Training in progress, step 460000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6931208249dada9481d4f15fa6a8eb29e66faab6c960f940cb42178be058ede5
+oid sha256:b547411c79d357104c70e5661a49a33c4c727f3979f31a84e358578efcb1bf5d
 size 202194449

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96730bdf9c613274e5002868e7a4d31f7cf6da025343ac9c04b48c36b22d877f
+oid sha256:e9908cf9403ac4306b20a0d3eb86bc03da4da8a781371917c67d6447e4350b51
 size 102501541

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0eac835ca5ea6ff1c5bc401311ec38950e11a1e99d93162fecdaf18652f830d
+oid sha256:c14f347b3051d84f6b39fd81f0a25c5ca1660537f9dd78ea3f5348e6e0fe62d0
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0eac835ca5ea6ff1c5bc401311ec38950e11a1e99d93162fecdaf18652f830d
+oid sha256:c14f347b3051d84f6b39fd81f0a25c5ca1660537f9dd78ea3f5348e6e0fe62d0
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0eac835ca5ea6ff1c5bc401311ec38950e11a1e99d93162fecdaf18652f830d
+oid sha256:c14f347b3051d84f6b39fd81f0a25c5ca1660537f9dd78ea3f5348e6e0fe62d0
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0eac835ca5ea6ff1c5bc401311ec38950e11a1e99d93162fecdaf18652f830d
+oid sha256:c14f347b3051d84f6b39fd81f0a25c5ca1660537f9dd78ea3f5348e6e0fe62d0
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0eac835ca5ea6ff1c5bc401311ec38950e11a1e99d93162fecdaf18652f830d
+oid sha256:c14f347b3051d84f6b39fd81f0a25c5ca1660537f9dd78ea3f5348e6e0fe62d0
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0eac835ca5ea6ff1c5bc401311ec38950e11a1e99d93162fecdaf18652f830d
+oid sha256:c14f347b3051d84f6b39fd81f0a25c5ca1660537f9dd78ea3f5348e6e0fe62d0
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0eac835ca5ea6ff1c5bc401311ec38950e11a1e99d93162fecdaf18652f830d
+oid sha256:c14f347b3051d84f6b39fd81f0a25c5ca1660537f9dd78ea3f5348e6e0fe62d0
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0eac835ca5ea6ff1c5bc401311ec38950e11a1e99d93162fecdaf18652f830d
+oid sha256:c14f347b3051d84f6b39fd81f0a25c5ca1660537f9dd78ea3f5348e6e0fe62d0
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc29c434fb0390a8f4f90d65ac745a0b4f381dbd06e857762d450d4a464c7045
+oid sha256:d60fd80961b777bf4901f5c7189278f8f31f61a50c51a19e170f6a1919a5ce33
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 10.037473233404711,
-  "global_step": 450000,
+  "epoch": 10.260528194147037,
+  "global_step": 460000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -9006,11 +9006,211 @@
       "eval_samples_per_second": 1139.483,
       "eval_steps_per_second": 17.859,
       "step": 450000
+    },
+    {
+      "epoch": 10.05,
+      "learning_rate": 1.770155470293445e-05,
+      "loss": 0.2555,
+      "step": 450500
+    },
+    {
+      "epoch": 10.06,
+      "learning_rate": 1.7548110926261522e-05,
+      "loss": 0.2557,
+      "step": 451000
+    },
+    {
+      "epoch": 10.06,
+      "eval_loss": 0.23789702355861664,
+      "eval_runtime": 2.0142,
+      "eval_samples_per_second": 1140.419,
+      "eval_steps_per_second": 17.873,
+      "step": 451000
+    },
+    {
+      "epoch": 10.07,
+      "learning_rate": 1.7396170301425777e-05,
+      "loss": 0.2558,
+      "step": 451500
+    },
+    {
+      "epoch": 10.08,
+      "learning_rate": 1.7245734490025544e-05,
+      "loss": 0.2556,
+      "step": 452000
+    },
+    {
+      "epoch": 10.08,
+      "eval_loss": 0.2400251030921936,
+      "eval_runtime": 1.9794,
+      "eval_samples_per_second": 1160.467,
+      "eval_steps_per_second": 18.188,
+      "step": 452000
+    },
+    {
+      "epoch": 10.09,
+      "learning_rate": 1.7096805137202738e-05,
+      "loss": 0.2559,
+      "step": 452500
+    },
+    {
+      "epoch": 10.1,
+      "learning_rate": 1.6949383871624917e-05,
+      "loss": 0.2556,
+      "step": 453000
+    },
+    {
+      "epoch": 10.1,
+      "eval_loss": 0.24092479050159454,
