Training in progress, step 594000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc9ad53a3115139f361080abe79a9737051bc035a423bc59f9cc8d229a8e895a
+oid sha256:fe0d9f56726daf6b16bb8d5d4f4ade97bb5cc7e60a7f11eb05a8e66f54c42e0f
 size 3871544599

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb3e0019bc999b90253f77b24ce40dc1e78a96ded902156b1cdea866c7ce4331
+oid sha256:650171e8ad578ef8686cb7eda72ac3586fdcc3a1cb73b9e45f5553776bec0a1b
 size 1944201353

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52330c0aa0d02fcb5799ed6e9cc612a980458016cf0a3f065d156f1aa64d865b
+oid sha256:26c8c95b482dc20288935c89df5726ca51c516105c7e5f74e609c7af3177d0c8
 size 14575

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13ae0c12d6dffd3dc4ba83c4aefd7c6399f9d43d426c023af851822645281d9d
+oid sha256:e77e56a2ba56c21827ec91d155588126ec53ab90307574dd6bbda5b13092a2f8
 size 557

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec9b92b3a1b3f86b4bf4ceafccb75f91a766a16a540352fed8d3f4b4b3e97656
+oid sha256:64ce8d836ce27c39f0d4109ce68497decb68e999658c622e881394a4eb6c288a
 size 627

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 15.492277526711474,
-  "global_step": 591000,
+  "epoch": 15.570917784232105,
+  "global_step": 594000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -7098,11 +7098,47 @@
       "learning_rate": 6.024926992769612e-07,
       "loss": 1.0252,
       "step": 591000
+    },
+    {
+      "epoch": 15.51,
+      "learning_rate": 5.991455467779178e-07,
+      "loss": 1.0212,
+      "step": 591500
+    },
+    {
+      "epoch": 15.52,
+      "learning_rate": 5.958064514933821e-07,
+      "loss": 1.04,
+      "step": 592000
+    },
+    {
+      "epoch": 15.53,
+      "learning_rate": 5.924754275768859e-07,
+      "loss": 1.023,
+      "step": 592500
+    },
+    {
+      "epoch": 15.54,
+      "learning_rate": 5.891591269459249e-07,
+      "loss": 1.0252,
+      "step": 593000
+    },
+    {
+      "epoch": 15.56,
+      "learning_rate": 5.85844271876021e-07,
+      "loss": 1.0256,
+      "step": 593500
+    },
+    {
+      "epoch": 15.57,
+      "learning_rate": 5.825375304011768e-07,
+      "loss": 1.0333,
+      "step": 594000
     }
   ],
   "max_steps": 762960,
   "num_train_epochs": 20,
-  "total_flos": 7.070228286116659e+17,
+  "total_flos": 7.103152678841303e+17,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb3e0019bc999b90253f77b24ce40dc1e78a96ded902156b1cdea866c7ce4331
+oid sha256:650171e8ad578ef8686cb7eda72ac3586fdcc3a1cb73b9e45f5553776bec0a1b
 size 1944201353

runs/Jun01_02-00-15_72d6bfb1a401/events.out.tfevents.1685586378.72d6bfb1a401.2268.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e58b715a66e89807c52ea029fcbe06f9781357371c2f8198cbfab569dccf0ea
-size 12141
+oid sha256:fa6281f8fec358f3409920ee2385a0c2769b293403eb4304c3a5bc9ceb1b5b04
+size 13101