Training in progress, step 990000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a37ff0bb2125ba916e184875051de31c0a53ab6d8764d350d94b8f895cf97825
+oid sha256:d0c84155e298a5a6b7ee070a8179e83bcd232eb2e5869a2fab62635fe434a15b
 size 893441093

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29e72a077e735dda0d42d87bba36bdd29e6f03ff47e8d9d7c8531209111d469e
+oid sha256:6119a41cc84dfc82b1ad8e160d2de4f6723c4c70df2567e7b05d5135b2ad413c
 size 449450757

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22c34d3305b209ee825f5aed33939719436301cfaf9de55d7b3b5639a3350e80
+oid sha256:5d92331d191f9b54e8682c7179f1d46d8e4298cbee5bf860f80c01313d919cbf
 size 14583

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6315416921462fe0ecc7a0c3f368f4b3c932064b761ab22ca7678bb4befc6c5
+oid sha256:2b3f3f7f2089f141dbb6bfd17083ac633b398668fbdd29b4239ed78cd16828ef
 size 14583

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a76def7122ba11f5e0b58c3da4b2e90151c2789ca35782d50ddc98428cb6201
+oid sha256:6a1e11f0bc52abbbd19f8d4cb2af2cb9140b19cf7c5678a2b90ba0e9593a2025
 size 14583

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8dd7ce8763729f28d8acde8cd6b3dfea779e9b4dbaa1cc534d994758c7e6d95d
+oid sha256:bffc19433b361587fa636d9fe7f366ad621d886a3e88e7b929e925c972115064
 size 14583

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3093dd66e653e1347d48de0c3738e9baef47fa7023af660daaa6d276c2516c1c
+oid sha256:baf40a9092f2a61c65fa8d4b01ad107ecd14742f4e2c480971b7e313c2ab669b
 size 14583

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c71863cae64230816d8f7da13edddd177d84ad915ea936c18a2d7e479676590
+oid sha256:35d8ccac7b1580c03e5bd6e78ceed5d6b1e846215ceb31ec6a8e03829af4c92e
 size 14583

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1106c2b8026b5aad28464b0bd2b8b204a664cd4c27abf0a87c50c85c6899ce87
+oid sha256:5a564015df3012aed298103a98abad0123fee1b00b18b24191670937f37a6281
 size 14583

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4abf64edbda9080a72948f7486c0ac7635f48e74d5752a1a9ab0d947e838bf23
+oid sha256:a3839c7b56c36b9afc190821fb76a047c055639f3ce0f32d8cdce397cba6fa5f
 size 14583

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f6a86f148673573f563d78ae30ad4429d07d6c9eca28255a514457fc218ec48
+oid sha256:b8600853d84ba2918d905e70ba99b5bea80c1839bef1da439315875bb3ad462d
 size 627

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.4982422015130619,
-  "global_step": 980000,
+  "epoch": 1.5181718895735843,
+  "global_step": 990000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -11766,11 +11766,131 @@
       "learning_rate": 1.0153046094685783e-05,
       "loss": 0.2831,
       "step": 980000
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 1.0145492062574731e-05,
+      "loss": 0.2826,
+      "step": 980500
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 1.0138129010020992e-05,
+      "loss": 0.2831,
+      "step": 981000
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 1.0130956957154867e-05,
+      "loss": 0.2831,
+      "step": 981500
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 1.0123975923584488e-05,
+      "loss": 0.2824,
+      "step": 982000
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 1.0117185928395721e-05,
+      "loss": 0.2828,
+      "step": 982500
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 1.0110586990152152e-05,
+      "loss": 0.2831,
+      "step": 983000
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 1.0104179126895039e-05,
+      "loss": 0.2829,
+      "step": 983500
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 1.0097962356143219e-05,
+      "loss": 0.2831,
+      "step": 984000
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 1.009193669489312e-05,
+      "loss": 0.2834,
+      "step": 984500
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 1.0086102159618668e-05,
+      "loss": 0.2834,
+      "step": 985000
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 1.0080458766271252e-05,
+      "loss": 0.2832,
+      "step": 985500
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 1.0075006530279694e-05,
+      "loss": 0.2833,
+      "step": 986000
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 1.0069745466550205e-05,
+      "loss": 0.2827,
+      "step": 986500
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 1.0064675589466339e-05,
+      "loss": 0.2821,
+      "step": 987000
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 1.005979691288893e-05,
+      "loss": 0.2834,
+      "step": 987500
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 1.0055109450156098e-05,
+      "loss": 0.2831,
+      "step": 988000
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 1.0050613214083197e-05,
+      "loss": 0.2822,
+      "step": 988500
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 1.0046308216962759e-05,
+      "loss": 0.2826,
+      "step": 989000
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 1.0042194470564472e-05,
+      "loss": 0.2824,
+      "step": 989500
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 1.0038271986135177e-05,
+      "loss": 0.2827,
+      "step": 990000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 2,
-  "total_flos": 6.625495046923828e+22,
+  "total_flos": 6.693099686599179e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29e72a077e735dda0d42d87bba36bdd29e6f03ff47e8d9d7c8531209111d469e
+oid sha256:6119a41cc84dfc82b1ad8e160d2de4f6723c4c70df2567e7b05d5135b2ad413c
 size 449450757