End of training

all_results.json

@@ -1,14 +1,14 @@
 {
-    "epoch": 10.53,
-    "eval_accuracy": 0.833371612310519,
-    "eval_f1": 0.8794946550048591,
-    "eval_loss": 0.5784164071083069,
-    "eval_precision": 0.8553875236294896,
-    "eval_recall": 0.905,
-    "eval_runtime": 3.53,
+    "epoch": 16.0,
+    "eval_accuracy": 0.8368167202572347,
+    "eval_f1": 0.8891074502089993,
+    "eval_loss": 0.6541090607643127,
+    "eval_precision": 0.8746976294146106,
+    "eval_recall": 0.904,
+    "eval_runtime": 3.562,
     "eval_samples": 54,
-    "eval_samples_per_second": 15.297,
-    "eval_steps_per_second": 1.133,
+    "eval_samples_per_second": 15.16,
+    "eval_steps_per_second": 1.123,
     "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": 0.50620361328125,
-    "train_runtime": 250.4274,
+    "train_loss": 0.43604583740234376,
+    "train_runtime": 307.9087,
     "train_samples": 150,
-    "train_samples_per_second": 6.389,
-    "train_steps_per_second": 1.597
+    "train_samples_per_second": 7.795,
+    "train_steps_per_second": 1.299
 }

eval_results.json

@@ -1,12 +1,12 @@
 {
-    "epoch": 10.53,
-    "eval_accuracy": 0.833371612310519,
-    "eval_f1": 0.8794946550048591,
-    "eval_loss": 0.5784164071083069,
-    "eval_precision": 0.8553875236294896,
-    "eval_recall": 0.905,
-    "eval_runtime": 3.53,
+    "epoch": 16.0,
+    "eval_accuracy": 0.8368167202572347,
+    "eval_f1": 0.8891074502089993,
+    "eval_loss": 0.6541090607643127,
+    "eval_precision": 0.8746976294146106,
+    "eval_recall": 0.904,
+    "eval_runtime": 3.562,
     "eval_samples": 54,
-    "eval_samples_per_second": 15.297,
-    "eval_steps_per_second": 1.133
+    "eval_samples_per_second": 15.16,
+    "eval_steps_per_second": 1.123
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09c539b37ae0e9a660c60e3ec980a33949184bb678cbc4ce1034cc7f63cfd9c6
+oid sha256:c62f2603023811174e7f8e06b32bf0110d49f234eba1b9e7230533d7919edd56
 size 501420883

runs/Aug24_19-24-22_bernini/1724520274.220852/events.out.tfevents.1724520274.bernini.13887.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:949a243e5b00cd5a646ba3ec282056929391036a03d8eac637597678e58c2956
+size 4665

runs/Aug24_19-24-22_bernini/events.out.tfevents.1724520274.bernini.13887.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0208a85de259cae48b3c66b9e998b2714993dfc255c4888c4664ffca6d913b95
+size 11945

runs/Aug24_19-24-22_bernini/events.out.tfevents.1724520591.bernini.13887.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04382d93bf526390c5db203e5f32b221f1f8bb40d1696422279b9ee810c47f77
+size 512

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 10.53,
-    "train_loss": 0.50620361328125,
-    "train_runtime": 250.4274,
+    "epoch": 16.0,
+    "train_loss": 0.43604583740234376,
+    "train_runtime": 307.9087,
     "train_samples": 150,
-    "train_samples_per_second": 6.389,
-    "train_steps_per_second": 1.597
+    "train_samples_per_second": 7.795,
+    "train_steps_per_second": 1.299
 }

