Training in progress, step 1

logs/events.out.tfevents.1761303109.ip-172-31-12-22.65348.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a26b4e358d856dc91484e54a4f45338e232c5a6f5ce514d326c78f3b94312f95
+size 5656

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d3da67edd943622b4f38b7c0f48a60c9a4d53ce9348a923e2d4ace9919015fa
+oid sha256:518220ce1fb2f29d6e762c7441e24a74cf3160780e885bd8cdddc4ce8f5d17a0
 size 46634832

training_artifacts/training_history.csv

@@ -1,12 +1,11 @@
-loss;grad_norm;learning_rate;epoch;step;eval_loss;eval_accuracy;eval_f1;eval_precision;eval_recall;eval_runtime;eval_samples_per_second;eval_steps_per_second;train_runtime;train_samples_per_second;train_steps_per_second;total_flos;train_loss
-0.6651;2.0492517948150635;3.3333333333333333e-06;0.2857142857142857;1;;;;;;;;;;;;;
-;;;0.2857142857142857;1;0.641178548336029;0.9002624671916011;0.0;0.0;0.0;5.428;70.191;4.422;;;;;
-;;;0.5714285714285714;2;0.6362672448158264;0.9238845144356955;0.0;0.0;0.0;5.345;71.282;4.49;;;;;
-;;;0.8571428571428571;3;0.6264415383338928;0.94750656167979;0.0;0.0;0.0;5.2138;73.076;4.603;;;;;
-;;;1.1428571428571428;4;0.6125248074531555;0.9606299212598425;0.0;0.0;0.0;5.2287;72.867;4.59;;;;;
-;;;1.4285714285714286;5;0.5944115519523621;0.968503937007874;0.0;0.0;0.0;5.3131;71.709;4.517;;;;;
-;;;1.7142857142857144;6;0.5722081661224365;0.973753280839895;0.0;0.0;0.0;5.3197;71.62;4.512;;;;;
-;;;2.0;7;0.5467000603675842;0.979002624671916;0.0;0.0;0.0;5.2338;72.796;4.586;;;;;
-;;;2.2857142857142856;8;0.5230435729026794;0.9816272965879265;0.0;0.0;0.0;5.3484;71.237;4.487;;;;;
-;;;2.571428571428571;9;0.5007050633430481;0.9816272965879265;0.0;0.0;0.0;5.4954;69.331;4.367;;;;;
-;;;2.571428571428571;9;;;;;;;;;92.7268;45.726;0.647;2140139840256.0;0.6428146097395155
+eval_loss;eval_accuracy;eval_f1;eval_precision;eval_recall;eval_runtime;eval_samples_per_second;eval_steps_per_second;epoch;step;train_runtime;train_samples_per_second;train_steps_per_second;total_flos;train_loss
+0.6739318370819092;0.8110236220472441;0.02702702702702703;0.014925373134328358;0.14285714285714285;5.4658;69.706;4.391;0.2857142857142857;1;;;;;
+0.6692991852760315;0.8372703412073491;0.0;0.0;0.0;5.4265;70.21;4.423;0.5714285714285714;2;;;;;
+0.659990131855011;0.9081364829396326;0.0;0.0;0.0;5.4075;70.457;4.438;0.8571428571428571;3;;;;;
+0.646578311920166;0.9658792650918635;0.0;0.0;0.0;5.484;69.475;4.376;1.1428571428571428;4;;;;;
+0.6292694211006165;0.979002624671916;0.0;0.0;0.0;5.5523;68.62;4.323;1.4285714285714286;5;;;;;
+0.6079225540161133;0.9816272965879265;0.0;0.0;0.0;5.4019;70.531;4.443;1.7142857142857144;6;;;;;
+0.5826576352119446;0.9816272965879265;0.0;0.0;0.0;5.3839;70.767;4.458;2.0;7;;;;;
+0.5580222606658936;0.9816272965879265;0.0;0.0;0.0;5.6743;67.145;4.23;2.2857142857142856;8;;;;;
+0.5341243743896484;0.9816272965879265;0.0;0.0;0.0;5.4883;69.421;4.373;2.571428571428571;9;;;;;
+;;;;;;;;2.571428571428571;9;93.9944;45.109;0.638;2164459611168.0;0.6654236051771376

