End of training

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 10.0,
+    "eval_f1": 0.8607594936708861,
+    "eval_loss": 0.26272934675216675,
+    "eval_runtime": 10.1059,
+    "eval_samples_per_second": 7.817,
+    "eval_steps_per_second": 0.099,
+    "train_loss": 0.3480381011962891,
+    "train_runtime": 655.7401,
+    "train_samples_per_second": 6.801,
+    "train_steps_per_second": 0.107
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 10.0,
+    "eval_f1": 0.8607594936708861,
+    "eval_loss": 0.26272934675216675,
+    "eval_runtime": 10.1059,
+    "eval_samples_per_second": 7.817,
+    "eval_steps_per_second": 0.099
+}

runs/Dec06_17-37-40_ce9085252610/events.out.tfevents.1670349330.ce9085252610.3736.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02ac11f532aeab94515cdfa0de58df2746f2d5207403662b9da1495385bbd7a7
+size 351

train_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 10.0,
+    "train_loss": 0.3480381011962891,
+    "train_runtime": 655.7401,
+    "train_samples_per_second": 6.801,
+    "train_steps_per_second": 0.107
+}

trainer_state.json

@@ -0,0 +1,157 @@
+{
+  "best_metric": 0.26272934675216675,
+  "best_model_checkpoint": "/leicester_binary_convnext_small6/checkpoint-70",
+  "epoch": 10.0,
+  "global_step": 70,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_f1": 0.8607594936708861,
+      "eval_loss": 0.5187062621116638,
+      "eval_runtime": 10.04,
+      "eval_samples_per_second": 7.869,
+      "eval_steps_per_second": 0.1,
+      "step": 7
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 1.7142857142857142e-05,
+      "loss": 0.5904,
+      "step": 10
+    },
+    {
+      "epoch": 2.0,
+      "eval_f1": 0.8607594936708861,
+      "eval_loss": 0.4272507429122925,
+      "eval_runtime": 10.0147,
+      "eval_samples_per_second": 7.888,
+      "eval_steps_per_second": 0.1,
+      "step": 14
+    },
+    {
+      "epoch": 2.86,
+      "learning_rate": 1.4285714285714287e-05,
+      "loss": 0.3981,
+      "step": 20
+    },
+    {
+      "epoch": 3.0,
+      "eval_f1": 0.8607594936708861,
+      "eval_loss": 0.411451131105423,
+      "eval_runtime": 10.0801,
+      "eval_samples_per_second": 7.837,
+      "eval_steps_per_second": 0.099,
+      "step": 21
+    },
+    {
+      "epoch": 4.0,
+      "eval_f1": 0.8607594936708861,
+      "eval_loss": 0.40291550755500793,
+      "eval_runtime": 10.1912,
+      "eval_samples_per_second": 7.752,
+      "eval_steps_per_second": 0.098,
+      "step": 28
+    },
+    {
+      "epoch": 4.29,
+      "learning_rate": 1.1428571428571429e-05,
+      "loss": 0.3285,
+      "step": 30
+    },
+    {
+      "epoch": 5.0,
+      "eval_f1": 0.8607594936708861,
+      "eval_loss": 0.3401729464530945,
+      "eval_runtime": 10.0131,
+      "eval_samples_per_second": 7.89,
+      "eval_steps_per_second": 0.1,
+      "step": 35
+    },
+    {
+      "epoch": 5.71,
+      "learning_rate": 8.571428571428571e-06,
+      "loss": 0.308,
+      "step": 40
+    },
+    {
+      "epoch": 6.0,
+      "eval_f1": 0.8607594936708861,
+      "eval_loss": 0.31382453441619873,
+      "eval_runtime": 10.0365,
+      "eval_samples_per_second": 7.871,
+      "eval_steps_per_second": 0.1,
+      "step": 42
+    },
+    {
+      "epoch": 7.0,
+      "eval_f1": 0.8607594936708861,
+      "eval_loss": 0.29120802879333496,
+      "eval_runtime": 10.1307,
+      "eval_samples_per_second": 7.798,
+      "eval_steps_per_second": 0.099,
+      "step": 49
+    },
+    {
+      "epoch": 7.14,
+      "learning_rate": 5.7142857142857145e-06,
+      "loss": 0.2952,
+      "step": 50
+    },
+    {
+      "epoch": 8.0,
+      "eval_f1": 0.8607594936708861,
+      "eval_loss": 0.2751685678958893,
+      "eval_runtime": 9.9617,
+      "eval_samples_per_second": 7.93,
+      "eval_steps_per_second": 0.1,
+      "step": 56
+    },
+    {
+      "epoch": 8.57,
+      "learning_rate": 2.8571428571428573e-06,
+      "loss": 0.2593,
+      "step": 60
+    },
+    {
+      "epoch": 9.0,
+      "eval_f1": 0.8607594936708861,
+      "eval_loss": 0.2657069265842438,
+      "eval_runtime": 10.0549,
+      "eval_samples_per_second": 7.857,
+      "eval_steps_per_second": 0.099,
+      "step": 63
+    },
+    {
+      "epoch": 10.0,
+      "learning_rate": 0.0,
+      "loss": 0.2568,
+      "step": 70
+    },
+    {
+      "epoch": 10.0,
+      "eval_f1": 0.8607594936708861,
+      "eval_loss": 0.26272934675216675,
+      "eval_runtime": 10.516,
+      "eval_samples_per_second": 7.512,
+      "eval_steps_per_second": 0.095,
+      "step": 70
+    },
+    {
+      "epoch": 10.0,
+      "step": 70,
+      "total_flos": 1.9921607202889728e+17,
+      "train_loss": 0.3480381011962891,
+      "train_runtime": 655.7401,
+      "train_samples_per_second": 6.801,
+      "train_steps_per_second": 0.107
+    }
+  ],
+  "max_steps": 70,
+  "num_train_epochs": 10,
+  "total_flos": 1.9921607202889728e+17,
+  "trial_name": null,
+  "trial_params": null
+}