+      "eval_runtime": 1.9634,
+      "eval_samples_per_second": 1169.917,
+      "eval_steps_per_second": 18.336,
+      "step": 453000
+    },
+    {
+      "epoch": 10.12,
+      "learning_rate": 1.6803472305467368e-05,
+      "loss": 0.2557,
+      "step": 453500
+    },
+    {
+      "epoch": 10.13,
+      "learning_rate": 1.665907203439568e-05,
+      "loss": 0.2557,
+      "step": 454000
+    },
+    {
+      "epoch": 10.13,
+      "eval_loss": 0.23987002670764923,
+      "eval_runtime": 1.9519,
+      "eval_samples_per_second": 1176.785,
+      "eval_steps_per_second": 18.443,
+      "step": 454000
+    },
+    {
+      "epoch": 10.14,
+      "learning_rate": 1.6516184637548058e-05,
+      "loss": 0.257,
+      "step": 454500
+    },
+    {
+      "epoch": 10.15,
+      "learning_rate": 1.6374811677518142e-05,
+      "loss": 0.2555,
+      "step": 455000
+    },
+    {
+      "epoch": 10.15,
+      "eval_loss": 0.2387952208518982,
+      "eval_runtime": 2.0231,
+      "eval_samples_per_second": 1135.362,
+      "eval_steps_per_second": 17.794,
+      "step": 455000
+    },
+    {
+      "epoch": 10.16,
+      "learning_rate": 1.6234954700338025e-05,
+      "loss": 0.2555,
+      "step": 455500
+    },
+    {
+      "epoch": 10.17,
+      "learning_rate": 1.6096615235461148e-05,
+      "loss": 0.2549,
+      "step": 456000
+    },
+    {
+      "epoch": 10.17,
+      "eval_loss": 0.23763985931873322,
+      "eval_runtime": 2.0435,
+      "eval_samples_per_second": 1124.037,
+      "eval_steps_per_second": 17.617,
+      "step": 456000
+    },
+    {
+      "epoch": 10.18,
+      "learning_rate": 1.59597947957458e-05,
+      "loss": 0.2557,
+      "step": 456500
+    },
+    {
+      "epoch": 10.19,
+      "learning_rate": 1.5824494877438344e-05,
+      "loss": 0.2551,
+      "step": 457000
+    },
+    {
+      "epoch": 10.19,
+      "eval_loss": 0.23833227157592773,
+      "eval_runtime": 2.01,
+      "eval_samples_per_second": 1142.798,
+      "eval_steps_per_second": 17.911,
+      "step": 457000
+    },
+    {
+      "epoch": 10.2,
+      "learning_rate": 1.569071696015702e-05,
+      "loss": 0.2549,
+      "step": 457500
+    },
+    {
+      "epoch": 10.22,
+      "learning_rate": 1.555846250687569e-05,
+      "loss": 0.2551,
+      "step": 458000
+    },
+    {
+      "epoch": 10.22,
+      "eval_loss": 0.23883755505084991,
+      "eval_runtime": 1.9432,
+      "eval_samples_per_second": 1182.062,
+      "eval_steps_per_second": 18.526,
+      "step": 458000
+    },
+    {
+      "epoch": 10.23,
+      "learning_rate": 1.542773296390789e-05,
+      "loss": 0.2555,
+      "step": 458500
+    },
+    {
+      "epoch": 10.24,
+      "learning_rate": 1.5298529760890945e-05,
+      "loss": 0.2559,
+      "step": 459000
+    },
+    {
+      "epoch": 10.24,
+      "eval_loss": 0.23782269656658173,
+      "eval_runtime": 1.9879,
+      "eval_samples_per_second": 1155.497,
+      "eval_steps_per_second": 18.11,
+      "step": 459000
+    },
+    {
+      "epoch": 10.25,
+      "learning_rate": 1.5170854310770376e-05,
+      "loss": 0.2557,
+      "step": 459500
+    },
+    {
+      "epoch": 10.26,
+      "learning_rate": 1.5044708009784457e-05,
+      "loss": 0.2555,
+      "step": 460000
+    },
+    {
+      "epoch": 10.26,
+      "eval_loss": 0.23906496167182922,
+      "eval_runtime": 1.9573,
+      "eval_samples_per_second": 1173.539,
+      "eval_steps_per_second": 18.392,
+      "step": 460000
     }
   ],
   "max_steps": 500000,
   "num_train_epochs": 12,
-  "total_flos": 1.4376636702238347e+22,
+  "total_flos": 1.4696123841012847e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96730bdf9c613274e5002868e7a4d31f7cf6da025343ac9c04b48c36b22d877f
+oid sha256:e9908cf9403ac4306b20a0d3eb86bc03da4da8a781371917c67d6447e4350b51
 size 102501541