Training in progress, step 500000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bba175f94af3131ddc7e585c8d0c85376ebd1433f20a5a01a35d8488fc39885b
+oid sha256:3e10f3bf4c9fdd6d04e4a45594e02e70886380f6c627ce307a2167e61722f396
 size 202194449

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc6bd31ef6b75d2ff57b791613279c5afe6c8244312a64f00fb084519b8aaac6
+oid sha256:e6f6ff68ce8f2343aee8e2f40adc1f066ed4b3aebc05b692c06e92c1edcc2d09
 size 102501541

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90520ba7330b686999308b8bbfc39f4cdbd59c0cf0ab7c6ba32bba11cfac21a5
+oid sha256:37572fbf72a1446a290380546bc3e45a2e14961acceac2bf85c43bfce749553b
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90520ba7330b686999308b8bbfc39f4cdbd59c0cf0ab7c6ba32bba11cfac21a5
+oid sha256:37572fbf72a1446a290380546bc3e45a2e14961acceac2bf85c43bfce749553b
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90520ba7330b686999308b8bbfc39f4cdbd59c0cf0ab7c6ba32bba11cfac21a5
+oid sha256:37572fbf72a1446a290380546bc3e45a2e14961acceac2bf85c43bfce749553b
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90520ba7330b686999308b8bbfc39f4cdbd59c0cf0ab7c6ba32bba11cfac21a5
+oid sha256:37572fbf72a1446a290380546bc3e45a2e14961acceac2bf85c43bfce749553b
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90520ba7330b686999308b8bbfc39f4cdbd59c0cf0ab7c6ba32bba11cfac21a5
+oid sha256:37572fbf72a1446a290380546bc3e45a2e14961acceac2bf85c43bfce749553b
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90520ba7330b686999308b8bbfc39f4cdbd59c0cf0ab7c6ba32bba11cfac21a5
+oid sha256:37572fbf72a1446a290380546bc3e45a2e14961acceac2bf85c43bfce749553b
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90520ba7330b686999308b8bbfc39f4cdbd59c0cf0ab7c6ba32bba11cfac21a5
+oid sha256:37572fbf72a1446a290380546bc3e45a2e14961acceac2bf85c43bfce749553b
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90520ba7330b686999308b8bbfc39f4cdbd59c0cf0ab7c6ba32bba11cfac21a5
+oid sha256:37572fbf72a1446a290380546bc3e45a2e14961acceac2bf85c43bfce749553b
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d798ff13d72fe751bc0ea721c37eb1e98064dde5819b90f3504db53fdceee97
+oid sha256:53a074c65f43dfe683b5f0e988de79e3365c939ebb4b13c8f9ce84b59bdb64a7
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 10.929693076374019,
-  "global_step": 490000,
+  "epoch": 11.152748037116346,
+  "global_step": 500000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -9806,11 +9806,211 @@
       "eval_samples_per_second": 1128.67,
       "eval_steps_per_second": 17.689,
       "step": 490000
+    },
+    {
+      "epoch": 10.94,
+      "learning_rate": 1.0286124377900624e-05,
+      "loss": 0.2541,
+      "step": 490500
+    },
+    {
+      "epoch": 10.95,
+      "learning_rate": 1.0256807270282153e-05,
+      "loss": 0.2537,
+      "step": 491000
+    },
+    {
+      "epoch": 10.95,
+      "eval_loss": 0.23797546327114105,
+      "eval_runtime": 1.9751,
+      "eval_samples_per_second": 1162.982,
+      "eval_steps_per_second": 18.227,
+      "step": 491000
+    },
+    {
+      "epoch": 10.96,
+      "learning_rate": 1.0229073051029455e-05,
+      "loss": 0.2539,
+      "step": 491500
+    },
+    {
+      "epoch": 10.97,
+      "learning_rate": 1.020292202343952e-05,
+      "loss": 0.254,
+      "step": 492000
+    },
+    {
+      "epoch": 10.97,
+      "eval_loss": 0.23647533357143402,
+      "eval_runtime": 2.0099,
+      "eval_samples_per_second": 1142.868,
+      "eval_steps_per_second": 17.912,
+      "step": 492000
+    },
+    {
+      "epoch": 10.99,
+      "learning_rate": 1.0178354473495813e-05,
+      "loss": 0.2539,
+      "step": 492500
+    },
+    {
+      "epoch": 11.0,
+      "learning_rate": 1.0155370669865077e-05,
+      "loss": 0.254,
+      "step": 493000
+    },
+    {
+      "epoch": 11.0,
+      "eval_loss": 0.2374097853899002,
