Training in progress, step 480000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31f8b72df9e81d9020de8c0d757b3e594d6732915b9d9225bd73528701124126
+oid sha256:6eb2914271748426c715383d1a24825a4ccdc25bc6a47fbcc44c61b6e8bc6904
 size 202194449

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:683da2699cf4f6f0cc7ad0bd863d30bc6b3ce3591f2b81f581d00b7a55c36f19
+oid sha256:c7c95c0d1c732de01b9184ed04d1f634a78d1007e2afb2aea4701f6f53ffae36
 size 102501541

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4c841acb13540ac94fe640beda68267e633bf6f66d1bd05ecc4a8b2a3acbdc1
+oid sha256:32e23eb9436e48648702bf0fff27668d87efa726ca368e875380deaf4f872988
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4c841acb13540ac94fe640beda68267e633bf6f66d1bd05ecc4a8b2a3acbdc1
+oid sha256:32e23eb9436e48648702bf0fff27668d87efa726ca368e875380deaf4f872988
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4c841acb13540ac94fe640beda68267e633bf6f66d1bd05ecc4a8b2a3acbdc1
+oid sha256:32e23eb9436e48648702bf0fff27668d87efa726ca368e875380deaf4f872988
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4c841acb13540ac94fe640beda68267e633bf6f66d1bd05ecc4a8b2a3acbdc1
+oid sha256:32e23eb9436e48648702bf0fff27668d87efa726ca368e875380deaf4f872988
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4c841acb13540ac94fe640beda68267e633bf6f66d1bd05ecc4a8b2a3acbdc1
+oid sha256:32e23eb9436e48648702bf0fff27668d87efa726ca368e875380deaf4f872988
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4c841acb13540ac94fe640beda68267e633bf6f66d1bd05ecc4a8b2a3acbdc1
+oid sha256:32e23eb9436e48648702bf0fff27668d87efa726ca368e875380deaf4f872988
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4c841acb13540ac94fe640beda68267e633bf6f66d1bd05ecc4a8b2a3acbdc1
+oid sha256:32e23eb9436e48648702bf0fff27668d87efa726ca368e875380deaf4f872988
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4c841acb13540ac94fe640beda68267e633bf6f66d1bd05ecc4a8b2a3acbdc1
+oid sha256:32e23eb9436e48648702bf0fff27668d87efa726ca368e875380deaf4f872988
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d15e11a6de6abd55121a73bc214cc950fb971f927ae2b1d5067145da50de5d0
+oid sha256:ebbfa680b1187d22cc7371654116ef29dab3c85749ad34b845956736ad3b3612
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 11.978184413068965,
-  "global_step": 470000,
+  "epoch": 12.233039400581069,
+  "global_step": 480000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -9406,11 +9406,211 @@
       "eval_samples_per_second": 773.322,
       "eval_steps_per_second": 12.373,
       "step": 470000
+    },
+    {
+      "epoch": 11.99,
+      "learning_rate": 1.2751163567020592e-05,
+      "loss": 0.2674,
+      "step": 470500
+    },
+    {
+      "epoch": 12.0,
+      "learning_rate": 1.2658977796373478e-05,
+      "loss": 0.2676,
+      "step": 471000
+    },
+    {
+      "epoch": 12.0,
+      "eval_loss": 0.8069332838058472,
+      "eval_runtime": 1.4521,
+      "eval_samples_per_second": 688.659,
+      "eval_steps_per_second": 11.019,
+      "step": 471000
+    },
+    {
+      "epoch": 12.02,
+      "learning_rate": 1.2568348644340153e-05,
+      "loss": 0.2674,
+      "step": 471500
+    },
+    {
+      "epoch": 12.03,
+      "learning_rate": 1.2479277102026465e-05,
+      "loss": 0.2673,
+      "step": 472000
+    },
+    {
+      "epoch": 12.03,
+      "eval_loss": 0.8061708211898804,
+      "eval_runtime": 1.3407,
+      "eval_samples_per_second": 745.886,
+      "eval_steps_per_second": 11.934,
+      "step": 472000
+    },
+    {
+      "epoch": 12.04,
+      "learning_rate": 1.2391764143504556e-05,
+      "loss": 0.2672,
+      "step": 472500
+    },
+    {
+      "epoch": 12.05,
+      "learning_rate": 1.2305810725802118e-05,
+      "loss": 0.2673,
+      "step": 473000
+    },
+    {
+      "epoch": 12.05,
+      "eval_loss": 0.8025499582290649,
