Training in progress, step 230000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f433a536827dfe71e22cc9ae1b5c51f05bbb1bc2aaf2cf12bf5dc6dc12de9e5
+oid sha256:a86561053adee90a2878214be6885b067bd76d574ba4d67a50de8ddc88d4e78d
 size 50044689

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03379cedc2b74fd0a67255e5dc1c2b3e73605ea40a87df2cb44842e9ffa68b98
+oid sha256:1bd756189a715f251243356fce3a9e9698eaa1c9541391c5ada1cd1bb927f2ca
 size 25761253

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:314d5ecbfbb389ee2a386d01176df549ad45d90c274986b7501f19ad88f8a435
+oid sha256:e3ae95e0a0d1a9ec67488894572c036dc35bd82e51ffb0fbd0fcc0a47e5aff06
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:314d5ecbfbb389ee2a386d01176df549ad45d90c274986b7501f19ad88f8a435
+oid sha256:e3ae95e0a0d1a9ec67488894572c036dc35bd82e51ffb0fbd0fcc0a47e5aff06
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:314d5ecbfbb389ee2a386d01176df549ad45d90c274986b7501f19ad88f8a435
+oid sha256:e3ae95e0a0d1a9ec67488894572c036dc35bd82e51ffb0fbd0fcc0a47e5aff06
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:314d5ecbfbb389ee2a386d01176df549ad45d90c274986b7501f19ad88f8a435
+oid sha256:e3ae95e0a0d1a9ec67488894572c036dc35bd82e51ffb0fbd0fcc0a47e5aff06
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:314d5ecbfbb389ee2a386d01176df549ad45d90c274986b7501f19ad88f8a435
+oid sha256:e3ae95e0a0d1a9ec67488894572c036dc35bd82e51ffb0fbd0fcc0a47e5aff06
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:314d5ecbfbb389ee2a386d01176df549ad45d90c274986b7501f19ad88f8a435
+oid sha256:e3ae95e0a0d1a9ec67488894572c036dc35bd82e51ffb0fbd0fcc0a47e5aff06
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:314d5ecbfbb389ee2a386d01176df549ad45d90c274986b7501f19ad88f8a435
+oid sha256:e3ae95e0a0d1a9ec67488894572c036dc35bd82e51ffb0fbd0fcc0a47e5aff06
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:314d5ecbfbb389ee2a386d01176df549ad45d90c274986b7501f19ad88f8a435
+oid sha256:e3ae95e0a0d1a9ec67488894572c036dc35bd82e51ffb0fbd0fcc0a47e5aff06
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49c292ab14a993919881f01d5b74688df2db2f4ea7c017c2175d0fea64e57565
+oid sha256:cde8387b01007811ac1b94d9590ed8f2f119f8e7b49d5ce42fb838c1939b856b
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 9.814418272662383,
-  "global_step": 220000,
+  "epoch": 10.260528194147037,
+  "global_step": 230000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -4406,11 +4406,211 @@
       "eval_samples_per_second": 1040.301,
       "eval_steps_per_second": 16.304,
       "step": 220000
+    },
+    {
+      "epoch": 9.84,
+      "learning_rate": 3.2176382151888054e-05,
+      "loss": 0.365,
+      "step": 220500
+    },
+    {
+      "epoch": 9.86,
+      "learning_rate": 3.1440176210975204e-05,
+      "loss": 0.3649,
+      "step": 221000
+    },
+    {
+      "epoch": 9.86,
+      "eval_loss": 0.3377821445465088,
+      "eval_runtime": 2.2679,
+      "eval_samples_per_second": 1012.829,
+      "eval_steps_per_second": 15.874,
+      "step": 221000
+    },
+    {
+      "epoch": 9.88,
+      "learning_rate": 3.071593666296585e-05,
+      "loss": 0.3648,
+      "step": 221500
+    },
+    {
+      "epoch": 9.9,
+      "learning_rate": 3.000369518844396e-05,
+      "loss": 0.3649,
+      "step": 222000
+    },
+    {
+      "epoch": 9.9,
+      "eval_loss": 0.33791235089302063,
+      "eval_runtime": 2.2027,
+      "eval_samples_per_second": 1042.832,
+      "eval_steps_per_second": 16.344,
+      "step": 222000
+    },
+    {
+      "epoch": 9.93,
+      "learning_rate": 2.9303482943159077e-05,
+      "loss": 0.3648,
+      "step": 222500
+    },
+    {
+      "epoch": 9.95,
+      "learning_rate": 2.861533055666306e-05,
+      "loss": 0.3646,
+      "step": 223000
+    },
+    {
+      "epoch": 9.95,
+      "eval_loss": 0.33819380402565,
