update model with 1.0 safeguard

checkpoint-48000/trainer_state.json

@@ -18,7 +18,7 @@
       "eval_bleu": 35.1474,
       "eval_gen_len": 40.395,
       "eval_loss": 0.10896337777376175,
-      "eval_runtime": 179.3655,
+      "eval_runtime": 179.3484,
       "eval_samples_per_second": 5.815,
       "eval_steps_per_second": 0.184,
       "step": 4000
@@ -34,9 +34,9 @@
       "eval_bleu": 41.0648,
       "eval_gen_len": 34.5983,
       "eval_loss": 0.10649073868989944,
-      "eval_runtime": 166.3848,
-      "eval_samples_per_second": 6.269,
-      "eval_steps_per_second": 0.198,
+      "eval_runtime": 171.3066,
+      "eval_samples_per_second": 6.088,
+      "eval_steps_per_second": 0.193,
       "step": 8000
     },
     {
@@ -50,8 +50,8 @@
       "eval_bleu": 41.4064,
       "eval_gen_len": 34.4353,
       "eval_loss": 0.10525061935186386,
-      "eval_runtime": 157.1928,
-      "eval_samples_per_second": 6.635,
+      "eval_runtime": 156.772,
+      "eval_samples_per_second": 6.653,
       "eval_steps_per_second": 0.21,
       "step": 12000
     },
@@ -66,9 +66,9 @@
       "eval_bleu": 40.6981,
       "eval_gen_len": 36.0038,
       "eval_loss": 0.10416892915964127,
-      "eval_runtime": 135.6043,
-      "eval_samples_per_second": 7.691,
-      "eval_steps_per_second": 0.243,
+      "eval_runtime": 133.8567,
+      "eval_samples_per_second": 7.792,
+      "eval_steps_per_second": 0.247,
       "step": 16000
     },
     {
@@ -82,9 +82,9 @@
       "eval_bleu": 41.7673,
       "eval_gen_len": 35.4631,
       "eval_loss": 0.10361550748348236,
-      "eval_runtime": 156.992,
-      "eval_samples_per_second": 6.644,
-      "eval_steps_per_second": 0.21,
+      "eval_runtime": 154.8814,
+      "eval_samples_per_second": 6.734,
+      "eval_steps_per_second": 0.213,
       "step": 20000
     },
     {
@@ -98,9 +98,9 @@
       "eval_bleu": 41.5766,
       "eval_gen_len": 35.7536,
       "eval_loss": 0.10351266711950302,
-      "eval_runtime": 148.1282,
-      "eval_samples_per_second": 7.041,
-      "eval_steps_per_second": 0.223,
+      "eval_runtime": 152.4909,
+      "eval_samples_per_second": 6.84,
+      "eval_steps_per_second": 0.216,
       "step": 24000
     },
     {
@@ -114,9 +114,9 @@
       "eval_bleu": 41.2765,
       "eval_gen_len": 35.535,
       "eval_loss": 0.10269948095083237,
-      "eval_runtime": 139.1706,
-      "eval_samples_per_second": 7.494,
-      "eval_steps_per_second": 0.237,
+      "eval_runtime": 132.6943,
+      "eval_samples_per_second": 7.86,
+      "eval_steps_per_second": 0.249,
       "step": 28000
     },
     {
@@ -130,9 +130,9 @@
       "eval_bleu": 42.0634,
       "eval_gen_len": 34.8495,
       "eval_loss": 0.10216742753982544,
-      "eval_runtime": 138.1687,
-      "eval_samples_per_second": 7.549,
-      "eval_steps_per_second": 0.239,
+      "eval_runtime": 141.3815,
+      "eval_samples_per_second": 7.377,
+      "eval_steps_per_second": 0.233,
       "step": 32000
     },
     {
@@ -146,9 +146,9 @@
       "eval_bleu": 41.2763,
       "eval_gen_len": 36.139,
       "eval_loss": 0.10178232192993164,
-      "eval_runtime": 118.4305,
-      "eval_samples_per_second": 8.807,
-      "eval_steps_per_second": 0.279,
+      "eval_runtime": 121.485,
+      "eval_samples_per_second": 8.585,
+      "eval_steps_per_second": 0.272,
       "step": 36000
     },
     {
@@ -162,9 +162,9 @@
       "eval_bleu": 42.3991,
       "eval_gen_len": 34.4545,
       "eval_loss": 0.10192298889160156,
-      "eval_runtime": 120.2656,
-      "eval_samples_per_second": 8.672,
-      "eval_steps_per_second": 0.274,
+      "eval_runtime": 118.8523,
+      "eval_samples_per_second": 8.776,
+      "eval_steps_per_second": 0.278,
       "step": 40000
     },
     {
@@ -178,9 +178,9 @@
       "eval_bleu": 42.1688,
       "eval_gen_len": 35.3145,
       "eval_loss": 0.1022704690694809,
-      "eval_runtime": 137.0088,
-      "eval_samples_per_second": 7.613,
-      "eval_steps_per_second": 0.241,
+      "eval_runtime": 139.2542,
+      "eval_samples_per_second": 7.49,
+      "eval_steps_per_second": 0.237,
       "step": 44000
     },
     {
@@ -194,9 +194,9 @@
       "eval_bleu": 42.5638,
       "eval_gen_len": 35.0738,
       "eval_loss": 0.10206188261508942,
-      "eval_runtime": 129.6219,
-      "eval_samples_per_second": 8.046,
-      "eval_steps_per_second": 0.255,
+      "eval_runtime": 135.8728,
+      "eval_samples_per_second": 7.676,
+      "eval_steps_per_second": 0.243,
       "step": 48000
     }
   ],

checkpoint-48000/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ceb79d8b854e02ccc5795cd91b8ba49e36367cb01aa95d1a05db465648548b6b
+oid sha256:06045bfca8d45b2ad5c21bc2afdbfa7788b5223a9722cafa595fbbe472e272c9
 size 3771

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ceb79d8b854e02ccc5795cd91b8ba49e36367cb01aa95d1a05db465648548b6b
+oid sha256:06045bfca8d45b2ad5c21bc2afdbfa7788b5223a9722cafa595fbbe472e272c9
 size 3771