End of training

all_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 1.0,
-    "train_loss": 8.903275526092911e-05,
-    "train_runtime": 1219.8966,
-    "train_samples": 147398,
-    "train_samples_per_second": 120.828,
-    "train_steps_per_second": 1.889
+    "train_loss": 9.778687784283113e-05,
+    "train_runtime": 1221.5492,
+    "train_samples": 147488,
+    "train_samples_per_second": 120.738,
+    "train_steps_per_second": 1.887
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da9572ed85cbe2d90b1dc5d5957cb7842fee5159f78cb999a6b0ba94be16fe00
+oid sha256:940f1b23272e881ef6760e16562085c4ae9c6f88f2983ee47516ba3f7250fb47
 size 891650871

runs/Nov18_20-49-42_DESKTOP-FPB11SM/1637265142.4499304/events.out.tfevents.1637265142.DESKTOP-FPB11SM.12768.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8790a0ea79422a2bf94318e775accf1511069e624b28cbe6ab5152f7318c0d65
+size 4740

runs/Nov18_20-49-42_DESKTOP-FPB11SM/events.out.tfevents.1637265142.DESKTOP-FPB11SM.12768.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce5c472c4696250f46fc77e7ebc71508c69d6004997018377ba9a6aed330ebdc
+size 11606

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 1.0,
-    "train_loss": 8.903275526092911e-05,
-    "train_runtime": 1219.8966,
-    "train_samples": 147398,
-    "train_samples_per_second": 120.828,
-    "train_steps_per_second": 1.889
+    "train_loss": 9.778687784283113e-05,
+    "train_runtime": 1221.5492,
+    "train_samples": 147488,
+    "train_samples_per_second": 120.738,
+    "train_steps_per_second": 1.887
 }

