Training in progress, step 136000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f8aa69fa081bb9b7470ad363847ef75f3a283f3463ddba236aafae461a2fd3b9
+oid sha256:c2f48d508ece7df760eb555c017887dbe66d0cba6c7cfec5e6d05c94a3f8988e
 size 3871544599

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ec088332debea15871857309043358ce7a97e1e0ca384609c2a131a5b45b6ec
+oid sha256:e2a9024dd8a689e9ae503a3b92563cbd3856dd8ddb0b64a278d1035564872316
 size 1944201353

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1efb79d23eba5169f878156012a33e95ccf5864793451e2ed51a78eaf9b34135
+oid sha256:586b3dca1089776e32d357296b4040f36f7c66e484c78b70291b9bf859f0da7d
 size 14575

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ab7e6a0965f9191616cbd8a7051ebb5ae9b3ed2cba001391ed6b68095ae5e49
+oid sha256:9be7d27f5adca25da92af93035570ac65d76bd8fd5301a951f17e1a456e8d376
 size 557

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a77689f98dc0a26b40937e0eae71a1cc87cd7724106c708110a77e3cf0feee9a
+oid sha256:19bd67e3926298d10573f580a7616d969cad0d6d8378e7cf425b0e24b2dc768a
 size 627

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.9327830855333823,
-  "global_step": 132000,
+  "epoch": 0.9610492396404545,
+  "global_step": 136000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1590,11 +1590,59 @@
       "learning_rate": 4.893511776430863e-06,
       "loss": 1.6672,
       "step": 132000
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 4.892709015746761e-06,
+      "loss": 1.6937,
+      "step": 132500
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 4.89190492131604e-06,
+      "loss": 1.676,
+      "step": 133000
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 4.891096271306403e-06,
+      "loss": 1.6808,
+      "step": 133500
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 4.890284675178114e-06,
+      "loss": 1.6601,
+      "step": 134000
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 4.8894701339311555e-06,
+      "loss": 1.6762,
+      "step": 134500
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 4.888654286477422e-06,
+      "loss": 1.6826,
+      "step": 135000
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 4.8878338638927996e-06,
+      "loss": 1.649,
+      "step": 135500
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 4.887010499209203e-06,
+      "loss": 1.677,
+      "step": 136000
     }
   ],
   "max_steps": 1415120,
   "num_train_epochs": 10,
-  "total_flos": 5.87863269950423e+16,
+  "total_flos": 6.00884944380887e+16,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ec088332debea15871857309043358ce7a97e1e0ca384609c2a131a5b45b6ec
+oid sha256:e2a9024dd8a689e9ae503a3b92563cbd3856dd8ddb0b64a278d1035564872316
 size 1944201353

runs/May16_05-26-38_740b6dbf3e56/events.out.tfevents.1684216250.740b6dbf3e56.4449.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60445f76728e4248bb41052178874475009af41b1d2b315a5a381d9378d96232
-size 13423
+oid sha256:53a86a89599e9513699a13d646354a3c7e3196e861192b3d15d0bfb827290eb6
+size 14703