Training in progress, step 621000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28258e1287b12e2894e7ee5338373df7e90323e2088570811700158685632333
+oid sha256:806be1299dc9f397b015bf45e4e9491d4765b5be56231fa086b220f80466e124
 size 3871544599

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0463186043fb0e3ac3533b11e5b51a4e826f1414cbaa678780d638011c23f2f0
+oid sha256:4467c2e695dbb515cc354d8e7385cc956efa20f7924c326db2a4ecdc2455acee
 size 1944201353

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06588fe97a646cc99cbc99bc6fc879fa8b718ed50182bb18f2b5f6cf1e106f74
-size 14511
+oid sha256:ce33c87ee60e5c5f09d3f93624e4aea152d072fa3e8cb2a51f34ae26cdbcf071
+size 14575

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b160f59d9a4d5ff1cbcc84dfea859f763b0557d32b23555427ac2d77baf72620
+oid sha256:aef3ed6db2003a0d35336f0e4da89c5bcb53719a88d56afdb76ca509399bfcd3
 size 557

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:596f120f60b2fe3394bea0a08b1f95c97fa26c6f8681ab0671cc1a73b408d7d9
+oid sha256:4d821665fd46cc125e074beaa5297a592c3b1a69d3f8eda9777d00bef746240d
 size 627

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 16.200050329764814,
-  "global_step": 618000,
+  "epoch": 16.278690587285443,
+  "global_step": 621000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -7422,11 +7422,47 @@
       "learning_rate": 4.3366854581669033e-07,
       "loss": 1.0156,
       "step": 618000
+    },
+    {
+      "epoch": 16.21,
+      "learning_rate": 4.307757117746536e-07,
+      "loss": 1.0203,
+      "step": 618500
+    },
+    {
+      "epoch": 16.23,
+      "learning_rate": 4.278974079867265e-07,
+      "loss": 1.0212,
+      "step": 619000
+    },
+    {
+      "epoch": 16.24,
+      "learning_rate": 4.2502211036962613e-07,
+      "loss": 1.0281,
+      "step": 619500
+    },
+    {
+      "epoch": 16.25,
+      "learning_rate": 4.2215560802978895e-07,
+      "loss": 1.0204,
+      "step": 620000
+    },
+    {
+      "epoch": 16.27,
+      "learning_rate": 4.1929791311755256e-07,
+      "loss": 1.0117,
+      "step": 620500
+    },
+    {
+      "epoch": 16.28,
+      "learning_rate": 4.1644903774592405e-07,
+      "loss": 1.024,
+      "step": 621000
     }
   ],
   "max_steps": 762960,
   "num_train_epochs": 20,
-  "total_flos": 7.367688153619661e+17,
+  "total_flos": 7.400442013835674e+17,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0463186043fb0e3ac3533b11e5b51a4e826f1414cbaa678780d638011c23f2f0
+oid sha256:4467c2e695dbb515cc354d8e7385cc956efa20f7924c326db2a4ecdc2455acee
 size 1944201353

runs/Jun02_06-43-44_462ae3634d0f/events.out.tfevents.1685689892.462ae3634d0f.537.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce136f2bc91e1f810b4a2b92cefb11196f462f2f1371d8da3b4558eb21ed800c
-size 9261
+oid sha256:6bf0201424bc705d483ce8d79fd3c5ea059fa9c2831940cf15877da9e6a36860
+size 10221