Training in progress, epoch 1

all_results.json

@@ -3,15 +3,15 @@
     "eval_accuracy": 0.9032258064516129,
     "eval_auc": 0.5,
     "eval_f1": 0.4745762711864407,
-    "eval_loss": 0.33827999234199524,
+    "eval_loss": 0.3023151159286499,
     "eval_precision": 0.9032258064516129,
     "eval_recall": 1.0,
-    "eval_runtime": 1.0789,
-    "eval_samples_per_second": 172.394,
-    "eval_steps_per_second": 2.781,
+    "eval_runtime": 0.6301,
+    "eval_samples_per_second": 295.208,
+    "eval_steps_per_second": 4.761,
     "total_flos": 1.8691703717363712e+17,
-    "train_loss": 0.28762030601501465,
-    "train_runtime": 70.3105,
-    "train_samples_per_second": 124.59,
-    "train_steps_per_second": 0.427
+    "train_loss": 0.2957582632700602,
+    "train_runtime": 47.4143,
+    "train_samples_per_second": 184.754,
+    "train_steps_per_second": 0.633
 }

eval_results.json

@@ -3,10 +3,10 @@
     "eval_accuracy": 0.9032258064516129,
     "eval_auc": 0.5,
     "eval_f1": 0.4745762711864407,
-    "eval_loss": 0.33827999234199524,
+    "eval_loss": 0.3023151159286499,
     "eval_precision": 0.9032258064516129,
     "eval_recall": 1.0,
-    "eval_runtime": 1.0789,
-    "eval_samples_per_second": 172.394,
-    "eval_steps_per_second": 2.781
+    "eval_runtime": 0.6301,
+    "eval_samples_per_second": 295.208,
+    "eval_steps_per_second": 4.761
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1dd2e3b6404034899d709305ce15a3ca43637919f5098d55edd7a72091de6aad
+oid sha256:4d07e7c41d6e3d022c28c3c64002a95b5a168904c992038f6dda631436efb1a4
 size 110342832

runs/May24_17-00-00_RTX3090/events.out.tfevents.1716537663.RTX3090.3776938.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:362058ec16218e8a98099fc83235a96e08487274902ee254d0b5a2f27661afda
+size 597

runs/May27_15-58-23_RTX3090/events.out.tfevents.1716793114.RTX3090.4190332.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86818b56df27abc12eeaacdac861f509e01147a2e1fa722bfa93fdbf0b61610d
+size 5277

runs/May27_16-00-38_RTX3090/events.out.tfevents.1716793245.RTX3090.4192365.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:283cd10d3002d8958503306ee9f92d2fa7ba78d98b4bc4f8627db85051b32e12
+size 5786

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 8.571428571428571,
     "total_flos": 1.8691703717363712e+17,
-    "train_loss": 0.28762030601501465,
-    "train_runtime": 70.3105,
-    "train_samples_per_second": 124.59,
-    "train_steps_per_second": 0.427
+    "train_loss": 0.2957582632700602,
+    "train_runtime": 47.4143,
+    "train_samples_per_second": 184.754,
+    "train_steps_per_second": 0.633
 }

