Training in progress, step 560000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c26dfdb95640433391e289b9d54c29ba637889e22ac54f90b0e4758926e0b34
+oid sha256:d8ab35ed4dfefd8dd33fb26f0ecf541378b45831852a54aeb8f775b92df21738
 size 893439185

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:affd4afd21029b52701e8d0046ed5d64853de0037c32a35ed3d7e452fd7c0e84
+oid sha256:5321ac05ebfcc017f8c041dae493ee5ce4f8eaceb97ac0dbd2e5b7ff1909ad9f
 size 449471589

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:668a667c0141b3007fbd5f23f3195d50d9a952d3b42af4d471955e90b35901bf
-size 14439
+oid sha256:1c595110edd758e9e0a71c6845041a2d22c5cf58679d14f120b5cb63abc84493
+size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed9a47d2a307e89814d3463ee5fc48f3b3365083fd9c82a5f581a3087e2941c8
+oid sha256:715147c7486ebd169cb8e58f73bc4aa6a8bc3129e6581c29e50cbdd2f06aae29
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e8a638d577539d28ce2053ec5b75e3eed1d5ad4a147b887facb578c40f25088
+oid sha256:2da28d7b7099d5f85e00929347b66a092dbe7cfdb67ae3df05ae5bcb6ee3a235
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30723df40dcd4e911f2e4b8fee07e2767c8ee7ced5c90fa064aabaf279f01230
-size 14503
+oid sha256:18d187c6fad30982ef7c6cac2865f72e7d2e1a26561d9ab8f74149dc0f5b946f
+size 14439

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8de7df7ff53e44669a043f69e39b55baa82d81ac1777f09e2f6159ffcb51dd66
+oid sha256:af9a25b33d29c3fd157c79676adec6abbe35f3978d907c7efc857fe0437c64ac
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 8.398613465267916,
-  "global_step": 550000,
+  "epoch": 8.551315528272786,
+  "global_step": 560000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -4076,11 +4076,85 @@
       "eval_samples_per_second": 1010.184,
       "eval_steps_per_second": 16.163,
       "step": 550000
+    },
+    {
+      "epoch": 8.41,
+      "learning_rate": 7.39887827118248e-05,
+      "loss": 0.259,
+      "step": 551000
+    },
+    {
+      "epoch": 8.43,
+      "learning_rate": 7.375818534442207e-05,
+      "loss": 0.2588,
+      "step": 552000
+    },
+    {
+      "epoch": 8.44,
+      "learning_rate": 7.352765623650435e-05,
+      "loss": 0.259,
+      "step": 553000
+    },
+    {
+      "epoch": 8.46,
+      "learning_rate": 7.329719790910108e-05,
+      "loss": 0.2587,
+      "step": 554000
+    },
+    {
+      "epoch": 8.47,
+      "learning_rate": 7.30668128824676e-05,
+      "loss": 0.2587,
+      "step": 555000
+    },
+    {
+      "epoch": 8.47,
+      "eval_runtime": 1.1635,
+      "eval_samples_per_second": 859.466,
+      "eval_steps_per_second": 13.751,
+      "step": 555000
+    },
+    {
+      "epoch": 8.49,
+      "learning_rate": 7.283650367605764e-05,
+      "loss": 0.2584,
+      "step": 556000
+    },
+    {
+      "epoch": 8.51,
+      "learning_rate": 7.260627280849581e-05,
+      "loss": 0.2585,
+      "step": 557000
+    },
+    {
+      "epoch": 8.52,
+      "learning_rate": 7.23761227975499e-05,
+      "loss": 0.2584,
+      "step": 558000
+    },
+    {
+      "epoch": 8.54,
+      "learning_rate": 7.21460561601037e-05,
+      "loss": 0.2584,
+      "step": 559000
+    },
+    {
+      "epoch": 8.55,
+      "learning_rate": 7.191607541212897e-05,
+      "loss": 0.2585,
+      "step": 560000
+    },
+    {
+      "epoch": 8.55,
+      "eval_runtime": 1.1711,
+      "eval_samples_per_second": 853.863,
+      "eval_steps_per_second": 13.662,
+      "step": 560000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 16,
-  "total_flos": 3.855509100123903e+22,
+  "total_flos": 3.92560936115425e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:affd4afd21029b52701e8d0046ed5d64853de0037c32a35ed3d7e452fd7c0e84
+oid sha256:5321ac05ebfcc017f8c041dae493ee5ce4f8eaceb97ac0dbd2e5b7ff1909ad9f
 size 449471589