+      "eval_runtime": 2.1945,
+      "eval_samples_per_second": 1046.691,
+      "eval_steps_per_second": 16.404,
+      "step": 223000
+    },
+    {
+      "epoch": 9.97,
+      "learning_rate": 2.793926813097066e-05,
+      "loss": 0.3645,
+      "step": 223500
+    },
+    {
+      "epoch": 9.99,
+      "learning_rate": 2.7275325239242546e-05,
+      "loss": 0.3647,
+      "step": 224000
+    },
+    {
+      "epoch": 9.99,
+      "eval_loss": 0.33774814009666443,
+      "eval_runtime": 2.2427,
+      "eval_samples_per_second": 1024.194,
+      "eval_steps_per_second": 16.052,
+      "step": 224000
+    },
+    {
+      "epoch": 10.02,
+      "learning_rate": 2.6623530924491626e-05,
+      "loss": 0.3645,
+      "step": 224500
+    },
+    {
+      "epoch": 10.04,
+      "learning_rate": 2.5983913698312782e-05,
+      "loss": 0.3644,
+      "step": 225000
+    },
+    {
+      "epoch": 10.04,
+      "eval_loss": 0.33505749702453613,
+      "eval_runtime": 2.2238,
+      "eval_samples_per_second": 1032.916,
+      "eval_steps_per_second": 16.188,
+      "step": 225000
+    },
+    {
+      "epoch": 10.06,
+      "learning_rate": 2.5356501539635512e-05,
+      "loss": 0.3644,
+      "step": 225500
+    },
+    {
+      "epoch": 10.08,
+      "learning_rate": 2.4741321893500244e-05,
+      "loss": 0.3644,
+      "step": 226000
+    },
+    {
+      "epoch": 10.08,
+      "eval_loss": 0.337401807308197,
+      "eval_runtime": 2.2527,
+      "eval_samples_per_second": 1019.654,
+      "eval_steps_per_second": 15.981,
+      "step": 226000
+    },
+    {
+      "epoch": 10.1,
+      "learning_rate": 2.4138401669857587e-05,
+      "loss": 0.3644,
+      "step": 226500
+    },
+    {
+      "epoch": 10.13,
+      "learning_rate": 2.3547767242391212e-05,
+      "loss": 0.3644,
+      "step": 227000
+    },
+    {
+      "epoch": 10.13,
+      "eval_loss": 0.33791208267211914,
+      "eval_runtime": 2.1965,
+      "eval_samples_per_second": 1045.741,
+      "eval_steps_per_second": 16.389,
+      "step": 227000
+    },
+    {
+      "epoch": 10.15,
+      "learning_rate": 2.2969444447364498e-05,
+      "loss": 0.3642,
+      "step": 227500
+    },
+    {
+      "epoch": 10.17,
+      "learning_rate": 2.240345858248992e-05,
+      "loss": 0.3651,
+      "step": 228000
+    },
+    {
+      "epoch": 10.17,
+      "eval_loss": 0.33648931980133057,
+      "eval_runtime": 2.2235,
+      "eval_samples_per_second": 1033.033,
+      "eval_steps_per_second": 16.19,
+      "step": 228000
+    },
+    {
+      "epoch": 10.19,
+      "learning_rate": 2.184983440582284e-05,
+      "loss": 0.3644,
+      "step": 228500
+    },
+    {
+      "epoch": 10.22,
+      "learning_rate": 2.1308596134678134e-05,
+      "loss": 0.3643,
+      "step": 229000
+    },
+    {
+      "epoch": 10.22,
+      "eval_loss": 0.3360297977924347,
+      "eval_runtime": 2.2193,
+      "eval_samples_per_second": 1035.0,
+      "eval_steps_per_second": 16.221,
+      "step": 229000
+    },
+    {
+      "epoch": 10.24,
+      "learning_rate": 2.0779767444571236e-05,
+      "loss": 0.3643,
+      "step": 229500
+    },
+    {
+      "epoch": 10.26,
+      "learning_rate": 2.0263371468182175e-05,
+      "loss": 0.3642,
+      "step": 230000
+    },
+    {
+      "epoch": 10.26,
+      "eval_loss": 0.33706384897232056,
+      "eval_runtime": 2.2761,
+      "eval_samples_per_second": 1009.19,
+      "eval_steps_per_second": 15.817,
+      "step": 230000
     }
   ],
   "max_steps": 250000,
   "num_train_epochs": 12,
-  "total_flos": 3.5236318752081277e+21,
+  "total_flos": 3.683792746091758e+21,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03379cedc2b74fd0a67255e5dc1c2b3e73605ea40a87df2cb44842e9ffa68b98
+oid sha256:1bd756189a715f251243356fce3a9e9698eaa1c9541391c5ada1cd1bb927f2ca
 size 25761253