End of training

all_results.json

@@ -0,0 +1,18 @@
+{
+    "epoch": 10.0,
+    "eval_accuracy": 0.9712816116588084,
+    "eval_f1": 0.9722260605223159,
+    "eval_loss": 0.1769445687532425,
+    "eval_precision": 0.9777654252362423,
+    "eval_recall": 0.9667491068974993,
+    "eval_roc_auc": 0.9714697915439877,
+    "eval_runtime": 4.8942,
+    "eval_samples": 6999,
+    "eval_samples_per_second": 1430.059,
+    "eval_steps_per_second": 5.721,
+    "train_loss": 0.04638458222828128,
+    "train_runtime": 631.2261,
+    "train_samples": 27992,
+    "train_samples_per_second": 443.454,
+    "train_steps_per_second": 1.743
+}

eval_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 10.0,
+    "eval_accuracy": 0.9712816116588084,
+    "eval_f1": 0.9722260605223159,
+    "eval_loss": 0.1769445687532425,
+    "eval_precision": 0.9777654252362423,
+    "eval_recall": 0.9667491068974993,
+    "eval_roc_auc": 0.9714697915439877,
+    "eval_runtime": 4.8942,
+    "eval_samples": 6999,
+    "eval_samples_per_second": 1430.059,
+    "eval_steps_per_second": 5.721
+}

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6198ea86755b5d9fa890fbf49e6b1daf73a30e258f446dff4cf3633e73799530
+oid sha256:f8d7d8a448bdc399d8c8c4694b4048100e75695960a19b0fcd4f193c05059a3a
 size 267855533

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 10.0,
+    "train_loss": 0.04638458222828128,
+    "train_runtime": 631.2261,
+    "train_samples": 27992,
+    "train_samples_per_second": 443.454,
+    "train_steps_per_second": 1.743
+}

