End of training

all_results.json

@@ -0,0 +1,18 @@
+{
+    "epoch": 10.0,
+    "eval_accuracy": 0.7019009565322678,
+    "eval_f1": 0.6654891304347826,
+    "eval_loss": 0.7599468231201172,
+    "eval_precision": 0.7660306537378793,
+    "eval_recall": 0.5882776843622388,
+    "eval_roc_auc": 0.7028302484311194,
+    "eval_runtime": 28.5103,
+    "eval_samples": 8259,
+    "eval_samples_per_second": 289.685,
+    "eval_steps_per_second": 6.454,
+    "train_loss": 0.4179859999087242,
+    "train_runtime": 3050.636,
+    "train_samples": 24774,
+    "train_samples_per_second": 81.209,
+    "train_steps_per_second": 1.806
+}

eval_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 10.0,
+    "eval_accuracy": 0.7019009565322678,
+    "eval_f1": 0.6654891304347826,
+    "eval_loss": 0.7599468231201172,
+    "eval_precision": 0.7660306537378793,
+    "eval_recall": 0.5882776843622388,
+    "eval_roc_auc": 0.7028302484311194,
+    "eval_runtime": 28.5103,
+    "eval_samples": 8259,
+    "eval_samples_per_second": 289.685,
+    "eval_steps_per_second": 6.454
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 10.0,
+    "train_loss": 0.4179859999087242,
+    "train_runtime": 3050.636,
+    "train_samples": 24774,
+    "train_samples_per_second": 81.209,
+    "train_steps_per_second": 1.806
+}

trainer_state.json

@@ -0,0 +1,215 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 10.0,
+  "global_step": 5510,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 8.101633393829401e-06,
+      "loss": 0.6213,
+      "step": 551
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6627921055817896,
+      "eval_f1": 0.6499937162247078,
+      "eval_loss": 0.5820437073707581,
+      "eval_precision": 0.6816025303110174,
+      "eval_recall": 0.6211866442469373,
+      "eval_roc_auc": 0.6631323846234687,
+      "eval_runtime": 28.6308,
+      "eval_samples_per_second": 288.465,
+      "eval_steps_per_second": 6.427,
+      "step": 551
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 7.203266787658802e-06,
+      "loss": 0.5585,
+      "step": 1102
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6689671873108124,
+      "eval_f1": 0.5894894894894895,
+      "eval_loss": 0.5801684856414795,
+      "eval_precision": 0.7861433720464558,
+      "eval_recall": 0.47153495075666585,
+      "eval_roc_auc": 0.670581928503333,
+      "eval_runtime": 28.9285,
+      "eval_samples_per_second": 285.497,
+      "eval_steps_per_second": 6.361,
+      "step": 1102
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 6.304900181488204e-06,
+      "loss": 0.5109,
+      "step": 1653
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.6885821528030028,
+      "eval_f1": 0.6392706872370266,
+      "eval_loss": 0.5686787962913513,
+      "eval_precision": 0.7681159420289855,
+      "eval_recall": 0.5474417487388902,
+      "eval_roc_auc": 0.689736499369445,
+      "eval_runtime": 28.9515,
+      "eval_samples_per_second": 285.27,
+      "eval_steps_per_second": 6.355,
+      "step": 1653
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 5.404900181488204e-06,
+      "loss": 0.4645,
+      "step": 2204
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.6972999152439763,
+      "eval_f1": 0.6525847693162868,
+      "eval_loss": 0.5875381827354431,
+      "eval_precision": 0.7741510056050115,
+      "eval_recall": 0.5640163343742494,
+      "eval_roc_auc": 0.6983900031246246,
+      "eval_runtime": 29.0279,
+      "eval_samples_per_second": 284.519,
+      "eval_steps_per_second": 6.339,
+      "step": 2204
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 4.504900181488204e-06,
+      "loss": 0.4161,
+      "step": 2755
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.709650078702022,
+      "eval_f1": 0.6926429120738272,
+      "eval_loss": 0.5819324254989624,
+      "eval_precision": 0.7425116790327013,
+      "eval_recall": 0.6490511650252222,
+      "eval_roc_auc": 0.7101456997001111,
+      "eval_runtime": 29.0292,
+      "eval_samples_per_second": 284.506,
+      "eval_steps_per_second": 6.338,
+      "step": 2755
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 3.6049001814882032e-06,
+      "loss": 0.3756,
+      "step": 3306
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.705775517617145,
+      "eval_f1": 0.6843335931410757,
+      "eval_loss": 0.6318923234939575,
+      "eval_precision": 0.7451202263083451,
+      "eval_recall": 0.6327167907758828,
+      "eval_roc_auc": 0.7063730438254414,
+      "eval_runtime": 29.1411,
+      "eval_samples_per_second": 283.414,
+      "eval_steps_per_second": 6.314,
+      "step": 3306
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 2.706533575317604e-06,
+      "loss": 0.3451,
+      "step": 3857
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.7025063567017799,
+      "eval_f1": 0.6842308186608405,
+      "eval_loss": 0.6542169451713562,
+      "eval_precision": 0.7357656163626313,
+      "eval_recall": 0.6394427095844343,
+      "eval_roc_auc": 0.7030221360422172,
+      "eval_runtime": 29.0336,
+      "eval_samples_per_second": 284.464,
+      "eval_steps_per_second": 6.337,
+      "step": 3857
+    },
+    {
+      "epoch": 8.0,
+      "learning_rate": 1.8065335753176044e-06,
+      "loss": 0.3144,
+      "step": 4408
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.701658796464463,
+      "eval_f1": 0.6680140123955807,
+      "eval_loss": 0.7204051613807678,
+      "eval_precision": 0.7606627799938631,
+      "eval_recall": 0.5954840259428297,
+      "eval_roc_auc": 0.7025271692214148,
+      "eval_runtime": 29.0414,
+      "eval_samples_per_second": 284.387,
+      "eval_steps_per_second": 6.336,
+      "step": 4408
+    },
+    {
+      "epoch": 9.0,
+      "learning_rate": 9.065335753176044e-07,
+      "loss": 0.2978,
+      "step": 4959
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.7032328369051943,
+      "eval_f1": 0.6755790866975514,
+      "eval_loss": 0.7168041467666626,
+      "eval_precision": 0.7523584905660378,
+      "eval_recall": 0.6130194571222676,
+      "eval_roc_auc": 0.7039706660611338,
+      "eval_runtime": 29.0774,
+      "eval_samples_per_second": 284.035,
+      "eval_steps_per_second": 6.328,
+      "step": 4959
+    },
+    {
+      "epoch": 10.0,
+      "learning_rate": 6.533575317604356e-09,
+      "loss": 0.2757,
+      "step": 5510
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.7019009565322678,
+      "eval_f1": 0.6654891304347826,
+      "eval_loss": 0.7599468231201172,
+      "eval_precision": 0.7660306537378793,
+      "eval_recall": 0.5882776843622388,
+      "eval_roc_auc": 0.7028302484311194,
+      "eval_runtime": 29.101,
+      "eval_samples_per_second": 283.804,
+      "eval_steps_per_second": 6.323,
+      "step": 5510
+    },
+    {
+      "epoch": 10.0,
+      "step": 5510,
+      "total_flos": 6.51831328548864e+16,
+      "train_loss": 0.4179859999087242,
+      "train_runtime": 3050.636,
+      "train_samples_per_second": 81.209,
+      "train_steps_per_second": 1.806
+    }
+  ],
+  "max_steps": 5510,
+  "num_train_epochs": 10,
+  "total_flos": 6.51831328548864e+16,
+  "trial_name": null,
+  "trial_params": null
+}