Training in progress, step 450000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d13dee40bf739e07daa5e776dbbdc46c2654fbf14746060e2ac946fb44dbe8e5
+oid sha256:c75b6a012ab82fb16d27738e0a95c3b1b8ef7e5d1f6ee0116a8c50549bb847f8
 size 202194449

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61e3683717b89ff6ecb486f42da196e91a7d9315fab8b8963d03c3872a54d691
+oid sha256:78b24f59351cac08b9824b3f79acd0f1dc0a89b48a8f25dc820166f982b53fa7
 size 102501541

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce0e6291f372fe9f86b6a4068760fc679c69ce294ee69065c8ff7ec587e652c0
+oid sha256:9a4f1f1c1cb0bb3ff6487630da96ece6a563c0a58db594f3dd7e10d4cd4b3713
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce0e6291f372fe9f86b6a4068760fc679c69ce294ee69065c8ff7ec587e652c0
+oid sha256:9a4f1f1c1cb0bb3ff6487630da96ece6a563c0a58db594f3dd7e10d4cd4b3713
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce0e6291f372fe9f86b6a4068760fc679c69ce294ee69065c8ff7ec587e652c0
+oid sha256:9a4f1f1c1cb0bb3ff6487630da96ece6a563c0a58db594f3dd7e10d4cd4b3713
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce0e6291f372fe9f86b6a4068760fc679c69ce294ee69065c8ff7ec587e652c0
+oid sha256:9a4f1f1c1cb0bb3ff6487630da96ece6a563c0a58db594f3dd7e10d4cd4b3713
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce0e6291f372fe9f86b6a4068760fc679c69ce294ee69065c8ff7ec587e652c0
+oid sha256:9a4f1f1c1cb0bb3ff6487630da96ece6a563c0a58db594f3dd7e10d4cd4b3713
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce0e6291f372fe9f86b6a4068760fc679c69ce294ee69065c8ff7ec587e652c0
+oid sha256:9a4f1f1c1cb0bb3ff6487630da96ece6a563c0a58db594f3dd7e10d4cd4b3713
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce0e6291f372fe9f86b6a4068760fc679c69ce294ee69065c8ff7ec587e652c0
+oid sha256:9a4f1f1c1cb0bb3ff6487630da96ece6a563c0a58db594f3dd7e10d4cd4b3713
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce0e6291f372fe9f86b6a4068760fc679c69ce294ee69065c8ff7ec587e652c0
+oid sha256:9a4f1f1c1cb0bb3ff6487630da96ece6a563c0a58db594f3dd7e10d4cd4b3713
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1894f32b2441ea8820978bbb44f8f2d9ce0a579e669301efbd1655378591798a
+oid sha256:bc29c434fb0390a8f4f90d65ac745a0b4f381dbd06e857762d450d4a464c7045
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 10.251869801253523,
-  "global_step": 440000,
+  "epoch": 10.484866842191105,
+  "global_step": 450000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -8806,11 +8806,211 @@
       "eval_samples_per_second": 1530.896,
       "eval_steps_per_second": 24.377,
       "step": 440000
+    },
+    {
+      "epoch": 10.26,
+      "learning_rate": 2.1083388335824145e-05,
+      "loss": 0.2526,
+      "step": 440500
+    },
+    {
+      "epoch": 10.28,
+      "learning_rate": 2.0900255633978873e-05,
+      "loss": 0.2525,
+      "step": 441000
+    },
+    {
+      "epoch": 10.28,
+      "eval_loss": 0.23552300035953522,
+      "eval_runtime": 1.4323,
+      "eval_samples_per_second": 1534.608,
+      "eval_steps_per_second": 24.436,
+      "step": 441000
+    },
+    {
+      "epoch": 10.29,
+      "learning_rate": 2.0718589425453314e-05,
+      "loss": 0.2527,
+      "step": 441500
+    },
+    {
+      "epoch": 10.3,
+      "learning_rate": 2.0538391696920015e-05,
+      "loss": 0.2521,
+      "step": 442000
+    },
+    {
+      "epoch": 10.3,
+      "eval_loss": 0.23650765419006348,
+      "eval_runtime": 1.4235,
+      "eval_samples_per_second": 1544.133,
+      "eval_steps_per_second": 24.588,
+      "step": 442000
+    },
+    {
+      "epoch": 10.31,
+      "learning_rate": 2.035966441899249e-05,
+      "loss": 0.2523,
+      "step": 442500
+    },
+    {
+      "epoch": 10.32,
+      "learning_rate": 2.0182409546203555e-05,
+      "loss": 0.2523,
+      "step": 443000
+    },
+    {
+      "epoch": 10.32,
+      "eval_loss": 0.23561330139636993,
