End of training

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 9.97,
+    "eval_accuracy": 0.5259515570934256,
+    "eval_loss": 1.5658899545669556,
+    "eval_runtime": 10.6962,
+    "eval_samples_per_second": 81.057,
+    "eval_steps_per_second": 2.618,
+    "total_flos": 1.427863337526786e+18,
+    "train_loss": 0.991901319367545,
+    "train_runtime": 910.8419,
+    "train_samples_per_second": 20.3,
+    "train_steps_per_second": 0.154
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 9.97,
+    "eval_accuracy": 0.5259515570934256,
+    "eval_loss": 1.5658899545669556,
+    "eval_runtime": 10.6962,
+    "eval_samples_per_second": 81.057,
+    "eval_steps_per_second": 2.618
+}

runs/Jan27_16-01-39_7536e74eae36/events.out.tfevents.1674836336.7536e74eae36.23.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f33bce341b734eac6481f60f5d292ce4ab643ef332c853fe588f8e2c2775fba9
+size 363

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 9.97,
+    "total_flos": 1.427863337526786e+18,
+    "train_loss": 0.991901319367545,
+    "train_runtime": 910.8419,
+    "train_samples_per_second": 20.3,
+    "train_steps_per_second": 0.154
+}

trainer_state.json

@@ -0,0 +1,199 @@
+{
+  "best_metric": 0.5259515570934256,
+  "best_model_checkpoint": "beit-base-patch16-224-pt22k-ft22k-finetuned-FER2013-7e-05-finetuned-FER2013-7e-05/checkpoint-70",
+  "epoch": 9.96551724137931,
+  "global_step": 140,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.69,
+      "learning_rate": 4.9999999999999996e-05,
+      "loss": 1.6537,
+      "step": 10
+    },
+    {
+      "epoch": 0.97,
+      "eval_accuracy": 0.4682814302191465,
+      "eval_loss": 1.4980024099349976,
+      "eval_runtime": 10.8254,
+      "eval_samples_per_second": 80.09,
+      "eval_steps_per_second": 2.587,
+      "step": 14
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 6.666666666666666e-05,
+      "loss": 1.4325,
+      "step": 20
+    },
+    {
+      "epoch": 1.97,
+      "eval_accuracy": 0.5040369088811996,
+      "eval_loss": 1.4777436256408691,
+      "eval_runtime": 15.6158,
+      "eval_samples_per_second": 55.521,
+      "eval_steps_per_second": 1.793,
+      "step": 28
+    },
+    {
+      "epoch": 2.14,
+      "learning_rate": 6.111111111111111e-05,
+      "loss": 1.2959,
+      "step": 30
+    },
+    {
+      "epoch": 2.83,
+      "learning_rate": 5.5555555555555545e-05,
+      "loss": 1.1532,
+      "step": 40
+    },
+    {
+      "epoch": 2.97,
+      "eval_accuracy": 0.49596309111880044,
+      "eval_loss": 1.5006924867630005,
+      "eval_runtime": 10.9073,
+      "eval_samples_per_second": 79.488,
+      "eval_steps_per_second": 2.567,
+      "step": 42
+    },
+    {
+      "epoch": 3.55,
+      "learning_rate": 4.9999999999999996e-05,
+      "loss": 1.0428,
+      "step": 50
+    },
+    {
+      "epoch": 3.97,
+      "eval_accuracy": 0.48904267589388695,
+      "eval_loss": 1.5480250120162964,
+      "eval_runtime": 11.2715,
+      "eval_samples_per_second": 76.919,
+      "eval_steps_per_second": 2.484,
+      "step": 56
+    },
+    {
+      "epoch": 4.28,
+      "learning_rate": 4.444444444444444e-05,
+      "loss": 1.0278,
+      "step": 60
+    },
+    {
+      "epoch": 4.97,
+      "learning_rate": 3.8888888888888884e-05,
+      "loss": 0.8716,
+      "step": 70
+    },
+    {
+      "epoch": 4.97,
+      "eval_accuracy": 0.5259515570934256,
+      "eval_loss": 1.5658899545669556,
+      "eval_runtime": 10.9859,
+      "eval_samples_per_second": 78.919,
+      "eval_steps_per_second": 2.549,
+      "step": 70
+    },
+    {
+      "epoch": 5.69,
+      "learning_rate": 3.333333333333333e-05,
+      "loss": 0.892,
+      "step": 80
+    },
+    {
+      "epoch": 5.97,
+      "eval_accuracy": 0.49596309111880044,
+      "eval_loss": 1.6132378578186035,
+      "eval_runtime": 10.8011,
+      "eval_samples_per_second": 80.27,
+      "eval_steps_per_second": 2.592,
+      "step": 84
+    },
+    {
+      "epoch": 6.41,
+      "learning_rate": 2.7777777777777772e-05,
+      "loss": 0.8109,
+      "step": 90
+    },
+    {
+      "epoch": 6.97,
+      "eval_accuracy": 0.5167243367935409,
+      "eval_loss": 1.5894672870635986,
+      "eval_runtime": 11.3704,
+      "eval_samples_per_second": 76.251,
+      "eval_steps_per_second": 2.463,
+      "step": 98
+    },
+    {
+      "epoch": 7.14,
+      "learning_rate": 2.222222222222222e-05,
+      "loss": 0.8478,
+      "step": 100
+    },
+    {
+      "epoch": 7.83,
+      "learning_rate": 1.6666666666666664e-05,
+      "loss": 0.7413,
+      "step": 110
+    },
+    {
+      "epoch": 7.97,
+      "eval_accuracy": 0.5201845444059977,
+      "eval_loss": 1.6271343231201172,
+      "eval_runtime": 11.1874,
+      "eval_samples_per_second": 77.498,
+      "eval_steps_per_second": 2.503,
+      "step": 112
+    },
+    {
+      "epoch": 8.55,
+      "learning_rate": 1.111111111111111e-05,
+      "loss": 0.765,
+      "step": 120
+    },
+    {
+      "epoch": 8.97,
+      "eval_accuracy": 0.5040369088811996,
+      "eval_loss": 1.599065899848938,
+      "eval_runtime": 10.4618,
+      "eval_samples_per_second": 82.873,
+      "eval_steps_per_second": 2.676,
+      "step": 126
+    },
+    {
+      "epoch": 9.28,
+      "learning_rate": 5.555555555555555e-06,
+      "loss": 0.6946,
+      "step": 130
+    },
+    {
+      "epoch": 9.97,
+      "learning_rate": 0.0,
+      "loss": 0.6575,
+      "step": 140
+    },
+    {
+      "epoch": 9.97,
+      "eval_accuracy": 0.49596309111880044,
+      "eval_loss": 1.6040576696395874,
+      "eval_runtime": 10.956,
+      "eval_samples_per_second": 79.134,
+      "eval_steps_per_second": 2.556,
+      "step": 140
+    },
+    {
+      "epoch": 9.97,
+      "step": 140,
+      "total_flos": 1.427863337526786e+18,
+      "train_loss": 0.991901319367545,
+      "train_runtime": 910.8419,
+      "train_samples_per_second": 20.3,
+      "train_steps_per_second": 0.154
+    }
+  ],
+  "max_steps": 140,
+  "num_train_epochs": 10,
+  "total_flos": 1.427863337526786e+18,
+  "trial_name": null,
+  "trial_params": null
+}