End of training

all_results.json

@@ -1,14 +1,14 @@
 {
-    "epoch": 26.32,
-    "eval_accuracy": 0.8407211759301791,
-    "eval_f1": 0.9107187266849044,
-    "eval_loss": 0.8859658241271973,
-    "eval_precision": 0.9059871350816427,
-    "eval_recall": 0.9155,
-    "eval_runtime": 3.6172,
+    "epoch": 13.16,
+    "eval_accuracy": 0.843706936150666,
+    "eval_f1": 0.8903638151425762,
+    "eval_loss": 0.6187416911125183,
+    "eval_precision": 0.875725338491296,
+    "eval_recall": 0.9055,
+    "eval_runtime": 3.5518,
     "eval_samples": 54,
-    "eval_samples_per_second": 14.929,
-    "eval_steps_per_second": 1.106,
+    "eval_samples_per_second": 15.203,
+    "eval_steps_per_second": 1.126,
     "predict_accuracy": 0.8218373936014088,
     "predict_f1": 0.9038133181559477,
     "predict_loss": 0.6888472437858582,
@@ -17,9 +17,9 @@
     "predict_runtime": 2.0596,
     "predict_samples_per_second": 8.74,
     "predict_steps_per_second": 0.971,
-    "train_loss": 0.23488603591918944,
-    "train_runtime": 622.7344,
+    "train_loss": 0.43045907592773436,
+    "train_runtime": 334.1747,
     "train_samples": 150,
-    "train_samples_per_second": 6.423,
-    "train_steps_per_second": 1.606
+    "train_samples_per_second": 5.985,
+    "train_steps_per_second": 1.496
 }

eval_results.json

@@ -1,12 +1,12 @@
 {
-    "epoch": 26.32,
-    "eval_accuracy": 0.8407211759301791,
-    "eval_f1": 0.9107187266849044,
-    "eval_loss": 0.8859658241271973,
-    "eval_precision": 0.9059871350816427,
-    "eval_recall": 0.9155,
-    "eval_runtime": 3.6172,
+    "epoch": 13.16,
+    "eval_accuracy": 0.843706936150666,
+    "eval_f1": 0.8903638151425762,
+    "eval_loss": 0.6187416911125183,
+    "eval_precision": 0.875725338491296,
+    "eval_recall": 0.9055,
+    "eval_runtime": 3.5518,
     "eval_samples": 54,
-    "eval_samples_per_second": 14.929,
-    "eval_steps_per_second": 1.106
+    "eval_samples_per_second": 15.203,
+    "eval_steps_per_second": 1.126
 }

runs/Aug24_20-01-03_bernini/events.out.tfevents.1724522476.bernini.3656.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:326a8e2567c92819a278b3aef5c7a9e8fbe155d9899827d2beb299c0a1190035
-size 8943
+oid sha256:1ebffba089df6720bc7855efeac0eaf724f5e919477468b3deba7cd7cdd9094d
+size 9297

runs/Aug24_20-01-03_bernini/events.out.tfevents.1724522819.bernini.3656.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3507ccb33cdf46ad0ff7b52bfbf0e43b717ac21ed19e9578203c6f9d468cea0f
+size 512

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 26.32,
-    "train_loss": 0.23488603591918944,
-    "train_runtime": 622.7344,
+    "epoch": 13.16,
+    "train_loss": 0.43045907592773436,
+    "train_runtime": 334.1747,
     "train_samples": 150,
-    "train_samples_per_second": 6.423,
-    "train_steps_per_second": 1.606
+    "train_samples_per_second": 5.985,
+    "train_steps_per_second": 1.496
 }

