Training in progress, epoch 0

all_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 8.88888888888889,
     "total_flos": 7.753465317556224e+16,
-    "train_loss": 0.0,
-    "train_runtime": 58.6116,
-    "train_samples_per_second": 147.411,
-    "train_steps_per_second": 1.024
+    "train_loss": 3.181795922267553e+30,
+    "train_runtime": 46.0692,
+    "train_samples_per_second": 187.544,
+    "train_steps_per_second": 1.302
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d7de0af86b01dbddefa3d8722acd70cdb59a362b124821c15c419da054faa6e
+oid sha256:1a28aa672236f18658afc6ad148fb337d606300bac7df8e79600f13d84e83adb
 size 44766388

runs/Jun06_03-56-50_b446df81307f/events.out.tfevents.1717646218.b446df81307f.157.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f8b441fb053d616627dbd57cc98021dcad74321f15d3d8e867532da605649d7
+size 5281

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 8.88888888888889,
     "total_flos": 7.753465317556224e+16,
-    "train_loss": 0.0,
-    "train_runtime": 58.6116,
-    "train_samples_per_second": 147.411,
-    "train_steps_per_second": 1.024
+    "train_loss": 3.181795922267553e+30,
+    "train_runtime": 46.0692,
+    "train_samples_per_second": 187.544,
+    "train_steps_per_second": 1.302
 }

