Training in progress, step 780000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9cd115a94124bab2069eaa28cc8b9048cd539d53dac292919b3e0c103db4c72e
+oid sha256:890c3645e30988fbc5ac02a5c9693d8c822f6832717890f847f916940b8917f0
 size 893439185

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca7fa82eacf1e8434be7ded7b8c684db48c7eb8a95a9938e56bd64eca327a5df
+oid sha256:17a0ac59c1a590fb0b4ddc65e6bb2658bacb5a0663836f6f2274e6f629ddfc34
 size 449471589

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7d3b820a136ad2a4ba7c86024ef116cb8408b724ca033611384f2431449421e
-size 14439
+oid sha256:ea98db79feb7bd77c6b30fe400da36cd82405ae772f74dc10713919b9a54cc9c
+size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9edcea991831f16f231bcb3a9b5fa5ff10be4f8fa58a6379f44531e869bdb54a
+oid sha256:dc09ddff61301c0c5eccac0afa50f3b30fb23f1076c8704a7c837b633adb5f1f
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d7420c489d698358bef68e17228256f66ae1823918a8b52fcc13ba74d224c70
+oid sha256:600393b72704693ee1558234d21ac990bdb0183a6915029960f504a3ddebf729
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:682c61168677972229ed1e1a9e1518def3be9c6cebcff3c8dc65ade2edc13840
-size 14503
+oid sha256:82e1bd3bf6bfdee64d2c02c2ee85e6573d4dab2dec5b65656a03ae0a39be94d8
+size 14439

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c87245ad3a3a643f81f3f2450a9b83d6c09d17eda4b9f8dcf29bf1d0ea618777
+oid sha256:c067c2b3d8b4465df473fc8f38cbbeff61d1e95141d65c9e7d5985b861950165
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 11.758058851375083,
-  "global_step": 770000,
+  "epoch": 11.910760914379953,
+  "global_step": 780000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -5704,11 +5704,85 @@
       "eval_samples_per_second": 1187.898,
       "eval_steps_per_second": 19.006,
       "step": 770000
+    },
+    {
+      "epoch": 11.77,
+      "learning_rate": 2.9130937724604947e-05,
+      "loss": 0.2401,
+      "step": 771000
+    },
+    {
+      "epoch": 11.79,
+      "learning_rate": 2.8972196080501208e-05,
+      "loss": 0.2392,
+      "step": 772000
+    },
+    {
+      "epoch": 11.8,
+      "learning_rate": 2.8814012468285748e-05,
+      "loss": 0.2395,
+      "step": 773000
+    },
+    {
+      "epoch": 11.82,
+      "learning_rate": 2.865638861782922e-05,
+      "loss": 0.2387,
+      "step": 774000
+    },
+    {
+      "epoch": 11.83,
+      "learning_rate": 2.849932625288079e-05,
+      "loss": 0.2383,
+      "step": 775000
+    },
+    {
+      "epoch": 11.83,
+      "eval_runtime": 0.7561,
+      "eval_samples_per_second": 1322.637,
+      "eval_steps_per_second": 21.162,
+      "step": 775000
+    },
+    {
+      "epoch": 11.85,
+      "learning_rate": 2.8342827091049336e-05,
+      "loss": 0.2383,
+      "step": 776000
+    },
+    {
+      "epoch": 11.86,
+      "learning_rate": 2.8186892843784587e-05,
+      "loss": 0.2384,
+      "step": 777000
+    },
+    {
+      "epoch": 11.88,
+      "learning_rate": 2.803152521635851e-05,
+      "loss": 0.2382,
+      "step": 778000
+    },
+    {
+      "epoch": 11.9,
+      "learning_rate": 2.7876725907846578e-05,
+      "loss": 0.2378,
+      "step": 779000
+    },
+    {
+      "epoch": 11.91,
+      "learning_rate": 2.7722496611109243e-05,
+      "loss": 0.2378,
+      "step": 780000
+    },
+    {
+      "epoch": 11.91,
+      "eval_runtime": 0.7835,
+      "eval_samples_per_second": 1276.363,
+      "eval_steps_per_second": 20.422,
+      "step": 780000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 16,
-  "total_flos": 5.397712871587094e+22,
+  "total_flos": 5.467813132617441e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca7fa82eacf1e8434be7ded7b8c684db48c7eb8a95a9938e56bd64eca327a5df
+oid sha256:17a0ac59c1a590fb0b4ddc65e6bb2658bacb5a0663836f6f2274e6f629ddfc34
 size 449471589