Training in progress, step 450000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a4ad94b9d5ed920cecf2394888d2a87ad3ee893c3c5ddbd5617ff00b81d3e84
+oid sha256:6931208249dada9481d4f15fa6a8eb29e66faab6c960f940cb42178be058ede5
 size 202194449

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c579869ee7eca1f3cfb28c1e8c5c1a2c4c07c47eb9cbbb5f2453c93bc559b64a
+oid sha256:96730bdf9c613274e5002868e7a4d31f7cf6da025343ac9c04b48c36b22d877f
 size 102501541

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25a654aa71fcb8c8c7fac3eb694717c26bcb1def578ecd3a5246da103da0b6ce
+oid sha256:d0eac835ca5ea6ff1c5bc401311ec38950e11a1e99d93162fecdaf18652f830d
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25a654aa71fcb8c8c7fac3eb694717c26bcb1def578ecd3a5246da103da0b6ce
+oid sha256:d0eac835ca5ea6ff1c5bc401311ec38950e11a1e99d93162fecdaf18652f830d
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25a654aa71fcb8c8c7fac3eb694717c26bcb1def578ecd3a5246da103da0b6ce
+oid sha256:d0eac835ca5ea6ff1c5bc401311ec38950e11a1e99d93162fecdaf18652f830d
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25a654aa71fcb8c8c7fac3eb694717c26bcb1def578ecd3a5246da103da0b6ce
+oid sha256:d0eac835ca5ea6ff1c5bc401311ec38950e11a1e99d93162fecdaf18652f830d
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25a654aa71fcb8c8c7fac3eb694717c26bcb1def578ecd3a5246da103da0b6ce
+oid sha256:d0eac835ca5ea6ff1c5bc401311ec38950e11a1e99d93162fecdaf18652f830d
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25a654aa71fcb8c8c7fac3eb694717c26bcb1def578ecd3a5246da103da0b6ce
+oid sha256:d0eac835ca5ea6ff1c5bc401311ec38950e11a1e99d93162fecdaf18652f830d
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25a654aa71fcb8c8c7fac3eb694717c26bcb1def578ecd3a5246da103da0b6ce
+oid sha256:d0eac835ca5ea6ff1c5bc401311ec38950e11a1e99d93162fecdaf18652f830d
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25a654aa71fcb8c8c7fac3eb694717c26bcb1def578ecd3a5246da103da0b6ce
+oid sha256:d0eac835ca5ea6ff1c5bc401311ec38950e11a1e99d93162fecdaf18652f830d
 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": 9.814418272662383,
-  "global_step": 440000,
+  "epoch": 10.037473233404711,
+  "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": 1153.611,
       "eval_steps_per_second": 18.08,
       "step": 440000
+    },
+    {
+      "epoch": 9.83,
+      "learning_rate": 2.1083388335824145e-05,
+      "loss": 0.2568,
+      "step": 440500
+    },
+    {
+      "epoch": 9.84,
+      "learning_rate": 2.0900255633978873e-05,
+      "loss": 0.257,
+      "step": 441000
+    },
+    {
+      "epoch": 9.84,
+      "eval_loss": 0.23978090286254883,
+      "eval_runtime": 2.0085,
+      "eval_samples_per_second": 1143.638,
+      "eval_steps_per_second": 17.924,
+      "step": 441000
+    },
+    {
+      "epoch": 9.85,
+      "learning_rate": 2.0718589425453314e-05,
+      "loss": 0.2559,
+      "step": 441500
+    },
+    {
+      "epoch": 9.86,
+      "learning_rate": 2.0538391696920015e-05,
+      "loss": 0.2559,
+      "step": 442000
+    },
+    {
+      "epoch": 9.86,
+      "eval_loss": 0.23992407321929932,
+      "eval_runtime": 1.9856,
+      "eval_samples_per_second": 1156.855,
+      "eval_steps_per_second": 18.131,
+      "step": 442000
+    },
+    {
+      "epoch": 9.87,
+      "learning_rate": 2.035966441899249e-05,
+      "loss": 0.2557,
+      "step": 442500
+    },
+    {
+      "epoch": 9.88,
+      "learning_rate": 2.0182409546203555e-05,
+      "loss": 0.2556,
+      "step": 443000
+    },
+    {
+      "epoch": 9.88,
+      "eval_loss": 0.23771096765995026,
+      "eval_runtime": 1.9588,
+      "eval_samples_per_second": 1172.656,
+      "eval_steps_per_second": 18.379,
