Training in progress, step 890000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f011531683b29e6010c43a1101dacea9ed4a18363936f0bda8424b0b64fd61d5
+oid sha256:7aed45f0ab31dea98b9869760d36ab73a26078c09333a23350a1212c72042c48
 size 893441093

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:761b97519f5fabc1226f543fdfda1e57b01e50e22126717fe93929f009e6d948
+oid sha256:07c213d1a42d199003850d981d6ccc1a53b07b35352b3c677b2fec2729c3a474
 size 449450757

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:935da3b045c8c8b8ce754d2c39cf0981b2085a82929dd47cd40a448687388e6a
+oid sha256:c77bc69e9635ccd1de21423522e341a85a08863f86590b713104bba2dbfd70bb
 size 14583

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bbdeea7578a634cee6754d432445c1d3c22f4d3700bcbfbce695f5cbf096739a
+oid sha256:1993aafd21a33893d293353cc2d3a986655d484aa3f8d8bd3ce1158082956b62
 size 14583

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6c5ff5b48c10910314f1846b5d56765a69ff07e0a1c2179950e7e708be45c72
+oid sha256:d31a0dbc0a9de5b13d8d236df1a529fa25f2a462a9bcc23416d4f0397bad521d
 size 14583

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:538db9627b3319da412d82dd2d788799c67c9fd4db76e45825c3a463b4ec891a
+oid sha256:f2118e2247b5fdbceb9d1ec4a69c6b9d09754ac3081a89daca9da9f417d9a57c
 size 14583

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cefdc80aebec1bb7388820de673e9b9482e6730079e6308c4991cb6f1f6a1673
+oid sha256:5ce1b40c469ef20ff3c2e73618244894f6c048059642c597ebc6bc915a80cce6
 size 14583

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:078a7ec7b0b49e632a586c20c54dd7869580bfe51e6466659e4a1c049cec1d5c
+oid sha256:ce8dd4b4014883403bd302ffd7cbfd4827bc6596e89d4a566a074b59e6257940
 size 14583

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0ee34e421a4579fb938367d875bd6d0e9cb1e7cc940564954160dbbd10ab58c
+oid sha256:c955d0a8374d68c8c7fd0b4a59ac81688e461d16a4ab83367d33bbcd82c828c2
 size 14583

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d7f6c3ac5b3d9ff9275bcc6f2b68cf34b2b33a4d26ba0d17a6dea955ffb4848b
+oid sha256:e5d88d03c1c6897f3e815db204f99493002f497118b104ebefc70815e22888c1
 size 14583

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6c3b9739e151e083ac7876c028ada3eeb37ab066447f172eee69fac580c5323
+oid sha256:f1d5e819bb6a0b170d191713e427e3ac82a202a5b895fa2fdb4da78756f26177
 size 627

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.2989453209078372,
-  "global_step": 880000,
+  "epoch": 1.3188750089683596,
+  "global_step": 890000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -10566,11 +10566,131 @@
       "learning_rate": 1.543971715158307e-05,
       "loss": 0.2863,
       "step": 880000
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 1.539507089487205e-05,
+      "loss": 0.2865,
+      "step": 880500
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 1.535060126557028e-05,
+      "loss": 0.2861,
+      "step": 881000
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 1.5306308385255997e-05,
+      "loss": 0.2859,
+      "step": 881500
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 1.5262192375024284e-05,
+      "loss": 0.2856,
+      "step": 882000
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 1.521825335548661e-05,
+      "loss": 0.2861,
+      "step": 882500
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 1.5174491446770566e-05,
+      "loss": 0.2866,
+      "step": 883000
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 1.5130906768519563e-05,
+      "loss": 0.2862,
+      "step": 883500
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 1.508749943989242e-05,
+      "loss": 0.2864,
+      "step": 884000
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 1.5044269579563144e-05,
+      "loss": 0.286,
+      "step": 884500
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 1.500121730572051e-05,
+      "loss": 0.2859,
+      "step": 885000
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 1.4958342736067783e-05,
+      "loss": 0.2856,
+      "step": 885500
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 1.4915645987822406e-05,
+      "loss": 0.2858,
+      "step": 886000
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 1.4873127177715653e-05,
+      "loss": 0.2847,
+      "step": 886500
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 1.4830786421992347e-05,
+      "loss": 0.2863,
+      "step": 887000
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 1.4788623836410479e-05,
+      "loss": 0.2857,
+      "step": 887500
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 1.4746639536240942e-05,
+      "loss": 0.2856,
+      "step": 888000
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 1.4704833636267232e-05,
+      "loss": 0.2858,
+      "step": 888500
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 1.4663206250785055e-05,
+      "loss": 0.2854,
+      "step": 889000
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 1.4621757493602125e-05,
+      "loss": 0.2857,
+      "step": 889500
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 1.4580487478037748e-05,
+      "loss": 0.2854,
+      "step": 890000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 2,
-  "total_flos": 5.949418752030229e+22,
+  "total_flos": 6.017029328628566e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:761b97519f5fabc1226f543fdfda1e57b01e50e22126717fe93929f009e6d948
+oid sha256:07c213d1a42d199003850d981d6ccc1a53b07b35352b3c677b2fec2729c3a474
 size 449450757