Training in progress, step 940000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46ff1d8d7d94b8fc5390751564ccb419f91a9858db9bdfd9f11bebe5113b944a
+oid sha256:eecce8a24d008f6560478b115a93f60ad26f968d3ddf31f980be259930161927
 size 893441093

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d2bac07d166f73980c3c9cce6825ce7a1c1f5f22b97d0264ce5e7ba42eeb3df
+oid sha256:3e98104480ffe165c63b6085beb91814af4abc00786a31fbe9ca7364388e7fd7
 size 449450757

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:523ad7de15419f9770d9e7768264983ffe3ed3b6b2e41d3411de9307e3568dda
+oid sha256:6e5a9ccad5520e92d8772f310d7fdda3e07cfbb13ef5c7d62c7867e7bebc124b
 size 14583

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f02b76320d64a6c1fa36467fd16fb842d38967c6960f680698d2b6c46fa9ddb
+oid sha256:c122c7c46f7a52340c6d76de6ecac3033b4eb22c4f622df7095c80bbdc58bbda
 size 14583

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb4ba7042a42dc2dddfda89081c338c759af082271bf3d6b2249d374dfb5549f
+oid sha256:ed89074af6bf56092de6f7f69bec6b0962f68e0ef26b7f849107336565f843e4
 size 14583

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d492de85ba9ca1e7e895ebf249111dbc1e669c10034dc3697642d6b066377bc6
+oid sha256:3c180309b549d4feb0af8c96f555ed5574acd58bfc58b660812ae5e9d9e08c50
 size 14583

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87bf88b63314cf7e6bc76f627a1120e94df3871d06e2e6a10b31a22c360f0003
+oid sha256:f0bb0af833997f5b0c50461291524b2fc678bcc9d26f6e79d5bfe28f62abb339
 size 14583

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b861dd3cac874664255fa5c36d008a64ba119b36b6461f68fec95ff34294b32
+oid sha256:824645f1c25785303da3dc203bf2689aba1f62a78c6bdfef5a484af4a0860aef
 size 14583

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b64737ac04d5942009955008d940bd1d1005db5a2c22b7982f258d011e0ad8cb
+oid sha256:e242b745198753e15159abe0972314bc254dd07db526f1dc4d19cc5c285dfb8e
 size 14583

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1bb15e8b762074a6cf94106e13146d7507cbb10c383c4eadc6b62f549780de27
+oid sha256:a0e565516de72353a91a8afad67f1979b57e142666bec47e27765241642f3d4f
 size 14583

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8bf7fa4ff5edd25c6aca18d0779a09bdac81be773b8a02595b2a01362d92297
+oid sha256:a619368d8fa94ba3412b069e884d3c02325231635774dd381c11c0f2a15299d7
 size 627

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.3985937612104495,
-  "global_step": 930000,
+  "epoch": 1.418523449270972,
+  "global_step": 940000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -11166,11 +11166,131 @@
       "learning_rate": 1.1867138192639601e-05,
       "loss": 0.2842,
       "step": 930000
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 1.1840677154152987e-05,
+      "loss": 0.2848,
+      "step": 930500
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 1.1814402460652382e-05,
+      "loss": 0.2842,
+      "step": 931000
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 1.178831418397181e-05,
+      "loss": 0.2839,
+      "step": 931500
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 1.176241239543558e-05,
+      "loss": 0.2842,
+      "step": 932000
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 1.173669716585822e-05,
+      "loss": 0.2847,
+      "step": 932500
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 1.171116856554418e-05,
+      "loss": 0.2836,
+      "step": 933000
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 1.168582666428768e-05,
+      "loss": 0.284,
+      "step": 933500
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 1.1660671531372517e-05,
+      "loss": 0.2837,
+      "step": 934000
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 1.1635703235571846e-05,
+      "loss": 0.2848,
+      "step": 934500
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 1.1610921845148052e-05,
+      "loss": 0.2845,
+      "step": 935000
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 1.1586327427852503e-05,
+      "loss": 0.2847,
+      "step": 935500
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 1.156192005092539e-05,
+      "loss": 0.2843,
+      "step": 936000
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 1.153769978109557e-05,
+      "loss": 0.2836,
+      "step": 936500
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 1.1513666684580308e-05,
+      "loss": 0.2847,
+      "step": 937000
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 1.1489820827085185e-05,
+      "loss": 0.2839,
+      "step": 937500
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 1.1466162273803876e-05,
+      "loss": 0.2844,
+      "step": 938000
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 1.144269108941795e-05,
+      "loss": 0.284,
+      "step": 938500
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 1.1419407338096732e-05,
+      "loss": 0.285,
+      "step": 939000
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 1.1396311083497103e-05,
+      "loss": 0.2841,
+      "step": 939500
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 1.1373402388763346e-05,
+      "loss": 0.2834,
+      "step": 940000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 2,
-  "total_flos": 6.287461350629951e+22,
+  "total_flos": 6.355066839128279e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d2bac07d166f73980c3c9cce6825ce7a1c1f5f22b97d0264ce5e7ba42eeb3df
+oid sha256:3e98104480ffe165c63b6085beb91814af4abc00786a31fbe9ca7364388e7fd7
 size 449450757