trainer_state.json

@@ -11,134 +11,134 @@
     {
       "epoch": 0.8888888888888888,
       "eval_accuracy": 0.3958333333333333,
-      "eval_loss": NaN,
-      "eval_runtime": 0.4778,
-      "eval_samples_per_second": 200.917,
-      "eval_steps_per_second": 6.279,
+      "eval_loss": 2.8539976205603575e+30,
+      "eval_runtime": 0.2573,
+      "eval_samples_per_second": 373.047,
+      "eval_steps_per_second": 11.658,
       "step": 6
     },
     {
       "epoch": 1.4814814814814814,
-      "grad_norm": NaN,
+      "grad_norm": 22.85268211364746,
       "learning_rate": 4.62962962962963e-05,
-      "loss": 0.0,
+      "loss": 3.195940475249626e+30,
       "step": 10
     },
     {
       "epoch": 1.925925925925926,
       "eval_accuracy": 0.3958333333333333,
-      "eval_loss": NaN,
-      "eval_runtime": 0.6635,
-      "eval_samples_per_second": 144.694,
-      "eval_steps_per_second": 4.522,
+      "eval_loss": 2.8539976205603575e+30,
+      "eval_runtime": 0.2547,
+      "eval_samples_per_second": 376.954,
+      "eval_steps_per_second": 11.78,
       "step": 13
     },
     {
       "epoch": 2.962962962962963,
-      "grad_norm": NaN,
+      "grad_norm": 26.933372497558594,
       "learning_rate": 3.7037037037037037e-05,
-      "loss": 0.0,
+      "loss": 3.1627329754809595e+30,
       "step": 20
     },
     {
       "epoch": 2.962962962962963,
       "eval_accuracy": 0.3958333333333333,
-      "eval_loss": NaN,
-      "eval_runtime": 0.3323,
-      "eval_samples_per_second": 288.879,
-      "eval_steps_per_second": 9.027,
+      "eval_loss": 2.8539976205603575e+30,
+      "eval_runtime": 0.2507,
+      "eval_samples_per_second": 382.993,
+      "eval_steps_per_second": 11.969,
       "step": 20
     },
     {
       "epoch": 4.0,
       "eval_accuracy": 0.3958333333333333,
-      "eval_loss": NaN,
-      "eval_runtime": 0.3964,
-      "eval_samples_per_second": 242.174,
-      "eval_steps_per_second": 7.568,
+      "eval_loss": 2.8539976205603575e+30,
+      "eval_runtime": 0.3363,
+      "eval_samples_per_second": 285.439,
+      "eval_steps_per_second": 8.92,
       "step": 27
     },
     {
       "epoch": 4.444444444444445,
-      "grad_norm": NaN,
+      "grad_norm": 28.446868896484375,
       "learning_rate": 2.777777777777778e-05,
-      "loss": 0.0,
+      "loss": 3.162728139777681e+30,
       "step": 30
     },
     {
       "epoch": 4.888888888888889,
       "eval_accuracy": 0.3958333333333333,
-      "eval_loss": NaN,
-      "eval_runtime": 0.3124,
-      "eval_samples_per_second": 307.344,
-      "eval_steps_per_second": 9.604,
+      "eval_loss": 2.8539976205603575e+30,
+      "eval_runtime": 0.2484,
+      "eval_samples_per_second": 386.545,
+      "eval_steps_per_second": 12.08,
       "step": 33
     },
     {
       "epoch": 5.925925925925926,
-      "grad_norm": NaN,
+      "grad_norm": 29.070621490478516,
       "learning_rate": 1.8518518518518518e-05,
-      "loss": 0.0,
+      "loss": 3.203328220933291e+30,
       "step": 40
     },
     {
       "epoch": 5.925925925925926,
       "eval_accuracy": 0.3958333333333333,
-      "eval_loss": NaN,
-      "eval_runtime": 0.4093,
-      "eval_samples_per_second": 234.54,
-      "eval_steps_per_second": 7.329,
+      "eval_loss": 2.8539976205603575e+30,
+      "eval_runtime": 0.2586,
+      "eval_samples_per_second": 371.285,
+      "eval_steps_per_second": 11.603,
       "step": 40
     },
     {
       "epoch": 6.962962962962963,
       "eval_accuracy": 0.3958333333333333,
-      "eval_loss": NaN,
-      "eval_runtime": 0.349,
-      "eval_samples_per_second": 275.092,
-      "eval_steps_per_second": 8.597,
+      "eval_loss": 2.8539976205603575e+30,
+      "eval_runtime": 0.2547,
+      "eval_samples_per_second": 376.967,
+      "eval_steps_per_second": 11.78,
       "step": 47
     },
     {
       "epoch": 7.407407407407407,
-      "grad_norm": NaN,
+      "grad_norm": 29.25043487548828,
       "learning_rate": 9.259259259259259e-06,
-      "loss": 0.0,
+      "loss": 3.2033323312810776e+30,
       "step": 50
     },
     {
       "epoch": 8.0,
       "eval_accuracy": 0.3958333333333333,
-      "eval_loss": NaN,
-      "eval_runtime": 0.3242,
-      "eval_samples_per_second": 296.083,
-      "eval_steps_per_second": 9.253,
+      "eval_loss": 2.8539976205603575e+30,
+      "eval_runtime": 0.2704,
+      "eval_samples_per_second": 355.065,
+      "eval_steps_per_second": 11.096,
       "step": 54
     },
     {
       "epoch": 8.88888888888889,
-      "grad_norm": NaN,
+      "grad_norm": 29.65780258178711,
       "learning_rate": 0.0,
-      "loss": 0.0,
+      "loss": 3.162713390882682e+30,
       "step": 60
     },
     {
       "epoch": 8.88888888888889,
       "eval_accuracy": 0.3958333333333333,
-      "eval_loss": NaN,
-      "eval_runtime": 0.309,
-      "eval_samples_per_second": 310.706,
-      "eval_steps_per_second": 9.71,
+      "eval_loss": 2.8539976205603575e+30,
+      "eval_runtime": 0.3257,
+      "eval_samples_per_second": 294.758,
+      "eval_steps_per_second": 9.211,
       "step": 60
     },
     {
       "epoch": 8.88888888888889,
       "step": 60,
       "total_flos": 7.753465317556224e+16,
-      "train_loss": 0.0,
-      "train_runtime": 58.6116,
-      "train_samples_per_second": 147.411,
-      "train_steps_per_second": 1.024
+      "train_loss": 3.181795922267553e+30,
+      "train_runtime": 46.0692,
+      "train_samples_per_second": 187.544,
+      "train_steps_per_second": 1.302
     }
   ],
   "logging_steps": 10,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28a919d5ac808fb1e608d7cf9bfab74aeec01596efcb3855debf2bb6f8ee5689
+oid sha256:5d2122e108f1986add0878418492368ef0309c0bf3dc4e3aa32e19fe51429f8a
 size 5112