Training in progress, step 56000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d732736de6501f4899754db0c10e4570a7fe2fa3ac8b9511bcea1224fb0cd3f5
+oid sha256:f60349f7766510102278629c2843f7b172c8d269ab71299853bf7d28b34c7f3c
 size 3871543575

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a305ef9c307c5169cce5f064424696b26f73c6db38d14bf539dd6e0d005ea169
+oid sha256:ed8496b300c153eda223d64ce6ae8d9b85a0b85fbf04784c5f7f9870564dd2d0
 size 1944201353

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e66928c63fad4b4599d1ab60d609e927e7ea8e3552c715ad8baff6ed9f3f4bbb
-size 14639
+oid sha256:9f322551d5dbc26a22a31f8ddc9da458bedc2e38dc7d116217d0c411ed1e9ed7
+size 14511

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:042c44b032d6bdd4466f03a28e4b55638760717a01ada6222dbb596f3a3bfc8d
+oid sha256:4b5ecbe8e8e0cd94fc7935cc448aa50e35fab0ed1e11419e7e3c7f29c567044d
 size 557

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f383fd584c5ee76e07a987b34c6a36868eb4f11d22aa3c2299d21c5081aef278
+oid sha256:e7a050ce0f4a32bb580c5f82cff9cdb29e8cb3d0f09c683f3a23deca0c0b8df1
 size 627

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5511919525974921,
-  "global_step": 52000,
+  "epoch": 0.5935913335665299,
+  "global_step": 56000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -630,11 +630,59 @@
       "learning_rate": 4.962640872518639e-06,
       "loss": 1.7226,
       "step": 52000
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 4.961920533507775e-06,
+      "loss": 1.7142,
+      "step": 52500
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 4.961193369338535e-06,
+      "loss": 1.7193,
+      "step": 53000
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 4.960460856809599e-06,
+      "loss": 1.7472,
+      "step": 53500
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 4.9597200620304265e-06,
+      "loss": 1.7407,
+      "step": 54000
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 4.958972448193223e-06,
+      "loss": 1.741,
+      "step": 54500
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 4.958218017370592e-06,
+      "loss": 1.7572,
+      "step": 55000
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 4.957458300945332e-06,
+      "loss": 1.7177,
+      "step": 55500
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 4.9566902560686915e-06,
+      "loss": 1.7255,
+      "step": 56000
     }
   ],
   "max_steps": 943410,
   "num_train_epochs": 10,
-  "total_flos": 2.9278349279870976e+16,
+  "total_flos": 3.15281974910976e+16,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a305ef9c307c5169cce5f064424696b26f73c6db38d14bf539dd6e0d005ea169
+oid sha256:ed8496b300c153eda223d64ce6ae8d9b85a0b85fbf04784c5f7f9870564dd2d0
 size 1944201353

runs/May14_15-54-58_fce7ca761ee9/events.out.tfevents.1684081292.fce7ca761ee9.347.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6022b19808a5b1c1becd15f0e3a653d2b7f29f01c522b6e28688114bff28c7f1
-size 9583
+oid sha256:f6da5c4ee3bf608db87622a1727ed032f59decd9ff80a8d0ed29d509a99c4a91
+size 10863