Training in progress, epoch 1

all_results.json

@@ -3,16 +3,16 @@
     "eval_accuracy": 72.47706422018348,
     "eval_average_metrics": 72.47706422018348,
     "eval_loss": 0.27757981419563293,
-    "eval_runtime": 4.8177,
-    "eval_samples_per_second": 339.375,
+    "eval_runtime": 4.7969,
+    "eval_samples_per_second": 340.847,
     "test_accuracy": 70.58103975535168,
     "test_average_metrics": 70.58103975535168,
     "test_loss": 0.2894817888736725,
-    "test_runtime": 4.7931,
-    "test_samples_per_second": 341.116,
+    "test_runtime": 4.7627,
+    "test_samples_per_second": 343.293,
     "train_loss": 0.2005054286374884,
-    "train_runtime": 1452.5651,
+    "train_runtime": 1293.5612,
     "train_samples": 9427,
-    "train_samples_per_second": 129.798,
-    "train_steps_per_second": 4.062
+    "train_samples_per_second": 145.753,
+    "train_steps_per_second": 4.561
 }

eval_results.json

@@ -3,6 +3,6 @@
     "eval_accuracy": 72.47706422018348,
     "eval_average_metrics": 72.47706422018348,
     "eval_loss": 0.27757981419563293,
-    "eval_runtime": 4.8177,
-    "eval_samples_per_second": 339.375
+    "eval_runtime": 4.7969,
+    "eval_samples_per_second": 340.847
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70e0afe718876729ceb4662c13216a6f93ad8ab28e4515c3bc06c629b8768ed9
+oid sha256:8b456c85c073efe312e20263b9d0ea6131e6bd25a2ae380d0b5b9a05bb7e4db5
 size 7551621

runs/Jan30_13-22-26_node4/events.out.tfevents.1643520205.node4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:318d41142b63bd0f3b6de3b08ce372231f3d5c0314d27a0bf061ad9f65835f77
-size 12159
+oid sha256:7c386d1d87d4769df03105f9f78bad84c2cffb87243f02b86932829117ae4545
+size 12835

runs/Jan30_13-22-26_node4/events.out.tfevents.1643521504.node4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7d3a7920fe84e6aeee03e0f08d874c2be8e08008cda881294fcd9cebb9c91c9
+size 684

runs/Jan30_14-11-22_node4/1643523178.183361/events.out.tfevents.1643523178.node4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:803a759d7658d5676971ced9587758760977012f2d7304233ad753fe22e325eb
+size 5020

runs/Jan30_14-11-22_node4/events.out.tfevents.1643523178.node4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b85098ba0d4fa00c1797749294af04d62dc8591938451c7e62f2f830d4624ebc
+size 4314

test_results.json

@@ -3,6 +3,6 @@
     "test_accuracy": 70.58103975535168,
     "test_average_metrics": 70.58103975535168,
     "test_loss": 0.2894817888736725,
-    "test_runtime": 4.7931,
-    "test_samples_per_second": 341.116
+    "test_runtime": 4.7627,
+    "test_samples_per_second": 343.293
 }

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 20.0,
     "train_loss": 0.2005054286374884,
-    "train_runtime": 1452.5651,
+    "train_runtime": 1293.5612,
     "train_samples": 9427,
-    "train_samples_per_second": 129.798,
-    "train_steps_per_second": 4.062
+    "train_samples_per_second": 145.753,
+    "train_steps_per_second": 4.561
 }

