Training in progress, step 610000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa3e03e9ecd0026fc79482638e67bfbb968ad2fb2a2251138fea448958ad2549
+oid sha256:58bbdb63dd5f35ddeda47e9dc139795456694d0aba5e0383355b4522b67e77b3
 size 893439185

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff751ae05b56a482e47a728b40ba33717079b6b3d77d92ae8823ddd2e524f99f
+oid sha256:b37572e353c74d53a74256f6a8b831fe7ecaed9eb997d03f96697e3f38be10fb
 size 449471589

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e165b16ec4c4b7c229152423019cf42f78fde1837556dbc7f0e0a0d03eb92f2
-size 14439
+oid sha256:e969b0a1f38bb709ff184bddc11e3e1b7a366f1f525d658e15c5e0e9638178b2
+size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d6acb016c9e03d8943408e9c25efa54b6209d293a5e14d07d93d97c6c5df995b
-size 14567
+oid sha256:e472d706bbb24da1ae339dbf5b5e166d6a3aff07e50beb6830b013698716675c
+size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a372c6638d81ac9bbd86bc3b09ec3143aa46879e63bc5f10b74bd9c0aea9c32b
-size 14503
+oid sha256:bb9d01b196a085088b251b99e2302b0af5c57d846827fd2f433da2dd23ebd86a
+size 14567

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a1ca703723e30170efc3dee97c3c7534e4adefa45396ecce1b5c543326f570d
+oid sha256:0f9539e61c7b8fd54fd055839d1a6ea3b2cd4ea6f97a1aef7d0a7c91c2429be6
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34904d09dca1d79fb910d11916faed0bf8107fa6c955fc65b114b5f30425510a
+oid sha256:71de57969ec7a3201bd7bf6de3d6e1584c8439f398aacc61865ba691cc2653d6
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 9.162123780292271,
-  "global_step": 600000,
+  "epoch": 9.314825843297143,
+  "global_step": 610000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -4446,11 +4446,85 @@
       "eval_samples_per_second": 928.316,
       "eval_steps_per_second": 14.853,
       "step": 600000
+    },
+    {
+      "epoch": 9.18,
+      "learning_rate": 6.259170789846017e-05,
+      "loss": 0.2546,
+      "step": 601000
+    },
+    {
+      "epoch": 9.19,
+      "learning_rate": 6.236759027106965e-05,
+      "loss": 0.2542,
+      "step": 602000
+    },
+    {
+      "epoch": 9.21,
+      "learning_rate": 6.214366546888694e-05,
+      "loss": 0.2541,
+      "step": 603000
+    },
+    {
+      "epoch": 9.22,
+      "learning_rate": 6.191993594071785e-05,
+      "loss": 0.2541,
+      "step": 604000
+    },
+    {
+      "epoch": 9.24,
+      "learning_rate": 6.169640413323262e-05,
+      "loss": 0.254,
+      "step": 605000
+    },
+    {
+      "epoch": 9.24,
+      "eval_runtime": 1.0913,
+      "eval_samples_per_second": 916.334,
+      "eval_steps_per_second": 14.661,
+      "step": 605000
+    },
+    {
+      "epoch": 9.25,
+      "learning_rate": 6.147307249093929e-05,
+      "loss": 0.2537,
+      "step": 606000
+    },
+    {
+      "epoch": 9.27,
+      "learning_rate": 6.124994345615693e-05,
+      "loss": 0.2532,
+      "step": 607000
+    },
+    {
+      "epoch": 9.28,
+      "learning_rate": 6.102701946898891e-05,
+      "loss": 0.2536,
+      "step": 608000
+    },
+    {
+      "epoch": 9.3,
+      "learning_rate": 6.0804302967296225e-05,
+      "loss": 0.2545,
+      "step": 609000
+    },
+    {
+      "epoch": 9.31,
+      "learning_rate": 6.058179638667089e-05,
+      "loss": 0.2536,
+      "step": 610000
+    },
+    {
+      "epoch": 9.31,
+      "eval_runtime": 1.0284,
+      "eval_samples_per_second": 972.365,
+      "eval_steps_per_second": 15.558,
+      "step": 610000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 16,
-  "total_flos": 4.20600974820749e+22,
+  "total_flos": 4.276110009237837e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff751ae05b56a482e47a728b40ba33717079b6b3d77d92ae8823ddd2e524f99f
+oid sha256:b37572e353c74d53a74256f6a8b831fe7ecaed9eb997d03f96697e3f38be10fb
 size 449471589