Training in progress, step 710000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81ece12c6f9c13f5471c677109a4bde83e1a050417df99ad047004ba4276bba6
+oid sha256:640777d4df17094532677050d169633ab25c6e5307fe7b26b1ef2480f2fa436c
 size 893441093

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bfb425b9bd2d7db89a175b6be9f6f3add2f5419aac09b70a86f8357b95b72148
+oid sha256:589beff1989fc9c0ae009d9c4e89cc81dea78aca3df050a942a083e247b0b3bb
 size 449450757

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:513fd308756b62d456cf51dbabd0e5432e6e9f801b69e6b4147b7910a92409c3
+oid sha256:8d73966766ab27f8d8b82049597603e5e27df9de3bfb4bc68f052966836974a7
 size 14583

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1b41b44339013cf2c800ebd15e56c0ab490da939473759245613333c4ad094b
+oid sha256:3d01455789648693f3c874de11c7ed6063a3725328c7accf41053ba2de2ef602
 size 14583

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8acf2390c55c3fcc1c7f54edfdb7e51d825ccf03ad02c2710478f24d67d8d927
+oid sha256:dea50129c89a3bcb4d508277085bd760cf99e8e7596db26b1b0416ea6e662c44
 size 14583

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b884538c1c7cf25c9c76b4e2aeb5b233c0e82af8266b74f74badb8738101de61
+oid sha256:f4ef7983f20d7466e22a66c14b4eb278bac441cabcddf12c2ab45c6a7ad45ccb
 size 14583

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0611954260b29d5933679a0b205628fe7afa2763d89a93117a665d8810ddfaa
+oid sha256:7030fabf7b722e2752b51d9deb3cc7dac4745661c75fe5c48a022d295a9ffb0d
 size 14583

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a2570d894279bdec746170684ab6ee38cfa6adc0692ab4c8e2d19fca72b235d
+oid sha256:db8fd80ed1622a37fb8836b353462fe160453f93a1dbe072cd8bd1e37f25f658
 size 14583

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c360a23dde048e054ef7310a763eb2729b26bcfc6d980f3d3e175d2d2287e150
+oid sha256:9333397ba4ec25f889f96bb6104d7c6cf0bc5fd5c8036f75df959bdd43d52a66
 size 14583

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ded6c10a8ae184d010b20213595dce955d5ae9ca4fec0187e6e124f4763508bf
+oid sha256:58730a986e4ecbe1e49387372f3829be2d2d88e8ab521897bf3b764a726b44be
 size 14583

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:afc49fe155c033502b3ff00fe8f2d949db5aba4e89748d4722dc58fa6f673d45
+oid sha256:335855e99fe5c1eafe16f664b8e35342405853ed0ef1faa2892c2126df9feea5
 size 627

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.3993339170554817,
-  "global_step": 700000,
+  "epoch": 1.4193244015848456,
+  "global_step": 710000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -8406,11 +8406,131 @@
       "learning_rate": 4.171362893143013e-05,
       "loss": 0.2965,
       "step": 700000
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 4.1616785247027506e-05,
+      "loss": 0.2963,
+      "step": 700500
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 4.1520046500868384e-05,
+      "loss": 0.2966,
+      "step": 701000
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 4.1423412957432775e-05,
+      "loss": 0.2963,
+      "step": 701500
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 4.1326884880913074e-05,
+      "loss": 0.2966,
+      "step": 702000
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 4.123046253521341e-05,
+      "loss": 0.2962,
+      "step": 702500
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 4.1134146183948724e-05,
+      "loss": 0.2961,
+      "step": 703000
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 4.1037936090444315e-05,
+      "loss": 0.296,
+      "step": 703500
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 4.0941832517734885e-05,
+      "loss": 0.2959,
+      "step": 704000
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 4.084583572856388e-05,
+      "loss": 0.2962,
+      "step": 704500
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 4.0749945985382915e-05,
+      "loss": 0.2961,
+      "step": 705000
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 4.065416355035087e-05,
+      "loss": 0.296,
+      "step": 705500
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 4.0558488685333235e-05,
+      "loss": 0.2958,
+      "step": 706000
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 4.04629216519015e-05,
+      "loss": 0.2961,
+      "step": 706500
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 4.036746271133223e-05,
+      "loss": 0.2962,
+      "step": 707000
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 4.0272112124606546e-05,
+      "loss": 0.2962,
+      "step": 707500
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 4.0176870152409324e-05,
+      "loss": 0.296,
+      "step": 708000
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 4.008173705512842e-05,
+      "loss": 0.295,
+      "step": 708500
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 3.998671309285417e-05,
+      "loss": 0.2958,
+      "step": 709000
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 3.989179852537839e-05,
+      "loss": 0.2964,
+      "step": 709500
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 3.979699361219395e-05,
+      "loss": 0.2956,
+      "step": 710000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 2,
-  "total_flos": 4.732499294618889e+22,
+  "total_flos": 4.800106373011031e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bfb425b9bd2d7db89a175b6be9f6f3add2f5419aac09b70a86f8357b95b72148
+oid sha256:589beff1989fc9c0ae009d9c4e89cc81dea78aca3df050a942a083e247b0b3bb
 size 449450757