Training in progress, step 490000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6eb2914271748426c715383d1a24825a4ccdc25bc6a47fbcc44c61b6e8bc6904
+oid sha256:cab54be7cb4d2572a34bddaadf5aa44b09e63a53da564cdebcbf1c0114515cb4
 size 202194449

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7c95c0d1c732de01b9184ed04d1f634a78d1007e2afb2aea4701f6f53ffae36
+oid sha256:0cd7e757b48942dd6939c67ce3bb195396690b3f6c6d27ddc20a0b96e1fdb0e9
 size 102501541

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:32e23eb9436e48648702bf0fff27668d87efa726ca368e875380deaf4f872988
+oid sha256:e90597af9402f8b4ddc86423edd1595c0f03275adba0e3f54a96b077337ac052
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:32e23eb9436e48648702bf0fff27668d87efa726ca368e875380deaf4f872988
+oid sha256:e90597af9402f8b4ddc86423edd1595c0f03275adba0e3f54a96b077337ac052
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:32e23eb9436e48648702bf0fff27668d87efa726ca368e875380deaf4f872988
+oid sha256:e90597af9402f8b4ddc86423edd1595c0f03275adba0e3f54a96b077337ac052
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:32e23eb9436e48648702bf0fff27668d87efa726ca368e875380deaf4f872988
+oid sha256:e90597af9402f8b4ddc86423edd1595c0f03275adba0e3f54a96b077337ac052
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:32e23eb9436e48648702bf0fff27668d87efa726ca368e875380deaf4f872988
+oid sha256:e90597af9402f8b4ddc86423edd1595c0f03275adba0e3f54a96b077337ac052
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:32e23eb9436e48648702bf0fff27668d87efa726ca368e875380deaf4f872988
+oid sha256:e90597af9402f8b4ddc86423edd1595c0f03275adba0e3f54a96b077337ac052
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:32e23eb9436e48648702bf0fff27668d87efa726ca368e875380deaf4f872988
+oid sha256:e90597af9402f8b4ddc86423edd1595c0f03275adba0e3f54a96b077337ac052
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:32e23eb9436e48648702bf0fff27668d87efa726ca368e875380deaf4f872988
+oid sha256:e90597af9402f8b4ddc86423edd1595c0f03275adba0e3f54a96b077337ac052
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ebbfa680b1187d22cc7371654116ef29dab3c85749ad34b845956736ad3b3612
+oid sha256:7d798ff13d72fe751bc0ea721c37eb1e98064dde5819b90f3504db53fdceee97
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 12.233039400581069,
-  "global_step": 480000,
+  "epoch": 12.487894388093174,
+  "global_step": 490000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -9606,11 +9606,211 @@
       "eval_samples_per_second": 759.093,
       "eval_steps_per_second": 12.145,
       "step": 480000
+    },
+    {
+      "epoch": 12.25,
+      "learning_rate": 1.1204252864868377e-05,
+      "loss": 0.2669,
+      "step": 480500
+    },
+    {
+      "epoch": 12.26,
+      "learning_rate": 1.1143368309400725e-05,
+      "loss": 0.2672,
+      "step": 481000
+    },
+    {
+      "epoch": 12.26,
+      "eval_loss": 0.8035285472869873,
+      "eval_runtime": 1.597,
+      "eval_samples_per_second": 626.161,
+      "eval_steps_per_second": 10.019,
+      "step": 481000
+    },
+    {
+      "epoch": 12.27,
+      "learning_rate": 1.1084056947009348e-05,
+      "loss": 0.2671,
+      "step": 481500
+    },
+    {
+      "epoch": 12.28,
+      "learning_rate": 1.1026319426313837e-05,
+      "loss": 0.267,
+      "step": 482000
+    },
+    {
+      "epoch": 12.28,
+      "eval_loss": 0.8039422035217285,
+      "eval_runtime": 1.2756,
+      "eval_samples_per_second": 783.963,
+      "eval_steps_per_second": 12.543,
+      "step": 482000
+    },
+    {
+      "epoch": 12.3,
+      "learning_rate": 1.097015637872247e-05,
+      "loss": 0.2669,
+      "step": 482500
+    },
+    {
+      "epoch": 12.31,
+      "learning_rate": 1.0915568418425301e-05,
+      "loss": 0.2669,
+      "step": 483000
+    },
+    {
+      "epoch": 12.31,