trainer_state.json

@@ -1,217 +1,217 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 10.526315789473685,
+  "epoch": 16.0,
   "global_step": 400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.66,
-      "eval_accuracy": 0.5721175930179145,
-      "eval_f1": 0.34372003835091086,
-      "eval_loss": 1.351142406463623,
-      "eval_precision": 0.3301104972375691,
-      "eval_recall": 0.3585,
-      "eval_runtime": 3.6101,
-      "eval_samples_per_second": 14.958,
-      "eval_steps_per_second": 1.108,
+      "epoch": 1.0,
+      "eval_accuracy": 0.6092099219108865,
+      "eval_f1": 0.43809958885335776,
+      "eval_loss": 1.2830967903137207,
+      "eval_precision": 0.40328006728343146,
+      "eval_recall": 0.4795,
+      "eval_runtime": 3.5046,
+      "eval_samples_per_second": 15.408,
+      "eval_steps_per_second": 1.141,
       "step": 25
     },
     {
-      "epoch": 1.32,
-      "eval_accuracy": 0.7614836931557188,
-      "eval_f1": 0.7229437229437228,
-      "eval_loss": 0.905920684337616,
-      "eval_precision": 0.6964782205746061,
-      "eval_recall": 0.7515,
-      "eval_runtime": 3.5063,
-      "eval_samples_per_second": 15.401,
-      "eval_steps_per_second": 1.141,
+      "epoch": 2.0,
+      "eval_accuracy": 0.7748047772163528,
+      "eval_f1": 0.7586042065009561,
+      "eval_loss": 0.8177912831306458,
+      "eval_precision": 0.7266483516483516,
+      "eval_recall": 0.7935,
+      "eval_runtime": 3.5776,
+      "eval_samples_per_second": 15.094,
+      "eval_steps_per_second": 1.118,
       "step": 50
     },
     {
-      "epoch": 1.97,
-      "eval_accuracy": 0.7796279283417548,
-      "eval_f1": 0.7946449916327994,
-      "eval_loss": 0.7163704633712769,
-      "eval_precision": 0.7613376087952359,
-      "eval_recall": 0.831,
-      "eval_runtime": 3.5828,
-      "eval_samples_per_second": 15.072,
-      "eval_steps_per_second": 1.116,
+      "epoch": 3.0,
+      "eval_accuracy": 0.7990353697749196,
+      "eval_f1": 0.814344962185899,
+      "eval_loss": 0.6842699646949768,
+      "eval_precision": 0.7951405431157694,
+      "eval_recall": 0.8345,
+      "eval_runtime": 3.5751,
+      "eval_samples_per_second": 15.104,
+      "eval_steps_per_second": 1.119,
       "step": 75
     },
     {
-      "epoch": 2.63,
-      "eval_accuracy": 0.799265043638034,
-      "eval_f1": 0.8249158249158249,
-      "eval_loss": 0.6392571926116943,
-      "eval_precision": 0.7947173308619092,
-      "eval_recall": 0.8575,
-      "eval_runtime": 3.5968,
-      "eval_samples_per_second": 15.013,
-      "eval_steps_per_second": 1.112,
+      "epoch": 4.0,
+      "eval_accuracy": 0.8161460725769407,
+      "eval_f1": 0.8306801736613604,
+      "eval_loss": 0.6316555142402649,
+      "eval_precision": 0.8024231127679403,
+      "eval_recall": 0.861,
+      "eval_runtime": 3.6093,
+      "eval_samples_per_second": 14.962,
+      "eval_steps_per_second": 1.108,
       "step": 100
     },
     {
-      "epoch": 3.29,
-      "eval_accuracy": 0.8104042259990814,
-      "eval_f1": 0.8409859835669407,
-      "eval_loss": 0.5755508542060852,
-      "eval_precision": 0.813844714686623,
-      "eval_recall": 0.87,
-      "eval_runtime": 3.5975,
-      "eval_samples_per_second": 15.011,
-      "eval_steps_per_second": 1.112,
+      "epoch": 5.0,
+      "eval_accuracy": 0.8233807992650436,
+      "eval_f1": 0.8600191754554171,
+      "eval_loss": 0.5964206457138062,
+      "eval_precision": 0.8259668508287292,
+      "eval_recall": 0.897,
+      "eval_runtime": 3.5003,
+      "eval_samples_per_second": 15.427,
+      "eval_steps_per_second": 1.143,
       "step": 125
     },
     {
-      "epoch": 3.95,
-      "eval_accuracy": 0.8323380799265043,
-      "eval_f1": 0.8506134231416886,
-      "eval_loss": 0.5508233308792114,
-      "eval_precision": 0.8196569309225776,
-      "eval_recall": 0.884,
-      "eval_runtime": 3.6045,
-      "eval_samples_per_second": 14.981,
-      "eval_steps_per_second": 1.11,
+      "epoch": 6.0,
+      "eval_accuracy": 0.8207395498392283,