trainer_state.json

@@ -1,157 +1,151 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 26.31578947368421,
-  "global_step": 1000,
+  "epoch": 13.157894736842104,
+  "global_step": 500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
+    {
+      "epoch": 1.32,
+      "eval_accuracy": 0.7606798346348186,
+      "eval_f1": 0.7277096851718338,
+      "eval_loss": 0.9062727689743042,
+      "eval_precision": 0.7006015733456733,
+      "eval_recall": 0.757,
+      "eval_runtime": 3.59,
+      "eval_samples_per_second": 15.042,
+      "eval_steps_per_second": 1.114,
+      "step": 50
+    },
     {
       "epoch": 2.63,
-      "eval_accuracy": 0.798690858980248,
-      "eval_f1": 0.8287769784172662,
-      "eval_loss": 0.6110699772834778,
-      "eval_precision": 0.7963133640552995,
-      "eval_recall": 0.864,
-      "eval_runtime": 3.5435,
-      "eval_samples_per_second": 15.239,
-      "eval_steps_per_second": 1.129,
+      "eval_accuracy": 0.7967386311437759,
+      "eval_f1": 0.8242074927953891,
+      "eval_loss": 0.6386759281158447,
+      "eval_precision": 0.7929759704251387,
+      "eval_recall": 0.858,
+      "eval_runtime": 3.6147,
+      "eval_samples_per_second": 14.939,
+      "eval_steps_per_second": 1.107,
       "step": 100
     },
+    {
+      "epoch": 3.95,
+      "eval_accuracy": 0.825447864033073,
+      "eval_f1": 0.8485576923076923,
+      "eval_loss": 0.5691221356391907,
+      "eval_precision": 0.8171296296296297,
+      "eval_recall": 0.8825,
+      "eval_runtime": 3.5957,
+      "eval_samples_per_second": 15.018,
+      "eval_steps_per_second": 1.112,
+      "step": 150
+    },
     {
       "epoch": 5.26,
-      "eval_accuracy": 0.826596233348645,
-      "eval_f1": 0.8665358194308145,
-      "eval_loss": 0.5860626697540283,
-      "eval_precision": 0.850674373795761,
-      "eval_recall": 0.883,
-      "eval_runtime": 3.5697,
-      "eval_samples_per_second": 15.127,
-      "eval_steps_per_second": 1.121,
+      "eval_accuracy": 0.822347266881029,
+      "eval_f1": 0.8555474629764507,
+      "eval_loss": 0.5723332166671753,
+      "eval_precision": 0.831524303916942,
+      "eval_recall": 0.881,
+      "eval_runtime": 3.6337,
+      "eval_samples_per_second": 14.861,
+      "eval_steps_per_second": 1.101,
       "step": 200
     },
+    {
+      "epoch": 6.58,
+      "eval_accuracy": 0.8292374827744603,
+      "eval_f1": 0.8729388942774006,
+      "eval_loss": 0.5896942019462585,
+      "eval_precision": 0.847457627118644,
+      "eval_recall": 0.9,
+      "eval_runtime": 3.5978,
+      "eval_samples_per_second": 15.009,
+      "eval_steps_per_second": 1.112,
+      "step": 250
+    },
     {
       "epoch": 7.89,
-      "eval_accuracy": 0.8425585668350941,
-      "eval_f1": 0.8826268071551091,
-      "eval_loss": 0.5855879783630371,
-      "eval_precision": 0.865449303219606,
-      "eval_recall": 0.9005,
-      "eval_runtime": 3.5797,
-      "eval_samples_per_second": 15.085,
-      "eval_steps_per_second": 1.117,
+      "eval_accuracy": 0.8283187873220027,
+      "eval_f1": 0.874515503875969,
+      "eval_loss": 0.6122345924377441,
+      "eval_precision": 0.8482142857142857,
+      "eval_recall": 0.9025,
+      "eval_runtime": 3.5423,
+      "eval_samples_per_second": 15.244,
+      "eval_steps_per_second": 1.129,
       "step": 300
     },
+    {
+      "epoch": 9.21,
+      "eval_accuracy": 0.8392282958199357,
+      "eval_f1": 0.8740884783665532,
+      "eval_loss": 0.6045289635658264,
+      "eval_precision": 0.8505203405865658,
+      "eval_recall": 0.899,
+      "eval_runtime": 3.5491,
+      "eval_samples_per_second": 15.215,
+      "eval_steps_per_second": 1.127,
+      "step": 350
+    },
     {
       "epoch": 10.53,
-      "eval_accuracy": 0.8426734037666513,
-      "eval_f1": 0.8897131552917903,
-      "eval_loss": 0.6501617431640625,
-      "eval_precision": 0.8801369863013698,
-      "eval_recall": 0.8995,
-      "eval_runtime": 3.5894,
-      "eval_samples_per_second": 15.044,
-      "eval_steps_per_second": 1.114,
+      "eval_accuracy": 0.8446256316031235,
+      "eval_f1": 0.8851733464470125,
