Training in progress, step 800000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20b6bf8d8d5ac37a0b6971256a9cb8002960aa2ad847514a0c95822b7371956c
+oid sha256:3a28142d72c1a639c002962982eef85320960aec72ba5875c70ba183bc4428b1
 size 893441093

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f69469f2f4fdd57ec4edb31c8576ad74c022cba61a82ed361e8c725a8bfd2e3
+oid sha256:ce05dc3d2487d7ae9aa6b0c59ea7f4616a5a7c54ca64071fd6c540348ab08786
 size 449450757

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5afad9e10e656b39d9c034eb9ad27905a1d701ec7ef4e06fa31f7ac951907d8c
+oid sha256:81c65759179a0409080d1617c50ff7701ce92dbb64fc3e317b9b62050537c3c7
 size 14583

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03e2d491d974215512be82d6817d741af1d742ce064c8b5b0baa9340cdbe75ca
+oid sha256:44a3c67c522ab27350032a90eb3d95a3dabd1324000cbd2835b62067512227df
 size 14583

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0bcd5267c0fedea8e2e55ea80159101ae68ee5e1146b9a301bf39c2aa9967fc9
+oid sha256:9d08d861261452452fd94fae84216cedf28f7702bcc30b7c349d5fe92376b24f
 size 14583

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:520166b189f0edf67170e629d5706d1486c93dc11ca389dea5cc1d7e88d1c779
+oid sha256:68acbc45c81b60f69d2a54d496b38309d0cdcd82a52bd9be2a013dfa91b5b790
 size 14583

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b0087d17439da3954b20dcc50e6499dffee5c672acc2c36f39d3118a283f2182
+oid sha256:f7bd01ddf08fc5e563abc90c1bcd231f2103e9ae4cae190ae9888d8dbb7258d1
 size 14583

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4fbf378409b94ea4e42885f8fd80f66f4b8772dfb60fc2828754427211bf4250
+oid sha256:294721238c7a8c697c0dc55ae3f4c4580f7fc2de42c41858980ea55e897cb68b
 size 14583

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1391cf6e3c77ca8f90819d71da90612fe1be4331051d0d6f5e3bcd7b00dcd5f4
+oid sha256:a269e37b31e512e59995e2d8559babba1725032fdbd7ed2e8cd2d1c9cdf42315
 size 14583

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:551b9dc6c1d0749787d20f6ec1e55e5ed180247a2ee512bc66f5e7851b51c414
+oid sha256:5ada5eca471a55afc26d1f38512d1163ebd3e62514e19a602711641b70fa1cc7
 size 14583

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:228d16b33dbcec485ca9a2cd36ed151eb467accc3519b3dbd8f821e5f67aeb40
+oid sha256:bc1b9455cfc1cc0d89898dcc5885e6586d120f989c1d84c4e74dce29a1aeae31
 size 627

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.119578128363135,
-  "global_step": 790000,
+  "epoch": 1.1395078164236574,
+  "global_step": 800000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -9486,11 +9486,131 @@
       "learning_rate": 2.6211922240019883e-05,
       "loss": 0.2908,
       "step": 790000
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 2.6137923994427768e-05,
+      "loss": 0.2911,
+      "step": 790500
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 2.6064073005694758e-05,
+      "loss": 0.2909,
+      "step": 791000
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 2.5990369475726598e-05,
+      "loss": 0.2898,
+      "step": 791500
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 2.591681360602595e-05,
+      "loss": 0.2902,
+      "step": 792000
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 2.5843405597691748e-05,
+      "loss": 0.2909,
+      "step": 792500
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 2.577014565141866e-05,
+      "loss": 0.2899,
+      "step": 793000
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 2.569703396749661e-05,
+      "loss": 0.2905,
+      "step": 793500
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 2.562407074581014e-05,
+      "loss": 0.2908,
+      "step": 794000
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 2.5551256185837897e-05,
+      "loss": 0.2904,
+      "step": 794500
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 2.5478590486652137e-05,
+      "loss": 0.2905,
+      "step": 795000
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 2.5406073846918076e-05,
+      "loss": 0.2901,
+      "step": 795500
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 2.533370646489347e-05,
+      "loss": 0.2904,
+      "step": 796000
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 2.526148853842796e-05,
+      "loss": 0.2903,
+      "step": 796500
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 2.5189420264962586e-05,
+      "loss": 0.2898,
+      "step": 797000
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 2.5117501841529297e-05,
+      "loss": 0.291,
+      "step": 797500
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 2.504573346475026e-05,
+      "loss": 0.2897,
+      "step": 798000
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 2.497411533083753e-05,
+      "loss": 0.2901,
+      "step": 798500
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 2.4902647635592324e-05,
+      "loss": 0.2909,
+      "step": 799000
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 2.483133057440458e-05,
+      "loss": 0.2899,
+      "step": 799500
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 2.476016434225246e-05,
+      "loss": 0.2901,
+      "step": 800000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 2,
-  "total_flos": 5.340954623628781e+22,
+  "total_flos": 5.4085624444111735e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f69469f2f4fdd57ec4edb31c8576ad74c022cba61a82ed361e8c725a8bfd2e3
+oid sha256:ce05dc3d2487d7ae9aa6b0c59ea7f4616a5a7c54ca64071fd6c540348ab08786
 size 449450757