training_artifacts/training_history.json

@@ -1,125 +1,118 @@
 [
   {
-    "loss": 0.6651,
-    "grad_norm": 2.0492517948150635,
-    "learning_rate": 3.3333333333333333e-06,
+    "eval_loss": 0.6739318370819092,
+    "eval_accuracy": 0.8110236220472441,
+    "eval_f1": 0.02702702702702703,
+    "eval_precision": 0.014925373134328358,
+    "eval_recall": 0.14285714285714285,
+    "eval_runtime": 5.4658,
+    "eval_samples_per_second": 69.706,
+    "eval_steps_per_second": 4.391,
     "epoch": 0.2857142857142857,
     "step": 1
   },
   {
-    "eval_loss": 0.641178548336029,
-    "eval_accuracy": 0.9002624671916011,
+    "eval_loss": 0.6692991852760315,
+    "eval_accuracy": 0.8372703412073491,
     "eval_f1": 0.0,
     "eval_precision": 0.0,
     "eval_recall": 0.0,
-    "eval_runtime": 5.428,
-    "eval_samples_per_second": 70.191,
-    "eval_steps_per_second": 4.422,
-    "epoch": 0.2857142857142857,
-    "step": 1
-  },
-  {
-    "eval_loss": 0.6362672448158264,
-    "eval_accuracy": 0.9238845144356955,
-    "eval_f1": 0.0,
-    "eval_precision": 0.0,
-    "eval_recall": 0.0,
-    "eval_runtime": 5.345,
-    "eval_samples_per_second": 71.282,
-    "eval_steps_per_second": 4.49,
+    "eval_runtime": 5.4265,
+    "eval_samples_per_second": 70.21,
+    "eval_steps_per_second": 4.423,
     "epoch": 0.5714285714285714,
     "step": 2
   },
   {
-    "eval_loss": 0.6264415383338928,
-    "eval_accuracy": 0.94750656167979,
+    "eval_loss": 0.659990131855011,
+    "eval_accuracy": 0.9081364829396326,
     "eval_f1": 0.0,
     "eval_precision": 0.0,
     "eval_recall": 0.0,
-    "eval_runtime": 5.2138,
-    "eval_samples_per_second": 73.076,
-    "eval_steps_per_second": 4.603,
+    "eval_runtime": 5.4075,
+    "eval_samples_per_second": 70.457,
+    "eval_steps_per_second": 4.438,
     "epoch": 0.8571428571428571,
     "step": 3
   },
   {
-    "eval_loss": 0.6125248074531555,
-    "eval_accuracy": 0.9606299212598425,
+    "eval_loss": 0.646578311920166,
+    "eval_accuracy": 0.9658792650918635,
     "eval_f1": 0.0,
     "eval_precision": 0.0,
     "eval_recall": 0.0,
-    "eval_runtime": 5.2287,
-    "eval_samples_per_second": 72.867,
-    "eval_steps_per_second": 4.59,
+    "eval_runtime": 5.484,
+    "eval_samples_per_second": 69.475,
+    "eval_steps_per_second": 4.376,
     "epoch": 1.1428571428571428,
     "step": 4
   },
   {
-    "eval_loss": 0.5944115519523621,
-    "eval_accuracy": 0.968503937007874,
+    "eval_loss": 0.6292694211006165,
+    "eval_accuracy": 0.979002624671916,
     "eval_f1": 0.0,
     "eval_precision": 0.0,
     "eval_recall": 0.0,
-    "eval_runtime": 5.3131,
-    "eval_samples_per_second": 71.709,
-    "eval_steps_per_second": 4.517,
+    "eval_runtime": 5.5523,
+    "eval_samples_per_second": 68.62,
+    "eval_steps_per_second": 4.323,
     "epoch": 1.4285714285714286,
     "step": 5
   },
   {
-    "eval_loss": 0.5722081661224365,
-    "eval_accuracy": 0.973753280839895,
+    "eval_loss": 0.6079225540161133,
+    "eval_accuracy": 0.9816272965879265,
     "eval_f1": 0.0,
     "eval_precision": 0.0,
     "eval_recall": 0.0,
-    "eval_runtime": 5.3197,
-    "eval_samples_per_second": 71.62,
-    "eval_steps_per_second": 4.512,
+    "eval_runtime": 5.4019,
+    "eval_samples_per_second": 70.531,
+    "eval_steps_per_second": 4.443,
     "epoch": 1.7142857142857144,
     "step": 6
   },
   {
-    "eval_loss": 0.5467000603675842,
-    "eval_accuracy": 0.979002624671916,
+    "eval_loss": 0.5826576352119446,
+    "eval_accuracy": 0.9816272965879265,
     "eval_f1": 0.0,
     "eval_precision": 0.0,
     "eval_recall": 0.0,
-    "eval_runtime": 5.2338,
-    "eval_samples_per_second": 72.796,
-    "eval_steps_per_second": 4.586,
+    "eval_runtime": 5.3839,
+    "eval_samples_per_second": 70.767,
+    "eval_steps_per_second": 4.458,
     "epoch": 2.0,
     "step": 7
   },
   {
-    "eval_loss": 0.5230435729026794,
+    "eval_loss": 0.5580222606658936,
     "eval_accuracy": 0.9816272965879265,
     "eval_f1": 0.0,
     "eval_precision": 0.0,
     "eval_recall": 0.0,
-    "eval_runtime": 5.3484,
-    "eval_samples_per_second": 71.237,
-    "eval_steps_per_second": 4.487,
+    "eval_runtime": 5.6743,
+    "eval_samples_per_second": 67.145,
+    "eval_steps_per_second": 4.23,
     "epoch": 2.2857142857142856,
     "step": 8
   },
   {
-    "eval_loss": 0.5007050633430481,
+    "eval_loss": 0.5341243743896484,
     "eval_accuracy": 0.9816272965879265,
     "eval_f1": 0.0,
     "eval_precision": 0.0,
     "eval_recall": 0.0,
-    "eval_runtime": 5.4954,
-    "eval_samples_per_second": 69.331,
-    "eval_steps_per_second": 4.367,
+    "eval_runtime": 5.4883,
+    "eval_samples_per_second": 69.421,
+    "eval_steps_per_second": 4.373,
     "epoch": 2.571428571428571,
     "step": 9
   },
   {
-    "train_runtime": 92.7268,
-    "train_samples_per_second": 45.726,
-    "train_steps_per_second": 0.647,
-    "total_flos": 2140139840256.0,
-    "train_loss": 0.6428146097395155,
+    "train_runtime": 93.9944,
+    "train_samples_per_second": 45.109,
+    "train_steps_per_second": 0.638,
+    "total_flos": 2164459611168.0,
+    "train_loss": 0.6654236051771376,
     "epoch": 2.571428571428571,
     "step": 9
   }