Training in progress, step 690000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:55e5d00d2cd7677d6c62be4befe12ceb99e54aa60af5a94e2947d4ae516faaf9
+oid sha256:c9c0e525e514fe1c5cef0557ef6488da0c1fdebf6272aba47004231ca6976c18
 size 893441093

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fdc51c6b56a4707511277be7ae25e9ceecb4c1ce951b8055606cd763924bc386
+oid sha256:e75512fbedd8d7adaa6c4c34c4ac863b89edc805a7194b74d72eea23cbb4e11b
 size 449450757

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c5cdde6fe1592597eb282f0c1adb0c3419a3256dc73cdd2ad8141425d3367aa1
+oid sha256:57580e912c8eb48eaacc83064464221889da2f0844a835381b4fa326341cb678
 size 14583

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f3c1fcd1d388653574e603211bfc56c68bd7e902268c20d36edbd0c9c2c455ef
+oid sha256:62f6f091581690af80f436a9b86b0d75c2dad2d63b594e5185c0e63d2bb68d1e
 size 14583

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c40db2c616071d5de318f5594c12558c6be71cc3185a20daba66531013c4562
+oid sha256:0a7b8b83cde1bd3869fe090f1cb9c794e65d5033208eec9d00a90a14b364e27f
 size 14583

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:abefb15d42bbdbc9d96701958a628e317cbc9e1c294d8e8a76d57bee1d799f4e
+oid sha256:1804d7c7415f17b94f7dec6a3f79e792faa4e7579f021ed604639d6ae0a4f8f2
 size 14583

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b5923e1314a170c5cdfcf9c517450e0d99f3907dcef2765f816ff70cb6461364
+oid sha256:5379aefa05a140fc154bf332c86fa067c2c130445bc4590eb14522743a5b9947
 size 14583

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9887b880e911257bf7ed749ed55b173537ca64c83004df1495db6bddcf868768
+oid sha256:601105f28ea2021a75065a3124db1406fa8cee4a2f9774cf405bde49613afb37
 size 14583

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f6acc5ebd016f0085aa2c2381f509e3d8d43d4652dca878fe5c1e4ef96b864c
+oid sha256:578996460506c4bb1c40a07e7da011e3e8db58802532f0ccbbdc09eaa32c4f08
 size 14583

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b5eeebb55361b678fa47ae3e37f81a72056ae8266b737b634b72a45e273417dd
+oid sha256:a80cf61947b33b1a7acf0fb558355efcd3fbb3669a40d006ee3d143181ad13b1
 size 14583

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:390e03fe3cc05eeca400d470fa9829ae91cb8c4659d5322fb96cb732dc98e5e1
+oid sha256:ccd22c7052fac9ec9f037ee44414440d92721875c54fac648c7b4ca864fbffde
 size 627

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.3593529479967534,
-  "global_step": 680000,
+  "epoch": 1.3793434325261176,
+  "global_step": 690000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -8166,11 +8166,131 @@
       "learning_rate": 4.567035473186444e-05,
       "loss": 0.2978,
       "step": 680000
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 4.556953360325625e-05,
+      "loss": 0.2978,
+      "step": 680500
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 4.546880660622845e-05,
+      "loss": 0.2975,
+      "step": 681000
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 4.5368174016164844e-05,
+      "loss": 0.2976,
+      "step": 681500
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 4.5267636108191036e-05,
+      "loss": 0.2983,
+      "step": 682000
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 4.5167193157173913e-05,
+      "loss": 0.2978,
+      "step": 682500
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 4.5066845437720555e-05,
+      "loss": 0.2977,
+      "step": 683000
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 4.4966593224177866e-05,
+      "loss": 0.2976,
+      "step": 683500
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 4.4866436790631564e-05,
+      "loss": 0.2971,
+      "step": 684000
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 4.476637641090551e-05,
+      "loss": 0.2975,
+      "step": 684500
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 4.4666412358560955e-05,
+      "loss": 0.2978,
+      "step": 685000
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 4.456654490689578e-05,
+      "loss": 0.2967,
+      "step": 685500
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 4.4466774328943796e-05,
+      "loss": 0.2979,
+      "step": 686000
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 4.4367100897474e-05,
+      "loss": 0.2975,
+      "step": 686500
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 4.426752488498972e-05,
+      "loss": 0.2972,
+      "step": 687000
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 4.4168046563727945e-05,
+      "loss": 0.2972,
+      "step": 687500
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 4.406866620565862e-05,
+      "loss": 0.2968,
+      "step": 688000
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 4.396938408248383e-05,
+      "loss": 0.2973,
+      "step": 688500
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 4.3870200465637164e-05,
+      "loss": 0.2972,
+      "step": 689000
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 4.377111562628282e-05,
+      "loss": 0.2965,
+      "step": 689500
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 4.3672129835314955e-05,
+      "loss": 0.2971,
+      "step": 690000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 2,
-  "total_flos": 4.597284714742531e+22,
+  "total_flos": 4.664892321779864e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fdc51c6b56a4707511277be7ae25e9ceecb4c1ce951b8055606cd763924bc386
+oid sha256:e75512fbedd8d7adaa6c4c34c4ac863b89edc805a7194b74d72eea23cbb4e11b
 size 449450757