Training in progress, step 850000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc81750a4eb225fa74ef3e834e447b2cf3b9d46b04a3dcc0606a474798d1e20b
+oid sha256:8f5555a3264f90296bf2491c36524039e7c271dde5eda23b82bfd2628385f7d8
 size 893439185

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61d539fc493053cb9a04c81161d0492689b9ab7fcaaea2c1a24a3e6ce4acc990
+oid sha256:9b915770d637a85b511b8ce95890fcc501fb257fa086404572aeee5022ceaa62
 size 449471589

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a81aaecde25369e5575d31d6c4641f897f68348ded1792ee668fac75f81b865d
+oid sha256:8772dddd6d938192c990459978e84fe841726f65afecb856e653e8f92d71ae84
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91bed33973e1e6566de030884af5ce2f52f782d9e7ad79ccceffa9ead0f4b212
+oid sha256:746d31cdff1a7ba11b9440e11b64572184b75f7cc296f7a28b273c21a8883fc1
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83dc738e3825b6749be56158669ca941276cf2897108d6fb521bf33692ea02ee
+oid sha256:f51720bf9dead85db06417d336f89d75a1f13549e41b0ebc50dae00a0a00b614
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ad21b9ae0990cf2f16f8fe417227b8f259cc3ef9a1ae3ddbfa629ee1f04f4cc
-size 14503
+oid sha256:ce8c9d7e6207f2bddc524a75c48baf98682e25fb31bb85ed872f40875802e4db
+size 14567

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b75da63b821a4c72c4b37f39fc301b88ce6e4d7dc37edf4f078b7f5706f736e3
+oid sha256:6fbbdae9c95471a40e6c6d019353b081fa6055bc839ed4f2163c0c1b80837934
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 12.82697329240918,
-  "global_step": 840000,
+  "epoch": 12.979675355414052,
+  "global_step": 850000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -6222,11 +6222,85 @@
       "eval_samples_per_second": 1334.897,
       "eval_steps_per_second": 21.358,
       "step": 840000
+    },
+    {
+      "epoch": 12.84,
+      "learning_rate": 1.945553091971727e-05,
+      "loss": 0.2334,
+      "step": 841000
+    },
+    {
+      "epoch": 12.86,
+      "learning_rate": 1.933967761107847e-05,
+      "loss": 0.234,
+      "step": 842000
+    },
+    {
+      "epoch": 12.87,
+      "learning_rate": 1.9224487674006694e-05,
+      "loss": 0.234,
+      "step": 843000
+    },
+    {
+      "epoch": 12.89,
+      "learning_rate": 1.9109962368200602e-05,
+      "loss": 0.2379,
+      "step": 844000
+    },
+    {
+      "epoch": 12.9,
+      "learning_rate": 1.8996102946090586e-05,
+      "loss": 0.2335,
+      "step": 845000
+    },
+    {
+      "epoch": 12.9,
+      "eval_runtime": 0.7039,
+      "eval_samples_per_second": 1420.612,
+      "eval_steps_per_second": 22.73,
+      "step": 845000
+    },
+    {
+      "epoch": 12.92,
+      "learning_rate": 1.888291065282509e-05,
+      "loss": 0.2338,
+      "step": 846000
+    },
+    {
+      "epoch": 12.93,
+      "learning_rate": 1.8770386726256865e-05,
+      "loss": 0.2329,
+      "step": 847000
+    },
+    {
+      "epoch": 12.95,
+      "learning_rate": 1.8658532396929565e-05,
+      "loss": 0.2334,
+      "step": 848000
+    },
+    {
+      "epoch": 12.96,
+      "learning_rate": 1.8547348888064178e-05,
+      "loss": 0.2341,
+      "step": 849000
+    },
+    {
+      "epoch": 12.98,
+      "learning_rate": 1.8436837415545772e-05,
+      "loss": 0.2356,
+      "step": 850000
+    },
+    {
+      "epoch": 12.98,
+      "eval_runtime": 0.8308,
+      "eval_samples_per_second": 1203.685,
+      "eval_steps_per_second": 19.259,
+      "step": 850000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 16,
-  "total_flos": 5.888414041731375e+22,
+  "total_flos": 5.958514302761722e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61d539fc493053cb9a04c81161d0492689b9ab7fcaaea2c1a24a3e6ce4acc990
+oid sha256:9b915770d637a85b511b8ce95890fcc501fb257fa086404572aeee5022ceaa62
 size 449471589