Training in progress, step 790000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:890c3645e30988fbc5ac02a5c9693d8c822f6832717890f847f916940b8917f0
+oid sha256:7bbcfc7841d8e3c7279dc9562dd48dabc2017ffc2b9998700cfd92549b10b258
 size 893439185

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17a0ac59c1a590fb0b4ddc65e6bb2658bacb5a0663836f6f2274e6f629ddfc34
+oid sha256:a6d2e303b79c843dd2e255dcb66b42d622f3c11aae0591a4594fe30435ca030b
 size 449471589

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea98db79feb7bd77c6b30fe400da36cd82405ae772f74dc10713919b9a54cc9c
-size 14503
+oid sha256:b0b06454874bab75beb606d73861ef28c53072edff450f0d67541ae83ce33a54
+size 14439

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc09ddff61301c0c5eccac0afa50f3b30fb23f1076c8704a7c837b633adb5f1f
+oid sha256:74183b2ff4f54786fe97746a804e5ce75e50372685a561e44836c051c4c6a5de
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:600393b72704693ee1558234d21ac990bdb0183a6915029960f504a3ddebf729
+oid sha256:a238c961e97eac6dc08d049a0a3111fbea4302b13b1d99d77dbbe38ac524b535
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:82e1bd3bf6bfdee64d2c02c2ee85e6573d4dab2dec5b65656a03ae0a39be94d8
-size 14439
+oid sha256:70dfde4719f025927689d32aa4b2f68fdcbdc6cc2b55cd4fb96def6b3d827e65
+size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c067c2b3d8b4465df473fc8f38cbbeff61d1e95141d65c9e7d5985b861950165
+oid sha256:83d1297302d20060e31d476195b98906c23904815e65152eb2d3ffb7dd074183
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 11.910760914379953,
-  "global_step": 780000,
+  "epoch": 12.063462977384825,
+  "global_step": 790000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -5778,11 +5778,85 @@
       "eval_samples_per_second": 1276.363,
       "eval_steps_per_second": 20.422,
       "step": 780000
+    },
+    {
+      "epoch": 11.93,
+      "learning_rate": 2.7568839012773365e-05,
+      "loss": 0.238,
+      "step": 781000
+    },
+    {
+      "epoch": 11.94,
+      "learning_rate": 2.7415754793213826e-05,
+      "loss": 0.2375,
+      "step": 782000
+    },
+    {
+      "epoch": 11.96,
+      "learning_rate": 2.7263245626535116e-05,
+      "loss": 0.2377,
+      "step": 783000
+    },
+    {
+      "epoch": 11.97,
+      "learning_rate": 2.7111313180553077e-05,
+      "loss": 0.2378,
+      "step": 784000
+    },
+    {
+      "epoch": 11.99,
+      "learning_rate": 2.6959959116776587e-05,
+      "loss": 0.2376,
+      "step": 785000
+    },
+    {
+      "epoch": 11.99,
+      "eval_runtime": 0.7664,
+      "eval_samples_per_second": 1304.853,
+      "eval_steps_per_second": 20.878,
+      "step": 785000
+    },
+    {
+      "epoch": 12.0,
+      "learning_rate": 2.6809185090389406e-05,
+      "loss": 0.2371,
+      "step": 786000
+    },
+    {
+      "epoch": 12.02,
+      "learning_rate": 2.6658992750232167e-05,
+      "loss": 0.2373,
+      "step": 787000
+    },
+    {
+      "epoch": 12.03,
+      "learning_rate": 2.6509383738784218e-05,
+      "loss": 0.2374,
+      "step": 788000
+    },
+    {
+      "epoch": 12.05,
+      "learning_rate": 2.6360359692145757e-05,
+      "loss": 0.237,
+      "step": 789000
+    },
+    {
+      "epoch": 12.06,
+      "learning_rate": 2.6211922240019883e-05,
+      "loss": 0.2368,
+      "step": 790000
+    },
+    {
+      "epoch": 12.06,
+      "eval_runtime": 0.7543,
+      "eval_samples_per_second": 1325.719,
+      "eval_steps_per_second": 21.212,
+      "step": 790000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 16,
-  "total_flos": 5.467813132617441e+22,
+  "total_flos": 5.537912736579639e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17a0ac59c1a590fb0b4ddc65e6bb2658bacb5a0663836f6f2274e6f629ddfc34
+oid sha256:a6d2e303b79c843dd2e255dcb66b42d622f3c11aae0591a4594fe30435ca030b
 size 449471589