+      "step": 443000
+    },
+    {
+      "epoch": 9.89,
+      "learning_rate": 2.000662901698415e-05,
+      "loss": 0.2562,
+      "step": 443500
+    },
+    {
+      "epoch": 9.9,
+      "learning_rate": 1.983232475364195e-05,
+      "loss": 0.2565,
+      "step": 444000
+    },
+    {
+      "epoch": 9.9,
+      "eval_loss": 0.24137504398822784,
+      "eval_runtime": 1.9524,
+      "eval_samples_per_second": 1176.51,
+      "eval_steps_per_second": 18.439,
+      "step": 444000
+    },
+    {
+      "epoch": 9.91,
+      "learning_rate": 1.9659498662340474e-05,
+      "loss": 0.2563,
+      "step": 444500
+    },
+    {
+      "epoch": 9.93,
+      "learning_rate": 1.948815263307819e-05,
+      "loss": 0.2562,
+      "step": 445000
+    },
+    {
+      "epoch": 9.93,
+      "eval_loss": 0.23801474273204803,
+      "eval_runtime": 2.0266,
+      "eval_samples_per_second": 1133.424,
+      "eval_steps_per_second": 17.764,
+      "step": 445000
+    },
+    {
+      "epoch": 9.94,
+      "learning_rate": 1.9318288539667765e-05,
+      "loss": 0.2562,
+      "step": 445500
+    },
+    {
+      "epoch": 9.95,
+      "learning_rate": 1.914990823971574e-05,
+      "loss": 0.2558,
+      "step": 446000
+    },
+    {
+      "epoch": 9.95,
+      "eval_loss": 0.23844870924949646,
+      "eval_runtime": 2.0906,
+      "eval_samples_per_second": 1098.726,
+      "eval_steps_per_second": 17.22,
+      "step": 446000
+    },
+    {
+      "epoch": 9.96,
+      "learning_rate": 1.8983013574602096e-05,
+      "loss": 0.2559,
+      "step": 446500
+    },
+    {
+      "epoch": 9.97,
+      "learning_rate": 1.8817606369460156e-05,
+      "loss": 0.2555,
+      "step": 447000
+    },
+    {
+      "epoch": 9.97,
+      "eval_loss": 0.23887751996517181,
+      "eval_runtime": 2.059,
+      "eval_samples_per_second": 1115.606,
+      "eval_steps_per_second": 17.484,
+      "step": 447000
+    },
+    {
+      "epoch": 9.98,
+      "learning_rate": 1.865368843315663e-05,
+      "loss": 0.2561,
+      "step": 447500
+    },
+    {
+      "epoch": 9.99,
+      "learning_rate": 1.8491261558271762e-05,
+      "loss": 0.2558,
+      "step": 448000
+    },
+    {
+      "epoch": 9.99,
+      "eval_loss": 0.2371719628572464,
+      "eval_runtime": 1.9897,
+      "eval_samples_per_second": 1154.434,
+      "eval_steps_per_second": 18.093,
+      "step": 448000
+    },
+    {
+      "epoch": 10.0,
+      "learning_rate": 1.833032752107986e-05,
+      "loss": 0.256,
+      "step": 448500
+    },
+    {
+      "epoch": 10.02,
+      "learning_rate": 1.817088808152978e-05,
+      "loss": 0.2563,
+      "step": 449000
+    },
+    {
+      "epoch": 10.02,
+      "eval_loss": 0.23607970774173737,
+      "eval_runtime": 2.0104,
+      "eval_samples_per_second": 1142.561,
+      "eval_steps_per_second": 17.907,
+      "step": 449000
+    },
+    {
+      "epoch": 10.03,
+      "learning_rate": 1.801294498322569e-05,
+      "loss": 0.2559,
+      "step": 449500
+    },
+    {
+      "epoch": 10.04,
+      "learning_rate": 1.7856499953407978e-05,
+      "loss": 0.2555,
+      "step": 450000
+    },
+    {
+      "epoch": 10.04,
+      "eval_loss": 0.238793283700943,
+      "eval_runtime": 2.0158,
+      "eval_samples_per_second": 1139.483,
+      "eval_steps_per_second": 17.859,
+      "step": 450000
     }
   ],
   "max_steps": 500000,
   "num_train_epochs": 12,
-  "total_flos": 1.4057178017725262e+22,
+  "total_flos": 1.4376636702238347e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c579869ee7eca1f3cfb28c1e8c5c1a2c4c07c47eb9cbbb5f2453c93bc559b64a
+oid sha256:96730bdf9c613274e5002868e7a4d31f7cf6da025343ac9c04b48c36b22d877f
 size 102501541