+      "eval_runtime": 1.4199,
+      "eval_samples_per_second": 1548.043,
+      "eval_steps_per_second": 24.65,
+      "step": 443000
+    },
+    {
+      "epoch": 10.33,
+      "learning_rate": 2.000662901698415e-05,
+      "loss": 0.2521,
+      "step": 443500
+    },
+    {
+      "epoch": 10.35,
+      "learning_rate": 1.983232475364195e-05,
+      "loss": 0.2523,
+      "step": 444000
+    },
+    {
+      "epoch": 10.35,
+      "eval_loss": 0.23662236332893372,
+      "eval_runtime": 1.4145,
+      "eval_samples_per_second": 1553.873,
+      "eval_steps_per_second": 24.743,
+      "step": 444000
+    },
+    {
+      "epoch": 10.36,
+      "learning_rate": 1.9659498662340474e-05,
+      "loss": 0.2524,
+      "step": 444500
+    },
+    {
+      "epoch": 10.37,
+      "learning_rate": 1.948815263307819e-05,
+      "loss": 0.2519,
+      "step": 445000
+    },
+    {
+      "epoch": 10.37,
+      "eval_loss": 0.23521380126476288,
+      "eval_runtime": 1.4054,
+      "eval_samples_per_second": 1563.94,
+      "eval_steps_per_second": 24.903,
+      "step": 445000
+    },
+    {
+      "epoch": 10.38,
+      "learning_rate": 1.9318288539667765e-05,
+      "loss": 0.2524,
+      "step": 445500
+    },
+    {
+      "epoch": 10.39,
+      "learning_rate": 1.914990823971574e-05,
+      "loss": 0.2523,
+      "step": 446000
+    },
+    {
+      "epoch": 10.39,
+      "eval_loss": 0.2357960045337677,
+      "eval_runtime": 1.4368,
+      "eval_samples_per_second": 1529.784,
+      "eval_steps_per_second": 24.36,
+      "step": 446000
+    },
+    {
+      "epoch": 10.4,
+      "learning_rate": 1.8983013574602096e-05,
+      "loss": 0.2521,
+      "step": 446500
+    },
+    {
+      "epoch": 10.41,
+      "learning_rate": 1.8817606369460156e-05,
+      "loss": 0.2521,
+      "step": 447000
+    },
+    {
+      "epoch": 10.41,
+      "eval_loss": 0.23412732779979706,
+      "eval_runtime": 1.4282,
+      "eval_samples_per_second": 1538.96,
+      "eval_steps_per_second": 24.506,
+      "step": 447000
+    },
+    {
+      "epoch": 10.43,
+      "learning_rate": 1.865368843315663e-05,
+      "loss": 0.252,
+      "step": 447500
+    },
+    {
+      "epoch": 10.44,
+      "learning_rate": 1.8491261558271762e-05,
+      "loss": 0.2519,
+      "step": 448000
+    },
+    {
+      "epoch": 10.44,
+      "eval_loss": 0.23749284446239471,
+      "eval_runtime": 1.4343,
+      "eval_samples_per_second": 1532.461,
+      "eval_steps_per_second": 24.402,
+      "step": 448000
+    },
+    {
+      "epoch": 10.45,
+      "learning_rate": 1.833032752107986e-05,
+      "loss": 0.2518,
+      "step": 448500
+    },
+    {
+      "epoch": 10.46,
+      "learning_rate": 1.817088808152978e-05,
+      "loss": 0.2519,
+      "step": 449000
+    },
+    {
+      "epoch": 10.46,
+      "eval_loss": 0.2349672168493271,
+      "eval_runtime": 1.4127,
+      "eval_samples_per_second": 1555.927,
+      "eval_steps_per_second": 24.776,
+      "step": 449000
+    },
+    {
+      "epoch": 10.47,
+      "learning_rate": 1.801294498322569e-05,
+      "loss": 0.2517,
+      "step": 449500
+    },
+    {
+      "epoch": 10.48,
+      "learning_rate": 1.7856499953407978e-05,
+      "loss": 0.2519,
+      "step": 450000
+    },
+    {
+      "epoch": 10.48,
+      "eval_loss": 0.2356027066707611,
+      "eval_runtime": 1.4379,
+      "eval_samples_per_second": 1528.604,
+      "eval_steps_per_second": 24.341,
+      "step": 450000
     }
   ],
   "max_steps": 500000,
   "num_train_epochs": 12,
-  "total_flos": 1.4057409136168932e+22,
+  "total_flos": 1.4376896274943432e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61e3683717b89ff6ecb486f42da196e91a7d9315fab8b8963d03c3872a54d691
+oid sha256:78b24f59351cac08b9824b3f79acd0f1dc0a89b48a8f25dc820166f982b53fa7
 size 102501541