e-06,
+      "loss": 0.1682,
+      "step": 60
+    },
+    {
+      "epoch": 1.2280701754385965,
+      "grad_norm": 0.5261658430099487,
+      "learning_rate": 7.5438596491228074e-06,
+      "loss": 0.1543,
+      "step": 70
+    },
+    {
+      "epoch": 1.4035087719298245,
+      "grad_norm": 0.5462292432785034,
+      "learning_rate": 7.192982456140352e-06,
+      "loss": 0.1492,
+      "step": 80
+    },
+    {
+      "epoch": 1.5789473684210527,
+      "grad_norm": 0.6172283887863159,
+      "learning_rate": 6.842105263157896e-06,
+      "loss": 0.1214,
+      "step": 90
+    },
+    {
+      "epoch": 1.7543859649122808,
+      "grad_norm": 0.48490244150161743,
+      "learning_rate": 6.491228070175439e-06,
+      "loss": 0.1209,
+      "step": 100
+    },
+    {
+      "epoch": 1.7543859649122808,
+      "eval_loss": 0.15530365705490112,
+      "eval_runtime": 24.2994,
+      "eval_samples_per_second": 9.342,
+      "eval_steps_per_second": 0.329,
+      "step": 100
+    },
+    {
+      "epoch": 1.9298245614035088,
+      "grad_norm": 6.183306694030762,
+      "learning_rate": 6.140350877192983e-06,
+      "loss": 0.1262,
+      "step": 110
+    },
+    {
+      "epoch": 2.1052631578947367,
+      "grad_norm": 0.6162407994270325,
+      "learning_rate": 5.789473684210527e-06,
+      "loss": 0.1122,
+      "step": 120
+    },
+    {
+      "epoch": 2.280701754385965,
+      "grad_norm": 0.4731535315513611,
+      "learning_rate": 5.438596491228071e-06,
+      "loss": 0.1169,
+      "step": 130
+    },
+    {
+      "epoch": 2.456140350877193,
+      "grad_norm": 0.3595629334449768,
+      "learning_rate": 5.087719298245615e-06,
+      "loss": 0.0814,
+      "step": 140
+    },
+    {
+      "epoch": 2.6315789473684212,
+      "grad_norm": 0.3399164080619812,
+      "learning_rate": 4.736842105263158e-06,
+      "loss": 0.0914,
+      "step": 150
+    },
+    {
+      "epoch": 2.807017543859649,
+      "grad_norm": 2.8990585803985596,
+      "learning_rate": 4.385964912280702e-06,
+      "loss": 0.0856,
+      "step": 160
+    },
+    {
+      "epoch": 2.982456140350877,
+      "grad_norm": 5.240866184234619,
+      "learning_rate": 4.035087719298246e-06,
+      "loss": 0.0874,
+      "step": 170
+    },
+    {
+      "epoch": 3.1578947368421053,
+      "grad_norm": 0.3441706597805023,
+      "learning_rate": 3.6842105263157896e-06,
+      "loss": 0.0895,
+      "step": 180
+    },
+    {
+      "epoch": 3.3333333333333335,
+      "grad_norm": 0.3535279631614685,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 0.0881,
+      "step": 190
+    },
+    {
+      "epoch": 3.5087719298245617,
+      "grad_norm": 0.6653788685798645,
+      "learning_rate": 2.9824561403508774e-06,
+      "loss": 0.0911,
+      "step": 200
+    },
+    {
+      "epoch": 3.5087719298245617,
+      "eval_loss": 0.10813982784748077,
+      "eval_runtime": 29.8414,
+      "eval_samples_per_second": 7.607,
+      "eval_steps_per_second": 0.268,
+      "step": 200
+    },
+    {
+      "epoch": 3.6842105263157894,
+      "grad_norm": 0.271210640668869,
+      "learning_rate": 2.631578947368421e-06,
+      "loss": 0.1006,
+      "step": 210
+    },
+    {
+      "epoch": 3.8596491228070176,
+      "grad_norm": 0.35550448298454285,
+      "learning_rate": 2.280701754385965e-06,
+      "loss": 0.0703,
+      "step": 220
+    },
+    {
+      "epoch": 4.035087719298246,
+      "grad_norm": 0.5986644625663757,
+      "learning_rate": 1.929824561403509e-06,
+      "loss": 0.1125,
+      "step": 230
+    },
+    {
+      "epoch": 4.2105263157894735,
+      "grad_norm": 0.29196077585220337,
+      "learning_rate": 1.5789473684210526e-06,
+      "loss": 0.076,
+      "step": 240
+    },
+    {
+      "epoch": 4.385964912280702,
+      "grad_norm": 0.2573108673095703,
+      "learning_rate": 1.2280701754385965e-06,
+      "loss": 0.0574,
+      "step": 250
+    },
+    {
+      "epoch": 4.56140350877193,
+      "grad_norm": 0.2528444230556488,
+      "learning_rate": 8.771929824561404e-07,
+      "loss": 0.0565,
+      "step": 260
+    },
+    {
+      "epoch": 4.7368421052631575,
+      "grad_norm": 0.25505849719047546,
+      "learning_rate": 5.263157894736843e-07,
+      "loss": 0.0498,
+      "step": 270
+    },
+    {
+      "epoch": 4.912280701754386,
+      "grad_norm": 0.541071891784668,
+      "learning_rate": 1.7543859649122808e-07,
+      "loss": 0.0945,
+      "step": 280
+    },
+    {
+      "epoch": 5.0,
+      "step": 285,
+      "total_flos": 7.020774259082035e+17,
+      "train_loss": 0.15416914590618067,
+      "train_runtime": 2897.051,
+      "train_samples_per_second": 3.148,
+      "train_steps_per_second": 0.098
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 285,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 7.020774259082035e+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 sha256:675d2df7c745117e4c8ab72db056f7d067ed11eedc9ebb4b2fb08e9399f36b42
+oid sha256:8584a59e7f712b9beaab6a28f54d58e27e0a3520f0055141cb1bfa9260ddfdf2
 size 5240