trainer_state.json

@@ -12,8 +12,8 @@
       "eval_accuracy": 62.62996941896024,
       "eval_average_metrics": 62.62996941896024,
       "eval_loss": 0.2848173677921295,
-      "eval_runtime": 4.504,
-      "eval_samples_per_second": 363.014,
+      "eval_runtime": 4.5081,
+      "eval_samples_per_second": 362.682,
       "step": 295
     },
     {
@@ -27,8 +27,8 @@
       "eval_accuracy": 62.62996941896024,
       "eval_average_metrics": 62.62996941896024,
       "eval_loss": 0.27746617794036865,
-      "eval_runtime": 4.5022,
-      "eval_samples_per_second": 363.153,
+      "eval_runtime": 4.4839,
+      "eval_samples_per_second": 364.64,
       "step": 590
     },
     {
@@ -36,8 +36,8 @@
       "eval_accuracy": 62.62996941896024,
       "eval_average_metrics": 62.62996941896024,
       "eval_loss": 0.2767568826675415,
-      "eval_runtime": 4.4934,
-      "eval_samples_per_second": 363.871,
+      "eval_runtime": 4.4969,
+      "eval_samples_per_second": 363.585,
       "step": 885
     },
     {
@@ -51,8 +51,8 @@
       "eval_accuracy": 62.75229357798165,
       "eval_average_metrics": 62.75229357798165,
       "eval_loss": 0.2767893373966217,
-      "eval_runtime": 4.7772,
-      "eval_samples_per_second": 342.253,
+      "eval_runtime": 4.7449,
+      "eval_samples_per_second": 344.579,
       "step": 1180
     },
     {
@@ -60,8 +60,8 @@
       "eval_accuracy": 63.36391437308868,
       "eval_average_metrics": 63.36391437308868,
       "eval_loss": 0.26716169714927673,
-      "eval_runtime": 4.7616,
-      "eval_samples_per_second": 343.37,
+      "eval_runtime": 4.7487,
+      "eval_samples_per_second": 344.302,
       "step": 1475
     },
     {
@@ -75,8 +75,8 @@
       "eval_accuracy": 66.11620795107034,
       "eval_average_metrics": 66.11620795107034,
       "eval_loss": 0.2606015205383301,
-      "eval_runtime": 4.7573,
-      "eval_samples_per_second": 343.683,
+      "eval_runtime": 4.7538,
+      "eval_samples_per_second": 343.936,
       "step": 1770
     },
     {
@@ -90,8 +90,8 @@
       "eval_accuracy": 69.0519877675841,
       "eval_average_metrics": 69.0519877675841,
       "eval_loss": 0.25209498405456543,
-      "eval_runtime": 4.7545,
-      "eval_samples_per_second": 343.882,
+      "eval_runtime": 4.7471,
+      "eval_samples_per_second": 344.422,
       "step": 2065
     },
     {
@@ -99,8 +99,8 @@
       "eval_accuracy": 69.2354740061162,
       "eval_average_metrics": 69.2354740061162,
       "eval_loss": 0.25652435421943665,
-      "eval_runtime": 4.7648,
-      "eval_samples_per_second": 343.14,
+      "eval_runtime": 4.7461,
+      "eval_samples_per_second": 344.493,
       "step": 2360
     },
     {
@@ -114,8 +114,8 @@
       "eval_accuracy": 71.0091743119266,
       "eval_average_metrics": 71.0091743119266,
       "eval_loss": 0.24900275468826294,
-      "eval_runtime": 4.7724,
-      "eval_samples_per_second": 342.596,
+      "eval_runtime": 4.7529,
+      "eval_samples_per_second": 344.002,
       "step": 2655
     },
     {
@@ -123,8 +123,8 @@
       "eval_accuracy": 71.80428134556574,
       "eval_average_metrics": 71.80428134556574,
       "eval_loss": 0.2635628283023834,
-      "eval_runtime": 4.7656,
-      "eval_samples_per_second": 343.086,
+      "eval_runtime": 4.7533,
+      "eval_samples_per_second": 343.974,
       "step": 2950
     },
     {
@@ -138,8 +138,8 @@
       "eval_accuracy": 70.70336391437309,
       "eval_average_metrics": 70.70336391437309,
       "eval_loss": 0.26442670822143555,
-      "eval_runtime": 4.7895,
-      "eval_samples_per_second": 341.37,
+      "eval_runtime": 4.7661,
+      "eval_samples_per_second": 343.05,