+      "eval_f1": 0.8444552293132735,
+      "eval_loss": 0.6049793362617493,
+      "eval_precision": 0.8203677510608204,
+      "eval_recall": 0.87,
+      "eval_runtime": 3.5639,
+      "eval_samples_per_second": 15.152,
+      "eval_steps_per_second": 1.122,
       "step": 150
     },
     {
-      "epoch": 4.61,
-      "eval_accuracy": 0.8327974276527331,
-      "eval_f1": 0.8600435097897026,
-      "eval_loss": 0.5458412170410156,
-      "eval_precision": 0.8324754328497894,
-      "eval_recall": 0.8895,
-      "eval_runtime": 3.5309,
-      "eval_samples_per_second": 15.294,
-      "eval_steps_per_second": 1.133,
+      "epoch": 7.0,
+      "eval_accuracy": 0.8168350941662839,
+      "eval_f1": 0.8474740149867052,
+      "eval_loss": 0.628131091594696,
+      "eval_precision": 0.8203088441740758,
+      "eval_recall": 0.8765,
+      "eval_runtime": 3.5404,
+      "eval_samples_per_second": 15.252,
+      "eval_steps_per_second": 1.13,
       "step": 175
     },
     {
-      "epoch": 5.26,
-      "eval_accuracy": 0.826596233348645,
-      "eval_f1": 0.8491160087188181,
-      "eval_loss": 0.5740342736244202,
-      "eval_precision": 0.8233912635039925,
-      "eval_recall": 0.8765,
-      "eval_runtime": 3.622,
-      "eval_samples_per_second": 14.909,
-      "eval_steps_per_second": 1.104,
+      "epoch": 8.0,
+      "eval_accuracy": 0.8234956361966008,
+      "eval_f1": 0.8708504967288586,
+      "eval_loss": 0.6227801442146301,
+      "eval_precision": 0.844851904090268,
+      "eval_recall": 0.8985,
+      "eval_runtime": 3.5716,
+      "eval_samples_per_second": 15.119,
+      "eval_steps_per_second": 1.12,
       "step": 200
     },
     {
-      "epoch": 5.92,
-      "eval_accuracy": 0.8361276986678916,
-      "eval_f1": 0.8709914320685433,
-      "eval_loss": 0.5719187259674072,
-      "eval_precision": 0.8532374100719424,
-      "eval_recall": 0.8895,
-      "eval_runtime": 3.5659,
-      "eval_samples_per_second": 15.143,
-      "eval_steps_per_second": 1.122,
+      "epoch": 9.0,
+      "eval_accuracy": 0.826596233348645,
+      "eval_f1": 0.8566561207106351,
+      "eval_loss": 0.621345579624176,
+      "eval_precision": 0.8345187292555714,
+      "eval_recall": 0.88,
+      "eval_runtime": 3.5239,
+      "eval_samples_per_second": 15.324,
+      "eval_steps_per_second": 1.135,
       "step": 225
     },
     {
-      "epoch": 6.58,
-      "eval_accuracy": 0.8263665594855305,
-      "eval_f1": 0.8736131210805596,
-      "eval_loss": 0.5435599684715271,
-      "eval_precision": 0.8438956197576887,
-      "eval_recall": 0.9055,
-      "eval_runtime": 3.5266,
-      "eval_samples_per_second": 15.312,
-      "eval_steps_per_second": 1.134,
+      "epoch": 10.0,
+      "eval_accuracy": 0.8356683509416628,
+      "eval_f1": 0.8702401164200824,
+      "eval_loss": 0.6172508597373962,
+      "eval_precision": 0.8450306170513424,
+      "eval_recall": 0.897,
+      "eval_runtime": 3.508,
+      "eval_samples_per_second": 15.394,
+      "eval_steps_per_second": 1.14,
       "step": 250
     },
     {
-      "epoch": 7.24,
-      "eval_accuracy": 0.8290078089113458,
-      "eval_f1": 0.8783914728682171,
-      "eval_loss": 0.5714461207389832,
-      "eval_precision": 0.8519736842105263,
-      "eval_recall": 0.9065,
-      "eval_runtime": 3.6124,
-      "eval_samples_per_second": 14.948,
-      "eval_steps_per_second": 1.107,
+      "epoch": 11.0,
+      "eval_accuracy": 0.8299265043638034,
+      "eval_f1": 0.8633826741082262,
+      "eval_loss": 0.6476383209228516,
+      "eval_precision": 0.8387553041018387,
+      "eval_recall": 0.8895,
+      "eval_runtime": 3.4928,
+      "eval_samples_per_second": 15.46,
+      "eval_steps_per_second": 1.145,
       "step": 275
     },
     {
-      "epoch": 7.89,
-      "eval_accuracy": 0.8280891134588884,
-      "eval_f1": 0.8791048406713695,
-      "eval_loss": 0.5853330492973328,
-      "eval_precision": 0.8559924206537186,
-      "eval_recall": 0.9035,
-      "eval_runtime": 3.6008,