+      "eval_loss": 0.8074455857276917,
+      "eval_runtime": 1.3487,
+      "eval_samples_per_second": 741.458,
+      "eval_steps_per_second": 11.863,
+      "step": 483000
+    },
+    {
+      "epoch": 12.32,
+      "learning_rate": 1.0862556142387571e-05,
+      "loss": 0.2673,
+      "step": 483500
+    },
+    {
+      "epoch": 12.33,
+      "learning_rate": 1.081112013034298e-05,
+      "loss": 0.267,
+      "step": 484000
+    },
+    {
+      "epoch": 12.33,
+      "eval_loss": 0.8040180802345276,
+      "eval_runtime": 1.3584,
+      "eval_samples_per_second": 736.142,
+      "eval_steps_per_second": 11.778,
+      "step": 484000
+    },
+    {
+      "epoch": 12.35,
+      "learning_rate": 1.0761260944787561e-05,
+      "loss": 0.267,
+      "step": 484500
+    },
+    {
+      "epoch": 12.36,
+      "learning_rate": 1.0712979130973347e-05,
+      "loss": 0.267,
+      "step": 485000
+    },
+    {
+      "epoch": 12.36,
+      "eval_loss": 0.8028098940849304,
+      "eval_runtime": 1.3341,
+      "eval_samples_per_second": 749.592,
+      "eval_steps_per_second": 11.993,
+      "step": 485000
+    },
+    {
+      "epoch": 12.37,
+      "learning_rate": 1.0666275216902535e-05,
+      "loss": 0.2668,
+      "step": 485500
+    },
+    {
+      "epoch": 12.39,
+      "learning_rate": 1.0621149713321656e-05,
+      "loss": 0.2668,
+      "step": 486000
+    },
+    {
+      "epoch": 12.39,
+      "eval_loss": 0.8054640889167786,
+      "eval_runtime": 1.3289,
+      "eval_samples_per_second": 752.527,
+      "eval_steps_per_second": 12.04,
+      "step": 486000
+    },
+    {
+      "epoch": 12.4,
+      "learning_rate": 1.0577603113715964e-05,
+      "loss": 0.2669,
+      "step": 486500
+    },
+    {
+      "epoch": 12.41,
+      "learning_rate": 1.0535635894304106e-05,
+      "loss": 0.2669,
+      "step": 487000
+    },
+    {
+      "epoch": 12.41,
+      "eval_loss": 0.8062050342559814,
+      "eval_runtime": 1.3114,
+      "eval_samples_per_second": 762.54,
+      "eval_steps_per_second": 12.201,
+      "step": 487000
+    },
+    {
+      "epoch": 12.42,
+      "learning_rate": 1.0495248514032875e-05,
+      "loss": 0.2669,
+      "step": 487500
+    },
+    {
+      "epoch": 12.44,
+      "learning_rate": 1.045644141457218e-05,
+      "loss": 0.2669,
+      "step": 488000
+    },
+    {
+      "epoch": 12.44,
+      "eval_loss": 0.8053330779075623,
+      "eval_runtime": 1.3085,
+      "eval_samples_per_second": 764.21,
+      "eval_steps_per_second": 12.227,
+      "step": 488000
+    },
+    {
+      "epoch": 12.45,
+      "learning_rate": 1.0419215020310254e-05,
+      "loss": 0.2671,
+      "step": 488500
+    },
+    {
+      "epoch": 12.46,
+      "learning_rate": 1.0383569738348988e-05,
+      "loss": 0.267,
+      "step": 489000
+    },
+    {
+      "epoch": 12.46,
+      "eval_loss": 0.8089292049407959,
+      "eval_runtime": 1.3008,
+      "eval_samples_per_second": 768.73,
+      "eval_steps_per_second": 12.3,
+      "step": 489000
+    },
+    {
+      "epoch": 12.48,
+      "learning_rate": 1.0349505958499436e-05,
+      "loss": 0.2671,
+      "step": 489500
+    },
+    {
+      "epoch": 12.49,
+      "learning_rate": 1.0317024053277693e-05,
+      "loss": 0.267,
+      "step": 490000
+    },
+    {
+      "epoch": 12.49,
+      "eval_loss": 0.8080971837043762,
+      "eval_runtime": 1.3533,
+      "eval_samples_per_second": 738.941,
+      "eval_steps_per_second": 11.823,
+      "step": 490000
     }
   ],
   "max_steps": 500000,
   "num_train_epochs": 13,
-  "total_flos": 1.533522091421946e+22,
+  "total_flos": 1.565470805299396e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7c95c0d1c732de01b9184ed04d1f634a78d1007e2afb2aea4701f6f53ffae36
+oid sha256:0cd7e757b48942dd6939c67ce3bb195396690b3f6c6d27ddc20a0b96e1fdb0e9
 size 102501541