trainer_state.json

@@ -0,0 +1,215 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 10.0,
+  "global_step": 1100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 9e-05,
+      "loss": 0.2594,
+      "step": 110
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.951993141877411,
+      "eval_f1": 0.9531642040702537,
+      "eval_loss": 0.14524979889392853,
+      "eval_precision": 0.9671852899575671,
+      "eval_recall": 0.9395438307227261,
+      "eval_roc_auc": 0.9525100105994584,
+      "eval_runtime": 4.6691,
+      "eval_samples_per_second": 1498.989,
+      "eval_steps_per_second": 5.997,
+      "step": 110
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 8e-05,
+      "loss": 0.0966,
+      "step": 220
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9644234890698671,
+      "eval_f1": 0.9655839668279198,
+      "eval_loss": 0.1103191077709198,
+      "eval_precision": 0.971357063403782,
+      "eval_recall": 0.9598790876614455,
+      "eval_roc_auc": 0.9646121628783418,
+      "eval_runtime": 4.725,
+      "eval_samples_per_second": 1481.272,
+      "eval_steps_per_second": 5.926,
+      "step": 220
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 7e-05,
+      "loss": 0.0499,
+      "step": 330
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9639948564080583,
+      "eval_f1": 0.9652796913750344,
+      "eval_loss": 0.11932428181171417,
+      "eval_precision": 0.967946946670351,
+      "eval_recall": 0.962627095355867,
+      "eval_roc_auc": 0.9640516429160287,
+      "eval_runtime": 4.7987,
+      "eval_samples_per_second": 1458.529,
+      "eval_steps_per_second": 5.835,
+      "step": 330
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 6e-05,
+      "loss": 0.0251,
+      "step": 440
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.962280325760823,
+      "eval_f1": 0.9639639639639641,
+      "eval_loss": 0.12893760204315186,
+      "eval_precision": 0.9576891781936534,
+      "eval_recall": 0.9703215169002474,
+      "eval_roc_auc": 0.9619464727358379,
+      "eval_runtime": 4.816,
+      "eval_samples_per_second": 1453.283,
+      "eval_steps_per_second": 5.814,
+      "step": 440
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 5e-05,
+      "loss": 0.0132,
+      "step": 550
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.9659951421631662,
+      "eval_f1": 0.9673435784851812,
+      "eval_loss": 0.1495329588651657,
+      "eval_precision": 0.9660180871471636,
+      "eval_recall": 0.9686727122835944,
+      "eval_roc_auc": 0.9658839751894163,
+      "eval_runtime": 4.8435,
+      "eval_samples_per_second": 1445.041,
+      "eval_steps_per_second": 5.781,
+      "step": 550
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 4e-05,
+      "loss": 0.0086,
+      "step": 660
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.9684240605800829,
+      "eval_f1": 0.9692071896335517,
+      "eval_loss": 0.1759045422077179,
+      "eval_precision": 0.9830412662521198,
+      "eval_recall": 0.9557570761198131,
+      "eval_roc_auc": 0.968949966631335,
+      "eval_runtime": 4.8741,
+      "eval_samples_per_second": 1435.957,
+      "eval_steps_per_second": 5.745,
+      "step": 660
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 3e-05,
+      "loss": 0.0054,
+      "step": 770
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.9699957136733819,
+      "eval_f1": 0.9709141274238227,
+      "eval_loss": 0.15680807828903198,
+      "eval_precision": 0.9787768779670483,
+      "eval_recall": 0.9631766968947513,
+      "eval_roc_auc": 0.9702788246378518,
+      "eval_runtime": 4.886,
+      "eval_samples_per_second": 1432.464,
+      "eval_steps_per_second": 5.731,
+      "step": 770
+    },
+    {
+      "epoch": 8.0,
+      "learning_rate": 2e-05,
+      "loss": 0.0023,
+      "step": 880
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.9707101014430632,
+      "eval_f1": 0.9717280375120674,
+      "eval_loss": 0.17754127085208893,
+      "eval_precision": 0.9753599114064231,
+      "eval_recall": 0.9681231107447101,
+      "eval_roc_auc": 0.9708175077533074,
+      "eval_runtime": 4.8851,
+      "eval_samples_per_second": 1432.728,
+      "eval_steps_per_second": 5.732,
+      "step": 880
+    },
+    {
+      "epoch": 9.0,
+      "learning_rate": 1e-05,
+      "loss": 0.0023,
+      "step": 990
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.9709958565509359,
+      "eval_f1": 0.9718953343486086,
+      "eval_loss": 0.17516092956066132,
+      "eval_precision": 0.9793526785714286,
+      "eval_recall": 0.964550700741962,
+      "eval_roc_auc": 0.9712634456090762,
+      "eval_runtime": 4.8624,
+      "eval_samples_per_second": 1439.42,
+      "eval_steps_per_second": 5.759,
+      "step": 990
+    },
+    {
+      "epoch": 10.0,
+      "learning_rate": 0.0,
+      "loss": 0.0011,
+      "step": 1100
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.9712816116588084,
+      "eval_f1": 0.9722260605223159,
+      "eval_loss": 0.1769445687532425,
+      "eval_precision": 0.9777654252362423,
+      "eval_recall": 0.9667491068974993,
+      "eval_roc_auc": 0.9714697915439877,
+      "eval_runtime": 4.9001,
+      "eval_samples_per_second": 1428.327,
+      "eval_steps_per_second": 5.714,
+      "step": 1100
+    },
+    {
+      "epoch": 10.0,
+      "step": 1100,
+      "total_flos": 1.854013711589376e+16,
+      "train_loss": 0.04638458222828128,
+      "train_runtime": 631.2261,
+      "train_samples_per_second": 443.454,
+      "train_steps_per_second": 1.743
+    }
+  ],
+  "max_steps": 1100,
+  "num_train_epochs": 10,
+  "total_flos": 1.854013711589376e+16,
+  "trial_name": null,
+  "trial_params": null
+}