Training in progress, step 840000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d676bdecf6cef07d6d1557838930ff920f76201e2414575a644361d9ebd0ca5
+oid sha256:fc81750a4eb225fa74ef3e834e447b2cf3b9d46b04a3dcc0606a474798d1e20b
 size 893439185

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c181b3b0e0340fe0f0c6e90ca26f9e2021277f659fa06f6c810cab95d243c9f
+oid sha256:61d539fc493053cb9a04c81161d0492689b9ab7fcaaea2c1a24a3e6ce4acc990
 size 449471589

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10fb0b6575db7cc3fd463d26671f67a57f4c817b1f162f6dd70df0ba155fea6a
+oid sha256:a81aaecde25369e5575d31d6c4641f897f68348ded1792ee668fac75f81b865d
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b966173ec2647fe3f9ce64251f9ba275015c518c4e11801d8a5787cb53077e4
+oid sha256:91bed33973e1e6566de030884af5ce2f52f782d9e7ad79ccceffa9ead0f4b212
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:626675f0b56b6320753b402844bd4c05cb33ef3bdd886b37ae3b7133c13f9441
+oid sha256:83dc738e3825b6749be56158669ca941276cf2897108d6fb521bf33692ea02ee
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25a0cb16e446a0582e61cafe4a89816af44798dc1964f3425f293eb3e6cf9c2b
+oid sha256:4ad21b9ae0990cf2f16f8fe417227b8f259cc3ef9a1ae3ddbfa629ee1f04f4cc
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b44f4d1ea700e774f5dee0343ba4324675c77c29852dd54fec6a281d849ccd3b
+oid sha256:b75da63b821a4c72c4b37f39fc301b88ce6e4d7dc37edf4f078b7f5706f736e3
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 12.67427122940431,
-  "global_step": 830000,
+  "epoch": 12.82697329240918,
+  "global_step": 840000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -6148,11 +6148,85 @@
       "eval_samples_per_second": 1364.889,
       "eval_steps_per_second": 21.838,
       "step": 830000
+    },
+    {
+      "epoch": 12.69,
+      "learning_rate": 2.0650267139558772e-05,
+      "loss": 0.2339,
+      "step": 831000
+    },
+    {
+      "epoch": 12.7,
+      "learning_rate": 2.052785098775293e-05,
+      "loss": 0.2339,
+      "step": 832000
+    },
+    {
+      "epoch": 12.72,
+      "learning_rate": 2.04060852138404e-05,
+      "loss": 0.234,
+      "step": 833000
+    },
+    {
+      "epoch": 12.74,
+      "learning_rate": 2.028497114943219e-05,
+      "loss": 0.234,
+      "step": 834000
+    },
+    {
+      "epoch": 12.75,
+      "learning_rate": 2.0164510119012263e-05,
+      "loss": 0.2338,
+      "step": 835000
+    },
+    {
+      "epoch": 12.75,
+      "eval_runtime": 0.7099,
+      "eval_samples_per_second": 1408.578,
+      "eval_steps_per_second": 22.537,
+      "step": 835000
+    },
+    {
+      "epoch": 12.77,
+      "learning_rate": 2.0044703439923217e-05,
+      "loss": 0.2336,
+      "step": 836000
+    },
+    {
+      "epoch": 12.78,
+      "learning_rate": 1.9925552422351654e-05,
+      "loss": 0.2338,
+      "step": 837000
+    },
+    {
+      "epoch": 12.8,
+      "learning_rate": 1.9807058369314016e-05,
+      "loss": 0.2335,
+      "step": 838000
+    },
+    {
+      "epoch": 12.81,
+      "learning_rate": 1.968922257664231e-05,
+      "loss": 0.2337,
+      "step": 839000
+    },
+    {
+      "epoch": 12.83,
+      "learning_rate": 1.9572046332969825e-05,
+      "loss": 0.2335,
+      "step": 840000
+    },
+    {
+      "epoch": 12.83,
+      "eval_runtime": 0.7491,
+      "eval_samples_per_second": 1334.897,
+      "eval_steps_per_second": 21.358,
+      "step": 840000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 16,
-  "total_flos": 5.818313780701028e+22,
+  "total_flos": 5.888414041731375e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c181b3b0e0340fe0f0c6e90ca26f9e2021277f659fa06f6c810cab95d243c9f
+oid sha256:61d539fc493053cb9a04c81161d0492689b9ab7fcaaea2c1a24a3e6ce4acc990
 size 449471589