Training in progress, step 700000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c9c0e525e514fe1c5cef0557ef6488da0c1fdebf6272aba47004231ca6976c18
+oid sha256:81ece12c6f9c13f5471c677109a4bde83e1a050417df99ad047004ba4276bba6
 size 893441093

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e75512fbedd8d7adaa6c4c34c4ac863b89edc805a7194b74d72eea23cbb4e11b
+oid sha256:bfb425b9bd2d7db89a175b6be9f6f3add2f5419aac09b70a86f8357b95b72148
 size 449450757

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:57580e912c8eb48eaacc83064464221889da2f0844a835381b4fa326341cb678
+oid sha256:513fd308756b62d456cf51dbabd0e5432e6e9f801b69e6b4147b7910a92409c3
 size 14583

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:62f6f091581690af80f436a9b86b0d75c2dad2d63b594e5185c0e63d2bb68d1e
+oid sha256:f1b41b44339013cf2c800ebd15e56c0ab490da939473759245613333c4ad094b
 size 14583

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a7b8b83cde1bd3869fe090f1cb9c794e65d5033208eec9d00a90a14b364e27f
+oid sha256:8acf2390c55c3fcc1c7f54edfdb7e51d825ccf03ad02c2710478f24d67d8d927
 size 14583

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1804d7c7415f17b94f7dec6a3f79e792faa4e7579f021ed604639d6ae0a4f8f2
+oid sha256:b884538c1c7cf25c9c76b4e2aeb5b233c0e82af8266b74f74badb8738101de61
 size 14583

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5379aefa05a140fc154bf332c86fa067c2c130445bc4590eb14522743a5b9947
+oid sha256:d0611954260b29d5933679a0b205628fe7afa2763d89a93117a665d8810ddfaa
 size 14583

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:601105f28ea2021a75065a3124db1406fa8cee4a2f9774cf405bde49613afb37
+oid sha256:1a2570d894279bdec746170684ab6ee38cfa6adc0692ab4c8e2d19fca72b235d
 size 14583

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:578996460506c4bb1c40a07e7da011e3e8db58802532f0ccbbdc09eaa32c4f08
+oid sha256:c360a23dde048e054ef7310a763eb2729b26bcfc6d980f3d3e175d2d2287e150
 size 14583

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a80cf61947b33b1a7acf0fb558355efcd3fbb3669a40d006ee3d143181ad13b1
+oid sha256:ded6c10a8ae184d010b20213595dce955d5ae9ca4fec0187e6e124f4763508bf
 size 14583

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ccd22c7052fac9ec9f037ee44414440d92721875c54fac648c7b4ca864fbffde
+oid sha256:afc49fe155c033502b3ff00fe8f2d949db5aba4e89748d4722dc58fa6f673d45
 size 627

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.3793434325261176,
-  "global_step": 690000,
+  "epoch": 1.3993339170554817,
+  "global_step": 700000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -8286,11 +8286,131 @@
       "learning_rate": 4.3672129835314955e-05,
       "loss": 0.2971,
       "step": 690000
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 4.3573243363356916e-05,
+      "loss": 0.297,
+      "step": 690500
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 4.347445648076057e-05,
+      "loss": 0.2969,
+      "step": 691000
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 4.337576945760554e-05,
+      "loss": 0.2978,
+      "step": 691500
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 4.327718256369826e-05,
+      "loss": 0.2965,
+      "step": 692000
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 4.317869606857162e-05,
+      "loss": 0.2973,
+      "step": 692500
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 4.3080310241483885e-05,
+      "loss": 0.2967,
+      "step": 693000
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 4.298202535141818e-05,
+      "loss": 0.2974,
+      "step": 693500
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 4.2883841667081675e-05,
+      "loss": 0.2967,
+      "step": 694000
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 4.2785759456904745e-05,
+      "loss": 0.2966,
+      "step": 694500
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 4.268777898904044e-05,
+      "loss": 0.2969,
+      "step": 695000
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 4.2589900531363606e-05,
+      "loss": 0.2967,
+      "step": 695500
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 4.2492124351470214e-05,
+      "loss": 0.2962,
+      "step": 696000
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 4.239445071667666e-05,
+      "loss": 0.297,
+      "step": 696500
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 4.2296879894018835e-05,
+      "loss": 0.2966,
+      "step": 697000
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 4.219941215025171e-05,
+      "loss": 0.2971,
+      "step": 697500
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 4.210204775184834e-05,
+      "loss": 0.2973,
+      "step": 698000
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 4.2004786964999304e-05,
+      "loss": 0.2962,
+      "step": 698500
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 4.190763005561186e-05,
+      "loss": 0.2964,
+      "step": 699000
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 4.1810577289309266e-05,
+      "loss": 0.2968,
+      "step": 699500
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 4.171362893143013e-05,
+      "loss": 0.2965,
+      "step": 700000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 2,
-  "total_flos": 4.664892321779864e+22,
+  "total_flos": 4.732499294618889e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e75512fbedd8d7adaa6c4c34c4ac863b89edc805a7194b74d72eea23cbb4e11b
+oid sha256:bfb425b9bd2d7db89a175b6be9f6f3add2f5419aac09b70a86f8357b95b72148
 size 449450757