trainer_state.json

@@ -2,300 +2,300 @@
   "best_metric": null,
   "best_model_checkpoint": null,
   "epoch": 1.0,
-  "global_step": 2304,
+  "global_step": 2305,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 0.02,
-      "learning_rate": 4.891493055555556e-05,
-      "loss": 0.0,
+      "learning_rate": 4.8915401301518446e-05,
+      "loss": 0.001,
       "step": 50
     },
     {
       "epoch": 0.04,
-      "learning_rate": 4.782986111111111e-05,
-      "loss": 0.0006,
+      "learning_rate": 4.7830802603036875e-05,
+      "loss": 0.0003,
       "step": 100
     },
     {
       "epoch": 0.07,
-      "learning_rate": 4.674479166666667e-05,
+      "learning_rate": 4.674620390455532e-05,
       "loss": 0.0006,
       "step": 150
     },
     {
       "epoch": 0.09,
-      "learning_rate": 4.5659722222222224e-05,
-      "loss": 0.0,
+      "learning_rate": 4.5661605206073755e-05,
+      "loss": 0.0001,
       "step": 200
     },
     {
       "epoch": 0.11,
-      "learning_rate": 4.457465277777778e-05,
-      "loss": 0.0,
+      "learning_rate": 4.45770065075922e-05,
+      "loss": 0.0003,
       "step": 250
     },
     {
       "epoch": 0.13,
-      "learning_rate": 4.3489583333333334e-05,
-      "loss": 0.0001,
+      "learning_rate": 4.349240780911063e-05,
+      "loss": 0.0003,
       "step": 300
     },
     {
       "epoch": 0.15,
-      "learning_rate": 4.240451388888889e-05,
+      "learning_rate": 4.240780911062907e-05,
       "loss": 0.0,
       "step": 350
     },
     {
       "epoch": 0.17,
-      "learning_rate": 4.1319444444444445e-05,
+      "learning_rate": 4.132321041214751e-05,
       "loss": 0.0,
       "step": 400
     },
     {
       "epoch": 0.2,
-      "learning_rate": 4.0234375e-05,
-      "loss": 0.0002,
+      "learning_rate": 4.0238611713665944e-05,
+      "loss": 0.0,
       "step": 450
     },
     {
       "epoch": 0.22,
-      "learning_rate": 3.914930555555556e-05,
-      "loss": 0.0001,
+      "learning_rate": 3.915401301518438e-05,
+      "loss": 0.0,
       "step": 500
     },
     {
       "epoch": 0.24,
-      "learning_rate": 3.806423611111111e-05,
+      "learning_rate": 3.8069414316702824e-05,
       "loss": 0.0,
       "step": 550
     },
     {
       "epoch": 0.26,
-      "learning_rate": 3.697916666666667e-05,
+      "learning_rate": 3.698481561822126e-05,
       "loss": 0.0,
       "step": 600
     },
     {
       "epoch": 0.28,
-      "learning_rate": 3.589409722222222e-05,
-      "loss": 0.0002,
+      "learning_rate": 3.59002169197397e-05,
+      "loss": 0.0,
       "step": 650
     },
     {
       "epoch": 0.3,
-      "learning_rate": 3.4809027777777784e-05,
-      "loss": 0.0,
+      "learning_rate": 3.481561822125813e-05,
+      "loss": 0.0002,
       "step": 700
     },
     {
       "epoch": 0.33,
-      "learning_rate": 3.372395833333333e-05,
+      "learning_rate": 3.3731019522776576e-05,
       "loss": 0.0,
       "step": 750
     },
     {
       "epoch": 0.35,
-      "learning_rate": 3.263888888888889e-05,
-      "loss": 0.0002,
+      "learning_rate": 3.264642082429501e-05,
+      "loss": 0.0001,
       "step": 800
     },
     {
       "epoch": 0.37,
-      "learning_rate": 3.155381944444444e-05,
-      "loss": 0.0002,
+      "learning_rate": 3.156182212581345e-05,
+      "loss": 0.0,
       "step": 850
     },
     {
       "epoch": 0.39,
-      "learning_rate": 3.0468750000000002e-05,
-      "loss": 0.0001,
+      "learning_rate": 3.0477223427331893e-05,
+      "loss": 0.0,
       "step": 900
     },
     {
       "epoch": 0.41,
-      "learning_rate": 2.938368055555556e-05,
-      "loss": 0.0002,
+      "learning_rate": 2.9392624728850326e-05,
+      "loss": 0.0,
       "step": 950
     },
     {
       "epoch": 0.43,
-      "learning_rate": 2.8298611111111113e-05,
+      "learning_rate": 2.8308026030368766e-05,
       "loss": 0.0,
       "step": 1000
     },
     {
       "epoch": 0.46,
-      "learning_rate": 2.721354166666667e-05,
-      "loss": 0.0001,
+      "learning_rate": 2.7223427331887202e-05,
+      "loss": 0.0,
       "step": 1050
     },
     {
       "epoch": 0.48,
-      "learning_rate": 2.6128472222222223e-05,
+      "learning_rate": 2.6138828633405642e-05,
       "loss": 0.0,
       "step": 1100
     },
     {
       "epoch": 0.5,
-      "learning_rate": 2.504340277777778e-05,
+      "learning_rate": 2.505422993492408e-05,
       "loss": 0.0,
       "step": 1150
     },
     {
       "epoch": 0.52,
-      "learning_rate": 2.3958333333333334e-05,
+      "learning_rate": 2.3969631236442515e-05,
       "loss": 0.0,
       "step": 1200
     },
     {
       "epoch": 0.54,
-      "learning_rate": 2.287326388888889e-05,
