update model with 1.0 safeguard

checkpoint-72000/trainer_state.json

@@ -18,9 +18,9 @@
       "eval_bleu": 42.2846,
       "eval_gen_len": 33.5896,
       "eval_loss": 0.0983600914478302,
-      "eval_runtime": 122.9468,
-      "eval_samples_per_second": 8.483,
-      "eval_steps_per_second": 0.537,
+      "eval_runtime": 125.1063,
+      "eval_samples_per_second": 8.337,
+      "eval_steps_per_second": 0.528,
       "step": 8000
     },
     {
@@ -34,9 +34,9 @@
       "eval_bleu": 42.1887,
       "eval_gen_len": 34.0508,
       "eval_loss": 0.097293421626091,
-      "eval_runtime": 162.7475,
-      "eval_samples_per_second": 6.409,
-      "eval_steps_per_second": 0.406,
+      "eval_runtime": 165.8917,
+      "eval_samples_per_second": 6.287,
+      "eval_steps_per_second": 0.398,
       "step": 16000
     },
     {
@@ -50,9 +50,9 @@
       "eval_bleu": 42.7367,
       "eval_gen_len": 33.7747,
       "eval_loss": 0.09722033143043518,
-      "eval_runtime": 127.375,
-      "eval_samples_per_second": 8.188,
-      "eval_steps_per_second": 0.518,
+      "eval_runtime": 119.8443,
+      "eval_samples_per_second": 8.703,
+      "eval_steps_per_second": 0.551,
       "step": 24000
     },
     {
@@ -66,9 +66,9 @@
       "eval_bleu": 42.9551,
       "eval_gen_len": 34.4238,
       "eval_loss": 0.0965743437409401,
-      "eval_runtime": 120.0033,
-      "eval_samples_per_second": 8.691,
-      "eval_steps_per_second": 0.55,
+      "eval_runtime": 122.2105,
+      "eval_samples_per_second": 8.534,
+      "eval_steps_per_second": 0.54,
       "step": 32000
     },
     {
@@ -82,9 +82,9 @@
       "eval_bleu": 42.7141,
       "eval_gen_len": 34.0872,
       "eval_loss": 0.09599015861749649,
-      "eval_runtime": 144.0409,
-      "eval_samples_per_second": 7.241,
-      "eval_steps_per_second": 0.458,
+      "eval_runtime": 147.1092,
+      "eval_samples_per_second": 7.09,
+      "eval_steps_per_second": 0.449,
       "step": 40000
     },
     {
@@ -98,9 +98,9 @@
       "eval_bleu": 42.4802,
       "eval_gen_len": 34.1266,
       "eval_loss": 0.09718813002109528,
-      "eval_runtime": 121.2752,
-      "eval_samples_per_second": 8.6,
-      "eval_steps_per_second": 0.544,
+      "eval_runtime": 126.9046,
+      "eval_samples_per_second": 8.219,
+      "eval_steps_per_second": 0.52,
       "step": 48000
     },
     {
@@ -114,9 +114,9 @@
       "eval_bleu": 42.6361,
       "eval_gen_len": 34.1045,
       "eval_loss": 0.0969875305891037,
-      "eval_runtime": 137.2112,
-      "eval_samples_per_second": 7.601,
-      "eval_steps_per_second": 0.481,
+      "eval_runtime": 144.8881,
+      "eval_samples_per_second": 7.199,
+      "eval_steps_per_second": 0.456,
       "step": 56000
     },
     {
@@ -130,9 +130,9 @@
       "eval_bleu": 42.8271,
       "eval_gen_len": 34.4851,
       "eval_loss": 0.09680665284395218,
-      "eval_runtime": 134.8615,
-      "eval_samples_per_second": 7.734,
-      "eval_steps_per_second": 0.489,
+      "eval_runtime": 136.6783,
+      "eval_samples_per_second": 7.631,
+      "eval_steps_per_second": 0.483,
       "step": 64000
     },
     {
@@ -146,9 +146,9 @@
       "eval_bleu": 42.9999,
       "eval_gen_len": 34.0671,
       "eval_loss": 0.09675087034702301,
-      "eval_runtime": 110.3226,
-      "eval_samples_per_second": 9.454,
-      "eval_steps_per_second": 0.598,
+      "eval_runtime": 115.9998,
+      "eval_samples_per_second": 8.991,
+      "eval_steps_per_second": 0.569,
       "step": 72000
     }
   ],

checkpoint-72000/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6cf5ee38f2194704c244e5c80610b2c3775d2eb9a6a936f61d49a9795e266a86
+oid sha256:edf2021650916951d996ad74978de6ba9cbe3e25bd074e8ad6124d4670a0477b
 size 3771

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6cf5ee38f2194704c244e5c80610b2c3775d2eb9a6a936f61d49a9795e266a86
+oid sha256:edf2021650916951d996ad74978de6ba9cbe3e25bd074e8ad6124d4670a0477b
 size 3771