       "step": 3245
     },
     {
@@ -153,8 +153,8 @@
       "eval_accuracy": 71.49847094801223,
       "eval_average_metrics": 71.49847094801223,
       "eval_loss": 0.2672346830368042,
-      "eval_runtime": 4.7696,
-      "eval_samples_per_second": 342.793,
+      "eval_runtime": 4.761,
+      "eval_samples_per_second": 343.414,
       "step": 3540
     },
     {
@@ -162,8 +162,8 @@
       "eval_accuracy": 72.47706422018348,
       "eval_average_metrics": 72.47706422018348,
       "eval_loss": 0.27757981419563293,
-      "eval_runtime": 4.7935,
-      "eval_samples_per_second": 341.085,
+      "eval_runtime": 4.7532,
+      "eval_samples_per_second": 343.982,
       "step": 3835
     },
     {
@@ -177,8 +177,8 @@
       "eval_accuracy": 70.8868501529052,
       "eval_average_metrics": 70.8868501529052,
       "eval_loss": 0.29447805881500244,
-      "eval_runtime": 4.7712,
-      "eval_samples_per_second": 342.681,
+      "eval_runtime": 4.7492,
+      "eval_samples_per_second": 344.268,
       "step": 4130
     },
     {
@@ -186,8 +186,8 @@
       "eval_accuracy": 70.21406727828746,
       "eval_average_metrics": 70.21406727828746,
       "eval_loss": 0.2965507209300995,
-      "eval_runtime": 4.7813,
-      "eval_samples_per_second": 341.96,
+      "eval_runtime": 4.7633,
+      "eval_samples_per_second": 343.251,
       "step": 4425
     },
     {
@@ -201,8 +201,8 @@
       "eval_accuracy": 72.29357798165138,
       "eval_average_metrics": 72.29357798165138,
       "eval_loss": 0.3127536177635193,
-      "eval_runtime": 4.7677,
-      "eval_samples_per_second": 342.93,
+      "eval_runtime": 4.7675,
+      "eval_samples_per_second": 342.95,
       "step": 4720
     },
     {
@@ -216,8 +216,8 @@
       "eval_accuracy": 70.9480122324159,
       "eval_average_metrics": 70.9480122324159,
       "eval_loss": 0.3478758931159973,
-      "eval_runtime": 4.7648,
-      "eval_samples_per_second": 343.144,
+      "eval_runtime": 4.7792,
+      "eval_samples_per_second": 342.105,
       "step": 5015
     },
     {
@@ -225,8 +225,8 @@
       "eval_accuracy": 72.17125382262996,
       "eval_average_metrics": 72.17125382262996,
       "eval_loss": 0.33715757727622986,
-      "eval_runtime": 4.7601,
-      "eval_samples_per_second": 343.478,
+      "eval_runtime": 4.7549,
+      "eval_samples_per_second": 343.858,
       "step": 5310
     },
     {
@@ -240,8 +240,8 @@
       "eval_accuracy": 71.92660550458716,
       "eval_average_metrics": 71.92660550458716,
       "eval_loss": 0.34181272983551025,
-      "eval_runtime": 4.7537,
-      "eval_samples_per_second": 343.942,
+      "eval_runtime": 4.753,
+      "eval_samples_per_second": 343.993,
       "step": 5605
     },
     {
@@ -249,8 +249,8 @@
       "eval_accuracy": 71.80428134556574,
       "eval_average_metrics": 71.80428134556574,
       "eval_loss": 0.34913983941078186,
-      "eval_runtime": 4.7707,
-      "eval_samples_per_second": 342.716,
+      "eval_runtime": 4.7538,
+      "eval_samples_per_second": 343.937,
       "step": 5900
     },
     {
@@ -258,9 +258,9 @@
       "step": 5900,
       "total_flos": 5.78564930408256e+16,
       "train_loss": 0.2005054286374884,
-      "train_runtime": 1452.5651,
-      "train_samples_per_second": 129.798,
-      "train_steps_per_second": 4.062
+      "train_runtime": 1293.5612,
+      "train_samples_per_second": 145.753,
+      "train_steps_per_second": 4.561
     }
   ],
   "max_steps": 5900,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73a8c254a6f9831029ac09903dd9bf673889f14c8b169f60f14b9240c83b3523
+oid sha256:9f650df5107240b0979f2b966fe940e6b1b2320e544e6096f1d36e8920c3418f
 size 3183