Training in progress, step 990000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90e6f74ca02156084fa05f854168c4cbdee8fc0fa6687cea7dfffc7ceaa970ef
+oid sha256:4cbfc1ed883942984be588c84681fbb0b292e529986dcbab5a1fecaa3f6ad447
 size 893439185

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44a8bb7d1ad03b47ab97301f2bf5aa4416e913d62ffabd09bdd937d55c43233d
+oid sha256:fc73418bd52c0694a19af6083331d7a4a133f36616e77cb56fc9fc0bb18ad264
 size 449471589

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2693c812482df2fdf768d0c19e41d192e583b64a43dbe767a2677f629f2520e7
+oid sha256:c3cbe84c4b275ece4dfc8b045971a9447b9468599c6de1ac7856d818ab7fcce6
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39770cef90df6052fa5bdc49403a83d0e05cc2d3766019022596476c4a73f3b2
+oid sha256:6ca4b049386ceb25b5284b9754462b13ddabb069762bc1b4ce1a9e94d95e348c
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:708a00e78f0bdafbd2eb890af573c704006de2c61a1f639e3fb47ce38e039820
+oid sha256:733172b1d4a99d1dcac219cdba47537d2e3c42c728e60a468833c7a7eb409d93
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c3d789d948e2afb641edc41de23d3e0ac8454e4ca3cace740853515e0185e05d
+oid sha256:e1a20d0d880982442a49c1adeca0b36b7c4aa9ce9768b58e40b03f2358d78bf3
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1f60f9446cba0320cf9ced93c4b14816af8d6988d011f7cc2f5b01e8ada101d
+oid sha256:b2358905887cd0ce80c53b6e8a0174e039c4c5bd62c6c91c86f0312f9b46fcf7
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 14.964802174477377,
-  "global_step": 980000,
+  "epoch": 15.11750423748225,
+  "global_step": 990000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -7258,11 +7258,85 @@
       "eval_samples_per_second": 1335.226,
       "eval_steps_per_second": 21.364,
       "step": 980000
+    },
+    {
+      "epoch": 14.98,
+      "learning_rate": 1.0138129010020992e-05,
+      "loss": 0.2272,
+      "step": 981000
+    },
+    {
+      "epoch": 15.0,
+      "learning_rate": 1.0123975923584488e-05,
+      "loss": 0.2273,
+      "step": 982000
+    },
+    {
+      "epoch": 15.01,
+      "learning_rate": 1.0110586990152152e-05,
+      "loss": 0.227,
+      "step": 983000
+    },
+    {
+      "epoch": 15.03,
+      "learning_rate": 1.0097962356143219e-05,
+      "loss": 0.2273,
+      "step": 984000
+    },
+    {
+      "epoch": 15.04,
+      "learning_rate": 1.0086102159618668e-05,
+      "loss": 0.227,
+      "step": 985000
+    },
+    {
+      "epoch": 15.04,
+      "eval_runtime": 0.7868,
+      "eval_samples_per_second": 1271.022,
+      "eval_steps_per_second": 20.336,
+      "step": 985000
+    },
+    {
+      "epoch": 15.06,
+      "learning_rate": 1.0075006530279694e-05,
+      "loss": 0.2271,
+      "step": 986000
+    },
+    {
+      "epoch": 15.07,
+      "learning_rate": 1.0064675589466339e-05,
+      "loss": 0.2268,
+      "step": 987000
+    },
+    {
+      "epoch": 15.09,
+      "learning_rate": 1.0055109450156098e-05,
+      "loss": 0.2272,
+      "step": 988000
+    },
+    {
+      "epoch": 15.1,
+      "learning_rate": 1.0046308216962759e-05,
+      "loss": 0.2269,
+      "step": 989000
+    },
+    {
+      "epoch": 15.12,
+      "learning_rate": 1.0038271986135177e-05,
+      "loss": 0.2272,
+      "step": 990000
+    },
+    {
+      "epoch": 15.12,
+      "eval_runtime": 0.7713,
+      "eval_samples_per_second": 1296.438,
+      "eval_steps_per_second": 20.743,
+      "step": 990000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 16,
-  "total_flos": 6.869816382019938e+22,
+  "total_flos": 6.939915985982136e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44a8bb7d1ad03b47ab97301f2bf5aa4416e913d62ffabd09bdd937d55c43233d
+oid sha256:fc73418bd52c0694a19af6083331d7a4a133f36616e77cb56fc9fc0bb18ad264
 size 449471589