Upload trainer_state.json

trainer_state.json

@@ -0,0 +1,208 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 9.943181818181818,
+  "global_step": 7000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.71,
+      "learning_rate": 1.8579545454545456e-05,
+      "loss": 0.2388,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.955911435328983,
+      "eval_f1": 0.6304884742041712,
+      "eval_loss": 0.12564246356487274,
+      "eval_precision": 0.5805432722678459,
+      "eval_recall": 0.6898363609067708,
+      "eval_runtime": 23.1707,
+      "eval_samples_per_second": 215.703,
+      "eval_steps_per_second": 3.409,
+      "step": 704
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 1.715909090909091e-05,
+      "loss": 0.1435,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9644715470321716,
+      "eval_f1": 0.7096952908587256,
+      "eval_loss": 0.1017220988869667,
+      "eval_precision": 0.6586964905514847,
+      "eval_recall": 0.769253865785918,
+      "eval_runtime": 23.0705,
+      "eval_samples_per_second": 216.641,
+      "eval_steps_per_second": 3.424,
+      "step": 1408
+    },
+    {
+      "epoch": 2.13,
+      "learning_rate": 1.5738636363636364e-05,
+      "loss": 0.1235,
+      "step": 1500
+    },
+    {
+      "epoch": 2.84,
+      "learning_rate": 1.431818181818182e-05,
+      "loss": 0.1134,
+      "step": 2000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9680506083834383,
+      "eval_f1": 0.7407717535412742,
+      "eval_loss": 0.0903325304389,
+      "eval_precision": 0.6920469361147328,
+      "eval_recall": 0.7968773457438822,
+      "eval_runtime": 23.4345,
+      "eval_samples_per_second": 213.275,
+      "eval_steps_per_second": 3.371,
+      "step": 2112
+    },
+    {
+      "epoch": 3.55,
+      "learning_rate": 1.2897727272727274e-05,
+      "loss": 0.1064,
+      "step": 2500
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.9693671102499074,
+      "eval_f1": 0.758053270115744,
+      "eval_loss": 0.08625791221857071,
+      "eval_precision": 0.7077203489129019,
+      "eval_recall": 0.8160936796276835,
+      "eval_runtime": 23.121,
+      "eval_samples_per_second": 216.167,
+      "eval_steps_per_second": 3.417,
+      "step": 2816
+    },
+    {
+      "epoch": 4.26,
+      "learning_rate": 1.1477272727272729e-05,
+      "loss": 0.1014,
+      "step": 3000
+    },
+    {
+      "epoch": 4.97,
+      "learning_rate": 1.0056818181818183e-05,
+      "loss": 0.0982,
+      "step": 3500
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.9711851366369362,
+      "eval_f1": 0.7691875570535777,
+      "eval_loss": 0.08078513294458389,
+      "eval_precision": 0.7225593667546174,
+      "eval_recall": 0.8222489115748386,
+      "eval_runtime": 23.0774,
+      "eval_samples_per_second": 216.575,
+      "eval_steps_per_second": 3.423,
+      "step": 3520
+    },
+    {
+      "epoch": 5.68,
+      "learning_rate": 8.636363636363637e-06,
+      "loss": 0.0954,
+      "step": 4000
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.9720115122674038,
+      "eval_f1": 0.7794034890264491,
+      "eval_loss": 0.07870787382125854,
+      "eval_precision": 0.7332892124420913,
+      "eval_recall": 0.8317069509082721,
+      "eval_runtime": 23.1155,
+      "eval_samples_per_second": 216.218,
+      "eval_steps_per_second": 3.418,
+      "step": 4224
+    },
+    {
+      "epoch": 6.39,
+      "learning_rate": 7.215909090909091e-06,
+      "loss": 0.0924,
+      "step": 4500
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.972296469381358,
+      "eval_f1": 0.7826697563373359,
+      "eval_loss": 0.0774768590927124,
+      "eval_precision": 0.7352242744063324,
+      "eval_recall": 0.8366611619876896,
+      "eval_runtime": 23.1245,
+      "eval_samples_per_second": 216.135,
+      "eval_steps_per_second": 3.416,
+      "step": 4928
+    },
+    {
+      "epoch": 7.1,
+      "learning_rate": 5.795454545454546e-06,
+      "loss": 0.0918,
+      "step": 5000
+    },
+    {
+      "epoch": 7.81,
+      "learning_rate": 4.3750000000000005e-06,
+      "loss": 0.0901,
+      "step": 5500
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.9724332487960562,
+      "eval_f1": 0.7843714927048261,
+      "eval_loss": 0.07700537145137787,
+      "eval_precision": 0.7361421988150099,
+      "eval_recall": 0.8393634589400991,
+      "eval_runtime": 23.2661,
+      "eval_samples_per_second": 214.819,
+      "eval_steps_per_second": 3.395,
+      "step": 5632
+    },
+    {
+      "epoch": 8.52,
+      "learning_rate": 2.954545454545455e-06,
+      "loss": 0.0897,
+      "step": 6000
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.9725415324993588,
+      "eval_f1": 0.7841514726507715,
+      "eval_loss": 0.07681868225336075,
+      "eval_precision": 0.7357547045663904,
+      "eval_recall": 0.8393634589400991,
+      "eval_runtime": 23.0357,
+      "eval_samples_per_second": 216.968,
+      "eval_steps_per_second": 3.429,
+      "step": 6336
+    },
+    {
+      "epoch": 9.23,
+      "learning_rate": 1.5340909090909093e-06,
+      "loss": 0.0889,
+      "step": 6500
+    },
+    {
+      "epoch": 9.94,
+      "learning_rate": 1.1363636363636364e-07,
+      "loss": 0.0886,
+      "step": 7000
+    }
+  ],
+  "max_steps": 7040,
+  "num_train_epochs": 10,
+  "total_flos": 3165679668609024.0,
+  "trial_name": null,
+  "trial_params": null
+}