+      "eval_runtime": 1.3181,
+      "eval_samples_per_second": 758.664,
+      "eval_steps_per_second": 12.139,
+      "step": 473000
+    },
+    {
+      "epoch": 12.07,
+      "learning_rate": 1.222141778889195e-05,
+      "loss": 0.2674,
+      "step": 473500
+    },
+    {
+      "epoch": 12.08,
+      "learning_rate": 1.2138586255681707e-05,
+      "loss": 0.2672,
+      "step": 474000
+    },
+    {
+      "epoch": 12.08,
+      "eval_loss": 0.8044158220291138,
+      "eval_runtime": 1.3667,
+      "eval_samples_per_second": 731.706,
+      "eval_steps_per_second": 11.707,
+      "step": 474000
+    },
+    {
+      "epoch": 12.09,
+      "learning_rate": 1.2057317032003731e-05,
+      "loss": 0.2673,
+      "step": 474500
+    },
+    {
+      "epoch": 12.11,
+      "learning_rate": 1.1977611006605263e-05,
+      "loss": 0.2671,
+      "step": 475000
+    },
+    {
+      "epoch": 12.11,
+      "eval_loss": 0.8067881464958191,
+      "eval_runtime": 1.3916,
+      "eval_samples_per_second": 718.588,
+      "eval_steps_per_second": 11.497,
+      "step": 475000
+    },
+    {
+      "epoch": 12.12,
+      "learning_rate": 1.1899469051138602e-05,
+      "loss": 0.267,
+      "step": 475500
+    },
+    {
+      "epoch": 12.13,
+      "learning_rate": 1.1822892020151667e-05,
+      "loss": 0.2672,
+      "step": 476000
+    },
+    {
+      "epoch": 12.13,
+      "eval_loss": 0.8038668632507324,
+      "eval_runtime": 1.2711,
+      "eval_samples_per_second": 786.735,
+      "eval_steps_per_second": 12.588,
+      "step": 476000
+    },
+    {
+      "epoch": 12.14,
+      "learning_rate": 1.1747880751078614e-05,
+      "loss": 0.2673,
+      "step": 476500
+    },
+    {
+      "epoch": 12.16,
+      "learning_rate": 1.1674436064230637e-05,
+      "loss": 0.2673,
+      "step": 477000
+    },
+    {
+      "epoch": 12.16,
+      "eval_loss": 0.8077553510665894,
+      "eval_runtime": 1.3519,
+      "eval_samples_per_second": 739.677,
+      "eval_steps_per_second": 11.835,
+      "step": 477000
+    },
+    {
+      "epoch": 12.17,
+      "learning_rate": 1.1602558762787069e-05,
+      "loss": 0.2672,
+      "step": 477500
+    },
+    {
+      "epoch": 12.18,
+      "learning_rate": 1.1532249632786582e-05,
+      "loss": 0.2671,
+      "step": 478000
+    },
+    {
+      "epoch": 12.18,
+      "eval_loss": 0.8061319589614868,
+      "eval_runtime": 1.3348,
+      "eval_samples_per_second": 749.202,
+      "eval_steps_per_second": 11.987,
+      "step": 478000
+    },
+    {
+      "epoch": 12.19,
+      "learning_rate": 1.1463509443118552e-05,
+      "loss": 0.2672,
+      "step": 478500
+    },
+    {
+      "epoch": 12.21,
+      "learning_rate": 1.1396338945514663e-05,
+      "loss": 0.2673,
+      "step": 479000
+    },
+    {
+      "epoch": 12.21,
+      "eval_loss": 0.802213728427887,
+      "eval_runtime": 1.3304,
+      "eval_samples_per_second": 751.663,
+      "eval_steps_per_second": 12.027,
+      "step": 479000
+    },
+    {
+      "epoch": 12.22,
+      "learning_rate": 1.133073887454072e-05,
+      "loss": 0.267,
+      "step": 479500
+    },
+    {
+      "epoch": 12.23,
+      "learning_rate": 1.1266709947588599e-05,
+      "loss": 0.267,
+      "step": 480000
+    },
+    {
+      "epoch": 12.23,
+      "eval_loss": 0.8064542412757874,
+      "eval_runtime": 1.3174,
+      "eval_samples_per_second": 759.093,
+      "eval_steps_per_second": 12.145,
+      "step": 480000
     }
   ],
   "max_steps": 500000,
   "num_train_epochs": 13,
-  "total_flos": 1.5015747254358005e+22,
+  "total_flos": 1.533522091421946e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:683da2699cf4f6f0cc7ad0bd863d30bc6b3ce3591f2b81f581d00b7a55c36f19
+oid sha256:c7c95c0d1c732de01b9184ed04d1f634a78d1007e2afb2aea4701f6f53ffae36
 size 102501541