Training in progress, step 550000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3cce3705a1c8b8d8d4264e967a6f95acb36457da2099b2e0f10708b7bc8b02f7
+oid sha256:6c26dfdb95640433391e289b9d54c29ba637889e22ac54f90b0e4758926e0b34
 size 893439185

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10387ca16d2be862ac39f8a7dd403935e8f63c843663bd6c250c84cc9afccb17
+oid sha256:affd4afd21029b52701e8d0046ed5d64853de0037c32a35ed3d7e452fd7c0e84
 size 449471589

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d6a05599d68c81d8f28a8a18f0fba06e8b974a2ea269e8529ff0449633b1df0
-size 14503
+oid sha256:668a667c0141b3007fbd5f23f3195d50d9a952d3b42af4d471955e90b35901bf
+size 14439

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa440e15eff2f549811ca7872de21865d48dd11cb8b6542ab71253c6945d2c0d
-size 14567
+oid sha256:ed9a47d2a307e89814d3463ee5fc48f3b3365083fd9c82a5f581a3087e2941c8
+size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24051c040fbf1ab84f4d62008b8fd2ab04d63f18b11e30fd62216b89cf665574
+oid sha256:3e8a638d577539d28ce2053ec5b75e3eed1d5ad4a147b887facb578c40f25088
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28fbe9c447e2dbc1b0d90d8fb5fa32bb60a8b179ed5bdf4dc956ff563b72c4fc
+oid sha256:30723df40dcd4e911f2e4b8fee07e2767c8ee7ced5c90fa064aabaf279f01230
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:312a9240a59bfb6f588851dc4640a2bea628ee45c54031017e35bcac8788a581
+oid sha256:8de7df7ff53e44669a043f69e39b55baa82d81ac1777f09e2f6159ffcb51dd66
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 8.245911402263044,
-  "global_step": 540000,
+  "epoch": 8.398613465267916,
+  "global_step": 550000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -4002,11 +4002,85 @@
       "eval_samples_per_second": 849.063,
       "eval_steps_per_second": 13.585,
       "step": 540000
+    },
+    {
+      "epoch": 8.26,
+      "learning_rate": 7.629795553284005e-05,
+      "loss": 0.2602,
+      "step": 541000
+    },
+    {
+      "epoch": 8.28,
+      "learning_rate": 7.606681437777081e-05,
+      "loss": 0.2605,
+      "step": 542000
+    },
+    {
+      "epoch": 8.29,
+      "learning_rate": 7.583571623538939e-05,
+      "loss": 0.26,
+      "step": 543000
+    },
+    {
+      "epoch": 8.31,
+      "learning_rate": 7.560466363294806e-05,
+      "loss": 0.2596,
+      "step": 544000
+    },
+    {
+      "epoch": 8.32,
+      "learning_rate": 7.537365909720104e-05,
+      "loss": 0.2595,
+      "step": 545000
+    },
+    {
+      "epoch": 8.32,
+      "eval_runtime": 1.1629,
+      "eval_samples_per_second": 859.911,
+      "eval_steps_per_second": 13.759,
+      "step": 545000
+    },
+    {
+      "epoch": 8.34,
+      "learning_rate": 7.514270515437691e-05,
+      "loss": 0.2595,
+      "step": 546000
+    },
+    {
+      "epoch": 8.35,
+      "learning_rate": 7.491180433015101e-05,
+      "loss": 0.2594,
+      "step": 547000
+    },
+    {
+      "epoch": 8.37,
+      "learning_rate": 7.468095914961777e-05,
+      "loss": 0.2596,
+      "step": 548000
+    },
+    {
+      "epoch": 8.38,
+      "learning_rate": 7.445017213726307e-05,
+      "loss": 0.2596,
+      "step": 549000
+    },
+    {
+      "epoch": 8.4,
+      "learning_rate": 7.421944581693674e-05,
+      "loss": 0.2594,
+      "step": 550000
+    },
+    {
+      "epoch": 8.4,
+      "eval_runtime": 0.9899,
+      "eval_samples_per_second": 1010.184,
+      "eval_steps_per_second": 16.163,
+      "step": 550000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 16,
-  "total_flos": 3.785408839093556e+22,
+  "total_flos": 3.855509100123903e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10387ca16d2be862ac39f8a7dd403935e8f63c843663bd6c250c84cc9afccb17
+oid sha256:affd4afd21029b52701e8d0046ed5d64853de0037c32a35ed3d7e452fd7c0e84
 size 449471589