Training in progress, step 830000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ece7b379c7a5a58ecf06bad11ca4cf9bd52de11683f133c698a0cd46d58e7f3f
+oid sha256:0d676bdecf6cef07d6d1557838930ff920f76201e2414575a644361d9ebd0ca5
 size 893439185

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83c02b97525bdc0170d693b11906b5064b3417228255adea84f3fccd20f429d1
+oid sha256:8c181b3b0e0340fe0f0c6e90ca26f9e2021277f659fa06f6c810cab95d243c9f
 size 449471589

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:471be9073ca16931b802d54b255e23b3102b1be6c0e243832ecda5d9de213243
+oid sha256:10fb0b6575db7cc3fd463d26671f67a57f4c817b1f162f6dd70df0ba155fea6a
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c26d9707c692819517328265ab4fd028c1ec91f8e531a3899c963382192856e1
-size 14567
+oid sha256:7b966173ec2647fe3f9ce64251f9ba275015c518c4e11801d8a5787cb53077e4
+size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f7ef808d3e0c55b070bb63a51ac31108dc6594c932f2329575c64f0ec5d34a6
-size 14439
+oid sha256:626675f0b56b6320753b402844bd4c05cb33ef3bdd886b37ae3b7133c13f9441
+size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3915824192442b74d4af5e3ad4160d4a09adeeec3fcac9fa02d181a6969e8279
+oid sha256:25a0cb16e446a0582e61cafe4a89816af44798dc1964f3425f293eb3e6cf9c2b
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c63a65d51252613e1cd5f3ab255f2a8e56d55631776ee22be37789c5802ebbf2
+oid sha256:b44f4d1ea700e774f5dee0343ba4324675c77c29852dd54fec6a281d849ccd3b
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 12.521569166399438,
-  "global_step": 820000,
+  "epoch": 12.67427122940431,
+  "global_step": 830000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -6074,11 +6074,85 @@
       "eval_samples_per_second": 1609.99,
       "eval_steps_per_second": 25.76,
       "step": 820000
+    },
+    {
+      "epoch": 12.54,
+      "learning_rate": 2.1909901420919184e-05,
+      "loss": 0.2351,
+      "step": 821000
+    },
+    {
+      "epoch": 12.55,
+      "learning_rate": 2.1781056286210997e-05,
+      "loss": 0.235,
+      "step": 822000
+    },
+    {
+      "epoch": 12.57,
+      "learning_rate": 2.1652847824543744e-05,
+      "loss": 0.2347,
+      "step": 823000
+    },
+    {
+      "epoch": 12.58,
+      "learning_rate": 2.1525277437984636e-05,
+      "loss": 0.2348,
+      "step": 824000
+    },
+    {
+      "epoch": 12.6,
+      "learning_rate": 2.1398346521623e-05,
+      "loss": 0.2345,
+      "step": 825000
+    },
+    {
+      "epoch": 12.6,
+      "eval_runtime": 0.7605,
+      "eval_samples_per_second": 1314.934,
+      "eval_steps_per_second": 21.039,
+      "step": 825000
+    },
+    {
+      "epoch": 12.61,
+      "learning_rate": 2.1272056463554978e-05,
+      "loss": 0.2343,
+      "step": 826000
+    },
+    {
+      "epoch": 12.63,
+      "learning_rate": 2.114640864486845e-05,
+      "loss": 0.2346,
+      "step": 827000
+    },
+    {
+      "epoch": 12.64,
+      "learning_rate": 2.1021404439627775e-05,
+      "loss": 0.2344,
+      "step": 828000
+    },
+    {
+      "epoch": 12.66,
+      "learning_rate": 2.089704521485896e-05,
+      "loss": 0.2344,
+      "step": 829000
+    },
+    {
+      "epoch": 12.67,
+      "learning_rate": 2.0773332330534513e-05,
+      "loss": 0.2343,
+      "step": 830000
+    },
+    {
+      "epoch": 12.67,
+      "eval_runtime": 0.7327,
+      "eval_samples_per_second": 1364.889,
+      "eval_steps_per_second": 21.838,
+      "step": 830000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 16,
-  "total_flos": 5.748213519670681e+22,
+  "total_flos": 5.818313780701028e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83c02b97525bdc0170d693b11906b5064b3417228255adea84f3fccd20f429d1
+oid sha256:8c181b3b0e0340fe0f0c6e90ca26f9e2021277f659fa06f6c810cab95d243c9f
 size 449471589