+      "eval_loss": 0.5662067532539368,
+      "eval_precision": 0.8708272859216255,
+      "eval_recall": 0.9,
+      "eval_runtime": 3.6229,
+      "eval_samples_per_second": 14.905,
+      "eval_steps_per_second": 1.104,
       "step": 400
     },
     {
-      "epoch": 13.16,
-      "learning_rate": 5e-06,
-      "loss": 0.4088,
-      "step": 500
+      "epoch": 11.84,
+      "eval_accuracy": 0.843706936150666,
+      "eval_f1": 0.888943488943489,
+      "eval_loss": 0.5973214507102966,
+      "eval_precision": 0.8739130434782608,
+      "eval_recall": 0.9045,
+      "eval_runtime": 3.6244,
+      "eval_samples_per_second": 14.899,
+      "eval_steps_per_second": 1.104,
+      "step": 450
     },
     {
       "epoch": 13.16,
-      "eval_accuracy": 0.8372760679834634,
-      "eval_f1": 0.8959365708622398,
-      "eval_loss": 0.7679007649421692,
-      "eval_precision": 0.888015717092338,
-      "eval_recall": 0.904,
-      "eval_runtime": 3.5844,
-      "eval_samples_per_second": 15.065,
-      "eval_steps_per_second": 1.116,
-      "step": 500
-    },
-    {
-      "epoch": 15.79,
-      "eval_accuracy": 0.8332567753789619,
-      "eval_f1": 0.8928395061728396,
-      "eval_loss": 0.8370674848556519,
-      "eval_precision": 0.8819512195121951,
-      "eval_recall": 0.904,
-      "eval_runtime": 3.4921,
-      "eval_samples_per_second": 15.463,
-      "eval_steps_per_second": 1.145,
-      "step": 600
-    },
-    {
-      "epoch": 18.42,
-      "eval_accuracy": 0.8336012861736335,
-      "eval_f1": 0.9036561264822135,
-      "eval_loss": 0.8320176601409912,
-      "eval_precision": 0.89306640625,
-      "eval_recall": 0.9145,
-      "eval_runtime": 3.5735,
-      "eval_samples_per_second": 15.111,
-      "eval_steps_per_second": 1.119,
-      "step": 700
-    },
-    {
-      "epoch": 21.05,
-      "eval_accuracy": 0.8340606338998622,
-      "eval_f1": 0.9051275699777063,
-      "eval_loss": 0.8494298458099365,
-      "eval_precision": 0.8969072164948454,
-      "eval_recall": 0.9135,
-      "eval_runtime": 3.6561,
-      "eval_samples_per_second": 14.77,
-      "eval_steps_per_second": 1.094,
-      "step": 800
-    },
-    {
-      "epoch": 23.68,
-      "eval_accuracy": 0.8385392742305926,
-      "eval_f1": 0.907196029776675,
-      "eval_loss": 0.8700249195098877,
-      "eval_precision": 0.9004926108374385,
-      "eval_recall": 0.914,
-      "eval_runtime": 3.5188,
-      "eval_samples_per_second": 15.346,
-      "eval_steps_per_second": 1.137,
-      "step": 900
-    },
-    {
-      "epoch": 26.32,
       "learning_rate": 0.0,
-      "loss": 0.061,
-      "step": 1000
+      "loss": 0.4305,
+      "step": 500
     },
     {
-      "epoch": 26.32,
-      "eval_accuracy": 0.8407211759301791,
-      "eval_f1": 0.9107187266849044,
-      "eval_loss": 0.8859658241271973,
-      "eval_precision": 0.9059871350816427,
-      "eval_recall": 0.9155,
-      "eval_runtime": 3.6186,
-      "eval_samples_per_second": 14.923,
-      "eval_steps_per_second": 1.105,
-      "step": 1000
+      "epoch": 13.16,
+      "eval_accuracy": 0.843706936150666,
+      "eval_f1": 0.8903638151425762,
+      "eval_loss": 0.6187416911125183,
+      "eval_precision": 0.875725338491296,
+      "eval_recall": 0.9055,
+      "eval_runtime": 3.6234,
+      "eval_samples_per_second": 14.903,
+      "eval_steps_per_second": 1.104,
+      "step": 500
     },
     {
-      "epoch": 26.32,
-      "step": 1000,
-      "total_flos": 1040713895079936.0,
-      "train_loss": 0.23488603591918944,
-      "train_runtime": 622.7344,
-      "train_samples_per_second": 6.423,
-      "train_steps_per_second": 1.606
+      "epoch": 13.16,
+      "step": 500,
+      "total_flos": 520356947539968.0,
+      "train_loss": 0.43045907592773436,
+      "train_runtime": 334.1747,
+      "train_samples_per_second": 5.985,
+      "train_steps_per_second": 1.496
     }
   ],
-  "max_steps": 1000,
-  "num_train_epochs": 27,
-  "total_flos": 1040713895079936.0,
+  "max_steps": 500,
+  "num_train_epochs": 14,
+  "total_flos": 520356947539968.0,
   "trial_name": null,
   "trial_params": null
 }