Training in progress, step 800000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7bbcfc7841d8e3c7279dc9562dd48dabc2017ffc2b9998700cfd92549b10b258
+oid sha256:d6ec057c0ea307d9f51e3009e95cfba4d493f3e514026b596f1c721e347110a2
 size 893439185

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6d2e303b79c843dd2e255dcb66b42d622f3c11aae0591a4594fe30435ca030b
+oid sha256:c985c5c271524f27a0a6ac2cedd7bd56467790c039bcfe7ae085c019b80866ff
 size 449471589

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b0b06454874bab75beb606d73861ef28c53072edff450f0d67541ae83ce33a54
+oid sha256:0493bee6992b67d925775f2df83491a04dff10cd3cfaddd00934784185d10d2e
 size 14439

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74183b2ff4f54786fe97746a804e5ce75e50372685a561e44836c051c4c6a5de
+oid sha256:04d30c889b2c1188805f0e0743f415f3e88c779ab0ac6888677c659a1fcc6f0f
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a238c961e97eac6dc08d049a0a3111fbea4302b13b1d99d77dbbe38ac524b535
+oid sha256:5feee3a51b2120b65724867d176679fa33e4ec4b388d10b3340281bee5153e6a
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70dfde4719f025927689d32aa4b2f68fdcbdc6cc2b55cd4fb96def6b3d827e65
+oid sha256:34638a46c5b98d6fa60d632175553537f127fe65e252717a514cd2f205e50dee
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83d1297302d20060e31d476195b98906c23904815e65152eb2d3ffb7dd074183
+oid sha256:57cc3662a36c24e948440a9c5383a944373362c15a98a0fb5317ec1e024dd4c4
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 12.063462977384825,
-  "global_step": 790000,
+  "epoch": 12.216165040389695,
+  "global_step": 800000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -5852,11 +5852,85 @@
       "eval_samples_per_second": 1325.719,
       "eval_steps_per_second": 21.212,
       "step": 790000
+    },
+    {
+      "epoch": 12.08,
+      "learning_rate": 2.6064073005694758e-05,
+      "loss": 0.2381,
+      "step": 791000
+    },
+    {
+      "epoch": 12.09,
+      "learning_rate": 2.591681360602595e-05,
+      "loss": 0.2373,
+      "step": 792000
+    },
+    {
+      "epoch": 12.11,
+      "learning_rate": 2.577014565141866e-05,
+      "loss": 0.2377,
+      "step": 793000
+    },
+    {
+      "epoch": 12.12,
+      "learning_rate": 2.562407074581014e-05,
+      "loss": 0.2382,
+      "step": 794000
+    },
+    {
+      "epoch": 12.14,
+      "learning_rate": 2.5478590486652137e-05,
+      "loss": 0.2374,
+      "step": 795000
+    },
+    {
+      "epoch": 12.14,
+      "eval_runtime": 0.8227,
+      "eval_samples_per_second": 1215.581,
+      "eval_steps_per_second": 19.449,
+      "step": 795000
+    },
+    {
+      "epoch": 12.16,
+      "learning_rate": 2.533370646489347e-05,
+      "loss": 0.237,
+      "step": 796000
+    },
+    {
+      "epoch": 12.17,
+      "learning_rate": 2.5189420264962586e-05,
+      "loss": 0.2367,
+      "step": 797000
+    },
+    {
+      "epoch": 12.19,
+      "learning_rate": 2.504573346475026e-05,
+      "loss": 0.2371,
+      "step": 798000
+    },
+    {
+      "epoch": 12.2,
+      "learning_rate": 2.4902647635592324e-05,
+      "loss": 0.2372,
+      "step": 799000
+    },
+    {
+      "epoch": 12.22,
+      "learning_rate": 2.476016434225246e-05,
+      "loss": 0.2372,
+      "step": 800000
+    },
+    {
+      "epoch": 12.22,
+      "eval_runtime": 0.741,
+      "eval_samples_per_second": 1349.61,
+      "eval_steps_per_second": 21.594,
+      "step": 800000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 16,
-  "total_flos": 5.537912736579639e+22,
+  "total_flos": 5.6080129976099865e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6d2e303b79c843dd2e255dcb66b42d622f3c11aae0591a4594fe30435ca030b
+oid sha256:c985c5c271524f27a0a6ac2cedd7bd56467790c039bcfe7ae085c019b80866ff
 size 449471589