trainer_state.json

@@ -13,12 +13,12 @@
       "eval_accuracy": 0.9032258064516129,
       "eval_auc": 0.5,
       "eval_f1": 0.4745762711864407,
-      "eval_loss": 0.33827999234199524,
+      "eval_loss": 0.3023151159286499,
       "eval_precision": 0.9032258064516129,
       "eval_recall": 1.0,
-      "eval_runtime": 1.0242,
-      "eval_samples_per_second": 181.602,
-      "eval_steps_per_second": 2.929,
+      "eval_runtime": 0.5993,
+      "eval_samples_per_second": 310.347,
+      "eval_steps_per_second": 5.006,
       "step": 3
     },
     {
@@ -26,19 +26,19 @@
       "eval_accuracy": 0.9032258064516129,
       "eval_auc": 0.5,
       "eval_f1": 0.4745762711864407,
-      "eval_loss": 0.3653673529624939,
+      "eval_loss": 0.36768200993537903,
       "eval_precision": 0.9032258064516129,
       "eval_recall": 1.0,
-      "eval_runtime": 1.0375,
-      "eval_samples_per_second": 179.274,
-      "eval_steps_per_second": 2.892,
+      "eval_runtime": 0.6162,
+      "eval_samples_per_second": 301.832,
+      "eval_steps_per_second": 4.868,
       "step": 7
     },
     {
       "epoch": 2.857142857142857,
-      "grad_norm": 4.537749767303467,
+      "grad_norm": 2.596181631088257,
       "learning_rate": 3.7037037037037037e-05,
-      "loss": 0.3833,
+      "loss": 0.4028,
       "step": 10
     },
     {
@@ -46,12 +46,12 @@
       "eval_accuracy": 0.9032258064516129,
       "eval_auc": 0.5,
       "eval_f1": 0.4745762711864407,
-      "eval_loss": 0.3421719968318939,
+      "eval_loss": 0.32757532596588135,
       "eval_precision": 0.9032258064516129,
       "eval_recall": 1.0,
-      "eval_runtime": 1.0114,
-      "eval_samples_per_second": 183.911,
-      "eval_steps_per_second": 2.966,
+      "eval_runtime": 0.6008,
+      "eval_samples_per_second": 309.59,
+      "eval_steps_per_second": 4.993,
       "step": 10
     },
     {
@@ -59,12 +59,12 @@
       "eval_accuracy": 0.9032258064516129,
       "eval_auc": 0.5,
       "eval_f1": 0.4745762711864407,
-      "eval_loss": 0.3555563986301422,
+      "eval_loss": 0.32863086462020874,
       "eval_precision": 0.9032258064516129,
       "eval_recall": 1.0,
-      "eval_runtime": 1.0242,
-      "eval_samples_per_second": 181.606,
-      "eval_steps_per_second": 2.929,
+      "eval_runtime": 0.6313,
+      "eval_samples_per_second": 294.647,
+      "eval_steps_per_second": 4.752,
       "step": 14
     },
     {
@@ -72,19 +72,19 @@
       "eval_accuracy": 0.9032258064516129,
       "eval_auc": 0.5,
       "eval_f1": 0.4745762711864407,
-      "eval_loss": 0.3424948453903198,
+      "eval_loss": 0.3271201252937317,
       "eval_precision": 0.9032258064516129,
       "eval_recall": 1.0,
-      "eval_runtime": 1.0046,
-      "eval_samples_per_second": 185.14,
-      "eval_steps_per_second": 2.986,
+      "eval_runtime": 0.6283,
+      "eval_samples_per_second": 296.051,
+      "eval_steps_per_second": 4.775,
       "step": 17
     },
     {
       "epoch": 5.714285714285714,
-      "grad_norm": 1.4052001237869263,
+      "grad_norm": 1.759938359260559,
       "learning_rate": 1.8518518518518518e-05,
-      "loss": 0.2492,
+      "loss": 0.2494,
       "step": 20
     },
     {
@@ -92,12 +92,12 @@
       "eval_accuracy": 0.9032258064516129,
       "eval_auc": 0.5,
       "eval_f1": 0.4745762711864407,
-      "eval_loss": 0.3400775194168091,
+      "eval_loss": 0.32589343190193176,
       "eval_precision": 0.9032258064516129,
       "eval_recall": 1.0,
-      "eval_runtime": 1.0288,
-      "eval_samples_per_second": 180.792,
-      "eval_steps_per_second": 2.916,
+      "eval_runtime": 0.607,
+      "eval_samples_per_second": 306.423,
+      "eval_steps_per_second": 4.942,
       "step": 21
     },
     {
@@ -105,12 +105,12 @@
       "eval_accuracy": 0.9032258064516129,
       "eval_auc": 0.5,
       "eval_f1": 0.4745762711864407,
-      "eval_loss": 0.35429030656814575,
+      "eval_loss": 0.3279106020927429,
       "eval_precision": 0.9032258064516129,
       "eval_recall": 1.0,
-      "eval_runtime": 0.999,
-      "eval_samples_per_second": 186.195,
-      "eval_steps_per_second": 3.003,
+      "eval_runtime": 0.6103,
+      "eval_samples_per_second": 304.771,
+      "eval_steps_per_second": 4.916,
       "step": 24
     },
     {
@@ -118,19 +118,19 @@
       "eval_accuracy": 0.9032258064516129,
       "eval_auc": 0.5,
       "eval_f1": 0.4745762711864407,
-      "eval_loss": 0.3571774363517761,
+      "eval_loss": 0.3266947269439697,
       "eval_precision": 0.9032258064516129,
       "eval_recall": 1.0,
-      "eval_runtime": 1.0317,
-      "eval_samples_per_second": 180.286,
-      "eval_steps_per_second": 2.908,
+      "eval_runtime": 0.6353,
+      "eval_samples_per_second": 292.77,
+      "eval_steps_per_second": 4.722,
       "step": 28
     },
     {
       "epoch": 8.571428571428571,
-      "grad_norm": 1.283613920211792,
+      "grad_norm": 2.163374423980713,
       "learning_rate": 0.0,
-      "loss": 0.2304,
+      "loss": 0.2351,
       "step": 30
     },
     {
@@ -138,22 +138,22 @@
       "eval_accuracy": 0.9032258064516129,
       "eval_auc": 0.5,
       "eval_f1": 0.4745762711864407,
-      "eval_loss": 0.35649099946022034,
+      "eval_loss": 0.32613006234169006,
       "eval_precision": 0.9032258064516129,
       "eval_recall": 1.0,
-      "eval_runtime": 1.006,
-      "eval_samples_per_second": 184.89,
-      "eval_steps_per_second": 2.982,
+      "eval_runtime": 0.6179,
+      "eval_samples_per_second": 301.013,
+      "eval_steps_per_second": 4.855,
       "step": 30
     },
     {
       "epoch": 8.571428571428571,
       "step": 30,
       "total_flos": 1.8691703717363712e+17,
-      "train_loss": 0.28762030601501465,
-      "train_runtime": 70.3105,
-      "train_samples_per_second": 124.59,
-      "train_steps_per_second": 0.427
+      "train_loss": 0.2957582632700602,
+      "train_runtime": 47.4143,
+      "train_samples_per_second": 184.754,
+      "train_steps_per_second": 0.633
     }
   ],
   "logging_steps": 10,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d4c5476f8f49bfc14a67ca98ff73785fd0e5765eba1ff25ad649cd22bc6aaea
+oid sha256:2e96781d201b4962023e2deb6df7f41bd5345729797e7384d64800c6fd5a32f6
 size 4731