Training in progress, step 880000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7de9e7a475185d5a4f5233f2eaa1e382e39bf61b0b26422c710d12b1c428f053
+oid sha256:f011531683b29e6010c43a1101dacea9ed4a18363936f0bda8424b0b64fd61d5
 size 893441093

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2cc5f078f248ee95608611561bbd9aea19a49de30cb9f351661140392a113dcb
+oid sha256:761b97519f5fabc1226f543fdfda1e57b01e50e22126717fe93929f009e6d948
 size 449450757

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc1e6c47e318d84077f6a967794dd3042b980af9f2017841afbd1886d7db9904
+oid sha256:935da3b045c8c8b8ce754d2c39cf0981b2085a82929dd47cd40a448687388e6a
 size 14583

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4623ab6fbb26e814bfa3dd96c774e4b841513bb02553b1e19ff1a3408dd2f2ba
+oid sha256:bbdeea7578a634cee6754d432445c1d3c22f4d3700bcbfbce695f5cbf096739a
 size 14583

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b84195dd425f6794c5806a9bed14c1dd56437e46af995a7b88fe65b75813426e
+oid sha256:c6c5ff5b48c10910314f1846b5d56765a69ff07e0a1c2179950e7e708be45c72
 size 14583

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a330644903d9cebc0a0cef1ede19ebdfcc46633ad2affcbf69e9f23412d356cb
+oid sha256:538db9627b3319da412d82dd2d788799c67c9fd4db76e45825c3a463b4ec891a
 size 14583

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d23d54ddb4a3e42a55be419de46e8b2afb37f587b9bc4ebb416244cb1aa1460d
+oid sha256:cefdc80aebec1bb7388820de673e9b9482e6730079e6308c4991cb6f1f6a1673
 size 14583

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50c90440bc56cdec79071a507653e9cc50024a2dbba647fc3d934431503f32da
+oid sha256:078a7ec7b0b49e632a586c20c54dd7869580bfe51e6466659e4a1c049cec1d5c
 size 14583

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f41c8eaa88d8a5dc08e3c2e3def98b7a8b86cad84a79d3f83ed3a1a7c681beb0
+oid sha256:d0ee34e421a4579fb938367d875bd6d0e9cb1e7cc940564954160dbbd10ab58c
 size 14583

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1faf83b262a97abbbb6024851cdc5f7c1c92261d8aa4e9260f21590a330cc4e
+oid sha256:d7f6c3ac5b3d9ff9275bcc6f2b68cf34b2b33a4d26ba0d17a6dea955ffb4848b
 size 14583

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:843b249180999e01b18cb497ce97e55f21bbe186ae977c32256fbedc40db0e39
+oid sha256:c6c3b9739e151e083ac7876c028ada3eeb37ab066447f172eee69fac580c5323
 size 627

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.2790156328473148,
-  "global_step": 870000,
+  "epoch": 1.2989453209078372,
+  "global_step": 880000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -10446,11 +10446,131 @@
       "learning_rate": 1.6369542546558626e-05,
       "loss": 0.2864,
       "step": 870000
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 1.6321390014277996e-05,
+      "loss": 0.2868,
+      "step": 870500
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 1.6273411576885517e-05,
+      "loss": 0.2869,
+      "step": 871000
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 1.6225607365552378e-05,
+      "loss": 0.2863,
+      "step": 871500
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 1.617797751097349e-05,
+      "loss": 0.2866,
+      "step": 872000
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 1.6130522143367032e-05,
+      "loss": 0.2868,
+      "step": 872500
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 1.608324139247421e-05,
+      "loss": 0.2864,
+      "step": 873000
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 1.6036135387558756e-05,
+      "loss": 0.2862,
+      "step": 873500
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 1.5989204257406693e-05,
+      "loss": 0.286,
+      "step": 874000
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 1.594244813032595e-05,
+      "loss": 0.286,
+      "step": 874500
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 1.5895867134145974e-05,
+      "loss": 0.2861,
+      "step": 875000
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 1.5849461396217467e-05,
+      "loss": 0.2855,
+      "step": 875500
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 1.5803231043411912e-05,
+      "loss": 0.286,
+      "step": 876000
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 1.575717620212132e-05,
+      "loss": 0.2867,
+      "step": 876500
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 1.5711296998257902e-05,
+      "loss": 0.2867,
+      "step": 877000
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 1.5665593557253623e-05,
+      "loss": 0.2865,
+      "step": 877500
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 1.562006600405996e-05,
+      "loss": 0.286,
+      "step": 878000
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 1.5574714463147512e-05,
+      "loss": 0.2857,
+      "step": 878500
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 1.5529539058505624e-05,
+      "loss": 0.286,
+      "step": 879000
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 1.5484539913642175e-05,
+      "loss": 0.2862,
+      "step": 879500
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 1.543971715158307e-05,
+      "loss": 0.2863,
+      "step": 880000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 2,
-  "total_flos": 5.881811674297794e+22,
+  "total_flos": 5.949418752030229e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2cc5f078f248ee95608611561bbd9aea19a49de30cb9f351661140392a113dcb
+oid sha256:761b97519f5fabc1226f543fdfda1e57b01e50e22126717fe93929f009e6d948
 size 449450757