Training in progress, step 600000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d50e70f554eb188534935fd7909d648a293a6459a6b08fb795f89d4b99b56d3
+oid sha256:428a42c91913879b41a1c2803d998875b9da7f68b57269ba88572bd6d7ce4f64
 size 3871544599

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b7c41f1dd1fe09e5edbc6dde6212884240e407d1845e563c5f3b4dc645e0c8c
+oid sha256:b080b9b29f961ef52eafaad1999ae2f632518cab5bfbea3cab5786c34f1394b5
 size 1944201353

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f13282abbf7fd053ee4fe6be05fa78fe3b39f9f4687f3d241e7e649eca4d78be
-size 14575
+oid sha256:3a962056376cc55caa0509a94dce6afead45bd33809ddcfeee2f662b8cd813c4
+size 14511

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81e510f8e25cf139f6febe3cdf067c5193934d192326aa6b7345eb94b2015331
+oid sha256:c222d234df96e58f4e769dcdcf413da5cbddf18b696f2ea0f7db071920b58233
 size 557

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a86b6bd5cda860a250f0b8282ba91a7303c4f8c8676b50ffc257a329d6605a0
+oid sha256:ed4046b8b982634729686d6bf5e39b07e66c1d3c6391448d15bb8c916db29fc5
 size 627

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 15.649568527120403,
-  "global_step": 597000,
+  "epoch": 15.728208784641033,
+  "global_step": 600000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -7170,11 +7170,47 @@
       "learning_rate": 5.628747568951393e-07,
       "loss": 1.0314,
       "step": 597000
+    },
+    {
+      "epoch": 15.66,
+      "learning_rate": 5.596251846756392e-07,
+      "loss": 1.0358,
+      "step": 597500
+    },
+    {
+      "epoch": 15.68,
+      "learning_rate": 5.563838371869096e-07,
+      "loss": 1.0075,
+      "step": 598000
+    },
+    {
+      "epoch": 15.69,
+      "learning_rate": 5.531507281681564e-07,
+      "loss": 1.027,
+      "step": 598500
+    },
+    {
+      "epoch": 15.7,
+      "learning_rate": 5.499323127925932e-07,
+      "loss": 1.0259,
+      "step": 599000
+    },
+    {
+      "epoch": 15.72,
+      "learning_rate": 5.467221302031053e-07,
+      "loss": 1.0216,
+      "step": 599500
+    },
+    {
+      "epoch": 15.73,
+      "learning_rate": 5.435137855349992e-07,
+      "loss": 1.0323,
+      "step": 600000
     }
   ],
   "max_steps": 762960,
   "num_train_epochs": 20,
-  "total_flos": 7.136369757666017e+17,
+  "total_flos": 7.169441382292193e+17,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b7c41f1dd1fe09e5edbc6dde6212884240e407d1845e563c5f3b4dc645e0c8c
+oid sha256:b080b9b29f961ef52eafaad1999ae2f632518cab5bfbea3cab5786c34f1394b5
 size 1944201353

runs/Jun02_00-39-49_138e59608869/events.out.tfevents.1685668028.138e59608869.1307.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dde10911f1a5a06553b08b6521d1601b8f9f8f9aa97b33235b07c786ca876155
-size 5421
+oid sha256:394490a971e3aa4fe7457345f302913ccbdb7dd358e0ce79b6cebace43b0f673
+size 6381