End of training

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 5.0,
+    "eval_accuracy": 0.9699248120300752,
+    "eval_loss": 0.18238767981529236,
+    "eval_runtime": 8.6326,
+    "eval_samples_per_second": 15.407,
+    "eval_steps_per_second": 0.695,
+    "train_loss": 0.3897728649052707,
+    "train_runtime": 301.7547,
+    "train_samples_per_second": 17.133,
+    "train_steps_per_second": 0.729
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 5.0,
+    "eval_accuracy": 0.9699248120300752,
+    "eval_loss": 0.18238767981529236,
+    "eval_runtime": 8.6326,
+    "eval_samples_per_second": 15.407,
+    "eval_steps_per_second": 0.695
+}

train_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 5.0,
+    "train_loss": 0.3897728649052707,
+    "train_runtime": 301.7547,
+    "train_samples_per_second": 17.133,
+    "train_steps_per_second": 0.729
+}

trainer_state.json

@@ -0,0 +1,202 @@
+{
+  "best_metric": 0.18238767981529236,
+  "best_model_checkpoint": "./beans_outputs/checkpoint-220",
+  "epoch": 5.0,
+  "global_step": 220,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.9090909090909094e-05,
+      "loss": 1.0242,
+      "step": 10
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.8181818181818182e-05,
+      "loss": 0.898,
+      "step": 20
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 1.7272727272727274e-05,
+      "loss": 0.7761,
+      "step": 30
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 1.6363636363636366e-05,
+      "loss": 0.672,
+      "step": 40
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9398496240601504,
+      "eval_loss": 0.5671981573104858,
+      "eval_runtime": 2.1561,
+      "eval_samples_per_second": 61.686,
+      "eval_steps_per_second": 2.783,
+      "step": 44
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 1.5454545454545454e-05,
+      "loss": 0.583,
+      "step": 50
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 1.4545454545454546e-05,
+      "loss": 0.5104,
+      "step": 60
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 1.3636363636363637e-05,
+      "loss": 0.4104,
+      "step": 70
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 1.2727272727272728e-05,
+      "loss": 0.411,
+      "step": 80
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9699248120300752,
+      "eval_loss": 0.30274108052253723,
+      "eval_runtime": 4.0989,
+      "eval_samples_per_second": 32.448,
+      "eval_steps_per_second": 1.464,
+      "step": 88
+    },
+    {
+      "epoch": 2.05,
+      "learning_rate": 1.181818181818182e-05,
+      "loss": 0.3473,
+      "step": 90
+    },
+    {
+      "epoch": 2.27,
+      "learning_rate": 1.0909090909090909e-05,
+      "loss": 0.3066,
+      "step": 100
+    },
+    {
+      "epoch": 2.5,
+      "learning_rate": 1e-05,
+      "loss": 0.2993,
+      "step": 110
+    },
+    {
+      "epoch": 2.73,
+      "learning_rate": 9.090909090909091e-06,
+      "loss": 0.2402,
+      "step": 120
+    },
+    {
+      "epoch": 2.95,
+      "learning_rate": 8.181818181818183e-06,
+      "loss": 0.2542,
+      "step": 130
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9699248120300752,
+      "eval_loss": 0.20783478021621704,
+      "eval_runtime": 2.6143,
+      "eval_samples_per_second": 50.874,
+      "eval_steps_per_second": 2.295,
+      "step": 132
+    },
+    {
+      "epoch": 3.18,
+      "learning_rate": 7.272727272727273e-06,
+      "loss": 0.257,
+      "step": 140
+    },
+    {
+      "epoch": 3.41,
+      "learning_rate": 6.363636363636364e-06,
+      "loss": 0.2739,
+      "step": 150
+    },
+    {
+      "epoch": 3.64,
+      "learning_rate": 5.4545454545454545e-06,
+      "loss": 0.1899,
+      "step": 160
+    },
+    {
+      "epoch": 3.86,
+      "learning_rate": 4.5454545454545455e-06,
+      "loss": 0.1886,
+      "step": 170
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.9699248120300752,
+      "eval_loss": 0.1881999671459198,
+      "eval_runtime": 4.3782,
+      "eval_samples_per_second": 30.378,
+      "eval_steps_per_second": 1.37,
+      "step": 176
+    },
+    {
+      "epoch": 4.09,
+      "learning_rate": 3.6363636363636366e-06,
+      "loss": 0.1929,
+      "step": 180
+    },
+    {
+      "epoch": 4.32,
+      "learning_rate": 2.7272727272727272e-06,
+      "loss": 0.1909,
+      "step": 190
+    },
+    {
+      "epoch": 4.55,
+      "learning_rate": 1.8181818181818183e-06,
+      "loss": 0.1607,
+      "step": 200
+    },
+    {
+      "epoch": 4.77,
+      "learning_rate": 9.090909090909091e-07,
+      "loss": 0.1953,
+      "step": 210
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 0.0,
+      "loss": 0.1931,
+      "step": 220
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.9699248120300752,
+      "eval_loss": 0.18238767981529236,
+      "eval_runtime": 4.8076,
+      "eval_samples_per_second": 27.664,
+      "eval_steps_per_second": 1.248,
+      "step": 220
+    },
+    {
+      "epoch": 5.0,
+      "step": 220,
+      "total_flos": 4.006371770595533e+17,
+      "train_loss": 0.3897728649052707,
+      "train_runtime": 301.7547,
+      "train_samples_per_second": 17.133,
+      "train_steps_per_second": 0.729
+    }
+  ],
+  "max_steps": 220,
+  "num_train_epochs": 5,
+  "total_flos": 4.006371770595533e+17,
+  "trial_name": null,
+  "trial_params": null
+}