Training in progress, step 651000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e5bea9d12c75a0b740c6d8b4981219431448ed3eb923f814d21069105e05d49
+oid sha256:49722fb4525cdfb5db10b91cc9964d6d93d53a3f624d39e81da612430ad473a1
 size 3871544599

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6cb7b8cc7b5b8722aa68b4b7cf587f4547a045eca51ff1e2e5ae8bc0ba0bea7
+oid sha256:ca9a9edb197fdbdf00385a4c3210b7e932baf72faf125a9727ef9e5c30f08804
 size 1944201353

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49a1f303969f3b335e0a213dce28b4e82a49515af15f73aa829adea5984a539d
+oid sha256:c0e68f9154824758e939f3f203bd07329f72d1b44231a034da24c8f1b729ad93
 size 14575

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd4e31f2b5a2b50d87a2c036b30a0f484ab180c55282c2662507270edacf55e6
+oid sha256:f803e795f13c2c61f76367562826b3d0d4c17b6383f5b4bcdb43021fd0dba972
 size 557

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a404533909d18775309ba447db15bad866db16477eb7c0fea9085dcbc40d504
+oid sha256:2f3d07c5e6735b6a42b3fb3c809508eeb0916a9cf2438aa81c83c4bba3bf70b8
 size 627

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 16.986463390338784,
-  "global_step": 648000,
+  "epoch": 17.065103647859413,
+  "global_step": 651000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -7782,11 +7782,47 @@
       "learning_rate": 2.7607930630074693e-07,
       "loss": 1.0151,
       "step": 648000
+    },
+    {
+      "epoch": 17.0,
+      "learning_rate": 2.7373283880098636e-07,
+      "loss": 1.0206,
+      "step": 648500
+    },
+    {
+      "epoch": 17.01,
+      "learning_rate": 2.7139580785331824e-07,
+      "loss": 0.9983,
+      "step": 649000
+    },
+    {
+      "epoch": 17.03,
+      "learning_rate": 2.690682233637923e-07,
+      "loss": 0.9983,
+      "step": 649500
+    },
+    {
+      "epoch": 17.04,
+      "learning_rate": 2.6675009519841726e-07,
+      "loss": 1.023,
+      "step": 650000
+    },
+    {
+      "epoch": 17.05,
+      "learning_rate": 2.6444143318311964e-07,
+      "loss": 1.0061,
+      "step": 650500
+    },
+    {
+      "epoch": 17.07,
+      "learning_rate": 2.621422471037019e-07,
+      "loss": 1.0198,
+      "step": 651000
     }
   ],
   "max_steps": 762960,
   "num_train_epochs": 20,
-  "total_flos": 7.69810904722686e+17,
+  "total_flos": 7.731104357603082e+17,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6cb7b8cc7b5b8722aa68b4b7cf587f4547a045eca51ff1e2e5ae8bc0ba0bea7
+oid sha256:ca9a9edb197fdbdf00385a4c3210b7e932baf72faf125a9727ef9e5c30f08804
 size 1944201353

runs/Jun03_20-07-36_5814eb69ea9a/events.out.tfevents.1685824428.5814eb69ea9a.704.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20bd31051705cb5f3c2eeb46f9ad32dc0958974622b8cf5b78877d1c92ca5984
-size 11181
+oid sha256:dacfe16a4c0981146c418235b9967b5b1712f3ffaff1b3360c7304894f973112
+size 12141