Training in progress, step 950000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eecce8a24d008f6560478b115a93f60ad26f968d3ddf31f980be259930161927
+oid sha256:2c2cdf0990859411fb7c85ca63e432d10f1471e48dc5f4dc74184b1445318034
 size 893441093

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e98104480ffe165c63b6085beb91814af4abc00786a31fbe9ca7364388e7fd7
+oid sha256:79b1f53feeac1b0edb668de9a470df4f2aa602aafbbbab02b19fa387a049f810
 size 449450757

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e5a9ccad5520e92d8772f310d7fdda3e07cfbb13ef5c7d62c7867e7bebc124b
+oid sha256:b45d64f58ccbc19a103ee2b486e3ae0d8fd8e258fc7af4c2eaad0b83f3fc572a
 size 14583

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c122c7c46f7a52340c6d76de6ecac3033b4eb22c4f622df7095c80bbdc58bbda
+oid sha256:37baaaf1d34b48eab4b9f1b1e6566c4b0dfab731d43bb497206f05b08fc421b1
 size 14583

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed89074af6bf56092de6f7f69bec6b0962f68e0ef26b7f849107336565f843e4
+oid sha256:cabc42515409358ec344dd617c3827e15301aec86dd40b0703aaa747b9ab648c
 size 14583

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c180309b549d4feb0af8c96f555ed5574acd58bfc58b660812ae5e9d9e08c50
+oid sha256:4a0e8f2e6be0cbf1f9833f696c2eada7987f3d4cdaf496d37f24cbf254d548cb
 size 14583

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f0bb0af833997f5b0c50461291524b2fc678bcc9d26f6e79d5bfe28f62abb339
+oid sha256:47f83c0e7dd1b3e03445f4411dbb9c9cc1bcbb9c018fe7bb512c0dfe29ba0b84
 size 14583

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:824645f1c25785303da3dc203bf2689aba1f62a78c6bdfef5a484af4a0860aef
+oid sha256:0346809d8d3cd0e408dd0cf4407790a6097435d9d23dfae50689beef17f52894
 size 14583

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e242b745198753e15159abe0972314bc254dd07db526f1dc4d19cc5c285dfb8e
+oid sha256:8e01ce41a891cf7dcd8a18eccba168a8c04bb813917e1e626e5c83157e4ba5c0
 size 14583

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0e565516de72353a91a8afad67f1979b57e142666bec47e27765241642f3d4f
+oid sha256:8c9b4e343a2af7c2bb37729c1a96b7743275839cf7669689259960b84916a4f7
 size 14583

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a619368d8fa94ba3412b069e884d3c02325231635774dd381c11c0f2a15299d7
+oid sha256:7ad6f8d9094ac28168658283f3ee5d2511e53f4b22c1d6e5c9b4e90d7a8c2ccb
 size 627

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.418523449270972,
-  "global_step": 940000,
+  "epoch": 1.4384531373314946,
+  "global_step": 950000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -11286,11 +11286,131 @@
       "learning_rate": 1.1373402388763346e-05,
       "loss": 0.2834,
       "step": 940000
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 1.1350681316526965e-05,
+      "loss": 0.2837,
+      "step": 940500
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 1.1328147928906494e-05,
+      "loss": 0.2842,
+      "step": 941000
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 1.1305802287507358e-05,
+      "loss": 0.2839,
+      "step": 941500
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 1.1283644453421678e-05,
+      "loss": 0.284,
+      "step": 942000
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 1.1261674487228149e-05,
+      "loss": 0.2839,
+      "step": 942500
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 1.1239892448991798e-05,
+      "loss": 0.2834,
+      "step": 943000
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 1.1218298398263894e-05,
+      "loss": 0.2833,
+      "step": 943500
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 1.1196892394081743e-05,
+      "loss": 0.284,
+      "step": 944000
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 1.1175674494968552e-05,
+      "loss": 0.2833,
+      "step": 944500
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 1.1154644758933235e-05,
+      "loss": 0.2835,
+      "step": 945000
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 1.11338032434703e-05,
+      "loss": 0.2832,
+      "step": 945500
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 1.1113150005559644e-05,
+      "loss": 0.2836,
+      "step": 946000
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 1.1092685101666438e-05,
+      "loss": 0.284,
+      "step": 946500
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 1.1072408587740942e-05,
+      "loss": 0.2836,
+      "step": 947000
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 1.1052320519218383e-05,
+      "loss": 0.2833,
+      "step": 947500
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 1.1032420951018755e-05,
+      "loss": 0.2841,
+      "step": 948000
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 1.1012709937546722e-05,
+      "loss": 0.2837,
+      "step": 948500
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 1.0993187532691458e-05,
+      "loss": 0.2844,
+      "step": 949000
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 1.0973853789826454e-05,
+      "loss": 0.2842,
+      "step": 949500
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 1.0954708761809438e-05,
+      "loss": 0.2843,
+      "step": 950000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 2,
-  "total_flos": 6.355066839128279e+22,
+  "total_flos": 6.422672857591212e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e98104480ffe165c63b6085beb91814af4abc00786a31fbe9ca7364388e7fd7
+oid sha256:79b1f53feeac1b0edb668de9a470df4f2aa602aafbbbab02b19fa387a049f810
 size 449450757