+      "learning_rate": 2.2885032537960955e-05,
       "loss": 0.0,
       "step": 1250
     },
     {
       "epoch": 0.56,
-      "learning_rate": 2.1788194444444445e-05,
+      "learning_rate": 2.1800433839479395e-05,
       "loss": 0.0,
       "step": 1300
     },
     {
       "epoch": 0.59,
-      "learning_rate": 2.0703125e-05,
+      "learning_rate": 2.0715835140997834e-05,
       "loss": 0.0,
       "step": 1350
     },
     {
       "epoch": 0.61,
-      "learning_rate": 1.9618055555555555e-05,
+      "learning_rate": 1.963123644251627e-05,
       "loss": 0.0002,
       "step": 1400
     },
     {
       "epoch": 0.63,
-      "learning_rate": 1.853298611111111e-05,
-      "loss": 0.0003,
+      "learning_rate": 1.8546637744034707e-05,
+      "loss": 0.0002,
       "step": 1450
     },
     {
       "epoch": 0.65,
-      "learning_rate": 1.7447916666666666e-05,
+      "learning_rate": 1.7462039045553147e-05,
       "loss": 0.0,
       "step": 1500
     },
     {
       "epoch": 0.67,
-      "learning_rate": 1.636284722222222e-05,
+      "learning_rate": 1.6377440347071584e-05,
       "loss": 0.0001,
       "step": 1550
     },
     {
       "epoch": 0.69,
-      "learning_rate": 1.527777777777778e-05,
+      "learning_rate": 1.5292841648590023e-05,
       "loss": 0.0,
       "step": 1600
     },
     {
       "epoch": 0.72,
-      "learning_rate": 1.4192708333333336e-05,
+      "learning_rate": 1.420824295010846e-05,
       "loss": 0.0,
       "step": 1650
     },
     {
       "epoch": 0.74,
-      "learning_rate": 1.3107638888888891e-05,
-      "loss": 0.0,
+      "learning_rate": 1.3123644251626898e-05,
+      "loss": 0.0004,
       "step": 1700
     },
     {
       "epoch": 0.76,
-      "learning_rate": 1.2022569444444445e-05,
-      "loss": 0.0,
+      "learning_rate": 1.2039045553145336e-05,
+      "loss": 0.0001,
       "step": 1750
     },
     {
       "epoch": 0.78,
-      "learning_rate": 1.09375e-05,
+      "learning_rate": 1.0954446854663774e-05,
       "loss": 0.0,
       "step": 1800
     },
     {
       "epoch": 0.8,
-      "learning_rate": 9.852430555555555e-06,
-      "loss": 0.0,
+      "learning_rate": 9.869848156182213e-06,
+      "loss": 0.0001,
       "step": 1850
     },
     {
       "epoch": 0.82,
-      "learning_rate": 8.76736111111111e-06,
+      "learning_rate": 8.78524945770065e-06,
       "loss": 0.0,
       "step": 1900
     },
     {
       "epoch": 0.85,
-      "learning_rate": 7.682291666666668e-06,
+      "learning_rate": 7.70065075921909e-06,
       "loss": 0.0,
       "step": 1950
     },
     {
       "epoch": 0.87,
-      "learning_rate": 6.597222222222223e-06,
+      "learning_rate": 6.616052060737528e-06,
       "loss": 0.0,
       "step": 2000
     },
     {
       "epoch": 0.89,
-      "learning_rate": 5.512152777777778e-06,
+      "learning_rate": 5.531453362255966e-06,
       "loss": 0.0,
       "step": 2050
     },
     {
       "epoch": 0.91,
-      "learning_rate": 4.427083333333334e-06,
+      "learning_rate": 4.446854663774403e-06,
       "loss": 0.0,
       "step": 2100
     },
     {
       "epoch": 0.93,
-      "learning_rate": 3.342013888888889e-06,
+      "learning_rate": 3.362255965292842e-06,
       "loss": 0.0,
       "step": 2150
     },
     {
       "epoch": 0.95,
-      "learning_rate": 2.2569444444444443e-06,
-      "loss": 0.0003,
+      "learning_rate": 2.27765726681128e-06,
+      "loss": 0.0001,
       "step": 2200
     },
     {
       "epoch": 0.98,
-      "learning_rate": 1.1718750000000001e-06,
+      "learning_rate": 1.193058568329718e-06,
       "loss": 0.0,
       "step": 2250
     },
     {
       "epoch": 1.0,
-      "learning_rate": 8.680555555555556e-08,
+      "learning_rate": 1.0845986984815619e-07,
       "loss": 0.0,
       "step": 2300
     },
     {
       "epoch": 1.0,
-      "step": 2304,
-      "total_flos": 1.824601497550848e+16,
-      "train_loss": 8.903275526092911e-05,
-      "train_runtime": 1219.8966,
-      "train_samples_per_second": 120.828,
-      "train_steps_per_second": 1.889
+      "step": 2305,
+      "total_flos": 1.828765247127552e+16,
+      "train_loss": 9.778687784283113e-05,
+      "train_runtime": 1221.5492,
+      "train_samples_per_second": 120.738,
+      "train_steps_per_second": 1.887
     }
   ],
-  "max_steps": 2304,
+  "max_steps": 2305,
   "num_train_epochs": 1,
-  "total_flos": 1.824601497550848e+16,
+  "total_flos": 1.828765247127552e+16,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37965f20e4224692e9ce75eebe5b5077a2ec83505220564aa7c847843215e9e0
+oid sha256:de8bf22c818a83c8a830b1d4ce820d7be4b116abfa1e76aceafa60c7dd2d8c03
 size 2991