Training in progress, step 160, checkpoint

last-checkpoint/trainer_state.json

@@ -11,9 +11,9 @@
     {
       "epoch": 0.001183431952662722,
       "eval_loss": 11.5,
-      "eval_runtime": 3.3956,
-      "eval_samples_per_second": 442.336,
-      "eval_steps_per_second": 27.683,
+      "eval_runtime": 3.3777,
+      "eval_samples_per_second": 444.678,
+      "eval_steps_per_second": 27.829,
       "step": 1
     },
     {
@@ -33,9 +33,9 @@
     {
       "epoch": 0.023668639053254437,
       "eval_loss": 11.5,
-      "eval_runtime": 3.3351,
-      "eval_samples_per_second": 450.363,
-      "eval_steps_per_second": 28.185,
+      "eval_runtime": 3.3046,
+      "eval_samples_per_second": 454.517,
+      "eval_steps_per_second": 28.445,
       "step": 20
     },
     {
@@ -55,9 +55,9 @@
     {
       "epoch": 0.047337278106508875,
       "eval_loss": 11.5,
-      "eval_runtime": 3.3126,
-      "eval_samples_per_second": 453.421,
-      "eval_steps_per_second": 28.377,
+      "eval_runtime": 3.3267,
+      "eval_samples_per_second": 451.492,
+      "eval_steps_per_second": 28.256,
       "step": 40
     },
     {
@@ -77,9 +77,9 @@
     {
       "epoch": 0.07100591715976332,
       "eval_loss": 11.5,
-      "eval_runtime": 3.3352,
-      "eval_samples_per_second": 450.349,
-      "eval_steps_per_second": 28.184,
+      "eval_runtime": 3.3414,
+      "eval_samples_per_second": 449.509,
+      "eval_steps_per_second": 28.132,
       "step": 60
     },
     {
@@ -99,9 +99,9 @@
     {
       "epoch": 0.09467455621301775,
       "eval_loss": 11.5,
-      "eval_runtime": 3.3585,
-      "eval_samples_per_second": 447.222,
-      "eval_steps_per_second": 27.989,
+      "eval_runtime": 3.3003,
+      "eval_samples_per_second": 455.107,
+      "eval_steps_per_second": 28.482,
       "step": 80
     },
     {
@@ -121,9 +121,9 @@
     {
       "epoch": 0.11834319526627218,
       "eval_loss": 11.5,
-      "eval_runtime": 3.3221,
-      "eval_samples_per_second": 452.122,
-      "eval_steps_per_second": 28.295,
+      "eval_runtime": 3.3009,
+      "eval_samples_per_second": 455.027,
+      "eval_steps_per_second": 28.477,
       "step": 100
     },
     {
@@ -143,9 +143,9 @@
     {
       "epoch": 0.14201183431952663,
       "eval_loss": 11.5,
-      "eval_runtime": 3.328,
-      "eval_samples_per_second": 451.328,
-      "eval_steps_per_second": 28.246,
+      "eval_runtime": 3.2885,
+      "eval_samples_per_second": 456.742,
+      "eval_steps_per_second": 28.584,
       "step": 120
     },
     {
@@ -165,9 +165,9 @@
     {
       "epoch": 0.16568047337278108,
       "eval_loss": 11.5,
-      "eval_runtime": 3.3864,
-      "eval_samples_per_second": 443.539,
-      "eval_steps_per_second": 27.758,
+      "eval_runtime": 3.3618,
+      "eval_samples_per_second": 446.782,
+      "eval_steps_per_second": 27.961,
       "step": 140
     },
     {
@@ -187,9 +187,9 @@
     {
       "epoch": 0.1893491124260355,
       "eval_loss": 11.5,
-      "eval_runtime": 3.35,
-      "eval_samples_per_second": 448.364,
-      "eval_steps_per_second": 28.06,
+      "eval_runtime": 3.2697,
+      "eval_samples_per_second": 459.367,
+      "eval_steps_per_second": 28.749,
       "step": 160
     }
   ],

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4193abd9d3c8f06a0b72e6601d6500a541caf61561918ea14e1ccfe5bac411cf
+oid sha256:d7035c75fb5e19850d98db1473a837c5eeffdee69ec47b2fd17744e2e4e4ec70
 size 8312