+      "eval_runtime": 1.9968,
+      "eval_samples_per_second": 1150.347,
+      "eval_steps_per_second": 18.029,
+      "step": 493000
+    },
+    {
+      "epoch": 11.01,
+      "learning_rate": 1.0133970863894557e-05,
+      "loss": 0.2537,
+      "step": 493500
+    },
+    {
+      "epoch": 11.02,
+      "learning_rate": 1.0114155289609061e-05,
+      "loss": 0.2535,
+      "step": 494000
+    },
+    {
+      "epoch": 11.02,
+      "eval_loss": 0.23701806366443634,
+      "eval_runtime": 2.0405,
+      "eval_samples_per_second": 1125.682,
+      "eval_steps_per_second": 17.642,
+      "step": 494000
+    },
+    {
+      "epoch": 11.03,
+      "learning_rate": 1.0095924163708572e-05,
+      "loss": 0.2542,
+      "step": 494500
+    },
+    {
+      "epoch": 11.04,
+      "learning_rate": 1.0079277685565724e-05,
+      "loss": 0.2538,
+      "step": 495000
+    },
+    {
+      "epoch": 11.04,
+      "eval_loss": 0.23448336124420166,
+      "eval_runtime": 1.9969,
+      "eval_samples_per_second": 1150.279,
+      "eval_steps_per_second": 18.028,
+      "step": 495000
+    },
+    {
+      "epoch": 11.05,
+      "learning_rate": 1.0064216037223772e-05,
+      "loss": 0.2536,
+      "step": 495500
+    },
+    {
+      "epoch": 11.06,
+      "learning_rate": 1.0050739383394454e-05,
+      "loss": 0.2539,
+      "step": 496000
+    },
+    {
+      "epoch": 11.06,
+      "eval_loss": 0.23559238016605377,
+      "eval_runtime": 2.0311,
+      "eval_samples_per_second": 1130.902,
+      "eval_steps_per_second": 17.724,
+      "step": 496000
+    },
+    {
+      "epoch": 11.07,
+      "learning_rate": 1.003884787145633e-05,
+      "loss": 0.2532,
+      "step": 496500
+    },
+    {
+      "epoch": 11.09,
+      "learning_rate": 1.002854163145305e-05,
+      "loss": 0.2533,
+      "step": 497000
+    },
+    {
+      "epoch": 11.09,
+      "eval_loss": 0.23612073063850403,
+      "eval_runtime": 2.0421,
+      "eval_samples_per_second": 1124.803,
+      "eval_steps_per_second": 17.629,
+      "step": 497000
+    },
+    {
+      "epoch": 11.1,
+      "learning_rate": 1.0019820776091995e-05,
+      "loss": 0.2531,
+      "step": 497500
+    },
+    {
+      "epoch": 11.11,
+      "learning_rate": 1.0012685400743077e-05,
+      "loss": 0.2533,
+      "step": 498000
+    },
+    {
+      "epoch": 11.11,
+      "eval_loss": 0.23812700808048248,
+      "eval_runtime": 2.036,
+      "eval_samples_per_second": 1128.176,
+      "eval_steps_per_second": 17.681,
+      "step": 498000
+    },
+    {
+      "epoch": 11.12,
+      "learning_rate": 1.0007135583437572e-05,
+      "loss": 0.2531,
+      "step": 498500
+    },
+    {
+      "epoch": 11.13,
+      "learning_rate": 1.0003171384867436e-05,
+      "loss": 0.2534,
+      "step": 499000
+    },
+    {
+      "epoch": 11.13,
+      "eval_loss": 0.23714645206928253,
+      "eval_runtime": 2.0313,
+      "eval_samples_per_second": 1130.821,
+      "eval_steps_per_second": 17.723,
+      "step": 499000
+    },
+    {
+      "epoch": 11.14,
+      "learning_rate": 1.0000792848384467e-05,
+      "loss": 0.2535,
+      "step": 499500
+    },
+    {
+      "epoch": 11.15,
+      "learning_rate": 1e-05,
+      "loss": 0.2535,
+      "step": 500000
+    },
+    {
+      "epoch": 11.15,
+      "eval_loss": 0.23556514084339142,
+      "eval_runtime": 1.9635,
+      "eval_samples_per_second": 1169.857,
+      "eval_steps_per_second": 18.335,
+      "step": 500000
     }
   ],
   "max_steps": 500000,
   "num_train_epochs": 12,
-  "total_flos": 1.5654585257336347e+22,
+  "total_flos": 1.5974043941849432e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc6bd31ef6b75d2ff57b791613279c5afe6c8244312a64f00fb084519b8aaac6
+oid sha256:e6f6ff68ce8f2343aee8e2f40adc1f066ed4b3aebc05b692c06e92c1edcc2d09
 size 102501541