Training in progress, step 930000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee3aeed50a2a4c25efaca58a22f8e74eeb4a5176131dc454fbde37631acf016d
+oid sha256:f7e7257d85066f44137f90721b6eeea6b47af4fdd60cb740d773a3a975cd64d8
 size 893439185

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49c53e22d617d625d68b0b7c24d68f147254236ebb3b272bd10eecf6d93598e9
+oid sha256:d3151d7e7cec0857fd8c0138e846e83ffe158233cc9712166843e469c2af9c3a
 size 449471589

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b532accc0aeba393068677a9f95a8872109f8bff87e999a983cbe001ebba335b
+oid sha256:e1557f867cc6f3d40a606a0ce0859f55e4a3fbdcdcb8655429fb299c80a41a4d
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b532accc0aeba393068677a9f95a8872109f8bff87e999a983cbe001ebba335b
+oid sha256:e1557f867cc6f3d40a606a0ce0859f55e4a3fbdcdcb8655429fb299c80a41a4d
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b532accc0aeba393068677a9f95a8872109f8bff87e999a983cbe001ebba335b
+oid sha256:e1557f867cc6f3d40a606a0ce0859f55e4a3fbdcdcb8655429fb299c80a41a4d
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b532accc0aeba393068677a9f95a8872109f8bff87e999a983cbe001ebba335b
+oid sha256:e1557f867cc6f3d40a606a0ce0859f55e4a3fbdcdcb8655429fb299c80a41a4d
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b532accc0aeba393068677a9f95a8872109f8bff87e999a983cbe001ebba335b
+oid sha256:e1557f867cc6f3d40a606a0ce0859f55e4a3fbdcdcb8655429fb299c80a41a4d
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b532accc0aeba393068677a9f95a8872109f8bff87e999a983cbe001ebba335b
+oid sha256:e1557f867cc6f3d40a606a0ce0859f55e4a3fbdcdcb8655429fb299c80a41a4d
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b532accc0aeba393068677a9f95a8872109f8bff87e999a983cbe001ebba335b
+oid sha256:e1557f867cc6f3d40a606a0ce0859f55e4a3fbdcdcb8655429fb299c80a41a4d
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b532accc0aeba393068677a9f95a8872109f8bff87e999a983cbe001ebba335b
+oid sha256:e1557f867cc6f3d40a606a0ce0859f55e4a3fbdcdcb8655429fb299c80a41a4d
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7df508c344c1f04d3b388cef9605593fbfd129cd18e2830701d3110873541479
+oid sha256:3b0e1b3397ffbcdba72f77e0e72529212805b3efe290aff36c3ecd969d87bca4
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 9.903505347802326,
-  "global_step": 920000,
+  "epoch": 10.01503407202525,
+  "global_step": 930000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -18406,11 +18406,211 @@
       "eval_samples_per_second": 860.053,
       "eval_steps_per_second": 13.479,
       "step": 920000
+    },
+    {
+      "epoch": 9.91,
+      "learning_rate": 1.240520421060586e-05,
+      "loss": 0.1818,
+      "step": 920500
+    },
+    {
+      "epoch": 9.91,
+      "learning_rate": 1.2375216942216713e-05,
+      "loss": 0.1817,
+      "step": 921000
+    },
+    {
+      "epoch": 9.91,
+      "eval_loss": 0.17294897139072418,
+      "eval_runtime": 2.7216,
+      "eval_samples_per_second": 843.974,
+      "eval_steps_per_second": 13.227,
+      "step": 921000
+    },
+    {
+      "epoch": 9.92,
+      "learning_rate": 1.2345414557402198e-05,
+      "loss": 0.1811,
+      "step": 921500
+    },
+    {
+      "epoch": 9.93,
+      "learning_rate": 1.2315797137640906e-05,
+      "loss": 0.1814,
+      "step": 922000
+    },
+    {
+      "epoch": 9.93,
+      "eval_loss": 0.1728929877281189,
+      "eval_runtime": 2.6867,
+      "eval_samples_per_second": 854.941,
+      "eval_steps_per_second": 13.399,
+      "step": 922000
+    },
+    {
+      "epoch": 9.93,
+      "learning_rate": 1.2286364763905723e-05,
+      "loss": 0.1813,
+      "step": 922500
+    },
+    {
+      "epoch": 9.94,
+      "learning_rate": 1.225711751666363e-05,
+      "loss": 0.1815,
+      "step": 923000
+    },
+    {
+      "epoch": 9.94,