-      "eval_samples_per_second": 14.997,
-      "eval_steps_per_second": 1.111,
+      "epoch": 12.0,
+      "eval_accuracy": 0.838194763435921,
+      "eval_f1": 0.8761018609206659,
+      "eval_loss": 0.6358577609062195,
+      "eval_precision": 0.8584452975047985,
+      "eval_recall": 0.8945,
+      "eval_runtime": 3.4999,
+      "eval_samples_per_second": 15.429,
+      "eval_steps_per_second": 1.143,
       "step": 300
     },
     {
-      "epoch": 8.55,
-      "eval_accuracy": 0.8389986219568213,
-      "eval_f1": 0.8807785888077859,
-      "eval_loss": 0.570177435874939,
-      "eval_precision": 0.8578199052132701,
-      "eval_recall": 0.905,
-      "eval_runtime": 3.5637,
-      "eval_samples_per_second": 15.153,
-      "eval_steps_per_second": 1.122,
+      "epoch": 13.0,
+      "eval_accuracy": 0.8394579696830501,
+      "eval_f1": 0.8911815278801277,
+      "eval_loss": 0.6469025611877441,
+      "eval_precision": 0.8759053597295993,
+      "eval_recall": 0.907,
+      "eval_runtime": 3.5529,
+      "eval_samples_per_second": 15.199,
+      "eval_steps_per_second": 1.126,
       "step": 325
     },
     {
-      "epoch": 9.21,
-      "eval_accuracy": 0.8418695452457511,
-      "eval_f1": 0.8775261748234722,
-      "eval_loss": 0.5666728019714355,
-      "eval_precision": 0.8552444233507357,
-      "eval_recall": 0.901,
-      "eval_runtime": 3.5809,
-      "eval_samples_per_second": 15.08,
-      "eval_steps_per_second": 1.117,
+      "epoch": 14.0,
+      "eval_accuracy": 0.8372760679834634,
+      "eval_f1": 0.8879606879606879,
+      "eval_loss": 0.651043176651001,
+      "eval_precision": 0.8729468599033816,
+      "eval_recall": 0.9035,
+      "eval_runtime": 3.5289,
+      "eval_samples_per_second": 15.302,
+      "eval_steps_per_second": 1.133,
       "step": 350
     },
     {
-      "epoch": 9.87,
-      "eval_accuracy": 0.8338309600367478,
-      "eval_f1": 0.8786773644541697,
-      "eval_loss": 0.5793057084083557,
-      "eval_precision": 0.8551822053951728,
-      "eval_recall": 0.9035,
-      "eval_runtime": 3.5472,
-      "eval_samples_per_second": 15.223,
-      "eval_steps_per_second": 1.128,
+      "epoch": 15.0,
+      "eval_accuracy": 0.8354386770785485,
+      "eval_f1": 0.8834476003917728,
+      "eval_loss": 0.6554981470108032,
+      "eval_precision": 0.8656429942418427,
+      "eval_recall": 0.902,
+      "eval_runtime": 3.5307,
+      "eval_samples_per_second": 15.294,
+      "eval_steps_per_second": 1.133,
       "step": 375
     },
     {
-      "epoch": 10.53,
-      "eval_accuracy": 0.833371612310519,
-      "eval_f1": 0.8794946550048591,
-      "eval_loss": 0.5784164071083069,
-      "eval_precision": 0.8553875236294896,
-      "eval_recall": 0.905,
-      "eval_runtime": 3.5919,
-      "eval_samples_per_second": 15.034,
-      "eval_steps_per_second": 1.114,
+      "epoch": 16.0,
+      "eval_accuracy": 0.8368167202572347,
+      "eval_f1": 0.8891074502089993,
+      "eval_loss": 0.6541090607643127,
+      "eval_precision": 0.8746976294146106,
+      "eval_recall": 0.904,
+      "eval_runtime": 3.5967,
+      "eval_samples_per_second": 15.014,
+      "eval_steps_per_second": 1.112,
       "step": 400
     },
     {
-      "epoch": 10.53,
+      "epoch": 16.0,
       "step": 400,
-      "total_flos": 416496442306560.0,
-      "train_loss": 0.50620361328125,
-      "train_runtime": 250.4274,
-      "train_samples_per_second": 6.389,
-      "train_steps_per_second": 1.597
+      "total_flos": 632652823756800.0,
+      "train_loss": 0.43604583740234376,
+      "train_runtime": 307.9087,
+      "train_samples_per_second": 7.795,
+      "train_steps_per_second": 1.299
     }
   ],
   "max_steps": 400,
-  "num_train_epochs": 11,
-  "total_flos": 416496442306560.0,
+  "num_train_epochs": 16,
+  "total_flos": 632652823756800.0,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b9738bcfd98ccbf71720f6b0ac66e4c20f1ded32caa28f7663edc931468381e
+oid sha256:37424644f6eb08c9f71a2b7231711a0ffb4a5590473227e020a76cca07225420
 size 2927