+      "eval_loss": 0.17273372411727905,
+      "eval_runtime": 2.6851,
+      "eval_samples_per_second": 855.459,
+      "eval_steps_per_second": 13.407,
+      "step": 923000
+    },
+    {
+      "epoch": 9.94,
+      "learning_rate": 1.2228055475875488e-05,
+      "loss": 0.1811,
+      "step": 923500
+    },
+    {
+      "epoch": 9.95,
+      "learning_rate": 1.2199178720995825e-05,
+      "loss": 0.1814,
+      "step": 924000
+    },
+    {
+      "epoch": 9.95,
+      "eval_loss": 0.17107011377811432,
+      "eval_runtime": 2.7626,
+      "eval_samples_per_second": 831.466,
+      "eval_steps_per_second": 13.031,
+      "step": 924000
+    },
+    {
+      "epoch": 9.95,
+      "learning_rate": 1.217048733097256e-05,
+      "loss": 0.181,
+      "step": 924500
+    },
+    {
+      "epoch": 9.96,
+      "learning_rate": 1.2141981384246874e-05,
+      "loss": 0.1808,
+      "step": 925000
+    },
+    {
+      "epoch": 9.96,
+      "eval_loss": 0.17153695225715637,
+      "eval_runtime": 2.6072,
+      "eval_samples_per_second": 881.021,
+      "eval_steps_per_second": 13.808,
+      "step": 925000
+    },
+    {
+      "epoch": 9.96,
+      "learning_rate": 1.211366095875293e-05,
+      "loss": 0.1811,
+      "step": 925500
+    },
+    {
+      "epoch": 9.97,
+      "learning_rate": 1.2085526131917685e-05,
+      "loss": 0.181,
+      "step": 926000
+    },
+    {
+      "epoch": 9.97,
+      "eval_loss": 0.1717982143163681,
+      "eval_runtime": 2.6346,
+      "eval_samples_per_second": 871.846,
+      "eval_steps_per_second": 13.664,
+      "step": 926000
+    },
+    {
+      "epoch": 9.98,
+      "learning_rate": 1.2057576980660691e-05,
+      "loss": 0.181,
+      "step": 926500
+    },
+    {
+      "epoch": 9.98,
+      "learning_rate": 1.2029813581393866e-05,
+      "loss": 0.1813,
+      "step": 927000
+    },
+    {
+      "epoch": 9.98,
+      "eval_loss": 0.17178404331207275,
+      "eval_runtime": 2.6835,
+      "eval_samples_per_second": 855.987,
+      "eval_steps_per_second": 13.416,
+      "step": 927000
+    },
+    {
+      "epoch": 9.99,
+      "learning_rate": 1.2002236010021269e-05,
+      "loss": 0.1811,
+      "step": 927500
+    },
+    {
+      "epoch": 9.99,
+      "learning_rate": 1.197484434193893e-05,
+      "loss": 0.1811,
+      "step": 928000
+    },
+    {
+      "epoch": 9.99,
+      "eval_loss": 0.17153653502464294,
+      "eval_runtime": 2.6987,
+      "eval_samples_per_second": 851.135,
+      "eval_steps_per_second": 13.34,
+      "step": 928000
+    },
+    {
+      "epoch": 10.0,
+      "learning_rate": 1.1947638652034617e-05,
+      "loss": 0.1809,
+      "step": 928500
+    },
+    {
+      "epoch": 10.0,
+      "learning_rate": 1.192061901468768e-05,
+      "loss": 0.1811,
+      "step": 929000
+    },
+    {
+      "epoch": 10.0,
+      "eval_loss": 0.17235822975635529,
+      "eval_runtime": 2.6438,
+      "eval_samples_per_second": 868.809,
+      "eval_steps_per_second": 13.617,
+      "step": 929000
+    },
+    {
+      "epoch": 10.01,
+      "learning_rate": 1.1893785503768736e-05,
+      "loss": 0.1812,
+      "step": 929500
+    },
+    {
+      "epoch": 10.02,
+      "learning_rate": 1.1867138192639601e-05,
+      "loss": 0.1809,
+      "step": 930000
+    },
+    {
+      "epoch": 10.02,
+      "eval_loss": 0.1709609031677246,
+      "eval_runtime": 2.6178,
+      "eval_samples_per_second": 877.459,
+      "eval_steps_per_second": 13.752,
+      "step": 930000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 12,
-  "total_flos": 6.449174726764297e+22,
+  "total_flos": 6.519269511347128e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49c53e22d617d625d68b0b7c24d68f147254236ebb3b272bd10eecf6d93598e9
+oid sha256:d3151d7e7cec0857fd8c0138e846e83ffe158233cc9712166843e469c2af9c3a
 size 449471589